Method and system for controlling downstream production process for chemical product and relevant computer program or non-transitory computer readable medium

Abstract

This invention relates to a method for controlling a downstream production process that uses at least one precursor material to manufacture a chemical product. The method includes: providing a set of downstream control setpoints for controlling the production of the chemical product, wherein the downstream control setpoints are determined based on: a downstream object identifier; the downstream object identifier including precursor information; at least one desired downstream performance parameter related to the chemical product; downstream historical data; and wherein the set of downstream control setpoints can be used to manufacture the chemical product at a downstream industrial plant. This invention also relates to a system, an application, and a software product.

Description

Technical Field

[0001] This instruction is primarily about computer-aided chemical production. Prior Technology

[0002] In industrial plants, input materials are processed to manufacture one or more products. Therefore, the properties of the manufactured products are dependent on manufacturing parameters. Typically, it is necessary to correlate manufacturing parameters with at least some properties of the product to ensure product quality or production stability.

[0003] In process industries or industrial plants (such as chemical or biological production plants), production processes are used to process one or more input materials to produce one or more chemical or biological products. The production environment in process industries can be complex, and therefore, the properties of the product can vary depending on the production parameters affecting those properties. Typically, the dependence of properties on production parameters can be complex and entangled with additional dependencies on one or more combinations of specific parameters. In some cases, the production process can be divided into multiple stages, which can further exacerbate the problem. Therefore, producing chemical or biological products with consistent and / or predictable quality can be challenging.

[0004] In some cases, downstream industrial plants may receive precursor materials from upstream plants used to produce chemical products at the downstream plant. Precursor materials may have a range of properties, including one or more of those inherent to precursor materials. These properties can vary due to variations in the production of precursor materials at the upstream plant. Furthermore, variations can also occur at the downstream plant. Therefore, the chemical products produced at the downstream plant may also have a range of properties inherent to chemical products. Depending on the various variations and their combinations, certain portions of the chemical product may become unacceptable or unusable due to poor quality or performance. This leads to waste and increased production costs.

[0005] Furthermore, compared to discrete processing, chemical or biological processes such as continuous, motion, or batch processes can provide a wealth of time-series data. However, machine learning via traditional time-series methods has proven less practical, as it may be difficult to integrate data according to the needs of horizontal integration across the value chain. Specifically, simple and meaningful data exchange or standardization poses a major problem.

[0006] Therefore, there is a need for methods that can improve control and production stability across the entire supply chain, from the material container to the final product. Summary of the Invention

[0007] At least some of the problems inherent in the prior art will be demonstrated to be solved by the subject matter of the accompanying independent item. At least some of the other advantageous alternatives will be summarized in the appendix.

[0008] For low-level computer-aided chemical production, input materials processed by the equipment in the low-level chemical production environment are categorized into physical packages or real-world packages (or respectively, "physical packages" or "product packages") within the term "packaged objects." The package size of such objects can be fixed, for example, by material weight or quantity, or determined based on weight or quantity, for which the processing equipment can provide significantly constant process parameters or equipment operating parameters. Such packaged objects can be generated from input liquid and / or solid raw materials using a dispensing unit.

[0009] Subsequent processing of such packaged objects is managed using corresponding data objects, including so-called "object identifiers," such as those described below as "downstream object identifiers." These object identifiers are assigned to each packaged object via a computing unit coupled to or even part of the device in question. Data objects, including the corresponding "downstream object identifiers" for the underlying packaged objects, are stored in the memory storage elements of the computing unit.

[0010] It can generate data objects in response to a trigger signal provided by the device, preferably in response to configuring the output of the corresponding sensor at each of the device units. The underlying industrial plant may include different types of sensors, such as sensors for measuring one or more process parameters and / or sensors for measuring equipment operating conditions or parameters related to the equipment or process unit.

[0011] From a first perspective, a method for controlling a downstream production process for manufacturing a chemical product at a downstream industrial plant, the downstream industrial plant including at least one downstream device, and the product being manufactured by processing at least one precursor material via the downstream device using the downstream production process, the method being performed at least in part via a downstream computing unit, and the method comprising: - A set of downstream control setpoints for controlling the production of the chemical product is provided at the downstream computing unit, wherein these downstream control setpoints are determined based on the following: - The downstream object identifier mentioned; the downstream object identifier contains precursor information indicating one or more properties of the precursor material, - At least one desired downstream performance parameter that is related to the chemical product; - Downstream historical data; wherein this downstream historical data includes downstream process parameters and / or operating settings used to manufacture one or more chemical products in the past; and wherein - This set of downstream control settings can be used to manufacture the chemical product at the downstream industrial plant.

[0012] The applicant has recognized that, thereby, at least one desired downstream performance parameter related to the desired quality of a chemical product can be used to control the manner in which that particular precursor material, having associated properties with a particular precursor material, is processed at a downstream facility. In some cases, the downstream industrial plant may comprise multiple facility zones, such that downstream control setpoints can be zone-specific.

[0013] Therefore, chemical products can be produced considering not only downstream variations but also precursor material variations, based on desired properties or performance parameters. Precursor data encapsulated in downstream object identifiers can be used to find downstream control settings aimed at achieving at least one desired downstream performance parameter. Thus, for example, by considering not only the random variations in precursor material properties but also by selecting control settings to apply downstream historical data for the same purpose (i.e., to achieve at least one desired downstream performance), the quality of chemical products can be improved and / or made more consistent. Downstream historical data can come from equipment producing one or more chemical products, such as downstream equipment, but it can even come at least partially from another piece of equipment.

[0014] According to one example, downstream historical data includes information from one or more historical downstream object identifiers related to, for example, previously processed precursor materials in the downstream equipment area.

[0015] According to one example, at least one of the historical downstream object identifiers has been attached with at least a portion of downstream process data, which indicates the downstream process parameters and / or equipment operating conditions under which the previously processed precursor material was processed, for example, in a downstream equipment area.

[0016] Such historical downstream object identifiers encapsulate the corresponding portions of their downstream process data, under which individual previously input materials were processed to produce or process individual chemical products in the past. As disclosed herein, the downstream historical data is therefore a highly relevant yet concise set of data that can be used to determine control settings for downstream equipment. In cases where downstream equipment is configured to include multiple downstream equipment areas for manufacturing one or more chemical products, downstream control settings can then be provided for each of these downstream equipment areas as a target for achieving the desired performance of the chemical product, as specified by at least one desired performance parameter.

[0017] According to one approach, each or some of the historical downstream object identifiers includes at least one downstream performance parameter related to one or more properties of an associated chemical product, for example, produced in a downstream industrial plant in the past. Therefore, each or some of the historical downstream object identifiers has been appended with its corresponding at least one downstream performance parameter.

[0018] In this way, historical downstream data can be further targeted by associating it with each portion of the downstream process data (each with at least one downstream performance parameter) within any downstream object identifier. Thus, based on potentially extensive process data, a concise yet effective snapshot of process parameters and / or operating settings is digitally coupled to the specific chemistry produced along with its performance. The determination of control settings can therefore be synergistically improved. This can be achieved by attaching at least one downstream performance parameter to the downstream object identifier, the details of which will be discussed in this disclosure. Therefore, when a downstream object identifier is used as a historical object identifier for future downstream production, the associated data within the identifier can be better utilized to improve future production.

[0019] It should be understood that the object identifiers proposed in the context of this teaching can not only improve the downstream and upstream traceability of chemical products through the supply chain, but also be used to ensure that the production process is controlled in a way that results in more consistent quality of chemical products. At least a portion of the production chain (e.g., downstream equipment or equipment areas) can be controlled in a more adjustable manner to achieve the desired performance of the chemical products, rather than relying on general control settings that can produce a wide range of chemical products manufactured at different times. Therefore, any variability in precursor materials and / or process parameters and / or equipment operating conditions can be taken into account at least in part, while providing downstream control settings or downstream-area-specific control settings for the production of chemical products.

[0020] Therefore, this method also includes: - Use downstream control setpoints to execute downstream production processes.

[0021] Downstream production processes can be executed by at least some of the downstream control settings provided to or entered into a downstream factory control system, which is operatively coupled to downstream equipment or a downstream equipment area. Alternatively, downstream production processes can be executed by automatically providing at least some of the downstream control settings to the downstream factory control system. The downstream control settings can be directly transmitted to the downstream factory control system from a downstream computing unit, or they can be provided at a downstream memory location operatively coupled to the downstream computing unit, from which the downstream factory control system can read or retrieve the downstream control settings.

[0022] In some cases, the downstream computing unit can be at least partially part of the downstream plant control system, allowing it to directly use downstream control setpoints to at least partially control the downstream production process. As discussed, the downstream control setpoints can allow control of the downstream production process at each of the downstream equipment areas. Therefore, finer granularity and flexibility of control can be achieved based on at least one desired downstream performance parameter to ensure the performance of the chemical product.

[0023] Based on a single-state sample, the method further includes: - Receive downstream real-time process data from one or more downstream devices or device areas at the downstream computing unit; wherein the downstream real-time process data includes downstream real-time process parameters and / or device operating conditions.

[0024] Downstream computing units can therefore be coupled to downstream devices or device areas via communication and / or operation.

[0025] According to another state, the method includes: - A subset of downstream real-time process data is determined by the downstream computing unit based on the downstream object identifier and the downstream area presence signal; wherein the downstream area presence signal indicates the presence of precursor material in a specific equipment area during the downstream production process.

[0026] Downstream computing units can therefore select downstream process data associated with downstream object identifiers. This associated data, or a subset of downstream real-time process data, can be selected based on where the material is located within the production chain or by means of a usage area presence signal.

[0027] According to another sample, the method includes: - Calculate at least one downstream performance parameter of a chemical product associated with a downstream object identifier using a subset of downstream real-time process data and downstream historical data via a computing unit.

[0028] As should be understood, downstream process data may have variability associated with one or more of the components of the data. For example, two different batches of precursor materials mixed at different times in the same mixer may have been mixed in different ways. Similar variability may also exist with other parameters and / or operating conditions. The variability between individual components may be random and independent of or partially independent of the variability of other components. Furthermore, combinations of such variability can cause variability in the performance or quality of the chemical product. Therefore, as specified above, depending on a subset of the downstream real-time process data, the downstream computing unit may be configured to calculate at least one downstream performance parameter. Thus, at least one downstream performance parameter indicating the quality of the chemical product can be determined substantially as the precursor material is processed in the downstream equipment area. At least one downstream performance parameter may be displayed to the operator, for example, via a human-machine interface ("HMI"). The operator can then adjust the downstream production process such that each or some of the at least one downstream performance parameter may be the same as, or become closer to, its associated value.

[0029] Alternatively or additionally, the method includes: - Attach at least one downstream performance parameter to the downstream object identifier.

[0030] Downstream performance parameters can be appended as meta-data to downstream object identifiers, for example. Therefore, the downstream object identifier also encompasses at least one downstream performance parameter calculated during the downstream production process. This not only improves the traceability of chemical products but also simplifies quality control.

[0031] Alternatively or additionally, the method includes: - The downstream production process is controlled by the downstream computing unit to minimize the difference between at least one of the downstream performance parameters and their respective associated values ​​of the desired downstream performance parameter.

[0032] The calculated performance values ​​can thus be tracked for desired performance parameter values. Therefore, the granularity of process control can be further improved at a finer scale. This control allows for at least partial consideration of the variability of various process parameters and / or operating conditions. Potentially, each of the downstream equipment areas can be automated, resulting in more consistent performance or quality of the final chemical product.

[0033] Alternatively or additionally, the method includes: - Attach a subset of downstream real-time process data to the downstream object identifier.

[0034] Therefore, relevant downstream process data can also be captured and encapsulated or packaged together with precursor data or precursor material data within the downstream object identifier, thereby capturing any relationships between chemical products possessing the properties of precursor materials. This provides a more complete understanding of the relationships between various dependencies that can affect one or more properties or performance of the chemical product. Another advantage is that combinations of various interdependencies that may exist between precursor material properties and / or downstream process parameters are also captured within the downstream object identifier. The downstream object identifier is thus enriched with information that can be used not only to track chemical products and / or their specific components, such as precursor materials, but also to access real-time data from the specific downstream processes responsible for producing the chemical product. Therefore, object identifiers such as each of historical downstream object identifiers can be more easily integrated for any machine learning (ML) and such purposes. Consequently, downstream object identifiers can also be used as historical object identifiers for future downstream production.

[0035] It should be understood that desired downstream performance parameters may be directly related to one or more properties of the chemical product, and / or may be related to one or more properties of the downstream derivative materials produced during the downstream manufacturing process. For example, in cases where precursor materials are converted into downstream derivative materials during the downstream manufacturing process, it may sometimes be necessary to track and / or control the quality or performance of such derivative materials. It should be understood that in such cases, the downstream derivative material is an intermediate material produced from the precursor material, which is then used to produce the chemical product. Since the chemical product also depends on the downstream derivative material, it may sometimes be necessary to track and control the downstream derivative material as well.

[0036] Therefore, according to a given state, at least one of the desired downstream performance parameters is related to one or more properties of the downstream derivative material.

[0037] According to one embodiment, a downstream region presence signal can be generated by a downstream computing unit through a region-time conversion, which maps at least one property associated with the precursor material to a specific equipment region. For example, the property associated with the precursor material could be the weight of the precursor material, allowing the determination of the presence of the precursor material or its derivative material during the downstream production process using, for example, knowledge of the production process via downstream real-time process data. As one embodiment, if a precursor material with a specific weight in a first downstream equipment region traverses to a second downstream equipment region during the downstream production process, then a weight measurement at the second downstream region, for example, at a predetermined time or within a predetermined time period, can be used to generate a region presence signal for the second downstream region. Similarly, the flow rate value (e.g., mass flow rate or volumetric flow rate) of the precursor material or its derivative material traversing the production process can be a property used to generate a downstream region presence signal. As another embodiment, the speed or rate at which the precursor material traverses the equipment region can be used to determine the spatial or positional location of the input material or its corresponding derivative material at a given time. Alternatively or additionally, other non-limiting embodiments of properties related to the input material include volume, filler value, content, color, etc.

[0038] The applicant has found it advantageous to generate presence signals by mapping downstream real-time process data to spatial data, thereby mapping the actual production process using digital process elements representing precursor materials. This downstream real-time process data is time-dependent data, such as time-series data, within the production environment. For example, the digital flow of precursor materials can be tracked via downstream object identifiers, and the availability of time-dependent downstream real-time process data can be used to locate materials along the downstream production process. Materials are thus tracked or located via measured time and downstream real-time process data (i.e., by using the time dimension of the downstream process data), which is related to the time dimension of the precursor material's flow along the downstream production chain.

[0039] The presence signal can be intermittent, for example, generated by regular or irregular time intervals, or it can be generated continuously. This can have the advantage that materials associated with individual object identifiers can be continuously or substantially continuously located within the production chain, thus enabling the addition of data highly relevant to the materials and their transformation to the chemical products. Regular or irregular time intervals can be used, for example, to check the presence of materials at certain checkpoints within the production chain. This can be supplemented by the presence of one or more sensors in downstream real-time process data, for example, as outlined below.

[0040] In chemical production, since time-dependent operating parameters such as residence time and flow rate are known, zone-time conversion can be a simple mapping of the time scale. Alternatively, more complex models based on process simulation can be used to match the time scale of the material flow with real-time process data. In any case, the time scale of the process data can be finer than that of the material flow to more precisely attribute process data parameters to the material flow.

[0041] Therefore, a subset of downstream real-time process data, or even its components (such as each or some of the downstream process parameters and / or equipment operating conditions), can be further optimized or simplified based on the time the material spends in a specific sub-section or area of ​​the equipment. For example, if an equipment area, such as a first downstream equipment area, includes a mixer followed by a heater, then a subset of the downstream real-time data could include downstream process parameters and / or equipment operating conditions associated with the mixer only while the precursor material is in the mixer. Similarly, downstream process parameters and / or equipment operating conditions associated with the heater could be included only from the time the material is exposed to the heater (e.g., upon leaving the mixer). In this way, the relevance of the dataset can be further finely managed and optimized based on the relevance of specific materials. As will be understood, an alternative could be: a subset of downstream process data includes all downstream process parameters and / or equipment operating conditions related to the downstream equipment area from the time the precursor material enters the downstream equipment area until the time the precursor leaves the downstream equipment area. This alternative already has the advantage of providing data that is highly correlated with the downstream object identifier. However, by further specifying individual components of the downstream process data as explained, within the area itself, the subset of downstream real-time process data can be further optimized and the correlation of the data encapsulated within each individual downstream object identifier can be further improved.

[0042] Alternatively, the presence signal in the downstream region may be provided at least in part via a sensor associated with the specific region. For example, a weight sensor and / or an image sensor may be used to detect the presence of precursor or derivative materials in space or in a specific device area.

[0043] "Equipment" can refer to any one or more assets within a particular industrial plant (such as a downstream industrial plant). As a non-limiting embodiment, equipment can refer to any one or more of the following, or any combination thereof: computing units or controllers such as programmable logic controllers (PLCs) or distributed control systems (DCS); sensors; actuators; terminal effector units; conveying elements such as conveyor systems; heat exchangers such as heaters; boilers; cooling units; distillation units; extractors; reactors; mixers; mills; shredders; compressors; slicers; extruders; dryers; sprayers; pressure or vacuum chambers; pipes; bins; silos; and any other type of equipment directly or indirectly used in or during production in an industrial plant. Preferably, equipment systematically refers to assets, equipment, or components directly or indirectly involved in the production process. More preferably, it refers to assets, equipment, or components that can affect the performance of chemical products. The equipment may be buffered, or it may be unbuffered. Furthermore, the equipment may involve mixing or not mixing, separation or not separation. Some non-limiting embodiments of unbuffered equipment without mixing include conveyor systems or belts, extruders, granulators, and heat exchangers. Some non-limiting embodiments of buffered equipment without mixing include buffer silos, bins, etc. Some non-limiting embodiments of buffered equipment with mixing include silos with mixers, mixing containers, shear mills, double-cone mixers, solidification tubes, etc. Some non-limiting embodiments of unbuffered equipment with mixing include static or dynamic mixers, etc. Some non-limiting embodiments of buffered equipment with separation include towers, separators, extractors, thin-film vaporizers, filters, sieves, etc. The equipment may even be, or may include, storage or encapsulation elements, such as octabin filling, rollers, bags, tank trucks. Sometimes, a combination of two or more components of the equipment can also be considered as equipment.

[0044] In the context of downstream industrial plants, "equipment zones" refer to physically separate areas that are part of the same component of equipment, or that may be different components of equipment used to manufacture chemical products. These zones are therefore physically located in different places. The locations can be different geographically, both laterally and / or vertically. Input materials therefore begin in the upstream equipment zone and traverse downstream towards one or more downstream equipment zones. The various steps of the downstream production process can therefore be distributed among these zones.

[0045] In this disclosure, the terms "equipment" and "equipment area" are used interchangeably.

[0046] "Equipment operating conditions" refers to any characteristic or value that indicates the status of equipment in a particular area, such as set point, controller output, production sequence, calibration status, any equipment-related warnings, vibration measurements, speed, temperature, and fouling values ​​(such as filter differential pressure, maintenance date, etc.).

[0047] The term "downstream" should be understood as referring to the direction of the production process. For example, the final equipment area where the production process ends is the downstream equipment area. However, the term is used in a relative sense within the meaning of this disclosure. For example, the intermediate equipment area located between the first equipment area and the final equipment area can also be referred to as the downstream area of ​​the first equipment area and the "upstream" equipment area of ​​the final equipment area. The final equipment area is therefore the downstream area of ​​the first equipment area and the intermediate equipment area. Similarly, both the first equipment area and the intermediate equipment area are upstream of the final equipment area.

[0048] "Industrial plant" or "plant" can mean, but is not limited to, any technological infrastructure used for industrial purposes of manufacturing, producing, or processing one or more industrial products (i.e., manufacturing or production processes or processing carried out by an industrial plant). Industrial products can be, for example, any physical product, such as chemicals, biological products, pharmaceuticals, food, beverages, textiles, metals, plastics, semiconductors. Alternatively or additionally, industrial products can even be service products, such as recycling or waste treatment, such as chemical processing, such as decomposition or dissolution into one or more chemical products. Thus, an industrial plant can be one or more of a chemical plant, a process plant, a pharmaceutical plant, a fossil fuel processing facility (such as oil and / or natural gas wells), a refinery, a petrochemical plant, a cracking plant, and the like. An industrial plant can even be any of a distillery, a processing plant, or a recycling plant. An industrial plant can even be any combination of any of the embodiments given above or the like.

[0049] The basic structure may include equipment or process units such as any one or more of the following: heat exchangers, towers such as fractionation towers, boilers, reaction chambers, cracking units, storage tanks, extruders, granulators, settlers, blenders, mixers, cutters, curing tubes, vaporizers, filters, screens, wires, chimneys, valves, actuators, grinders, transformers, transmission systems, circuit breakers, machinery such as heavy rotating equipment, such as turbines, generators, grinders, compressors, industrial fans, pumps, conveying elements such as conveyor systems, electric motors, etc. Sometimes a combination of two or more of the above elements may also be considered equipment.

[0050] Furthermore, industrial plants typically include multiple sensors and at least one control system for controlling at least one parameter related to processes or process parameters within the plant. Such control functions are typically performed by the control system or controller in response to at least one measurement signal from at least one of the sensors. The plant's controller or control system may be implemented as a distributed control system (DCS) and / or a programmable logic controller (PLC).

[0051] Therefore, at least some of the equipment or process units in an industrial plant (i.e., an upstream or downstream industrial plant) can be monitored and / or controlled for the production of one or more industrial products. Monitoring and / or control can even be performed to optimize the production of one or more products. The equipment or process units can be monitored and / or controlled via controllers such as a DCS in response to one or more signals from one or more sensors. Additionally, the plant may even include at least one programmable logic controller (“PLC”) for controlling some of the processes. An industrial plant may typically include a plurality of sensors distributed throughout the plant for monitoring and / or control purposes. Such sensors can generate large amounts of data. Sensors may or may not be considered part of the equipment. Therefore, production, such as chemical and / or service production, can be a data-heavy environment. Consequently, each industrial plant can generate a large amount of process-related data.

[0052] Those skilled in the art will understand that industrial plants typically include instruments that may include various types of sensors. Sensors can be used to measure one or more process parameters and / or to measure equipment operating conditions or parameters related to equipment or process units. For example, sensors can be used to measure process parameters such as flow rate within a line, water level inside a tank, boiler temperature, and the chemical composition of gases, and some sensors can be used to measure the vibration of a grinder, fan speed, valve opening, line corrosion, and voltage across a transformer. The differences between these sensors are not only based on the parameters they sense, but also on the sensing principles used by each sensor. Some embodiments of sensors based on their sensed parameters may include: temperature sensors, pressure sensors, radiation sensors such as light sensors, flow sensors, vibration sensors, displacement sensors, and chemical sensors, such as sensors for detecting specific substances such as gases. Examples of sensors that employ different sensing principles include, for example, piezoelectric sensors, piezoresistive sensors, thermocouples, impedance sensors such as capacitive and resistive sensors, etc.

[0053] An industrial plant can even be part of a plurality of industrial plants. As used herein, the term "plural industrial plant" is a broad term and is given its common and conventional meaning to those skilled in the art, without limitation any specific or customary meaning. Specifically, the term can refer to, but is not limited to, a combination of at least two industrial plants having at least one common industrial purpose. Specifically, a plurality of industrial plants can comprise at least two, at least five, at least ten, or even more industrial plants that are physically and / or chemically coupled. A plurality of industrial plants can be coupled such that the industrial plants forming the plurality of industrial plants can share one or more of their supply chains, precipitates, and / or products. A plurality of industrial plants can also be referred to as a complex, a complex site, a verbund, or a verbund site. Furthermore, the supply chain production of a plurality of industrial plants from various intermediate products to final products can be dispersed in various locations (such as in various industrial plants) or integrated into a verbund site or chemical park. Such integrated sites or chemical parks may be or may contain one or more industrial plants, wherein products manufactured in at least one industrial plant may serve as raw materials for another industrial plant.

[0054] Downstream manufacturing processes for producing chemical products can involve multiple steps, which may further involve various process parameters and / or operating conditions that need to be strictly controlled to obtain chemical products with the desired properties.

[0055] This instruction not only allows the establishment of relationships between at least some of the relevant data that can reflect such interdependencies, but also allows for the monitoring and / or adjustable control of at least downstream production processes aimed at achieving consistent quality of chemical products.

[0056] The downstream control setpoint may be determined at least in part by the upstream computing unit. Alternatively, the downstream control setpoint may be determined at least in part by the downstream computing unit. The upstream computing unit may be part of an upstream industrial plant or facility, wherein the precursor material is produced from or supplied to the downstream industrial plant.

[0057] It should be understood that a downstream industrial plant is one that receives input materials or precursor materials from an upstream industrial plant. The downstream industrial plant can therefore be located far from the upstream industrial plant. Precursor materials can be supplied at the downstream industrial plant via suitable transport media, such as by truck, rail, ship, or even a combination thereof, for example, transport by truck followed by ship. The transport media can even be a closed medium such as a line or the like. In some cases, the precursor materials may be packaged in fixed quantities in packages during production at the upstream plant and / or prior to shipment, for example, packages containing 10 kg of each of the precursor materials. Alternatively or concurrently, the precursor materials may be supplied in any other suitable one or more containing units (such as octagonal bins, cylinders, or boxes).

[0058] Precursor materials may be stored and / or produced at upstream industrial plants and then transported or shipped to downstream industrial plants for use in the manufacture of chemical products. The transport or shipment may be carried out in response to the sequence of the precursor materials, which is initiated via the downstream plant that receives the precursor materials. The precursor materials received at the downstream plant can thus be used in the manufacture of downstream chemical products.

[0059] In some cases, downstream control setpoints determined by the upstream computing unit can be provided at the downstream memory location via the upstream computing unit. An advantage is that the control setpoints can be provided directly as a service by the upstream industrial plant producing the precursor materials. This potentially beneficial scenario is when the upstream plant already has the infrastructure and computing resources to predict and provide downstream control setpoints, allowing these setpoints to be determined based on the details of the precursor materials via their associated object identifiers. The setpoints can thus be provided to downstream plants that may be customers of the upstream plant, enabling creative (out-of-the-box) deployment of the setpoints without any additional computational work from the downstream plant. Therefore, the downstream plant can enjoy optimized production and improved quality of chemical products without modifying its production environment or requiring any additional computing resources.

[0060] In such cases, downstream object identifiers can be provided via upstream computing units. At least one desired downstream performance parameter can be provided to the upstream industrial plant or upstream computing unit, for example, as a quality grade required by the downstream plant for the chemical product. The downstream industrial plant can therefore provide downstream historical data, preferably including one or more downstream performance parameters, to the upstream industrial plant or upstream computing unit for determining downstream control settings. At least some of the data to be provided to the upstream computing unit may be sensitive data that the downstream plant wants to protect. This data may be provided, for example, at a shared memory location accessible to both the upstream and downstream plants. The shared memory location may be cloud storage accessible via plant-specific access policies. The access policies determine what type of access rights the plants (i.e., the upstream plant or upstream computing unit and the downstream plant or downstream computing unit) have. The access policies may also define authentication measures, such as encryption and / or multi-factor authentication.

[0061] Downstream memory locations may also be, for example, shared memory locations or registry entries that can be accessed by both upstream and downstream computing units.

[0062] By using a shared, isolated registry accessible to both plants, isolation and security can be maintained between them. For example, the downstream plant or computing unit can have read access, allowing it to read or retrieve settings without exposing the downstream control system or equipment to external access.

[0063] Similarly, when it is necessary to provide downstream historical data and / or desired performance parameters to the upstream computing unit, read access can be provided to the upstream computing unit. Therefore, neither the upstream nor the downstream computing unit needs to access the other factory, thus reducing security vulnerabilities in either factory.

[0064] In some cases, downstream control settings can be provided via tags associated with the transport of precursor materials to downstream plants. These tags may be transported to the downstream plant along with the precursor materials, or they may be provided separately. The tags may be hardware tags such as electronic chips and / or near-field communication (NFC) based tags, and / or digitally readable code that can be read at the downstream industrial plant to retrieve control settings suitable for producing chemical products using the supplied precursors (aiming to achieve at least one desired performance parameter). The tags may even be encrypted with restricted access provided to the downstream industrial plant.

[0065] In some cases, the downstream control settings determined by the downstream computing unit depend on the precursor data. The precursor data may also be available at a shared memory location as previously discussed.

[0066] According to one approach, an upstream object identifier is provided via an upstream industrial plant. For example, an upstream object identifier is provided in response to a sequence signal received at the upstream industrial plant for precursor materials to be supplied at a downstream industrial plant. The upstream object identifier may be provided automatically in response to the sequence signal, for example, via an upstream computing unit. The sequence signal may be received via the upstream industrial plant's enterprise resource planning (ERP) system in response to which upstream computing unit can provide the upstream object identifier. The upstream object identifier may be accompanied by input material information, indicating one or more properties of the input materials used in the production of the precursor materials, and the upstream object identifier is provided for the input materials at the upstream industrial plant. The upstream object identifier may also be accompanied by a subset of upstream process data from the upstream industrial plant, including upstream process parameters and / or equipment operating conditions under which the input materials are processed to produce the precursor materials.

[0067] The upstream object identifier may be provided via an upstream interface, preferably at an upstream memory storage unit operatively coupled to the upstream computing unit. Either or both of the upstream memory storage unit and the upstream computing unit may be at least partially part of a cloud platform or service. Similarly, either or both of the downstream memory storage unit and the downstream computing unit may be at least partially part of a cloud platform or service.

[0068] The advantage of providing upstream object identifiers is that relevant portions or subsets of upstream process data can be attached to specific input materials used to produce precursors. This means that not only the properties of the input material, but also the conditions under which a specific precursor is produced can be captured within the upstream object identifier, thus better defining one or more properties of the precursor material. The manner in which one or more upstream object identifiers are provided can be similar to the alternatives discussed for downstream object identifiers. Therefore, there is no need for repetitive patterns for both upstream and downstream identifiers. Thus, those skilled in the art will understand that a pattern from one can be applied to the other without being explicitly stated herein. For example, an upstream industrial plant may also include upstream equipment areas, and similarly to those discussed for downstream process data, upstream process data from individual areas can be captured in a similar manner and attached to one or more upstream object identifiers. The overall advantage is that substantially complete traceability and quality tracking and / or control can be achieved from the input material to the final product, i.e., the chemical product, via object identifiers. Furthermore, the state of the region can be used in upstream industrial plants or equipment to determine individual subsets of process data attached to individual object identifiers.

[0069] According to one approach, a downstream object identifier is attached with at least a portion of the data from an upstream object identifier. This downstream object identifier may be referred to as an additional downstream object identifier. Therefore, the additional downstream object identifier, or the downstream object identifier attached with at least a portion of the data from the upstream object identifier, can provide a more holistic picture of the production chain and can thus generate a more complete data set, at least encompassing object identifier references or encapsulations from input materials to precursors, which allows for better determination of downstream control setpoints. For example, a subset of upstream real-time process data attached to the upstream object identifier also references at least the downstream object identifier. Alternatively or concurrently, any one or more upstream performance parameters, determined by sampling and / or calculated by an upstream computing unit, can be provided to the downstream object identifier via the upstream object identifier.

[0070] In some cases, at least some of the downstream control setpoints are determined by the downstream computing unit. In such cases, a subset of upstream real-time process data provided via an upstream object identifier can be used by the downstream computing unit to determine the downstream control setpoints. For example, the upstream computing unit may provide the upstream object identifier in shared memory, similar to what has been discussed previously. It is also possible that the downstream object identifier is provided via the upstream computing unit in shared memory. The downstream computing unit can therefore use the downstream object identifier to determine the set of downstream control setpoints.

[0071] The advantage of this method is that upstream industrial plants do not need to have access to downstream historical data. However, information protection and security issues may arise because downstream plants can determine the local settings for control settings. Therefore, downstream plants can better protect information or data. It should be understood that the upstream computing unit provides upstream object identifiers rather than directly providing downstream object identifiers; these upstream object identifiers are then used by the downstream computing unit to generate downstream object identifiers. Those skilled in the art will recognize that this is equivalent to the upstream computing unit providing the downstream object identifier.

[0072] In some cases, the upstream computing unit can provide downstream object identifiers or upstream object identifiers that encapsulate predictive and / or control logic that can be used or applied to determine a set of downstream control setpoints based on historical downstream data. To mitigate any information protection issues at the downstream industrial plant, the predictive and / or control logic can be trained at the downstream industrial plant, for example, via the downstream computing unit.

[0073] Predictive and / or control logic may include a predictive model that, when trained using downstream historical data, produces a downstream data-driven model. A "data-driven model" refers to a model that is at least partially derived from data (in this case, from downstream historical data). Compared to rigorous models derived purely from physiological and chemical laws, data-driven models allow for the description of relationships that cannot be modeled using physiological and chemical laws. The use of data-driven models allows for the description of relationships without solving equations derived from, for example, physiological and chemical laws relevant to processes occurring within individual production processes. This can reduce computational requirements and / or improve speed. Furthermore, upstream industrial plants may not need to know the details of downstream production to provide such a model usable at the downstream industrial plant.

[0074] Data-driven models can be regression models. Data-driven models can also be mathematical models. Mathematical models can describe the relationship between the provided performance properties and the determined performance properties as a function.

[0075] In some cases, the prediction and / or control logic or prediction model may include an upstream data-driven model, i.e., a model trained from an upstream industrial plant using historical upstream data. Trained prediction and / or control logic or a trained prediction model can provide a more holistic prediction at the downstream plant without exposing upstream production details to the downstream plant.

[0076] Therefore, in this context, a data-driven model (preferably a data-driven machine learning ("ML") model or a data-only model) refers to a trained mathematical model parameterized from individual training datasets (such as upstream or downstream historical data) to reflect the reaction kinetics or physiological-chemical processes associated with individual production processes. An untrained mathematical model refers to a model that does not reflect reaction kinetics or physiological-chemical processes; for example, an untrained mathematical model is not derived from physical laws that provide scientific generalizations based on experimental observations. Therefore, kinetic or physiological-chemical properties may not be inherent in an untrained mathematical model. Untrained models do not reflect such properties. The parameterization of untrained mathematical models is achieved through feature engineering and training of individual training datasets. The result of this training is a data-driven model, preferably a data-driven ML model, which, as a result of training a process (preferably only as a result of training a process), reflects the reaction kinetics or physiological-chemical processes associated with individual production processes.

[0077] Predictive and / or control logic can even be a hybrid model. A hybrid model can refer to a model that includes a first-principles component (the so-called white box) and a data-driven component as previously explained (the so-called black box). Predictive and / or control logic can include a combination of white-box, black-box, and / or gray-box models. White-box models can be based on physiological and chemical laws. Physiological and chemical laws can be derived from first principles. Physiological and chemical laws can include one or more of the following: chemical kinetics, the law of conservation of mass, momentum and energy, and particle populations in any dimension. White-box models can be selected based on the physiological and chemical laws governing individual production processes or parts thereof. Black-box models can be based on historical data, such as downstream and / or upstream historical data. Black-box models can be constructed using one or more of machine learning, deep learning, neural networks, or other forms of artificial intelligence. A black-box model can be any model that produces a good fit between the training dataset and the test dataset. A gray-box model is a model that combines theoretical structures and data to complete the model.

[0078] The trained model can include serial or parallel architectures. In a serial architecture, the output of the white-box model can be used as the input of the black-box model, or the output of the black-box model can be used as the input of the white-box model. In a parallel architecture, the combined output of the white-box and black-box models can be determined, for example, by superimposing the outputs. As a non-limiting embodiment, a first sub-model can predict performance parameters and / or control setpoints based on a hybrid model having an analytical white-box model and a data-driven model, the data-driven model acting as a black-box corrector trained on individual historical data. This first sub-model can have a serial architecture, where the output of the white-box model is the input of the black-box model, or the first sub-model can have a parallel architecture. The predicted output of the white-box model can be compared with a test dataset containing a portion of the historical data. The error between the calculated white-box output and the test data can be learned by the data-driven model and can then be applied to any prediction. A second sub-model can have a parallel architecture. Other embodiments are also possible.

[0079] As used herein, the term "machine learning" or "ML" can refer to statistical methods that enable machines to "learn" tasks from data without explicit programming. Machine learning techniques can include "traditional machine learning"—a workflow in which we manually select features and then train the model. Examples of traditional machine learning techniques can include decision trees, support vector machines, and ensemble methods. In some embodiments, data-driven models can include data-driven deep learning models. Deep learning is a subset of machine learning that loosely models the neural pathways of the human brain. Deep refers to multiple layers between the input and output layers. In deep learning, algorithms automatically learn which features are useful. Examples of deep learning techniques can include convolutional neural networks (CNNs), recurrent neural networks such as long short-term memory (LSTMs), and deep Q-networks.

[0080] Based on a given state, the prediction and / or control logic is configured to generate modification data that can be used to modify the prediction and / or control logic to improve the calculation of downstream control setpoints.

[0081] In another scenario, trained prediction, i.e., prediction and / or control logic, can be trained at the downstream industrial plant, and / or modified data can be provided to the upstream industrial plant. The trained prediction and / or control logic and / or modified data can be provided, for example, via a downstream object identifier or a portion thereof provided to the upstream computing unit. The same shared memory or another suitable medium can be used for this purpose. The advantage of this method is that, for the purpose of improving upstream production processes while protecting downstream plant production data from the influence of upstream plants, downstream object identifiers with attached trained prediction and / or control logic can be used. This thus improves data protection between the two plants.

[0082] Another advantage is that trained predictive and / or control logic can even be provided to one or more other downstream plants to improve their production processes, while respecting the data security of downstream plants that provide trained predictive and / or control logic to upstream industrial plants (e.g., to upstream computing units).

[0083] Predictive and / or control logic can even be obfuscated, for example, encapsulated in a protected container, protecting the logic from unauthorized access or reading. The advantage of this is that upstream plants can provide services to improve downstream plant production while reducing security concerns related to logic exposed to unauthorized parties. Furthermore, downstream plants do not need to develop solutions internally or expose downstream historical data, but still benefit from downstream production improvements provided by object identifiers and logic from upstream industrial plants. This improves data security for both upstream and downstream plants, while potentially providing production improvements at both ends.

[0084] "Production process," such as downstream production process, refers to any industrial process that provides a downstream chemical product by using or applying it to a precursor material. Thus, a chemical product is provided through a downstream production process that generates a chemical product by directly converting the precursor, or by converting the precursor via one or more derivative materials. Similarly, upstream production process refers to any industrial process that provides a precursor by using or applying it to an input material.

[0085] Therefore, a manufacturing process can be any suitable manufacturing or processing process that involves at least part of one or more chemical processes or a combination of multiple processes for obtaining a chemical product at least partially from a precursor material. A manufacturing process can even include the packaging and / or stacking of the chemical product. Therefore, a manufacturing process can be a combination of chemical and physical processes.

[0086] The terms “in manufacture,” “in production,” or “in processing” will be used interchangeably in the context of the respective production processes. The terms may cover any kind of application of input materials to industrial processes, including chemical processes, that produces one or more precursor materials, and any kind of application of precursors to industrial processes, including chemical processes, that produces one or more chemical products.

[0087] The term "chemical product" in this disclosure may refer to any industrial product, such as chemicals, pharmaceuticals, nutritional products, cosmetics, or biological products, or even any combination thereof. A chemical product may consist entirely of natural components, or may at least partially contain one or more synthetic components. Some non-limiting examples of chemical products are organic or inorganic compositions, monomers, polymers, foams, pesticides, herbicides, fertilizers, feed, nutritional products, precursors, pharmaceuticals, or therapeutic products, or any one or more of their components or active ingredients. Preferably, the chemical product may be a product available to the end user or consumer, such as footwear, cosmetics, or pharmaceutical products.

[0088] "Precursor material" or simply "precursor" refers to a product or substance that can be used to manufacture one or more other chemical products. Precursors can be provided in any form, such as solids, semi-solids, pastes, liquids, emulsions, solutions, pellets, granules, beads, particles such as thermoplastic polyurethane ("TPU") particles, or powders. As several non-limiting embodiments, in some cases, the chemical product can be a shoe, helmet, padding, or tire having a sole made of synthetic foam. As several non-limiting embodiments, in such cases, at least one of the precursors can be, for example, thermoplastic polyurethane ("TPU") and / or expanded TPU ("ETPU") in bead or particle form.

[0089] Because such precursors and / or chemical products can be difficult to trace or track, especially during their production process, let alone establish traceability to the specific starting materials from which they are produced. It should be understood that input materials can be referred to as the starting materials for precursors produced at upstream plants. Similarly, precursors can be referred to as the starting materials for chemical products produced at downstream plants. As an example, during production, input materials can be mixed with another material, and / or input materials can be segmented into different portions downstream of the production chain, for example, for different processing methods. Input materials can be converted, for example, into one or more derivative materials more than once before being converted into precursor materials. Similarly, precursors can be mixed and / or segmented and / or converted multiple times during downstream production processes. Furthermore, different portions of the precursor can be shipped to different downstream industrial plants or customers. For example, precursors can be segmented and packaged in different packages. Although in some cases it may be possible to label the packaged precursor or portions thereof, it may be difficult to accurately reflect the details of the production process responsible for producing a particular precursor or portion thereof. Similar problems can exist in downstream production chains. In many cases, input materials and / or precursors and / or chemical products may be in a form that is difficult to physically identify. Therefore, this teaching provides one or more object identifiers that can be used to overcome such limitations.

[0090] Production processes, i.e., upstream and / or downstream processes, can be continuous in operation, such as batch chemical production processes when catalysts require recovery. A key difference between these production types lies in the frequency of data generated during production. For example, in batch processes, production data extends from the beginning of the process to the last of the various batches already in operation. In continuous settings, data becomes more continuous with potential deviations in production operations and / or with maintenance-driven downtime.

[0091] "Process data" refers to data contained in individual production processes, such as values ​​(e.g., numerical or dual-signal values) measured by one or more sensors. Process data can be time-series data of one or more process parameters and / or equipment operating conditions, such as downstream time-series data in the case of a downstream plant. Preferably, individual components of the process data include time information of process parameters and / or equipment operating conditions of their respective plants; for example, the data contains timestamps for at least some of the data points related to the process parameters and / or equipment operating conditions. More preferably, the process data includes spatiotemporal data, i.e., time data and location or data associated with one or more physically located equipment areas, such that spatiotemporal relationships can be derived from the data. Spatiotemporal relationships can be used, for example, to calculate the location of input materials at a given time.

[0092] "Real-time process data" refers to process data that is measured or substantially transient when a specific material (e.g., a precursor) is processed using individual manufacturing processes. For example, real-time process data for input materials or upstream real-time process data is upstream process data that is processed simultaneously or approximately simultaneously with the upstream manufacturing process. Similarly, real-time process data for precursor materials or downstream real-time process data is downstream process data that is processed simultaneously or approximately simultaneously with the downstream manufacturing process.

[0093] Here, "approximately the same time" means with very little or no time delay. The term "instantaneous" is understood in the technical field of computers and instruments. As a particular non-limiting embodiment, the time delay between the occurrence of production during individual production processes for individual materials and the process data measured or read out is less than 15 seconds, specifically no more than 10 seconds, and more specifically no more than 5 seconds. For high-volume processing, the delay is less than one second, or less than a few milliseconds, or is stable. Instantaneous data can therefore be understood as the streaming of time-dependent process data generated during the processing of individual materials at their respective plants.

[0094] "Process parameters" can refer to any of the variables related to the production process, such as temperature, pressure, time, content, etc.

[0095] "Input material" can refer to at least one raw material or untreated material used in the production of precursors. Input material can be any organic or inorganic substance or even a combination thereof. Therefore, input material can even be a mixture or may contain a plurality of organic and / or inorganic components in any form. In some cases, input material can even be, for example, derivative material or intermediate material received or transferred from upstream equipment areas. A few non-limiting examples of input materials may be any one or more of the following: polyether alcohol, polyether glycol, polytetrahydrofuran, polyester glycol such as adipic acid and butane-1,4-diol, isocyanate, filler materials (organic or inorganic materials such as wood powder, starch, flax, kapok, ramie, jute, sisal, cotton, cellulose or aramid fiber, silicate, barite, glass beads, zeolite, metal or metal oxide, talc, chalk, kaolin, aluminum hydroxide, magnesium hydroxide, aluminum nitrite, aluminum silicate, barium sulfate, calcium carbonate, calcium sulfate, silicon dioxide, quartz powder, aerosil, clay, mica or wollastonite, iron powder, glass beads, glass fiber or carbon fiber.

[0096] As another non-limiting embodiment, the input material may be methylene diphenyl diisocyanate (MDI) and / or polytetrahydrofuran (PTHF) undergoing at least a portion of the manufacturing process to obtain TPU. It should be understood that the input material is thus chemically processed in one or more equipment areas to obtain thermoplastic polyurethane, which in some cases may be a derivative material and / or a precursor material. In this case, a derivative material means a material derived from the input material but further processed to obtain a precursor. For example, the thermoplastic polyurethane may be further processed in one or more additional equipment areas to obtain expanded thermoplastic polyurethane or ETPU. Expanded thermoplastic polyurethane may, for example, be a precursor material provided to downstream plants. However, in some cases, the thermoplastic polyurethane itself may even be a precursor sent to downstream plants. The chemical product may, for example, be a shoe manufactured using at least a portion of TPU or ETPU.

[0097] "Input material data" refers to data relating to one or more characteristics or properties of the input material. Therefore, input material data may include any one or more values ​​indicating properties such as quantity of the input material. Alternatively or additionally, the value indicating quantity may be the fill power and / or mass flow rate of the input material. These values ​​are preferably measured via one or more sensors operatively coupled to or included in upstream equipment. Alternatively or additionally, input material data may include sample / test data relating to the input material. Alternatively or additionally, input material data may include values ​​indicating any physical and / or chemical properties of the input material, such as density, concentration, purity, pH, composition, viscosity, temperature, weight, volume, etc., any one or more.

[0098] "Precursor data" or "precursor material data" refers to data relating to one or more characteristics or properties of a precursor material. Therefore, precursor material data may include any one or more values ​​indicating the properties (such as quantity) of the precursor material. Alternatively or additionally, the value indicating quantity may be the filler content and / or mass flow rate of the precursor material. At least some of these values ​​may be measured via one or more sensors operatively coupled to or included in downstream equipment. Some of the values ​​may be provided by an upstream plant or upstream computing unit, for example via an upstream object identifier, or in some cases by the provision of the downstream object identifier itself. Alternatively or additionally, precursor data may include sample / test data related to the precursor material. Alternatively or additionally, precursor material data may include values ​​indicating any one or more physical and / or chemical properties (such as density, concentration, purity, pH, composition, viscosity, temperature, weight, volume, etc.) of the precursor material. In some cases, precursor data may include a portion of data from an upstream object identifier. For example, precursor data may then include a reference or link to an upstream object identifier, or even in some cases, at least a subset of upstream process data.

[0099] "Object identifier" refers to a digital identifier used for its respective material. For example, an upstream object identifier is provided for input material. Similarly, a historical upstream object identifier corresponds to a specific historical input material processed earlier. Object identifiers are preferably generated by a computing unit. The provision or generation of object identifiers can be triggered by individual devices or in response to triggering events or signals, such as those from upstream devices. Object identifiers can be stored in memory storage or memory storage elements operatively coupled to the computing unit. For example, an upstream memory storage is operatively coupled to an upstream computing unit. Similarly, a downstream memory storage is operatively coupled to a downstream computing unit. In some cases, as discussed, a shared memory storage may also be provided, operatively coupled to or accessible by both the upstream and downstream computing units. In some cases, the shared memory storage may be, or at least partially, a part of the upstream memory storage, and / or the shared memory storage may be, or at least partially, a part of the downstream memory storage. The memory storage may contain at least one database, or may be a part of at least one database. Therefore, an object identifier may even be part of a database. It should be understood that object identifiers may be provided by any suitable means, such as being able to transmit, receive, or generate object identifiers.

[0100] Each “computing unit” (i.e., an upstream computing unit or a downstream computing unit) may include or be a processing component or computer processor having one or more processing cores, such as a microprocessor, microcontroller, or the like. In some cases, a computing unit may be at least partially part of a device, for example, it may be a process controller, such as a programmable logic controller (“PLC”) or a distributed control system (“DCS”), and / or it may be at least partially a remote server. Thus, each computing unit may receive one or more input signals from one or more sensors operatively connected to each device. If the individual computing unit is not part of the individual device, it may receive one or more input signals from the individual device. Alternatively or additionally, each computing unit may control one or more actuators or switches operatively coupled to each individual device.

[0101] One or more actuators or switches may even be part of the device in operation.

[0102] "Memory storage" or "memory storage element" (e.g., upstream memory storage and / or downstream memory storage) can refer to a device or system for storing information in data form in a suitable storage medium. Preferably, the memory storage is a digital storage device suitable for storing machine-readable information in digital form, such as digital data readable by a computer processor. The memory storage can therefore be implemented as a digital memory storage device readable by a computer processor. The memory storage can be implemented at least partially in a cloud service. More preferably, the memory storage on the digital memory storage device can also be controlled by a computer processor. For example, any portion of the data recorded on the digital memory storage device can be partially or wholly written to and / or erased and / or overwritten with new data by a computer processor.

[0103] Each "computing unit" (i.e., an upstream computing unit or a downstream computing unit) may include or be a processing component or computer processor having one or more processing cores, such as a microprocessor, microcontroller, or the like. In some cases, each computing unit may be at least partially part of a particular device; for example, it may be a process controller, such as a programmable logic controller ("PLC") or a distributed control system ("DCS"), and / or it may be at least partially a remote server and / or cloud service. Therefore, each computing unit may receive one or more input signals from one or more sensors operatively connected to the particular device or a plurality of device areas. If the computing unit is not part of a device, it may receive one or more input signals from the device or device area. Alternatively or additionally, the computing unit may control one or more actuators or switches operatively coupled to the device. One or more actuators or switches may even be operatively part of the device. The computing unit is operatively coupled to the device or a plurality of device areas.

[0104] Therefore, each computing unit can control one or more parameters related to a particular production process by controlling any one or more of the actuator or switch and / or terminal effector units (e.g., by controlling one or more of the operating conditions of the respective equipment). Control is preferably performed in response to one or more signals acquired from the equipment.

[0105] In this context, "terminal effector unit" or "terminal effector" refers to a device that is part of and / or operatively connected to a device, and is therefore controllable via the device and / or a separate computing unit for the purpose of interacting with the environment surrounding the device. As several non-limiting embodiments, a terminal effector may be a cutter, a gripper, an atomizer, a mixing unit, an extruder tip or the like, or even a portion thereof designed to interact with the environment (e.g., input materials and / or precursors and / or chemical products).

[0106] With respect to individual materials (i.e., input materials, precursor materials, or derivative materials), "property" can refer to any one or more of the following: the quantity of the material, batch information, and one or more values ​​of a specified quality (such as the purity, concentration, viscosity, or any characteristic of the material).

[0107] An "interface" can be a hardware and / or software component that is at least part of one of the individual devices or another computing unit that provides an object identifier. For example, an interface can be an application programming interface (API). In some cases, an interface can also connect to at least one network, for example, for interfacing two components of hardware components and / or protocol layers within the network. For example, an interface can be an interface between individual devices and individual computing units. In the case of a downstream factory, a downstream interface can be an interface between a downstream device and a downstream computing unit. Similarly, in the case of an upstream factory, an upstream interface can be an interface between an upstream device and an upstream computing unit. In some cases, individual devices can be communicatively coupled to their respective computing units via individual networks. Therefore, an interface can even be a network interface, or may include a network interface. In some cases, an interface can even be a connectivity interface, or may include a connectivity interface.

[0108] "Network interface" refers to a device or group of one or more hardware and / or software components that allow operational connection to a network.

[0109] "Connectivity interface" refers to a software and / or hardware interface used to establish communication (such as transmission or exchange of signals or data). Communication may be wired or wireless. A connectivity interface is preferably based on one or more communication protocols or supports one or more communication protocols. Communication protocols may be wireless protocols, such as short-range communication protocols, such as Bluetooth® or WiFi; or long-range communication protocols, such as cellular or mobile networks, such as second-generation (2G), 3G, 4G, Long-Term Evolution (LTE), or 5G. Alternatively or additionally, a connectivity interface may even be based on proprietary short-range or long-range protocols. A connectivity interface may support any one or more standards and / or proprietary protocols. The connectivity interface and the network interface may be the same unit or may be different units.

[0110] The term "network" as used herein can refer to any suitable type of data transmission medium, wired, wireless, or a combination thereof. A specific type of network does not limit the scope or generality of this teaching. A network can therefore refer to any suitable, arbitrary interconnection between at least one communication endpoint and another. A network may include one or more distribution points, routers, or other types of communication hardware. The interconnection of networks can be formed by means of physical hardwiring, optical, and / or radio frequency methods. Specifically, a network may be or may include physical networks made wholly or partially of hardwiring, such as fiber-optic networks or networks made wholly or partially of conductive cables, or combinations thereof. A network may at least partially include the Internet. At least a portion of a network at an upstream plant or upstream network may be isolated from at least a portion of a network at a downstream plant or downstream network. Furthermore, upstream and downstream networks may at least partially be non-public networks, i.e., isolated from public networks such as the Internet. Through isolation, it should be understood that these networks can be isolated at each plant using security measures (such as one or more network firewalls). Alternatively or additionally, other security and isolation measures can be in place to protect the networks and production environment at one or two plants.

[0111] As discussed, in some cases, individual subsets of process data are attached to individual object identifiers. For example, a subset of upstream real-time process data related to input materials being processed by upstream equipment may be entirely included in the upstream object identifier, or a portion thereof may be attached or saved. Therefore, a snapshot of the upstream real-time process data related to the processing of input materials in the upstream equipment or equipment area may be available or linked to the upstream object identifier. Whether the real-time process data is entirely saved or only a portion thereof may be based, for example, on a determination by the upstream computing unit regarding which portion of the process data should be attached to the object identifier. Similarly, a subset of downstream real-time process data related to precursor materials being processed by downstream equipment may be entirely included in the downstream object identifier, or a portion thereof may be attached or saved.

[0112] Alternatively or additionally, for the purposes discussed above, or additionally, this determination may be based, for example, on the most important individual process parameters and / or equipment operating conditions that affect the desired properties of the resulting precursor or chemical product. This can be advantageous in certain situations, particularly when the relevant real-time process data is large in volume, thus allowing individual computing units to determine which subset of the individual real-time process data should be appended, rather than appending a large amount of data to individual object identifiers. Therefore, the portion of real-time process data appended to object identifiers can be determined by individual computing units. For example, a downstream computing unit can determine which subset of the downstream real-time process data should be appended to the downstream object identifier.

[0113] Furthermore, this determination can be based on one or more ML models. Such models will be discussed in more detail below.

[0114] According to another approach, the upstream object identifier also includes upstream process-specific information. This upstream process-specific information can be any one or more of the following: upstream enterprise resource planning (ERP) data, such as order numbers and / or production codes and / or production process formulas and / or batch data from downstream plants; recipient information, such as downstream plant data; and digital models or logic relating to the transformation of input materials and / or precursor materials into chemical products. Examples of this digital model have previously been discussed based on predictive and / or control logic.

[0115] ERP data can be received from the ERP system associated with the upstream industrial plant. The digital model can be any one or more of the following: a computer-readable mathematical model representing one or more entities and / or chemical changes related to the transformation of input materials and / or precursors into chemical products. Batch data can be related to batches in production and / or to data related to previous products manufactured via the same equipment. In this way, precursor traceability can be further improved by bundling associated process-specific data. More specifically, batch data can be used to more optimally sequence the production of various precursors that are at least partially produced via the same upstream equipment, but which have one or more different properties or specifications. For example, the production of such precursors can then be adjusted and / or sequenced in a way that minimizes the impact attributable to previous batches. For example, if two or more precursors have different colors, the production sequence can be determined by the upstream computing unit so that the color traces from the previously manufactured precursors are minimally affected by the previously manufactured precursors.

[0116] Similarly, downstream object identifiers may be accompanied by downstream process-specific information. This downstream process-specific information may be any one or more of the following: downstream enterprise resource planning (“ERP”) data, such as order numbers and / or production codes and / or production process formulas and / or batch data destined for upstream plants; supplier information, such as upstream plant data; and digital models or logic relating to the transformation of input materials and / or precursor materials into chemical products. Examples of this digital model have previously been discussed in relation to predictive and / or control logic, which may be provided, for example, by an upstream computing unit.

[0117] "Control setpoint" refers to any individual controllable setpoint and / or value that can be affected by one or more plant control systems that are functionally or operatively coupled to individual equipment, in such a way that the setpoint and / or controllable value affects the manner in which individual materials (and related derivative materials) are processed to produce precursors or chemical products, respectively. For example, a downstream control setpoint is determined using downstream process parameters and / or operating conditions for the production of a chemical product. Similarly, an upstream control setpoint is determined using upstream process parameters and / or operating conditions for the production of a precursor. For example, a control setpoint can be a setpoint for one or more controllers in one or more plant control systems for an individual plant. A control setpoint can, for example, be related to a temperature setpoint that the controller should use to process at the equipment area. Another control setpoint can be a period of time during which one or more materials should be processed (e.g., mixed). Other non-limiting embodiments of control setpoints include values ​​such as processing time, pressure, amount such as weight or volume, ratio, content, rate of change such as flow rate, output, speed, rotational speed (such as revolutions per minute (rpm)), and mass. Additionally or alternatively, individual control setpoints may even determine the formulation for producing precursors or chemical products. For example, at least some of the individual control setpoints may determine the amount or percentage of material to be used, such as selecting the ratio at which two components should be mixed and / or the amount of additives added at each individual unit.

[0118] Therefore, "zone-specific control setpoint" refers to a control setpoint, that is, any controllable setpoint and / or value, which is, for example, zone-specific for an upstream device. Similarly, downstream control setpoints can also be zone-specific.

[0119] Each "performance parameter" may be, or may be, an indication of, any one or more properties of a precursor or chemical product, or related to any one or more properties of a precursor or chemical product. Therefore, a downstream performance parameter may be a parameter that meets one or more predefined criteria indicating the suitability or fitness of a chemical product for a particular application or use. It should be understood that, in some cases, a performance parameter may indicate a lack of suitability, or unsuitability, for a particular application or use of a material or product. Similarly, an upstream performance parameter may be a parameter that meets one or more predefined criteria indicating the suitability or fitness of a precursor material and / or even a chemical product for a particular application or use. As a non-limiting embodiment, performance parameters may be any one or more of the following, determined by testing using predefined criteria: tensile strength, hardness such as Shore hardness, density such as bulk density, color, concentration, composition, viscosity, melt flow value (MFV) such as TPU, hardness such as Young's modulus, purity or impurity such as parts per million (ppm), failure rate such as mean time to failure (MTTF), or any one or more values ​​or variations thereof. Downstream performance parameters thus represent the performance or quality of the chemical product. Predefined criteria may be, for example, one or more reference values ​​or ranges to which the performance parameters of the chemical product and / or precursor are compared to determine the quality or performance of the chemical product and / or precursor. Predefined criteria may have been established using one or more tests (such as laboratory tests, reliability tests, or wear tests) to determine the suitability of performance parameters for precursors or chemical products for one or more specific uses or applications. In some cases, performance parameters may be related to the properties of the derivative materials or derived from the quality measurements of the derivative materials.

[0120] Generally, any of the performance parameters can be calculated via corresponding computing units associated with individual production processes. Object identifiers enable more efficient and reliable calculation of these parameters. Any of these parameters can be part of historical data so that individual computing units can determine production setpoints and monitor the manufacturing process and / or control product quality as needed. Furthermore, as proposed, historical data can be updated based on current production (e.g., via downstream object identifiers). Historical data can also be used to train one or more ML models, for example, for predicting operational quality using any of these performance parameters. In the case of predictive and / or control logic, this trained ML model can be at least partially a data-driven model.

[0121] Each "desired performance parameter" may be, or may be indicative of, any one or more desired properties of the precursor or chemical product, or related to any one or more desired properties of the precursor or chemical product. Therefore, a desired performance parameter may correspond to a desired value of a performance parameter. For example, a desired upstream performance parameter may correspond to a desired value of an upstream performance parameter. Similarly, a desired downstream performance parameter may correspond to a desired value of a downstream performance parameter.

[0122] It should be understood that, in this context, "area-specific" refers to a specific equipment area, such as a specific area in an upstream device or a specific area in a downstream device.

[0123] Typically, individual performance parameters are determined from one or more samples of chemical products and / or precursor materials collected during and / or after their respective production processes. Samples may be brought into the laboratory and analyzed to determine individual performance parameters. The results of the analysis or the determined performance parameters may be included or affixed to individual object identifiers and thus included in individual historical data.

[0124] However, it should be understood that the entire process of collecting, processing, or testing samples, and then analyzing the results, can be time-consuming and resource-intensive. Therefore, there can be a significant delay between sample collection and any adjustments to input materials and / or process parameters and / or equipment operating conditions. This delay or lag may result in the production of suboptimal chemical products, or, in the worst case, halt production until the samples have been analyzed and any corrective actions have been taken by adjusting input or precursor materials and / or process parameters and / or equipment operating conditions.

[0125] As a solution to at least reduce the variability in the performance of chemical products (and, in some cases, precursor materials), this instruction can be used to more closely control individual production processes via historical data and, in some cases, via at least one region-specific performance parameter that can be attached to at least some of the historical object identifiers. Therefore, the need for manual sampling can be reduced.

[0126] In one scenario, at least one downstream performance parameter is calculated using a downstream analytical computer model. In another scenario, at least one downstream machine learning ("ML") model is used to determine the downstream control setpoint. The downstream ML model can be trained based on downstream historical data preferably derived from one or more historical downstream object identifiers. As in the case of prediction and / or control logic, the trained downstream ML model can be at least partially a data-driven model.

[0127] Similarly, the calculation of at least one upstream performance parameter can be performed using an upstream analytical computer model. Furthermore, depending on the circumstances, at least one upstream machine learning ("ML") model can be used to determine the upstream control setpoint. The upstream ML model can be trained based on upstream historical data preferably derived from one or more upstream object identifiers. As in the case of prediction and / or control logic, the trained upstream ML model can be at least partially a data-driven model.

[0128] Chemical production can be a data-intensive environment, generating vast amounts of data from various facilities. It should also be understood that the proposed teachings enable the implementation of suitable and more efficient monitoring and / or control methods or systems for edge computing, at least for downstream industrial plants. Similarly, equivalent features can be applied to upstream industrial plants to further establish more complete traceability and quality control from input materials via chemical products, even if production takes place in different, isolated plants. It will also be appreciated that monitoring, such as safety and / or quality control and / or control of at least downstream production processes, can therefore be performed essentially at point (e.g., within each downstream equipment area) with reduced computational resource (e.g., processing power) and / or memory requirements, as object identifiers provide a highly targeted dataset of relevant data for calculating performance parameters. It is also possible to reduce computational latency, thus ensuring sufficient time for number crunching algorithms without slowing down individual production processes. This can also be used to make the training process of ML models faster and more efficient. Furthermore, data and / or logic from upstream production processes can be further utilized downstream for more precise control of product performance.

[0129] For similar reasons, this instruction is also applicable to cloud computing, as datasets can become dense and efficient. Many cloud service providers operate on a pay-per-use model based on the utilization of computing resources, thus reducing costs and / or enabling more efficient use of computing power.

[0130] Therefore, according to a given scenario, at least one downstream ML model can be trained based on data from one or more historical downstream object identifiers or downstream historical data. The data used to train the downstream ML model may also include historical and / or current laboratory test data, or data such as downstream performance parameters measured from past and / or recent samples of chemical products and / or precursor materials. For example, quality data from one or more analyses, laboratory equipment, or other measurement techniques, such as image analysis, can be used. By including the analyzed performance parameters in their associated historical object identifiers, a more complete relationship between performance parameters and their corresponding process data is captured efficiently. This allows for more accurate utilization of expensive and time-consuming laboratory results to improve the quality of future chemical products. It also reduces the scope of human error due to the integration of quality data with snapshots of their associated process data.

[0131] In some cases, if the chemical product or its derivative material is to be analyzed, a sample identifier is automatically provided. This can be based on a confidence value or whether the calculation unit cannot minimize the difference between the calculated performance parameter and its corresponding desired value. The results of the analysis or measurement of the sample can therefore be included or appended to the sample identifier, thereby further accurately encapsulating the data and reducing the range of human error. Data from the sample identifier can also be included in downstream historical data.

[0132] At least one downstream ML model trained with data (e.g., from historical downstream object identifiers) can therefore be used to determine at least some of the downstream control settings, which may even be zone-specific control settings for downstream devices.

[0133] Therefore, to determine downstream control setpoints, a downstream ML model trained using downstream historical data can receive precursor data and at least one desired downstream performance parameter as input. The downstream ML model can thus provide the downstream control setpoints as calculated values. As previously discussed, the calculated values ​​can be provided to the operator via an HMI and / or directly to the downstream control system. Similarly, the downstream ML model can be used to automatically adopt downstream production processes based on details of the precursor material obtained from the precursor data and the desired performance obtained from at least one desired downstream performance parameter and a subset of downstream real-time process data. The downstream calculation unit can, for example, minimize the difference between each or some of the downstream performance parameters calculated by the downstream ML model and their respective desired performance parameter values.

[0134] According to another approach, the downstream ML model can also provide at least one confidence value indicating the downstream control setpoints. In some cases, the confidence value can also be appended to the downstream object identifier, for example, as meta-data. If the confidence level of the prediction or calculation of any of the downstream control setpoints falls below the accuracy threshold, a warning can be triggered at the downstream control system used for production. The warning can be generated as a warning signal, for example, to start downstream production using a set of preset setpoints, or it can be used to determine whether the downstream ML model should be retrained.

[0135] In some cases, when the confidence level of a prediction or calculation responding to any of the downstream control setpoints falls below the accuracy threshold, a retraining object identifier is automatically provided via the downstream interface. The downstream processing unit can be configured to attach the confidence value, precursor data, and at least one desired downstream performance parameter to the retraining object identifier. The retraining object identifier can be used to determine which insights are lacking for controlling downstream production processes using the set of variables included in the retraining object identifier. The retraining object identifier can thus be used to further refine downstream historical data for future decisions via the downstream computing unit. As a case study, the chemical products produced associated with the retraining object identifier can be sampled and analyzed. The results of the analysis (e.g., measured downstream performance parameters) can be attached to the retraining object identifier. The retraining object identifier can thus be included in the downstream historical data. In this way, complete material traceability can be maintained, and the correct products can be sampled so that downstream historical data is effectively enriched even for situations not fully covered by previous downstream historical data. Therefore, this allows one or more correct samples to be collected from production based on tracking provided by the retrained object identifier, and the samples, along with data from the retrained object identifier, can be analyzed to find the cause of the decline in the confidence level. This allows for a better understanding of the complex relationships between various variables, enabling further improvements to downstream control processes.

[0136] In some cases, the same downstream ML model or another downstream ML model can be used by the downstream computing unit to determine which subsets or components of the downstream real-time process data have the most significant impact on the chemical product. Therefore, the downstream computing unit is enabled to exclude downstream process parameters and / or equipment operating conditions that have a negligible impact on at least one downstream performance parameter. The relevance of the downstream real-time process data for a specific chemical product can thus be improved for its individual object identifiers.

[0137] In some cases, a downstream object identifier is appended with at least a portion of an upstream object identifier. Therefore, the entire upstream object identifier may be encompassed within or only a portion of the downstream object identifier. For example, this portion may be a reference to an upstream object identifier or a link that directly connects two object identifiers or connects them via one or more other object identifiers that may have already been created between these two object identifiers.

[0138] As discussed, downstream control setpoints can be zone-specific and vary for different areas traversed by the precursor material during downstream production processes. This allows for adjustments to the downstream production process within the downstream zone based on downstream process data from upstream material handling. Consequently, the granularity of control can be further refined and made more flexible. For example, any suboptimal upstream processing can be corrected by adjusting the downstream zone-specific control setpoints.

[0139] In addition to determining specific control settings for downstream areas, downstream object identifiers may also be supplemented with at least a portion of real-time process data from individual downstream equipment areas based on presence signals as discussed. This not only provides more granular control but also further improves the relevance of downstream object identifiers, particularly encapsulations and / or data referenced therein.

[0140] As discussed, a downstream object identifier may at least partially encapsulate or enrich an upstream object identifier, or more specifically, data from an upstream object identifier that has been appended with at least a subset of upstream real-time process data. Alternatively, a downstream object identifier may be linked to an upstream object identifier. In other words, it can be claimed that a downstream object identifier is appended to an upstream object identifier. Thus, the downstream object identifier is associated with the upstream object identifier by the upstream object identifier being at least partially a part of the downstream object identifier.

[0141] Downstream computing units can even provide additional downstream object identifiers, such as when precursor materials are segmented or combined with other materials during downstream production. Specific subsets of data, as discussed earlier, can be attached to their respective additional downstream object identifiers. By doing so, finer visibility into the quality of various components in the downstream production chain can be improved. For example, performance parameters for each specific region can also be used to track and control the quality of materials within that specific region.

[0142] Similar to the above discussion, other ML models can also be applied to any of the other downstream object identifiers. These additional ML models can be used to predict performance parameters and / or control downstream production by adjusting specific downstream control setpoints based on outputs from individual models.

[0143] Those skilled in the art will understand that the term "attached" or "with attachment" can mean including or attaching (e.g., storing) different data elements, such as meta data, to the same database or memory storage element at adjacent or different locations in the same database or memory storage. The term can even mean linking one or more data elements, packages, or streams at the same or different locations in such a way that the data packages or streams can be read and / or retrieved and / or combined as needed. At least one of these locations may be part of a remote server or even at least partially part of a cloud-based service.

[0144] "Remote server" refers to one or more computers or computer servers located far from the factory. A remote server can therefore be located several kilometers or more away from the factory. A remote server can even be located in different countries. A remote server can even be implemented at least partially as a cloud-based service or platform, such as a Platform as a Service (PaaS). The term can also collectively refer to more than one computer or server located in different locations. A remote server can be a data management system.

[0145] It should be understood that the precursor material after traversing the initial downstream equipment zone can be substantially different in nature from when it entered the initial downstream equipment zone. Therefore, as discussed, after traversing the initial downstream equipment zone, the precursor material may have been transformed into a derivative material or intermediate processing material when it enters another downstream equipment zone. However, for simplicity and without losing the generality of this teaching, the term precursor material will also be used to refer to the situation where the precursor material has been transformed into this intermediate processing material or derivative material during the downstream production process. For example, a batch of precursor material in the form of a mixture of chemical components may have traversed the initial downstream equipment zone on a conveyor belt in which that batch was heated to induce a chemical reaction. Therefore, when the precursor material leaves the initial downstream equipment zone or enters another downstream equipment zone directly after traversing other zones, the material may have become a derivative material with properties different from the precursor material. For example, a precursor in the form of TPU in the initial downstream equipment zone may have been transformed into ETPU when entering another downstream equipment zone. In this embodiment, the ETPU can be referred to as a derivative or intermediate processing material. However, as mentioned above, such derivative materials can still be referred to as precursor materials, at least because the relationship between this intermediate processing material and the precursor material can be defined and determined by the downstream production process. Furthermore, in other cases, such as when the initial downstream equipment area only dries the precursor material or filters it to remove traces of undesirable material, the precursor material can retain substantially similar properties even after traversing the initial downstream equipment area or other areas. Therefore, those skilled in the art should understand that precursor materials in any intermediate area may or may not be converted into derivative materials.

[0146] As discussed, when samples of precursor materials, derivative materials, or chemical products are collected for analysis, such samples may also be provided with sample object identifiers. These sample object identifiers may be similar to those discussed in this disclosure and therefore include relevant corresponding process information, as discussed. Thus, the sample may also be accompanied by an accurate snapshot of the downstream production process related to the properties of the sample. This allows for further improvements in analysis and quality control. Furthermore, the downstream production process may be collaboratively improved, for example, based on improved training of one or more ML models.

[0147] According to another approach, when downstream production processes involve physically conveying or moving precursor materials within or between zones using conveyor elements such as conveyor systems, downstream real-time process data may also include information indicating the speed of the conveyor elements and / or the speed at which the precursor material is conveyed during the downstream production process. Speed ​​can be provided directly by one or more sensors and / or calculated by a downstream computing unit, for example, based on the time of entry into the zone and the time of exit from the zone, or the time of entry into another zone after entering the zone. Downstream object identifiers can thus be further enriched with processing time profiles within the zones, particularly those that may influence one or more downstream performance parameters of the chemical product. Furthermore, by using timestamps for entry and exit or subsequent zone entry, the requirement for speed measurement sensors or conveyor element devices can be avoided.

[0148] According to another approach, each object identifier includes a unique identifier, preferably a globally unique identifier (GUID). At least for chemical products, tracking can be enhanced by attaching a GUID to each virtual package of the chemical product. Where appropriate, the chemical product can be traced back to the input material used in the production of precursor materials. GUIDs also reduce the management of process data such as time-series data and enable direct correlation between virtual / physical packages, production history, and quality control history.

[0149] As discussed regarding ML models, an upstream ML model can be trained based on data from upstream object identifiers, according to a single-state sample. Training data may also include past and / or current laboratory test data, or data from past and / or recent samples of precursor materials and / or chemical products. Object identifiers also make it easier for upstream plants to link the performance of chemical products produced at downstream plants with specific input materials used to produce precursors and upstream process data used to process those materials. This can have significant benefits in ensuring consistent quality of chemical products.

[0150] In addition to the advantages of ML models discussed earlier, trained models based on zones in individual production lines allow for more detailed tracking of materials and prediction of their individual performance parameters, and even performance parameters of chemical products.

[0151] In some production scenarios, such as batch production, this type of model can be used in operation to identify quality control issues not only for the chemical products being produced but also for any derivative materials.

[0152] Therefore, any one or each of the upstream and / or downstream equipment areas can be monitored and / or controlled by an individual ML model, which is trained based on data from individual object identifiers (which come from the equipment area).

[0153] According to one specification, in response to any one or more values ​​indicating the properties of the precursor material and / or any one or more values ​​from the operating conditions of the downstream equipment and / or any one or more values ​​of the downstream process parameters reaching, meeting, or exceeding a predefined threshold, the provision of individual object identifiers, such as downstream object identifiers, to the area may occur or be triggered. Any such value may be measured via one or more downstream sensors and / or switches. For example, the predefined threshold may be related to the weight or quantity of the precursor material introduced at the downstream equipment. Therefore, a trigger signal may be generated when the quantity of precursor material received at the downstream equipment, such as the weight, reaches a predefined quantity threshold, such as a weight threshold. Ideally, an upstream object identifier is automatically attached to a downstream object identifier, for example, via process-specific data and / or tags from the incoming precursor material. Certain embodiments of triggering events or the provision of object identifiers are also discussed earlier in this disclosure. An object identifier can be provided in response to a trigger signal, or directly in response to the quantity or weight reaching a predefined weight threshold. The trigger signal can be a single signal, or it can be simply an event, such as a specific signal that meets predefined criteria such as threshold values ​​detected by a computing unit and / or device. Therefore, it should also be understood that an object identifier can be provided in response to the quantity of precursor material reaching a predefined quantity threshold. The quantity can be measured as weight as explained in the above embodiments, and / or it can be any one or more other values, such as content, filler content or filler percentage, or volume, and / or by summing the mass flow rate of the precursor material or by applying an integral to the mass flow rate of the precursor material.

[0154] Therefore, for example, a downstream object identifier may be provided in response to a trigger event or signal, preferably provided via a downstream device or an initial downstream device area. This may be in response to the output of any of one or more downstream sensors and / or switches operatively coupled to the downstream device. The trigger event or signal may be related to the quantity of the precursor material, for example, to the occurrence of a quantity reaching or conforming to a predetermined quantity threshold. This occurrence may be detected via a downstream computing unit and / or downstream device, for example using one or more weight sensors, content sensors, fill sensors, or any suitable sensors capable of measuring or detecting the quantity of the precursor material.

[0155] The advantage of using quantity as a trigger for providing downstream object identifiers is that any change in the amount of material during the production process can be used as a trigger for providing one or more additional downstream object identifiers as explained in this teaching. The applicant has recognized that this provides an optimal way to segment the generation of different object identifiers in an industrial environment used to process or produce one or more chemical products, allowing traceability of precursor materials, any derivative materials, and final chemical products substantially throughout the entire production chain, taking into account both quantity and mass flow rates. By providing object identifiers only at the point where new material is introduced or input, or where material is segmented, the number of object identifiers can be minimized, while maintaining material traceability not only at the endpoints of production but also within them. In equipment or production areas where no new material is added or where no material is segmented, knowledge of the process within such areas can be used to maintain observability within two adjacent object identifiers.

[0156] From one perspective, any one or more of the control setpoints and / or performance parameters generated according to any of the methodologies disclosed herein can also be used to control a production process (e.g., a downstream plant). More specifically, downstream control setpoints and / or at least one downstream performance parameter.

[0157] Thus, any of the downstream plants discussed can obtain an improved production process for manufacturing one or more chemical products.

[0158] From another perspective, a system for controlling downstream production processes can also be provided, configured to perform any of the methods disclosed herein. Alternatively, a system for controlling a downstream production process in which a chemical product is manufactured at a downstream industrial plant comprising at least one downstream device, and the product is manufactured by processing at least one precursor material via that downstream device using a downstream production process, wherein the system is configured to perform any of the methods disclosed herein.

[0159] For example, a system may be provided for controlling a downstream manufacturing process of a chemical product at a downstream industrial plant, the downstream industrial plant including at least one downstream device and a downstream computing unit, wherein the product is manufactured by processing at least one precursor material via the downstream device using the downstream manufacturing process, wherein the system is configured to: - A set of downstream control setpoints for controlling the production of the chemical product is provided at the downstream computing unit, wherein these downstream control setpoints are determined based on the following: - Downstream object identifier; the downstream object identifier contains precursor information indicating one or more properties of the precursor material, - At least one desired downstream performance parameter that is related to the chemical product; - Downstream historical data; wherein this downstream historical data includes downstream process parameters and / or operating settings used to manufacture one or more chemical products in the past; and wherein - This set of downstream control settings can be used to manufacture the chemical product at the downstream industrial plant.

[0160] From another perspective, a computer program containing instructions, when executed by a suitable computing unit, can also be provided to cause the computing unit to perform any of the methods disclosed herein. A non-transitory computer-readable medium storing a program that causes a suitable computing unit to perform any of the method steps disclosed herein can also be provided.

[0161] For example, a computer program or a non-transitory computer-readable medium storing the program may be provided, comprising instructions that, when executed by a suitable computing unit, are operatively coupled to at least one apparatus for manufacturing a chemical product at a downstream industrial plant by processing at least one precursor material using a downstream manufacturing process, such that the computing unit: - A set of downstream control setpoints for controlling the production of the chemical product is provided at the downstream computing unit, wherein these downstream control setpoints are determined based on the following: - Downstream object identifier; the downstream object identifier contains precursor information indicating one or more properties of the precursor material, - At least one desired downstream performance parameter that is related to the chemical product; - Downstream historical data; wherein this downstream historical data includes downstream process parameters and / or operating settings used to manufacture one or more chemical products in the past; and wherein - This set of downstream control settings can be used to manufacture the chemical product at the downstream industrial plant.

[0162] It should be understood that the set of downstream control setpoints is suitable for manufacturing chemical products at downstream industrial plants.

[0163] Computer-readable data media or carriers include any suitable data storage device on which one or more instruction sets (e.g., software) embodying any one or more of the methods or functions described herein are stored. Instructions may also reside wholly or at least partially in main memory and / or processor during their execution by computing units, main memory, and processing devices, which may constitute computer-readable storage media. These instructions may further be transmitted or received over a network via a network interface device.

[0164] Computer programs used to implement one or more of the specific examples described herein may be stored and / or distributed on suitable media, such as optical storage media or solid-state media supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems. However, computer programs may also be presented on a network such as the World Wide Web and downloaded from such a network to the working memory of a data processor.

[0165] In addition, a data carrier or data storage medium may be provided for making a computer program product available for download, the computer program product being configured to perform any of the methods disclosed herein.

[0166] From another perspective, a computing unit may also be provided, which includes computer program code for performing the methods disclosed herein. Furthermore, a computing unit operatively coupled to memory storage may be provided, which includes computer program code for performing the methods disclosed herein.

[0167] It will be clear to those skilled in the art that two or more components are operatively coupled or connected. In a non-limiting manner, this means that at least a communication connection may exist between the coupled or connected components, for example, via an interface or any other suitable interface. The communication connection may be fixed or removable. Furthermore, the communication connection may be unidirectional or bidirectional. Additionally, the communication connection may be wired and / or wireless. In some cases, the communication connection may also be used to provide control signals.

[0168] In this context, "parameter" refers to any relevant physical or chemical property and / or its measure, such as temperature, orientation, location, quantity, density, weight, color, moisture content, velocity, acceleration, rate of change, pressure, force, distance, pH, concentration, and composition. A parameter can also refer to the presence or absence of a particular property.

[0169] "Actuator" means any component responsible for the direct or indirect movement and control of mechanisms associated with equipment such as machinery. An actuator can be a valve, motor, drive, or the like. An actuator can be operated electrically, hydraulically, pneumatically, or in combination thereof.

[0170] "Computer processor" refers to any logic circuit system configured to perform basic operations of a computer or system, and / or generally refers to a device configured to perform calculations or logical operations. Specifically, a processing component or computer processor can be configured to process basic instructions that drive a computer or system. As an embodiment, a processing component or computer processor may include: at least one arithmetic logic unit (ALU); at least one floating-point unit (FPU), such as a mathematical coprocessor or a numerical coprocessor; a plurality of temporary registers, specifically configured to supply operands to the ALU and store operation results; and memory, such as L1 and L2 cache. Specifically, a processing component or computer processor may be a multi-core processor. Specifically, a processing component or computer processor may be or may include a central processing unit (CPU). The processing component or computer processor may be a Complex Instruction Set Computing (CISC) microprocessor, a Reduced Instruction Set Computing (RISC) microprocessor, a Very Long Instruction Word (VLIW) microprocessor, or a processor implementing other instruction sets or combinations of instruction sets. The processing component may also be one or more special-purpose processing devices, such as Application-Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), Complex Programmable Logic Devices (CPLDs), Digital Signal Processors (DSPs), network processors, or the like. The methods, systems, and apparatus described herein may be implemented as software in a DSP, a microcontroller, or any other side processor, or as hardware within an ASIC, CPLD, or FPGA. It should be understood that the term processing component or processor may also refer to one or more processing devices, such as distributed systems of processing devices located across multiple computer systems (e.g., cloud computing), and unless otherwise specified, is not limited to a single device.

[0171] "Computer-readable data media" or carriers include any suitable data storage device or computer-readable memory that stores one or more instruction sets (e.g., software) embodying any one or more of the methods or functions described herein. The instructions may also reside wholly or at least partially in the main memory and / or processor during execution by a computing unit, main memory, and processing device, which may constitute a computer-readable storage medium. The instructions may further be transmitted or received over a network via a network interface device. Simple Explanation of the Diagram

[0172] Certain aspects of this teaching will now be discussed with reference to the following diagrams, which illustrate these aspects through embodiments. Since the generality of this teaching does not depend on them, the diagrams may not be to scale. Some features shown in the diagrams may be logical features presented together with physical features for the sake of understanding and without affecting the generality of this teaching. For easy identification of any particular element or action, one or more of the most significant digits of the element symbol refer to the drawing number that first introduces the element. [Figure 1] illustrates some of the states of the system according to this teaching. [Figure 2] illustrates the method and posture according to this teaching. [Figure 3] A first concrete example of the system and corresponding method according to this teaching is shown by means of a combination of blocks / flowcharts. [Figure 4] A second concrete example of the system and corresponding method according to this teaching is shown by means of a combination of blocks / flowcharts. [Figure 5] A third concrete example of the system and corresponding method according to this teaching is shown by means of a combination of blocks / flowcharts. [Figure 6] illustrates a first concrete example of a graph-based database configuration representing the topology of an industrial plant or cluster of plants, comprising a plurality of equipment units and corresponding plurality of equipment areas, wherein input materials move between these plurality of equipment areas during the manufacturing or production process. [Figure 7] shows a second specific example of a graph-based database configuration as shown in Figure 6. [Figure 8] This figure illustrates another concrete example of a system and corresponding method based on this teaching using a cloud computing platform, with the help of a combination of blocks / flowcharts, in which the machine learning (ML) process is implemented in the cloud. Implementation

[0173] Figure 1 illustrates an embodiment of a system 168 for controlling a downstream production process in which chemical product 170 is manufactured at a downstream industrial plant. At least some of the method embodiments will also be understood from the following discussion. The downstream industrial plant includes at least one downstream facility, which may have multiple equipment areas for manufacturing or producing chemical product 170 using the downstream production process. Chemical product 170 can be in any form, such as a pharmaceutical product, foam, nutritional product, or agricultural product. For example, chemical product 170 can be footwear, such as shoes containing a sole made of ETPU. Therefore, ETPU can be a precursor material 114 used in the production of footwear.

[0174] Precursor material 114 can be supplied from an upstream industrial plant, which can be isolated from the downstream industrial plant. Precursor material 114 can be manufactured at the upstream industrial plant using at least one input material. For example, the input material can be methylene diphenyl diisocyanate ("MDI") and / or polytetrahydrofuran ("PTHF"), used in the upstream production process at the upstream industrial plant producing TPU and / or ETPU materials, which are then supplied to or provided to the downstream industrial plant to produce chemical product 170.

[0175] Precursor material 114 can even be packaged in batches, for example, 10 kg each. As discussed, due to the nature of such products, such as precursor material 114 or even the materials that make precursor material 114, or the materials or products that are converted from precursor material 114 using downstream manufacturing processes, such materials and / or products may be difficult to trace in the production chain. However, it can be important to ensure that each component (e.g., each unit or package) or even an internal part has consistent and desired properties or quality. This teaching enables the production of chemical product 170 to achieve one or more desired downstream performance parameters.

[0176] Downstream equipment may or may not have multiple equipment zones. In this embodiment, the downstream equipment in FIG1 can be considered to include multiple zones. For example, a hopper or mixing furnace 104 may be part of the initial downstream equipment zone. The mixing furnace 104 receives at least one precursor material 114, which may be a single material or may contain multiple components. In this embodiment, the precursor material 114 is received in two parts, shown as being supplied to the mixing furnace 104 via a first valve 112a and a second valve 112b, respectively. The first valve 112a and the second valve 112b may also belong to the initial downstream equipment zone.

[0177] An object identifier is provided for precursor material 114, or in this case, a downstream object identifier 122. The downstream object identifier 122 may be provided at a downstream computing unit 124. The downstream computing unit 124 may, for example, provide the downstream object identifier 122 to a downstream memory storage 128 via a downstream interface. As discussed, in some cases, the downstream object identifier 122 may be provided to the downstream computing unit 124 by an upstream computing unit, for example, via a shared memory storage. In some cases, the downstream memory storage 128 may be a shared memory storage accessible via an upstream computing unit. The upstream computing unit may be a computing unit belonging to an upstream industrial plant. The downstream object identifier 122 contains data related to the precursor material 114, or precursor data. The precursor data indicates one or more properties of the precursor material 114.

[0178] Downstream object identifier 122, or more specifically, data from downstream object identifier 122, can be used to determine a set of downstream control setpoints for controlling the production of chemical product 170. Downstream object identifier 122, at least one desired downstream performance parameter associated with chemical product 170, and downstream historical data can be used to provide the set of downstream control setpoints. The set of downstream control setpoints can be determined at least partially by the upstream computing unit and / or at least some of the downstream control setpoints can be determined by the downstream computing unit 124. The downstream historical data includes downstream process parameters and / or operating setpoints used for manufacturing one or more past chemical products via downstream equipment. The set of downstream control setpoints is then used to manufacture chemical product 170 with the goal of achieving at least one desired downstream performance parameter. The desired downstream performance parameter is related to the desired performance or quality of chemical product 170.

[0179] For example, at least some of the control setpoints can determine how the first valve 112a and / or the second valve 112b should be operated, such as how much material should be allowed and at what ratio. They can even determine how the mixing furnace 104 should operate, such as the mixing duration and / or the mixer speed. Alternatively, the control setpoints can determine and control what values ​​and for how long specific process parameters need to be, such as equipment operating conditions, like setpoints. Therefore, the control setpoints are automatically determined based on the details of the precursor material 114 and the equipment. It should be understood that the set of downstream control setpoints may include control setpoints for the initial downstream equipment area, i.e., area-specific control setpoints, and similarly include area-specific control setpoints for any other equipment area (if they exist). In some cases, the set of downstream control setpoints may include global control setpoints, i.e., setpoints applicable to the entire production chain. Alternatively, even within the equipment area, at least some of the area-specific control setpoints can be adapted in operation based on real-time process data from the equipment area, for example, in response to the output of one or more ML models trained using downstream historical data. The control setpoints can be provided to a plant control system such as a DCS and / or PLC for controlling downstream equipment. Preferably, the setpoints are provided to the control system automatically; however, in some cases, these setpoints can be provided by the operator.

[0180] The downstream object identifier 122 may be a unique identifier, preferably a globally unique identifier (“GUID”), which distinguishes it from other object identifiers. The GUID may be provided depending on the details of a specific industrial plant and / or the details of the chemical product 170 being manufactured and / or the details of the date and time and / or the details of the specific precursor material 114 being used. The downstream object identifier 122 is shown here as being provided at a downstream memory storage 128 operatively coupled to a downstream computing unit 124. The downstream memory storage 128 may even be part of the downstream computing unit 124. The downstream memory storage 128 and / or the downstream computing unit 124 may be at least partially part of a cloud service, such as MS Azure.

[0181] Downstream computing unit 124 is operatively coupled to downstream equipment, for example, via downstream network 138, which can be any suitable type of data transmission medium. Downstream computing unit 124 may even be part of the downstream equipment, for example, it may be at least partially part of the initial downstream equipment area. Downstream computing unit 124 may even be at least partially part of the factory control system of a downstream industrial plant. Downstream computing unit 124 may receive one or more signals from one or more sensors operatively coupled to the downstream equipment, such as sensors in the initial downstream equipment area. For example, downstream computing unit 124 may receive one or more signals from fill sensor 144 and / or one or more sensors associated with conveying elements 102a to 102b. These sensors are also part of the initial downstream equipment area. Downstream computing unit 124 can therefore control the initial downstream equipment area or parts thereof, at least partially, according to control settings as previously explained. For example, downstream computing unit 124 may control valves 112a, 112b, for instance, via its respective actuators and / or heaters 118 and / or conveying elements 102a to 102b. Conveying elements 102a, 102b, and others in the embodiment of FIG1, are shown as a conveyor system, which may include one or more motors and a belt driven by those motors, such that its movement conveys the precursor material 114 of the belt in the direction of the belt's transverse plane 120.

[0182] Without affecting the scope or generality of this teaching, other types of conveying elements may be used in place of or in combination with conveyor systems. In some cases, any kind of equipment involving the flow of material (e.g., the entry and exit of one or more materials) may be called a conveying element. Therefore, in addition to conveyor systems or belts, equipment such as extruders, granulators, heat exchangers, buffer silos, silos with mixers, mixers, mixing vessels, shear mills, double cone blenders, solidification tubes, towers, separators, extractors, thin-film vaporizers, filters, and sieves may also be called conveying elements. Therefore, it should be understood that the presence of a conveying system as a conveyor system may be optional, at least because in some cases, material may move directly from one device to another by mass flow rate, or by normal flow rate. For example, material may move directly from a heat exchanger to a separator or even further to a tower, etc. Therefore, in some cases, one or more conveying elements or systems may be inherent to the equipment.

[0183] In some cases, the downstream object identifier 122 may be provided in response to a trigger signal or event, which may be a signal or event related to the amount of precursor material 114. For example, the fill sensor 144 may be used to detect at least one quantity, such as the fill level and / or weight of the precursor material 114. When the quantity reaches a predetermined threshold, the downstream computing unit 124 may automatically provide the downstream object identifier 122 at the downstream memory storage 128.

[0184] Downstream computing unit 124 is then configured to determine a set of process and / or operating parameters based on downstream object identifier 122 and at least one desired performance parameter. Downstream computing unit 124 can thus determine zone-specific control settings for each of the equipment areas based on the determined set of process and / or operating parameters and historical data. Historical data includes information from one or more historical upstream object identifiers associated with previously processed input materials in the upstream equipment area, and each historical upstream object identifier is accompanied by at least a portion of process data indicating the process parameters and / or equipment operating conditions under which the previously processed input material was processed in the upstream equipment area. Zone-specific control settings are then provided for controlling the production process of chemical product 170. Zone-specific control settings may be provided via an output interface (which may be the same as the interface) or different components. Zone-specific control settings are thus used by downstream computing unit 124 and / or the plant control system to manufacture chemical product 170.

[0185] In some cases, the downstream computing unit 124 may receive process data from all equipment or equipment areas in the industrial plant. The downstream computing unit 124 may determine a subset of the real-time process data based on upstream object identifiers and area presence signals. For example, trigger signals or events may also be used to generate area presence signals for upstream equipment areas. Alternatively or concurrently, area presence signals are provided by mapping real-time process data, which is time-dependent data in the production environment, to spatial data. Area presence signals can therefore be used not only to determine process parameters and / or equipment operating conditions related to the processing of precursor material 114 in the upstream equipment area, but also to determine the temporal state of those process parameters and / or equipment operating conditions, which are included in the real-time process data.

[0186] In some cases, downstream calculation unit 124 may even calculate at least one downstream performance parameter associated with chemical product 170, which is associated with downstream item identifier 122. In some cases, the downstream performance parameter may even be a region-specific parameter. The calculation is based on a subset of downstream real-time process data 126, which in this case is shown as appended to downstream item identifier 122 as appropriate. The calculation of the downstream performance parameter is also based on downstream historical data, which may include data from one or more historical downstream item identifiers. Each historical downstream item identifier is associated with a particular precursor material previously processed in the downstream equipment area. Each historical downstream item identifier is accompanied by at least a portion of downstream process data indicating the downstream process parameters and / or equipment operating conditions under which the previously processed precursor material was processed in the downstream equipment area. In some cases, at least some of the historical downstream item identifiers may also include or be accompanied by their associated downstream performance parameters.

[0187] At least one downstream performance parameter can be appended as post-data to the downstream object identifier 122, for example. Therefore, the downstream object identifier 122 is enriched with performance parameters related to the quality of the chemical product 170. The quality control process can thus be simplified and improved, for example, by coupling quality-related data with the resulting chemical product 170, while simultaneously improving traceability. Furthermore, at least the calculated downstream performance parameters can be used in other downstream areas to adapt the downstream production process. The downstream production process can thus become more granularly controlled and flexible while maintaining the performance of the chemical product 170.

[0188] A subset of the downstream real-time process data 126 from the downstream equipment area can be data within the time window during which the precursor material 114 is in the initial downstream equipment area, or the time window can be even shorter, precisely during the time that the precursor material 114 is processed by the mixing furnace 104. The downstream real-time process data can be used to determine the time window. Therefore, the downstream object identifier 122 can be enriched with highly relevant data using the time dimension of the downstream real-time process data. Thus, the object identifier can not only be used to track materials in the production process but also encapsulate high-quality data that enables more efficient edge computing and / or cloud computing. Object identifier data is highly suitable for faster training and retraining of machine learning models. Data integration is also simplified because the data encapsulated in the object identifier can be more compact than traditional datasets.

[0189] At least a subset of the downstream real-time process data 126 indicates process parameters and / or equipment operating conditions under which the precursor or precursor material 114 is processed in the downstream equipment area, i.e., the operating conditions of the mixing furnace 104 and valves 112a to 112b, such as any one or more of the following: inlet mass flow rate, outlet mass flow rate, fill level, temperature, moisture content, timestamp or entry time, exit time, etc. In this case, the equipment operating conditions may be control signals and / or setpoints of valves 112a, 112b and / or mixing furnace 104. For example, downstream control setpoints may be used to control these operating conditions. The subset of the downstream real-time process data 126 may be or may include time-series data, meaning that it may include time-dependent signals that can be obtained via one or more sensors (e.g., the output of fill sensor 144). The time-series data may include continuous signals or signals that may be interrupted at regular or irregular time intervals. A subset of downstream just-in-time process data 126 may even include timestamps from one or more of the mixing furnace 104, such as entry and / or exit times. Therefore, a specific precursor material 114 can be associated with a subset of the downstream just-in-time process data 126 related to the precursor material 114 via a downstream object identifier 122. The downstream object identifier 122 can be attached to other object identifiers downstream of the production process, allowing specific process data and / or equipment operating conditions to be associated with specific chemical products. Other important benefits have been discussed in other parts of this disclosure, such as in the overview section.

[0190] For example, a conveyor system including conveyor elements 102a, 102b and associated belts can be considered as an intermediate equipment area downstream of the downstream equipment area. In this embodiment, the intermediate equipment area includes a heater 118 for applying heat to the precursor material traversing the belt. The conveyor system may even include one or more sensors, such as speed sensors, weight sensors, temperature sensors, or any other type of sensor for measuring or detecting process parameters and / or properties of the precursor material 114 at the intermediate equipment area. Any or all outputs of the sensors may be provided to the downstream computing unit 124.

[0191] As the precursor material 114 advances along the transverse plane 120, it is heated by the heater 118. The heater 118 may be operatively coupled to a downstream computing unit 124, i.e., the downstream computing unit 124 may receive signals or real-time process data from the heater 118. Furthermore, the heater 118 may be controlled by the downstream computing unit 124, for example, via one or more control signals and / or setpoints that can be set to or obtained from downstream control setpoints. Thus, the manner in which the precursor material 114 is processed at the downstream equipment is determined by at least some of the downstream control setpoints. Some of the downstream control setpoints may be used to control other downstream regions, as will be explained further.

[0192] Similarly, the conveyor system including conveyor elements 102a, 102b and associated belts can also be operatively coupled to a downstream computing unit 124, that is, the downstream computing unit 124 can receive signals or a portion of downstream process data from the conveyor elements 102a, 102b. Coupling can be, for example, via a downstream network 138. Furthermore, the conveyor elements 102a, 102b can even be controlled as downstream control setpoints or in response to downstream control setpoints via the downstream computing unit 124 (e.g., via one or more control signals and / or setpoints provided by the downstream computing unit 124). Therefore, the speeds of the conveyor elements 102a, 102b can be observed and / or controlled by the downstream computing unit 124.

[0193] Depending on the circumstances, since the amount of precursor material 114 in the intermediate equipment zone is constant or nearly constant, it is not necessary to provide additional object identifiers for the intermediate equipment zone. Therefore, process data from the intermediate equipment zone, i.e., from heater 118 and / or conveyor elements 102a, 102b, can also be attached to the object identifiers of the preceding or preceding zones, i.e., the downstream object identifier 122. The subset of the attached downstream real-time process data 126 can thus be enriched to further indicate the process parameters and / or equipment operating conditions of the precursor material 114 processed below it in the intermediate equipment zone, i.e., the operating conditions of heater 118 and / or conveyor elements 102a, 102b, such as incoming mass flow rate, outgoing mass flow rate, one or more temperature values ​​from the intermediate zone, entry time, exit time, and any one or more of the speeds of conveyor elements 102a, 102b and / or belts. In this case, the equipment operating conditions can be the control signals and / or setpoints of the conveying elements 102a, 102b and / or heater 118 that can be derived from the downstream control setpoints.

[0194] It will be apparent that a subset of the downstream real-time process data 126 is significantly related to the time period during which the precursor material 114 is present in each of the respective equipment areas. Therefore, an accurate snapshot of the relevant process data for a specific precursor material 114 can be provided via the downstream object identifier 122. Further observability of the precursor material 114 can be extracted via knowledge of specific parts or components (e.g., chemical reactions) of the downstream production process within the intermediate equipment area. Alternatively or additionally, the speed at which the precursor material 114 traverses the intermediate equipment area can be used to extract further observability via the downstream computing unit 124. By combining a subset or time-series of the downstream real-time process data 126 with specific timestamps and / or the entry and / or exit times of the precursor material 114 in the intermediate equipment area, more granular details of the conditions under which the precursor material 114 is processed within the intermediate equipment area can be obtained from the downstream object identifier 122.

[0195] Data from downstream object identifier 122 can be used to train one or more downstream ML models to monitor and / or control downstream production processes as a whole and / or specific parts thereof (e.g., portions of downstream production processes within the initial downstream equipment area and / or intermediate equipment area). The downstream ML models and / or downstream object identifier 122 can even be used to correlate one or more downstream performance parameters of a chemical product with details of downstream production processes within one or more areas.

[0196] It should be understood that as the precursor material 114 moves along the transverse plane 120, its properties can change and it can be transformed or converted into the derivative material 116. For example, when the heater 118 heats the precursor material 114, it can produce the derivative material 116. Those skilled in the art will understand that, for simplicity and ease of understanding, the derivative material 116 may sometimes also be referred to as the precursor in this teaching. For example, in the case of the equipment area or component discussed below, it will thus be apparent that the precursor plays a role in the downstream production process described in the description of such embodiments.

[0197] An embodiment of a material divided into multiple sections is now discussed. Figure 1 shows this section as an additional downstream equipment section including a shear mill 142 and second conveying elements 106a, 106b. The derivative material 116, which traverses along the transverse plane 154, is divided or segmented using the shear mill 142, thus producing multiple sections, shown in this embodiment as a first divided material 140a and a second divided material 140b.

[0198] Therefore, according to one aspect of this teaching, an individual object identifier can be provided for each part. However, in some cases, an object identifier may be provided only for one or some of the parts, rather than an individual object identifier for each part. For example, this may be the case if there is no interest in any of the tracking parts. For example, an object identifier may not be provided for the discarded part of derivative material 116. Referring now back to FIG1, a first additional downstream object identifier 130a is provided for the first divided material 140a and a second additional downstream object identifier 130b is provided for the second divided material 140b.

[0199] The first additional downstream object identifier 130a includes at least a portion of the downstream object identifier 122, and similarly, the second additional downstream object identifier 130b includes at least a portion of the downstream object identifier 122. The downstream calculation unit 124 may then determine another subset of downstream real-time process data (e.g., the first subset of downstream real-time process data 132a and / or the second subset of downstream real-time process data 132b) based on the additional downstream object identifiers and the area presence signal. The downstream calculation unit 124 may then determine additional area-specific control settings for the downstream equipment area and, where appropriate, for other equipment areas downstream of that downstream equipment area, based on data from the downstream object identifier 122, another subset of the real-time process data, and downstream historical data from one or more historical downstream object identifiers associated with previously processed precursors in the additional downstream equipment area.

[0200] The first additional downstream object identifier 130a may be supplemented with a first subset of downstream real-time process data 132a, and the second additional downstream object identifier 130b may be supplemented with a second subset of downstream real-time process data 132b. The first subset of downstream real-time process data 132a may be a copy of the second subset of downstream real-time process data 132b, or may be partially the same data. For example, if the first divided material 140a and the second divided material 140b undergo the same process (i.e., in substantially the same location and time), the process data supplemented to the additional downstream object identifier 130a and the second additional downstream object identifier 130b may be the same or similar. However, if the additional downstream object identifier 130a and the second additional downstream object identifier 130b are processed differently in the additional downstream equipment area, the first subset of downstream real-time process data 132a and the second subset of downstream real-time process data 132b may be different from each other.

[0201] However, those skilled in the art will understand that in some cases, only one object identifier may be provided at the shear mill 142, and multiple object identifiers may be provided after the shear mill 142 if the material processed by the shear mill 142 is divided into multiple parts. Therefore, depending on the details of a particular downstream production process, the shear mill may or may not be a separating device. Similarly, in some cases, no new object identifier can be provided for the shear mill so that process data from the zone is appended to the previous object identifier. New object identifiers may therefore be provided at the zone where the material is divided and / or combined. For example, in some cases, additional downstream object identifiers 130a and a second additional downstream object identifier 130b may be provided after the shear mill 142, for example, at different zones after entering the shear mill 142.

[0202] In this embodiment, the additional downstream device area also includes an imaging sensor 146, which may be a camera or any other type of optical sensor. The imaging sensor 146 may also be operatively coupled to the downstream computing unit 124. The imaging sensor 146 can be used to measure or detect one or more properties of the derivative material 116 before it enters the additional downstream device area. This can be done, for example, to reject or divert material that does not meet a given quality criterion. Because the mass flow rate of the material changes in the additional downstream device area, according to one aspect of this teaching, another object identifier (not shown in FIG. 1) may have been provided before the additional downstream object identifier 130a and the second additional downstream object identifier 130b.

[0203] Additional downstream object identifiers 130a and 130b are provided in response to the derivative material 116 being triggered via imaging sensor 146 through quality criteria. By correlating data from neighboring regions or from object identifiers (e.g., mass flow rate from intermediate equipment regions and mass flow rate to downstream equipment regions), downstream computing unit 124 can determine which specific precursor material 114 or derivative material 116 is associated with the material entering the subsequent region. Alternatively or additionally, two or more timestamps can be correlated between these regions, for example, a departure timestamp from an intermediate equipment region and an entry timestamp detected via imaging sensor 146 and / or at another downstream equipment region. The speed of the transport elements 102a, 102b, directly measured via sensor output or determined from two or more timestamps, can also be used to establish a relationship between a specific package or batch of the precursor and its object identifier. Therefore, it is even possible to determine the location of a specific chemical product 170 within the production process at a given time, thus establishing a time-space relationship. Some or all of these samples can not only be used to improve the traceability of chemical product 170 from precursor to finished product, but also to monitor and improve the production process, making it more adjustable and controllable.

[0204] As discussed, the first additional downstream object identifier 130a and the second additional downstream object identifier 130b are respectively attached with a first subset of downstream real-time process data 132a and a second subset of downstream real-time process data 132b from the additional downstream equipment area. The first subset of downstream real-time process data 132a and the second subset of downstream real-time process data 132b may even be linked to or attached to the downstream object identifier 122. Similar to the previously discussed downstream object identifier 122, the first subset of downstream real-time process data 132a and the second subset of downstream real-time process data 132b indicate the downstream process parameters and / or equipment operating conditions under which the derivative material 116 is processed in the additional downstream equipment area, namely the output of the imaging sensor 146, the operating conditions of the shear mill 142 and the second conveying elements 106a, 106b, such as any one or more of the following: incoming mass flow rate, outgoing mass flow rate, fill factor, temperature, optical properties, timestamp, etc. In this case, the equipment operating conditions can be the control signals and / or setpoints of the shear mill 142 and / or the second conveying elements 106a, 106b, which can be derived from additional downstream control settings. Furthermore, the zone-specific control settings can therefore be optimized based on data from the downstream object identifier 122 (e.g., at least one zone-specific performance parameter attached to the downstream object identifier 122).

[0205] The first subset of downstream real-time process data 132a and the second subset of downstream real-time process data 132b may contain time-series data, meaning that they may include time-dependent signals that can be obtained via one or more sensors (e.g., the output of imaging sensor 146 and / or the speed of the second delivery elements 106a, 106b).

[0206] As the derivative material 116 continues after encountering the imaging sensor 146, it moves toward the shear mill 142 in the direction of the transverse plane 154 driven by the second conveyor elements 106a, 106b. In this embodiment, the second conveyor elements 106a, 106b are shown as part of a second conveyor system separate from the conveyor system containing the conveyor elements 102a, 102b. It should be understood that the second conveyor system may even be part of the same conveyor system containing the conveyor elements 102a, 102b. Therefore, a separate downstream equipment area may include some of the same equipment used in another area.

[0207] As can be seen in Figure 1, although the first divided material 140a and the second divided material 140b are used in different ways in production later, their individual object identifiers (i.e., additional downstream object identifiers 130a and second additional downstream object identifiers 130b) are allowed to follow or track the downstream object identifiers 130a and second additional downstream object identifiers 130b individually through the remaining production process and in some cases beyond the remaining production process.

[0208] After leaving the downstream equipment area, the first divided material 140a is fed into the extruder 150, while the second divided material 140b is conveyed for curing in a third equipment area comprising the curing device 162 and third conveying elements 108a, 108b. The conveying elements 108a, 108b shown are therefore non-limiting embodiments, as previously discussed. It should be understood that the third equipment area is downstream of the initial downstream equipment area and other downstream equipment areas.

[0209] As the second diced material 140b moves along the belt in the direction of the transverse plane 156, it undergoes a curing process via the curing equipment 162 to produce a cured second diced material 160. Since no substantial quality change can occur, no new object identifier can be provided for the third equipment zone, as is previously discussed. Therefore, process data from the third equipment zone can also be attached to a second additional downstream object identifier 130b. Similar to the above, a second subset of the attached downstream real-time process data 132b can thus be enriched to further indicate the process parameters and / or equipment operating conditions of the second diced material 140b processed below it in the third equipment zone, i.e., the operating conditions of the curing equipment 162 and / or the conveyor elements 108a, 108b, such as incoming mass flow rate, outgoing mass flow rate, one or more temperature values ​​from the third zone, entry time, exit time, and any one or more of the speeds of the conveyor elements 108a, 108b and / or the belt. In this case, the equipment operating conditions can be the control signals and / or setpoints of the delivery elements 102a, 102b and / or the curing device 162, which can also be derived from other zone-specific control settings. These other zone-specific control settings can therefore be optimized based on data from the downstream object identifier 122 (e.g., at least one zone-specific performance parameter attached to the downstream object identifier 122).

[0210] Similarly, the first segmented material 140a advances to the fourth equipment area, which includes the extruder 150, temperature sensor 148, and fourth conveying elements 110a and 110b. Here, as no substantial quality change can occur, no new object identifier is provided for the fourth equipment area, as is generally true. Therefore, as previously discussed, process data from the fourth equipment area can also be attached to another downstream object identifier 130a. Similar to the above, the first subset of the additional downstream real-time process data 132a can therefore be enriched to further indicate the process parameters and / or equipment operating conditions of the first segmented material 140a processed below it in the third equipment zone from the fourth equipment zone, i.e., the operating conditions of the extruder 150 and / or temperature sensor 148 and / or conveyor elements 108a, 108b, such as incoming mass flow rate, outgoing mass flow rate, one or more temperature values ​​from the third zone, entry time, exit time, speed of conveyor elements 110a, 110b and / or belt, etc. In this case, the equipment operating conditions can be the control signals and / or setpoints of the conveyor elements 108a, 108b and / or extruder 150, which can also be adjusted as previously explained based on the calculated performance parameters and related real-time process data.

[0211] Furthermore, the properties and dependencies of the transformation from the first divided material 140a to the extruded material 152 can also be included in the additional downstream object identifier 130a. It should be understood that the fourth equipment area is also downstream of the downstream equipment area and the additional downstream equipment area.

[0212] As can be understood, the number of individual object identifiers can be reduced, while material and product monitoring can be improved throughout the production process.

[0213] As the extruded material 152 moves further along the transverse plane 158 created by the conveying elements 108a, 108b, the extruded material can be collected in a collection area 166. The collection area 166 can be a storage unit, or it can be an additional processing unit for further steps in downstream production processes. Additional material can be combined in the collection area 166; for example, as shown here, a cured second segmented material 160 can be combined with the extruded material 152. Thus, a new object identifier can be provided as previously discussed. This object identifier is shown as the final downstream object identifier 134. The final downstream object identifier 134 can be supplemented with a subset of the final zone real-time process data 136, which may include all or part of the additional downstream object identifiers 130a and 130b. The final downstream object identifier 134 therefore possesses process parameters and / or equipment operating conditions from the collection area 166, similar to those described in detail in this disclosure. Depending on the function or additional processing (if any function or additional processing is performed in the collection area 166), it may include data such as any one or more of the following as the final area real-time process data 136: incoming mass flow rate, outgoing mass flow rate, one or more temperature values ​​from the collection area 166, entry time, exit time, speed, etc.

[0214] In some cases, individual batches may be sent from collection area 166 for storage and / or sorting and / or packaging. This individual batch is shown as product collection bin 164a. Because the quantity is further divided, individual item identifiers can be provided for each silo, so that the chemical product 170 in that silo (i.e., the individual item identifier for product collection bin 164a) can be associated with the process data or conditions of the place where the chemical product 170 is exposed.

[0215] As will be understood, each of the object identifiers may be a GUID. Each may include whole or part of information from previous object identifiers, or may be linked. Related quality information may thus be attached to a specific chemical product 170 as a snapshot or traceability link.

[0216] As also discussed, one or more downstream ML models can be used to calculate or predict one or more downstream performance parameters and / or downstream control setpoints, any one or both of which may be region-specific. It is also possible that each or some of the downstream ML models are configured to provide a confidence value indicating the confidence level of at least one downstream performance parameter and / or downstream control setpoint. If the confidence level of the predicted downstream performance parameter is lower than a predetermined limit, a warning can be generated as a warning signal, for example, by performing laboratory analysis using physical testing of the initial sample. It is also possible to automatically provide a sample object identifier via an interface in response to the predicted confidence level falling below an accuracy threshold. A sample object identifier can be provided in a similar manner, and the downstream calculation unit 124 can attach a subset of relevant downstream process data to the sample object identifier for the material associated with the sample object identifier, shown here as sample material 172. The downstream calculation unit 124 can also attach at least one region-specific performance parameter with a low confidence level to the sample object identifier. Sample material 172 can therefore be collected, inspected, and / or analyzed to further improve quality control using object identifiers.

[0217] Figure 2 illustrates a flowchart 200 or process route, particularly as observed from the initial downstream equipment area, representing the method of this teaching. In block 202, a set of downstream control settings for controlling the production of chemical product 170 is provided at the downstream computing unit 124. The downstream control settings are determined based on a downstream object identifier 122. The downstream object identifier 122 contains precursor information indicating one or more properties of the precursor material 114. The downstream control settings are also determined based on at least one desired downstream performance parameter associated with chemical product 170. The downstream control settings are also determined based on downstream historical data. The downstream historical data contains downstream process parameters and / or operating settings used for manufacturing one or more past chemical products via downstream equipment. The set of downstream control settings can be used to manufacture the chemical product at a downstream industrial plant. Where appropriate, in block 204, downstream real-time process data is received at the downstream computing unit 124 from one or more downstream equipment or equipment areas. The downstream real-time process data contains downstream real-time process parameters and / or equipment operating conditions. Alternatively, depending on the situation, in block 206, a subset of downstream real-time process data is determined by the downstream computing unit 124 based on the downstream object identifier and the downstream area presence signal. The downstream area presence signal indicates the presence of precursor material in a specific equipment area during the downstream production process.

[0218] Similarly, as the precursor progresses to the subsequent region, it can be determined whether another object identifier should be provided. If not, downstream process data from the subsequent region can also be attached to the same object identifier. If it is determined that another object identifier should be provided, then process data from the subsequent region is attached to the other object identifier. In this disclosure, for example in the overview section and with reference to Figure 1, each of these options, such as the details of intermediate equipment regions and additional downstream equipment regions, are discussed in detail.

[0219] The block diagram shown in Figure 3 represents a portion of the product manufacturing system of an industrial plant. In this specific example, these portions each include ten product processing devices or units 300 to 318 or technical equipment arranged along the entire product processing line shown. In this specific example, one of these processing units (processing unit 308) includes three corresponding equipment areas 320, 322, and 324 (see also more detailed examples in Figures 3 and 5).

[0220] In this embodiment, the chemical products used as input materials are produced based on raw materials supplied to the processing line via a liquid raw material storage tank 300, a solid raw material storage tank 302, and a recycling silo 304. The recycling silo recycles any chemical products or intermediate products, including, for example, those with insufficient material / product properties or insufficient material / product quality. The individual raw materials input to processing lines 306 to 318 are processed via individual processing equipment: a dispensing unit 306, a subsequent heating unit 308, a subsequent processing unit including a material buffer 310, and a subsequent sorting unit 312. Downstream of these processing equipment 306 to 312, a conveying unit 314 is configured to convey materials that need to be recycled from the sorting unit to the recycling silo 304, for example, due to insufficient quality of the produced materials. Finally, the materials sorted by the sorting unit 312 are transferred to the first packaging unit 316 and the second packaging unit 318, which package the corresponding materials into material containers for transportation purposes. These material containers are, for example, material packages in the case of bulk materials or bottles in the case of liquid materials.

[0221] In this specific example, production systems 300 to 318 provide a data interface for the computing unit (neither depicted in this block diagram), through which data objects containing information about individual input materials and changes attributable to processing are provided. The entire production process is at least partially controlled by the computing unit.

[0222] The input material being processed by processing units 306 to 312 is divided into physical or real-world so-called "packaged objects" (hereinafter also referred to as "physical packages" or "product packages"), wherein these packaged objects are disposed of or processed by each of processing units 306 to 312. The package size of such packaged objects may be fixed, for example, by the weight of the material (e.g., 10 kg, 50 kg, etc.) or by the amount of material (e.g., 1 decimeter, 1 / 10 cubic meter, etc.), or even determined by weight or amount, for which the processing equipment can provide significantly constant process parameters or equipment operating parameters.

[0223] The dispensing unit 306 first produces such packaged items from input liquid and / or solid raw materials and / or recycled materials supplied by the recycling silo 304. After producing the packaged items, the dispensing unit conveys these items to the homogenization unit 308. The homogenization unit 308 homogenizes the materials of the packaged items, that is, homogenizes, for example, liquid and solid materials or two liquid or solid materials. After a heating process, the heating unit 308 conveys the corresponding heated packaged items to the processing unit 310, which transforms the materials of the input packaged items into different physical and / or chemical states, for example, by heating, drying or humidifying or by a chemical reaction. The correspondingly transformed packaged items are then conveyed to one or more of the three downstream packaging units 316, 318 or the aforementioned conveying unit 314.

[0224] The subsequent processing of real-world packaged objects is managed by corresponding data objects 330, 332, and 334 (including or representing the previously described "downstream object identifiers"), which are assigned to each packaged object via computing units operatively coupled to or part of devices 306 to 312 and stored in memory storage elements of the computing units. According to this specific example, the three data objects 330 to 334 are generated in response to trigger signals provided via devices 306 to 312, i.e., in response to the outputs of corresponding sensors respectively configured at each of device units 306 to 312 or corresponding switches, wherein such sensors are operatively coupled to device units 306 to 312. As previously mentioned, industrial plants may include different types of sensors, such as sensors for measuring one or more process parameters and / or for measuring equipment operating conditions or parameters related to equipment or process units. In this specific example, sensors for measuring the flow rate and content of bulk and / or liquid materials processed inside equipment units 306 to 312 are disposed in these units.

[0225] In this specific example, the three exemplary data objects 330, 332, and 334 depicted in Figure 3 are each differently associated with the three equipment areas 320, 322, and 324 of the entire product manufacturing process based on processing units 306 to 312 and 314 to 318.

[0226] The first two data objects 330 and 332 contain product package objects containing process data. Process data includes information on the processing / treatment that the relevant physical package has undergone during its residence / processing within several processing units. Process data may be aggregated data, such as the calculated average temperature during the residence time of the underlying physical package within the relevant processing unit, and / or it may be time-series data of the underlying manufacturing process.

[0227] The first data object 330 is a first type of package (referred to as "Package A" in Figure 3), which in this specific example is assigned to a physical package that has been delivered by two processing units (Dispensing Unit 306 and Heating Unit 308). At the current point in the processing time, the first data object 330 includes relevant data from both units during each dwell period. The first data object includes a corresponding "Product Package ID".

[0228] Heating unit 308 contains several device areas, specifically three device areas 320, 322, and 324 ("Area 1", "Area 2", and "Area 3" in this embodiment). These different device areas are used as classification groups for categorizing or selecting relevant process data. This classification helps obtain information about the packaged object from the relevant device area, which is related to the processing of the underlying physical package at the corresponding point during the packaging of the relevant physical object within this device area. However, in this embodiment, the material composition of the physical package is not changed by processing units 306 and 308.

[0229] Once package A 330 has reached the next processing unit 310 (in this specific example, a "processing unit with a buffer"), the material composition of each physical package changes because this processing unit 310 not only delivers the physical packages in a plug flow pattern, but also includes a buffer volume larger than the initial package size, resulting in a defined degree of demixing for this type of physical package. Therefore, each physical package leaving this processing unit 310 is a different type of physical package, referred to as "package B" in Figure 3.

[0230] The corresponding second data object 332 ("B package") also includes a corresponding "product package ID". Data object 332 further includes data from a defined number of previous data objects. In this specific example, data object 330 is designated as "A package" by a defined percentage, the so-called "aggregated data from the relevant A package". The corresponding aggregation scheme or algorithm depends on, for example, the underlying processing unit, the size of the underlying physical package, the mixing capability of the underlying physical package materials, and the residence time of the underlying physical package within the underlying processing unit, or the corresponding device area of ​​the processing unit.

[0231] Once the processed entity (product) package is packaged into a discrete entity package by one of two packaging units 316, 318, such as by packaging the processed entity package into a container, roller, or octagonal container or the like, in this specific example, the corresponding packaged entity package is disposed of or tracked via another data object 334 referred to as the "entity package". This data object 334 includes related previous entity packages already packaged therein (such as "package A" and "package B" in this context). The designation of a "product package ID" is sufficient, for example, for tracking purposes, rather than using the complete data object, because such product package IDs can be easily linked together during later data processing (e.g., data processing performed by means of an external "cloud computing" platform).

[0232] The first data object (or "object identifier") 330 specifically includes the following information: - The "Product Package ID" used for underlying packaging; - General information about the underlying package, such as information or specifications regarding the materials used in the underlying package; - Current position of the underlying package within the entire processing line 306 to 318; - Process data, namely, the temperature and / or weight of the polymer of the processed material used as the underlying encapsulation; - Time series data of the underlying production process; and The connection to the sample from the underlying package, whereby the product package passes through a sampling station, and at a defined time, the operator obtains a sample from this product package and provides it to the laboratory. For this sample, a sample object (see Figure 6, reference symbols 634 and 638) will be generated and linked to the relevant product package (see Figure 6, reference symbols 626 and 630). This sample object specifically contains corresponding product quality control (QC) data from the laboratory and / or performance data from the corresponding testing equipment.

[0233] The second object identifier 332 also includes - Aggregated data from the relevant A package, which is generated in a processing unit with buffer 310.

[0234] The third item identifier 334 is generated by the two packaging units 316 and 318 using the specified timestamp "physical packaging 1976-02-06 19:12:21.123" and includes the following information: - Similarly, the corresponding package or object identifier ("package ID"); - The product name is packaged into two material containers for the shipping purpose depicted in Figure 3; - The order number for the product in the corresponding package; and The batch number of the product in the corresponding packaging.

[0235] The overall packaging information of the first object identifier 330 and the second object identifier 332 includes material information of the input raw material, which in this specific example indicates the chemical and / or physical properties (such as material temperature and / or weight) of the input material or processed material, and in this specific example also includes the aforementioned laboratory sample or test data related to the input material, such as historical test results.

[0236] According to the product manufacturing process illustrated in Figure 3, process data from the entire equipment is collected via the mentioned interface. This includes process parameters such as the temperature and / or weight of the processed materials, and in this specific example, it also indicates the operating conditions of the equipment under which the material is processed, such as the temperature of the heater and / or the applied dosing parameters. In this specific example, the collected process data is only a portion of the process data from the relevant A-package polymer data, which is appended to the second object identifier 332.

[0237] As previously described, in this specific example, three object identifiers 330 to 334 are used to associate or map the mentioned input material information and / or specific process parameters and / or equipment operating conditions to at least one performance parameter of the chemical product, which is respectively or respectively indicating any one or more properties of the underlying material (e.g., the corresponding chemical product).

[0238] According to the specific example shown in Figure 3, the collected process data (as aggregated values) included in the two object identifiers 330 and 332 contains values ​​indicating process parameters and additionally indicating equipment operating conditions measured during the production process. Furthermore, object identifiers 330 and 332 include process data provided as time-series data of one or more of the process parameters and / or equipment operating conditions. Equipment operating conditions can be, for example, any characteristic or value representing the state of the equipment based on vibration measurements; in this specific example, production machine setpoints, controller outputs, and any equipment-related warnings. Additionally, they may include conveyor speed, temperature, and fouling values, such as filter differential pressure and maintenance dates.

[0239] In a specific example of the product manufacturing system shown in Figure 3, the entire product handling equipment 306 to 318 comprises the aforementioned plurality of three equipment zones 320 to 324, such that during the production process, input raw materials 300 to 304 traverse the entire processing line 306 to 318, and in this specific example, proceed from the first equipment zone 320 to the second equipment zone 322 and from the second equipment zone 322 to the third equipment zone 324. In this production scenario, a first object identifier 330 is provided at the first equipment zone 320, while a second object identifier 332 is provided when the input material enters the second equipment zone 322 after being processed by the first equipment zone 320. The second object identifier 332 is accompanied by or includes at least a portion of the data or information provided by the first object identifier 330, and further includes the final data / information "aggregate data from the relevant A package".

[0240] It is worth noting that any or each of the object identifiers 330 to 334 may include a unique identifier, preferably a globally unique identifier (“GUID”), so as to allow the object identifier to be reliably and securely assigned to the corresponding package throughout the manufacturing process.

[0241] In this product processing scenario, the process data attached to the first object identifier 330 is at least a portion of the process data collected from the first equipment area 320. Therefore, the second object identifier 332 is attached with at least a portion of the process data collected from the second equipment area 322, wherein the process data collected from the second equipment area 322 indicates the process parameters and / or equipment operating conditions under which the input raw materials 300 to 304 are processed in the second equipment area 322.

[0242] Table 1 below again presents another exemplary object identifier in tabular format. This object identifier contains significantly more information / data than the three object identifiers 330 to 334 previously described.

[0243] This illustrative object identifier relates to a so-called "B package" with an underlying date and time stamp "1976-02-06 18:31:53.401", as described in Figure 4 below, but including more information than the B package included in Figure 4.

[0244] In this embodiment, the unique identifier ("Unique ID") contains a unique URL ("uniqueObjectURL"). In this embodiment, the key details of the underlying encapsulation ("Encapsulation Details") are the date and timestamp ("Generation Timestamp") of the encapsulation with two values, "02.02.1976 18:31:53.401", and the encapsulation type ("Encapsulation Type"). In this embodiment, the encapsulation type is "B". The current position of the encapsulation along the underlying production line ("Encapsulation Position") is defined by the "Encapsulation Position Link," which in this embodiment is the transport link to "Conveyor Belt 1" of the production line.

[0245] At conveyor belt 1, a measuring device (see “Measuring Point” including exemplary processed data or values) is provided to measure the average temperature (“Average”) of the corresponding description (“Description”) of the currently exposed material temperature of 85°C and the underlying temperature zone (“Temperature Zone 1” in this embodiment). Additionally, the measuring device may include sensors for detecting the entry date / time (“Entry Time”) of the package at conveyor belt 1, which in this embodiment is “02.02.1976 18:31:54.431”, and for detecting the departure date / time (“Departure Time”) of the package from conveyor belt 1, which in this embodiment is “02.02.1976 18:31:57.234”. Finally, the measuring device includes a sensor device for detecting time series values ​​(“Time Series Values”) of underlying time series information (“Time Series”) related to the production process.

[0246] In addition, in this embodiment, the object identifier further includes information about the downstream positioning "conveyor belt 2", the downstream positioning "mixer 1" and the downstream positioning "silo 1" for storing the processed material in the middle. - Package B, 1976-02-06 18:31:53.401 - Unique ID - Unique URL uniqueObjectUrl - Packaging details - Generate timestamp 02.02.1976 18:31:53.401 - Encapsulation type B - Package location - Encapsulated location link Conveyor Belt 1 - Conveyor Belt 1 - Measurement points - Average 85℃ - describe Temperature Zone 1 - Entry Time 02.02.1976 18:31:54.431 - Departure time 02.02.1976 18:31:57.234 - Time series Time series values - Conveyor Belt 2 - Mixer 1 - Silo 1 Table 1: Illustrative Table Object Identifiers

[0247] Figure 4 shows a second specific example of the process section of the underlying product manufacturing system of an industrial plant. In this second specific example, these process sections respectively include six product handling devices 400, 402, 406, 410, 412, 416 or technical equipment.

[0248] The "upstream process" 400 for processing packaged objects is connected to the "classification unit" 402 for classifying processed packaged objects. The upstream process 400 and the classification unit 402 are managed by means of a first data object 404. This data object 404 pertains to the described "B package," which has an underlying date and timestamp depicting the date and time of its creation: "1976-02-06 18:51:43.431." The data object 404 includes a "package ID" (so-called "object identifier") for the currently processed packaged object. The data object 404 further includes n pre-described chemical and / or physical properties of the currently processed packaged object, in this embodiment, "property 1" and "property n."

[0249] In this embodiment, the input material (i.e., the corresponding packaged object fed into the upstream process 400) is provided by the "recycling silo" 406. On the other hand, the recycling silo 406 receives bottom-layer recycled material from the "transport unit 1" 410 that transports the packaged objects to the recycling silo 406. These packaged objects must be recycled and sorted accordingly by the sorting unit 402. The bottom-layer transport process step 410 is managed by means of a second data object 408, which relates to the "B package" described above and includes the mentioned bottom-layer date and time stamp "1976-02-06 18:51:43.431", the "package ID" of the currently processed packaged object, and two chemical and / or physical properties "property 1" and "property n". However, due to the aforementioned requirements of the recycled underlying packaged object, the second data object 408 further includes another chemical and / or physical property of the underlying packaged object, in this embodiment "property 2", which specifically includes individual performance indicators for the packaged object, in this embodiment "low or insufficient material or product performance".

[0250] Depending on the performance value of the corresponding packaged item, packaged items processed by upstream process 400 but not classified by sorting unit 402 are provided by sorting unit 402 to the first "packaging unit 1" 412 or the second "packaging unit 2" 416. Packaging units 412 and 416 are used to package the corresponding packaged items into individual containers 414 and 418. The packaging process performed by the two packaging units 412 and 416 is managed by third data item 420 and fourth data item 422.

[0251] Both data objects 420 and 422 relate to "physical packaging" and include the same date "1976-02-06" as the "B package" described above, but include a later timestamp "19:12:21.123" compared to the "B package" described above. They also include the "package ID" of the underlying package object. However, data objects 420 and 422 further include performance indicators for the underlying final product, which in this embodiment are the "intermediate performance range" for the product stored in the first container (or refill bag) 414 and the "high performance range" for the product stored in the second container (or refill bag) 418. Additionally, both data objects 420 and 422 include the "order number" and "batch number" corresponding to the final product.

[0252] Figure 5 illustrates a third specific example of a portion of a basic chemical product manufacturing process or system implemented in an industrial plant. In this second specific example, these portions respectively include nine product handling devices 500 to 516 or technical equipment.

[0253] This product processing method is based on two raw materials, namely "raw material liquid" 500 and "raw material solid" 502, in order to produce polymeric materials in a known manner. As in the production scenario previously described according to Figures 3 and 4, the technical equipment includes a "recycling silo" 504 for using recycled materials, as previously described.

[0254] The technical apparatus further includes a "dosing unit 506" for producing encapsulated objects based on the input raw materials processed by the aforementioned reaction unit 508, which conveys the encapsulated objects along the four shown polymerization reaction zones ("Zones 1 to 4") 510, 512, 514, 516 for processing and by a "curing unit" 518 for curing the polymeric material produced in reaction unit 508 (i.e., the corresponding encapsulated objects). In this specific example, the curing unit 518 only includes a material buffer and does not include a remixing device. The curing unit 518 also conveys the corresponding processed encapsulated objects.

[0255] "Conveyor Unit 1" 520 conveys packaged items sorted for recycling by means of recycling silo 504. The finally processed (i.e. unsorted) units are then conveyed again to the first "Packaging Unit 1" 522 and the second "Packaging Unit 2" 524. The two packaging units 522 and 524 convert the corresponding packaged items and convey them to individual containers or filler bags 526 and 528.

[0256] The production process depicted in Figure 5 is managed by the first data object 530 and the second data object 534.

[0257] The first data object 530 pertains to "Package A" which has a production date of "1976-02-06" and a production time of "18:31:53.401". In this production context, data object 530 also includes a pre-described "Package ID", process information regarding the dispensing process performed by dispensing unit 506 ("Dispensing Properties"), and additional process information regarding the production of polymer materials by means of reaction unit 508 ("Reaction Unit Properties"). Dispensing Properties include information regarding the amount of raw materials for each package, namely "Percentage Raw Material 1 (Liquid)", "Percentage Raw Material 2 (Solid)", and product temperature. Reaction Unit Properties include the temperatures of the four polymerization reaction zones 510 to 516 ("Temperature Zone 1", "Temperature Zone 2", "Temperature Zone 3", and "Temperature Zone 4").

[0258] Additionally, the first data object 530 includes the current position (current encapsulation position) of the underlying encapsulation object along processing lines 506 to 524. In this specific example, the current position of the encapsulation object is managed using a "encapsulation position link" and a corresponding "zone position". Finally, it includes chemical and / or physical information related to the underlying polymerization reaction, i.e., the "enthalpy / turnover". Thus, processing units 506 to 524, which deliver a given encapsulation object, calculate the enthalpy value and permanently write / implement it into the first data object 530. This is possible due to existing information regarding the encapsulation position and corresponding residence time, as well as regarding the corresponding process values ​​(e.g., encapsulation temperature). Based on the current value of the enthalpy and / or turnover included in the first data object 530, the curing time parameters are adjusted based on the calculated enthalpy value via communication line 532 between the first data object 530 and the curing unit 518.

[0259] The second data item 534 relates to the "physical package" processed by one of the packaging units 522 and 524, and includes the corresponding date / time information "1976-02-06 19:12:21.123". It includes the "package ID", "product" description / instruction manual, "order number", "lot number", and the calculated enthalpy and / or turnover rate as mentioned.

[0260] Figure 6 illustrates a first concrete example of a graphical database configuration representing the hierarchical or topological structure of a lower-level industrial plant 602, which is part of an industrial plant cluster 600 and includes a plurality of equipment units and corresponding equipment areas as part of corresponding product processing lines 604. This topology allows observation of the functional relationships between different parts of the lower level of the industrial plant 602 (or the lower-level plant cluster 600) to enable improved processing or planning of the lower-level product packaging. The circular nodes shown in the graphical database are linked by connecting lines, for which different link types are possible.

[0261] In this specific example, the apparatus includes material processing units 606 and 614 connected to sensors / actuators 608 and 616 via signal and / or data connections. These sensors / actuators are part of the processing units 606 and 614 and are connected to several input / output (I / O) devices 610, 612 and 618, 620.

[0262] In this specific example, the first processing unit 606 is further connected to three exemplary product packages (product packages 1 to 3) 622, 624, and 626, while the second processing unit 614 is further connected to three other product packages (product packages 4 to n) 628, 630, and 632. Only the exemplary "product package 3" 626 is connected to product sample (sample 1) 634, while "product package 5" 630 is connected to another product sample (sample n) 638. "Sample 1" 634 is further connected to "inspection lot 1" 636, while "sample n" is further connected to "inspection lot n" 640. Finally, both inspection lots 636 and 640 are connected to "inspection instruction 1" unit 642, which acts as a specification on how the aforementioned inspection lots are generated and how the analysis / quality control of the individual underlying samples 634 and 638 is implemented.

[0263] The topology shown in Figure 6 provides an advantageous data structure that allows for an intuitive and easy understanding of the functionality and processes of the chemical plant, and thus allows users (especially machine / plant operators) to easily manage this complex production process of the chemical plant or cluster of chemical plants, as the displayed objects (nodes) are modeled to be very similar to their corresponding real-world objects.

[0264] More specifically, this topology provides a high degree of contextual information, which users / operators can use to easily collect the technical and / or material properties of each object. This also allows users to perform fairly complex queries, such as those concerning production-related connections or relationships between objects, particularly across several nodes or even topological / hierarchical levels. Furthermore, the objects (nodes) shown in Figure 6 can be easily expanded during runtime using additional properties and / or values.

[0265] Figure 7 shows a second specific example of the graph-based database configuration shown in Figure 6, but only for production line 700 ("Line 1").

[0266] In this specific example, the equipment includes material handling units 702 "Unit 1" and "Unit n" 708, which are connected to sensors / actuators "Sensors / actuators 1" 704 and "Sensors / actuators n" 710 via signal and / or data connections. These sensors / actuators are connected to corresponding input / output (I / O) devices "I / O 1" 706 and "I / O n" 712. These I / O devices include connections to a PLC (not shown) for controlling the operation of the production line 700.

[0267] In this specific example, the first processing unit ("Unit 1") 702 is further connected to three exemplary product packages ("Product Parts" 1 to 3) 714, 716, and 718, wherein the second processing unit ("Unit n") 708 is further connected to two other product packages ("Product Parts" 4 and n) 720 and 722. Exemplarily only, product package 3 718 is connected to product sample ("Sample 1") 724, wherein product package n 722 is connected to another product sample ("Sample n") 728.

[0268] Compared to the specific example shown in Figure 6, the first "sensor / actuator 1" 704 is also connected to the first product sample ("sample 1") 724, and the second "sensor / actuator n" 710 is also connected to the second product sample ("sample n") 728. These two additional connections offer the advantage of enabling samples to be obtained independently at different sampling stations at independent times or even simultaneously. For example, the sensor / actuator 704 could be a button located at the sampling station, pressed by a user or operator when a sample is obtained.

[0269] Alternatively, this sample can be a signal that can be automatically generated by the sampling machine. This automatically generated signal can, for example, reach the sensor / actuator object 704 via the shown I / O object 706, where the I / O object 706 receives the mentioned button information from a PLC / DCS (not shown). At the moment the sample is acquired, the sample object 724 will (for example) generate and link to the part of the product located at the sampling station position at that moment.

[0270] Based on the corresponding samples 724 and 728, one or more inspection batches 726 and 730 can be generated, or even for only one (and identical) sample. However, one or more samples can be generated independently or even simultaneously within a processing line.

[0271] Finally, in the specific example shown in Figure 6, "Sample 1" 724 is further connected to the first "Inspection Unit 1" 726, where "Sample n" is further connected to the second "Inspection Unit n" 730. Both Inspection Units 726 and 730 are ultimately connected to "Inspection Instruction 1" unit 732, which again serves as the specification, as in the case of "Inspection Instruction 1" unit 642 depicted in Figure 6, i.e., the specification regarding how to generate the mentioned inspection batch and how to implement the analysis / quality control of the underlying samples 724 and 728. "Inspection Instruction 1" unit 732 can be generated independently and can be generated only once, while "Inspection Batch 1" 726 and another "Inspection Batch n" 730 use Inspection Instruction 732 for more than one inspection batch, as illustrated in Figure 7.

[0272] Figure 8 depicts an abstraction layer 800, which includes an object database 801 and serves as an abstraction layer for pre-described production equipment and corresponding raw materials. For pre-described product information, it may include pre-described physical packaging or product packaging-related information, i.e., as a corresponding digital twin.

[0273] In this specific example, the abstraction layer 800 provides an external cloud computing platform 804 for bidirectional communication lines 802. Furthermore, the abstraction layer 800 also communicates with n production PLCs / DCSs and / or machine PLCs 806, 808, which are bidirectional (810) in the case of "PLC / DCS 1" 806, or unidirectional (812) in the case of "PLC / DCS n" 808. In this specific example, the cloud computing platform 804 includes a bidirectional communication line 814 to a customer integration interface or platform 816, through which customers of the production plant owner can transmit and / or deliver control signals to pre-described equipment units within the plant.

[0274] The object database 801 further includes other related objects, such as samples, inspection batches, sample instructions, sensors / actuators, devices, device-related documents, users (e.g., machine or plant operators), corresponding user groups and user rights, formulas, orders, sets of setpoint parameters, or received objects from cloud / edge devices.

[0275] At the cloud computing platform 804, an Artificial Intelligence (AI) or Machine Learning (ML) system is implemented to find or generate the best algorithm deployed to the Internet-of-Things (IoT) edge device or component 820 via a dedicated deployment pipeline 818, so that the generated or discovered algorithm can be used to control the edge device 820. In this specific example, the edge device 820 communicates bidirectionally with the abstraction layer 800 822.

[0276] Using the abstraction layer 800 and its included object database 801, pre-described entity or product packages are generated, as described in this document. The abstraction layer 800 can also connect to certain processing and / or AI (or ML) components within the cloud computing platform 804. For this connection, the known data streaming protocol "Kafka" can be used. Thus, at or approximately the time the underlying product package is generated, empty data packets can first be sent out as messages, particularly independently of the underlying time-series data. Subsequently, another message can be sent out when the final product package has been processed. These messages contain object identifiers of the underlying package as data packet IDs, allowing the related packets to be relinked on the cloud platform side. This has the advantage of avoiding the transmission of large data packets to the cloud, thus minimizing the required transmission bandwidth or capacity.

[0277] Within the cloud computing platform 804, the streamed and received product data is used by the mentioned AI or ML methods to find or generate algorithms for obtaining additional data related to the underlying product, such as predicted product quality control (QC) values. This process within the cloud computing platform 804 requires additional data, such as QC data or quantifiable performance parameters of the relevant product (or physical) package. This can be received via a database 801 containing sample objects and inspection batch objects (see also Figure 6) that present this information about the relevant product package.

[0278] This information can also be received from any system other than the object database. In this case, the other system sends the QC and / or performance data, along with the same product / inspection batch ID, from the object database. Within the cloud computing platform 804, this data will be combined and used to find, for example, ML-based algorithms / models. This allows for efficient use of the computing power within the cloud platform 804.

[0279] In this specific example, the correspondingly discovered algorithm or model is deployed to the edge device 820 via deployment pipeline 818. The edge device 820 may be a component located near the object database 801 of the abstraction layer 800 and therefore also near PLC / DCS 1 806 to PLC / DCS n 808, i.e., in terms of network security level and location allowing low network latency and direct and secure communication.

[0280] Since the use of the ML model does not require this computational power, the edge device 820 uses the ML model to generate the aforementioned advanced information and provides it to the object database 801. Therefore, the edge device 820 needs the same information or a subset of information used at the cloud computing platform 804 to generate ML-based algorithms or models. The object database 801 can provide this information to the edge device 820, for example, via an open network protocol for machine-to-machine communication, such as the known Message Queuing Telemetry Transport (MQTT) protocol.

[0281] This setup enables advanced process control based on AI / ML and the autonomous manufacturing and operation of corresponding machines. As illustrated in the specific example shown in Figure 8, based on data from pre-described data objects 330 to 334 (Figure 3), this data is used as training data on the cloud computing platform 804 to train the AI / ML system or corresponding AI / ML model. In this specific example, the training data can therefore include historical and current laboratory test data indicating the performance parameters of chemical products, especially data from the past.

[0282] AI / ML models can be used to predict one or more of the pre-described performance parameters, preferably via a computing unit. Alternatively, AI / ML models can be used to at least partially control the production process by adjusting equipment operating conditions, and more preferably, this control is performed via the aforementioned computing unit. Alternatively, AI / ML models can also be used, for example, by the computing unit to determine which of the process parameters and / or equipment operating conditions has a major influence on the chemical product, such that the major influencer of the process parameters and / or equipment operating conditions is respectively attached to the data object or the mentioned object identifier.

[0283] Those skilled in the art will understand that method steps performed, at least by a computing unit, can be performed "instantaneously" or nearly instantaneously. These terms are understood within the context of computer technology. As a specific example, the time delay between any two steps performed by the computing unit is no more than 15 seconds, specifically no more than 10 seconds, and more specifically no more than 5 seconds. Preferably, the delay is less than one second, more preferably less than a few milliseconds. Therefore, the computing unit can be configured to perform method steps in an instantaneous manner. Furthermore, software products can enable the computing unit to perform method steps in an instantaneous manner.

[0284] For example, the method steps may be performed in the order shown in the embodiments or examples. However, it should be noted that different orders may be possible in certain situations. Furthermore, it is possible to perform one or more of the method steps once or repeatedly. These steps may be repeated at regular or irregular times. Additionally, it is possible to perform two or more of the method steps simultaneously or in a timely overlapping manner, specifically, when some or more of the method steps are repeated. The method may include additional steps not listed.

[0285] Various embodiments have been disclosed above for: a method for controlling a production process; a system for performing the method disclosed herein; a system for controlling a production process; an application; a software program; and a computing unit comprising computer program code for performing the method disclosed herein. More specifically, this teaching relates to a method for controlling a downstream production process of manufacturing a chemical product using at least one precursor material, the method comprising: A set of downstream control setpoints for controlling the production of the chemical product is provided, wherein these downstream control setpoints are determined based on: a downstream object identifier; the downstream object identifier containing precursor information; at least one desired downstream performance parameter related to the chemical product; downstream historical data; and wherein the set of downstream control setpoints can be used to manufacture the chemical product at the downstream industrial plant. However, those skilled in the art will understand that changes and modifications can be made to these embodiments without departing from the spirit and scope of the appended claims and their equivalents. It should be further understood that various combinations of specific examples of methods and products discussed herein are permissible.

[0286] 102a: Conveying element 102b: Conveying element 104: Mixing Furnace 106a: Second conveying element 106b: Second conveying element 108a: Third conveying element 108b: Third conveying element 110a: Fourth conveying element 110b: Fourth conveying element 112a: First valve 112b: Second valve 114: Precursor Materials 116: Derivative Materials 118: Heater 120: Horizontal axis plane 122: Downstream object identifier 124: Downstream computing unit 126: Downstream Just-in-Time Process Data 128: Downstream memory storage 130a: First additional downstream object identifier 130b: Second downstream object identifier 132a: Downstream Just-in-Time Process Data 132b: Downstream Just-in-Time Process Data 134: Last downstream object identifier 136: Last-line real-time process data 138: Downstream Network 140a: First meridian-divided material 140b: Second Classified Material 142: Shear mill 144: Fill Sensor 146: Imaging Sensor 148: Temperature sensor 150: Extruder 152: Extruded material 154: Horizontal Axis 156: Horizontal Axis 158: Horizontal Axis 160: Cured second-stage material 162: Curing equipment 164a: Product Collection Warehouse 164b: Product Collection Warehouse 166: Collection Area 168: System 170: Chemical products 172: Sample Materials 200: Flowchart 202: Square 204: Square 206: Square 300: Liquid Raw Material Storage Unit 302: Solid raw material storage container 304: Recirculating Silo 306: Distribution Unit 308: Heating Unit / Homogeneous Unit 310: Material Buffer 312: Classification Unit 314: Conveying Unit 316: Downstream Packaging Unit 318: Downstream Packaging Unit 320: First Equipment Area 322: Second Equipment Area 324: Third Equipment Area 330: First Data Object 332: Data Objects 334: Data Objects 400: Upstream process 402: Classification Unit 404: First Data Object 406: Recirculating Silo 408: Second Data Object 410: Bottom-layer conveyor process steps 412: First Packaging Unit 414: First Container 416: Second Packaging Unit 418: Second Container 420: Third material object 422: Fourth Material Object 500: Raw material liquid 502: Raw material solid 504: Recirculating Silo 506: Distribution Unit 508: Reaction Unit 510: Polymerization Reaction Zone 512: Polymerization Reaction Zone 514: Polymerization Reaction Zone 516: Polymerization Reaction Zone 518: Curing Unit 520: Conveying Unit 522: First Packaging Unit 524: Second Packaging Unit 526: Containers or filling bags 528: Containers or filling bags 530: First Data Object 532: Communication line 534: Second Data Object 600: Collection 602: Bottom-level industrial factory 604: Product Processing Line 606: Material Processing Unit / First Processing Unit 608: Sensors / Action Devices 610: Input / output device 612: Input / Output Device 614: Material processing unit / Second processing unit 616: Sensors / Action Devices 618: Input / Output Device 620: Input / Output Device 622: Product Packaging 624: Product Packaging 626: Product Packaging 628: Product Packaging 630: Product Packaging 632: Product Packaging 634: Product Sample 636: Inspection Batch 638: Product Sample 640: Inspection Batch 642: Check instruction unit 700: Production Line 702: Material Handling Unit 704: Sensors / Action Devices 706: Input / Output Device 708: Material Handling Unit 710: Sensors / Action Devices 712: Input / Output Device 714: Product Packaging 716: Product Packaging 718: Product Packaging 720: Product Packaging 722: Product Packaging 724: Product Sample 726: Inspection Batch 728: Product Sample 730: Inspection Batch 732: Inspection Instruction 800: Abstraction layer 801: Object Database 802: Two-way communication line 804: External cloud computing platform 806: PLC / DCS 808: PLC / DCS 810: Two-way 812: One-way 814: Two-way communication line 816: Customer integration interface or platform 818: Dedicated deployment pipeline 820: Edge device or component 822:Communication

Claims

1. A method for controlling a downstream production process for manufacturing a chemical product at a downstream industrial plant, the downstream industrial plant including at least one downstream device, and the product being manufactured by processing at least one precursor material via the downstream device using the downstream production process, the method being performed at least in part via a downstream computing unit, and the method comprising: providing at the downstream computing unit a set of downstream control setpoints for controlling the production of the chemical product, wherein the downstream control setpoints are determined based on: a downstream object identifier; the downstream object identifier including precursor data indicating one or more properties of the precursor material; an upstream object identifier; the upstream object identifier including a subset of upstream process data; at least one desired downstream performance parameter related to the chemical product; downstream historical data; wherein the downstream historical data includes downstream process parameters and / or operating setpoints used for manufacturing one or more past chemical products; and wherein the set of downstream control setpoints can be used to manufacture the chemical product at the downstream industrial plant; At least one of the desired downstream performance parameters is related to one or more properties of the downstream derivative material.

2. The method of claim 1, wherein the precursor material processed by the device is divided into at least two packages, wherein the size of one package is fixed or determined based on the weight or amount of a precursor material, and the device can provide significantly constant process parameters or device operating parameters for the weight or amount of the precursor material.

3. The method of request 1 or request 2, wherein the processing of the at least two encapsulations is managed by means of corresponding data objects, each of which includes at least one object identifier.

4. The method of claim 1 or claim 2, wherein a data object is generated in response to a trigger signal provided by the device.

5. The method of claim 4, wherein the trigger signal is provided in response to the output of a corresponding sensor configured at each device unit in the device.

6. The method of Request 1 or Request 2, wherein at least some of the downstream control settings are determined by an upstream computing unit associated with an upstream industrial plant, and wherein at least one of the precursor materials is provided by the upstream industrial plant.

7. The method of claim 6, wherein at least some of the downstream control settings are provided in a shared memory storage that is accessible to both the upstream computing unit and the downstream computing unit.

8. The method of request item 6, wherein at least some of the downstream control settings are determined by the downstream computing unit.

9. The method of claim 8, wherein the upstream process data includes upstream process parameters and / or operating settings for manufacturing the precursor material at the upstream industrial plant.

10. The method of claim 9, wherein the downstream object identifier is provided by the upstream computing unit, preferably the downstream object identifier is accompanied by data from the upstream object identifier.

11. The method of claim 9, wherein the upstream object identifier includes a prediction and / or control logic for providing at least some of the downstream control settings based on the downstream historical data, preferably the prediction and / or control logic being encrypted or obfuscated from unauthorized readouts.

12. The method of claim 11, wherein the prediction and / or control logic includes a data-driven model that can be trained from the downstream historical data.

13. The method of claim 12, wherein the trained prediction and / or control logic generates modification data that can be used to modify the prediction and / or control logic to improve the calculation of the downstream control setpoints.

14. The method of claim 13, wherein the trained prediction and / or control logic and / or the modified data are provided to the upstream computing unit.

15. The method of claim 1 or claim 2, wherein the method also includes: preferably using the downstream control settings to execute the downstream production process by automatically providing the downstream control settings to the downstream computing unit and / or a plant control system for controlling the downstream production process.

16. The method of claim 1 or claim 2, wherein the method further comprises: receiving downstream real-time process data at the downstream computing unit from one or more of the downstream devices or device areas; wherein the downstream real-time process data includes downstream real-time process parameters and / or device operating conditions.

17. The method of claim 16, wherein the method comprises: determining a subset of the downstream real-time process data by the downstream computing unit based on the downstream object identifier and a downstream area presence signal; wherein the downstream area presence signal indicates the presence of the precursor material in a specific equipment area during the downstream production process.

18. The method of claim 17, wherein the method also includes: attaching the subset of the downstream real-time process data and / or downstream process-specific data to the downstream object identifier.

19. The method of claim 17, wherein the method comprises: calculating, via the downstream computing unit, at least one downstream performance parameter of the chemical product associated with the downstream object identifier based on the subset of the downstream real-time process data and the downstream historical data, preferably attaching at least one downstream region-specific performance parameter to the downstream object identifier.

20. The method of claim 19, wherein the method comprises: controlling the downstream production process via the downstream computing unit such that the difference between at least one of the downstream performance parameters and their respective associated values ​​of the desired downstream performance parameter is minimized.

21. The method of claim 19, wherein the calculation of at least one downstream performance parameter is performed using at least one downstream machine learning ("ML") model, which is trained using the downstream historical data.

22. The method of claim 21, wherein the industrial plant includes an Internet of Things (IoT) edge device or component, and wherein an underlying ML system is implemented to find or generate an algorithm, which is deployed to the IoT edge device or component to control the IoT edge device using the correspondingly generated or discovered algorithm, and wherein an abstraction layer is provided, the abstraction layer including an object database and the abstraction layer acting as one of the abstraction layers for production equipment, for corresponding precursor materials, and for encapsulating related data.

23. The method of claim 22, wherein the abstraction layer is connected to a specific processing and / or ML component within a cloud computing platform, wherein a data streaming protocol is used for this connection, and wherein the streamed and received product data is used by the ML system to find or generate algorithms for obtaining additional data related to an underlying chemical product.

24. The method of claim 23, wherein the additional information is predictable product quality control (QC) information concerning the underlying chemical product.

25. A system for controlling a downstream production process for manufacturing a chemical product at a downstream industrial plant, the downstream industrial plant including at least one downstream device and a downstream computing unit, wherein the product is manufactured by processing at least one precursor material via the downstream device using the downstream production process, wherein the system is configured to: provide at the downstream computing unit a set of downstream control settings for controlling the production of the chemical product, wherein the downstream control settings are determined based on: a downstream object identifier; the downstream object identifier including precursor data indicating one or more properties of the precursor material; an upstream object identifier; the upstream object identifier including a subset of upstream process data; at least one desired downstream performance parameter related to the chemical product; downstream historical data; wherein the downstream historical data includes downstream process parameters and / or operating settings used for manufacturing one or more past chemical products; and wherein the set of downstream control settings can be used to manufacture the chemical product at the downstream industrial plant; At least one of the desired downstream performance parameters is related to one or more properties of the downstream derivative material.

26. A non-transitory computer-readable medium storing a computer program, comprising instructions that, when executed by a suitable computing unit, are operatively coupled to at least one apparatus for manufacturing a chemical product at a downstream industrial plant by processing at least one precursor material using a downstream production process, such that the computing unit: provides a set of downstream control settings for controlling the production of the chemical product, wherein the downstream control settings are determined based on: a downstream object identifier; the downstream object identifier comprising precursor data indicating one or more properties of the precursor material; an upstream object identifier; the upstream object identifier comprising a subset of upstream process data; at least one desired downstream performance parameter related to the chemical product; downstream historical data; wherein the downstream historical data comprises downstream process parameters and / or operating settings for manufacturing one or more past chemical products; and wherein the set of downstream control settings can be used to manufacture the chemical product at the downstream industrial plant; At least one of the desired downstream performance parameters is related to one or more properties of the downstream derivative material.

27. A computer program comprising instructions, when executed by a suitable computing unit, operatively coupled to at least one apparatus for manufacturing a chemical product at a downstream industrial plant by processing at least one precursor material using a downstream production process, such that the computing unit: provides a set of downstream control setpoints for controlling the production of the chemical product, wherein the downstream control setpoints are determined based on: a downstream object identifier; the downstream object identifier comprising precursor data indicating one or more properties of the precursor material; an upstream object identifier; the upstream object identifier comprising a subset of upstream process data; at least one desired downstream performance parameter relating to the chemical product; downstream historical data; wherein the downstream historical data comprises downstream process parameters and / or operating setpoints for manufacturing one or more past chemical products; and wherein the set of downstream control setpoints can be used to manufacture the chemical product at the downstream industrial plant; the at least one desired downstream performance parameter relating to one or more properties of the downstream derivative material.

Images