Method for monitoring and / or controlling one or more chemical plants

Abstract

To provide a method and a system for monitoring and / or controlling a chemical plant having a plurality of assets.SOLUTION: A method includes the steps of: providing containerized application including input data, output data, and an asset or plant template for specifying an asset or plant model; deploying the containerized application, and executing the deployed application in at least one of deployed layers; allocating the deployed layers on the basis of the input data, a load indicator or a system layer tag; executing the containerized application in the allocated deployed layer, and generating the output data for controlling and / or monitoring a chemical plant; and providing output data generated to control and / or monitor the chemical plant.SELECTED DRAWING: None

Description

[Technical Field]

[0001] Field The present disclosure relates to a method for monitoring and / or controlling a chemical plant with multiple assets via a distributed computing system with multiple deployment tiers. [Background technology]

[0002] background Chemical production is a highly sensitive production environment, especially with regard to security. A chemical plant typically contains multiple assets for producing chemical products. Multiple sensors are distributed throughout such plants for monitoring and control purposes, collecting large amounts of data. Therefore, chemical production is a data-rich environment. However, to date, the benefits from such data for increasing production efficiency in one or more chemical plants have not been fully utilized.

[0003] Therefore, applying new technologies to cloud computing and big data analytics is of great interest. However, unlike other manufacturing industries, the processing industry is subject to very high safety standards. For this reason, computing infrastructure is typically siloed with very limited access to monitoring and control systems. Due to these safety standards, latency and availability considerations contradict a simple migration from traditional embedded control systems to, for example, cloud computing systems. Bridging the gap between highly proprietary industrial manufacturing systems and cloud technology is one of the major challenges.

[0004] WO2016065493 discloses a client device and a system for data acquisition and preprocessing of large amounts of process-related data from at least one CNC machine or industrial robot and transmitting the process-related data to at least one data recipient, such as a cloud-based server. The client device includes at least one first data communication interface to at least one controller of the CNC machine or industrial robot for continuously recording hard real-time process-related data via at least one real-time data channel and for recording non-real-time process-related data via at least one non-real-time data channel. The client device further includes at least one data processing unit for data mapping at least the recorded non-real-time data to the recorded hard real-time data to compile a contextualized set of process-related data. The client device further includes at least one second data interface for transmitting the contextualized set of process-related data to the data recipient and for further data communication with the data recipient.

[0005] WO2019138120 discloses a method for improving a chemical manufacturing process. A plurality of derivative chemical products are produced through a derivative chemical manufacturing process based on at least some derivative process parameters at respective chemical manufacturing facilities, the chemical manufacturing facilities each including a separate respective facility intranet. At least some of the respective derivative process parameters are measured from the derivative chemical manufacturing process by a respective production sensor computer system within each facility intranet. A process model for simulating the derivative chemical manufacturing process is recorded in a process model management computer system external to the facility intranet.

[0006] US20160320768A1 discloses an example of a network environment for monitoring a plant process using a system computer operating as a root cause analyzer. The system computer communicates with a data server to access collected data of measurable process variables from a historical database. The data server is communicatively coupled to a distributed control system (DCS) that communicates the collected data to the data server over a communication network.

[0007] The object of the present invention relates to a highly scalable and flexible method for monitoring and / or controlling chemical plants in the process industry, which complies with high safety standards and allows for enhanced monitoring or control. Summary of the Invention

[0008] overview A method is proposed for monitoring and / or controlling a chemical plant having multiple assets via a distributed computing system with three or more deployment layers, the deployment layers including at least two of a first processing layer, a second processing layer, and an external processing layer. The method comprises: - providing a containerized application including an asset or plant template specifying input data, output data, and an asset or plant model; - deploying the containerized application to run in at least one of the deployment tiers, the deployment tiers being assigned based on input data, load indicators, or system tier tags, and running the containerized application in each deployment tier to generate output data for controlling and / or monitoring the chemical plant; - providing the generated output data for controlling and / or monitoring the chemical plant.

[0009] A system for monitoring and / or controlling a chemical plant having multiple assets with three or more deployment tiers is proposed, the deployment tiers including at least two of a first processing tier, a second processing tier, and an external processing tier, the system comprising: - providing a containerized application that includes an asset or plant template that specifies input data, output data, and an asset or plant model; - deploying the containerized application to run in at least one of the deployment tiers, the deployment tiers being assigned based on the input data, the load indicators, or the system tier tags, and running the containerized application in the assigned deployment tier to generate output data for controlling and / or monitoring the chemical plant; - Providing generated output data for controlling and / or monitoring chemical plants; It is structured as follows.

[0010] The present invention further relates to a distributed computer program or computer program product comprising computer readable instructions that, when executed on one or more processors, cause the processors to perform the methods for monitoring and / or controlling one or more chemical plants described herein. The present invention further relates to a computer readable non-volatile or non-transitory storage medium comprising computer readable instructions that, when executed on one or more processors, cause the processors to perform the methods for monitoring and / or controlling one or more chemical plants described herein.

[0011] The proposed method allows for the implementation of distributed computing systems that control and / or monitor chemical plants. This allows for highly efficient application processing in the computing system. The introduction of different processing and storage layers allows for the distribution of large amounts of application data transfer, integration, and execution across the various layers, enabling flexible application processing. Furthermore, due to the redundancy of the second processing layer and the external management layer, the three-system-layer concept allows for highly available and secure monitoring and / or control. In other words, less critical tasks can be assigned to external computing resources, while more critical tasks can be assigned to on-premise computing resources that do not rely on an external network. An additional benefit is that, based on the context, this method allows for the automation of application deployment and the automatic identification of the need for additional sensors or IoT sensor retrofitting.

[0012] Furthermore, the proposed method can accommodate multiple chemical plants via a second or external processing layer. Therefore, this method enables highly scalable application integration for more reliable and enhanced monitoring and / or control of chemical plants. In particular, the integration of containerized applications across diverse application landscapes can be orchestrated to comply with the specific needs of the process industry. For example, the deployment of containerized applications that ingest input data can be streamlined across multiple assets, even across multiple plants. Furthermore, the appropriate processing layer can be selected depending on the specific data required by the containerized application and the computing resources required to run such application, thereby complying with high availability standards for chemical plants. For example, computationally intensive applications that ingest plant-specific data can be executed in a second processing layer, while processing applications that ingest asset- or process-specific data and require low latency can be executed in a first processing layer. Further criteria for when to integrate with which deployment layer can be defined.

[0013] The following description relates to the above-listed systems, methods, computer programs, and computer-readable storage media. In particular, the systems, input units, computer programs, and computer-readable storage media are configured to perform the method steps described above and further described below.

[0014] In the context of this invention, a chemical plant refers to any manufacturing facility based on chemical processing, such as converting raw materials into products using chemical processes. In contrast to discrete manufacturing, chemical manufacturing is based on continuous or batch processing. As such, monitoring and / or control of a chemical plant is time-dependent and therefore based on large time-series data sets. A chemical plant may contain more than 1,000 sensors that generate measurement data points every few seconds. Such scale results in several terabytes of data being processed by systems for controlling and / or monitoring the chemical plant. A small chemical plant may contain thousands of sensors that generate data points every 1-10 seconds. For comparison, a large chemical plant may contain tens of thousands of sensors, e.g., 10,000-30,000, that generate data points every 1-10 seconds. To contextualize this data, hundreds of gigabytes to several terabytes are processed.

[0015] A chemical plant may manufacture a product through one or more chemical processes that convert feedstocks into products via one or more intermediate products. Preferably, a chemical plant provides an encapsulated facility that produces a product that can be used as a feedstock for the next step in the value chain. A chemical plant can be a large-scale plant such as an oil and gas facility, a gas cleaning plant, a carbon dioxide capture facility, a liquefied natural gas (LNG) plant, an oil refinery, a petrochemical facility, or a chemical facility. For example, an upstream chemical plant in the production of petrochemical processing may include a steam cracker that begins by processing naphtha into ethylene and propylene. These upstream products may then be used to further the chemical plant. to produce downstream products such as polyethylene or polypropylene, which may again serve as feedstock for chemical plants that produce further downstream products. Chemical plants may be used to manufacture individual products. In one example, one chemical plant may be used to manufacture precursors to polyurethane foam. Such precursors may be provided to a second chemical plant to manufacture individual products, such as separator plates containing polyurethane foam.

[0016] The value chain production, from various intermediate products to final products, can be decentralized at different locations or integrated into Verbund sites or e-chemical parks. Such Verbund sites or chemical parks constitute a network of interconnected chemical plants, where products produced in one plant can be used as raw materials for another.

[0017] A chemical plant may include multiple assets, such as heat exchangers, reactors, pumps, pipes, distillation columns, and absorption columns, to name a few. In a chemical plant, some assets may be critical. A critical asset is an asset that, if destroyed, has a significant impact on the operation of the plant. This may jeopardize the manufacturing process. Product quality may be reduced or production may be halted. In a worst-case scenario, a fire, explosion, or release of toxic gases may be the result of such a destruction. Therefore, such critical assets may require stricter monitoring and / or control than other assets, depending on the chemical process and chemicals involved. To monitor and / or control chemical processes and assets, multiple actors and sensors may be incorporated into a chemical plant. Such actors or sensors may provide process- or asset-specific data related, for example, to the status of individual assets, the status of individual actors, the composition of chemicals, or the state of a chemical process. In particular, process- or asset-specific data may fall into the following data categories: - Processing operation data, such as the composition of raw materials and intermediate products; - Process monitoring data such as flow, material temperature, etc. - Asset operation data such as current, voltage, and - Asset monitoring data such as asset temperature, asset pressure, vibration, etc. Contains one or more of the following:

[0018] In the context of this disclosure, an asset may include any component of a chemical plant, such as equipment, instrumentation, machinery, processes, or process components, etc. Thus, an asset model may relate to a machinery, equipment, instrumentation, process, or process component model.

[0019] Process or asset-specific data refers to data related to a specific asset or process and contextualized with respect to such specific asset or process. Process or asset-specific data may be contextualized only with respect to individual assets and processes. Process or asset-specific data may include measurements, data quality measurements, time, units of measurement, asset IDs for specific assets, or process IDs for specific processing sections or stages. Such process or asset-specific data is collected at the lowest or first processing layer and contextualized with respect to specific assets or processes within a single plant. Such contextualization may be related to context available at the first processing layer. Such context may be related to a single plant.

[0020] Plant-specific data refers to process- or asset-specific data that is contextualized with respect to one or more plants. Such plant-specific data may be collected in the second processing layer and contextualized with respect to multiple plants. Specifically, the contextualization may relate to context available in the second processing layer. Process- or asset-specific data points may be added via contextualized context such as plant identifier, plant type, reliability indicator, or alarm limits of the plant. In a further step, the technical asset structure of one or more plants, Verbund sites or chemical parks, other asset management structures (asset Networks, etc.), or application context (model identifiers, third-party exchanges, etc.) may be added. Such comprehensive context may originate from functional locations or digital twins, such as digital piping and instrumentation diagrams, 3D models, or scans with xyz coordinates of plant assets. Additionally or alternatively, local scans, for example from a mobile device linked to piping and instrumentation diagrams, may be used for contextualization.

[0021] In particular, plant-specific data related to interfaces between chemical plants in a manufacturing chain can be provided in a second or external processing layer. Thus, monitoring and / or control can be enhanced, for example, through anomaly detection, setpoint steering, and optimization of the chain across multiple plants. Processing applications with online input / output data profiles can be used to monitor and / or control the chain across multiple plants. Such data and processing applications can be transferred between plants. When combined with monitorable mass and energy balances, such processing applications can optimize the entire chain of chemical plants, rather than individual plants within the chain.

[0022] Contextualization involves linking data points available in one or more storage units. Such units may be persistent or non-volatile storage. Data points may be associated with measurements or contextual information. The storage units may be part of a first processing tier, a second processing tier, an external processing tier, or may be distributed across two or more of these tiers. Links may be generated dynamically or statically. For example, predefined or dynamically generated scripts may generate dynamic or static links between information data points within or between processing tiers. Links may be established by generating new data objects containing the linked data itself and storing such new data objects in a new instance. Any stored data points may be actively deleted if copies are stored elsewhere. In this way, any data points copied from one storage unit to a new data object in the same or another storage unit may be deleted to reduce storage space. Additionally or alternatively, links may be established by generating metadata objects with embedded links to address or access the respective data points in the distributed storage units. Any data points that are addressable or accessible via metadata objects in this manner may remain in the original storage unit. Linking such information to form new data objects may still be performed, for example, at an external processing layer. Data can be retrieved by directly accessing the data object or by using the metadata object to address or access data distributed across one or more storage units. Operations on such data, such as applications, may access such data directly or may access a non-persistent image of such data, for example, from a cache memory or a persistent copy of the data.

[0023] In this context, a containerized application refers to a processing application that can be executed in an encapsulated runtime environment that is independent of the host operating system. The application can therefore be considered to be running in a sandbox. Containerized applications can be based on a container image that includes the application. The container image can include the software components, e.g., a hierarchical tree of software components, necessary to execute the respective application in the encapsulated runtime environment. Such containerized applications can be stored in or associated with a registry of a second or external processing tier.

[0024] To deploy a containerized application, an integrated application associated with the second processing tier or the external processing tier may manage the execution of the containerized application. Such management may include general runtime environment configuration, such as storage and networking, for executing the containerized application. Such management may further include host allocation, which defines a distribution among a central master node or one or more computing nodes for executing the application in the first processing tier, the second processing tier, or the external management tier. In particular, such computing resource allocation depends on input data, load indicators, or system layer tags.

[0025] Input data may include real-time data from sensors such as wireless monitoring devices or IoT devices, non-real-time data, or output data of deployed containers or executed applications. Such data may relate to a machine, such as a machine type and sensor data measured about a machine, a chemical, such as a chemical type and sensor data measured about a chemical component processed in a chemical plant, a process, such as a chemical process type and sensor data measured about a chemical process performed in a chemical plant, and / or a plant, such as a plant type or sensor data measured about a chemical plant, e.g., environmental measurement data.

[0026] The asset or plant model may include a data-driven model or a dynamic model that provides, for example, health status, operation prediction, event prediction, or event trigger. The asset or plant model may be based solely on a data-driven model, a hybrid model that combines a data-driven model and a dynamic model, or a solely dynamic model. The asset or plant model may be further based on a scenario matrix that maps input data, for example, sensor data, to specific events. The asset model may reflect the physical behavior of a single or multiple assets. The plant model may reflect the physical behavior of portions of one or more plants, the entire plant, or multiple plants.

[0027] The output data may include key performance indicators related to the asset, the plant, the input data, the performance of the asset model, or the performance of the plant model. The performance of the asset model or the performance of the plant model may be embedded in the asset or plant model hosted by the containerized application. Any generated output data of the method may be used as input data in one or more further containerized applications. In this manner, a chain of containerized applications may be realized to build a system of system coverage, and the generated output data may be used to control and / or monitor one or more chemical plants. Such chemical plants may be parallel manufacturing plants or plants connected along a value chain.

[0028] The containerized application may include one or more operations for ingesting input data, providing the input data to respective asset or plant models to generate output data, and providing the generated output data for controlling and / or monitoring the chemical plant. Such output data may be passed to a persistence instance after execution of the application. In particular, such output data may be passed to a control instance, e.g., a first processing tier of a chemical plant. Additionally or alternatively, such output data may be passed to a monitoring instance on the first processing tier, a second processing tier, or an external processing tier. The output data may be passed to, for example, a client application for display to an operator or to a further containerized application for execution.

[0029] In one embodiment, the second processing tier has greater storage and computing power than the first processing tier. Alternatively or additionally, the external processing tier may include larger storage and computing resources than the second processing tier. Such a stacked resource structure helps bridge the gap between embedded control systems in chemical plants and available cloud technologies. In particular, embedded control systems in chemical plants have limited storage and processing capabilities. Expanding such resources can enhance monitoring and / or control.

[0030] The first and second processing layers may be hosted, deployed, or configured within a secure network. The first processing layer may be communicatively coupled to the second processing layer. The first processing layer may include at least one core processing system associated with the chemical plant or a single chemical plant. Preferably, the first processing layer is configured to control and / or monitor chemical processes and assets at the asset level of the individual plant. Thus, the first processing layer monitors and / or controls the chemical plant at the lowest level. More preferably, the first processing layer is configured to monitor and control critical assets. Critical assets are assets whose destruction would have a significant impact on the plant's operations. This could jeopardize manufacturing processes, reduce product quality, or halt production. In a worst-case scenario, fire, explosion, or release of toxic gases could result from such a disruption. Therefore, such critical assets may require stricter monitoring and / or control than other assets, depending on the chemical process and the chemicals involved.

[0031] Additionally or alternatively, the second processing layer may be configured to provide data to an external network, for example, via an interface to the external network. The second processing layer may be communicatively coupled to the external processing layer via the external network. Adding a stack processing layer within or within a secure network can comply with high safety standards in the chemical industry. In particular, such an architecture enables methods to run completely independently of the external management layer, enabling an island mode for one or more chemical plants. Here, island mode refers to monitoring and / or controlling a chemical plant without access to an external network.

[0032] In a further aspect, the first processing layer is configured to provide asset- or process-specific data, and the second processing layer is configured to provide plant-specific data. The second processing layer can be configured to contextualize the asset or process-specific data. In this way, the performance of the first processing layer is not affected. Because typical core processing systems in the first processing layer, especially in older plants, lack the necessary computing power, adding additional systems with higher performance can also enable contextualization. Furthermore, the second processing layer allows for data contextualization at the plant level rather than the asset level. Data contextualization in this context relates to adding contextual information to asset- or process-specific data or reducing data size by preprocessing the asset- or process-specific data. Adding context can include adding additional information tags to assets or processing specific data. Preprocessing can include filtering, aggregating, normalizing, averaging, or inferencing the asset- or process-specific data.

[0033] In one aspect, a first processing tier is associated with one or a single chemical plant. The first processing tier may be a core processing system including one or more processing and storage devices. Such a tier may include a programmable logic controller (PLC) system or one or more distributed processing and storage devices forming a decentralized control system (DCS) with control loops distributed throughout the chemical plant. Preferably, the first processing tier is configured to control and / or monitor chemical processes and assets at the asset level. Thus, the first processing tier may be configured to control and / or monitor the chemical processes and assets at the chemical plant. The first processing layer monitors and / or controls the assets at the lowest level. Additionally, the first processing layer may be configured to monitor and control critical assets. Additionally or alternatively, the first processing layer may be configured to provide process or asset specific data to the second processing layer. Such data may be provided directly or indirectly to the second processing layer.

[0034] In a further aspect, the second processing layer is associated with multiple chemical plants. The second processing layer may include a process management system with one or more processing and storage devices. A preferred second processing layer or process management system is configured to manage data transfer to and / or from the first processing layer. A further preferred second processing layer or process management system is configured to host and / or organize processing applications. Such processing applications may monitor and / or control one or more chemical plants or one or more assets. The process management system may be associated with one or more chemical plants. In other words, the process management system may be communicatively coupled to multiple first processing layers associated with one or more chemical plants.

[0035] In a further aspect, the second processing tier may include an intermediate processing system and a processing management system. Here, the intermediate processing system may be communicatively coupled to the first processing tier, preferably the core processing system, and the processing management system may be communicatively coupled to the intermediate tier. Preferably, the first processing tier and the processing management system are coupled or communicatively coupled via the intermediate processing system. The intermediate processing system may be configured to collect process- or asset-specific data provided by the first processing tier. The processing management system may be configured to provide plant-specific data for one or more chemical plants to an interface to an external network. The intermediate processing system may be associated with one or more chemical plants. In other words, the intermediate processing system may be communicatively coupled to the first processing tier of one chemical plant or multiple first processing tiers of multiple plants. The processing management system may be communicatively coupled to one or more intermediate processing systems. Adding an intermediate processing level to the second processing tier adds another layer of security. The security layer completely removes the toxic first processing tier from any external network access. Additionally, at the intermediate level, data processing can be further enhanced by reducing data transfer rates to external processing layers through preprocessing and improving data quality through contextualization. The intermediate processing system and processing management system may include one or more processing and storage devices.

[0036] In a further aspect, the secure network is an isolated network that includes three or more security regions separated by firewalls. Such firewalls may be network-based or host-based virtual or physical firewalls. The firewalls may be hardware-based or software-based to control incoming and outgoing network traffic, where predetermined rules in the sense of a whitelist may define allowed traffic via access control or other configuration settings. Depending on the firewall configuration, the security regions may comply with various security standards.

[0037] In a further aspect, the first processing tier is hosted, located, or configured within a first security domain through a first firewall, and the second processing tier is hosted, located, or configured within a second security domain through a second firewall. To secure the first processing tier, the first security level may comply with higher security standards than the second security level. The security level may comply with common industry standards, such as those set forth in Namur document IEC 62443. The second processing tier may provide further isolation through security domains. For example, an intermediate processing system may be hosted within a third security domain through a third firewall. The third and second security regions may be located, deployed, or configured in a first security region, and the process management system may be configured within a second security region via a second firewall. The third and second security regions may also be offset in terms of security standards. For example, the third security region may adhere to higher security standards than the second security region. This allows for higher security standards in the lower security region of the first processing tier and lower security standards in the higher security region of the second processing tier. In one embodiment, the first processing tier is in the first security region, the process management system is in the second security region, and the intermediate processing system is in the third security region.

[0038] The second processing layer can be configured to contextualize process- or asset-specific data. In this way, the performance of the first processing layer is not affected. Because typical core processing systems in older plants lack the necessary computing power, adding additional systems with higher performance also enables contextualization. Furthermore, the second processing layer, particularly the intermediate processing system, allows data contextualization at the plant level rather than the asset level. Contextualizing data in its current context relates to adding contextual information to process- or asset-specific data or reducing data size by preprocessing the process- or asset-specific data. Adding context can include adding further information tags to the process- or asset-specific data. Preprocessing can include filtering, aggregating, normalizing, averaging, or inferencing the process- or asset-specific data.

[0039] In a further aspect, unidirectional or bidirectional communication, e.g., data transfer or data access, may be implemented for data streams between different processing layers. In other words, the system may be configured to enable unidirectional or bidirectional communication, e.g., data transfer or data access between different processing layers. One data stream may include process- or asset-specific data from a first processing layer that is passed to a second processing layer, contextualized through the second processing layer, and communicated to an external processing layer. The contextualization may be performed by the second processing layer, the external processing layer, or both. In other words, the second processing layer, the external processing layer, or both may be configured to contextualize the process- or asset-specific data or plant-specific data. Furthermore, depending on the importance of the process- or asset-specific data or plant-specific data, such data may be assigned for unidirectional or bidirectional communication. In other words, the system may be configured to assign unidirectional or bidirectional communication to process- or asset-specific data or plant-specific data depending on the importance of the process- or asset-specific data or plant-specific data. For example, implementing a diode-type communication channel may prohibit data communication from the second processing layer or the external processing layer to a critical asset. Such communication only allows one-way communication from the critical assets to the processing layer, but not vice versa.

[0040] In a further aspect, data streams may be assigned critical or non-critical data. In other words, the system may be configured to assign critical or non-critical data tags. Critical data refers to data that is essential to the operation of a chemical plant, such as short-term data from which operating points for the chemical plant are derived. Such critical data may cover short-term periods, for example, from a few hours or days to a week or more, necessary to operate the plant optimally. Non-critical data refers to data that is not critical to the operation of a chemical plant, such as medium- to long-term data for monitoring the chemical plant based on medium- to long-term behavior. Such non-critical data may cover medium- to long-term periods, for example, from multiple weeks or months to a year or more, necessary to monitor and / or control an asset or plant over a period of time. Such data may also be referred to as cold, warm, and hot data, with hot data corresponding to critical data, warm data corresponding to medium-term non-critical data, and cold data corresponding to long-term non-critical data. Respond to data.

[0041] In a further aspect, data contextualization is staggered across system layers, processing layers, or processing systems included in such processing layers, with each layer mapping contextual information available at the respective layer. In other words, the system may be configured to stagger data contextualization across system layers, processing layers, or processing systems included in such processing layers, with each layer mapping contextual information available at the respective layer. The staggering may include contextualizing asset- or process-specific data at various levels, adding contextual information at the single-plant and / or multi-plant levels. In a layered system architecture, contextual information available at one layer may be mapped to data provided by a lower layer or processing system, where lower refers to closer to the chemical plant's data access. For example, process- or asset-specific data provided by a first processing layer may include asset-level contextual information. In other words, the first processing layer may be configured to provide process- or asset-specific data that includes asset-level contextual information. Such contextual information may relate to real-time information, such as measurement values, measurement quality, product quality, batch-related data, or measurement time. Asset-level contextual information may further relate to asset-specific information, such as asset identifiers, intralogistics, or unit of measure identifiers. Intermediate systems and process management systems may be configured to further add or contextualize contextual information to such process- or asset-specific data. Such contextual information may relate to the plant level rather than the asset level. For example, the contextual information relates to plant context, such as plant identifiers, plant types, reliability indicators, and alarm limits, or application context, such as model identifiers, third-party exchange identifiers, and confidentiality identifiers. In this way, data quality can be improved to maximize context, and that data management and resulting monitoring and / or control capabilities via process applications can be used.

[0042] In a further aspect, the intermediate processing system is configured to contextualize data by mapping heterogeneous process- or asset-specific data to a homogeneous data format at the plant level. In this context, heterogeneous refers to data associated with the asset level or multiple assets individually, and homogeneous data refers to data associated with a combination or equivalent type of asset within a plant. The intermediate processing system may be configured to provide such plant-specific data to a process management system. The process management system may be further configured to contextualize the plant-specific data provided by the intermediate processing system, preferably at a multi-plant level. Such contextualization may include adding contextual information at a multi-plant level, or at a site level, such as multiple plants, or adding a site context that includes asset management information such as the technical asset structure or asset network of one or more plants. Additionally or alternatively, such contextualization may include adding application context, such as a model identifier, a third-party exchange identifier, or a confidentiality identifier.

[0043] Additionally or alternatively, the first processing layer may be configured to provide assets or process specific data to the second processing layer. Such data may be provided directly or indirectly to the second processing layer. The second processing layer may be associated with one or more plants. The second processing layer may include a process management system and, optionally, an intermediate processing layer. The first processing layer may include a plant-specific core processing system. The core processing system may optionally be communicatively coupled to the process management system via the intermediate processing layer. The second processing layer, particularly the process management system, and the external processing layer may be configured to contextualize, store, or aggregate data from one or more chemical plants and / or integrate process models of one or more chemical plants.

[0044] In a further aspect, the intermediate processing system is configured to contextualize the data by mapping heterogeneous process or asset-specific data into a homogenous data format at the plant level. In this context, heterogeneous refers to data relating to an asset level or multiple assets individually, while homogeneous data refers to data relating to a combination or equivalent type of assets within a plant. The intermediate processing system may be configured to provide such plant-specific data to the process management system. The process management system may further be configured to contextualize the plant-specific data provided by the intermediate processing system, preferably at a multiple plant level. Such contextualization may include adding contextual information at a multiple plant level, or at a site level, such as multiple plants, or adding a site context that includes asset management information such as the technical asset structure or asset network of one or more plants. Additionally or alternatively, such contextualization may include adding application context, such as a model identifier, a third-party exchange identifier, or a confidentiality identifier.

[0045] The second processing layer, preferably a process management system, may be communicatively coupled to the external processing layer via an external network. The second processing layer, preferably a process management system, may be configured to manage data transfer to and / or from the external processing layer in real time or on demand. The second processing layer, preferably a process management system, may be configured to provide plant-specific data to the interface to the external network based on an identifier added, for example, by contextualization. Such an identifier may be a confidentiality identifier based on which such data is not provided to the interface to the external network.

[0046] The external processing layer may be a computing or cloud environment that provides virtualized computing resources such as data storage and computing power. The external processing layer may provide a private, hybrid, public, community, or multiple cloud environment. Cloud environments are advantageous because they provide on-demand storage and computing power. Furthermore, when monitoring and / or controlling multiple chemical plants operated by different parties, data or processing applications that affect the chemical plants may be shared in such a cloud environment.

[0047] In a further aspect, the second processing layer, preferably a process management system, is configured to provide plant-specific data from one or more chemical plants to the external processing layer. The second processing layer, preferably a process management system, may be further configured to delete at least a portion of the data transferred to the external processing layer. The external processing layer may be configured to store historical data from one or more chemical plants. The external processing layer may be configured to aggregate, store, or contextualize plant-specific data from multiple chemical plants and / or store historical data from multiple chemical plants. Aggregation here refers to grouping data via an aggregation function such as sum, average, or mode. Thus, aggregation relates to the ability to reduce size or storage space. In this way, data storage can be externalized, reducing required on-premise storage capacity and making historical transfers redundant. Furthermore, due to the flexible computing and storage resources of the external processing layer and the fact that data is available at the external processing layer, processing applications can be built, trained, tested, or modified at the external processing layer.

[0048] In a further aspect, the second processing layer, preferably a processing management system, is configured to manage data transfers to and / or from the external processing layer in real time or on demand. Real-time transfers may be buffered depending on the network and computing load of the interface to the external network. On-demand transfers may be triggered in a predefined or dynamic manner. Preferably, data transfers to the external processing layer are managed in real time, and transfers from the external processing layer are managed on demand.

[0049] In a further embodiment, the second processing layer, preferably a process management system, is configured to store or manage access to historical data, real-time data, and planning data. In a further embodiment, the second processing layer, preferably a process management system, is configured to store or manage access to historical data for a first time frame, and the external processing layer is configured to store historical data for a second time frame, the first time frame being shorter than the second time frame. Here, the first time frame may correspond to a critical time frame during which the system can monitor and / or control the chemical plant in island mode without an external network connection. The first time frame may be considered a hot window during which historical data is needed to safely control and / or monitor the chemical plant. The first time frame or hot window may be determined based on the storage capacity of the second processing layer, preferably a process management system, or preferably by the processing applications and the historical data needed to run on the processing applications in island mode without an external network connection. In this way, the availability of the system for monitoring and / or control is always guaranteed.

[0050] In a further aspect, the deployment is managed by an integration application that manages the deployment of containerized applications based on input data, load indicators, or system tier tags. Additionally or alternatively, the integration application is hosted by a second processing tier and / or an external processing tier. In a further aspect, the integration application hosted by the second processing tier at runtime manages critical containerized applications. Additionally or alternatively, the integration application hosted by the external processing tier at runtime manages non-critical containerized applications. Such management at runtime can be statically or dynamically assigned. In a dynamic scenario, if external network connectivity is interrupted, the second processing tier can host backups of critical containerized applications, and the integration application hosted by the second processing system can access such backups. Here, a critical containerized application refers to a containerized application that monitors and / or controls critical assets. Therefore, such applications are required when monitoring and / or control needs to be performed in island mode.

[0051] In a further aspect, management of critical containerized applications is assigned to the second processing tier based on a historical criterion reflecting a time window of historical data available at the first or second processing tier. The second processing tier may be configured to store historical aggregate data for a first time window, and the external processing tier may be configured to store historical aggregate data for a second time window, the first time window being shorter than the first time window. In a preferred embodiment, the first time window is selected so that critical containerized applications can be executed at the first or second processing tier. In a further aspect, containerized applications are deployed to run at the second processing tier or the external management tier depending on a historical criterion reflecting a time window of available historical data. In such an embodiment, applications can be executed at the level at which such data is available. Therefore, there is no need to transfer additional data between processing tiers, reducing communication and processing load. Processing plant-specific data at the first processing tier, combined with the concept of staggered contextualization between tiers, introduces redundant data transfer from the first processing tier to the second processing tier for contextualization and back to the first processing tier for application execution.

[0052] The deployment may depend on the input data. In a further aspect, the assignment of a deployment tier depends on a data availability indicator, an importance indicator, or a latency indicator.

[0053] Data availability indicators are consumed by containerized applications. Based on such indicators, execution may be assigned to a deployment tier where the data is directly available or stored. For example, a first processing tier may be configured to provide asset- or process-specific data, and a second processing tier may be configured to provide plant-specific data. Containerized applications that ingest asset- or process-specific data may be deployed to the first processing tier. Similarly, containerized applications that ingest plant-specific data may be deployed to the second processing tier. To avoid redundant data transfers and reduce load, applications may be executed in the processing tier that hosts the data.

[0054] The criticality indicator may be static or dynamic. In the case of a static asset criticality indicator, an asset group or plant may be predefined. In the case of a dynamic indicator, the criticality indicator may be dynamically assigned depending on the output data of previous application runs or other application runs. For example, the criticality indicator may be determined based on key performance parameters, such as the health of the asset. If the asset's health becomes critical over time, the criticality criteria may be changed, and as a result of such a change, the containerized application may be executed in a different deployment tier, e.g., to reduce data transfer latency. In one example, if a containerized application ingests an asset or processes specific data for a specific asset and the execution is assigned to a second processing tier instead of a first processing tier, the criticality indicator may be indicated as met. If the health of a specific asset changes and closer monitoring, e.g., more frequently, is required, the criticality indicator may be reset when the execution is assigned to the second processing tier, indicating that the criticality indicator is not met. In such a case, the application may be assigned to the first processing tier.

[0055] The latency indicator may be a static indicator or a dynamic indicator. In the case of a static indicator, the latency requirement for an asset, an asset group, a part of a plant, or a plant may be predefined. In the case of a dynamic indicator, the latency requirement may be dynamically assigned depending on the signature of the input data. Such a signature may be related to the frequency of changes in real-time measurement data, for example, derived from historical real-time measurement data. In one example, a pump monitoring signal may exhibit a higher frequency than a heat exchanger monitoring signal. In such a case, a containerized application monitoring a pump may be deployed at the asset level directly to the pump controller or to the core processing system of the respective plant. For example, with respect to a pump, each containerized application may be deployed in a processing tier as close as possible to the pump to reduce latency. Thus, the latency metric may indicate the time-criticality of the containerized application.

[0056] The load indicators may be based on the processing and / or network load of the respective deployment tier. Additionally or alternatively, applications may be executed in a deployment tier that provides sufficient computing and storage resources to reduce the processing load on other processing tiers and avoid impacting the execution of critical applications. In such cases, input data may be forwarded to the respective deployment tier. This is particularly advantageous for applications that require high computing loads or less time-criticality, thus allowing for data transfer latency.

[0057] In a further aspect, the deployment may depend on a system layer tag associated with the containerized application. The system layer tag may be, for example, the configuration of an integrated application that deploys, runs, and monitors the containerized application. In such a case, the containerized application may be configured to use the system layer tag associated with the containerized application when the integrated application is deployed. The deployment may include application identifiers that can be used to identify critical applications. In this way, deployment may be "hardwired" to ensure that critical applications run on the appropriate tier. Such a deployment scheme may be particularly relevant for containerized applications that monitor and / or control critical assets. In this context, critical assets are assets that, if destroyed, have a significant impact on the operation of the plant. Here, plant-specific data refers to contextualized asset or process-specific data.

[0058] In a further aspect, the containerized application is deployed to multiple assets or plants of the same type. Assets of the same type may relate to assets with similar functionality from the same supplier and / or assets with similar characteristics, e.g., performance characteristics. Plants of the same type may relate to plants that produce similar intermediate or final products, have similar physical asset structures, or are based on similar chemical processes. Similar here means that the behavior of the assets or plants does not deviate beyond a tolerable error or exhibits behavior that can be modeled with a single model. Preferably, the containerized application is associated with an asset or plant identifier. Such an identifier may be a configuration setting for the integrated application or the containerized application. The plant or asset identifier may be one-dimensional, representing a single plant or asset type, or multi-dimensional, representing multiple plants or assets on which the containerized application runs. In particular, if the first processing layer is specific to different processing units, plants, assets, or processes, such asset identifiers enable assets associated with different processing units to be simultaneously addressed, thereby enabling highly efficient deployment of containerized applications.

[0059] In a further aspect, the containerized application is modified based on input and output data of the containerized application executed on multiple assets or plants of the same type. This may be performed periodically at predefined times or dynamically. By aggregating such data, the accuracy of the containerized application, particularly the plant or asset model, can be verified or improved. In this way, the model can be adapted to reflect the behavior of the physical plant or asset. This is particularly important for maintenance cycles or lifecycles, as the physical plant or asset may shift its behavior depending on the stage of such cycle. Such shifts can be compensated for in an automated and self-optimized manner by the proposed system.

[0060] In a further aspect, the containerized application is monitored based on confidence levels of input data, asset models, or plant models. The containerized application may provide confidence levels for output data, etc. Each operation may be incorporated into the containerized application via the asset model or plant model or via a separate model. The confidence level of the input data may be generated, for example, by analyzing patterns of real-time measurement data. A confidence level for the asset or plant model may be generated as part of the execution of the model operations based on the input data.

[0061] In a further aspect, an event signal is triggered if the confidence level falls below a confidence threshold, e.g., if the confidence level is less than 70%, 80%, or 90%. Such an event signal may indicate a fault in the asset or operation of the application. If an abnormal pattern is detected in the input data and the respective confidence level falls below a threshold, the execution of the application may be stopped and a fault signal may be passed to a control instance of a first processing tier of the chemical plant. Additionally or alternatively, such a fault signal may be passed to, for example, a monitoring instance of the first or second processing tier, or to a client application for display to, for example, an operator. In this manner, sensor failures and the need for retrofitting may be detected. do.

[0062] In a further aspect, when the confidence level exceeds a threshold, a change to the asset or plant model is triggered. The change may be triggered automatically. Such a change may include hardware or software changes. For example, the change may include retraining the asset or plant model based on historical data, adapting input data channels, adapting a scenario matrix, or triggering an event signal to maintain hardware such as an Internet of Things (IoT) device.

[0063] In a further aspect, changes to the asset or plant model are performed in a second processing layer, particularly a process management system, or external processing layer, where such changes may be computed and reduce the monitoring and / or control processing load on more critical processing layers, such as the first and second processing layers, since such changes do not interfere with the containerized applications to begin with.

[0064] In a further aspect, an external containerized application from a third-party environment is provided and deployed to run on the external processing tier. An application from a third-party environment means any application that was not created in the proprietary systems of the first processing tier, the second processing tier, and the external processing tier. In this manner, the risk of a third-party containerized application infecting the chemical plant monitoring and / or control system is mitigated.

[0065] In a further aspect, creation of new containerized applications is performed in an external processing layer. For example, an asset or plant model may be trained in the external processing layer. Preferably, the external processing layer is configured to store aggregated data for multiple chemical plants. The second processing layer may be configured to provide the aggregated data from one or more chemical plants to the external processing layer. The second processing layer may be configured to forward the aggregated data to the external processing layer in real time or on demand. The second processing layer may be configured to delete at least a portion of the data forwarded to the external processing layer.

[0066] Exemplary embodiments of the present disclosure are illustrated in the accompanying drawings. However, it should be noted that the accompanying drawings illustrate only particular embodiments of the present disclosure and therefore should not be considered as limiting its scope. The technical teachings may encompass other equally effective embodiments. [Brief explanation of the drawings]

[0067] [Figure 1] 1 is a first schematic diagram of a system for monitoring and / or controlling one or more chemical plants; [Figure 2] FIG. 2 is a second schematic diagram of a system for monitoring and / or controlling one or more chemical plants. [Figure 3] FIG. 10 is a third schematic diagram of a system for monitoring and / or controlling one or more chemical plants. [Figure 4]FIG. 4 is a schematic diagram of the concept of data contextualization in a system such as that shown in FIGS. 1 to 3. [Figure 5] 1 is a flow chart of a schematic diagram of a method for monitoring and / or controlling one or more chemical plants. [Figure 6] FIG. 1 is a schematic diagram of a system for monitoring and / or controlling one or more chemical plants via containerized applications. [Figure 7] 1 is a flow chart of a schematic diagram of a method for monitoring and / or controlling a chemical plant having multiple assets. [Figure 8] 1 is a schematic diagram of a system for monitoring and / or controlling multiple chemical plants in different secure networks configured for data and application transfer; DETAILED DESCRIPTION OF THE INVENTION

[0068] Detailed Description In petrochemical processing, industrial production typically begins with upstream products and is used to derive further downstream products. To date, production along the value chain from various intermediate products to final products has been very limited and based on siloed infrastructure. This hinders the adoption of new technologies such as IoT, cloud computing, and big data analytics.

[0069] Unlike other manufacturing industries, the process industry is subject to very high standards, especially regarding availability and security. For this reason, computing infrastructure is typically unidirectional and siloed, and access to chemical plant monitoring and control systems is very limited.

[0070] Chemical manufacturing plants are typically embedded in enterprise architectures in a siloed manner at various levels to functionally separate operational technology and information technology solutions.

[0071] Level 0 relates to the physical process and specifies the actual physical processes of the plant. Level 1 relates to intelligent devices for sensing and manipulating the physical process, for example, through process sensors, analyzers, actuators, and related instrumentation. Level 2 relates to the control system for supervising, monitoring, and controlling the physical process. Typical components include real-time control and software, i.e., DCS, human-machine interface (HMI), and supervisory and data acquisition (SCADA) software. Level 3 relates to the manufacturing operations system for managing the production workflow to produce the desired product. Typical components include batch management, manufacturing execution / operations control systems (MES / MOMS), laboratories, maintenance, plant performance management systems, data historians, and related middleware. Control and monitoring time frames may be shifts, hours, minutes, or seconds. Level 4 relates to the business logistics system for managing the business-related activities of the manufacturing operation. ERP is the primary system, establishing the basic plant production schedule, material usage, shipments, and inventory levels. The time frame may be a month, a week, a day, a shift.

[0072] Furthermore, such structures adhere to strict one-way communication protocols, so there is no data flow below Level 2. Such architectures do not include the company or the external Internet. However, this model remains an essential concept within the realm of cybersecurity. In this context, the challenge is to leverage the benefits of cloud computing and big data while ensuring the established advantages of existing architectures: high availability and reliability of the lower-level systems (Level 1 and Level 2) that control chemical plants and cybersecurity.

[0073] The technical teachings presented herein allow for systematic modification of this framework with enhanced monitoring and / or control, allowing new functionality to be introduced that is compatible with existing architectures. The present disclosure is particularly relevant for highly scalable, flexible, and available computing infrastructures for the processing industry, while at the same time adhering to high security standards.

[0074] FIG. 1 shows a first schematic diagram of a system 10 for monitoring and / or controlling a chemical plant 12 .

[0075] The system 10 comprises two processing layers, including a first processing layer in the form of a core processing system 14 associated with each chemical plant 12 and a second processing layer 16 in the form of, for example, a process management system associated with the two chemical plants 12. The core processing system 14 is communicatively coupled to the second processing layer 16 to enable unidirectional or bidirectional data transfer. The core processing system 14 comprises a distributed set of processing units associated with the assets of the chemical plants 12.

[0076] The core processing system 14 and the second processing tier 16 are configured within a secure network 18, 20, which generally includes two security domains. The first security domain is located at the core processing system 14 level, with a first firewall 18 controlling incoming and outgoing network traffic to and from the core processing system 14. The second security domain is located on the second processing tier 16, with a second firewall 20 controlling incoming and outgoing network traffic to and from the second processing tier 16. Such an isolated network architecture can protect vulnerable plant operations from cyber attacks.

[0077] The core processing system 14 provides process- or asset- or process-specific data 22 of the chemical plant 12 to a second processing layer 16. The second processing layer 16 is configured to contextualize the process- or asset- or process-specific data of the chemical plant 12. The second processing layer 16 is further configured to provide plant-specific data 24 of the chemical plant 12 to an interface 26 to an external network, where the plant-specific data may refer to the contextualized process- or asset- or process-specific data.

[0078] Process or asset or process specific data may include value, quality, time, units of measure, asset identifier. Contextualization may add further context such as plant identifier, plant type, reliability indicator, or plant alarm limits. In a next step, application context (model identifier, third party exchange, etc.) may be added in addition to the technical asset structure and other asset management (asset network, etc.) of one or more plants or sites.

[0079] The second processing layer 16 is communicatively coupled to an external processing layer 30 via an interface 26 to an external network. The external processing layer 30 may be a computing or cloud environment that provides virtualized computing resources such as data storage and computing power. The second processing layer 16 is configured to provide plant-specific data 24 from one or more chemical plants 12 to the external processing layer 30. Such data may be provided in real time or on demand. The second processing layer 16 is configured to manage data transfer to and / or from the external processing layer in real time or on demand. The second processing layer 16 may provide the plant-specific data 24 to the interface 26 to the external network based on an identifier added, for example, by contextualization. Such an identifier may be a confidentiality identifier based on which such data is not provided to the interface 26 to the external network. The second processing layer 16 may further be configured to remove at least a portion of the data transferred to the external processing layer 30.

[0080] The external processing layer 30 is configured to aggregate plant-specific data from multiple chemical plants and / or store historical data from multiple chemical plants. In this way, data storage can be externalized, reducing the required on-premise storage capacity and making historical transfer redundant. Furthermore, such a storage concept allows for storing historical data in the second processing tier 16 during hot windows, which are critical time frames that allow the system 10 to monitor and / or control a chemical plant in island mode without an external network connection. In this way, the availability of the system 10 for monitoring and / or control is always guaranteed.

[0081] The second processing layer 16 and the external processing layer 30 are configured to host and / or organize processing applications. In particular, the second processing layer 16 may host and / or organize processing applications related to core plant operations, and the external processing layer 30 may be configured to host and / or organize processing applications related to non-core plant operations.

[0082] Additionally, the second processing layer 16 and the external processing layer 30 may be configured to exchange data with third-party management systems, e.g., via integration of a third-party external processing layer, to organize data visualization, to organize computing processing workflows, to organize data calculations, to organize APIs to access data, to organize data storage, transfer, and calculation metadata, to provide an interactive plant data work environment for users, e.g., operators, and to verify and improve data quality.

[0083] FIG. 2 shows a second schematic diagram of a system 10 for monitoring and / or controlling one or more chemical plants 12 .

[0084] The system 10 shown in Figure 2 is similar to the system shown in Figure 1, except that the system of Figure 2 includes a second processing tier with a processing management system 32 and an intermediate processing system 34. The intermediate processing systems 34.1, 34.2 are configured in a secure network security domain via a firewall 40.

[0085] The intermediate processing systems 34.1, 34.2 may be configured to ingest process or asset or process-specific data 22 from individual or multiple chemical plants 12. Such data may be contextualized at the plant level in the intermediate processing systems 34.1, 34.2, and the plant-specific data 38 may be provided to the process management system 32 where further contextualization may be performed across the plant level, for example, at the Verbund or site level. In this setup, data contextualization is staggered between different system 10 tiers, with each tier 14, 34, 32 mapping the contextual information available at the respective tier 14, 34, 32.

[0086] FIG. 3 shows a third schematic diagram of a system 10 for monitoring and / or controlling one or more chemical plants 12 .

[0087] The system 10 shown in Figure 3 is similar to the systems shown in Figures 1 and 2. However, the system of Figure 3 includes a monitoring device 44 communicatively coupled to the process management system 32 or external processing layer 30. The monitoring device 36 may be configured to forward monitoring data to the process management system 32 or external processing layer 30. The process management system 32 or external processing layer 30 may be configured to manage multiple monitoring devices 44. Because such IoT devices are not considered trusted, the monitoring data provided by the monitoring device 44 may be one-way tagged, and any control loops associated with the chemical plant 12 may include filters for such tags. Therefore, such data is not used in managing the chemical plant 12.

[0088] FIG. 4 shows a schematic diagram of the data contextualization concept of the system 10 as shown in FIGS.

[0089] The system 10 of Figures 1-3 includes two internal processing layers 14, 16, 32, 34 and an external processing layer 30. The first processing layer 14 may be a distributed control system for supervising, monitoring, and controlling physical processes within the chemical plant 12. The first processing layer 14 may be configured to provide process or asset- or process-specific data. The second processing layer 16, 32, 34 may include an intermediate processing system 34 and a process management system 32. The intermediate processing system 34 may be configured as an edge computing layer. Such a layer may be associated with Level 3 of an individual plant. The intermediate processing system 34 may: Processing or collection of asset- or processing-specific data; Level 2 basic automation system interaction, Initial contextualization (bottom-up approach) where context is added within distributed edge devices based on what is known at Level 2 and Level 1; It may be configured for:

[0090] The process management system 32 may be configured as a centralized edge computing tier. Such a tier may be associated with Level 4 of multiple plants. The process management system 32 may: integration of data from various distributed edge devices, including intermediate processing systems 34 or monitoring devices 44; Further contextualization (bottom-up approach) where additional context is added based on the distributed pre-processed context in distributed edge devices; It may be configured for:

[0091] The external processing layer 30 may be configured as a centralized cloud computing platform. Such a platform may be associated with Level 5 of multiple plants. The external processing layer 30 may be configured as a manufacturing data workspace with complete data integration across multiple plants, including the transfer and streaming of manufacturing data history and the collection of all data from all edge components. In this way, complete contextualization of all lower-level contexts may be integrated into the external processing layer 30 of multiple plants. Thus, the external processing layer 30 may: Run cloud-native apps and Connect with external PaaS and SaaS tenants, Integrate machine learning with manufacturing data and processing, train-test-deploy, Visualize data, access apps, and organize them It may be further configured as follows.

[0092] The system architecture may realize a bottom-up contextualization concept. Such a concept is illustrated in FIG. 4. In a bottom-up context, all information available at lower levels may already be added to the data as attributes, so that the context at the lower levels is not lost. Here, the first processing layer 14, as the lowest context level, may contain measurements 11 contextualized with respect to the item 13 at which the measurement was taken. The intermediate processing system 34 may be further contextualized by adding tags 15 related to individual chemical plants 12. The process management system 32 may be further contextualized by adding tags 17 related to multiple chemical plants 12 and / or business information. The external processing layer 30 may be further contextualized by adding tags 19 related to multiple plants and / or external context information, for example, from a third party.

[0093] The concept of contextualization can cover at least two basic types of context. A data point may be a functional location within a production environment that includes multiple chemical plants. This may cover information about what and where this data point represents within the production environment. Examples include connections to functional locations, attributes about the physical assets from which the data is collected, etc. This context can be beneficially used in later applications to explain which data is available for which plants and assets.

[0094] Another type may be a confidentiality classification. Such a tag may be added at the lowest possible level, and this information may be propagated to further processing layers. Such tags may be added automatically or manually. For example, technical measures may be implemented, such as through filters embedded in a firewall, to automatically prohibit "strictly confidential" data from being integrated up to the external processing layer 30. Sharing data with an external party automatically notifies the party that "confidential data" is being shared. An automatic contract check may be implemented to verify whether this data can be shared with this external party.

[0095] Overall, the contextualization concept thus realized allows for highly efficient data usage in processing applications deployed at any layer of the system.

[0096] FIG. 5 shows a flow chart of a schematic diagram of a method for monitoring and / or controlling one or more chemical plants.

[0097] Preferably, the method is executed on the distributed computing system shown in Figures 1-3 associated with the chemical plant 12 and including a first processing tier 14 communicatively coupled to second processing tiers 16, 32, 34. The method may perform all steps described in the context of Figures 1-4, including steps related to contextualization, data processing, processing application management, and monitoring device management.

[0098] In a first step 61, process or asset or process specific data of the chemical plant 12 is provided via the first process layer 14 to the second process layer 16, 32, 34.

[0099] In a second step 63, the process or asset or process specific data is contextualized via a second process layer 16, 32, 34 to generate plant specific data.

[0100] In a third step 65, plant-specific data for one or more chemical plants 12 is provided via a second processing layer 16, 32, 34 to an interface 26 to an external network.

[0101] In a fourth step 67, the one or more chemical plants are monitored and / or controlled via the second processing layer 16, 32, 34 or the first processing layer 14 based on the process or asset or process-specific data or the plant-specific data. The monitoring and / or control of the one or more chemical plants 12 may be performed via the second processing layer 16, 32, 34 or the external processing layer 30 based on the plant-specific data. Additionally, the monitoring and / or control may be performed via the first processing layer 14 based on the process or asset or process-specific data. Such monitoring and / or control may be performed via a processing application that ingests the respective data and provides monitoring and / or control of the outputs, as further shown in FIGS. 6-8.

[0102] FIG. 6 shows a schematic diagram of a distributed computing system for monitoring and / or controlling one or more chemical plants having multiple assets via a distributed computing system 10 with more than two deployment layers 14, 16, 30.

[0103] The schematic diagram of FIG. 6 depicts a containerized application organization at various deployment tiers 14, 16, and 30. The system 10 includes an external processing system 30, a second processing tier 16, and a first processing tier 14. Here, the second processing tier 16 may include greater storage and computing resources than the first processing tier 14, and / or the external processing tier 30 may include greater storage and computing resources than the second processing tier 16. The architecture and functionality of the system 10 may conform to the architecture and functionality described with respect to FIGS. 1-3. In particular, the first and second processing tiers 14, 16 may be configured within secure networks 20, 40, and 18. The first processing tier 14 may be communicatively coupled to the second processing tier 16, which may be communicatively coupled to the external processing tier 30 via an external network 24.

[0104] The orchestration applications 56, 58 may be hosted by the external processing layer 30 and the second processing layer 16, 32, 34, respectively. Accordingly, the containerized application or container images 48, 50 may be stored in registries of the external processing layer 30 and the second processing layer 16, 32, 34, respectively. The containerized applications 48, 50 for execution may include one or more operations for ingesting input data, providing the input data to a respective asset or plant model that generates output data, and providing the generated output data for controlling and / or monitoring the chemical plant 12. In this manner, the external processing layer 30 and the second processing layer 16, 32, 34 act as a facilitation layer that reduces the computing and storage resources required for the first processing layer 14 at the asset level.

[0105] FIG. 7 shows a flowchart of a schematic diagram of a method for monitoring and / or controlling a chemical plant 12 having multiple assets via a distributed computing system 10 as may be implemented in the system 10 shown in FIGS. 1-4.

[0106] In a first step 60, a containerized application 48, 50 is provided that includes an asset or plant template that specifies input data, output data, and an asset or plant model. The containerized application 48, 50 may be created on the external processing layer 30 or modified on the second processing layer 30. An external containerized application from a third-party environment may be provided.

[0107] In a second step 62, the containerized applications 48, 50 are deployed to run in at least one of the deployment tiers 30, 32, 16, 34, 14, where the deployment tier 30, 32, 16, 34, 14 is assigned based on input data, load indicators, or system tier tags, and the containerized applications 48, 50 may execute in the assigned deployment tier 30, 32, 16, 34, 14 to generate output data for controlling and / or monitoring the chemical plant 12. The deployment may be managed by an integration application 56, 50 that manages the deployment of the containerized applications 48, 50 based on the input data, load indicators, or system tier tags. The integration application may be hosted by the second processing tier 16, 23, 34 and / or the external processing tier 30. The integration applications 56, 58 hosted by the second processing tier 16, 32, 34 may manage critical containerized applications 48, 50, while the orchestration applications 56, 58 hosted by the external processing tier 30 may manage non-critical containerized applications 48, 50. The allocation of deployment tiers 30, 32, 34, 16, 14 may be based on input data that depends on data availability indicators, criticality indicators, or latency indicators. Containerized applications from third-party environments can be deployed to run on the external processing tier 30.

[0108] The orchestration applications 56, 58 may be hosted by the external processing tier 30 and the second processing tier 16, respectively. The orchestration applications 56, 58 may deploy the containerized applications 48, 50 to any deployment tier 30, 16, 14. The containerized applications 48, 50 may then be executed in the respective deployment tier 30, 16, 14 by running the processing applications 46, 52, 54 in a sandbox-type environment. The deployment tiers 30, 16, 14 may be assigned based on input data, load indicators, or system tier tags. For example, management of a critical containerized application 50 may optionally be assigned to the second processing tier 16 based on historical criteria reflecting the time frame of historical data available on the first or second processing tier 16. Advantageously, the containerized applications 48, 50 may be deployed to multiple assets or plants of the same type. Additionally, the containerized applications 50, 48 may be modified based on input and output data provided by containerized applications 46, 52, 54 executed on multiple assets or plants of the same type.

[0109] In a third step 64, the containerized applications 48, 50 may be monitored during or after each execution based on a confidence level of the input data, asset model, or plant model. Based on the resulting confidence level, an event signal or a change to the asset or plant model may be triggered. Such a trigger may be set if the confidence level exceeds a threshold. Such a threshold may be predefined or dynamic. If a trigger is set, the asset or plant model change may be executed, for example, in the second processing layer 16, 32, 34 or the external processing layer 30.

[0110] In a fourth step 66, the generated output data is provided for controlling and / or monitoring the chemical plant 12. Such output data may be passed to a persistence instance after execution of the containerized application 48, 50. In particular, such output data may be passed to a control instance on, for example, the first processing tier 14 of the chemical plant 12. Additionally or alternatively, such output data may be passed to a monitoring instance on the first processing tier 14, the second processing tier 16, 32, 34, or the external processing tier 30. The output data may be passed to, for example, a client application for display to an operator or to a further containerized application 48, 50 for execution.

[0111] FIG. 8 shows a schematic diagram of systems 10.2, 10.2 for monitoring and / or controlling multiple chemical plants 12.1, 12.2 within separate secure networks 20.1, 20.2 configured for data and processing application transfer. FIG. 8 illustrates the system 10 of FIGS. 1-3, including, by way of example, first and second processing layers 14, 16, 32, 34 and an external processing layer 30. Other system architectures may be similarly suitable for processing applications and data transfer. Both systems are associated with separate secure networks 20.1, 20.2 and communicatively coupled to external networks 24.1, 24.2 via interfaces 26.1, 26.2.

[0112] Systems 10.1, 10.2 are configured to exchange process- or asset- or process-specific data or processing applications based on transfer tags. By adding transfer tags at the earliest possible level, i.e., where the data or application is generated or where it first enters the system, the transfer tag becomes an inherent part of any data point or application as soon as the tag is added and follows the data or application on its path through systems 10.1, 10.2. Such transfer tags enable seamless and secure integration of external data sources or external applications and transfer of data or applications to external resources.

[0113] In one case shown in FIG. 8, an application 48 is exchanged between systems 10.1 and 10.2. In this example, the containerized application 48 is transferred via external processing layers 30.1 and 30.2, which are communicatively coupled to the two systems 10.1 and 10.2. Here, the external processing layer 30.1 is communicatively coupled to system 10.1, and the external processing layer 30.2 is communicatively coupled to system 10.2. The exchange of the containerized application 48 is performed indirectly via the external processing layers 30.1 and 30.2. The containerized application is tagged with a transfer tag that includes two transfer settings related to confidentiality settings and / or third-party transfer settings. In this manner, for example, if a transfer using a respective third-party identifier is not associated with a third-party identifier stored in a database of permitted third-party transfers for the processing application 48, the transfer may be prohibited based on a compliance check by the external processing layer 30.2. Similarly, process or asset or process-specific data may be transferred 72 between systems 10.1 and 10.2. Any transfer between systems 10.1, 10.2 may then be followed by a further transfer from the external processing layer 30.1, 30.2 to the respective system 10.1, 10.2.

[0114] Additionally, such forwarding based on forwarding tags can be performed directly between systems 10.1, 10.2 between processing layers 32, 16 associated with secure networks 20.1, 20.1. Such forwarding based on forwarding tags can be achieved via a secure connection 74 between such layers 16, 23, such as a VPN connection. Any forwarding between systems 10.1, 10.2 can then be followed by further forwarding between system components within secure networks 20.1, 20.2 or to processing layers 30.1, 30.2 external to the respective systems 10.1, 10.2. By attaching forwarding tags to any data points and processing applications, whether containerized or not, third-party forwarding between systems 10.1, 10.2 within separate secure networks 20.1, 20.1 can be securely handled.

[0115] Any of the components described herein used to implement the methods described herein may be in the form of a distributed computer system having one or more processing devices capable of executing computer instructions. The components of the computer system may be communicatively coupled (e.g., networked) to other machines in a local area network, a secure network, an intranet, an extranet, or the Internet. The components of the computer system may operate as peer machines in a peer-to-peer (or distributed) network environment. Part of the computer system may be a virtualized cloud computing environment, an edge gateway, a web appliance, a server, a network router, a switch, or a bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify operations to be performed by that machine. Furthermore, it should be understood that terms such as "computer system," "machine," "electronic circuit," and the like are not necessarily limited to a single component, but are intended to include a collection of machines that individually or jointly execute a set (or sets) of instructions to perform any one or more of the methodologies described herein.

[0116] Some or all of the components of such a computer system may be utilized by or exemplify any of the components of system 10. In some embodiments, one or more of these components may be distributed across multiple devices or integrated into fewer devices than shown. Furthermore, some components may refer to physical components implemented in hardware, while other components may refer to virtual components implemented in software on remote hardware.

[0117] Any processing layer may include a general-purpose processing device such as a microprocessor, microcontroller, central processing unit, etc. More specifically, the processing layer may include 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 a combination of instruction sets. The processing layer may also include one or more special-purpose processing devices, such as an Application-Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a Complex Programmable Logic Device (CPLD), a Digital Signal Processor (DSP), a network processor, etc. The methods, systems, and devices described herein may be implemented as software in a DSP, microcontroller, or any other side processor, or as hardware circuitry within an ASIC, CPLD, or FPGA. It should be understood that the term "processing tier" may refer to one or more processing devices, such as a distributed system of processing devices located across multiple computer systems (e.g., cloud computing), and is not limited to a single device unless otherwise specified.

[0118] Any processing layer may include a suitable data storage device, such as a computer-readable storage medium, on which is stored one or more sets of instructions (e.g., software) embodying any one or more of the methodologies or functions described herein. The instructions may also reside, completely or at least partially, within a main memory and / or within a processor during its execution by a processing device, which may constitute a computer system, the main memory, and the computer-readable storage medium. The instructions may further be transmitted or received over a network via a network interface device.

[0119] A computer program for implementing one or more of the embodiments described herein may be stored and / or distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as over the Internet or other wired or wireless communication systems, although the computer program may also be presented over a network such as the World Wide Web and may be downloaded into the working memory of a data processor from such a network.

[0120] The terms "computer-readable storage medium," "machine-readable storage medium," and the like should be interpreted to include a single medium or multiple media (e.g., centralized or distributed databases, and / or associated caches and servers) that store one or more sets of instructions. The terms "computer-readable storage medium," "machine-readable storage medium," and the like should also be interpreted to include any transitory or non-transitory medium that can store, encode, or carry a set of instructions for execution by a machine, whereby the machine performs any one or more of the methodologies of the present disclosure. Thus, the term "computer-readable storage medium" should be interpreted to include, but is not limited to, solid-state memory, optical media, and magnetic media.

[0121] Some portions of the detailed descriptions may be presented in terms of algorithms and symbolic representations of operations on data bits within a computer memory. These algorithmic descriptions and representations are the means used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. An algorithm is here, and generally, conceived to be a self-consistent sequence of steps leading to a desired result. The steps are those requiring physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, transferred, combined, compared, and otherwise manipulated. It is sometimes convenient, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or the like.

[0122] It should be noted, however, that all of these and similar terms are associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. As is clear from the preceding discussion, unless otherwise stated, throughout the description, terms such as "receive," "retrieve," "send," "calculate," "generate," "add," "subtract," "multiply," "divide," "select," "optimize," "calibrate," "detect," "store," "execute," "analyze," "determine," "enable," "identify," "modify," "convert," "apply," "extract," and the like will be understood to refer to operations and processing of a computer system or similar electronic computing device that manipulates and transforms data represented as physical (e.g., electronic) quantities in the registers and memory of the computer system into other data similarly represented as physical quantities in the memory or registers of the computer system, or other such information storage, transmission, or display devices.

[0123] It should be noted that embodiments of the present invention are described with reference to different subject matter: in particular, some embodiments are described with reference to method-type claims, and other embodiments are described with reference to system-type claims.

[0124] However, those skilled in the art will gather from the above and following descriptions that, unless otherwise noted, any combination of features belonging to one type of subject matter, as well as any combination between features relating to different subjects, is considered to be disclosed in the present application, although all features may be combined to provide synergistic effects that are greater than the simple sum of the features.

[0125] While the invention has been illustrated and described in detail in the drawings and the foregoing description, such illustration and description are to be considered exemplary or exemplary, and not restrictive. That is, the invention is not limited to the disclosed embodiments. Other variations to the disclosed embodiments can be understood and practiced by those skilled in the art from a study of the drawings, the disclosure, and the appended claims. In some instances, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring the disclosure.

[0126] In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude a plurality. A single processor or controller or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. Reference signs in the claims are not to be construed as limiting the scope.

Claims

1. 1. A method for monitoring and / or controlling a chemical plant (12) having multiple assets via a distributed computing system (10) with three or more deployment layers (14, 16, 30, 32, 34), the deployment layers (14, 16, 30, 32, 34) including at least two of a first processing layer (14), a second processing layer (16, 32, 34), and an external processing layer (30), the method comprising: providing (60) a containerized application (48, 50) including input data, output data, and an asset or plant template that specifies an asset or plant model; deploying (62) the containerized application (48, 50) to run in at least one of the deployment tiers (14, 16, 30, 32, 34), the deployment tier (14, 16, 30, 32, 34) being assigned based on the input data, load indicators, or system layer tags, and executing the containerized application (46, 52, 54) in the assigned deployment tier (14, 16, 30, 32, 34) to generate output data for controlling and / or monitoring the chemical plant (12); providing (66) the generated output data for controlling and / or monitoring the chemical plant (12); A method comprising:

2. 2. The method of claim 1, wherein the second processing tier (16, 32, 34) includes greater storage and computing resources than the first processing tier (14) and / or the external processing tier (30) includes greater storage and computing resources than the second processing tier (16, 32, 34).

3. 3. The method of claim 1, wherein the first and second processing layers are configured within a secure network, the first processing layer being communicatively coupled to the second processing layer, and the second processing layer being communicatively coupled to the external processing layer via an external network.

4. 10. The method of any preceding claim, wherein the containerized application (48, 50) for execution includes one or more operations for ingesting input data, providing the input data to a respective asset or plant model that generates output data, and providing the generated output data to control and / or monitor the chemical plant (12).

5. 10. The method of any preceding claim, wherein the deployment is managed by an integration application (56, 58) that manages the deployment of containerized applications (48, 50) based on the input data, the load indicators, or the system layer tags.

6. The method of claim 5 , wherein the integrated application (56, 58) is hosted by the second processing layer (16, 32, 34) and / or the external processing layer (30).

7. 7. The method according to claim 5 or 6, wherein the integrated application (58) hosted by the second processing tier (16, 32, 34) manages critical containerized applications (48, 50) and the integrated application (56) hosted by the external processing tier (30) manages non-critical containerized applications (48, 50). The method described.

8. 8. The method of claim 5, wherein the management of critical containerized applications (56, 58) is assigned to the second processing tier (16, 32, 34) based on historical criteria that reflect a time frame of historical data available at the first or second processing tier (14, 16, 32, 34).

9. 10. The method of any of the preceding claims, wherein the allocation of the deployment tiers (14, 16, 30, 32, 34) based on input data depends on a data availability indicator, an importance indicator, or a latency indicator.

10. 10. The method of any preceding claim, wherein the containerized application is deployed to multiple assets or plants of the same type.

11. 10. The method of any preceding claim, wherein the containerized application (48, 50) is modified based on the input data and the output data provided by containerized applications (48, 50) executed on multiple assets or plants (12) of the same type.

12. 10. The method of any preceding claim, wherein the containerized application (48, 50) is monitored based on a confidence level of the input data, the asset model, or the plant model.

13. The method of claim 12 , wherein an event signal or a change to the asset or plant model is triggered when the confidence level falls below a confidence threshold.

14. 14. The method of claim 12 or 13, wherein the modification of the asset or plant model is performed in the second processing layer (15, 32, 34) or the external processing layer (30).

15. 10. The method of any preceding claim, wherein an external containerized application from a third party environment is provided and deployed to run on the external processing layer (30).

16. 1. A system (10) for monitoring and / or controlling a chemical plant (12) having multiple assets with three or more deployment tiers (14, 16, 30, 32, 34), the deployment tiers (14, 16, 30, 32, 34) including at least two of a first processing tier (14), a second processing tier (16, 32, 34), and an external processing tier (30), the system (10) comprising: providing (60) a containerized application (48, 50) including input data, output data, and an asset or plant template that specifies an asset or plant model; deploying (62) the containerized application (48, 50) to run in at least one of the deployment tiers (14, 16, 30, 32, 34), the deployment tier (14, 16, 30, 32, 34) being assigned based on the input data, load indicators, or system layer tags, executing the containerized application (46, 52, 54) in the assigned deployment tier (14, 16, 30, 32, 34) and generating output data for controlling and / or monitoring the chemical plant (12); The generated output data is used to control and / or monitor the chemical plant (12). (66) providing data; The system (10) is configured as follows.

Images