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

Abstract

A method for monitoring and / or controlling a chemical plant (12) having a plurality of assets via a distributed computing system (10) having more than two deployment layers (14, 16, 30, 32, 34), wherein the deployment layers (14, 16, 30, 32, 34) include 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 the steps of: providing (60) a containerized application (48, 50) including an asset or plant template specifying input data, output data and an asset or plant model , ‑deploying (62) a containerized application (48, 50) for execution on at least one of the deployment layers (14, 16, 30, 32, 34), wherein the deployment layers (14, 16, 30, 32, 34) are assigned based on input data, load indicators, or system layer tags, and executing the containerized application (46, 52, 54) on the assigned one or more deployment layers (14, 16, 30, 32, 34) to generate output data for controlling and / or monitoring a chemical plant (12), ‑providing (66) the generated output data for controlling and / or monitoring the chemical plant (12).

Description

Technical Field

[0001] The present disclosure relates to a method for monitoring and / or controlling a chemical plant having a plurality of assets via a distributed computing system having a plurality of deployment tiers. Background Art

[0002] Chemical production is a highly sensitive production environment, especially in terms of safety. Chemical plants typically include multiple assets to produce chemical products. Multiple sensors are distributed in such plants for monitoring and control purposes and collect large amounts of data. Therefore, chemical production is a data-heavy environment. However, the benefits of this data to improve the production efficiency of one or more chemical plants have not been fully exploited to date.

[0003] Therefore, there is a great deal of interest in applying new technologies in cloud computing and big data analytics. However, unlike other manufacturing industries, the process industry needs to comply with very high security standards. For this reason, the computing infrastructure is often isolated and access to monitoring and control systems is highly restricted. Due to such security standards, latency and availability considerations conflict with the simple migration of hitherto embedded control systems to, for example, cloud computing systems. Bridging the gap between highly proprietary industrial manufacturing systems and cloud technologies is one of the main challenges.

[0004] WO2016065493 discloses a client device and system for data acquisition and preprocessing of massive process-related data from at least one CNC machine or industrial robot, and sending the process-related data to at least one data recipient, such as the cloud-based server. The client device includes at least one first data communication interface with at least one controller of the CNC machine or industrial robot, the data communication interface being used to continuously record 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, which maps at least the recorded non-real-time data to the recorded hard real-time data to aggregate a collection of contextualized process-related data. In addition, the client device includes at least one second data interface, which is used to send the collection of contextualized process-related data to the data recipient and to perform further data communication with the data recipient.

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

[0006] US20160320768A1 discloses an example network environment for monitoring a plant process, wherein a system computer operates as a root cause analyzer. The system computer communicates with a data server to access data of measurable process variables collected from a historical database. The data server is communicatively coupled to a distributed control system (DCS), which in turn transmits the collected data to the data server via a communication network.

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

[0008] A method for monitoring and / or controlling a chemical plant having a plurality of assets via a distributed computing system having more than two deployment layers is proposed. The deployment layers include at least two of a first processing layer, a second processing layer, and an external processing layer. The method comprises the following steps:

[0009] - Provides a containerized application of an asset or factory template containing specified input data, output data and asset or factory models,

[0010] - deploying the containerized application to execute on at least one of the deployment layers, wherein the allocation of the deployment layers depends on the input data, the load indicator or the system layer tag, and executing the containerized application on the corresponding deployment layer to generate output data for controlling and / or monitoring the chemical plant,

[0011] - Providing the generated output data for use in controlling and / or monitoring the chemical plant.

[0012] A system for monitoring and / or controlling a chemical plant having a plurality of assets using a deployment layer having more than two layers, wherein the deployment layer comprises at least two of a first process layer, a second process layer, and an external process layer, the system being configured to:

[0013] - providing a containerized application including an asset or factory template specifying input data, output data and an asset or factory model,

[0014] - deploying a containerized application to execute on at least one of the deployment layers, wherein the deployment layers are assigned based on input data, load indicators, or system layer tags, and executing the containerized application on the assigned one or more deployment layers to generate output data for controlling and / or monitoring the plant,

[0015] - Providing the generated output data for use in controlling and / or monitoring the chemical plant.

[0016] The invention further relates to a distributed computer program or computer program product having computer-readable instructions which, when executed on one or more processors, cause the one or more processors to perform a method for monitoring and / or controlling one or more chemical plants as described herein. The invention further relates to a computer-readable non-volatile or non-transitory storage medium having computer-readable instructions which, when executed on one or more processors, cause the one or more processors to perform a method for monitoring and / or controlling one or more chemical plants as described herein.

[0017] The proposed approach allows for efficient application processing in distributed computing systems for controlling and / or monitoring chemical plants. By introducing different process and storage layers, the massive data transfer, orchestration and execution of applications can be distributed on different layers, thereby enabling flexible application processing. Furthermore, the concept of three system layers allows for highly available and secure monitoring and / or control, since the second processing and external management layers are redundant. In other words, more critical tasks can be assigned to local computing resources that do not rely on an external network, while less critical tasks can be assigned to external computing resources. Another advantage is that, based on the context, the approach enables automation of application deployment and automatic identification of the need for retrofitting of additional sensors or IOT sensors.

[0018] In addition, the proposed method can be adapted to multiple chemical plants via a second processing layer or an external processing layer. Therefore, the method realizes highly scalable application orchestration for more reliable and enhanced monitoring and / or control of chemical plants. In particular, the orchestration of containerized applications in different application environments can be organized to meet the specific needs of the process industry. For example, the deployment of containerized applications that obtain input data can be simplified for multiple assets even in multiple plants. In addition, depending on the specific data required by the containerized application and the computing resources required to run such applications, the appropriate processing layer can be selected to follow the high availability standards of the chemical plant. For example, applications that obtain plant-specific computationally intensive applications can be executed on the second processing layer, while process applications that obtain asset or process-specific data and require low latency can be executed on the first processing layer. Other criteria can be defined when to orchestrate on which deployment layer.

[0019] The following description relates to the above-mentioned system, method, computer program, computer-readable storage medium. In particular, the system, input unit, computer program and computer-readable storage medium are configured to perform the method steps as described above and further described below.

[0020] In the context of the present invention, a chemical plant refers to any manufacturing facility based on chemical processes, such as using chemical processes to convert raw materials into products. In contrast to discrete manufacturing, chemical manufacturing is based on continuous or batch processes. Therefore, the monitoring and / or control of chemical plants is time-dependent and therefore based on large time series data sets. A chemical plant may include more than 1,000 sensors, generating measurement data points every few seconds. Such dimensions result in the need to process several terabytes of data in a system for controlling and / or monitoring a chemical plant. A small chemical plant may include several thousand sensors, generating data points every 1 to 10 seconds. For comparison, a large chemical plant may include tens of thousands of sensors, such as 10,000 to 30,000, generating data points every 1 to 10 seconds. Contextualizing such data results in processing hundreds of GB to several TB of data.

[0021] Chemical plants can produce products via one or more chemical processes, which convert raw materials into products via one or more intermediate products. Preferably, chemical plants provide packaging facilities for producing products, which can be used as raw materials for subsequent steps in the value chain. Chemical plants can be large factories, such as oil and gas facilities, gas purification plants, carbon dioxide capture facilities, liquefied natural gas (LNG) plants, refineries, petrochemical facilities or chemical facilities. For example, an upstream chemical plant in petrochemical process production includes a steam cracker, which is processed into ethylene and propylene from naphtha. These upstream products can then be provided to further chemical plants to derive downstream products, such as polyethylene or polypropylene, which can be used again as raw materials for chemical plants that derive further downstream products. Chemical plants can be used to manufacture discrete products. In one example, a chemical plant can be used to manufacture a precursor for polyurethane foam. Such precursors can be provided to a second chemical plant to manufacture discrete products, such as a separator comprising polyurethane foam.

[0022] The production of the value chain from various intermediate products to the final product can be dispersed across different locations or integrated into an integrated site or chemical park, which consists of a network of interconnected chemical plants where the product produced in one plant can serve as a feedstock for another plant.

[0023] A chemical plant may include multiple assets, such as heat exchangers, reactors, pumps, pipelines, distillation or absorption towers, etc. In a chemical plant, some assets may be critical. Critical assets are those assets that will seriously affect the operation of the plant in the event of an interruption. This asset interruption may cause the manufacturing process to be compromised. It may cause product quality to deteriorate or even stop manufacturing. In the worst case, fire, explosion or toxic gas release may be the result of such an interruption. Therefore, depending on the chemical process and the chemicals involved, such critical assets may require stricter monitoring and / or control than other assets. In order to monitor and / or control chemical processes and assets, multiple actors and sensors can be embedded in the chemical plant. Such actors or sensors can provide process or asset specific data related to, for example, the status of individual assets, the status of individual actors, the composition of chemicals, or the status of chemical processes. In particular, process or asset specific data includes one or more of the following data categories:

[0024] - process operation data, such as the composition of raw materials or intermediate products,

[0025] -Process monitoring data, such as flow rate, material temperature,

[0026] -Asset operating data, such as current, voltage, and

[0027] -Asset monitoring data, such as asset temperature, asset pressure, vibration.

[0028] In the context of the present disclosure, an asset may include any component of a chemical plant, such as equipment, instrument, machine, process, or process component. Thus, an asset model may relate to a machine, equipment, instrument, process, or process component model.

[0029] Process or asset specific data refers to data that is related to a specific asset or process and is 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 identifiers for specific assets, or process identifiers for specific process parts or stages. Such process or asset specific data may be collected at the lowest or first processing layer and contextualized with respect to specific assets or processes in individual plants. Such contextualization may involve context available at the first processing layer. Such context may be related to a single plant.

[0030] Plant-specific data refers to process or asset-specific data that is contextualized about one or more plants. Such plant-specific data can be collected on the second processing layer and contextualized about multiple plants. Specifically, contextualization can involve context available on the second processing layer. Via contextualization, contexts such as plant identifiers, plant types, reliability indicators, or alarm limits of plants can be added to process or asset-specific data points. In a further step, technical asset structures, other asset management structures (such as asset networks), or application contexts (such as model identifiers, third-party exchanges) of one or more plants, integrated bases, or chemical parks can be added. This overall context can be derived from a functional location or digital twin, such as a digital piping and instrumentation diagram, a 3D model, or a scan with xyz coordinates of a plant asset. Additionally or alternatively, a local scan from a mobile device linked to, for example, a piping and instrumentation diagram can be used for contextualization.

[0031] In particular, plant-specific data related to the interface between chemical plants in the manufacturing chain can be provided on the second processing layer or the external processing layer. Therefore, monitoring and / or control, such as abnormal detection, set point guidance and optimization in the chain across multiple plants, can be enhanced. In order to monitor and / or control the chain across multiple plants, a process application with an online input / output data profile can be used. Such data and process applications can be transmitted between plants. In combination with the quality and energy balance that can be monitored, such process applications can optimize the entire chain across multiple chemical plants, rather than the individual plants in the chain.

[0032] The contextualization process refers to linking data points available in one or more storage units. One or more such units may be persistent or non-volatile storage. The data points may be related to measurements or contextual information. The (one or more) storage units may be part of the first processing layer, the second processing layer, the external processing layer, or distributed on two or more of these layers. Links may be generated dynamically or statically. For example, a predefined or dynamically generated script may generate dynamic or static links between information data points in one processing layer or across processing layers. Links may be established by generating a new data object including the link data itself and storing such new data object in a new instance. If the copy is stored elsewhere, any data points stored may be actively deleted. Therefore, 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 a metadata object with an embedded link to address or access corresponding data points in one or more distributed storage units. Therefore, any data points that can be addressed or accessed by the metadata object may remain in their original storage unit. For example, on the external processing layer, linking this information to form a new data object can still be performed. For retrieval of data, either data objects are accessed directly or metadata objects are used to address or access data distributed in one or more storage units. Any operation on such data (such as an application) can access such data directly or a non-persistent image of such data, such as from a cache memory or a persistent copy of the data.

[0033] In this context, a containerized application refers to a process application that can be executed in a packaged operating environment independent of the host operating system. Therefore, the application can be regarded as running in a sandbox. The containerized application can be based on a container image containing the application. The container image can include software components, such as a hierarchical tree of software components required to execute the corresponding application in the packaged operating environment. Such a containerized application can be stored in a registry of the second processing layer or the external processing layer or associated with the second processing layer or the external processing layer.

[0034] To deploy the containerized application, an orchestration application associated with the second processing layer or the external processing layer can manage the execution of the containerized application. Such management can include general operating environment configuration, such as storage or network for running the containerized application. Such management can further include host allocation, which defines the distribution between the central master node or one or more computing nodes to execute the application on the first processing layer, the second processing layer, or the external management layer. In particular, such allocation of computing resources depends on input data, load indicators, or system layer tags.

[0035] Input data may include real-time data from sensors (e.g., wireless monitoring devices or IoT devices), non-real-time data, or output data from deployed containers or executed applications. Such data may relate to machinery (e.g., machinery type or sensor data about machinery measurements), chemicals (e.g., chemical types or sensor data about chemical components measured in a chemical plant), processes (e.g., chemical process types or sensor data about chemical process measurements performed in a chemical plant), and / or plants (e.g., plant types or sensor data about chemical plant measurements, such as environmental measurements).

[0036] An asset or plant model may include data-driven or dynamic models, for example to provide health status, operational predictions, event predictions, or event triggers. An asset or plant model may be based on a pure data-driven model, a hybrid model combining data-driven and dynamic models, or a pure dynamic model. An asset or plant model may be further based on a scenario matrix that maps input data (e.g., sensor data) to specific events. An asset model may reflect the physical behavior of a single or multiple assets. A plant model may reflect the physical behavior of a portion of one or more plants, a complete plant, or multiple plants.

[0037] The output data may include key performance indicators related to the asset, plant, input data, asset model performance, or plant model performance. The asset model performance or plant model performance may be embedded in an asset or plant model hosted by a containerized application. Any generated output data of the method may be used as input data in one or more further containerized applications. In this way, a chain of containerized applications may be implemented to build a system of systems coverage and use the generated output data 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.

[0038] The containerized application may include one or more operations to obtain input data, provide the input data to a corresponding asset or plant model to generate output data, and provide the generated output data for controlling and / or monitoring the chemical plant. Such output data may be passed to a persistent instance after the application is executed. In particular, such output data may be passed to a control instance, such as on a first processing layer of the chemical plant. Additionally or alternatively, such output data may be passed to a monitoring instance on a first processing layer, a second processing layer, or an external processing layer. The output data may be passed to a client application, such as for display to an operator, or to a further containerized application for execution.

[0039] In one aspect, the second processing layer includes greater storage and computing resources than the first processing layer. Alternatively or additionally, the external processing layer may include greater storage and computing resources than the second processing layer. This stacked resource structure helps bridge the gap between the embedded control system of the chemical plant and available cloud technologies. In particular, the embedded control system of the chemical plant is limited in terms of storage and processing capabilities. Expanding such resources allows for enhanced monitoring and / or control.

[0040] The first processing layer and the second processing layer can be hosted, placed, configured in or inside a secure network. The first processing layer can be communicatively coupled to the second processing layer. The first processing layer may include at least one core process system associated with a 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 a separate plant. Therefore, the first processing layer monitors and / or controls the chemical plant at the lowest level. Further preferably, the first processing layer is configured to monitor and control key assets. Key assets refer to those assets that will have a serious impact on plant operations when interrupted. The interruption of this asset may cause the manufacturing process to be compromised. It may cause product quality to decline or even manufacturing to stop. In the worst case, fire, explosion or toxic gas release may be the result of such an interruption. Therefore, depending on the chemical process and the chemicals involved, such key assets may require stricter monitoring and / or control than other assets.

[0041] Additionally or alternatively, the second processing layer can be configured to provide data to an external network, for example via an interface to the external network. The second processing layer can be communicatively coupled to the external processing layer via the external network. Adding stacked processing layers in or within a secure network can allow compliance with high security standards in the chemical industry. In particular, this architecture allows the method to be performed completely independently of an external management layer, thereby enabling an island mode for one or more chemical plants. Island mode here refers to monitoring and / or controlling a chemical plant without access to an external network.

[0042] In another aspect, the first processing layer is configured to provide asset or process specific data, while the second processing layer is configured to provide plant specific data. The second processing layer may be configured to contextualize the asset or process specific data. This way the performance of the first processing layer is not affected. Since typical core process systems of the first processing layer, especially in older plants, do not have the required computing power, adding a further system with higher performance may even enable contextualization. Furthermore, the second processing layer allows data contextualization at the plant level rather than the asset level. Data contextualization in this context involves adding contextual information to the asset or process specific data or reducing the data size by preprocessing the asset or process specific data. Adding context may include adding (one or more) further information tags to the asset or process specific data. Preprocessing may include filtering, aggregation, normalization, averaging or inference of the asset or process specific data.

[0043] In one aspect, the first processing layer is associated with one or a single chemical plant. The first processing layer can be a core process system including one or more processing devices and storage devices. Such a layer can include one or more distributed processing and storage devices, which form a programmable logic controller (PLC) system or a distributed control system (DCS) distributed throughout the chemical plant with a control loop. Preferably, the first processing layer is configured to control and / or monitor chemical processes and assets at the asset level. Therefore, the first processing layer monitors and / or controls the chemical plant at the lowest level. In addition, the first processing layer can be configured to monitor and control key assets. Additionally or alternatively, the first processing layer is configured to provide process or asset specific data to the second processing layer. Such data can be provided to the second processing layer directly or indirectly.

[0044] On the other hand, the second processing layer is associated with more than one chemical plant. The second processing layer may include a process management system having one or more processing and storage devices. Preferably, the second processing layer or the process management system is configured to manage data transmission to and / or from the first processing layer. Further preferably, the second processing layer or the process management system is configured to host and / or orchestrate process applications. Such process applications can monitor and / or control one or more chemical plants or one or more assets. The process management system can be associated with one or more chemical plants. In other words, the process management system can be communicatively coupled to multiple first processing layers associated with one or more chemical plants.

[0045] On the other hand, the second processing layer may include an intermediate processing system and a process management system. Here, the intermediate processing system may be communicatively coupled to the first processing layer, preferably the core process system, and the process management system may be communicatively coupled to the intermediate layer. Preferably, the first processing layer and the process 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 layer. The process management system may be configured to provide plant specific data of one or more chemical plants to an interface with 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 layer of a chemical plant or multiple first processing layers of multiple plants. The process management system may be communicatively coupled to one or more intermediate processing systems. Adding an intermediate processing level to the second processing layer adds a further layer of security. It completely separates the first processing layer with a virus from any external network access. In addition, the intermediate layer allows further enhanced data processing capabilities by reducing the data transmission rate rate to the external processing layer through preprocessing, and allows improved data quality through contextualization. The intermediate processing system and the process management system may include one or more processing and storage devices.

[0046] On the other hand, a secure network is an isolated network that includes more than two secure zones separated by a firewall. Such a firewall can be a network or host-based virtual or physical firewall. Firewalls can be hardware or software based to control incoming and outgoing network traffic. Here, predetermined rules in the sense of a whitelist can define the allowed traffic via access management or other configuration settings. Depending on the firewall configuration, the secure zones may follow different security standards.

[0047] On the other hand, the first processing layer is hosted, placed or configured in or inside the first security area via the first firewall, and the second processing layer is hosted, placed or configured in or inside the second security area via the second firewall. In order to safely protect the first processing layer, the first security level can follow a higher security standard than the second security level. The security level can follow a general industry standard, such as described in the Namur document IEC 62443. The second processing layer can provide further isolation via a security zone. For example, the intermediate processing system can be hosted, placed or configured in or inside the third security area via the third firewall, and the process management system can be configured in the second security area via the second firewall. The third and second security areas can also be staggered in terms of security standards. For example, the third security area can follow a security standard higher than the second security area. This allows a higher security standard to be provided on the lower security area of ​​the first processing layer, and a lower security standard to be provided on the higher security area of ​​the second processing layer. In one embodiment, the first processing layer is inside the first security area, the process management system is inside the second security area, and the intermediate processing system is inside the third security area.

[0048] The second processing layer can be configured to contextualize the process or asset specific data. This way the performance of the first processing layer is not affected. Adding further systems with higher performance can even enable contextualization, as typical core process systems in older plants do not have the required computing power. Furthermore, the second processing layer, in particular the intermediate processing systems, allow data contextualization on a plant level instead of an asset level. Data contextualization in this context involves adding contextual information to the process or asset specific data or reducing the data size by preprocessing the process or asset specific data. Adding context may include adding one or more further information tags to the process or asset specific data. Preprocessing may include filtering, aggregating, normalizing, averaging or extrapolating the process or asset specific data.

[0049] On the other hand, unidirectional or bidirectional communication, such as data transmission or data access, can be implemented for data flows between different processing layers. In other words, the system can be configured to allow unidirectional or bidirectional communication, such as data transmission or data access between different processing layers. A data flow can include process or asset-specific data from a first processing layer, which is passed to a second processing layer and contextualized via the second processing layer and transmitted to an external processing layer. Contextualization can be performed on the second processing layer, the external processing layer, or both. In other words, the second processing layer, the external processing layer, or both can be configured to contextualize process or asset-specific data or plant-specific data. In addition, such data can be allocated for unidirectional or bidirectional communication depending on the criticality of the process or asset-specific data or plant-specific data. In other words, the system can be configured to allocate unidirectional or bidirectional communication to process or asset-specific data or plant-specific data depending on the criticality of the process or asset-specific data or plant-specific data. For example, by implementing a diode-type communication channel, data communication from a second or external processing layer to a critical asset can be prohibited. Such communication can only allow unidirectional communication from a critical asset to a processing layer, and vice versa.

[0050] On the other hand, data streams can be assigned critical or non-critical data. In other words, the system can be configured to assign critical or non-critical data tags. Critical data refers to data that is critical to the operation of a chemical plant, such as short-term data from which the operating point of the chemical plant is derived. Such critical data can cover a short-term range, such as a few hours or days in one or more weeks, which is required for the plant to operate in its optimized state. Non-critical data refers to data that is not critical to the operation of a chemical plant, such as medium- and long-term data for monitoring a chemical plant based on medium- and long-term behavior. Such non-critical data can cover medium- and long-term time ranges, such as weeks or months to a year or years, which is required, for example, to monitor and / or control one or more assets or one or more plants over a period of time. Such data can also be referred to as cold, warm and hot data, where hot data corresponds to critical data, warm data corresponds to medium-term non-critical data, and cold data corresponds to long-term non-critical data.

[0051] On the other hand, data contextualization is interleaved across system layers, processing layers, or processing systems included in such processing layers, with each layer mapping the context information available in the corresponding layer. In other words, the system can be configured to interleave data contextualization across system layers, processing layers, or processing systems included in such processing layers, with each layer mapping the context information available in the corresponding layer. Interleaving can include contextualization of asset or process specific data at different levels, thereby adding context information to a single plant level and / or a multi-plant level. In a layered system architecture, the context information available in one layer can be mapped to data provided by a lower layer or processing system. Here lower means closer to chemical plant data access. For example, process or asset specific data provided by a first processing layer can include context information at the asset level. In other words, the first processing layer can be configured to provide process or asset specific data including context information at the asset level. Such context information can be related to real-time information (e.g., measurement value, measurement quality, product quality, batch-related data, or measurement time). The context information at the asset level can be further related to asset specific information, such as asset identifiers, internal logistics, or measurement unit identifiers. Intermediate systems and process management systems may be configured to add or contextualize further context information to such process or asset specific data. Such context information may be related to the plant level rather than the asset level. For example, the context information relates to plant context such as plant identifier, plant type, reliability indicator, alarm limits, etc. or application context such as model identifier, third party exchange identifier, confidentiality identifier, etc. In this way, data quality may be improved to maximize context and improve data management and resulting monitoring and / or control capabilities via process applications.

[0052] On the other hand, the intermediate processing system is configured to contextualize the 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 related to the asset level or multiple assets individually, while homogeneous data refers to data related to a combination of assets or the same type of assets in a plant. The intermediate processing system can be configured to provide such plant-specific data to the process management system. The process management system can 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 a base level, such as a multi-plant or base context, including the technical asset structure of one or more plants or asset management information such as an asset network. Additionally or alternatively, such contextualization may include adding application context, such as a model identifier, a third-party exchange identifier, or a confidentiality identifier.

[0053] Additionally or alternatively, the first processing layer can be configured to provide asset or process specific data to the second processing layer. Such data can be provided to the second processing layer directly or indirectly. The second processing layer can be associated with one or more plants. The second processing layer can include a process management system and an optional intermediate processing layer. The first processing layer can include a plant-specific core process system. One or more core process systems can be optionally 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 can be configured to contextualize, store or aggregate data from one or more chemical plants, and / or to orchestrate process models for one or more chemical plants.

[0054] On the other hand, the intermediate processing system is configured to contextualize the 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 related to the asset level or multiple assets individually, while homogeneous data refers to data related to a combination of assets or the same type of assets in a plant. The intermediate processing system can be configured to provide such plant-specific data to the process management system. The process management system can 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 a base level, such as a multi-plant or base context, including the technical asset structure of one or more plants or asset management information such as an asset network. Additionally or alternatively, such contextualization may include adding application context, such as a model identifier, a third-party exchange identifier, or a confidentiality identifier.

[0055] The second processing layer, preferably a process management system, may be communicatively coupled to the external processing layer via the external network. The second processing layer, preferably a process management system, may be configured to manage data transmission 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, for example, to provide plant specific data to an interface with the external network based on an identifier added by contextualization. Such an identifier may be a confidentiality identifier based on which such data is not provided to the interface of the external network.

[0056] The external processing layer can be a computing or cloud environment that provides virtualized computing resources such as data storage and computing power. The external processing layer can provide a private, hybrid, public, community, or multi-cloud environment. Cloud environments are advantageous because they provide on-demand storage and computing power. In addition, in the case of monitoring and / or controlling multiple chemical plants operated by different parties, data or process applications that affect the chemical plants can be shared in such a cloud environment.

[0057] On the other hand, 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, can be further configured to delete at least a portion of the data transmitted to the external processing layer. The external processing layer can be configured to store historical data from one or more chemical plants. The external processing layer can be configured to aggregate, store or contextualize plant-specific data from multiple chemical plants and / or store historical data from more than one chemical plant. Aggregation here refers to grouping data via an aggregation function (such as sum, average or modulus). Therefore, aggregation is related to the function of reducing dimensions or storage space. In this way, data storage can be externalized, and the required local storage capacity can be reduced, and historical transmission becomes redundant. In addition, due to the flexible computing and storage resources of the external processing layer and the fact that data is available in the external processing layer, process applications can be built, trained, tested or modified in the external processing layer.

[0058] In another aspect, the second processing layer, preferably a process management system, is configured to manage data transmission to and / or from the external processing layer in real time or on demand. Depending on the network and computational load on the interface with the external network, real-time transmissions may be buffered. On-demand transmissions may be triggered in a predefined or dynamic manner. Preferably, data transmission to the external processing layer is managed in real time, and transmission from the external processing layer is managed on demand.

[0059] On the other hand, the second processing layer, preferably the process management system, is configured to store or manage access to historical data, real-time data and planned data. On the other hand, the second processing layer, preferably the process management system, is configured to store or manage access to historical data of a first time window, and the external processing layer is configured to store historical data of a second time window, wherein the first time window is shorter than the second time window. Here, the first time window may correspond to a critical time window that allows the system to monitor and / or control the chemical plant in an island mode without an external network connection. The first time window can be regarded as a hot window, and the historical data of the window is required to safely control and / or monitor the chemical plant. The first time window or hot window can be determined based on the storage capacity of the second processing layer (preferably the process management system), or preferably by the process application and the historical data required to execute on the process application in an island mode without an external network connection. This approach always ensures the availability of the system for monitoring and / or control.

[0060] On the other hand, deployment is managed by an orchestration application that manages the deployment of containerized applications based on input data, load indicators, or system-level tags. Additionally or alternatively, the orchestration application is hosted by a second processing layer and / or an external processing layer. On the other hand, the orchestration application hosted by the second processing layer at execution time manages critical containerized applications. Additionally or alternatively, the orchestration application hosted by the external processing layer at execution time manages non-critical containerized applications. This execution-time management can be assigned statically or dynamically. In a dynamic scenario, the second processing layer can host backups of critical containerized applications, which can be accessed by the orchestration application hosted by the second processing system if external network connectivity is interrupted. The critical containerized applications here refer to those containerized applications that monitor and / or control critical assets. Therefore, if monitoring and / or control needs to run in island mode, such applications are required.

[0061] On the other hand, management of critical containerized applications is assigned to the second processing layer based on historical criteria reflecting a time window of available historical data on the first processing layer or the second processing layer. The second processing layer can be configured to store historical aggregated data for the first time window, and the external processing layer can be configured to store historical aggregated data for the second time window, wherein the first time window is shorter than the first time window. In a preferred embodiment, the first time window is selected so that the critical containerized application can be executed on the first processing layer or the second processing layer. On the other hand, the containerized application is deployed to be executed on the second processing layer or the external management layer according to the historical criteria of the time window reflecting the available historical data. In such an embodiment, the application can be executed at a level where such data is available. Therefore, no further data transmission is required between the processing layers, thereby reducing communication and processing load. In combination with the concept of contextualization interleaved across layers, processing plant-specific data on the first processing layer will introduce redundant data transmission, once from the first processing layer to the second processing layer for contextualization, and then back to the first processing layer for application execution.

[0062] The deployment may depend on the input data. In another aspect, the assignment of the deployment tier depends on a data availability indicator, a criticality indicator, or a latency indicator.

[0063] The data availability indicator may be related to the input data acquired by the containerized application. Based on such an indicator, execution may be assigned to the 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, while a second processing tier may be configured to provide plant specific data. A containerized application that acquires asset or process specific data may be deployed on the first processing tier. Similarly, a containerized application that acquires plant specific data may be deployed on the second processing tier. Applications may be executed in the processing tier that hosts the data to avoid redundant data transfers and reduce load.

[0064] Criticality indicators can be static or dynamic indicators. In the case of static indicators, the criticality of an asset, asset group, or plant can be predefined. In the case of dynamic indicators, criticality indicators can be dynamically assigned based on output data from previous application runs or other application runs. For example, a criticality indicator can be determined based on a key performance parameter of an asset, such as its health status. If the health status of an asset becomes critical over time, the criticality criteria may change, and the containerized application may run in a different deployment layer due to this change, thereby reducing, for example, data transmission delays. In one example, if execution is assigned to the second processing layer instead of the first processing layer, the containerized application obtains asset or process-specific data for a particular asset, and the criticality indicator indicates that it has been completed. If the health status of a particular asset changes and may require, for example, closer monitoring at a higher frequency, if execution is assigned to the second processing layer, the criticality indicator can be reset to indicate that the criticality indicator has not been completed. In this case, the application can be assigned to the first processing layer.

[0065] The latency indicator can be a static or a dynamic indicator. In the case of a static indicator, the latency requirements of an asset, a group of assets, a part of a plant or a plant can be predefined. In the case of a dynamic indicator, the latency requirements can be dynamically assigned based on the signature of the input data. Such a signature can be related to the frequency of changes in the real-time measurement data, for example, derived from historical real-time measurement data. In one example, the monitoring signal of a pump can show a higher frequency than the monitoring signal of a heat exchanger. In this case, the containerized application monitoring the pump can be deployed directly on the pump controller or on the asset level on the core process system of the corresponding plant. For example, the corresponding containerized application can be deployed in the processing layer as close to the pump as possible to reduce latency. Therefore, the latency criterion can represent the time urgency of the containerized application.

[0066] The load indicator may be based on the processing and / or network load of the corresponding deployment layer. Additionally or alternatively, the application may be executed on a deployment layer that provides sufficient computing and storage resources to reduce the processing load on other processing layers and ensure that critical application execution is not affected. In this case, the input data may be transmitted to the corresponding deployment layer. This is particularly advantageous for applications that require high computing load or have low time requirements, thus allowing for data transmission delays.

[0067] On the other hand, deployment can depend on system-level tags associated with containerized applications. System-level tags can be, for example, configurations in an orchestration application that deploys, executes, and monitors containerized applications. In this case, the containerized application can include an application identifier that the orchestration application can use to identify it at deployment time. In this way, deployment can be "hardwired" to ensure that critical applications execute in the correct layer. This deployment scenario can be particularly relevant to containerized applications that monitor and / or control critical assets. In this context, critical assets refer to assets that would severely impact plant operations if disrupted. Here, plant-specific data refers to contextualized asset or process-specific data.

[0068] On the other hand, containerized applications are deployed to multiple assets or multiple plants of the same type. Assets of the same type may be associated with assets having similar functions, from the same supplier and / or having similar characteristics (e.g., performance characteristics). Plants of the same type may involve plants that produce similar intermediate or final products, have similar physical asset structures, or are based on similar chemical processes. Here, similar means comparable in the sense that the behavior of the asset or plant exhibits behavioral deviations that do not exceed the tolerance or can be modeled by a single model. Preferably, the containerized application is associated with an asset or plant identifier. Such an identifier may be a configuration setting for an orchestration application or a containerized application. The plant or asset identifier may be one-dimensional representing one plant or asset type or multi-dimensional representing multiple plants or assets, and the containerized application will be executed for these plant or asset identifiers. In particular, if the first processing layer has different processing unit plants or even asset or process specific, such an asset identifier allows assets associated with different processing units to be processed simultaneously, thereby allowing efficient deployment of containerized applications.

[0069] On the other hand, the containerized application is modified based on the input data and output data of the containerized application executed for multiple assets or plants of the same type. This can be done periodically or dynamically at each defined time. By aggregating this data, the containerized application, in particular the plant or asset model, can be verified or improved in accuracy. In this way, the model can be adjusted to reflect the behavior of the physical plant or asset. This is especially important for maintenance cycles or life cycles, as the physical plant or asset may transform its behavior depending on the stage of such a cycle. Such transformations can be automatically compensated and self-optimized by the proposed system.

[0070] In another aspect, a containerized application is monitored based on confidence in input data, an asset model, or a plant model. The containerized application may provide such confidence as output data. The corresponding operation may be embedded in the containerized application via the asset or plant model or via a separate model. The confidence for the input data may be generated by analyzing patterns in, for example, real-time measurement data. The confidence for the asset or plant model may be generated as part of performing model operations based on the input data.

[0071] On the other hand, if the confidence level drops below a threshold confidence level, for example if the confidence level is below 70%, 80% or 90%, an event signal is triggered. Such an event signal may indicate a failure in the operation of an asset or application. If an abnormal pattern is detected on the input data and the corresponding confidence level is below a threshold, application execution may be stopped and a failure signal may be delivered to a control instance, for example on a first process layer of a chemical plant. Additionally or alternatively, such a failure signal may be delivered to a monitoring instance, for example on a first or second process layer, or to a client application, for example for display to an operator. In this way, sensor failures and the need for modification may be detected.

[0072] On the other hand, if the confidence exceeds a threshold, a modification of the asset or plant model is triggered. The modification may be triggered automatically. Such a modification may include hardware or software modification. For example, the modification includes retraining the asset or plant model based on historical data, adjusting the input data channel, adjusting the scenario matrix, or triggering an event signal to maintain the hardware of, for example, an Internet of Things (IoT) device.

[0073] On the other hand, modifications to the asset or plant model are performed on a second processing layer, particularly a process management system or an external processing layer. Since such modifications do not interfere with the containerized application in the first place, the computation can be performed on the external processing layer, thereby reducing the processing load of monitoring and / or controlling more critical processing layers (e.g., the first processing layer and the second processing layer).

[0074] In another aspect, external containerized applications from a third-party environment are provided and deployed for execution on the external processing layer. Applications from a third-party environment are any applications that are not created in the proprietary systems of the first processing layer, the second processing layer, and the external processing layer. This can reduce the risk of third-party containerized applications infecting the monitoring and / or control system of the chemical plant.

[0075] In another aspect, creation of a new containerized application is performed in an external processing layer. For example, an asset or plant model may be trained on the external processing layer. Preferably, the external processing layer is configured to store aggregated data for a plurality of chemical plants. The second processing layer may be configured to provide aggregated data from one or more chemical plants to the external processing layer. The second processing layer may be configured to transmit 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 transmitted to the external processing layer. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Example embodiments of the present disclosure are illustrated in the accompanying drawings. However, it should be noted that the accompanying drawings only illustrate specific embodiments of the present disclosure and should not be considered to limit its scope. The technical teaching may encompass other equally effective embodiments.

[0077] Figure 1 A first schematic representation of a system for monitoring and / or controlling one or more chemical plants is shown.

[0078] Figure 2 A second schematic representation of a system for monitoring and / or controlling one or more chemical plants is shown.

[0079] Figure 3 A third schematic representation of a system for monitoring and / or controlling one or more chemical plants is shown.

[0080] Figure 4 Shows Figures 1 to 3 Schematic representation of the concept of data contextualization in the shown system.

[0081] Figure 5 A flow chart showing a schematic representation of a method for monitoring and / or controlling one or more chemical plants is shown.

[0082] Figure 6 A schematic representation of a system for monitoring and / or controlling one or more chemical plants via a containerized application is shown.

[0083] Figure 7 A flow chart of a schematic representation of a method for monitoring and / or controlling a chemical plant having a plurality of assets is shown.

[0084] Figure 8 Shown is a schematic representation of a system for monitoring and / or controlling a plurality of chemical plants in different secure networks, which are configured for data and application transmission. DETAILED DESCRIPTION

[0085] In the petrochemical industry, process industrial production usually starts with upstream products, which are used to derive further downstream products. Until now, the value chain production via various intermediate products to the final product has been highly restricted and based on isolated infrastructure. This has hindered the introduction of new technologies such as IoT, cloud computing and big data analysis.

[0086] Unlike other manufacturing industries, process industries need to comply with very high standards, especially in terms of availability and security. For this reason, computing infrastructure is often unidirectional and isolated, with highly restricted access to chemical plant monitoring and control systems.

[0087] Typically, chemical production plants are embedded in the enterprise architecture in a siloed manner, with different levels for functional separation between operational technology and information technology solutions.

[0088] Level 0 is related to physical processes and defines the actual physical processes in the factory. Level 1 involves intelligent devices used to sense and manipulate physical processes, such as through process sensors, analyzers, actuators and related instruments. Level 2 involves control systems used to supervise, monitor and control physical processes. Real-time control and software; DCS, human machine interface (HMI); Supervisory Control and Data Acquisition (SCADA) software are typical components. Level 3 involves manufacturing operations systems used to manage production workflow to produce the required products. Batch management; Manufacturing Execution / Operations Management System (MES / MOMS); Laboratory, Maintenance and Plant Performance Management System, Historian and related middleware are typical components. The time frame for control and monitoring can be shifts, hours, minutes, seconds. Level 4 involves business logistics systems used to manage the business-related activities of manufacturing operations. ERP is the main system that establishes basic factory production schedules, material usage, transportation and inventory levels. The time frame can be months, weeks, days, shifts.

[0089] Furthermore, such structures follow a strict one-way communication protocol that does not allow data to flow into level 2 or below. Such architectures do not cover the internet outside the company or enterprise. However, the model remains a fundamental concept within the cybersecurity field. In this context, the challenge is to take advantage of the benefits of cloud computing and big data while still guaranteeing the established advantages of the existing architecture: namely, high availability and reliability of the lower-level systems (levels 1 and 2) that control the chemical plant as well as cybersecurity.

[0090] The technical teachings presented here allow enhancing monitoring and / or control changes to this framework in a systematic way to introduce new functionalities compatible with the existing architecture.The present disclosure relates specifically to a highly scalable, flexible and available computing infrastructure for process industries that at the same time adheres to high security standards.

[0091] Figure 1 A first schematic representation of a system 10 for monitoring and / or controlling a chemical plant 12 is shown.

[0092] The system 10 includes two processing layers, including a first processing layer in the form of a core process system 14 associated with each of the chemical plants 12 and a second processing layer 16 in the form of a process management system associated with the two chemical plants 12, for example. The core process system 14 is communicatively coupled to the second processing layer 16, thereby allowing unidirectional or bidirectional data transfer. The core process system 14 includes a distributed collection of processing units associated with the assets of the chemical plants 12.

[0093] The core process system 14 and the second processing layer 16 are configured in a secure network 18, 20, which includes two security zones in the schematic representation. The first security zone is located at the core process system 14 level, where the first firewall 18 controls incoming and outgoing network traffic to and from the core process system 14. The second security zone is located on the second processing layer 16, where the second firewall 20 controls incoming and outgoing network traffic to and from the second processing layer 16. This isolated network architecture can protect vulnerable plant operations from cyber attacks.

[0094] The core process system 14 provides the process or asset or process-specific data 22 of the chemical plant 12 to the 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 the plant-specific data 24 of the chemical plant 12 to an interface 26 of an external network. Here, the plant-specific data may refer to the contextualized process or asset or process-specific data.

[0095] Process or asset or process specific data may include value, quality, time, measurement unit, asset identifier. Via contextualization, further context may be added, 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 or bases and other asset management (e.g. asset network) may be added, as well as application context (e.g. model identifier, third party exchange).

[0096] The second processing layer 16 is communicatively coupled to the external processing layer 30 via an interface 26 with an external network. The external processing layer 30 can 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 can be provided in real time or on demand. The second processing layer 16 is configured to manage data transmission to and / or from the external processing layer in real time or on demand. For example, the second processing layer 16 can provide plant-specific data 24 to the interface 26 with the external network based on an identifier added by contextualization. Such an identifier can be a confidentiality identifier, based on which such data is not provided to the interface 26 of the external network. The second processing layer 16 can be further configured to delete at least part of the data transmitted to the external processing layer 30.

[0097] 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 and the required local storage capacity can be reduced, and historical transmission becomes redundant. In addition, this storage concept allows storing historical data on the second processing layer 16 for thermal windows, which are critical time windows that allow the system 10 to monitor and / or control a chemical plant in an island mode without an external network connection. In this way, the availability of the system 10 for monitoring and / or control is always guaranteed.

[0098] The second processing layer 16 and the external processing layer 30 are configured to host and / or orchestrate process applications. In particular, the second processing layer 16 can host and / or orchestrate process applications related to core plant operations, and the external processing layer 30 can be configured to host and / or orchestrate process applications related to non-core plant operations.

[0099] In addition, the second processing layer 16 and the external processing layer 30 can be configured to, for example, exchange data with a third-party management system via integration with a third-party external processing layer, orchestrate data visualization, orchestrate computing process workflows, orchestrate data computation, orchestrate APIs to access data, orchestrate data storage, transmission, and computation, provide an interactive plant data work environment for users (e.g., operators), and verify and improve data quality.

[0100] Figure 2 A second schematic representation of a system 10 for monitoring and / or controlling one or more chemical plants 12 is shown.

[0101] Figure 2 The system 10 shown is similar to Figure 1 However, Figure 2The system has a second processing layer with a process management system 32 and an intermediate processing system 34. The intermediate processing systems 34.1, 34.2 are arranged in a secure area of ​​a secure network via a firewall 40.

[0102] The intermediate processing systems 34.1, 34.2 can be configured to acquire process or asset or process specific data 22 from a single or multiple chemical plants 12. Such data is contextualized at the plant level in the intermediate processing systems 34.1, 34.2, and the plant specific data 38 can be provided to the process management system 32, where further contextualization can be performed, for example, across the plant level or base level on the integration. In this arrangement, data contextualization is interleaved at different system 10 layers, with each layer 14, 34, 32 mapping the context information available in the corresponding layer 14, 34, 32.

[0103] Figure 3 A third schematic representation of a system 10 for monitoring and / or controlling one or more chemical plants 12 is shown.

[0104] Figure 3 The system 10 shown in FIG. 1 is similar to Figure 1 and Figure 2 However, Figure 3 The system includes monitoring devices 44 that are communicatively coupled to the process management system 32 or the external processing layer 30. The monitoring devices 36 can be configured to transmit monitoring data to the process management system 32 or the external processing layer 30. The process management system 32 or the external processing layer 30 can be configured to manage multiple monitoring devices 44. Because such IoT devices are not considered reliable, the monitoring data provided by the monitoring devices 44 can be unidirectionally tagged, and any control loops associated with the chemical plant 12 can include filters for such tags. Therefore, such data will not be used for any control of the chemical plant 12.

[0105] Figure 4 Shows Figures 1 to 3 A schematic representation of the concept of data contextualization in the system 10 is shown.

[0106] Figures 1 to 3 The system 10 includes two internal processing layers 14, 16, 32, 34 and an external processing layer 30. The first processing layer 14 can be a distributed control system that is used to supervise, monitor and control the physical processes in the chemical plant 12. The first processing layer 14 can be configured to provide process or asset or process specific data. The second processing layer 16, 32, 34 can include an intermediate processing system 34 and a process management system 32. The intermediate processing system 34 can be configured as an edge computing layer. Such a layer can be associated with level 3 of a single plant. The intermediate processing system 34 can be configured to

[0107] ■ Collect process or asset or process specific data,

[0108] ■Interact with basic automation systems from level 2,

[0109] ■ Initial contextualization (bottom-up approach), where context is added based on what is known at level 2 and level 1 and within distributed edge devices,

[0110] The process management system 32 may be configured as a centralized edge computing layer. Such a layer may be associated with level 4 of multiple plants. The process management system 32 may be configured to:

[0111] ■Integrate data from different distributed edge devices (including intermediate processing systems 34 or monitoring devices 44),

[0112] ■ Further contextualization (bottom-up approach), where additional context is added based on the pre-processed context distributed among distributed edge devices.

[0113] The external processing layer 30 can be configured as a centralized cloud computing platform. Such a platform can be associated with level 5 for multiple factories. The external processing layer 30 can be configured as a manufacturing data workspace with full data integration across multiple factories, including manufacturing data historical transmission and streaming, collection of all data from all edge components. In this way, the full contextualization of all lower-level contexts can be integrated onto the external processing layer 30 for multiple factories. Therefore, the external processing layer 30 can be further configured as:

[0114] ■Run cloud-native apps,

[0115] ■Connect with external PaaS and SaaS tenants,

[0116] ■Integrate machine learning with manufacturing data and processes, train-test-deploy,

[0117] ■Visualize data, access apps, and orchestrate.

[0118] Through the system architecture, the concept of bottom-up contextualization can be realized. Figure 4As shown. In the bottom-up concept, all information available at lower levels may have been added to the data as attributes so that the context of the lower levels is not lost. Here, the first processing layer 14 as the lowest context level may include measurements 11, which are contextualized about the item 13 where the measurement is made. The intermediate processing system 34 can further contextualize by adding further tags 15 related to individual plants 12. The process management system 32 can further contextualize by adding tags 17 related to multiple chemical plants 12 and / or business information. The external processing layer 30 can further contextualize by adding tags 19 related to multiple plants and / or external context information, for example from a third party.

[0119] The concept of contextualization can cover at least two basic types of context. One type can be a functional location in a production environment that includes multiple chemical plants. This may cover information about what and where in the production environment this data point represents. Examples are a connection to the functional location, properties of which physical asset the data is collected about, etc. This context can be beneficially used in later applications because it explains which data is available for which plants and assets.

[0120] Another type could be confidentiality classification. Such a label could be added at the lowest possible level and this information could be propagated to further processing layers. Such labels could be added automatically or manually. Using technical measures, such as via filters embedded in firewalls, "strictly confidential" data could be automatically prohibited from being integrated all the way to the external processing layer 30. Sharing data with the outside would result in an automatic notification that "confidential data" is being shared. An automatic contract check could be implemented to see if the data could be shared with this external processing layer.

[0121] Overall, the concept of contextualization implemented in this way allows efficient use of data in process applications deployed on any layer of the system.

[0122] Figure 5 A flow chart showing a schematic representation of a method for monitoring and / or controlling one or more chemical plants is shown.

[0123] Preferably, the method is carried out in Figures 1 to 3 The method may be performed on a distributed computing system as shown, the distributed computing system including a first processing layer 14 associated with a chemical plant 12 and communicatively coupled to a second processing layer 16, 32, 34. Figures 1 to 4 All steps described in the context of , including any steps related to contextualization, data processing, process application management, and monitoring device management.

[0124] In a first step 61 , processes or assets or process-specific data of the chemical plant 12 are provided to the second process layer 16 , 32 , 34 via the first process layer 14 .

[0125] In a second step 63 , the process or asset or process specific data is contextualized via the second processing layer 16 , 32 , 34 to generate plant specific data.

[0126] In a third step 65 , the plant-specific data of the chemical plant or plants 12 are provided via the second processing layer 16 , 32 , 34 to the interface 26 of the external network.

[0127] In a fourth step 67, one or more chemical plants are monitored and / or controlled based on the process or asset or process-specific data or plant-specific data via the second processing layer 16, 32, 34 or the first processing layer 14. Monitoring and / or control of one or more chemical plants 12 may be performed based on the plant-specific data via the second processing layer 16, 32, 34 or the external processing layer 30. In addition, monitoring and / or control may be performed based on the process or asset or process-specific data via the first processing layer 14. Such monitoring and / or control may be performed by a process application that acquires corresponding data and provides monitoring and / or control outputs, such as Figures 6 to 8 further listed in .

[0128] Figure 6 A schematic representation of a distributed computing system for monitoring and / or controlling one or more chemical plants having multiple assets via a distributed computing system 10 having more than two deployment layers 14 , 16 , 30 is shown.

[0129] Figure 6 The schematic diagram of FIG. 1 shows the containerized application orchestration in different deployment layers 14, 16, 30. The system 10 includes an external processing system 30, a second processing layer 16, and a first processing layer 14. Here, the second processing layer 16 may include greater storage and computing resources than the first processing layer 14, and / or the external processing layer 30 may include greater storage and computing resources than the second processing layer 16. The architecture and functionality of the system 10 may follow the Figures 1 to 3 Specifically, the first processing layer 14 and the second processing layer 16 may be configured in the secure network 20, 40, 18. The first processing layer 14 may be communicatively coupled to the second processing layer 16, and the second processing layer 16 may be communicatively coupled to the external processing layer 30 via the external network 24.

[0130] The orchestration applications 56, 58 may be hosted by the external processing layer 30 and the second processing layer 16, 32, 34, respectively. Thus, the containerized applications 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 to obtain input data, provide the input data to the corresponding assets or one or more plant models to generate output data, and provide the generated output data for controlling and / or monitoring the chemical plant 12. In this way, the external processing layer 30 and the second processing layer 16, 32, 34 act as a facilitating layer, thereby reducing the computing and storage resources required on the first processing layer 14 at the asset level.

[0131] Figure 7 A flow chart schematically showing a method for monitoring and / or controlling a chemical plant 12 having a plurality of assets via a distributed computing system 10 is shown. Figures 1 to 4 The system 10 is shown.

[0132] In a first step 60, a containerized application 48, 50 is provided, the containerized application including an asset or plant template specifying 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 may be modified on the second processing layer 30. An external containerized application from a third party environment may be provided.

[0133] In a second step 62, the containerized application 48, 50 is deployed to execute on at least one of the deployment layers 30, 32, 16, 34, 14, wherein the deployment layers 30, 32, 16, 34, 14 are assigned based on input data, load indicators, or system layer tags, and the containerized application 48, 50 can be executed on one or more of the assigned deployment layers 30, 32, 16, 34, 14 to generate output data for controlling and / or monitoring the chemical plant 12. The deployment can be managed by an orchestration application 56, 50, which manages the deployment of the containerized application 48, 50 based on the input data, load indicators, or system layer tags. The orchestration application can be hosted by the second processing layer 16, 23, 34 and / or the external processing layer 30. The orchestration applications 56, 58 hosted by the second processing layer 16, 32, 34 manage critical containerized applications 48, 50, wherein the orchestration applications 56, 58 hosted by the external processing layer 30 may manage non-critical containerized applications 48, 50. The allocation of the deployment layer 30, 32, 34, 16, 14 may be based on input data depending on a data availability indicator, a criticality indicator, or a latency indicator. Containerized applications from a third party environment may be deployed to execute on the external processing layer 30.

[0134] The orchestration applications 56, 58 may be hosted by the external processing layer 30 and the second processing layer 16, respectively. The orchestration applications 56, 58 may deploy the containerized applications 48, 50 on any deployment layer 30, 16, 14. Thus, the containerized applications 48, 50 may be executed on the respective deployment layers 30, 16, 14 by running the process applications 46, 52, 54 in a sandbox type environment. The deployment layers 30, 16, 14 may be assigned based on input data, load indicators, or system layer tags. For example, the management of the critical containerized application 50 may be optionally assigned to the second processing layer 16 based on historical criteria reflecting a time window of available historical data on the first or second processing layer 16. Advantageously, the containerized applications 48, 50 may be deployed to multiple assets or plants of the same type. Furthermore, the containerized applications 50, 48 may be modified based on input data and output data provided by the containerized applications 46, 52, 54 executed for multiple assets or plants of the same type.

[0135] In a third step 64, the containerized application 48, 50 may be monitored based on the confidence of the input data, asset model or plant model during or after each execution. Based on the obtained confidence, an event signal or modification of the asset or plant model may be triggered. If the confidence exceeds a threshold, such a trigger may be set. Such a threshold may be predefined or dynamic. If a trigger is set, the modification of the asset or plant model may be performed, for example, on the second processing layer 16, 32, 34 or the external processing layer 30.

[0136] 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 persistent instance after execution of the containerized application 48, 50. In particular, such output data may be passed to a control instance, such as on the first processing layer 14 of the chemical plant 12. Additionally or alternatively, such output data may be passed to a monitoring instance on the first processing layer 14, the second processing layer 16, 32, 34, or the external processing layer 30. The output data may be passed to a client application or further containerized application 48, 50 for execution, such as for display to an operator.

[0137] Figure 8 A schematic representation of a system 10.2, 10.2 for monitoring and / or controlling a plurality of chemical plants 12.1, 12.2 in different safety networks 20.1, 20.2, which are configured for data and process application transmission, is shown. As an example, Figure 8 The structure includes first and second treatment layers 14, 16, 32, 34 and an outer treatment layer 30 as an example. Figures 1 to 3Any other system architecture may be similarly adapted for process applications and data transmission. Both systems are associated with separate safety networks 20.1, 20.2 and are communicatively coupled to external networks 24.1, 24.2 via interfaces 26.1, 26.2.

[0138] The systems 10.1, 10.2 are configured to exchange processes or assets or process specific data or process applications based on transfer tags. By adding transfer tags at the earliest possible level (i.e., where the data or application is generated or first enters the system), the transfer tags become an inherent part of any data point or application as soon as the tags are added and follow the data or application on its path through the system 10.1, 10.2. Such transfer tags enable seamless but secure integration of external data sources or external applications, as well as the transfer of data or applications to external resources.

[0139] exist Figure 8 In one case shown, an application 48 is exchanged between systems 10.1, 10.2. In this example, the containerized application 48 is transmitted via an external processing layer 30.1, 30.2 that is communicatively coupled to the two systems 10.1, 10.2. Here, the external processing layer 30.1 is communicatively coupled to the system 10.1, and the external processing layer 30.2 is communicatively coupled to the system 10.2. The exchange of the containerized application 48 is performed indirectly through the external processing layers 30.1, 30.2. The containerized application is tagged with a transmission tag that includes two transmission settings related to confidentiality settings and / or third-party transmission settings. In this way, a transmission can be prohibited based on a compliance check of the external processing layer 30.2, for example if a transmission with a corresponding third-party identifier is not associated with a third-party identifier stored in a database of allowed third-party transmissions for the process application 48. Similarly, processes or assets or process-specific data can be transmitted 72 between the systems 10.1, 10.2. Any transmission between the systems 10.1, 10.2 may then be followed by a further transmission from the external processing layer 30.1, 30.2 to the respective system 10.1, 10.2.

[0140] Additionally, such transport tag based transports may be made directly between systems 10.1, 10.2 between processing layers 32, 16 associated with secure networks 20.1, 20.1. Such transport tag based transports may be accomplished via a secure connection 74 (e.g., a VPN connection) between such layers 16, 23. Thus, any transport between systems 10.1, 10.2 may be followed by further transports between system components within the secure network 20.1, 20.2 or to external processing layers 30.1, 30.2 of the respective systems 10.1, 10.2. By attaching transport tags to any data point and process application, whether containerized or not, third party transports between systems 10.1, 10.2 in separate secure networks 20.1, 20.1 may be securely handled.

[0141] Any component described herein for implementing the method 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 be operated as peer machines in a peer (or distributed) network environment. The part of the computer system may be a virtualized cloud computing environment, an edge gateway, a network device, a server, a network router, a switch or a bridge, or any machine capable of executing a set of instructions (sequentially or otherwise) that specify the actions to be taken by that machine. In addition, it should be understood that the terms "computer system", "machine", "electronic circuit", etc. are not necessarily limited to a single component, but should be understood to include any collection of machines that execute a set (or multiple sets) of instructions individually or jointly to execute any one or more methods discussed herein.

[0142] Some or all of the components of this computer system may be used or described by any component of system 10. In some embodiments, one or more of these components may be distributed among multiple devices, or may be combined into fewer devices than shown. In addition, some components may refer to physical components implemented in hardware, while others may refer to virtual components implemented in software on remote hardware.

[0143] Any processing layer may include general processing devices, such as microprocessors, microcontrollers, central processing units, etc. More specifically, the processing layer may include a CISC (complex instruction set computing) microprocessor, a RISC (reduced instruction set computing) microprocessor, a VLIW (very long instruction word) microprocessor, or a processor that implements other instruction sets or a processor that implements a combination of instruction sets. The processing layer may also include one or more special processing devices, such as ASIC (application-specific integrated circuit), FPGA (field programmable gate array), CPLD (complex programmable logic device), DSP (digital signal processor), 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 circuits in an ASIC, CPLD, or FPGA. It should be understood that the term "processing layer" may also refer to one or more processing devices, such as a distributed system of processing devices located on multiple computer systems (e.g., cloud computing), and is not limited to a single device unless otherwise specified.

[0144] 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 methods or functions described herein. The instructions may also reside completely or at least partially in a main memory and / or in a processor during execution thereof by a computer system, main memory, and processing device, which may constitute a computer-readable storage medium. The instructions may also be sent or received over a network via a network interface device.

[0145] The computer program for implementing one or more embodiments described herein may be stored and / or distributed on a suitable medium, such as an optical storage medium or solid-state medium provided together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. However, the computer program may also be presented over a network like the World Wide Web and may be downloaded from such a network into the working memory of a data processor.

[0146] The terms "computer-readable storage medium", "machine-readable storage medium", etc. should be understood to include a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) that store one or more sets of instructions. The terms "computer-readable storage medium", "machine-readable storage medium", etc. should also be understood to include any temporary or non-temporary medium that can store, encode, or carry a set of instructions to be executed by a machine and cause the machine to perform any one or more methods of the present disclosure. Therefore, the term "computer-readable storage medium" should be understood to include, but is not limited to, solid-state memories, optical media, and magnetic media.

[0147] Some portions of the detailed description may have been 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 art of data processing to most effectively communicate the content of their work to others skilled in the art. An algorithm is herein and generally considered to be a self-consistent sequence of steps leading to a desired result. These steps are steps that require physical manipulation of physical quantities. Typically, although not necessarily, these quantities take the form of electrical or magnetic signals that can be stored, transferred, combined, compared, and otherwise manipulated. At times, it has proven convenient, primarily for common reasons, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, etc.

[0148] It should be remembered, however, that all of these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. As will be apparent from the foregoing discussion, unless expressly stated otherwise, it should be understood that discussions throughout the description using terms such as "receive," "retrieve," "transmit," "compute," "generate," "add," "subtract," "multiply," "divide," "select," "optimize," "calibrate," "detect," "store," "execute," "analyze," "determine," "enable," "identify," "modify," "convert," "apply," "extract," and the like refer to the actions and processes of a computer system or similar electronic computing device that manipulate and transform data represented as physical (e.g., electronic) quantities in the computer system's registers and memories into other data similarly represented in the computer system's memories or registers or other such information storage, transmission, or display devices.

[0149] It must be noted that embodiments of the present invention are described with reference to different subject matters. In particular, some embodiments are described with reference to method type claims, whereas other embodiments are described with reference to system type claims.

[0150] However, it will be apparent to those skilled in the art from the above and following descriptions that, unless otherwise specified, any combination of features related to different subjects, in addition to any combination of features belonging to one subject, is also considered to be disclosed with the present application. However, all features can be combined to provide a synergistic effect that is not just the simple sum of the features.

[0151] Although the invention has been illustrated and described in detail in the drawings and the foregoing description, such illustration and description should be considered illustrative or exemplary rather than restrictive; the invention is not limited to the disclosed embodiments. Other variations to the disclosed embodiments and the claimed invention may be understood and implemented by those skilled in the art through a study of the drawings, the disclosure, and the appended claims. In some cases, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the disclosure.

[0152] In the claims, the word "comprising" does not exclude other elements or steps and the indefinite article "a" or "an" does 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 mean that a combination of these measures cannot be used to advantage. Any reference signs in the claims should not be construed as limiting the scope.

Claims

1. A method for monitoring and / or controlling a chemical plant having a plurality of assets via a distributed computing system having more than two deployment layers, wherein: The deployment layer includes at least two of a first processing layer, a second processing layer, and an external processing layer, the first processing layer and the second processing layer are configured inside a secure network, wherein the first processing layer is communicatively coupled to the second processing layer, and the second processing layer is communicatively coupled to the external processing layer via an external network, and the method includes the following steps: - providing a containerized application, the containerized application comprising an asset or plant template, the template specifying an asset or plant model, input data, and output data, - deploying the containerized application to execute on at least one of the deployment layers, wherein the deployment layers are assigned based on the input data, load indicators, or system layer tags, and executing the containerized application on the assigned deployment layer to generate output data for controlling and / or monitoring the chemical plant, - providing said generated output data for use in controlling and / or monitoring said chemical plant.

2. The method according to claim 1, wherein: The second processing layer includes greater storage and computing resources than the first processing layer, and / or the external processing layer includes greater storage and computing resources than the second processing layer.

3. The method according to claim 1, wherein: The containerized application for execution includes one or more operations to obtain input data, provide the input data to corresponding assets or one or more plant models to generate output data, and provide the generated output data for controlling and / or monitoring the chemical plant.

4. The method according to claim 1, wherein: The deployment is managed by an orchestration application that manages the deployment of the containerized application based on the input data, the load indicator, or the system layer tag.

5. The method according to claim 4, wherein: The orchestration application is hosted by the second processing layer and / or the external processing layer.

6. The method according to claim 4 or 5, wherein: The orchestration application hosted by the second processing layer manages critical containerized applications, wherein the orchestration application hosted by the external processing layer manages non-critical containerized applications.

7. The method according to claim 4 or 5, wherein: Management of a critical containerized application is assigned to the second processing layer based on historical criteria reflecting a time window of available historical data in the first processing layer or the second processing layer.

8. The method according to claim 1, wherein: The assigning of the deployment tier based on input data is dependent on a data availability indicator, a criticality indicator, or a latency indicator.

9. The method according to claim 1, wherein: The containerized application is deployed to multiple assets or plants of the same type.

10. The method according to claim 1, wherein: The containerized application is modified based on the input data and the output data provided by the containerized application executing against multiple assets or plants of the same type.

11. The method according to claim 1, wherein: The containerized application is monitored based on a confidence level of the input data, the asset, or the plant model.

12. The method according to claim 11, wherein: If the confidence level is below a confidence threshold, an event signal or a modification to the asset or plant model is triggered.

13. The method according to claim 12, wherein: Modifications to the asset or plant model are performed on the second processing layer or the external processing layer.

14. The method according to claim 1, wherein: External containerized applications from third-party environments are provided and deployed to execute on the external processing layer.

15. A system for monitoring and / or controlling a chemical plant having a plurality of assets at more than two deployment layers, wherein: The deployment layer includes at least two of a first processing layer, a second processing layer, and an external processing layer, the first processing layer and the second processing layer are configured inside a secure network, wherein the first processing layer is communicatively coupled to the second processing layer, and the second processing layer is communicatively coupled to the external processing layer via an external network, and the system is configured to: - providing a containerized application, the containerized application comprising an asset or plant template, the template specifying an asset or plant model, input data, and output data, - deploying the containerized application to execute on at least one of the deployment layers, wherein the deployment layers are allocated based on the input data, load indicators, or system layer tags, and executing the containerized application on the allocated one or more deployment layers to generate output data for controlling and / or monitoring the chemical plant, - providing said generated output data for use in controlling and / or monitoring said chemical plant.

Images