Method for controlling an industrial process

Abstract

A method of controlling an industrial process using a model of the industrial process, the method comprising selecting a production policy from a set of policies, where the policies are a set of advanced configurations applied in an advanced framework of the industrial process in respective predefined states, simulating the advanced configurations of the selected production policy, at least one performance indicator of the selected policy is evaluated, optionally, the selected policy is modified or another production policy is selected based on the at least one performance indicator, and the accepted policy is accepted and implemented.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to a method of controlling an industrial process. Further embodiments relate to an industrial control system for controlling an industrial process. In particular, the method and control system according to embodiments of the present disclosure can relate to pulp and / or paper processing. BACKGROUND

[0002] In industrial process control, energy consumption is increasingly becoming an important additional driving criterion. This indicates the need for a comprehensive and dynamic strategy for the planning and scheduling of industrial processes. In order to be able to reduce the energy consumption during an industrial process, it is necessary to know how much energy is consumed in which process step to produce a certain amount of product as a basis for combined planning and scheduling. In many industrial processes, in particular in pulp and / or paper making, a certain energy generation can be found on site. Since the energy usually originates from multiple sources, on-site power generation and power provided from the public grid are considered on one level, but also the power sources in the public grid and the heat or steam production, in particular using natural gas or hydrogen, are considered, so that there is a lack of feedback mechanisms from the industrial process to the energy management and vice versa. In particular, one would expect a production strategy implementation mechanism that incorporates these interactions. SUMMARY

[0003] In view of the foregoing, the present disclosure relates to a method and an industrial control system for controlling an industrial process, which allow to employ, adapt and test production strategies on a high-level framework, which production strategies are applied in predefined states, in particular in environment or energy related states.

[0004] According to one aspect of the present disclosure, a method of controlling an industrial process is provided. The industrial process is executed by a production plant, a distributed control system, a manufacturing execution system and / or an energy management system. The method employs a model of the industrial process and comprises a plurality of steps. The method comprises selecting a production strategy from a set of strategies, simulating a high-level configuration of the selected production strategy, evaluating at least one performance indicator of the selected production strategy, optionally modifying the selected production strategy or selecting another production strategy based on the at least one performance indicator, accepting the selected production strategy based on the at least one performance indicator, and implementing the accepted production strategy, and controlling the industrial process by associated low-level operational instructions of the production strategy.

[0005] According to another aspect of the present disclosure, an industrial control system for controlling an industrial process is provided. The system comprises a distributed control system module configured for implementing accepted production strategies and associated low-level operation instructions, a manufacturing execution system module configured for providing an overview of current production status and order fulfillment, an energy management system module configured for controlling energy flow in the industrial process, and an analytics module configured for modeling the industrial process, wherein the energy flow influences the material flow and the material flow influences the energy flow. Model of the industrial process

[0006] According to some embodiments of the present disclosure, the model of the industrial process can be built on a digital twin model of the industrial process, also referred to herein as “model”. In particular, the digital twin model can comprise the interaction and correlation of different steps of the industrial process. In embodiments, the digital twin model or parts of the digital twin model can be generated based on historical data. In particular, the historical data can allow to discover implicit interactions between different steps of the industrial process. In embodiments, the digital twin can be generated by using machine learning methods on historical data. The digital twin model can be composed of a production related model which allows to establish a model of the whole industrial process, in particular to track the energy flow and to track the production flow. The production flow can also be referred to as material flow. The general concept and possible implementations of a digital twin model are described, for example, in WO2022144082A1. If material flow and energy flow are incorporated, the digital twin model can be named “material flow and energy digital twin”. The digital twin model can be generated based on a process description, in particular based on a piping and instrumentation diagram (P&ID), and can be optimized using historical data or real-time data.

[0007] The model of the industrial process can comprise asset models of industrial process assets, including models of individual units and / or groups of machinery involved in the industrial process. Furthermore, the model of the industrial process can comprise a process structure of the industrial process.

[0008] In some embodiments, the model of the industrial process, in particular the digital twin model, can be initialized from current process values. The current process values can be obtained from a distributed control system (DCS) that controls the industrial process at a low level, or from edge devices that collect and provide process related signals. In particular, the DCS and / or the edge devices can comprise sensors that measure process values of the industrial process. In some embodiments, the model of the industrial process can be initialized from a production schedule, in particular provided by a planning and scheduling module. More particularly, the model of the industrial process can be initialized from a planned production state. In some embodiments, the model of the industrial process can be initialized from storage levels, in particular provided by a stock management. The storage levels can comprise at least one of a product storage level, an energy storage level, a raw material or intermediate material storage level, an auxiliary material storage level, an operating material storage level. In some embodiments, the model of the industrial process can be initialized from production states, in particular provided by a manufacturing execution system (MES). In some embodiments, the model of the industrial process can be initialized from historical data, in particular historical sensor data, historical storage level data, historical production state data, and / or historical cost data. In embodiments, the model of the industrial process can be initialized by a combination of the aforementioned initialization paths.

[0009] According to embodiments, the model of the industrial process can comprise a simulator. The simulator can use production related models to provide predictions of future process values, storage levels, and production states. The simulator can comprise production constraints and / or resource constraints. Production strategies can be implemented in the simulator. The simulator can be used to optimize production strategies.

[0010] In embodiments, the digital twin model, in particular the material and energy flow digital twin (MEFDT), can model the influence of changes in the material flow on the energy flow. Furthermore, it can model the influence of changes in process parameters and / or process settings on the energy flow. The MEFDT can model the energy flow based on the material flow and the steps of the industrial process that are required to achieve a specific material flow. In particular, the MEFDT models the energy flow based on precise low-level operation instructions that are associated with a specific production strategy. In particular, differences in the low-level operation instructions of different production strategies can be reflected in the energy flow of the MEFDT.

[0011] According to some embodiments, the digital twin model, in particular the material and energy flow digital twin (MEFDT), can model the influence of energy buffers. Energy buffers can be explicit by energy and / or heat storage machines, in particular batteries. Energy buffers can be implicit by implicit storage, in particular machines where the temperature can be set in a range. Industrial process / preceding claim 1

[0012] In embodiments, the model of the industrial process, in particular the digital twin model, more particularly the MEFDT, can be incorporated in an analysis module of the industrial process. The analysis module can further comprise a value chain model to generate performance indicators from the simulated predicted material and energy flows in the MEFDT. In particular, the performance indicators can be generated based on a selected production strategy, wherein low-level operation instructions are used to simulate the industrial process in the MEFDT.

[0013] According to some embodiments, the analysis module can further comprise a value chain optimization module. The value chain optimization module can amend the production strategy to optimize the performance indicators obtained by the value chain model. The amended production strategy can be simulated in the model of the industrial process, in particular in the digital twin model, more particularly in the MEFDT.

[0014] In embodiments, the analysis module can further comprise aggregated data from historical and / or current data of the DCS.

[0015] The industrial process is executed by a production plant, a distributed control system, a manufacturing execution system, and an energy management system. The production plant can comprise machinery needed in the production steps, a transportation system to move materials from one machine to another, a building to house the machinery, and / or an energy supply infrastructure.

[0016] In embodiments, an operator uses the distributed control system to control the plant. In some embodiments, the production plant can further comprise edge devices installed at the production site. The edge devices can collect information and exchange information and data with the DCS. The DCS can be configured to allow the operator to control the operation of the plant. Furthermore, the DCS can use sensor devices to obtain information about low-level process values. The DCS can implement set points for specific process values. The DCS can control the controllers of the machinery of the industrial process to achieve these set points. The controllers of the machinery can use control laws, in particular proportional control laws, proportional integral control laws, or proportional integral derivative (PID) control laws, to operate the machinery. If a specific controller and / or a sensor measured process value is outside a predefined range, the DCS can provide an alarm signal to the operator. The DCS can implement operator decisions, in particular high-level configuration decisions, as low-level operation instructions. The operator operating the production plant through the DCS can be one person or another module of the industrial process.

[0017] In embodiments, a manufacturing execution system (MES) can provide an overview of current production states and order fulfillment states to production plant managers and / or production planners. In particular, the MES can control plant operations on a high level. Plant managers and / or production planners can use the MES to optimize the execution and / or planning of industrial processes. In particular, the MES can include and use information from maintenance planning and production planning. The MES can use information from inventory management systems. The MES can exchange information with enterprise resource planning modules (ERP).

[0018] In embodiments, an energy management system (EMS) can manage energy flows in industrial processes. Energy flows can include electrical currents, steam flows, heat flows, and / or coolant flows. The EMS can receive information about energy flow parameters. Energy flow parameters can include energy flow availability, current prices for energy flows, future prices for energy flows, and / or sources of energy flows. Sources of energy flows can include providers of energy flows and / or production methods for energy flows and amounts of CO2 equivalents needed to produce energy flows. The EMS can exchange information with the MES and / or the DCS and / or the planning and scheduling system.

[0019] The analysis module can exchange information with the MES and / or the DCS and / or the planning and scheduling system. In particular, the MES can exchange information with the analysis module to test and / or validate and / or optimize high-level configurations on a lower level. The DCS can exchange information with the analysis module, in particular with the digital twin model, to start the digital twin model with current data and to select and / or optimize suitable production strategies on a higher level. The energy management system can exchange information with the analysis module to test the influence of changes in energy flows on production processes or to test the influence of changes in production processes, in particular changes in production strategies, on energy flows. Production strategies

[0020] In embodiments, a production strategy is a set of high-level configurations applied in a high-level framework of an industrial process in a respective predefined state. In particular, a production strategy can be described as follows: If a specific predefined state (i.e., an actual state corresponds to a predefined state) is met, a specific action is taken. Furthermore, a production strategy can aim to optimize at least one specific performance indicator. For a predefined state, multiple production strategies are available, in particular multiple production strategies optimized for different performance indicators.

[0021] In embodiments, the high-level framework of the industrial process can be a generalized and systematic description of the industrial process and interactions within the industrial process. In particular, generalized material flows and energy flows can be described in a high-level framework. Further, interactions between multiple steps of the industrial process can be described in the high-level framework. Within the high-level framework, production strategies can be constructed such that an experienced operator can easily think of a predefined state and take a specific action.

[0022] According to some embodiments, the high-level configuration can include a description of generalized operational modes of at least the distributed control system, the production process, and the energy management system in the high-level framework. In particular, the high-level configuration can focus on operational targets to be achieved in the production process. Thus, the high-level configuration is a generalized and abstracted description of the operation of the industrial process and production plant at an aggregated and abstracted level above the DCS that is understandable to a human operator. For example, the high-level configuration can be a production plan. Low-level operational instructions can be derived from the high-level configuration by the DCS and / or an experienced operator.

[0023] In embodiments, the predefined states of the production strategy can include at least one of an environmental state, an energy supply state, a process state, a stock level state, an energy source state, a market state. The predefined state can be a condition of an internal or external variable that can be reliably determined. The predefined state can be a historical state, a current state, or a future state. The predefined state can be a discrete attribute or a continuous attribute. The predefined state can be composed of multiple conditions of internal or external variables. The conditions of the internal or external variables can be expressed in the high-level framework.

[0024] In embodiments, the environmental state can comprise a weather state, in particular a temperature, a wind speed and / or a cloud cover level, an astrological state, in particular a sunrise and / or a sunset time, and / or a natural state, in particular a water level and / or a water quality of a water body. The energy supply state can comprise a price per unit of energy, in particular a price per unit of electricity and / or a price per unit of heat, an availability of energy, in particular an availability of electricity, heat or steam. The process state can be every state of the industrial process that can be reliably determined, including a state of a particular machine, a load level, an operator interaction, a malfunction of a part of the industrial process or machine and / or a reliably determinable property of a product of the industrial process. The inventory level state can comprise an inventory level of a product and / or a waste product of the industrial process and / or an inventory level of a raw material and / or a material required for the operation of the industrial process and / or an inventory level of a chemical and / or an available storage space for storing products. The inventory level state can comprise an inventory level of an energy source, in particular an inventory level of oil, a petroleum product, a liquefied or pressurized gas, hydrogen, coal and / or wood pellets, pulp or chips. The energy source state can comprise a power source, in particular an amount of electricity produced on site, a share of renewable electricity generation in a unit of electricity, a share of non-fossil electricity generation in a unit of electricity and / or a CO2 equivalent emission in a unit of electricity. The market state can comprise a price per unit of raw material, in particular a price per unit of pulp or old paper, an availability of raw materials, a price of a chemical, an availability of a chemical, a price per unit of product, in particular a price per unit of product at a particular point in time and / or a demand for a product.

[0025] According to some embodiments, the predefined state can comprise the aforementioned plurality of states. The predefined state can be calculated based on indicators of the aforementioned plurality of states. Selection strategy

[0026] In embodiments, selecting a production strategy can comprise selecting a production strategy for a future state, in particular planning production. In embodiments, selecting a production strategy can comprise selecting a production strategy for a historical state, in particular comparing different production strategies, optimizing a production strategy and / or conducting a failure analysis. The set of strategies can comprise at least one production strategy. In embodiments, the set of strategies can only comprise production strategies with the same predefined state.

[0027] In embodiments, the set of strategies can be limited to production strategies in which a pre-defined state is similar to the current state. The current state can be derived using DCS, EMS, and / or other input paths. These input paths can include the internet, e.g., for obtaining environmental information. In particular, a pre-defined state can be similar to the current state if conditions of internal and / or external variables of the state are similar. In embodiments, a plurality of states of the industrial process can be considered similar if differences of variables describing the states have not increased overall, if under the same operating conditions. In embodiments, the set of strategies can be limited to production strategies in which a pre-defined state is similar to the current state. The current state can be derived using DCS, EMS, and / or other input paths. These input paths can include the internet, e.g., for obtaining environmental information. In particular, a pre-defined state can be similar to the current state if conditions of internal and / or external variables of the state are similar. In embodiments, a plurality of states of the industrial process can be considered similar if differences of variables describing the states have not increased overall, if under the same operating conditions.

[0028] In embodiments, a production strategy in the set of strategies can be derived by a strategy generator. In particular, an initial production strategy that can be optimized can be derived by the strategy generator. The strategy generator combines a pre-defined state and at least one high-level operational instruction. The strategy generator can derive the production strategy from historical data. The strategy generator can also derive the production strategy from a set of historical data using machine learning methods, in particular discovering implicit operational procedures and / or interdependencies in the industrial process. The historical data can include costs, in particular at least one of energy costs, energy consumption, machine usage, energy and / or storage levels. The production strategy can be derived from operational experience of an operator. The production strategy can be derived from explicit standard operational procedures. The production strategy can be derived from reasoned guesses about how different aspects of the production process are connected and / or interact.

[0029] In embodiments, the strategy generator can combine a user-defined state with at least one high-level configuration in historical data. In embodiments, the strategy generator can derive a production strategy for the current state by comparing historical data in which the current state occurred to other current states. In particular, production strategies of historical states similar to the current state can be used to derive a production strategy for the current state. Simulated strategies

[0030] In embodiments, the high-level configuration of the selected production strategy is converted by the model of the industrial process into low-level operation instructions. The low-level operation instructions can comprise instructions to specifically set mechanical settings and / or set points of controller devices. The low-level operation instructions can be executed using a DCS. Suitable low-level instructions can be converted from the high-level configuration by the model of the industrial process, which employs information about the process structure as well as material and energy flows. In embodiments, historical data can be used to implement the high-level configuration into low-level operation instructions, in particular using machine learning methods. Additionally or alternatively, optimization algorithms can be used to convert the high-level configuration into low-level operation instructions. In particular, reinforcement learning methods as exemplarily described in DE 102021004426 A1 can be used to obtain the low-level operation instructions. After implementing the high-level configuration into low-level operation instructions, the industrial process can be simulated (“simulation of the high-level configuration”). In the digital twin model, material flows and energy flows can be derived. The value chain model can be used to derive at least one performance indicator. The performance indicator can also be referred to as key performance indicator (KPI).

[0031] In embodiments, the performance indicator can comprise at least one of a cost indicator, an energy consumption indicator, a production yield indicator, a product quality indicator, an efficiency indicator, a sustainability indicator, a greenhouse gas indicator, an environmental impact indicator, a wear indicator, a safety indicator. The performance indicator can be an indicator of a single property or can be generated from multiple properties. In particular, the performance indicator can be calculated from multiple performance indicating properties. The performance indicator can be a value of the digital twin model. In embodiments, the performance indicator can be calculated from at least one value of the digital twin model.

[0032] In embodiments, the cost indicators can include a total cost associated with a unit product of the industrial process, a marginal cost of an additional unit product of the industrial process, and / or an energy cost. The cost indicators can also include a cost of waste paper, in particular a cost of paper that does not meet quality standards. The energy usage indicators can include an amount of energy used for a unit product of the industrial process, an efficiency of energy used, waste heat, and / or an amount of energy used from different energy sources, in particular an amount or ratio of energy used from on-site energy sources. The production yield indicators can include a manufacturing defect indicator, a utilization indicator of the entire production plant and / or of specific machinery. The efficiency indicators can include an amount of energy required per unit product, an amount of raw materials required per unit product, and / or an amount of time required per unit product. The sustainability indicators can include an amount of renewable energy in the energy mix used. The environmental impact indicators can include an amount of waste per unit product and / or a composition of waste per unit product, in particular an amount of waste water per unit product. The environmental impact indicators can also include a use of waste paper, in particular an amount of recycled waste paper. The greenhouse gas indicators can include an amount of carbon dioxide equivalent emissions per unit product. The greenhouse gas indicators can also include a CO2 equivalent emissions of waste paper associated with producing a unit product. The wear indicators can include an amount of wear per unit product, an expected risk of failure due to wear, an expected lifetime of the production plant and / or of specific machinery due to wear, and / or a repair time required per unit product due to wear. The safety indicators can include a risk of exceeding safe operating conditions. Evaluation strategy

[0033] In embodiments, evaluating the production strategy comprises comparing the at least one performance indicator of the selected production strategy to an acceptance criterion. In particular, the acceptance criterion can be a predefined threshold of the at least one performance indicator and / or a predefined threshold of the performance indicator difference, more particularly, if the evaluation comprises a comparison to another production strategy. In embodiments, evaluating the at least one performance indicator of the selected production strategy can comprise presenting the selected production strategy and the at least one performance indicator of the selected production strategy. Presenting the selected production strategy and the at least one performance indicator of the selected production strategy can comprise visualizing the selected production strategy and the at least one performance indicator of the selected production strategy for an operator. In embodiments, evaluating the at least one performance indicator of the selected production strategy can comprise presenting the production strategy with its high-level configuration after the at least one performance indicator. In embodiments, evaluating the at least one performance indicator of the selected strategy can be performed by an operator. The at least one performance indicator can be selected together with the selected production strategy before simulating the selected production strategy. One or more performance indicators can be generated and evaluated for each selected production strategy. The selected production strategy can be evaluated in isolation. In embodiments, the at least one performance indicator of the selected production strategy is presented in combination with at least one other production strategy and the associated at least one performance indicator. The plurality of production strategies can be presented in a way that marks a preferred production strategy according to the performance indicators. Based on the generated and evaluated performance indicators, a revised production strategy can be suggested. An acceptance criterion can be defined for the at least one performance indicator, based on which the selected production strategy will be accepted. The acceptance criterion can be represented by a threshold of the at least one performance indicator. The acceptance criterion can comprise a plurality of thresholds for different performance indicators. In embodiments, evaluating the selected production strategy can not require user interaction. In embodiments, the at least one performance indicator of the selected strategy can be evaluated automatically. In embodiments, evaluating the at least one performance indicator of the selected production strategy can comprise saving the selected production strategy and the respective at least one performance indicator in a computer file, in particular in a temporary computer file and / or a log file. Modifying a strategy

[0034] In some embodiments, after the evaluation, the evaluated production strategy can be revised. These revisions can focus on the at least one performance indicator selected when evaluating the selected production strategy and / or evaluating the at least one respective performance indicator. In embodiments, the optimization of the evaluated production strategy can be performed by a value chain optimization. The value chain optimization can use an optimization algorithm, in particular gradient descent, to optimize the evaluated production strategy. In embodiments, a predefined state of the production strategy can be revised. In particular, the conditions of the variables of the predefined state can be revised. More particularly, the values considered to fulfill the predefined state can be revised. In embodiments, the high-level configuration applied in the predefined state can be revised.

[0035] In embodiments, the revised production strategy can be limited to evaluating a high-level configuration of the production strategy. The limitation of revisions to the high-level configuration can reduce the complexity of the optimization and provide more predictable optimization results for the operator and / or production planner and / or process planner. Further, the operator and / or production planner and / or process planner can select a production strategy based on a predefined state that has been materialized and can seek to optimize only the production strategy selection and the production strategy to be implemented in response to the materialized state. In embodiments, the production strategy can be automatically optimized if the predefined state occurs.

[0036] In embodiments, the revised production strategy can be simulated after the revisions to the production strategy. From the simulation of the revised production strategy, performance metrics can be generated. The generated performance metrics of the revised production strategy can be the same performance metrics as in the initial simulation. In embodiments, new performance metrics can be selected prior to modifying the selected production strategy.

[0037] The revised production strategy and the at least one performance metric of the revised production strategy can be compared to the initial production strategy and the at least one performance metric of the initial production strategy. In embodiments, the at least one performance metric of the revised production strategy can be compared to at least one performance metric of an acceptance criteria. The revised threshold can be accepted if a predefined threshold defined in the acceptance criteria is met. If the predefined threshold is not met, the acceptance criteria can be iteratively evaluated until the threshold is met.

[0038] In embodiments, the revised production strategy and the at least one performance metric of the revised performance metric can be compared to another production strategy of the set of strategies. If the other production strategy is better than the revised production strategy, the other production strategy can be adopted and accepted or further adapted. A production strategy can be considered better than another production strategy if the performance metric of the production strategy is closer to the threshold than the performance metric of the other production strategy.

[0039] In embodiments, in a hypothetical analysis, a production strategy can be compared to at least one other production strategy. The hypothetical analysis for comparing the production strategies can include a scenario reflected in a state and simulate the production strategy in a model of an industrial process initialized with process values associated with the scenario. At least one performance metric can be generated for each production strategy to be compared. In embodiments, multiple scenarios can be employed to compare the production strategies. At least one performance metric can be generated from the at least one performance metric of the multiple scenarios. Based on the comparison in the hypothetical analysis, a production strategy can be accepted.

[0040] In embodiments, the hypothetical analysis can include a queuing chain model, in particular for foreseeable interruptions, in particular for maintenance interruptions.

[0041] In embodiments, the production strategy can be tested in a hypothetical analysis to test the robustness of the production strategy. Testing the robustness of the production strategy can comprise setting scenarios outside of the standard operating scenarios. In embodiments, testing the robustness of the production strategy can comprise unexpected production interruptions, in particular, piecewise interruptions of production. In embodiments, testing the robustness of the production strategy can comprise unplanned maintenance interruptions. In embodiments, testing the robustness of the production strategy can comprise unexpected changes in product demand, in particular, additional product demand or less product demand, unexpected changes in energy prices, in particular, higher peak energy prices or negative energy prices. In embodiments, an indicator for the robustness of the production strategy can be the mean time between unplanned production stops and / or failures, or the uptime or downtime of the machinery and / or the production process. Accepting a strategy

[0042] In embodiments, the selected production strategy can be accepted based on the at least one performance indicator. In particular, the selected production strategy can be accepted if a threshold value of the at least one performance indicator is exceeded. The evaluated production strategy can be accepted if it can be considered superior to another production strategy, in particular, to the production strategy that is in use or that is designated to be used. In embodiments, one production strategy can be considered superior to another production strategy if the at least one performance indicator of the one production strategy is superior to the at least one performance indicator of the other production strategy. In embodiments, accepting the selected production strategy can be performed manually by a user. In embodiments, the selected production strategy can be accepted automatically as soon as a predefined threshold value is reached. Implementing a strategy

[0043] In embodiments, the accepted production strategy can be implemented. Implementing the accepted production strategy can comprise controlling the industrial process by implementing the associated low-level instructions by the DCS. In particular, implementing can comprise changing controller settings of the machinery controllers, revising set points of the machinery controllers, revising ranges of alarm signals, and / or revising instructions of operators.

[0044] In embodiments, implementing the accepted production strategy can comprise revisions of the energy management system. In particular, low-level instructions for energy procurement can be revised. In embodiments, low-level instructions for energy storage can be revised.

[0045] In embodiments, implementing the accepted production strategy can comprise revisions in the inventory management system. In particular, low-level instructions for replenishing inventory can be revised.

[0046] In embodiments, implementing the accepted production strategy can comprise revisions in the planning and scheduling system. In particular, the execution order and / or the timing of process steps can be revised.

[0047] In embodiments, implementing the accepted production strategy can comprise a revision in the manufacturing execution system. In particular, high-level configurations to be employed after a state outside of the plan can be revised and / or set. Miscellaneous

[0048] In embodiments, the industrial process controlled by the method can comprise pulp production. In embodiments, the industrial process controlled by the method can comprise paper production. In embodiments, the industrial process controlled by the method can comprise mining processes, mineral processing, food and beverage production, hydrogen generation, and / or steam generation. In embodiments, the industrial process controlled by the method can be a chemical industry process. In embodiments, the method can be used for controlling a water network.

[0049] In embodiments, the method can be used for revising a production strategy during production. In particular, a production strategy used can be selected and simulated in a model of the industrial process, wherein the model of the industrial process is initialized with a current production state. In embodiments, the revision process during production is implemented continuously during production. In embodiments, at regular intervals, in particular every hour, every two hours, every four hours, every eight hours, or every day, the production strategy is revised with the method. In embodiments, the production strategy is revised with the method if at least one predefined state changes. In embodiments, the production strategy is revised periodically or if at least one predefined state changes. In embodiments, the production strategy is revised with the method if the digital twin model of the industrial process is revised, in particular if the industrial process is revised. Industrial control system

[0050] The method according to embodiments described herein, in particular according to the method described herein, can be executed in an industrial control system. The industrial control system can comprise a distributed control system module, a manufacturing control system module, an energy management system module, and an analytics module.

[0051] In embodiments, the distributed control system module can comprise a plurality of sensor systems, a plurality of controller systems, and / or edge devices. In particular, the distributed control system can be distributed over the entire production plant. In embodiments, low-level operational instructions of the production strategy can be implemented in the edge devices and / or the controllers. In embodiments, low-level operational instructions of the production strategy can be processed centrally. In particular, sensor data can be transmitted to a central control infrastructure, and controller settings are revised due to centrally executed analytics.

[0052] In embodiments, the analytics module of the industrial control system can comprise a digital twin model of the industrial process, in particular a material flow and energy digital twin model. In embodiments, the digital twin can be accessed via a cloud computing infrastructure.

[0053] Embodiments of the present disclosure can allow controlling an industrial process by revising a production strategy in a digital twin model. In particular, the production strategy can be revised to incorporate an energy supply related to an external state. Embodiments can allow improving the sustainability of a unit product, in particular the CO2 equivalent emissions per unit product. Embodiments can allow controlling an industrial process in a way that optimizes production and / or production strategy along a flexible on-site electricity price. BRIEF DESCRIPTION OF DRAWINGS

[0054] The drawings relate to embodiments of the present disclosure and are described in the following: Figure 1 schematically illustrates a method for controlling an industrial process according to embodiments described herein; Figure 2 schematically illustrates a part of a method for controlling an industrial process according to embodiments described herein, in particular revising a selected strategy; Figure 3 schematically illustrates a part of a method for controlling an industrial process according to embodiments described herein, in particular revising a selected strategy; Figure 4 schematically illustrates a model of an industrial process according to embodiments described herein; Figure 5 schematically illustrates an interaction of a strategy generator according to embodiments described herein; Figure 6 schematically illustrates an interaction of a material flow and energy digital twin according to embodiments described herein; Figure 7 schematically illustrates an interaction of a material flow and energy digital twin according to embodiments described herein; Figure 8 schematically illustrates an interaction of a material flow and energy digital twin according to embodiments described herein; Figure 9 schematically illustrates an industrial control system according to embodiments described herein; and Figure 10 schematically illustrates an implementation of a production strategy according to embodiments described herein. DETAILED DESCRIPTION

[0055] Reference will now be made in detail to the various embodiments of the present disclosure, one or more examples of which are illustrated in the accompanying drawings. Generally, only the differences between various embodiments are described. Each example is provided by way of explanation of the present disclosure and is not meant as a limitation of the present disclosure. Further, features illustrated or described as part of one embodiment can be used on or in combination with other embodiments to yield yet another embodiment. It is intended that the present disclosure include these and all such modifications and variations.

[0056] Figure 1 A method of controlling an industrial process using a model of the industrial process is schematically illustrated. The method comprises a plurality of steps. In a first step, a production policy is selected from a set of policies. The set of policies comprises at least one policy. In Figure 1 The set of policies comprises four production policies (pp1, pp2, pp3, pp4). Exemplarily, pp2 is selected. The selected production policy is simulated in the model of the industrial process. In the model of the industrial process, the high-level configuration of the selected production policy is translated into low-level operation instructions. Further, performance indicators, also referred to as key performance indicators (KPIs), are generated within the model. At least one KPI of the selected production policy is evaluated. Based on the evaluation result of the at least one KPI of the selected production policy, the selected production policy is either accepted or adapted or another production policy is selected. Once a production policy is accepted, the production policy is implemented.

[0057] Figure 2 The adaptation of the selected production policy is schematically illustrated in more detail. The adaptation policy comprises amending the selected policy. The amended policy is simulated in the model of the industrial process. In the model of the industrial process, the high-level configuration of the amended production policy is translated into low-level operation instructions. Further, performance indicators are generated in the model. For each performance indicator, the value of the performance indicator is compared to a predefined threshold value. If the threshold value of the performance indicator is reached, the amended policy is accepted. If the threshold value of the performance indicator is not reached, the amended policy is further amended, the described process is iteratively repeated until the threshold value is reached. The amendment of the policy can be performed manually by an operator and / or a production planner. The amendment of the policy can be performed automatically by an optimization algorithm.

[0058] Figure 3 An adaptation embodiment of the selected production policy is schematically illustrated. The selected policy is amended and simulated as in the embodiment of Figure 2 The performance indicators of the amended policy are compared to the performance indicators of the initially selected policy. If the amended policy is considered better than the selected policy according to the comparison of the performance indicators, the amended policy is accepted. Otherwise, the amended policy is further amended, the described process is iteratively repeated until the amended policy is better than the selected policy. Figure 3Embodiments of the application are particularly suitable for optimization of already implemented production strategies.

[0059] Figure 4 The interaction within the model of the industrial process is schematically illustrated. The model of the industrial process, in particular as a digital twin model, comprises an energy flow and a material flow. In the model, the influence of the energy flow on the material flow, in particular the change of the energy flow on the material flow, is described. Furthermore, in the model, the influence of the material flow on the energy flow, in particular the change of the material flow on the energy flow, is described.

[0060] Figure 5 The interaction of a strategy generator according to embodiments herein is schematically illustrated. The state of the industrial process and the planned actions in the industrial process are input properties of the simulator module. In the simulator module, a high-level configuration of a production strategy is generated. The input state can comprise a current state, a historical state or a future state. The planned actions can be actions that have been executed in the past as a reaction to a historical state, and / or actions that have been executed in the past as a reaction to a historical state. The planned actions can also be actions according to best practice rules, standard operating procedures, operator experience and / or educated guesses.

[0061] Figure 6 The interaction of a material flow and energy digital twin according to embodiments herein is schematically illustrated. Information from a distributed control system (DCS) is used to start a material flow and energy digital twin with a current state of the production plant. A selected strategy is implemented in the material flow and energy digital twin. In the material flow and energy digital twin, the production process is simulated and at least one performance indicator is generated. The performance indicator can be used by an operator to decide whether to use the selected strategy in the industrial process.

[0062] Figure 7 The interaction of a material flow and energy digital twin according to embodiments herein is schematically illustrated. Information from a manufacturing execution system (MES) and a selected production strategy are implemented in a material flow and energy digital twin system. In the material flow and energy digital twin, the production process is simulated and at least one performance indicator is generated. The performance indicator can be used by an operator to correct the MES plan if the selected strategy is to be maintained. Alternatively or additionally, the selected strategy can be corrected.

[0063] Figure 8The interaction of material flow and energy digital twin according to embodiments described herein is schematically illustrated. The planned actions and the selected production strategy in the integrated planning and scheduling (IPS) system are implemented in the material flow and energy digital twin system. In the material flow and energy digital twin, the production process is simulated and at least one performance indicator is generated. The performance indicator can be used by the operator to correct the planned actions planned in the IPS if the selected strategy is to be maintained. Alternatively or additionally, the selected strategy can be corrected.

[0064] Figure 9 An industrial control system and its interaction with an industrial process are schematically illustrated. The industrial control system comprises an analytics module, an energy management system (EMS), a manufacturing execution system (MES) and a distributed control system (DCS). The distributed control system controls the industrial process and receives data from sensors and controllers of the industrial process. The analytics module can comprise a digital twin of the industrial process. The digital twin can be initialized using data from the distributed control data. The analytics module can receive data from the EMS to model the energy state and / or to reflect the energy market state. The analytics data from the digital twin can be used by the energy management system to correct the energy procurement. The MES can exchange information with the energy management system on a high level framework. In particular, information comprising general availability conditions of energy can be exchanged. The MES provides the analytics module with high level configurations to be translated into low level operation instructions. Data from the analytics module, in particular performance indicators, can be used to adapt and / or optimize the high level framework instructions and / or the high level configurations.

[0065] Figure 10 An implementation of a production strategy according to embodiments described herein is schematically illustrated. In particular, Figure 10 The illustrated industrial process is a papermaking process. The optimization of the production strategy acts on the material flow in the papermaking machine as well as on the energy flow, in particular the energy flow in the steam generating machine and the energy management. For the papermaking process Figure 10 The interaction of energy flow and material flow is optimized for the steam drying phase in. For other phases of the industrial process, similar optimizations can be performed.

Claims

1. A method for controlling an industrial process, said industrial process being executed by a production plant, a distributed control system, a manufacturing execution system, and an energy management system. Using the model of the industrial process, the method includes: (a) Select a production strategy from a set of strategies, where A strategy is a set of high-level configurations applied within the high-level framework of the industrial process under corresponding predefined states, and wherein... The high-level framework is a generalized and systematic description of the industrial process and the interactions within the industrial process. The advanced configuration includes a description of generalized operating modes of at least the distributed control system, the production process, and the energy management system within the advanced framework, and The status includes at least one of the following: environmental status, energy supply status, process status, inventory level status, and energy status. (b) Using the model of the industrial process to simulate the high-level configuration of the selected production strategy, wherein the simulation includes translating the high-level configuration of the selected production strategy into low-level operational instructions implemented in the industrial model, thereby generating at least one performance metric. (c) Evaluate at least one performance metric of the selected production strategy. (d) Optionally, the selected production strategy may be modified or another production strategy may be selected based on the at least one performance metric; (e) Accept the selected production strategy based on at least one of the performance metrics; as well as (f) Implement the accepted production strategy and associated low-level operational instructions to control the industrial process through the distributed control system.

2. The method according to claim 1, wherein the at least one performance indicator includes at least one of the following: cost indicator, energy use indicator, production output indicator, quality indicator, efficiency indicator, environmental impact indicator, and in particular greenhouse gas emission indicator.

3. The method of claim 1, wherein modifying the evaluated production strategy includes iteratively evaluating the acceptance criteria of the at least one performance metric. Until a predefined threshold of at least one of the performance metrics is reached.

4. The method of claim 3, wherein the acceptance criteria for evaluating the at least one performance metric include: The production strategy was revised. The model of the industrial process is used to simulate the high-level configuration of the modified production strategy, wherein the simulation includes translating the high-level configuration of the modified production strategy into low-level operational instructions implemented in the industrial model, thereby generating at least one performance metric. The generated at least one performance metric is compared with the predefined threshold of the at least one performance metric.

5. The method of claim 4, wherein modifying the evaluated production strategy includes modifying the predefined state.

6. The method of claim 4, wherein the scope of the modified production strategy is limited to the advanced configuration.

7. The method according to claim 1, wherein The model of the industrial process includes energy flow and material flow; The model of the industrial process describes the effect of changes in the energy flow on the material flow and the effect of changes in the material flow on the energy flow.

8. The method of claim 1, wherein at least one of the production strategies from the set of strategies is derived by a strategy generator.

9. The method of claim 8, particularly through a machine learning process, wherein the policy generator uses a machine learning process to generate a policy based on historical data.

10. The method of claim 1, wherein selecting another production strategy based on the at least one performance metric includes a comparison with at least one other production strategy.

11. The method of claim 10, wherein the comparison with at least one other production strategy comprises comparing the different production strategies in a hypothesis analysis.

12. The method of claim 1, further comprising initializing the model of the industrial process with a production state, wherein the production state is derived from at least one of historical data, current data, or planned production states.

13. The method of claim 1, wherein the industrial process comprises paper and / or pulp production.

14. An industrial control system for controlling an industrial process by means of the method according to any one of the preceding claims.

15. The industrial control system according to claim 14, comprising: A distributed control system module configured to implement the accepted production strategy and associated low-level operational instructions; A manufacturing execution system module, configured to provide an overview of the current production status and order fulfillment; An energy management system module, configured to control the energy flow in the industrial process; as well as An analysis module is configured to model the industrial process, wherein energy flow affects material flow, and material flow affects energy flow.

Images