Industrial system simulation deduction method and device, electronic equipment and medium

Abstract

The application discloses an industrial system simulation deduction method and device, electronic equipment and medium. The method comprises the following steps: obtaining simulation deduction scene information of an industrial system; determining an industrial simulation deduction template matched with the simulation deduction scene information; performing simulation parameter configuration on the industrial simulation deduction template to obtain a simulation model; generating dynamic strategy information for driving the simulation model according to the simulation deduction scene information; performing iterative simulation deduction on the simulation model according to the dynamic strategy information to obtain a simulation deduction result; in response to the simulation deduction result meeting a preset condition, saving and publishing the industrial simulation deduction template; and in response to the simulation deduction result not meeting the preset condition, adjusting a digital twin node and a topological layout in the industrial simulation deduction template until the simulation deduction result of the adjusted industrial simulation deduction template meets the preset condition. Thus, the reusability and adaptability of the simulation deduction template are improved, the problem solving efficiency of the industrial system is improved, and the loss of the industrial equipment is reduced.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to an industrial system simulation and deduction method, apparatus, electronic device and medium. Background Technology

[0002] Simulation is a technique that uses mathematical models and computer simulations to simulate the operation of industrial systems. It can simulate the operation of industrial systems under different conditions without affecting their actual operation, thus providing solutions to problems such as power consumption in real industrial systems.

[0003] For industrial system simulation, the usual method is to manually modify the template parameters of a preset general industrial system simulation template to obtain the industrial system simulation results.

[0004] However, in practice, it has been found that when using the above methods to simulate industrial systems, the following technical problems often arise: Because the industrial system simulation template is a general-purpose template, it cannot match complex and personalized industrial scenarios. The template adjustment is not flexible enough. Furthermore, manually adjusting template parameters based on human experience introduces subjective factors, leading to significant deviations between the simulation results and the actual operation of real industrial scenarios. This results in low reliability of the simulation results, causing high equipment wear and tear on various industrial devices within the industrial scenario, thus hindering the improvement of problem-solving efficiency and extending the solution time for industrial systems. Summary of the Invention

[0005] In view of this, this application provides an industrial system simulation and deduction method, apparatus, electronic device and medium to solve one or more of the technical problems mentioned in the background section above.

[0006] According to a first aspect of this application, an industrial system simulation and deduction method is provided, the method comprising: Acquire simulation and deduction scenario information of industrial systems; An industrial simulation template matching the simulation scenario information is determined, wherein the industrial simulation template defines each digital twin node and its topology layout in the industrial system; Perform simulation verification operations according to the industrial simulation template, wherein the simulation verification operations include: The simulation parameters of the industrial simulation template are configured to obtain the simulation model; Dynamic strategy information for driving the simulation model is generated based on the simulation scenario information; The simulation model is iteratively simulated and deduced based on the dynamic strategy information to obtain the simulation results. In response to the simulation results meeting preset conditions, the industrial simulation template is saved and published; In response to the simulation results not meeting the preset conditions, the digital twin nodes and topology layout in the industrial simulation template are adjusted, and the simulation verification operation is re-executed.

[0007] According to a second aspect of this application, an industrial system simulation and deduction device is provided, the device comprising: The acquisition unit is used to acquire simulation scenario information of the industrial system. The template determination unit is used to determine an industrial simulation template that matches the simulation scenario information, wherein the industrial simulation template defines each digital twin node and its topology layout in the industrial system. The simulation simulation unit is used to perform simulation simulation verification operations based on the industrial simulation simulation template, wherein the simulation simulation verification operations include: The simulation parameters of the industrial simulation template are configured to obtain the simulation model; Generate dynamic strategy information to drive the simulation model; The simulation model is iteratively simulated and deduced based on the dynamic strategy information to obtain the simulation results. In response to the simulation results meeting preset conditions, the industrial simulation template is saved and published; In response to the simulation results not meeting the preset conditions, the digital twin nodes and topology layout in the industrial simulation template are adjusted, and the simulation verification operation is re-executed.

[0008] According to a third aspect of this application, a computer-readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the above-described industrial system simulation and deduction method.

[0009] According to a fourth aspect of this application, an electronic device is provided, including one or more processors; a storage device having one or more programs stored thereon; when the one or more programs are executed by the one or more processors, the one or more processors implement the steps of the above-described industrial system simulation and deduction method.

[0010] By employing the aforementioned technical solution, the actual scenario information for industrial system simulation is first obtained. This scenario information is then used to match a suitable industrial simulation template for that scenario. Next, parameter configuration is used to configure the actual operating parameters of the industrial system for the digital twin nodes of the equipment in the template. This makes the operation of the digital twin nodes more closely resemble that of real industrial equipment, thus avoiding simulation distortion to a certain extent. Furthermore, a scenario-driven dynamic strategy is used to simulate the instantiated simulation model, and closed-loop feedback is implemented based on the feedback results generated by iterative simulation to optimize the node architecture and logical configuration of the template itself. This not only improves the adaptability and relevance of the industrial simulation template, dynamic strategy, and actual business scenarios, thus enhancing the accuracy of simulation, but also avoids errors in simulation caused by purely theoretical assumptions through model simulation. This makes the industrial simulation template closer to the operating state of real industrial systems, further improving the reliability and accuracy of simulation results. It also facilitates the reusability of the simulation template, reduces the workload of reconstruction, and improves the efficiency of simulation template construction.

[0011] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating the industrial system simulation and deduction method provided in an embodiment of this application is shown. Figure 2 This paper shows a structural block diagram of the industrial system simulation and deduction device provided in an embodiment of this application; Figure 3 A schematic diagram of the electronic structure of the electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0013] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0014] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0015] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “attached” to another element, it can be directly connected or attached to the other element, or there may be intermediate elements. Furthermore, “connected” or “attached” as used herein can include wireless connections or wireless interconnections. The term “and / or” as used herein includes all or any unit and all combinations of one or more associated listed items.

[0016] Exemplary embodiments according to this application will now be described in more detail with reference to the accompanying drawings. However, these exemplary embodiments may be implemented in many different forms and should not be construed as being limited to the embodiments set forth herein. It should be understood that these embodiments are provided so that the disclosure of this application is thorough and complete, and that the concept of these exemplary embodiments is fully conveyed to those skilled in the art.

[0017] This embodiment provides a method for simulating and extrapolating industrial systems, such as... Figure 1 As shown, the method includes: Step 101: Obtain simulation scenario information of the industrial system.

[0018] Specifically, simulation scenario information of industrial systems is used to mark equipment operating scenarios.

[0019] Step 102: Determine the industrial simulation template that matches the simulation scenario information.

[0020] The industrial simulation template defines the digital twin nodes and their topology layout within an industrial system. For example, it includes digital twin models of various devices within the industrial system, simulating the device layout, operational logic, and interaction processes of a real industrial system.

[0021] In practical applications, when using technical solutions to address the technical problems mentioned in the background, the following technical issues often arise: the geometric spatial layout and interrelationships of various industrial equipment within an industrial system can lead to higher energy consumption and reduced space utilization, increasing the damage to industrial equipment and potentially causing industrial accidents. A conventional solution to these issues is to use preset rules (such as power flow calculations and fault isolation strategies) to arrange the geometric layout of industrial equipment within the industrial system. However, this conventional solution still suffers from the following problems: the preset rules are somewhat subjective and cannot be updated in real-time according to the industrial system, resulting in an unreasonable topology layout, leading to higher energy consumption, reduced space utilization, and increased damage to industrial equipment. Therefore, step 102, namely determining the industrial simulation template that matches the simulation scenario information, specifically includes the following steps: Step 102-1: Retrieve the initial simulation template from the preset template library based on the simulation scenario information.

[0022] The aforementioned preset template library can be a pre-defined database used to store and publish available simulation templates. This database can be a graph database. The initial simulation template defines common digital twin nodes and their topology layout in the industrial system. The aforementioned digital twin nodes can be nodes formed by the digital twins of various industrial devices within the industrial system, within a topology graph. The aforementioned topology layout represents the information about the topological geometric layout formed by the connection relationships between the various digital twins.

[0023] In this embodiment, a combination of fuzzy matching and precise matching algorithms is used to retrieve templates from a pre-defined template library based on industrial system simulation scenario information. This not only eliminates the need to build simulation templates from scratch, but also allows for the direct reuse of pre-defined digital twin nodes and topology layout frameworks from the template library, significantly reducing the modeling cost of industrial simulations and improving template building efficiency. Furthermore, it ensures that the initial simulation template aligns with the actual needs of the industrial system from the outset, reducing the frequency and extent of subsequent template adjustments and improving the overall adaptability of the simulation.

[0024] In one embodiment, step 102-1, namely retrieving an initial simulation template from a preset template library based on the simulation scenario information, specifically includes: extracting graph features from the preset simulation templates stored in the preset template library to obtain corresponding graph feature vectors; extracting text features from the simulation scenario information to obtain corresponding text feature vectors; and selecting an initial simulation template from the preset simulation templates based on the similarity between the text feature vectors and the graph feature vectors.

[0025] Graph feature extraction can be achieved through graph embedding representation using a graph neural network model. Graph feature vectors are used to characterize the semantic information and spatial and logical relationships between digital twin nodes in the industrial simulation template. Text feature vectors are used to characterize the textual semantic information and topological graph structure information of the simulation scenario. Text feature extraction can be achieved through embedding representation using a large language model.

[0026] In this embodiment, the initial inference template is selected based on the similarity of two types of feature vectors. This not only achieves accurate and quantitative matching between the template and the scene in terms of feature dimensions, effectively avoiding information bias in traditional retrieval and subjective errors in manual selection, but also significantly improves the retrieval accuracy and objectivity of the initial template. Furthermore, due to the high efficiency of feature vector similarity retrieval, the template selection speed is significantly accelerated and the early matching cycle is shortened. Moreover, the retrieved initial template is highly consistent with the scene, which can reduce the workload and cost of subsequent template adjustment and optimization.

[0027] Step 102-2: Analyze the simulation scenario information to obtain scenario constraint information, scenario topology layout, and scenario device set.

[0028] The scenario constraint information includes scenario physical constraints, scenario logical constraints, and scenario performance constraints. For example, scenario physical constraints may be the boundary range of the scenario, insurmountable obstacle areas, etc.; scenario logical constraints may be determining the minimum safe distance between devices, the sequence of production flows, etc.; scenario performance constraints may be optimization objectives, cable or pipeline connection topology requirements, equipment inspection path requirements, etc. The scenario topology layout may be a geometric topology diagram composed of the spatial locations and relationships of various industrial devices included in the industrial system simulation scenario information. The scenario device digital twin nodes in the scenario device set may be digital twin models of the industrial devices included in the aforementioned industrial system simulation scenario information.

[0029] Step 102-3: Based on the scene constraint information, perform functional module division and network discretization processing on the scene topology layout to generate a layout optimization model.

[0030] Among them, the layout optimization model is used to describe an integer programming model that minimizes the cost of adjusting the topology information of an industrial system while satisfying geometric layout and equipment constraints.

[0031] In this embodiment, based on the interaction frequency and business collaboration relationships between devices, a clustering algorithm is used to divide related devices in the scene topology into the same functional module, and the initial relative positions of each functional module in the global space are defined. Furthermore, network discretization is used to divide the scene topology into discrete point, line, and surface elements that can be processed by the algorithm. An objective function for layout optimization is constructed using various constraints as targets, resulting in a layout optimization model. Thus, discretization processing and layout optimization algorithms are used to fine-tune the initial template and dynamically associate digital twin nodes to improve the efficiency of generating complex topology layouts.

[0032] As an example, using a community detection algorithm, the scene topology layout graph is dynamically divided into functional modules based on scene constraint information, resulting in a scene topology subgraph set. The scene topology subgraphs in this set can be structured subgraphs obtained by dividing the graph into different functional modules. Device locations can be represented using grid coordinates, rather than continuous coordinates. Then, the scene topology graph is discretized to obtain a discretized spatial grid set. The discretized spatial grid in this set can be a grid that divides the three-dimensional space of the scene topology graph into equally sized grid cells to represent the spatial distribution of the scene topology graph. Finally, based on the scene topology subgraph set and the discretized spatial grid set, a parallel layout optimization solution is performed on the layout optimization model of the scene topology subgraph set to obtain optimized layout information. The objectives of the layout optimization model can include, but are not limited to, at least one of the following: adjusting the objective function to minimize layout cost, maximizing space utilization constraints, minimizing device connection pipeline length constraints, and minimizing inter-device movement distance constraints. The optimized layout information can be layout information obtained after adjusting the spatial layout and connection relationships in the aforementioned scene topology subgraphs. As an example, the aforementioned execution entity can employ a non-dominated sorting genetic algorithm to perform parallel layout optimization on the scene topology layout update model of the aforementioned scene topology sub-graph set based on the aforementioned scene topology structure sub-graph set and discretized spatial grid set, thereby obtaining optimized layout information.

[0033] Step 102-4: Solve the layout optimization model to obtain the optimized layout information.

[0034] Understandably, a non-dominated sorting genetic algorithm can be used to perform parallel layout optimization on the scene topology layout update model of the aforementioned scene topology subgraph set and discretized spatial grid set, thereby obtaining optimized layout information. This optimized layout information can be the layout information obtained after adjusting the spatial layout and connectivity relationships in the scene topology subgraph.

[0035] Step 102-5: Perform collision detection on the optimized layout information, and adjust the topology layout and digital twin nodes of the preset simulation template according to the collision detection results and the scene device set to generate an industrial simulation template.

[0036] The collision detection results are used to represent information about the risk of spatial interference between digital twins of devices.

[0037] Specifically, adjustments to the topology layout and digital twin nodes include, but are not limited to, at least one of the following: adding or deleting digital twin nodes, replacing the type of digital twin nodes, modifying the connection relationships of digital twin nodes, and adding or deleting connection relationships.

[0038] In this embodiment, upon retrieving the initial simulation template, equipment information and topology layout information are extracted from the simulation scenario information to obtain scenario constraint information, scenario topology layout, and scenario equipment set. Based on the scenario constraint information, the scenario topology layout is functionally divided into modules to achieve region decoupling, reduce the impact range when adjusting the equipment digital twin model, and lower the computational difficulty. Furthermore, a layout optimization model is generated using discretization processing to transform the continuous three-dimensional space into uniformly sized grid cells, replacing continuous coordinates with discrete grid coordinates, simplifying the mathematical representation of spatial positions, reducing the complexity of subsequent layout optimization, unifying spatial measurement standards, and enabling parallel solving under constrained conditions. This improves the adaptability to industrial scenarios and shortens the solution time. After obtaining the optimized layout information from the solved model, collision detection is performed, and the topology layout and digital twin nodes of the initial simulation template are adjusted based on the detection results and the scenario equipment set to generate an industrial simulation template adapted to the actual scenario. This improves the template library reusability while ensuring the adaptability of the template's topology layout and digital twin nodes to the constraints and equipment configuration of the actual scenario. This approach balances template generation efficiency with the fit of industrial simulation templates to real-world scenarios.

[0039] In one embodiment, collision detection is performed on the optimized layout information, and the topology layout and digital twin nodes of the preset simulation template are adjusted according to the collision detection results and the scene device set to generate an industrial simulation simulation template. Specifically, this includes: performing voxelization processing on the scene device set to obtain a device voxel mesh set; performing multi-level collision detection on the optimized layout information according to the device voxel mesh set to obtain collision detection results; and generating the topology layout and digital twin nodes of the industrial simulation simulation template according to the optimized layout information representing collision passage, the target user layout information filtering operation information, and the scene device set in the collision detection results.

[0040] In this embodiment, multi-level collision detection after device voxelization simplifies the spatial geometric representation of the device while preserving its spatial occupancy characteristics, reducing the amount of collision detection data. Multi-level detection enables efficient and comprehensive collision risk identification. Based on the adjusted industrial simulation template, geometric layout adjustments to the industrial system can reduce energy consumption, improve space utilization, and minimize damage to industrial equipment.

[0041] As an example, axis-aligned bounding boxes (AABBs) can be used for rapid filtering. Based on the aforementioned device voxel network set, coarse-grained collision detection is performed on the optimized layout information to obtain coarse-grained collision check results. Then, using the separating axis theorem based on directed bounding boxes (OBBs), fine-grained collision detection is performed on at least one optimized layout information in the coarse-grained collision check results that indicates a collision has passed, to obtain fine-grained collision check results. Next, using the device working envelope trajectory, trajectory prediction is performed on at least one optimized layout information in the fine-grained collision check results that indicates a collision has passed, to obtain trajectory collision check results. The optimized value set of at least one optimized layout information in the trajectory collision check results that indicates a collision has passed is determined as a recommended value set. At least one optimized layout information is sorted and displayed according to the values ​​in the recommended value set from high to low. Subsequently, in response to the target user's instruction to select the displayed optimized layout information through layout information filtering, these optimized layout information are used as the final template topology layout. Conversely, in response to the target user's instruction not to select at least one of the above optimized layout information through layout information filtering, a warning can be issued to the target user. Finally, the scene equipment set was identified as each digital twin node, forming an industrial simulation template. Based on this template, the geometric layout of the industrial system can be updated in real time. This prevents unreasonable topology layouts in the industrial system, thereby reducing energy consumption, improving space utilization, and minimizing damage to industrial equipment.

[0042] Furthermore, in one embodiment, the industrial system simulation and deduction method further includes: if no initial deduction template is found from the preset template library, then based on the historical information of the industrial equipment corresponding to the simulation and deduction scenario information, the equipment interaction logic and digital twin model set of each industrial equipment are determined; based on the equipment interaction logic, a three-dimensional topology map is constructed on the digital twin model set, and the constructed three-dimensional topology map of the industrial equipment is used as the initial deduction template.

[0043] The digital twin model set can be a collection of models obtained by digitally mapping industrial equipment. This digital twin model can be a digital model created based on the shape, parameter, and structural information of the industrial equipment, and described and expressed from five dimensions: geometric model, logical model, information model, mechanistic model, and empirical model. The geometric model can present the geometric appearance, animation, and visualization effects of the equipment in a three-dimensional form. The logical model can define the logical relationships (e.g., spatial relationships, logical control relationships) of the three-dimensional twin. The information model can be a standard, structured language describing the characteristics and basic information of the three-dimensional twin. The mechanistic model can be a model based on the internal mechanisms and mathematical principles of the industrial equipment, reflecting the operating laws of the industrial equipment through geometric modeling. The empirical model can describe the input-output relationships of the industrial equipment. It is understood that the above digital twin models can be constructed using the ThingJS digital twin engine (an IoT 3D visualization development platform).

[0044] The device interaction logic can be information about the logical relationships between the inputs and outputs of the various industrial devices and the topological relationships of their spatial distribution.

[0045] Specifically, historical information of industrial equipment can be the input and output information of industrial equipment that is located before the current time, including but not limited to the equipment's design parameters, 3D model information, historical operating data of the equipment, communication connection relationships between equipment, and material flow records.

[0046] In this embodiment, when the preset template library lacks a suitable initial simulation template for the current scenario, input / output information and spatial location information of historical industrial equipment in the scenario are extracted, and the resulting historical equipment topology logic information is used as the equipment interaction logic. Simultaneously, a digital twin model set is constructed by combining the 3D model information and equipment design parameters from the historical industrial equipment information. Then, a 3D topology map is constructed based on this topology layout of the digital twin model set, and the final 3D topology map of the industrial equipment is used as the initial simulation template. This allows for personalized and scenario-based construction of initial simulation templates for various industrial simulation scenarios, achieving initial simulation template construction by filling gaps in the template library. This ensures a high degree of fit between the initial template and the actual industrial scenario and equipment operating rules, while also achieving full scenario coverage of industrial simulation simulation template construction. This avoids simulation work being unable to proceed due to a lack of matching items in the template library, significantly improving the scenario applicability and practicality of industrial simulation simulation technology.

[0047] As an example, the spatial location information and logical relationships of each digital twin model in the aforementioned data twin model set can be determined through the device interaction logic described above, thus obtaining the spatial location information and logical relationship information. Then, each digital twin model in the aforementioned digital twin model set is dragged and dropped to the corresponding spatial location information, and the associated edges of the digital twin models are constructed according to the logical relationship information, resulting in a 3D topology map of the industrial scene equipment.

[0048] Step 103: Perform simulation verification operation according to the industrial simulation template.

[0049] Specifically, the simulation verification operation includes: configuring simulation parameters for the industrial simulation template to obtain a simulation model; generating dynamic strategy information to drive the simulation model based on the simulation scenario information; performing iterative simulation on the simulation model based on the dynamic strategy information to obtain simulation results; saving and publishing the industrial simulation template in response to the simulation results meeting preset conditions; and adjusting the digital twin nodes and topology layout in the industrial simulation template in response to the simulation results not meeting preset conditions, and re-executing the simulation verification operation.

[0050] The preset conditions can be pre-defined conditions for the iterative iteration of the adjusted industrial simulation template. For example, the condition that the power consumption of the device at the end of the system is greater than or equal to 90% of the device's standard power.

[0051] Specifically, the configured simulation model is set with the simulation parameters required for the simulation process and the initial operating parameters of the device's digital twin nodes. The simulation parameters may include, but are not limited to, at least one of the following: simulation speed and simulation stopping conditions. The initial operating parameters of the device's digital twin nodes may include, but are not limited to, at least one of the following: device power information, device response delay information, and historical operating data of the device.

[0052] As an example, simulation parameters corresponding to input operations can be loaded into the runtime environment of the industrial simulation template through input operations on the model property panel, so as to configure relevant parameters for the simulation model.

[0053] The industrial system simulation and deduction method provided in this application first obtains the actual scenario information of the industrial system simulation and deduction, and then uses this scenario information to match a suitable industrial simulation and deduction template for that scenario. Next, it configures the actual operating parameters of the industrial system for the digital twin nodes of the equipment in the template through parameter configuration, making the operation of the digital twin nodes of the equipment closer to that of real industrial equipment, thus avoiding the distortion problem in simulation and deduction to a certain extent. Furthermore, it uses a scenario-driven dynamic strategy to perform simulation and deduction on the instantiated simulation model, and performs closed-loop feedback based on the feedback results generated by iterative simulation to optimize the node architecture and logical configuration of the template itself. This not only improves the adaptability and relevance of the industrial simulation and deduction template and dynamic strategy to actual business scenarios, thus improving the accuracy of simulation and deduction, but also avoids the errors in simulation and deduction caused by purely theoretical assumptions to a certain extent through the simulation and deduction of the model. This makes the industrial simulation and deduction template closer to the operating state of the real industrial system, further improving the reliability and accuracy of the simulation and deduction results, facilitating the reusability of the simulation and deduction template, reducing the workload of reconstruction, and improving the efficiency of simulation and deduction template construction.

[0054] In practical application scenarios, step 103 involves configuring simulation parameters for the industrial simulation deduction template to obtain a simulation model. Specifically, this includes: in response to the parameter configuration operation of the industrial simulation deduction template, verifying the simulation parameters indicated by the parameter configuration operation; if the verification passes, configuring the industrial simulation deduction template according to the simulation parameters to generate a simulation model; if the verification fails, replacing the failed simulation parameters with preset recommended parameters to configure the industrial simulation deduction template and generate a simulation model.

[0055] In this embodiment, in response to detecting a parameter configuration operation by a target user, the simulation parameters indicated by the parameter configuration operation are compared and verified with the device parameters corresponding to the simulation model knowledge graph. If the verification passes, an industrial simulation deduction template is configured based on the verified simulation parameters to generate a simulation model. Conversely, if the verification fails, preset recommended parameters are used to replace the failed simulation parameters in the industrial simulation deduction template to generate a simulation model. This approach avoids simulation model failures and distortion of deduction results caused by invalid or erroneous parameters from the source through parameter verification, ensuring the scientific validity and effectiveness of the simulation model. Furthermore, it avoids interrupting the configuration process due to failed parameter verification by automatically completing the configuration using preset recommended parameters, thus improving the efficiency of simulation model generation.

[0056] It is worth mentioning that the preset recommended parameters can be determined through a simulation model knowledge graph constructed from historical configuration information. Specifically, entity relationships are extracted from the historical configuration information corresponding to the industrial simulation template to determine the historical equipment entity relationship information; a knowledge graph is constructed from the historical equipment entity relationship information to obtain the simulation model knowledge graph; and the preset recommended parameters for the digital twin nodes in the industrial simulation template are determined based on the simulation model knowledge graph.

[0057] The historical configuration information includes records of parameter configurations, equipment manuals, and simulation results for each digital twin model of the equipment included in the simulation model prior to the current time. Historical equipment entity relationship information can be represented as triples, showing the associations and attribute value constraints between equipment entities and their attributes. For example, the triple could be <pump equipment, motor efficiency, efficiency>. Preset recommended parameters can be equipment parameters and simulation parameters of the simulation model that are adapted to the aforementioned industrial system simulation scenario.

[0058] In this embodiment, entity relationships are extracted from the historical configuration information of the industrial simulation template, and a simulation model knowledge graph is constructed. The knowledge graph is used to structure and visualize the historical configuration relationships, ensuring that parameter recommendations better align with the actual interaction logic of the equipment and the patterns of effective historical configurations. This guarantees the scientific validity and adaptability of the recommended parameters and avoids parameter deviations caused by blind configuration.

[0059] As an example, NLP (Natural Language Processing) technology can be used for entity extraction to obtain equipment entity information. An association rule mining algorithm is then employed to extract the set of associations and constraints for equipment entity information from historical configuration information. Triples are constructed from the aforementioned equipment entity information, the set of associations, and the set of constraints to obtain historical equipment entity relationship information. Finally, a graph neural network model can be used to recommend configuration parameters for the parameter set included in the industrial simulation template based on the aforementioned simulation model knowledge graph, resulting in preset recommended parameters.

[0060] In practical application scenarios, step 103 generates dynamic strategy information to drive the simulation model based on the simulation scenario information. Specifically, this includes: obtaining general strategy information and historical operating information of the equipment corresponding to the simulation scenario information; adjusting the general strategy information according to the historical operating information of the equipment to generate dynamic strategy information.

[0061] The simulation models are situated within scenarios including power system fault handling and / or HVAC system energy consumption optimization. Dynamic strategy information includes operating parameters, commands, or events that drive the entire simulation model and simulate the system's behavior under specific conditions. Examples include timing commands and event response rules.

[0062] In this embodiment, dynamic strategy information is generated by adjusting the general strategy according to the scenario through the historical operation information of the equipment. This not only reuses the basic framework of the general strategy and avoids the cost of building the strategy from scratch, but also makes adaptation adjustments based on the historical operation data of the equipment that fits the actual scenario. This makes the dynamic strategy more in line with the actual operation rules and scenario characteristics of industrial equipment, avoids the inference deviation caused by the disconnect between the general strategy and the specific scenario, and improves the driving adaptability of the strategy to the simulation model.

[0063] In practical application scenarios, step 103 involves iteratively simulating and deducing the simulation model based on the dynamic strategy information to obtain the simulation results. Specifically, this includes: inputting the dynamic strategy information into the simulation model for simulation to obtain the device status feedback information of the digital twin nodes; if the device status feedback information of any digital twin node does not meet the preset optimization conditions, adjusting the control parameters in the dynamic strategy information based on the device status feedback information and resimulating; if the device status feedback information of all digital twin nodes meets the preset optimization conditions, using the device status feedback information as the simulation result.

[0064] The simulation results can be presented in graphical form, displaying the operational status information and system performance data of the twin nodes of each device included in the simulation model. These system performance data can be indicators of the overall operational status of the entire industrial system. For example, these system performance data could include system power consumption and load information.

[0065] In this embodiment, dynamic strategy information is input into the simulation model for deduction. Based on the device status feedback information from the digital twin nodes, it is determined whether the optimization conditions are met. If not, the strategy control parameters are adjusted and the simulation is repeated until all node feedback meets the criteria, at which point the deduction result is determined. This achieves a closed-loop iteration of parameter adjustment, allowing the dynamic strategy to continuously adapt to the actual operating state of the simulation model. This process avoids deviations in the results of single-strategy deductions, ensuring that the simulation results closely match the actual operating logic of the industrial system. Simultaneously, the closed-loop verification mechanism can accurately optimize the strategy control parameters, contributing to improved accuracy and reliability of the simulation.

[0066] Taking HVAC systems as an example, to ensure indoor temperature and airflow while maintaining low load energy consumption, thereby reducing resource consumption and meeting low-carbon requirements, a conventional solution typically involves using a gated loop unit model to predict HVAC system energy consumption based on historical equipment energy consumption datasets. Then, a heuristic optimization algorithm is employed to generate optimized HVAC system energy consumption information based on this prediction. However, this conventional solution still suffers from the following problems: because the gated loop unit model only performs time-series processing through two gates, its ability to extract long-term time-series dependencies is low, resulting in low accuracy of predicted energy consumption information. This affects the accuracy of the optimized HVAC system energy consumption information generated based on the predicted energy consumption information, leading to higher energy consumption and equipment wear in the HVAC system. Therefore, this application proposes the following method steps in its embodiments: The first step is to determine that the simulation model obtained by configuration is the simulation model of an industrial HVAC system, that is, the current scenario is the HVAC system energy consumption optimization scenario, and then obtain the historical equipment energy consumption data (equipment historical operation information) of the industrial HVAC system.

[0067] Understandably, after obtaining historical equipment energy consumption data, preprocessing can be performed on this data to obtain preprocessed historical equipment energy consumption data. Preprocessing can smooth the data, improve its fluency, reduce useless data, lower data dimensionality, and reduce the overall size of the historical equipment energy consumption dataset.

[0068] Specifically, historical equipment energy consumption data can be information on resource consumption and operational efficiency indicators of industrial equipment operating before the current time. Preprocessing can include dimensionless processing, outlier removal, and correlation analysis. Dimensionless processing can be performed by subtracting the mean from the historical equipment energy consumption data and then dividing it by the ratio of the difference to the standard deviation. At this point, the dimensionless historical equipment energy consumption data will have values ​​between [0, 1] and conform to a Gaussian distribution. Then, the LOF (Local Outlier Factor) algorithm is used to optimize the dimensionless historical equipment energy consumption data by removing outliers, resulting in the removed historical equipment energy consumption data. In the LOF algorithm, outliers are identified when the absolute value of the historical equipment energy consumption data and the mean is greater than or equal to three times the standard deviation. Finally, the Pearson correlation coefficient algorithm is used to perform feature correlation analysis on the removed historical equipment energy consumption data, obtaining a group of energy consumption feature information with a linear relationship. Finally, any energy consumption feature is selected from each energy consumption feature information group that has a linear relationship to obtain the energy consumption feature information, which is used as the preprocessed historical equipment energy consumption data.

[0069] The second step is to adjust the general strategy information according to historical equipment energy consumption data to obtain HVAC system energy consumption optimization information (dynamic strategy information), such as optimization schemes for industrial systems to reduce energy consumption and improve operating efficiency of industrial equipment.

[0070] The particle swarm optimization algorithm can be used to adjust the general strategy information based on the historical equipment energy consumption data. Specifically, the historical equipment energy consumption data is input into a trained heuristic energy consumption prediction model to obtain the predicted energy consumption value of the HVAC system. An energy consumption scheduling model for the HVAC system is then generated. This HVAC system energy consumption scheduling model can include a scheduling model that includes an energy consumption minimization objective function, an indoor temperature constraint function, an equipment power constraint function, and an HVAC system start-stop frequency constraint function. Based on the predicted energy consumption value of the HVAC system, dynamic programming is performed on the energy consumption scheduling model to obtain HVAC system energy consumption optimization information. This dynamic programming solution can be a combination of one or more heuristic algorithms. The HVAC system energy consumption optimization information can be regional and time-period-specific optimization information for the HVAC system.

[0071] It should be noted that the heuristic energy consumption prediction model is obtained through the following steps: Sub-step 2-1 involves performing theoretical numerical model encoding optimization on the initial optimization population of the above-mentioned heuristic energy consumption prediction model to obtain the encoded initial optimization population. The initial optimization individuals in the above-mentioned initial optimization population can be a set of initial values ​​for model parameters of the heuristic energy consumption prediction model. Each model parameter corresponding to the above-mentioned set of initial values ​​can have a range of values. The above-mentioned set of initial values ​​can include, but is not limited to, at least one of the following: initial learning rate, initial number of neurons, and initial number of iterations. The above-mentioned heuristic energy consumption prediction model can be a deep neural network model used to predict the energy consumption information of a HVAC system at a future time. In practice, the execution entity can, for each initial optimization individual in the initial optimization population, first determine the sum of the product of the difference in the value range of the initial optimization individual, the decimal number of the randomly generated binary gene sequence of the initial optimization individual, the maximum decimal number corresponding to the length of the binary gene sequence, and the minimum value in the value range, as the encoded initial optimization individual.

[0072] Sub-step 2-2 involves inputting the aforementioned model training data into the spatial channel fusion attention mechanism layer of the heuristic energy consumption prediction model corresponding to the initial optimized population after encoding, to obtain the energy consumption attention feature vector. This spatial channel fusion attention mechanism layer can be an attention mechanism layer that fuses spatial and channel features of the input model training data. In practice, the execution entity can first input the aforementioned model training data into a convolutional layer, a batch normalization layer, and an activation function layer to obtain a training feature vector. The activation function can be a ReLU (Linear Rectification) function. Next, the training feature vector is evenly divided to obtain a first evenly divided training feature vector and a second evenly divided training feature vector. Then, the first evenly divided training feature vector is input into a global average pooling layer and a fully connected layer for linear transformation to obtain a spatial attention feature vector. Subsequently, the second evenly divided training feature vector is input into an SE (Squeeze-and-Excitation Networks) attention layer in parallel to obtain a channel attention feature vector. Next, the spatial attention feature vector and channel attention feature vector are concatenated, and then multiplied with the training feature vector to obtain the spatial-channel concatenated feature vector. Then, the training feature vector is fed into a global max pooling layer and a global average pooling layer respectively, concatenated, and then fed into a convolutional layer and a ReLU activation function layer to obtain the pooled concatenated feature vector. Finally, the pooled concatenated feature vector and the spatial-channel concatenated feature vector are multiplied and concatenated to obtain the energy consumption attention feature vector.

[0073] Sub-steps 2-3 involve inputting the aforementioned energy consumption attention feature vector into the energy consumption prediction network included in the heuristic energy consumption prediction model to obtain the heuristic predicted energy consumption value. This energy consumption prediction network can be a neural network model that performs temporal prediction on the input energy consumption attention feature vector. Alternatively, it can be a long short-term memory neural network model that inputs the energy consumption attention feature vector into a forgetting gate composed of a sigmoid activation function and a dot product to obtain an implicit feature vector. Then, based on the posterior probability maximization estimation algorithm, the implicit feature vector is solved using a long short-term memory neural network model.

[0074] Sub-steps 2-4 involve performing a global update process of selection, crossover, and mutation on the initial optimized population after encoding, resulting in an updated optimized population. This global update process can be performed using a genetic algorithm.

[0075] Sub-steps 2-5 involve performing global-local hybrid optimization on the initial heuristic energy consumption prediction model based on the updated optimized population and the initial optimized population, resulting in a trained heuristic energy consumption prediction model. As an example, the execution entity can terminate the global optimization of the heuristic energy consumption prediction model in response to determining that the difference between the fitness functions that minimize energy consumption corresponding to the updated optimized population and the initial optimized population is less than a preset fitness difference, thus obtaining a globally optimized energy consumption model. Then, using the particle swarm optimization algorithm, the local weight parameters of the globally optimized energy consumption model are optimized to obtain a trained heuristic energy consumption prediction model.

[0076] In the optimization training, theoretical mathematical model encoding optimization can improve gene inheritance efficiency. Global optimization using crossover mutation global update processing can improve the survival rate of dominant genes in the initial optimized population after encoding, thereby improving the survival ability of the optimized population and the convergence speed of the optimal solution in the search space, and obtaining more accurate initial values ​​of model parameters. Local weight parameter optimization through particle swarm optimization algorithm can further improve the accuracy of heuristic energy consumption prediction model. Furthermore, the spatial channel fusion attention mechanism layer extracts features from both spatial and channel perspectives, which can improve feature focusing performance, thereby improving model accuracy while reducing computational cost.

[0077] The third step involves performing the following first input step based on the HVAC system energy consumption optimization information: Sub-step 3-1 involves inputting the HVAC system energy consumption optimization information into the simulation model to obtain the equipment energy consumption status information group (equipment status feedback information) for each digital twin node of the aforementioned equipment. The equipment energy consumption information in this group can be the resource consumption information and operating efficiency information of the digital twin node under the aforementioned HVAC system energy consumption optimization information.

[0078] Sub-step 3-2: In response to the determination that there is equipment energy consumption status information in the equipment energy consumption status information group that does not meet the preset equipment energy consumption conditions (preset optimization conditions), the model parameters included in the HVAC system energy consumption optimization information are dynamically adjusted according to the equipment energy consumption status information group to obtain the adjusted HVAC system energy consumption optimization information. The aforementioned preset equipment energy consumption conditions can be the pre-set conditions where the energy consumption of the equipment digital twin node is less than or equal to a preset energy consumption threshold. The aforementioned dynamic adjustment can be an adjustment of the equipment parameters in the aforementioned HVAC system energy consumption optimization information. The aforementioned equipment parameters can include, but are not limited to, at least one of the following: water pump motor efficiency, chiller condensing pressure, cooling tower fan frequency, equipment distance information, and air system valve opening.

[0079] As an example, the system can determine the energy consumption gap information group between the aforementioned equipment energy consumption status information and the equipment energy consumption status information corresponding to the aforementioned preset equipment energy consumption conditions. Then, it determines the equipment parameter information set corresponding to the aforementioned energy consumption gap information group. Finally, through reinforcement learning, it dynamically adjusts the aforementioned equipment parameter information set to obtain the adjusted HVAC system energy consumption optimization information.

[0080] Sub-step 3-3 involves inputting the adjusted HVAC system energy consumption optimization information back into the simulation model to obtain the target equipment energy consumption status information group. The target equipment energy consumption status information in this group can be the operating status information of the digital twin node under the adjusted HVAC system energy consumption optimization information.

[0081] The fourth step is to filter the obtained target device energy consumption status information set to obtain a filtered target device energy consumption status information set. Specifically, the filtering process can involve selecting the target device energy consumption status information set with the lowest energy consumption from the aforementioned target device energy consumption status information sets.

[0082] The fifth step is to identify the energy consumption status information group of the target equipment after the above screening as the simulation result information.

[0083] Similarly, taking a power system as an example, the embodiments of this application propose the following method steps: The first step, once it is determined that the simulation model obtained is a simulation model of an industrial power system, and the industrial power system meets the conditions for power equipment failure, is to obtain a historical equipment failure dataset (historical equipment operation information) of the industrial power system. The historical equipment failure data in this dataset can be information about the operating status of various devices in the industrial power system at the time of the failure, prior to the current time.

[0084] Historical equipment failure data can be preprocessed, and the specific steps are the same as those in the HVAC system implementation example, so they will not be repeated here.

[0085] The second step involves adjusting the general strategy information based on historical equipment failure data to obtain power system failure optimization information (dynamic strategy information). This optimization information can identify the root cause of a system failure and modify the parameters of the corresponding digital twin model of the equipment to optimize the failure message. For example, a root cause analysis algorithm can be used to adjust the general strategy information based on the aforementioned historical equipment failure data to obtain the power system failure optimization information.

[0086] The third step, based on the power system fault optimization information, is to perform the following second input step: Sub-step 1 involves inputting power system fault optimization information into the simulation model to obtain the equipment operation status information group (equipment status feedback information) for each of the aforementioned digital twin nodes. The equipment operation status information in this group characterizes whether the digital twin model of the equipment is operating normally, and provides information on its status and performance during normal operation.

[0087] Sub-step 2: In response to determining that there is equipment operating status information in the aforementioned equipment operating status information group that does not meet preset operating conditions (preset optimization conditions), the model parameters included in the aforementioned power system fault optimization information are dynamically adjusted according to the equipment operating status information group to obtain adjusted power system fault optimization information. The aforementioned preset operating conditions can be the pre-set conditions under which no equipment fault has occurred. The aforementioned dynamic adjustment can be an adjustment of the equipment parameters in the aforementioned power system fault optimization information. The aforementioned equipment parameters can include, but are not limited to, at least one of the following: contact resistance of the distribution equipment, tripping time, operating cycle of the energy storage motor, load rate of the distribution transformer, and top oil temperature rise.

[0088] As an example, the system can determine the energy consumption gap information group between the aforementioned equipment operating status information group and the equipment operating status information group corresponding to the aforementioned preset operating conditions. Then, it determines the equipment operating parameter information corresponding to the aforementioned energy consumption gap information group. Finally, through reinforcement learning, it dynamically adjusts the aforementioned equipment operating parameter information to obtain adjusted power system fault optimization information.

[0089] Sub-step 3 involves inputting the aforementioned power system fault optimization information back into the simulation model to obtain the target equipment operating status information group. The target equipment operating status information in this group can be the operating status information of the equipment's digital twin model under the aforementioned power system fault optimization information conditions.

[0090] The fourth step is to filter the obtained target equipment operating status information group to obtain a filtered equipment operating status information group. This filtering process can involve selecting the target equipment energy consumption status information group from the target equipment operating status information group to address power system faults.

[0091] The fifth step is to identify the target equipment operating status information group after the above screening as the simulation result information.

[0092] In one embodiment, when the simulation results meet preset conditions, the industrial equipment can be dynamically adjusted directly based on the simulation parameters and equipment operating parameters configured in the simulation model. This improves the operating efficiency of the industrial equipment and reduces industrial losses. The equipment operating parameters may include, but are not limited to, at least one of the following: equipment rotational speed, equipment output power, and equipment operating time.

[0093] Optionally, an industrial simulation template that meets preset conditions can be saved to a target database, which can be a database that can only be accessed by the user.

[0094] In one embodiment, step 103, publishing the industrial simulation template, specifically includes: in response to detecting a template publishing request operation, reviewing the industrial simulation templates that meet the preset simulation conditions, and obtaining template review result information. In response to the confirmation that the template review result information indicates that the review has passed, publishing the industrial simulation templates that meet the preset simulation conditions to the preset simulation template resource center for use by other users.

[0095] The industrial system simulation and deduction method provided in this application can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0096] Furthermore, the executing entity of the aforementioned industrial system simulation and deduction method (e.g., electronic equipment) can acquire industrial system simulation and deduction scenario information through wired or wireless connections. This industrial system simulation and deduction scenario information can be information required for actual industrial scenario operation. This information can include: equipment information, industrial system operating environment constraint information, and industrial system operating performance requirement information. The equipment information can include physical information of the equipment, operating status information during equipment operation, and connection topology information between various devices. This equipment information can include: equipment type information, equipment quantity, equipment model information, and equipment physical location information. The industrial system operating environment constraint information can be information on environmental requirements during industrial system operation. This information can include, but is not limited to, at least one of the following: maximum temperature and humidity information, equipment rated power information, and computer room wind speed information. The industrial system operating performance requirement information can include, but is not limited to, at least one of the following: industrial system energy consumption information, industrial system fault early warning rule information, and equipment utilization rate information.

[0097] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0098] Furthermore, such as Figure 2 As shown, as a specific implementation of the above-mentioned industrial system simulation and deduction method, this application embodiment provides an industrial system simulation and deduction device 200, which includes: an acquisition unit 201, a template determination unit 202, and a simulation and deduction unit 203.

[0099] Among them, the acquisition unit 201 is used to acquire simulation scenario information of the industrial system; Template determination unit 202 is used to determine an industrial simulation simulation template that matches the simulation scenario information. The industrial simulation simulation template defines each digital twin node and its topology layout in the industrial system. The simulation simulation unit 203 is used to perform simulation simulation verification operations according to the industrial simulation simulation template, wherein the simulation simulation verification operations include: Configure simulation parameters on the industrial simulation template to obtain the simulation model; Generate dynamic strategy information to drive the simulation model; The simulation model is iteratively simulated and deduced based on dynamic strategy information to obtain simulation results. When the simulation results meet the preset conditions, save and publish the industrial simulation template; In response to the simulation results not meeting the preset conditions, the digital twin nodes and topology layout in the industrial simulation template are adjusted, and the simulation verification operation is re-executed.

[0100] Furthermore, the template determination unit 202 specifically includes: The matching unit (not shown in the figure) is used to retrieve the initial simulation template from the preset template library based on the simulation scenario information; The template optimization unit (not shown in the figure) is used to parse the simulation scenario information, obtain the scenario constraint information, scenario topology layout and scenario device set; perform functional module division and network discretization processing on the scenario topology layout according to the scenario constraint information to generate a layout optimization model; solve the layout optimization model to obtain the optimized layout information; and perform collision detection on the optimized layout information, and adjust the topology layout and digital twin nodes of the preset simulation template according to the collision detection results and the scenario device set to generate an industrial simulation simulation template.

[0101] Furthermore, the template determining unit 202 also includes: A creation unit (not shown in the figure) is used to determine the equipment interaction logic and digital twin model set of each industrial equipment based on the historical information of the industrial equipment corresponding to the simulation scenario information if the initial simulation template is not found in the preset template library; and to construct a three-dimensional topology map of the digital twin model set based on the equipment interaction logic, and use the constructed three-dimensional topology map of the industrial equipment as the initial simulation template.

[0102] Furthermore, the matching unit is specifically used to extract graph features from the preset inference templates stored in the preset template library to obtain the corresponding graph feature vectors; extract text features from the simulation inference scene information to obtain the corresponding text feature vectors; and select initial inference templates from the preset inference templates based on the similarity between the text feature vectors and the graph feature vectors.

[0103] Furthermore, the simulation and deduction unit 203 is specifically used to input dynamic strategy information into the simulation model for simulation to obtain the device status feedback information of the digital twin node; if the device status feedback information of any digital twin node does not meet the preset optimization conditions, the control parameters in the dynamic strategy information are adjusted according to the device status feedback information and the simulation is performed again; if the device status feedback information of all digital twin nodes meets the preset optimization conditions, the device status feedback information is used as the simulation and deduction result.

[0104] Furthermore, the simulation simulation unit 203 is specifically used to acquire the historical operating information of the equipment corresponding to the general strategy information and the simulation simulation scenario information; to adjust the general strategy information according to the historical operating information of the equipment and generate dynamic strategy information; wherein, the scenario to which the simulation model belongs includes the power system fault handling scenario and / or the HVAC system energy consumption optimization scenario.

[0105] Furthermore, the industrial system simulation and deduction device 200 also includes: The parameter recommendation unit (not shown in the figure) is used to extract entity relationships from the historical configuration information corresponding to the industrial simulation template, determine the historical equipment entity relationship information, construct a knowledge graph from the historical equipment entity relationship information to obtain the simulation model knowledge graph, and determine the preset recommended parameters of the digital twin nodes in the industrial simulation template based on the simulation model knowledge graph. The simulation deduction unit 203 is specifically used to respond to the parameter configuration operation of the industrial simulation deduction template, and to verify the simulation parameters indicated by the parameter configuration operation. If the verification passes, the industrial simulation deduction template is configured according to the simulation parameters to generate a simulation model. If the verification fails, the industrial simulation deduction template is configured with preset recommended parameters instead of the simulation parameters that failed the verification to generate a simulation model.

[0106] Specific limitations regarding the industrial system simulation and deduction device can be found in the limitations of the industrial system simulation and deduction method described above, and will not be repeated here. Each module in the aforementioned industrial system simulation and deduction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the electronic device, or stored in the memory of the electronic device as software, so that the processor can call and execute the operations corresponding to each module.

[0107] Based on the above, Figure 1 The method shown, and Figure 2 The virtual device embodiment shown is designed to achieve the above objectives, such as... Figure 3 As shown Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0108] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0109] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0110] In particular, according to some embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this application include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this application.

[0111] It should be noted that, in some embodiments of this application, the computer-readable storage medium described above can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. Computer-readable storage media are not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In some embodiments of this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this application, the computer-readable signal medium may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0112] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0113] The aforementioned computer-readable storage medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the following steps: acquiring simulation scenario information of an industrial system; determining an industrial simulation template matching the simulation scenario information, wherein the industrial simulation template defines each digital twin node and its topology layout in the industrial system; performing simulation verification operations according to the industrial simulation template, wherein the simulation verification operations include: configuring simulation parameters for the industrial simulation template to obtain a simulation model; generating dynamic strategy information for driving the simulation model based on the simulation scenario information; iteratively simulating the simulation model based on the dynamic strategy information to obtain simulation results; saving and publishing the industrial simulation template in response to the simulation results meeting preset conditions; and adjusting the digital twin nodes and topology layout in the industrial simulation template and re-executing the simulation verification operations in response to the simulation results not meeting preset conditions.

[0114] Computer program code for performing operations of some embodiments of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0115] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0116] The units described in some embodiments of this application can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an acquisition unit, a determination unit, a template adjustment unit, an execution unit, and a device digital twin node update unit. The names of these units do not necessarily limit the specific unit; for example, the acquisition unit may also be described as a "unit for acquiring information about industrial system simulation scenarios."

[0117] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0118] The above description is merely a selection of preferred embodiments of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this application.

Claims

1. A method for simulating and extrapolating industrial systems, characterized in that, The method includes: Acquire simulation scenario information for industrial systems; The initial simulation template is retrieved from the preset template library based on the simulation scenario information; Analyze the simulation scenario information to obtain scenario constraint information, scenario topology layout, and scenario device set; Based on the scenario constraint information, the scenario topology layout is divided into functional modules and the network is discretized to generate a layout optimization model. Solve the layout optimization model to obtain the optimized layout information; Collision detection is performed on the optimized layout information, and the topology layout and digital twin nodes of the initial simulation template are adjusted according to the collision detection results and the scene device set to generate an industrial simulation template that matches the simulation scene information. Perform simulation verification operations according to the industrial simulation template, wherein the simulation verification operations include: The simulation parameters of the industrial simulation template are configured to obtain the simulation model; Dynamic strategy information for driving the simulation model is generated based on the simulation scenario information; The simulation model is iteratively simulated and deduced based on the dynamic strategy information to obtain the simulation results. In response to the simulation results meeting preset conditions, the industrial simulation template is saved and published; In response to the simulation results not meeting the preset conditions, the digital twin nodes and topology layout in the industrial simulation template are adjusted, and the simulation verification operation is re-executed.

2. The industrial system simulation and deduction method according to claim 1, characterized in that, The method further includes: If the initial simulation template is not found in the preset template library, the equipment interaction logic and digital twin model set of each industrial equipment are determined based on the historical information of the industrial equipment corresponding to the simulation scenario information. Based on the device interaction logic, a three-dimensional topology map is constructed for the digital twin model set, and the constructed three-dimensional topology map of the industrial equipment is used as the initial deduction template.

3. The industrial system simulation and deduction method according to claim 1, characterized in that, The step of retrieving an initial simulation template from a preset template library based on the simulation scenario information includes: Graph features are extracted from the preset inference templates stored in the preset template library to obtain the corresponding graph feature vectors; Text feature extraction is performed on the simulation scenario information to obtain the corresponding text feature vector; The initial inference template is selected from the preset inference templates based on the similarity between the text feature vector and the graph feature vector.

4. The industrial system simulation and deduction method according to claim 1, characterized in that, The step of iteratively simulating and deducing the simulation model based on the dynamic strategy information to obtain the simulation results includes: The dynamic strategy information is input into the simulation model for simulation to obtain the device status feedback information of the digital twin node; If the device status feedback information of any digital twin node does not meet the preset optimization conditions, adjust the control parameters in the dynamic strategy information according to the device status feedback information and re-perform the simulation. If the device status feedback information of all digital twin nodes meets the preset optimization conditions, the device status feedback information is used as the simulation result.

5. The industrial system simulation and deduction method according to claim 1, characterized in that, The step of generating dynamic strategy information for driving the simulation model based on the simulation scenario information includes: Obtain general strategy information and historical device operation information corresponding to the simulation scenario information; The general strategy information is adjusted according to the historical operating information of the device to generate the dynamic strategy information; The simulation model is applicable to scenarios including power system fault handling and / or HVAC system energy consumption optimization.

6. The industrial system simulation and deduction method according to claim 1, characterized in that, The method further includes: Entity relationships are extracted from the historical configuration information corresponding to the industrial simulation template to determine the historical equipment entity relationship information; A knowledge graph is constructed from the historical device entity relationship information to obtain the simulation model knowledge graph; Based on the knowledge graph of the simulation model, the preset recommended parameters of the digital twin nodes in the industrial simulation inference template are determined; The process of configuring simulation parameters for the industrial simulation template to obtain a simulation model includes: In response to the parameter configuration operation of the industrial simulation template, the simulation parameters indicated by the parameter configuration operation are verified; If the verification passes, the industrial simulation template is configured according to the simulation parameters to generate the simulation model; If the verification fails, the industrial simulation template is configured with the preset recommended parameters instead of the simulation parameters that failed the verification, and the simulation model is generated.

7. An industrial system simulation and deduction device, characterized in that, The device includes: The acquisition unit is used to acquire simulation scenario information of the industrial system. The template determination unit is used to retrieve an initial simulation template from a preset template library based on the simulation scenario information; parse the simulation scenario information to obtain scenario constraint information, scenario topology layout, and scenario device set; perform functional module division and network discretization processing on the scenario topology layout based on the scenario constraint information to generate a layout optimization model; solve the layout optimization model to obtain optimized layout information; perform collision detection on the optimized layout information, and adjust the topology layout and digital twin nodes of the initial simulation template based on the collision detection results and the scenario device set to generate an industrial simulation template that matches the simulation scenario information. The simulation simulation unit is used to perform simulation simulation verification operations based on the industrial simulation simulation template, wherein the simulation simulation verification operations include: The simulation parameters of the industrial simulation template are configured to obtain the simulation model; Generate dynamic strategy information to drive the simulation model; The simulation model is iteratively simulated and deduced based on the dynamic strategy information to obtain the simulation results. In response to the simulation results meeting preset conditions, the industrial simulation template is saved and published; In response to the simulation results not meeting the preset conditions, the digital twin nodes and topology layout in the industrial simulation template are adjusted, and the simulation verification operation is re-executed.

8. A computer-readable storage medium having a program or instructions stored thereon, characterized in that, When the program or instructions are executed by the processor, they implement the industrial system simulation and deduction method as described in any one of claims 1 to 6.

9. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the industrial system simulation and deduction method as described in any one of claims 1 to 6.

Images