Power Plant Real-time Dynamic Control and Operation Management System Based on Big Data Twin

Abstract

The present invention provides a power plant real-time dynamic control and operation management system based on big data twin, belonging to the technical field of data processing, including: a construction module: obtaining the spatial structure data and full-condition full-physical process data of the power plant, and constructing a big data twin three-dimensional simulation model; an analysis module: obtaining the historical operation data and historical environment data of the power plant, and determining the expected operation strategy matrix of the power plant; an operation module: real-time collecting the real-time operation data and real-time environment data of the power plant, and determining the real-time operation vector of the power plant; a control module: determining the real-time dynamic control strategy of the power plant; a management module: generating a synchronous operator operation guidance dynamic report and an index optimization report. It can realize the global monitoring and intelligent management of the power plant operation, accurately and timely adjust the control strategy, optimize the small-index operation efficiency of the power plant under different working conditions, improve the energy utilization rate, reduce the equipment failure risk, and ensure the flexibility and adaptability of system regulation.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a power plant real-time dynamic control and operation management system based on big data twin. Background Art

[0002] The operation management system of power plants has experienced technological progress in multiple stages. In the early days, the management of power plants relied on manual monitoring and basic automation systems, which could not effectively cope with complex environmental changes and equipment failures. In the 1990s, with the development of computer technology, advanced process control systems (DCS) and real-time monitoring systems were introduced into power plants. The operation status of power plants was monitored through automated devices. However, these systems still mainly relied on single sensor data and manual adjustment, and could not achieve adaptive optimization for changing environmental conditions.

[0003] With the rise of big data, cloud computing and artificial intelligence technologies, power plants have started to adopt more intelligent management solutions. Based on a large amount of historical data and real-time data, machine learning and optimization algorithms have been introduced into the power plant management system to achieve intelligent prediction and dynamic adjustment of power plant operation. In addition, the integration technology of simulation models and operation data of power plants has gradually matured, making it possible to achieve global monitoring and intelligent control of power plant operation.

[0004] Therefore, the present invention provides a power plant real-time dynamic control and operation management system based on big data twin. Summary of the Invention

[0005] The present invention provides a power plant real-time dynamic control and operation management system based on big data twin. By constructing a big data twin three-dimensional simulation model, determining the expected matrix of the operation strategy of the power plant, determining the real-time operation vector of the power plant according to the real-time operation data, real-time environmental data and the big data twin three-dimensional simulation model, determining the real-time dynamic control strategy of the power plant according to the real-time environmental data, real-time operation vector and expected operation matrix, realizing the operation management of the power plant, and generating a synchronous operator operation guidance dynamic report and an index optimization report, it can achieve global monitoring and intelligent management of power plant operation, accurately and timely adjust the control strategy, optimize the operation efficiency of small indicators of the power plant under different working conditions, improve energy utilization rate, reduce the risk of equipment failure, and ensure the flexibility and adaptability of system regulation.

[0006] The present invention provides a power plant real-time dynamic control and operation management system based on big data twin, including:

[0007] A construction module: obtaining the spatial and system structure data of the power plant, obtaining the full-condition and full-physical process data of the power plant, and constructing a big data twin three-dimensional simulation model;

[0008] Analysis module: Obtain the historical operation data and historical environmental data of the power plant, and determine the expected operation strategy matrix of the power plant based on the historical operation data, historical environmental data, and the big data twin three-dimensional simulation model;

[0009] Operation module: Real-time collect the real-time operation data and real-time environmental data of the power plant, and determine the real-time operation vector of the power plant based on the real-time operation data, real-time environmental data, and the big data twin three-dimensional simulation model;

[0010] Control module: Determine the real-time dynamic control strategy of the power plant based on the real-time environmental data, real-time operation vector, and expected operation matrix of the power plant;

[0011] Management module: Implement the operation management of the power plant based on the real-time dynamic control strategy of the power plant, and generate a synchronous operator operation guidance dynamic report and an index optimization report.

[0012] According to the power plant real-time dynamic control and operation management system based on big data twin provided by the present invention, the construction module includes:

[0013] Spatial structure unit: Obtain the spatial structure data of the power plant based on the scanning device, wherein the spatial structure data includes the three-dimensional layout data of the power plant and equipment data, and the equipment data includes equipment identification and equipment coordinates;

[0014] Power plant three-dimensional model construction unit: Preprocess the spatial structure data, and construct a power plant three-dimensional model based on the three-dimensional layout data in the preprocessed spatial structure data;

[0015] Full-condition full-physical process unit: The full-condition full-physical process data includes physical process sub-data under multiple operating conditions, wherein the physical process sub-data includes equipment sub-data of multiple devices;

[0016] Big data twin process model construction unit: Preprocess the full-condition full-physical process data, and construct multiple big data twin process models based on the preprocessed full-condition full-physical process data;

[0017] Big data twin three-dimensional simulation model construction unit: Construct a big data twin three-dimensional simulation model of the power plant based on the power plant three-dimensional model and all big data twin process models.

[0018] According to the power plant real-time dynamic control and operation management system based on big data twin provided by the present invention, the analysis module includes:

[0019] First acquisition unit: Obtain historical operation sub-data within multiple specified time periods, and determine historical operation data based on the historical operation sub-data within all specified time periods and all historical operation sub-data period labels;

[0020] Second acquisition unit: Acquire historical environmental data within multiple specified time periods, and determine the historical environmental data based on the historical environmental sub-data and all historical environmental sub-data cycle tags within all specified time periods.

[0021] According to the power plant real-time dynamic control and operation management system based on big data twins provided by the present invention, the analysis module further includes:

[0022] Historical environmental vector unit: Preprocess the historical environmental data, extract features from the historical environmental sub-data of each cycle tag after preprocessing, and determine the historical environmental vector of each cycle tag;

[0023] Historical operation vector unit: Preprocess the historical operation data, determine the historical environmental vector of each historical operation sub-data in the historical operation data based on the cycle tag, input all historical operation sub-data and the corresponding historical environmental vectors in the preprocessed historical operation data into the big data twin three-dimensional simulation model, and determine the historical operation vector of each historical operation sub-data under the corresponding historical environmental vector based on the output result of the big data twin three-dimensional simulation model;

[0024] Initial cluster center unit: Analyze the differences of the historical environmental vectors of all cycle tags to determine the number of clusters a, randomly select the historical environmental vectors of a cycle tags as the initial cluster centers, and perform initial marking on the a historical environmental vectors;

[0025] First updated cluster center unit: Randomly select any historical environmental vector without initial marking, determine the similarity between the selected historical environmental vector and all initial cluster centers, assign the selected historical environmental vector to the cluster family of the initial cluster center with the greatest similarity, determine the updated cluster center based on the selected historical environmental vector and the historical environmental vector corresponding to the initial cluster center with the greatest similarity, and perform assignment marking on the selected historical environmental vector;

[0026] Second updated cluster center unit: Randomly select any historical environmental vector without initial marking or without assignment marking, determine the similarity between the selected historical environmental vector and the updated cluster centers of all clusters, assign the selected historical environmental vector to the cluster family of the updated cluster center with the greatest similarity, determine the updated cluster center based on the selected historical environmental vector and all historical environmental vectors in the cluster family of the updated cluster center with the greatest similarity, and perform assignment marking on the selected historical environmental vector;

[0027] Fitted environmental vector unit: When all historical environmental vectors have initial marking or assignment marking, determine each cluster family as an environmental category, and determine the fitted environmental vector of the corresponding environmental category based on all historical environmental vectors of each cluster family;

[0028] Cluster operation data unit: Extract the historical operation vectors corresponding to the periodic tags of all historical environment vectors of each cluster family from the historical operation data, and determine the cluster operation data of each cluster family;

[0029] First expected operation vector unit: Determine the expected operation vector of each cluster family based on all the historical operation vectors in the cluster operation data of each cluster family;

[0030] Operation strategy expected matrix unit: Determine the operation strategy expected matrix based on the fitted environment vectors of all cluster families and the expected operation vectors of all cluster families.

[0031] According to the power plant real-time dynamic control and operation management system based on big data twin provided by the present invention, the operation strategy expected matrix unit includes:

[0032] ;

[0033] Where M represents the operation strategy expected matrix, respectively represent the first fitted environment feature, the jth fitted environment feature, and the N2th fitted environment feature of the first cluster family, respectively represent the first fitted environment feature, the jth fitted environment feature, and the N2th fitted environment feature of the ith cluster family, respectively represent the first fitted environment feature, the jth fitted environment feature, and the N2th fitted environment feature of the N1th cluster family, respectively represent the first expected operation feature, the jth expected operation feature, and the N3th expected operation feature of the first cluster family, respectively represent the first expected operation feature, the jth expected operation feature, and the N3th expected operation feature of the first cluster family, respectively represent the first expected operation feature, the jth expected operation feature, and the N3th expected operation feature of the N1th cluster family, N1 represents the number of cluster families, N2 represents the number of fitted environment features in the fitted environment vector, and N3 represents the number of expected operation features in the expected operation vector.

[0034] According to the power plant real-time dynamic control and operation management system based on big data twin provided by the present invention, the operation module includes:

[0035] Real-time environment vector unit: Preprocess the real-time operation data and real-time environment data collected in real time, extract features from the preprocessed real-time environment data, and determine the real-time environment vector;

[0036] Real-time category unit: Determine the similarity between the real-time environment vector and the fitted environment vectors of each cluster family, and select the environmental category of the cluster family with the largest similarity of the fitted environment vector as the real-time category of the real-time environment data;

[0037] Real-time operation vector unit: Input the preprocessed real-time operation data, real-time environment data, and the real-time category of the real-time environment data into the big data twin three-dimensional simulation model, and determine the real-time operation vector of the power plant based on the output result of the big data twin three-dimensional simulation model.

[0038] According to the power plant real-time dynamic control and operation management system based on big data twin provided by the present invention, the control module includes:

[0039] Second expected operation vector unit: Determine the expected operation vector of the cluster corresponding to the real-time category of the real-time environment data based on the cluster corresponding to the real-time category of the real-time environment data and the operation strategy expectation matrix.

[0040] Real-time dynamic control strategy unit: Determine the real-time dynamic control strategy based on the similarity between the real-time environment vector of the power plant, the real-time operation vector, the expected operation vector of the cluster corresponding to the real-time category of the real-time environment data, and the fitting environment vector of the real-time environment data and the cluster corresponding to the real-time category of the real-time environment data.

[0041] Wherein, represents the real-time dynamic control strategy, represents the set control strategy, represents the actual adjustment control strategy, represents the maximum adjustable control strategy of the cluster of the fitting environment vector with the greatest similarity to the real-time environment vector, represents the time decay factor, represents the time dependence factor, ts represents the lower limit of the real-time acquisition time point, tp represents the current time point, represents the real-time environment vector, represents the fitting environment vector of the i-th cluster, represents the cluster of the fitting environment vector with the greatest similarity to the real-time environment vector, represents the fitting environment vector of the cluster of the fitting environment vector with the greatest similarity to the real-time environment vector, represents the real-time operation vector, represents the expected operation vector of the cluster of the fitting environment vector with the greatest similarity to the real-time environment vector, represents the expected adjustment parameter, represents the difference value between the real-time operation vector and the expected operation vector of the cluster of the fitting environment vector with the greatest similarity to the real-time environment vector, represents the similarity value between the real-time environment vector and the fitting environment vector of the cluster of the fitting environment vector with the greatest similarity to the real-time environment vector, represents the second fitting adjustment parameter, represents the first fitting adjustment parameter, represents the total number of historical environment vectors in all clusters, represents the number of historical environment vectors in the cluster of the fitting environment vector with the greatest similarity to the real-time environment vector, represents the influence value of the cluster of the fitting environment vector with the greatest similarity to the real-time environment vector on the real-time dynamic control strategy, represents the environmental similarity factor, represents the difference factor, represents the exponential adjustment factor.

[0042] According to the power plant real-time dynamic control and operation management system based on big data twin provided by the present invention, the management module includes:

[0043] Execution unit: Send the real-time dynamic control strategy to the control center of the power plant, the control center executes the real-time dynamic control strategy, and determines the execution result;

[0044] Report unit: Generate a synchronous operator operation guidance dynamic report and an index optimization report based on real-time operation data, real-time environment data, real-time dynamic control strategy, and execution result.

[0045] Compared with the prior art, the beneficial effects of the present application are as follows:

[0046] By constructing a big data twin three-dimensional simulation model, determining the operation strategy expectation matrix of the power plant, determining the real-time operation vector of the power plant according to real-time operation data, real-time environment data, and the big data twin three-dimensional simulation model, and determining the real-time dynamic control strategy of the power plant according to real-time environment data, real-time operation vector, and expected operation matrix, realizing the efficient operation management of the power plant, and generating a synchronous guidance and optimization report, it is possible to achieve global monitoring and intelligent management of power plant operation, accurately and timely adjust the control strategy, optimize the small-index operation efficiency of the power plant under different working conditions, improve energy utilization rate, reduce the risk of equipment failure, and ensure the flexibility and adaptability of system regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 is a schematic structural diagram of the power plant real-time dynamic control and operation management system based on big data twin provided by the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts fall within the protection scope of the present invention.

[0050] Embodiment 1:

[0051] The embodiment of the present invention provides a power plant real-time dynamic control and operation management system based on big data twins, as Figure 1 shown, including:

[0052] Construction module: Obtain the spatial and system structure data of the power plant, obtain the full-condition and full-physical process data of the power plant, and construct a big data twin three-dimensional simulation model;

[0053] Analysis module: Obtain the historical operation data and historical environment data of the power plant, and determine the expected operation strategy matrix of the power plant based on the historical operation data, historical environment data, and big data twin three-dimensional simulation model;

[0054] Operation module: Real-time collect the real-time operation data and real-time environment data of the power plant, and determine the real-time operation vector of the power plant based on the real-time operation data, real-time environment data, and big data twin three-dimensional simulation model;

[0055] Control module: Determine the real-time dynamic control strategy of the power plant based on the real-time environment data, real-time operation vector, and expected operation matrix of the power plant;

[0056] Management module: Implement the operation management of the power plant based on the real-time dynamic control strategy of the power plant, and generate a synchronous operator operation guidance dynamic report and an index optimization report.

[0057] In this embodiment, the spatial structure data represents the three-dimensional layout and equipment position data of the power plant, and is used to describe the physical space structure of the power plant.

[0058] In this embodiment, the full-condition and full-physical process data covers the physical process data of the power plant under various operating states, and reflects the energy flow and equipment operation characteristics under different working conditions.

[0059] In this embodiment, based on the spatial structure data and physical process data, a big data twin three-dimensional simulation model of the power plant is constructed, which is used to simulate the operating state of the power plant under different conditions.

[0060] In this embodiment, historical operation data and historical environmental data of the power plant for more than 300 days are collected. By combining the historical data, environmental data, and the big data twin three-dimensional simulation model, an expected matrix of operation strategies is determined through analysis. This matrix is used to define the ideal operation state of the power plant under different historical environments.

[0061] In this embodiment, the operation data and environmental data of the power plant are collected in real time, including the real-time status of equipment, environmental changes, etc. By combining the real-time data with the big data twin three-dimensional simulation model, the current operation vector of the power plant is determined, reflecting the real-time operation state of the power plant.

[0062] In this embodiment, based on the real-time environmental data, real-time operation vector, and the expected matrix of operation strategies, an optimized dynamic control strategy is formulated to adjust the operation of the power plant to ensure it reaches the optimal state.

[0063] In this embodiment, based on the real-time dynamic control strategy, the operation management of the power plant is implemented, and the operation of equipment and energy dispatching are adjusted in real time. At the same time, a real-time synchronous operator operation guidance dynamic report and an index optimization report are generated and provided to the management to feedback the current operation effect of the power plant and the execution result of the control strategy.

[0064] The beneficial effects of the above technical solutions: By constructing a big data twin three-dimensional simulation model, determining the expected matrix of operation strategies of the power plant, determining the real-time operation vector of the power plant according to the real-time operation data, real-time environmental data, and the big data twin three-dimensional simulation model, and determining the real-time dynamic control strategy of the power plant according to the real-time environmental data, real-time operation vector, and expected operation matrix, the operation management of the power plant is realized, and a synchronous operator operation guidance dynamic report and an index optimization report are generated. It can achieve global monitoring and intelligent management of the power plant operation, accurately and timely adjust the control strategy, optimize the operation efficiency of small indicators of the power plant under different working conditions, improve energy utilization rate, reduce the risk of equipment failure, and ensure the flexibility and adaptability of system regulation.

[0065] Embodiment 2:

[0066] The embodiment of the present invention provides a real-time dynamic control and operation management system for a power plant based on big data twin. The construction module includes:

[0067] Spatial structure unit: Obtain the spatial structure data of the power plant based on scanning equipment. Among them, the spatial structure data includes the three-dimensional layout data of the power plant and equipment data. The equipment data includes equipment identification and equipment coordinates.

[0068] Power plant three-dimensional model construction unit: Preprocess the spatial structure data and construct a power plant three-dimensional model based on the three-dimensional layout data in the preprocessed spatial structure data.

[0069] Full-condition and full-physical-process unit: The full-condition and full-physical-process data includes physical-process sub-data under multiple operating conditions, where the physical-process sub-data includes device sub-data of multiple devices;

[0070] Big data twin process model construction unit: Preprocess the full-condition and full-physical-process data, and construct multiple big data twin process models based on the preprocessed full-condition and full-physical-process data;

[0071] Big data twin three-dimensional simulation model construction unit: Construct a big data twin three-dimensional simulation model of the power plant based on the three-dimensional model of the power plant and all big data twin process models.

[0072] In this embodiment, spatial structure data of the power plant is obtained based on scanning devices (such as laser scanners, three-dimensional scanners, etc.). The spatial structure data includes three-dimensional layout data and device data of the power plant. The three-dimensional layout data describes the physical spatial structure of the power plant, such as the layout of buildings, devices, pipelines, etc. The device data includes the unique identifier of each device and its coordinates, ensuring the precise positioning of each device in three-dimensional space.

[0073] In this embodiment, by preprocessing the spatial structure data, the three-dimensional layout data therein is extracted, and a three-dimensional model of the power plant is constructed based on these data. This model provides a digital representation of the physical environment for subsequent simulation, analysis, and optimal control, helping engineers visualize the overall structure and device positions of the power plant.

[0074] In this embodiment, physical process data of the power plant under multiple operating conditions is collected. These data include the operating states, performance parameters, etc. of multiple devices under different conditions. The physical process data of each device is organized as device sub-data, reflecting the actual performance of the device.

[0075] In this embodiment, the collected full-condition and full-physical-process data is preprocessed, the behaviors of devices under different conditions are analyzed, and multiple big data twin process models are constructed based on these data. These models simulate the behaviors and reactions of the power plant under different working states, providing an important basis for simulation and optimization.

[0076] In this embodiment, a big data twin three-dimensional simulation model of the power plant is constructed based on the three-dimensional model of the power plant and all big data twin process models. This big data twin three-dimensional simulation model integrates the physical structure and operating process of the power plant.

[0077] Advantages of the above technical solution: Obtain the spatial and system structure data of the power plant, obtain the full-condition and full-physical-process data of the power plant, and construct a big data twin three-dimensional simulation model, which can simulate the overall operation of the power plant in a virtual environment, effectively improving the operation efficiency and safety of the power plant.

[0078] Example 3:

[0079] The embodiment of the present invention provides a power plant real-time dynamic control and operation management system based on big data twin. The analysis module includes:

[0080] The first acquisition unit: acquires historical operation sub-data within multiple specified time periods, and determines historical operation data based on the historical operation sub-data within all specified time periods and all historical operation sub-data period labels;

[0081] The second acquisition unit: acquires historical environment data within multiple specified time periods, and determines historical environment data based on the historical environment sub-data within all specified time periods and all historical environment sub-data period labels.

[0082] In this embodiment, sub-data related to the operation of the power plant is collected from multiple specified time periods. Each sub-data represents the operation data of the power plant during the corresponding time period.

[0083] In this embodiment, all the collected historical operation sub-data are integrated to generate a complete historical operation data set.

[0084] In this embodiment, environment data within multiple time periods is acquired, including external factors such as climate, temperature, and humidity, which have important impacts on the operation state of the power plant.

[0085] In this embodiment, the historical environment sub-data within multiple time periods are integrated, combined with the period labels, to form a complete historical environment data set. These data help analyze how the external environment affects the operation performance of the power plant.

[0086] The beneficial effects of the above technical solution: Acquiring the historical operation data and historical environment data of the power plant can provide a data basis for determining the operation strategy expectation matrix of the power plant, so as to comprehensively analyze the operation state of the power plant in different time periods and its influence by environmental factors.

[0087] Example 4:

[0088] The embodiment of the present invention provides a power plant real-time dynamic control and operation management system based on big data twin. The analysis module further includes:

[0089] The historical environment vector unit: preprocesses the historical environment data, extracts features from the historical environment sub-data of each period label after preprocessing, and determines the historical environment vector of each period label;

[0090] Historical operation vector unit: Preprocess historical operation data, determine the historical environment vectors of each historical operation sub-data in the historical operation data based on the cycle tags, input all historical operation sub-data and their corresponding historical environment vectors in the preprocessed historical operation data into the big data twin three-dimensional simulation model, and determine the historical operation vectors of each historical operation sub-data under the corresponding historical environment vectors based on the output results of the big data twin three-dimensional simulation model;

[0091] Initial cluster center unit: Analyze the differences in the historical environment vectors of all cycle tags to determine the number of clusters a, randomly select the historical environment vectors of a cycle tags as the initial cluster centers, and perform initial marking on the a historical environment vectors;

[0092] First updated cluster center unit: Randomly select any historical environment vector without initial marking, determine the similarity between the selected historical environment vector and all initial cluster centers, assign the selected historical environment vector to the cluster family of the initial cluster center with the greatest similarity, determine the updated cluster center based on the selected historical environment vector and the historical environment vector corresponding to the initial cluster center with the greatest similarity, and perform assignment marking on the selected historical environment vector;

[0093] Second updated cluster center unit: Randomly select any historical environment vector without initial marking or without assignment marking, determine the similarity between the selected historical environment vector and the updated cluster centers of all clusters, assign the selected historical environment vector to the cluster family of the updated cluster center with the greatest similarity, determine the updated cluster center based on the selected historical environment vector and all historical environment vectors in the cluster family of the updated cluster center with the greatest similarity, and perform assignment marking on the selected historical environment vector;

[0094] Fitted environment vector unit: When all historical environment vectors have initial marking or assignment marking, determine each cluster family as an environment category, and determine the fitted environment vector of the corresponding environment category based on all historical environment vectors of each cluster family;

[0095] Cluster operation data unit: Extract the historical operation vectors corresponding to the cycle tags of all historical environment vectors of each cluster family from the historical operation data, and determine the cluster operation data of each cluster family;

[0096] First expected operation vector unit: Determine the expected operation vectors of each cluster family based on all historical operation vectors in the cluster operation data of each cluster family;

[0097] Operation strategy expected matrix unit: Determine the operation strategy expected matrix based on the fitted environment vectors of all cluster families and the expected operation vectors of all cluster families.

[0098] In this embodiment, the historical environmental data is preprocessed, cleaned, and converted into a format that is easy to analyze. Then, features are extracted from the historical environmental sub-data of each cycle label to generate a historical environmental vector corresponding to each cycle label, representing the environmental characteristics of that time period.

[0099] In this embodiment, the historical operation data is preprocessed, and each sub-data in the historical operation data is associated with the corresponding historical environmental vector according to the cycle label. Then, this data is input into the big data twin three-dimensional simulation model, and the historical operation vector is output through the model, representing the operation characteristics under a specific historical environment.

[0100] In this embodiment, the differences between all historical environmental vectors are analyzed, and the number of clusters required is determined. Then, randomly select the historical environmental vectors of a cycle labels as the initial cluster centers, and mark the initial clusters for these vectors.

[0101] In this embodiment, randomly select unlabeled historical environmental vectors, calculate the similarity with all initial cluster centers, and assign them to the most similar cluster center. Then, based on the similarity between the historical environmental vector and the cluster center, update the cluster center and mark the historical environmental vector.

[0102] In this embodiment, the unlabeled historical environmental vectors are further processed, and the similarity with the existing cluster centers is calculated. Assign them to the most similar cluster and update the cluster center of this cluster. This process is repeated until all historical environmental vectors are assigned and marked.

[0103] In this embodiment, when all historical environmental vectors are marked, based on all historical environmental vectors of each cluster family, calculate the fitting environmental vector of each cluster family, representing the environmental characteristics of this cluster family.

[0104] In this embodiment, extract the historical operation vectors corresponding to the cycle labels related to each cluster family from the historical operation data, so as to determine the cluster operation data of each cluster family, and these data are used for subsequent operation analysis.

[0105] In this embodiment, based on the cluster operation data of each cluster family, determine the expected operation vector of each cluster family, reflecting the operation performance of this cluster family under ideal conditions.

[0106] The beneficial effects of the above technical solutions: Based on the historical operation data, historical environmental data, and the big data twin three-dimensional simulation model, determine the expected operation strategy matrix of the power plant, which can achieve precise operation control and optimization of the power plant under different environmental conditions, help the power plant dynamically adjust the operation strategy according to environmental changes, improve the energy efficiency and stability of the system, reduce the risk of failure and improve safety.

[0107] Embodiment 5:

[0108] The embodiment of the present invention provides a power plant real-time dynamic control and operation management system based on big data twin. The operation strategy expectation matrix unit includes:

[0109] ;

[0110] where M represents the operation strategy expectation matrix, respectively represent the first fitted environment feature, the j-th fitted environment feature, and the N2-th fitted environment feature of the first cluster family, respectively represent the first fitted environment feature, the j-th fitted environment feature, and the N2-th fitted environment feature of the i-th cluster family, respectively represent the first fitted environment feature, the j-th fitted environment feature, and the N2-th fitted environment feature of the N1-th cluster family, respectively represent the first expected operation feature, the j-th expected operation feature, and the N3-th expected operation feature of the first cluster family, respectively represent the first expected operation feature, the j-th expected operation feature, and the N3-th expected operation feature of the first cluster family, respectively represent the first expected operation feature, the j-th expected operation feature, and the N3-th expected operation feature of the N1-th cluster family. N1 represents the number of cluster families, N2 represents the number of fitted environment features in the fitted environment vector, and N3 represents the number of expected operation features in the expected operation vector.

[0111] In this embodiment, , , respectively represent the fitted environment vector of the first cluster family , the fitted environment vector of the i-th cluster family , and the fitted environment vector of the N1-th cluster family .

[0112] , , respectively represent the expected operation vector of the first cluster family , the expected operation vector of the i-th cluster family , and the expected operation vector of the N1-th cluster family .

[0113] The beneficial effects of the above technical solution: Determining the operation strategy expectation matrix based on the fitted environment vectors of all cluster families and the expected operation vectors of all cluster families can provide a data basis for determining the real-time dynamic control strategy of the power plant, and realize precise operation control and optimization of the power plant under different environmental conditions.

[0114] Example 6:

[0115] The embodiment of the present invention provides a power plant real-time dynamic control and operation management system based on big data twin. The operation module includes:

[0116] Real-time environment vector unit: Preprocess the real-time operation data and real-time environment data collected in real time, extract features from the preprocessed real-time environment data, and determine the real-time environment vector.

[0117] Real-time category unit: Determine the similarity between the real-time environment vector and the fitting environment vector of each cluster, and select the environment category of the cluster with the largest similarity of the fitting environment vector as the real-time category of the real-time environment data.

[0118] Real-time operation vector unit: Input the preprocessed real-time operation data, real-time environment data, and the real-time category of the real-time environment data into the big data twin three-dimensional simulation model, and determine the real-time operation vector of the power plant based on the output result of the big data twin three-dimensional simulation model.

[0119] In this embodiment, the power plant operation data and environment data collected in real time are preprocessed to ensure the standardization of the data format, remove noise and outliers. The processed real-time environment data will be further subjected to feature extraction to extract key environmental information therefrom to form a real-time environment vector. This vector represents the characteristics of the current environment where the power plant is located.

[0120] In this embodiment, by calculating the similarity between the real-time environment vector and the fitting environment vector of each cluster, the fitting environment vector most similar to the real-time environment vector is selected, and the real-time category of the environment data is determined according to the cluster to which it belongs. This real-time category describes the state category of the power plant in the current environment.

[0121] In this embodiment, the operation data, environment data collected in real time, and the real-time category determined by the real-time category unit are input into the big data twin three-dimensional simulation model. The big data twin three-dimensional simulation model simulates the actual operation state of the power plant based on these input information and outputs the corresponding real-time operation vector.

[0122] Beneficial effects of the above technical solution: Real-time collect the real-time operation data and real-time environment data of the power plant, and determine the real-time operation vector of the power plant based on the real-time operation data, real-time environment data, and the big data twin three-dimensional simulation model, which can provide a data basis for determining the real-time dynamic control strategy and optimize the energy consumption and equipment load of the power plant.

[0123] Embodiment 7:

[0124] The embodiment of the present invention provides a power plant real-time dynamic control and operation management system based on big data twin. The control module includes:

[0125] Second expected operating vector unit: Determine the expected operating vector of the cluster corresponding to the real-time category of real-time environmental data based on the cluster of the real-time category corresponding to the real-time environmental data and the operating strategy expectation matrix;

[0126] Real-time dynamic control strategy unit: Determine the real-time dynamic control strategy based on the real-time environmental vector of the power plant, the real-time operating vector, the expected operating vector of the cluster corresponding to the real-time category of real-time environmental data, and the similarity between the real-time environmental data and the fitting environmental vector of the cluster corresponding to the real-time category of real-time environmental data;

[0127] Among them, represents the real-time dynamic control strategy, represents the set control strategy, represents the actual adjustment control strategy, represents the maximum adjustable control strategy of the cluster of the fitting environmental vector with the greatest similarity to the real-time environmental vector, represents the time decay factor, represents the time dependence factor, ts represents the lower limit of the time point of real-time acquisition, tp represents the current time point, represents the real-time environmental vector, represents the fitting environmental vector of the i-th cluster, represents the cluster of the fitting environmental vector with the greatest similarity to the real-time environmental vector, represents the fitting environmental vector of the cluster of the fitting environmental vector with the greatest similarity to the real-time environmental vector, represents the real-time operating vector, represents the expected operating vector of the cluster of the fitting environmental vector with the greatest similarity to the real-time environmental vector, represents the expected adjustment parameter, represents the difference value between the real-time operating vector and the expected operating vector of the cluster of the fitting environmental vector with the greatest similarity to the real-time environmental vector, represents the similarity value between the real-time environmental vector and the fitting environmental vector of the cluster of the fitting environmental vector with the greatest similarity to the real-time environmental vector, represents the second fitting adjustment parameter, represents the first fitting adjustment parameter, represents the total number of historical environmental vectors in all clusters, represents the number of historical environmental vectors in the cluster of the fitting environmental vector with the greatest similarity to the real-time environmental vector, represents the influence value of the cluster of the fitting environmental vector with the greatest similarity to the real-time environmental vector on the real-time dynamic control strategy, represents the environmental similarity factor, represents the difference factor, represents the exponential adjustment factor.

[0128] In this embodiment, the real-time environmental data has been classified into a certain cluster by the real-time classification unit, and the operation strategy expectation matrix defines an expected operation vector for each cluster. By looking up the expected operation vector of the cluster corresponding to the real-time environmental data, this unit represents the optimal operation state that the power plant should achieve under the current environmental category.

[0129] In this embodiment, It represents the time difference between the lower limit of the time point of real-time acquisition and the current time point.

[0130] In this embodiment, It represents the weight of the cluster of the fitted environmental vector with the greatest similarity to the real-time environmental vector.

[0131] In this embodiment, It represents based on the real-time environmental vector, real-time operation vector, fitted environmental vector and the expected operation vector The actual adjustment and control strategy calculated therefrom.

[0132] The beneficial effects of the above technical solution: Based on the real-time environmental data, real-time operation vector and expected operation matrix of the power plant, determine the real-time dynamic control strategy of the power plant, which can accurately and immediately adjust the operation strategy, improve the adaptability of the power plant, reduce energy consumption, optimize equipment load, and enhance the operation efficiency and safety of the power plant.

[0133] Embodiment 8:

[0134] The embodiment of the present invention provides a real-time dynamic control and operation management system for a power plant based on big data twins. The management module includes:

[0135] Execution unit: Send the real-time dynamic control strategy to the control center of the power plant. The control center executes the real-time dynamic control strategy and determines the execution result;

[0136] Report unit: Generate a synchronous operator operation guidance dynamic report and an index optimization report based on the real-time operation data, real-time environmental data, real-time dynamic control strategy and execution result.

[0137] In this embodiment, the real-time dynamic control strategy is sent from the control system to the control center of the power plant. After receiving these strategies, the control center executes the strategies according to the predetermined rules and processes, so as to make real-time adjustments to the operation of the power plant. During the execution process, the control center will monitor the execution effect and confirm the final execution result, such as whether the expected operation state or control target has been achieved.

[0138] In this embodiment, a synchronous operator operation guidance dynamic report and an index optimization report are generated based on the following information: real-time operation data: the current operation status data of the power plant; real-time environmental data: the real-time status data of the environment where the power plant is located; real-time dynamic control strategy: the dynamic control strategy formulated by the system for the power plant; execution result: the execution effect of the control strategy.

[0139] In this embodiment, the index optimization report includes multiple sub-reports for optimizing small indices.

[0140] The beneficial effects of the above technical solution: realizing the operation management of the power plant based on the real-time dynamic control strategy of the power plant, and generating a synchronous operator operation guidance dynamic report and an index optimization report, can realize the intelligent management and monitoring of the power plant operation, adjust the operation in a closed-loop manner with the real-time dynamic control strategy, realize highly automated real-time feedback and adjustment, and improve the operation efficiency, response speed and safety of the power plant.

[0141] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0142] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, also by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0143] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A power plant real-time dynamic control and operation management system based on big data twins, characterized in that, Including: Construction module: Obtain the spatial and system structure data of the power plant, obtain the full-condition and full-physical process data of the power plant, and construct a big data twin three-dimensional simulation model; Analysis module: Obtain the DCS historical operation data and historical environment data of the power plant, and determine the expected operation strategy matrix of the power plant based on the historical operation data, historical environment data, and big data twin three-dimensional simulation model; Operation module: Real-time collect the real-time operation data and real-time environment data of the power plant, and determine the real-time operation vector of the power plant based on the real-time operation data, real-time environment data, and big data twin three-dimensional simulation model; Control module: Determine the real-time dynamic control strategy of the power plant based on the real-time environment data, real-time operation vector, and expected operation matrix of the power plant; Management module: Implement the operation management of the power plant based on the real-time dynamic control strategy of the power plant, and generate a synchronous operator operation guidance dynamic report and an index optimization report; Among them, the control module includes: Second expected operation vector unit: Determine the expected operation vector of the cluster corresponding to the real-time category of the real-time environment data based on the cluster corresponding to the real-time category of the real-time environment data and the expected operation strategy matrix; Real-time dynamic control strategy unit: Determine the real-time dynamic control strategy based on the real-time environment vector, real-time operation vector, expected operation vector of the cluster corresponding to the real-time category of the real-time environment data, and the similarity between the real-time environment data and the fitting environment vector of the cluster corresponding to the real-time category of the real-time environment data; Among them, represents the real-time dynamic control strategy, represents the set control strategy, represents the actual adjustment control strategy, represents the maximum adjustable control strategy of the cluster family of the fitted environment vectors with the greatest similarity to the real-time environment vector, represents the time decay factor, represents the time dependence factor, ts represents the lower limit of the time point of real-time acquisition, and tp represents the current time point, represents the real-time environment vector, represents the fitted environment vector of the i-th cluster family, represents the cluster family of the fitted environment vectors with the greatest similarity to the real-time environment vector, represents the fitted environment vector of the cluster family of the fitted environment vectors with the greatest similarity to the real-time environment vector, represents the real-time operation vector, represents the expected operation vector of the cluster family of the fitted environment vectors with the greatest similarity to the real-time environment vector, represents the expected adjustment parameter, represents the difference value between the real-time operation vector and the expected operation vector of the cluster family of the fitted environment vectors with the greatest similarity to the real-time environment vector, represents the similarity value between the real-time environment vector and the fitted environment vector of the cluster family of the fitted environment vectors with the greatest similarity to the real-time environment vector, represents the second fitted adjustment parameter, represents the first fitted adjustment parameter, represents the total number of historical environment vectors in all cluster families, represents the number of historical environment vectors in the cluster family of the fitted environment vectors with the greatest similarity to the real-time environment vector, represents the influence value of the cluster family of the fitted environment vectors with the greatest similarity to the real-time environment vector on the real-time dynamic control strategy, represents the environmental similarity factor, represents the difference factor, represents the exponential adjustment factor.

2. The real-time dynamic control and operation management system for power plants based on big data twins according to claim 1, characterized in that, The construction module includes: Spatial structure unit: Obtain the spatial structure data of the power plant based on the scanning device, where the spatial structure data includes the three-dimensional layout data and equipment data of the power plant, and the equipment data includes equipment identification and equipment coordinates; Power plant three-dimensional model construction unit: Preprocess the spatial structure data, and construct a power plant three-dimensional model based on the three-dimensional layout data in the preprocessed spatial structure data; Full-condition and full-physical process unit: The full-condition and full-physical process data includes physical process sub-data under multiple operating conditions, where the physical process sub-data includes equipment sub-data of multiple devices; Big data twin process model construction unit: Preprocess the full-condition and full-physical process data, and construct multiple big data twin process models based on the preprocessed full-condition and full-physical process data; Big data twin three-dimensional simulation model construction unit: Construct a big data twin three-dimensional simulation model of the power plant based on the power plant three-dimensional model and all big data twin process models.

3. The real-time dynamic control and operation management system for power plants based on big data twins according to claim 1, characterized in that The analysis module includes: First acquisition unit: Obtain historical operation sub-data within multiple specified time periods, and determine historical operation data based on the historical operation sub-data within all specified time periods and all historical operation sub-data period labels; Second acquisition unit: Obtain historical environment data within multiple specified time periods, and determine historical environment data based on the historical environment sub-data within all specified time periods and all historical environment sub-data period labels.

4. The real-time dynamic control and operation management system of a power plant based on big data twin according to claim 3, characterized in that, The analysis module further includes: Historical Environment Vector Unit: Preprocess historical environment data, extract features from the historical environment sub-data of each cycle label after preprocessing, and determine the historical environment vector of each cycle label; Historical Operation Vector Unit: Preprocess historical operation data, determine the historical environment vector of each historical operation sub-data in the historical operation data based on the cycle label, input all the historical operation sub-data and the corresponding historical environment vectors in the preprocessed historical operation data into the big data twin three-dimensional simulation model, and determine the historical operation vector of each historical operation sub-data under the corresponding historical environment vector based on the output result of the big data twin three-dimensional simulation model; Initial Cluster Center Unit: Analyze the differences of the historical environment vectors of all cycle labels to determine the number of clusters a, randomly select the historical environment vectors of a cycle labels as the initial cluster centers, and perform initial marking on the a historical environment vectors; First Updated Cluster Center Unit: Randomly select any historical environment vector without initial marking, determine the similarity between the selected historical environment vector and all initial cluster centers, assign the selected historical environment vector to the cluster family of the initial cluster center with the greatest similarity, determine the updated cluster center based on the selected historical environment vector and the historical environment vector corresponding to the initial cluster center with the greatest similarity, and perform assignment marking on the selected historical environment vector; Second Updated Cluster Center Unit: Randomly select any historical environment vector without initial marking or without assignment marking, determine the similarity between the selected historical environment vector and the updated cluster centers of all clusters, assign the selected historical environment vector to the cluster family of the updated cluster center with the greatest similarity, determine the updated cluster center based on the selected historical environment vector and all the historical environment vectors in the cluster family of the updated cluster center with the greatest similarity, and perform assignment marking on the selected historical environment vector; Fitted Environment Vector Unit: When all historical environment vectors have initial marking or assignment marking, determine each cluster family as an environment category, and determine the fitted environment vector of the corresponding environment category based on all the historical environment vectors of each cluster family; Cluster Operation Data Unit: Extract the historical operation vectors corresponding to the cycle labels of all the historical environment vectors of each cluster family from the historical operation data, and determine the cluster operation data of each cluster family; First Expected Operation Vector Unit: Determine the expected operation vector of each cluster family based on all the historical operation vectors in the cluster operation data of each cluster family; Operation Strategy Expected Matrix Unit: Determine the operation strategy expected matrix based on the fitted environment vectors of all cluster families and the expected operation vectors of all cluster families.

5. The real-time dynamic control and operation management system of a power plant based on big data twins according to claim 4, characterized in that, The operation strategy expected matrix unit includes: ； Among them, M represents the operation strategy expectation matrix, respectively represent the first fitted environment feature, the j-th fitted environment feature, and the N2-th fitted environment feature of the first cluster family, respectively represent the first fitted environment feature, the j-th fitted environment feature, and the N2-th fitted environment feature of the i-th cluster family, respectively represent the first fitted environment feature, the j-th fitted environment feature, and the N2-th fitted environment feature of the N1-th cluster family, respectively represent the first expected operation feature, the j-th expected operation feature, and the N3-th expected operation feature of the first cluster family, respectively represent the first expected operation feature, the j-th expected operation feature, and the N3-th expected operation feature of the first cluster family, respectively represent the first expected operation feature, the j-th expected operation feature, and the N3-th expected operation feature of the N1-th cluster family. N1 represents the number of cluster families, N2 represents the number of fitted environment features in the fitted environment vector, and N3 represents the number of expected operation features in the expected operation vector.

6. The power plant real-time dynamic control and operation management system based on big data twin according to claim 1, characterized in that, The operation module includes: Real-time Environment Vector Unit: Preprocess the real-time operation data and real-time environment data collected in real time, extract features from the preprocessed real-time environment data, and determine the real-time environment vector; Real-time Category Unit: Determine the similarity between the real-time environment vector and the fitted environment vectors of each cluster family, and select the environment category of the cluster family of the fitted environment vector with the greatest similarity as the real-time category of the real-time environment data; Real-time operating vector unit: Input the preprocessed real-time operating data, real-time environmental data, and the real-time category of the real-time environmental data into the big data twin three-dimensional simulation model, and determine the real-time operating vector of the power plant based on the output results of the big data twin three-dimensional simulation model.

7. The real-time dynamic control and operation management system of a power plant based on big data twins according to claim 1, characterized in that, The management module includes: Execution unit: Send the real-time dynamic control strategy to the AGC control center of the power plant, and the AGC control center executes the real-time dynamic control strategy and determines the execution result. Report unit: Generate a synchronous operator operation guidance dynamic report and an index optimization report based on the real-time operating data, real-time environmental data, real-time dynamic control strategy, and execution result.

Images