Power plant real-time dynamic control and operation management system based on big data twinning

Abstract

The invention provides a power plant real-time dynamic control and operation management system based on big data twinning, and belongs to the technical field of data processing, and the system comprises a construction module which obtains spatial structure data and full-working-condition full-physical process data of a power plant, and constructs a big data twinning three-dimensional simulation model; the analysis module is used for acquiring historical operation data and historical environment data of the power plant and determining an operation strategy expectation matrix of the power plant; the operation module is used for collecting real-time operation data and real-time environment data of the power plant in real time and determining a real-time operation vector of the power plant; the control module is used for determining a real-time dynamic control strategy of the power plant; and the management module is used for generating a synchronous operator operation guidance dynamic report and an index optimization report. Global monitoring and intelligent management of power plant operation can be realized, a control strategy can be accurately and timely adjusted, the small-index operation efficiency of the power plant under different working conditions is optimized, the energy utilization rate is improved, the equipment fault risk is reduced, and the flexibility and adaptability of system adjustment are ensured.

Description

Technical Field

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

[0002] The power plant operation management system has gone through several stages of technological progress. Early power plant management 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, power plants introduced advanced process control systems (DCS) and real-time monitoring systems to monitor the operation status of power plants through automated equipment, but these systems still mainly rely on single sensor data and manual adjustments, and cannot achieve adaptive optimization for changing environmental conditions.

[0003] With the rise of big data, cloud computing and artificial intelligence technologies, power plants have begun to adopt more intelligent management solutions. Based on a large amount of historical data and real-time data, power plant management systems have begun to introduce machine learning and optimization algorithms to achieve intelligent prediction and dynamic adjustment of power plant operations. In addition, the simulation model and operation data integration technology of power plants have gradually matured, making it possible to monitor and intelligently control the operation of power plants.

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

[0005] The present invention provides a real-time dynamic control and operation management system for power plants based on big data twins. By constructing a big data twin three-dimensional simulation model, the expected matrix of the power plant's operation strategy is determined. The real-time operation vector of the power plant is determined according to the real-time operation data, real-time environmental data and the big data twin three-dimensional simulation model. The real-time dynamic control strategy of the power plant is determined according to the real-time environmental data, the real-time operation vector and the expected operation matrix. The operation management of the power plant is realized, and a synchronous operator operation guidance dynamic report and an indicator optimization report are generated. Global monitoring and intelligent management of the power plant operation can be realized, and control strategies can be adjusted accurately and timely, and the operating efficiency of small indicators of the power plant under different operating conditions can be optimized, thereby improving energy utilization, reducing the risk of equipment failure and ensuring the flexibility and adaptability of system adjustment.

[0006] The present invention provides a real-time dynamic control and operation management system for a power plant based on big data twins, including: Construction module: obtain the spatial and system structure data of the power plant, obtain the full operating condition and full physical process data of the power plant, and build a big data twin 3D simulation model; Analysis module: Obtain the historical operation data and historical environmental data of the power plant, and determine the expected matrix of the power plant's operation strategy based on the historical operation data, historical environmental data and the big data twin 3D simulation model; Operation module: collects the real-time operation data and real-time environmental data of the power plant in real time, and determines the real-time operation vector of the power plant based on the real-time operation data, real-time environmental data and big data twin 3D simulation model; Control module: determines the real-time dynamic control strategy of the power plant based on the real-time environmental data of the power plant, the real-time operation vector and the expected operation matrix; Management module: realizes the operation management of the power plant based on the real-time dynamic control strategy of the power plant, and generates synchronous operator operation guidance dynamic report and indicator optimization report.

[0007] According to the real-time dynamic control and operation management system of a power plant based on big data twin provided by the present invention, the building module includes: Spatial structure unit: acquires spatial structure data of the power plant based on scanning equipment, wherein the spatial structure data includes three-dimensional layout data and equipment data of the power plant, and the equipment data includes equipment identification and equipment coordinates; A power plant three-dimensional model building unit: preprocesses the spatial structure data, and builds a three-dimensional model of the power plant based on the three-dimensional layout data in the preprocessed spatial structure data; Full-operating-condition full-physical process unit: Full-operating-condition full-physical process data includes physical process sub-data under multiple operating conditions, wherein the physical process sub-data includes device sub-data of multiple devices; Big data twin process model construction unit: pre-process the full-operating-condition and full-physical process data, and build multiple big data twin process models based on the pre-processed full-operating-condition and full-physical process data; Big data twin 3D simulation model construction unit: constructs a big data twin 3D simulation model of the power plant based on the 3D model of the power plant and all big data twin process models.

[0008] According to the real-time dynamic control and operation management system of a power plant based on big data twin provided by the present invention, the analysis module includes: A first acquisition unit: acquires historical operation sub-data within a plurality of specified time periods, and determines the historical operation data based on the historical operation sub-data within all specified time periods and all historical operation sub-data period labels; The second acquisition unit is used to acquire historical environment data within a plurality of specified time periods, and determine the historical environment data based on the historical environment sub-data within all specified time periods and all historical environment sub-data period labels.

[0009] According to the real-time dynamic control and operation management system of a power plant based on big data twin provided by the present invention, the analysis module further includes: Historical environment vector unit: preprocesses the historical environment data, extracts features from the preprocessed historical environment sub-data of each period label, and determines the historical environment vector of each period label; Historical operation vector unit: pre-process the historical operation data, determine the historical environment vector of each historical operation sub-data in the historical operation data based on the period label, input all the historical operation sub-data and the corresponding historical environment vector in the pre-processed historical operation data into the big data twin 3D 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 3D simulation model; Initial cluster center unit: Analyze the differences of the historical environment vectors of all periodic labels to determine the number of clusters a, randomly select a historical environment vectors of periodic labels as the initial cluster center, and initially mark the a historical environment vectors; The first cluster center update unit: randomly selects any historical environment vector without initial marking, determines the similarity between the selected historical environment vector and all initial cluster centers, assigns the selected historical environment vector to the cluster family of the initial cluster center with the greatest similarity, determines the update 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 assigns markings to the selected historical environment vector; The second update cluster center unit: randomly selects any historical environment vector without initial mark or assigned mark, determines the similarity between the selected historical environment vector and the update cluster centers of all clusters, assigns the selected historical environment vector to the cluster family of the update cluster center with the greatest similarity, determines the update cluster center based on the selected historical environment vector and all historical environment vectors in the cluster family of the update cluster center with the greatest similarity, and assigns marks to the selected historical environment vector; Fitting environment vector unit: when all historical environment vectors have initial tags or assigned tags, each cluster is determined as an environment category, and a fitting environment vector of the corresponding environment category is determined based on all historical environment vectors of each cluster; Cluster operation data unit: extracts historical operation vectors corresponding to the period labels of all historical environment vectors of each cluster family from the historical operation data, and determines the cluster operation data of each cluster family; A first expected operation vector unit: determining an expected operation vector for each cluster group based on all historical operation vectors in the cluster operation data of each cluster group; Operation strategy expectation matrix unit: determines the operation strategy expectation matrix based on the fitting environment vectors of all cluster families and the expected operation vectors of all cluster families.

[0010] According to the real-time dynamic control and operation management system of a power plant based on big data twin provided by the present invention, the operation strategy expectation matrix unit includes: ; Among them, M represents the expected matrix of the operation strategy, They represent the first fitting environment feature, the jth fitting environment feature, and the N2th fitting environment feature of the first cluster, respectively. They represent the first fitting environment feature, the jth fitting environment feature, and the N2th fitting environment feature of the i-th cluster, respectively. They represent the first fitting environment feature, the jth fitting environment feature, and the N2th fitting environment feature of the N1th cluster, respectively. They represent the first expected operating feature, the jth expected operating feature, and the N3th expected operating feature of the first cluster, respectively. They represent the first expected operating feature, the jth expected operating feature, and the N3th expected operating feature of the first cluster, respectively. They respectively represent the 1st expected operating feature, the jth expected operating feature, and the N3th expected operating feature of the N1th cluster group, N1 represents the number of cluster groups, N2 represents the number of fitting environment features in the fitting environment vector, and N3 represents the number of expected operating features in the expected operating vector.

[0011] According to the real-time dynamic control and operation management system of a power plant based on big data twin provided by the present invention, the operation module includes: Real-time environment vector unit: pre-processes the real-time operation data and real-time environment data collected in real time, extracts features from the pre-processed real-time environment data, and determines the real-time environment vector; 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 of the fitting environment vector with the greatest similarity as the real-time category of the real-time environment data; Real-time operation vector unit: The preprocessed real-time operation data, real-time environmental data and real-time category of the real-time environmental data are input into the big data twin three-dimensional simulation model, and the real-time operation vector of the power plant is determined based on the output results of the big data twin three-dimensional simulation model.

[0012] According to the real-time dynamic control and operation management system of a power plant based on big data twin provided by the present invention, the control module includes: A second expected operation vector unit: determining an expected operation vector of a cluster group corresponding to the real-time category of the real-time environment data based on the cluster group corresponding to the real-time category of the real-time environment data and the expected matrix of the operation strategy; Real-time dynamic control strategy unit: determines the real-time dynamic control strategy based on 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 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; in, represents the real-time dynamic control strategy, Indicates setting the control strategy. represents the actual regulation control strategy, The maximum adjustable control strategy representing the cluster of fitted environment vectors with the greatest similarity to the real environment vector, represents the time decay factor, Indicates the time dependency factor, ts indicates the lower limit of the time point for real-time acquisition, and tp indicates the current time point. represents the real-time environment vector, represents the fitted environment vector of the ith cluster, represents the cluster of fitted environment vectors that have the greatest similarity to the real-time environment vector, The fitted environment vector represents the cluster of fitted environment vectors with the greatest similarity to the real-time environment vector, represents the real-time running vector, represents the expected running vector of the cluster of fitted environment vectors that have the greatest similarity to the real-time environment vector, represents the desired adjustment parameter, represents the difference between the expected running vector of the cluster of the real-time running vector and the fitted environment vector that has 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 of fitted environment vectors 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 fitted environment vector that has the greatest similarity to the real-time environment vector, Indicates the impact of the cluster of 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.

[0013] According to the real-time dynamic control and operation management system of a power plant based on big data twin provided by the present invention, the management module includes: Execution unit: sends the real-time dynamic control strategy to the control center of the power plant, which executes the real-time dynamic control strategy and determines the execution result; Reporting unit: Generates synchronous operator operation guidance dynamic reports and indicator optimization reports based on real-time operation data, real-time environmental data, real-time dynamic control strategies and execution results.

[0014] Compared with the prior art, the beneficial effects of this application are as follows: By constructing a big data twin three-dimensional simulation model, the expected matrix of the power plant's operating strategy is determined, and the real-time operating vector of the power plant is determined based on the real-time operating data, real-time environmental data and the big data twin three-dimensional simulation model. The real-time dynamic control strategy of the power plant is determined based on the real-time environmental data, the real-time operating vector and the expected operating matrix. Efficient operation management of the power plant is achieved, and synchronous guidance and optimization reports are generated. This can realize global monitoring and intelligent management of power plant operations, accurately and timely adjust control strategies, optimize the operating efficiency of small indicators of power plants under different operating conditions, improve energy utilization, reduce the risk of equipment failure, and ensure the flexibility and adaptability of system adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a structural diagram of the real-time dynamic control and operation management system of a power plant based on big data twins provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Embodiment 1: 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, such as Figure 1 As shown, including: Construction module: obtain the spatial and system structure data of the power plant, obtain the full operating condition and full physical process data of the power plant, and build a big data twin 3D simulation model; Analysis module: Obtain the historical operation data and historical environmental data of the power plant, and determine the expected matrix of the power plant's operation strategy based on the historical operation data, historical environmental data and the big data twin 3D simulation model; Operation module: collects the real-time operation data and real-time environmental data of the power plant in real time, and determines the real-time operation vector of the power plant based on the real-time operation data, real-time environmental data and big data twin 3D simulation model; Control module: determines 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; Management module: realizes the operation management of the power plant based on the real-time dynamic control strategy of the power plant, and generates synchronous operator operation guidance dynamic report and indicator optimization report.

[0019] In this embodiment, the spatial structure data represents the three-dimensional layout and equipment location data of the power plant, and is used to describe the physical spatial structure of the power plant.

[0020] In this embodiment, the full operating condition and full physical process data cover the physical process data of the power plant under various operating conditions, reflecting the energy flow and equipment operation characteristics under different operating conditions.

[0021] In this embodiment, a big data twin three-dimensional simulation model of the power plant is constructed based on spatial structure data and physical process data to simulate the operating status of the power plant under different conditions.

[0022] In this embodiment, more than 300 days of historical operating data and historical environmental data of the power plant are collected, and the historical data, environmental data and big data twin three-dimensional simulation model are combined to determine the operating strategy expectation matrix through analysis. The matrix is ​​used to define the ideal operating state of the power plant under different historical environments.

[0023] In this embodiment, the operating data and environmental data of the power plant are collected in real time, including the real-time status of the equipment, environmental changes, etc. By combining the real-time data with the big data twin three-dimensional simulation model, the current operating vector of the power plant is determined to reflect the real-time operating status of the power plant.

[0024] In this embodiment, an optimized dynamic control strategy is formulated based on real-time environmental data, real-time operation vectors, and an operation strategy expectation matrix to adjust the operation of the power plant to ensure that it reaches the optimal state.

[0025] In this embodiment, based on the real-time dynamic control strategy, the power plant operation management is implemented, the equipment operation and energy scheduling are adjusted in real time, and real-time synchronous operator operation guidance dynamic report and indicator optimization report are generated to provide feedback to the management on the current operation effect of the power plant and the execution results of the control strategy.

[0026] The beneficial effects of the above technical solution are as follows: by constructing a big data twin three-dimensional simulation model, the expected matrix of the power plant's operating strategy is determined, the real-time operating vector of the power plant is determined according to the real-time operating data, real-time environmental data and the big data twin three-dimensional simulation model, and the real-time dynamic control strategy of the power plant is determined according to the real-time environmental data, the real-time operating vector and the expected operating matrix, so as to realize the operation management of the power plant, generate a synchronous operator operation guidance dynamic report and an indicator optimization report, realize the global monitoring and intelligent management of the power plant operation, accurately and timely adjust the control strategy, optimize the small indicator operation efficiency of the power plant under different operating conditions, improve energy utilization, reduce the risk of equipment failure and ensure the flexibility and adaptability of system adjustment.

[0027] Embodiment 2: 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, wherein the building module comprises: Spatial structure unit: acquires spatial structure data of the power plant based on scanning equipment, wherein the spatial structure data includes three-dimensional layout data and equipment data of the power plant, and the equipment data includes equipment identification and equipment coordinates; A power plant three-dimensional model building unit: preprocesses the spatial structure data, and builds a three-dimensional model of the power plant based on the three-dimensional layout data in the preprocessed spatial structure data; Full-operating-condition full-physical process unit: Full-operating-condition full-physical process data includes physical process sub-data under multiple operating conditions, wherein the physical process sub-data includes device sub-data of multiple devices; Big data twin process model construction unit: pre-process the full-operating-condition and full-physical process data, and build multiple big data twin process models based on the pre-processed full-operating-condition and full-physical process data; Big data twin 3D simulation model construction unit: constructs a big data twin 3D simulation model of the power plant based on the 3D model of the power plant and all big data twin process models.

[0028] In this embodiment, the spatial structure data of the power plant is obtained based on a scanning device (such as a laser scanner, a 3D scanner, etc.). The spatial structure data includes the 3D layout data and equipment data of the power plant. The 3D layout data describes the physical spatial structure of the power plant, such as the layout of buildings, equipment, pipelines, etc. The equipment data includes the unique identification of each device and its coordinates, ensuring that each device is accurately located in the 3D space.

[0029] In this embodiment, the spatial structure data is preprocessed to extract the three-dimensional layout data, and a three-dimensional model of the power plant is constructed based on the data. This model provides a digital representation of the physical environment for subsequent simulation, analysis, and optimization control, helping engineers visualize the overall structure and equipment location of the power plant.

[0030] In this embodiment, the physical process data of the power plant under multiple operating conditions are collected. These data include the operating status, performance parameters, etc. of multiple devices under different operating conditions. The physical process data of each device is organized into device sub-data, reflecting the actual performance of the device.

[0031] In this embodiment, the collected full-operating-condition and full-physical process data are preprocessed to analyze the behavior of the equipment under different operating conditions, and multiple big data twin process models are constructed based on these data. These models simulate the behavior and response of the power plant under different operating conditions, providing an important basis for simulation and optimization.

[0032] 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. The big data twin three-dimensional simulation model integrates the physical structure and operation process of the power plant.

[0033] The beneficial effects of the above technical solution are: obtaining the spatial and system structure data of the power plant, obtaining the full operating condition and full physical process data of the power plant, and building a big data twin three-dimensional simulation model, which can simulate the overall operation of the power plant in a virtual environment and effectively improve the operating efficiency and safety of the power plant.

[0034] Embodiment 3: 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, wherein the analysis module includes: A first acquisition unit: acquires historical operation sub-data within a plurality of specified time periods, and determines the historical operation data based on the historical operation sub-data within all specified time periods and all historical operation sub-data period labels; The second acquisition unit is used to acquire historical environment data within multiple specified time periods, and determine the historical environment data based on the historical environment sub-data within all specified time periods and all historical environment sub-data period labels.

[0035] In this embodiment, sub-data related to the operation of the power plant are collected from multiple specified time periods, and each sub-data represents the operation data of the power plant in a corresponding time period.

[0036] In this embodiment, all collected historical operation sub-data are integrated to generate a complete historical operation data set.

[0037] In this embodiment, environmental data within multiple time periods are obtained, including external factors such as climate, temperature, humidity, etc., which have an important impact on the operating status of the power plant.

[0038] In this embodiment, the historical environment sub-data in multiple time periods are integrated and combined with period labels to form a complete historical environment data set. These data are helpful for analyzing how the external environment affects the operating performance of the power plant.

[0039] The beneficial effects of the above technical solution are as follows: obtaining the historical operating data and historical environmental data of the power plant can provide a data basis for determining the expected matrix of the power plant's operating strategy, so as to comprehensively analyze the operating status of the power plant in different time periods and its impact by environmental factors.

[0040] Embodiment 4: 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, wherein the analysis module further includes: 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; Historical operation vector unit: pre-process the historical operation data, determine the historical environment vector of each historical operation sub-data in the historical operation data based on the period label, input all the historical operation sub-data and the corresponding historical environment vector in the pre-processed historical operation data into the big data twin 3D 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 3D simulation model; Initial cluster center unit: Analyze the differences of the historical environment vectors of all periodic labels to determine the number of clusters a, randomly select a historical environment vectors of periodic labels as the initial cluster center, and initially mark the a historical environment vectors; The first cluster center update unit: randomly selects any historical environment vector without initial marking, determines the similarity between the selected historical environment vector and all initial cluster centers, assigns the selected historical environment vector to the cluster family of the initial cluster center with the greatest similarity, determines the update 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 assigns markings to the selected historical environment vector; The second update cluster center unit: randomly selects any historical environment vector without initial mark or assigned mark, determines the similarity between the selected historical environment vector and the update cluster centers of all clusters, assigns the selected historical environment vector to the cluster family of the update cluster center with the greatest similarity, determines the update cluster center based on the selected historical environment vector and all historical environment vectors in the cluster family of the update cluster center with the greatest similarity, and assigns marks to the selected historical environment vector; Fitting environment vector unit: when all historical environment vectors have initial tags or assigned tags, each cluster is determined as an environment category, and a fitting environment vector of the corresponding environment category is determined based on all historical environment vectors of each cluster; Cluster operation data unit: extracts historical operation vectors corresponding to the period labels of all historical environment vectors of each cluster family from the historical operation data, and determines the cluster operation data of each cluster family; A first expected operation vector unit: determining an expected operation vector for each cluster group based on all historical operation vectors in the cluster operation data of each cluster group; Operation strategy expectation matrix unit: determines the operation strategy expectation matrix based on the fitting environment vectors of all cluster families and the expected operation vectors of all cluster families.

[0041] In this embodiment, the historical environment data is preprocessed, cleaned and converted into a format that is easy to analyze. Next, features are extracted from the historical environment sub-data of each period tag to generate a historical environment vector corresponding to each period tag, representing the environmental features of the time period.

[0042] In this embodiment, the historical operation data is preprocessed, and each sub-data in the historical operation data is associated with the corresponding historical environment vector according to the period label. Then, these data are input into the big data twin 3D simulation model, and the historical operation vector is output through the model to represent the operation characteristics under a specific historical environment.

[0043] In this embodiment, the differences between all historical environment vectors are analyzed and the number of clusters required is determined. Then, historical environment vectors of a periodic labels are randomly selected as initial cluster centers, and these vectors are marked with initial clusters.

[0044] In this embodiment, an unlabeled historical environment vector is randomly selected, and its similarity with all initial cluster centers is calculated, and it is assigned to the most similar cluster center. Then, based on the similarity between the historical environment vector and the cluster center, the cluster center is updated and the historical environment vector is labeled.

[0045] In this embodiment, the unlabeled historical context vector is further processed to calculate the similarity with the existing cluster center. It is assigned to the most similar cluster and the cluster center of the cluster is updated. This process is repeated until all historical context vectors are assigned and labeled.

[0046] In this embodiment, when all historical environment vectors are marked, a fitting environment vector of each cluster is calculated based on all historical environment vectors of each cluster to represent the environment characteristics of the cluster.

[0047] In this embodiment, historical operation vectors corresponding to periodic labels related to each cluster group are extracted from historical operation data, so as to determine cluster operation data of each cluster group, and these data are used for subsequent operation analysis.

[0048] In this embodiment, based on the cluster operation data of each cluster group, an expected operation vector of each cluster group is determined to reflect the operation performance of the cluster group under an ideal state.

[0049] The beneficial effects of the above technical solution are as follows: by determining the expected matrix of the power plant's operating strategy based on historical operating data, historical environmental data and the big data twin three-dimensional simulation model, precise operation control and optimization of the power plant under different environmental conditions can be achieved, which helps the power plant to dynamically adjust its operating strategy according to environmental changes, improve the energy efficiency and stability of the system, reduce the risk of failure and improve safety.

[0050] Embodiment 5: 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, wherein the operation strategy expectation matrix unit includes: ; Among them, M represents the expected matrix of the operation strategy, They represent the first fitting environment feature, the jth fitting environment feature, and the N2th fitting environment feature of the first cluster, respectively. They represent the first fitting environment feature, the jth fitting environment feature, and the N2th fitting environment feature of the i-th cluster, respectively. They represent the first fitting environment feature, the jth fitting environment feature, and the N2th fitting environment feature of the N1th cluster, respectively. They represent the first expected operating feature, the jth expected operating feature, and the N3th expected operating feature of the first cluster, respectively. They represent the first expected operating feature, the jth expected operating feature, and the N3th expected operating feature of the first cluster, respectively. They respectively represent the 1st expected operating feature, the jth expected operating feature, and the N3th expected operating feature of the N1th cluster group, N1 represents the number of cluster groups, N2 represents the number of fitting environment features in the fitting environment vector, and N3 represents the number of expected operating features in the expected operating vector.

[0051] In this embodiment, , , Represent the fitting environment vector of the first cluster family , the fitted environment vector of the ith cluster , the fitted environment vector of the N1th cluster .

[0052] , , Respectively represent the expected running vector of the first cluster family , the expected running vector of the ith cluster , the expected running vector of the N1th cluster .

[0053] The beneficial effects of the above technical solution are as follows: determining the expected matrix of the operation strategy based on the fitted environmental 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.

[0054] Embodiment 6: 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, wherein the operation module includes: Real-time environment vector unit: pre-processes the real-time operation data and real-time environment data collected in real time, extracts features from the pre-processed real-time environment data, and determines the real-time environment vector; 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 of the fitting environment vector with the greatest similarity as the real-time category of the real-time environment data; Real-time operation vector unit: The preprocessed real-time operation data, real-time environmental data and real-time category of the real-time environmental data are input into the big data twin three-dimensional simulation model, and the real-time operation vector of the power plant is determined based on the output results of the big data twin three-dimensional simulation model.

[0055] In this embodiment, the real-time collected power plant operation data and environmental data are preprocessed to ensure the data format is standardized and remove noise and abnormal values. The processed real-time environmental data will be further feature extracted to extract key environmental information and form a real-time environmental vector. This vector represents the characteristics of the current power plant environment.

[0056] 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. The real-time category describes the state category of the power plant under the current environment.

[0057] In this embodiment, the real-time collected operation data, environmental data and the real-time category determined by the real-time category unit are input into the big data twin 3D simulation model. The big data twin 3D simulation model simulates the actual operation state of the power plant based on the input information and outputs the corresponding real-time operation vector.

[0058] The beneficial effects of the above technical solution are: real-time collection of real-time operation data and real-time environmental data of the power plant, and determination of 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, which can provide data basis for determining the real-time dynamic control strategy and optimize the energy consumption and equipment load of the power plant.

[0059] Embodiment 7: 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, wherein the control module comprises: A second expected operation vector unit: determining an expected operation vector of a cluster group corresponding to the real-time category of the real-time environment data based on the cluster group corresponding to the real-time category of the real-time environment data and the expected matrix of the operation strategy; Real-time dynamic control strategy unit: determines the real-time dynamic control strategy based on 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 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; in, represents the real-time dynamic control strategy, Indicates setting the control strategy. represents the actual regulation control strategy, The maximum adjustable control strategy representing the cluster of fitted environment vectors with the greatest similarity to the real environment vector, represents the time decay factor, Indicates the time dependency factor, ts indicates the lower limit of the time point for real-time acquisition, and tp indicates the current time point. represents the real-time environment vector, represents the fitted environment vector of the ith cluster, represents the cluster of fitted environment vectors that have the greatest similarity to the real-time environment vector, The fitted environment vector represents the cluster of fitted environment vectors with the greatest similarity to the real-time environment vector, represents the real-time running vector, represents the expected running vector of the cluster of fitted environment vectors that have the greatest similarity to the real-time environment vector, represents the desired adjustment parameter, represents the difference between the expected running vector of the cluster of the real-time running vector and the fitted environment vector that has 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 of fitted environment vectors 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 fitted environment vector that has the greatest similarity to the real-time environment vector, Indicates the impact of the cluster of 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.

[0060] In this embodiment, the real-time environmental data has been classified into a certain cluster group through the real-time category unit, and the operation strategy expectation matrix defines an expected operation vector for each cluster group. The unit represents the optimal operating state that the power plant should achieve under the current environmental category by searching the expected operation vector of the cluster group corresponding to the real-time environmental data.

[0061] In this embodiment, Indicates the time difference between the lower limit of the real-time acquisition time point and the current time point.

[0062] In this embodiment, Represents the weight of the cluster of fitted environment vectors that have the greatest similarity to the real environment vector.

[0063] In this embodiment, Indicates real-time environment vector, real-time operation vector, and fitting environment vector and the expected run vector The actual regulation control strategy obtained by calculation.

[0064] The beneficial effects of the above technical solution are as follows: based on the real-time environmental data, real-time operation vector and expected operation matrix of the power plant, the real-time dynamic control strategy of the power plant is determined, the operation strategy can be adjusted accurately and instantly, the adaptability of the power plant is improved, energy consumption is reduced, equipment load is optimized, and the operating efficiency and safety of the power plant are improved.

[0065] Embodiment 8: 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, wherein the management module includes: Execution unit: sends the real-time dynamic control strategy to the control center of the power plant, which executes the real-time dynamic control strategy and determines the execution result; Reporting unit: Generates synchronous operator operation guidance dynamic reports and indicator optimization reports based on real-time operation data, real-time environmental data, real-time dynamic control strategies and execution results.

[0066] 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, thereby adjusting the operation of the power plant in real time. During the execution process, the control center monitors the effect of the execution and confirms the final execution result, such as whether the expected operating state or control target has been achieved.

[0067] In this embodiment, a synchronous operator operation guidance dynamic report and an indicator 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 in which the power plant is located; real-time dynamic control strategy: the dynamic control strategy formulated by the system for the power plant; execution results: the execution effect of the control strategy.

[0068] In this embodiment, the indicator optimization report includes multiple small indicator optimization sub-reports.

[0069] The beneficial effects of the above technical solution are: based on the real-time dynamic control strategy of the power plant, the operation management of the power plant is realized, and a synchronous operator operation guidance dynamic report and an indicator optimization report are generated, which can realize the intelligent management and monitoring of the power plant operation, the real-time dynamic control strategy closed-loop adjustment operation, and realize highly automated real-time feedback and adjustment, thereby improving the operation efficiency, response speed and safety of the power plant.

[0070] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0071] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for 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.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The real-time dynamic control and operation management system of power plants based on big data twins is characterized by: include: Construction module: obtain the spatial and system structure data of the power plant, obtain the full operating condition and full physical process data of the power plant, and build a big data twin 3D simulation model; Analysis module: Obtain the DCS historical operation data and historical environmental data of the power plant, and determine the power plant's operation strategy expectation matrix based on the historical operation data, historical environmental data and the big data twin 3D simulation model; Operation module: collects the real-time operation data and real-time environmental data of the power plant in real time, and determines the real-time operation vector of the power plant based on the real-time operation data, real-time environmental data and big data twin 3D simulation model; Control module: determines the real-time dynamic control strategy of the power plant based on the real-time environmental data of the power plant, the real-time operation vector and the expected operation matrix; Management module: realizes the operation management of the power plant based on the real-time dynamic control strategy of the power plant, and generates synchronous operator operation guidance dynamic report and indicator optimization report.

2. The real-time dynamic control and operation management system of a power plant based on big data twin according to claim 1 is characterized in that: The building blocks include: Spatial structure unit: acquires spatial structure data of the power plant based on scanning equipment, wherein the spatial structure data includes three-dimensional layout data and equipment data of the power plant, and the equipment data includes equipment identification and equipment coordinates; A power plant three-dimensional model building unit: preprocesses the spatial structure data, and builds a three-dimensional model of the power plant based on the three-dimensional layout data in the preprocessed spatial structure data; Full-operating-condition full-physical process unit: Full-operating-condition full-physical process data includes physical process sub-data under multiple operating conditions, wherein the physical process sub-data includes device sub-data of multiple devices; Big data twin process model construction unit: pre-process the full-operating-condition and full-physical process data, and build multiple big data twin process models based on the pre-processed full-operating-condition and full-physical process data; Big data twin 3D simulation model construction unit: constructs a big data twin 3D simulation model of the power plant based on the 3D model of the power plant and all big data twin process models.

3. The real-time dynamic control and operation management system of a power plant based on big data twin according to claim 1 is characterized in that: The analysis module comprises: A first acquisition unit: acquires historical operation sub-data within a plurality of specified time periods, and determines the historical operation data based on the historical operation sub-data within all specified time periods and all historical operation sub-data period labels; The second acquisition unit is used to acquire historical environment data within a plurality of specified time periods, and determine the 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 is characterized in that: The analysis module further includes: 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; Historical operation vector unit: pre-process the historical operation data, determine the historical environment vector of each historical operation sub-data in the historical operation data based on the period label, input all the historical operation sub-data and the corresponding historical environment vector in the pre-processed historical operation data into the big data twin 3D 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 3D simulation model; Initial cluster center unit: Analyze the differences of the historical environment vectors of all periodic labels to determine the number of clusters a, randomly select a historical environment vectors of periodic labels as the initial cluster center, and initially mark the a historical environment vectors; The first cluster center update unit: randomly selects any historical environment vector without initial marking, determines the similarity between the selected historical environment vector and all initial cluster centers, assigns the selected historical environment vector to the cluster family of the initial cluster center with the greatest similarity, determines the update 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 assigns markings to the selected historical environment vector; The second update cluster center unit: randomly selects any historical environment vector without initial mark or assigned mark, determines the similarity between the selected historical environment vector and the update cluster centers of all clusters, assigns the selected historical environment vector to the cluster family of the update cluster center with the greatest similarity, determines the update cluster center based on the selected historical environment vector and all historical environment vectors in the cluster family of the update cluster center with the greatest similarity, and assigns marks to the selected historical environment vector; Fitting environment vector unit: when all historical environment vectors have initial tags or assigned tags, each cluster is determined as an environment category, and a fitting environment vector of the corresponding environment category is determined based on all historical environment vectors of each cluster; Cluster operation data unit: extracts historical operation vectors corresponding to the period labels of all historical environment vectors of each cluster family from the historical operation data, and determines the cluster operation data of each cluster family; A first expected operation vector unit: determining an expected operation vector for each cluster group based on all historical operation vectors in the cluster operation data of each cluster group; Operation strategy expectation matrix unit: determines the operation strategy expectation matrix based on the fitting 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 twin according to claim 4 is characterized in that: The operation strategy expectation matrix unit includes: ； Among them, M represents the expected matrix of the operation strategy, They represent the first fitting environment feature, the jth fitting environment feature, and the N2th fitting environment feature of the first cluster, respectively. They represent the first fitting environment feature, the jth fitting environment feature, and the N2th fitting environment feature of the i-th cluster, respectively. They represent the first fitting environment feature, the jth fitting environment feature, and the N2th fitting environment feature of the N1th cluster, respectively. They represent the first expected operating feature, the jth expected operating feature, and the N3th expected operating feature of the first cluster, respectively. They represent the first expected operating feature, the jth expected operating feature, and the N3th expected operating feature of the first cluster, respectively. They respectively represent the 1st expected operating feature, the jth expected operating feature, and the N3th expected operating feature of the N1th cluster group, N1 represents the number of cluster groups, N2 represents the number of fitting environment features in the fitting environment vector, and N3 represents the number of expected operating features in the expected operating vector.

6. The real-time dynamic control and operation management system of a power plant based on big data twin according to claim 1 is characterized in that: The operation module comprises: Real-time environment vector unit: pre-processes the real-time operation data and real-time environment data collected in real time, extracts features from the pre-processed real-time environment data, and determines the real-time environment vector; 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 of the fitting environment vector with the greatest similarity as the real-time category of the real-time environment data; Real-time operation vector unit: The preprocessed real-time operation data, real-time environmental data and real-time category of the real-time environmental data are input into the big data twin three-dimensional simulation model, and the real-time operation vector of the power plant is determined 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 twin according to claim 6 is characterized in that: The control module comprises: A second expected operation vector unit: determining an expected operation vector of a cluster group corresponding to the real-time category of the real-time environment data based on the cluster group corresponding to the real-time category of the real-time environment data and the expected matrix of the operation strategy; Real-time dynamic control strategy unit: determines the real-time dynamic control strategy based on 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 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; in, represents the real-time dynamic control strategy, Indicates setting the control strategy. represents the actual regulation control strategy, The maximum adjustable control strategy representing the cluster of fitted environment vectors with the greatest similarity to the real environment vector, represents the time decay factor, Indicates the time dependency factor, ts indicates the lower limit of the time point for real-time acquisition, and tp indicates the current time point. represents the real-time environment vector, represents the fitted environment vector of the ith cluster, represents the cluster of fitted environment vectors that have the greatest similarity to the real-time environment vector, The fitted environment vector represents the cluster of fitted environment vectors with the greatest similarity to the real-time environment vector, represents the real-time running vector, represents the expected running vector of the cluster of fitted environment vectors that have the greatest similarity to the real-time environment vector, represents the desired adjustment parameter, represents the difference between the expected running vector of the cluster of the real-time running vector and the fitted environment vector that has 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 of fitted environment vectors 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 fitted environment vector that has the greatest similarity to the real-time environment vector, Indicates the impact of the cluster of 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.

8. The real-time dynamic control and operation management system of a power plant based on big data twin according to claim 1 is characterized in that: The management module comprises: Execution unit: sends the real-time dynamic control strategy to the AGC control center of the power plant. The AGC control center executes the real-time dynamic control strategy and determines the execution result. Reporting unit: Generates synchronous operator operation guidance dynamic reports and indicator optimization reports based on real-time operation data, real-time environmental data, real-time dynamic control strategies and execution results.

Images