Power failure calculation and prediction method and system based on digital twinning

Abstract

The invention provides a power fault calculation prediction method and system based on digital twinning, and relates to the technical field of data processing, and the method comprises the steps: obtaining the real-time operation parameters of a power system through a data sensing cloud platform, building a digital power twinning model, carrying out the analog simulation of historical fault information through the digital power twinning model, and obtaining a power fault prediction result. And generating a power fault simulation data set, calculating to obtain multiple pieces of power fault prediction information, carrying out pre-estimation analysis on the operation fault of the power system by utilizing the multiple pieces of power fault prediction information, and formulating a power operation scheduling strategy to carry out operation maintenance on the power system. According to the method, the technical problem that the power system is difficult to maintain in time due to the fact that the prediction accuracy of the power system fault is low in the prior art is solved, the fault is reasonably and accurately predicted through the digital twin technology, and the power system is better operated and maintained.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for calculating and predicting power failures based on digital twins. Background Art

[0002] With the rapid development of the power system and the continuous expansion and updating of the power grid, the scale of the power system has increased year by year, and the difficulty of operation has also increased accordingly. The power system is an important support for the development and production of modern society, but the stable operation of the power system faces many challenges. Some external factors, such as natural disasters, will directly lead to power system failures. There are also certain internal out-of-control factors. In addition, the accuracy of predicting power system failures in existing technologies is low, resulting in technical problems such as difficulty in timely maintenance of power system failures. Summary of the invention

[0003] The present application provides a method and system for calculating and predicting power faults based on digital twins, which is used to solve the technical problem in the prior art that the prediction accuracy of power system faults is low, resulting in difficulty in timely maintenance of power system faults.

[0004] In view of the above problems, the present application provides a power fault calculation and prediction method and system based on digital twins.

[0005] In the first aspect, the present application provides a method for calculating and predicting power faults based on digital twins, the method comprising: obtaining real-time operating parameters of the power system through the data sensing cloud platform; establishing a digital power twin model based on the real-time operating parameters; extracting historical fault information of the power system, simulating the historical fault information based on the digital power twin model, and generating a power fault simulation data set; calculating and obtaining multiple power fault prediction information based on the power fault simulation data set; using the multiple power fault prediction information to perform predictive analysis of power system operation faults and formulate a power operation scheduling strategy; and operating and maintaining the power system through the power operation scheduling strategy.

[0006] In the second aspect, the present application provides a power fault calculation and prediction system based on digital twins, and the system includes: a first parameter acquisition module, the first parameter acquisition module is used to obtain the real-time operating parameters of the power system through the data sensing cloud platform; a model building module, the model building module is used to establish a digital power twin model based on the real-time operating parameters; a first simulation module, the first simulation module is used to extract historical fault information of the power system, simulate the historical fault information based on the digital power twin model, and generate a power fault simulation data set; a first calculation module, the first calculation module is used to calculate and obtain multiple power fault prediction information based on the power fault simulation data set; a first analysis module, the first analysis module is used to use the multiple power fault prediction information to perform estimated analysis of power system operation failures and formulate power operation scheduling strategies; an operation and maintenance module, the operation and maintenance module is used to perform operation and maintenance on the power system through the power operation scheduling strategy.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The digital twin-based power fault calculation and prediction method and system provided in this application relate to the field of data processing technology. They solve the technical problem in the prior art that the prediction accuracy of power system faults is low, resulting in difficulty in timely maintenance of power system faults. They realize the rational and accurate prediction of faults through digital twin technology, and better operation and maintenance of power systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A flow chart of a power fault calculation and prediction method based on digital twin is provided for this application; Figure 2 A structural schematic diagram of a power fault calculation and prediction system based on digital twins is provided for this application.

[0009] Explanation of the accompanying drawings: first parameter acquisition module 1, model building module 2, first simulation module 3, first calculation module 4, first analysis module 5, operation and maintenance module 6. DETAILED DESCRIPTION

[0010] The present application provides a power fault calculation and prediction method and system based on digital twins to solve the technical problem in the prior art that the prediction accuracy of power system faults is low, resulting in difficulty in timely maintenance of power system faults.

[0011] Embodiment 1

[0012] like Figure 1As shown, an embodiment of the present application provides a power fault calculation prediction method based on digital twins, the method is applied to a power fault calculation prediction system based on digital twins, the power fault calculation prediction system based on digital twins is communicatively connected to a data sensing cloud platform, and the method includes: Step A100: obtaining real-time operating parameters of the power system through the data sensing cloud platform; Furthermore, step A100 of the present application also includes: Step A110: Select multiple sensors and monitoring devices based on the power system structure to build the data sensing cloud platform; Step A120: collecting data of the power system in real time through the data sensing cloud platform to obtain real-time power sensing monitoring data, wherein the real-time power sensing monitoring data includes real-time current monitoring parameters, real-time voltage monitoring parameters, and real-time temperature monitoring parameters; Step A130: clean the real-time current monitoring parameters, the real-time voltage monitoring parameters, and the real-time temperature monitoring parameters in turn, and obtain the real-time operating parameters of the power system through aggregation.

[0013] In the present application, the electric power fault calculation prediction method based on digital twin provided in the embodiment of the present application is applied to the electric power fault calculation prediction system based on digital twin. The electric power fault calculation prediction system based on digital twin is communicated with the data sensor cloud platform. The data sensor cloud platform is used to collect electric power parameters. The data sensor cloud platform selects appropriate sensors and monitoring equipment based on the structure of the electric power system. The sensors and monitoring equipment may include current transformers, voltage transformers, temperature transformers, etc. The sensors and monitoring equipment may perform real-time sensing and monitoring on the real-time current parameters, real-time voltage parameters, and real-time temperature parameters in the electric power system, thereby acquiring the electric power sensor monitoring data of the electric power system, and in the electric power sensor monitoring The measured data includes real-time current monitoring parameters, real-time voltage monitoring parameters, and real-time temperature monitoring parameters. Furthermore, the real-time current monitoring parameters, real-time voltage monitoring parameters, and real-time temperature monitoring parameters are cleaned in turn, which means that the real-time current monitoring parameters, real-time voltage monitoring parameters, and real-time temperature monitoring parameters all contain errors, missing values, duplicates, and inconsistencies. The above problems are solved through data cleaning, and the real-time current monitoring parameters, real-time voltage monitoring parameters, and real-time temperature monitoring parameters are identified and repaired to remove useless data and erroneous data to ensure data quality and consistency. Finally, the cleaned multiple data are aggregated, which means that the data from multiple data sources are integrated into one data source, so as to facilitate the later data analysis and decision-making of the power system, and at the same time obtain the real-time operation parameters of the power system for output, which serves as an important reference for the later calculation and prediction of power failures based on digital twin technology.

[0014] Step A200: Establishing a digital power twin model based on the real-time operating parameters; Furthermore, step A200 of the present application also includes: Step A210: extracting features of the real-time current monitoring parameter, the real-time voltage monitoring parameter, and the real-time temperature monitoring parameter to generate a feature vector set, wherein the feature vector set includes a current feature vector, a voltage feature vector, and a temperature feature vector; Step A220: using the current characteristic vector, the voltage characteristic vector, and the temperature characteristic vector as data labels, correspondingly marking the real-time current monitoring parameters, the real-time voltage monitoring parameters, and the real-time temperature monitoring parameters, and obtaining a plurality of marking results; Step A230: Based on the multiple identification results, supervised training is performed using deep learning. When the training data converges, the construction of the digital power twin model is completed.

[0015] Furthermore, step A343 of the present application includes: Step A221: Update data according to the real-time status of the power system to obtain actual operating parameters; Step A222: obtaining simulation operation parameters through the digital power twin model; Step A223: matching the actual operation parameters and the simulation operation parameters respectively, performing fitness analysis according to the matching results, and obtaining parameter fitness; Step A224: determining whether the parameter fitness is greater than or equal to a preset threshold value; if so, the operation state of the power system is considered to be normal, and a first data label is added, wherein the first data label is 0; Step A225: If it is less than, the operation state of the power system is considered to be abnormal, and a second data tag is added, wherein the second data tag is 1; Step A226: Update the multiple identification results based on the first data tag and the second data tag.

[0016] In this application, in order to better calculate and predict power system faults, it is necessary to construct a digital power twin model through the real-time operating parameters obtained above, which means firstly extracting effective features of real-time current monitoring parameters, real-time voltage monitoring parameters, and real-time temperature monitoring parameters through principal component analysis. In order to reduce the complexity of subsequent calculations, it is necessary to perform data dimensionality reduction on the extracted features, convert high-dimensional feature vectors into low-dimensional feature vectors, so as to obtain a feature vector set, and the feature vector set includes current feature vectors, voltage feature vectors, and temperature feature vectors. Furthermore, the values ​​of the current feature vectors, voltage feature vectors, and temperature feature vectors are respectively corresponded to a data label, and each data label contains the eigenvalue of the corresponding feature vector, so as to The temperature monitoring parameters are marked accordingly, and multiple marking results are obtained on this basis. The multiple marking results include the correlation between the real-time current monitoring parameters, the real-time voltage monitoring parameters, the real-time temperature monitoring parameters and the current characteristic vector, the voltage characteristic vector, and the temperature characteristic vector. Based on the multiple marking results, deep learning is used for supervised training to construct a digital power twin model. The digital power twin model includes an input layer, a hidden layer, and an output layer. The input layer is a layer for data input, the hidden layer is used to better separate the data features, and the output layer is a layer for result output. The digital power twin model is obtained by training with a training data set and a supervision data set. Each group of training data in the training data set includes multiple marking results, and the supervision data set is supervision data that corresponds one to one to the training data set.

[0017] Furthermore, the construction process of the digital power twin model is as follows: each group of training data in the training data set is input into the digital power twin model, and the output supervision adjustment of the digital power twin model is performed through the supervision data corresponding to this group of training data. When the output result of the digital power twin model is consistent with the supervision data, the training of the current group is completed, and when all the training data in the training data set are trained, the training of the digital power twin model is completed.

[0018] In order to ensure the convergence and accuracy of the digital power twin model, its convergence process can be that when the output data in the digital power twin model converges to a point and approaches a certain value, it is considered convergence. Its accuracy can be tested by means of a test data set. For example, the test accuracy can be set to 80%. When the test accuracy of the test data set meets 80%, the digital power twin model is constructed.

[0019] In order to more accurately perform fault monitoring on real-time current monitoring parameters, real-time voltage monitoring parameters, and real-time temperature monitoring parameters through multiple identification results, it is necessary to regularly update multiple identification results. First, the operating data in the power system is synchronously updated with the real-time operating status of the current power system to obtain the real-time operating parameters of the power system. Then, the simulated operating parameters of the power system are output through the digital power twin model. The operating data consistency of the actual operating parameters and the simulated operating parameters are matched respectively. A fitness analysis is performed based on the matching results. The higher the data consistency, the better the fitness. The parameter fitness of the power system is determined. Furthermore, the parameter fitness is compared with a preset threshold value. The preset threshold value is based on the power system in historical time. The operating fitness mean value within the segment is set to determine whether the parameter fitness is greater than or equal to the preset threshold value. If the parameter fitness is greater than or equal to the preset threshold value, the operating state of the power system is deemed to be normal, and a data label is added to the operating state in the power system at this time, which is recorded as the first data label, and the first data label is 0. If the parameter fitness is less than the preset threshold value, the operating state of the power system is deemed to be abnormal, and a data label is added to the operating state in the power system at this time, which is recorded as the second data label, and the second data label is 1. Finally, based on the first data label and the second data label, the data labels in multiple identification results are updated and replaced with corresponding values ​​to ensure their matching with the actual power system and improve the accuracy of the digital power twin model.

[0020] Step A300: extracting historical fault information of the power system, simulating the historical fault information based on the digital power twin model, and generating a power fault simulation data set; Furthermore, step A300 of the present application also includes: Step A310: extracting historical fault information by traversing the historical operation log of the power system; Step A320: setting a fault condition according to the historical fault information; Step A330: introducing the fault condition to simulate the digital power twin model and generate multiple simulation results; Step A340: Analyze the multiple simulation results to generate the power fault simulation data set.

[0021] In the present application, the historical operation log in the power system is extracted, and the historical operation log is used to record the various operating parameters of the power system in the historical time period. On this basis, the fault information recorded in the historical operation log is screened to obtain the historical fault information of the power system. At the same time, the fault conditions of the power system are set according to each power fault condition contained in the historical fault information. Furthermore, the digital power twin model constructed above is simulated based on the set fault conditions, which means that various fault conditions are introduced into the digital power twin model, such as equipment failure, line failure, etc., to simulate the impact of faults under different circumstances on the power system, perform fault simulation and prediction, and generate multiple simulation results, each simulation result corresponds to a fault condition, and finally perform fault analysis on the multiple simulation results to predict the potential probability of fault occurrence and the scope of fault impact, integrate the analysis results and record them as a power fault simulation data set for output, thereby ensuring the realization of computational prediction of power faults based on digital twin technology.

[0022] Step A400: Calculating and acquiring a plurality of power failure prediction information according to the power failure simulation data set; Furthermore, step A400 of the present application also includes: Step A410: Decomposing the power fault simulation data set according to time sequence to determine the running time sequence of the power fault simulation data set; Step A420: extracting multiple fault simulation data in the power fault simulation data set in sequence according to the running time sequence, wherein each fault simulation data in the multiple fault simulation data includes fault node data and fault probability data; Step A430: traverse the association between each fault node and other nodes in the plurality of fault simulation data to determine a plurality of fault-related nodes; Step A440: determining whether there is abnormal data in the plurality of fault-related nodes, and if so, locating the node with abnormal data and extracting abnormal power data; Step A450: Perform fault prediction based on the power abnormality data and the fault probability data of the nodes with abnormal data to generate the multiple power fault prediction information.

[0023] In the present application, in order to more accurately predict the faults of the power system in the future, the fault prediction calculation is performed using the power fault simulation data set generated as above. First, the power fault simulation data set is decomposed according to the operation time sequence of the power system to obtain the power fault simulation data corresponding to each operation moment of the power system. At the same time, the operation time series of the power fault simulation data set is determined. Furthermore, according to the operation time series, multiple fault simulation data contained in the power fault simulation data set are extracted in sequence, and each fault simulation data in the multiple fault simulation data contains fault node data and fault probability data. The fault nodes of each fault simulation data in the multiple fault simulation data are all node positions corresponding to the fault simulation data in the power system, and the fault probability data is in a one-to-one correspondence with the fault node data. The fault probability data is the probability of a fault occurring in the corresponding fault node. Furthermore, Step A430: Each fault node in the multiple fault simulation data is visited and traversed in turn with other nodes, and multiple fault-related nodes are determined according to the correlation between the nodes, wherein the correlation between the multiple fault-related nodes and the fault node is greater than 80%. Furthermore, it is judged whether there are abnormal data in the multiple fault-related nodes, which means that the multiple fault-related nodes that are associated with the fault node may have a fault or not. According to the judgment result, it is determined whether there is a fault in the multiple fault-related nodes. If there is abnormal data in the multiple fault-related nodes, the node is located according to the abnormal data, and the power parameters contained in the node are extracted and recorded as power abnormal data. Finally, based on the power abnormal data and the fault probability data of the node with abnormal data, the fault type and fault probability of the power system are predicted and evaluated, and the evaluation results are output as multiple power fault prediction information, which lays a solid foundation for the subsequent realization of computational prediction of power faults based on digital twin technology.

[0024] Step A500: using the plurality of power fault prediction information to perform an estimation analysis of power system operation faults and formulate a power operation dispatching strategy; Furthermore, step A500 of the present application also includes: Step A510: performing fault matching on the plurality of power fault prediction information according to the power fault data in the big data to generate a fault risk level; Step A520: performing weighted calculation on the plurality of power fault prediction information based on the fault risk level to obtain a fault prediction calculation result; Step A530: Based on the fault prediction calculation result, the risk of operation faults of the power system is predicted to generate power prediction risk information; Step A540: Formulate the power operation dispatch strategy of the power system according to the power forecast risk information.

[0025] In the present application, by using the multiple power fault prediction information determined by the above calculations to perform an estimated analysis of power system operation failures, it means that multiple power fault prediction information are matched with the power fault data in the big data to generate a fault risk level. The fault risk level can be divided according to the indicators for evaluating and classifying the possibility of potential faults in the power system and the degree of impact on the system operation, and can include high risk, medium risk, and low risk. High risk means that the possibility of potential faults is very high, and once a fault occurs, it will have a serious impact on the operation of the power system, and may even cause the system to collapse or power outages. Medium risk means that the possibility of potential faults is high, and it has a certain impact on the operation of the power system, but will not cause a complete collapse of the system or power outages. Low risk means the possibility of potential faults occurring. It is low and has little impact on the operation of the power system, and can be handled through routine maintenance and monitoring. Furthermore, a plurality of power fault prediction information is weighted based on the fault risk level. The weighted calculation of a plurality of power fault prediction information based on the fault risk level can help determine the priority and importance of different faults, thereby providing guidance for fault handling and maintenance plans. First, the weight can be set according to actual conditions and needs. For example, a high risk can be given a higher weight, a medium risk can be given a moderate weight, and a low risk can be given a lower weight. The weight of each fault risk level is determined to reflect its importance in the overall fault prediction. Each fault prediction information in the plurality of power fault prediction information is multiplied by its fault risk level and the corresponding weight to obtain a weighted value recorded as the fault prediction calculation result.Then all weighted values ​​are added together to obtain the final weighted calculation result. Multiple power fault prediction information can include health status monitoring of the power system, fault history records, environmental sensor data, etc. At the same time, the risk prediction of operating faults of the power system is performed according to the weights in the fault prediction calculation results. It means that based on the fault prediction calculation results, the fault prediction calculation results are combined with historical data, equipment status monitoring and other information to evaluate the probability of occurrence of each fault type in the power system. A higher fault probability means that the fault may be more likely to occur in the system. For each fault type, its impact on the operation of the power system is evaluated, and a higher fault impact means that the fault may cause Significant impact, based on statistical analysis, expert judgment or risk matrix, to evaluate and classify the probability and impact of faults, predict the risks of different fault types in the power system to generate power forecast risk information, and further formulate power operation and dispatching strategies for the power system based on the power forecast risk information, which means analyzing the power forecast risk information by analyzing historical fault data, equipment status monitoring data, etc. and determining the risks and probabilities of different power fault types, and then formulating power operation and dispatching strategies based on the power forecast risk information by adjusting generator output, changing the operation mode of transmission lines, adjusting loads, etc., so as to maximize the use of existing resources and ensure the safe and stable operation of the power system.

[0026] Step A600: Performing operation and maintenance on the power system through the power operation dispatching strategy.

[0027] In this application, in accordance with the above-mentioned power operation and dispatching strategy, regular inspection and maintenance of key equipment such as generators, transformers, switchgear, etc. can be carried out on the power system, including cleaning, lubrication, tightening, etc., to complete the inspection and maintenance of equipment in the power system. It is also possible to regularly inspect key equipment, replace aging parts, and formulate preventive maintenance plans based on the service life of the equipment, historical fault data, etc. Preventive maintenance, the monitoring technology deployed in the power system is used to monitor the operating status and health of the power monitoring equipment in real time, promptly detect abnormal conditions of the power system, and take corresponding maintenance measures. At the same time, the operating parameters of the power system, such as voltage, frequency, power factor, etc., are monitored and recorded, and potential operating problems are discovered and resolved in a timely manner by comparing with the equipment rated values. Furthermore, historical data and data analysis technology are used to analyze and optimize the operation and maintenance of the power system, thereby improving the accuracy of the subsequent calculation and prediction of power failures based on digital twin technology.

[0028] To sum up, the digital twin-based power fault calculation and prediction method provided in the embodiment of the present application includes at least the following technical effects, which realizes the rational and accurate prediction of faults through digital twin technology and better operation and maintenance of the power system.

[0029] Embodiment 2

[0030] Based on the same inventive concept as the power fault calculation prediction method based on digital twin in the aforementioned embodiment, Figure 2 As shown, the present application provides a power fault calculation prediction system based on digital twins, the system comprising: A first parameter acquisition module 1, the first parameter acquisition module 1 is used to obtain real-time operating parameters of the power system through the data sensing cloud platform; A model building module 2, wherein the model building module 2 is used to build a digital power twin model based on the real-time operating parameters; A first simulation module 3, wherein the first simulation module 3 is used to extract historical fault information of the power system, simulate the historical fault information based on the digital power twin model, and generate a power fault simulation data set; A first calculation module 4, the first calculation module 4 is used to calculate and obtain multiple power fault prediction information according to the power fault simulation data set; A first analysis module 5, the first analysis module 5 is used to use the plurality of power fault prediction information to perform an estimation analysis of power system operation faults and formulate a power operation dispatching strategy; The operation and maintenance module 6 is used to perform operation and maintenance on the power system through the power operation and scheduling strategy.

[0031] Furthermore, the system also includes: A platform construction module, the platform construction module is used to select a plurality of sensors and monitoring devices based on the power system structure to construct the data sensing cloud platform; A data acquisition module, wherein the data acquisition module is used to collect data of the power system in real time through the data sensing cloud platform to obtain real-time power sensing monitoring data, wherein the real-time power sensing monitoring data includes real-time current monitoring parameters, real-time voltage monitoring parameters, and real-time temperature monitoring parameters; The second parameter acquisition module is used to perform data cleaning on the real-time current monitoring parameters, the real-time voltage monitoring parameters, and the real-time temperature monitoring parameters in turn, and obtain the real-time operating parameters of the power system through aggregation.

[0032] Furthermore, the system also includes: A vector module, the vector module is used to extract features of the real-time current monitoring parameter, the real-time voltage monitoring parameter, and the real-time temperature monitoring parameter to generate a feature vector set, wherein the feature vector set includes a current feature vector, a voltage feature vector, and a temperature feature vector; an identification module, the identification module being used to use the current characteristic vector, the voltage characteristic vector, and the temperature characteristic vector as data labels, to correspondingly identify the real-time current monitoring parameter, the real-time voltage monitoring parameter, and the real-time temperature monitoring parameter, and to obtain a plurality of identification results; A construction module is used to perform supervised training using deep learning based on the multiple identification results, and when the training data converges, the construction of the digital power twin model is completed.

[0033] Furthermore, the system also includes: A first updating module, the first updating module is used to update data according to the real-time status of the power system and obtain actual operating parameters; a third parameter acquisition module, wherein the third parameter acquisition module is used to obtain simulation operation parameters through the digital power twin model; A first matching module, the first matching module is used to match the actual operation parameters and the simulation operation parameters respectively, perform fitness analysis according to the matching results, and obtain parameter fitness; A first judgment module, the first judgment module is used to judge whether the parameter fitness is greater than or equal to a preset threshold value, if it is greater than or equal to, it is considered that the operation state of the power system is normal, and a first data label is added, wherein the first data label is 0; A second judgment module, wherein if , the operating state of the power system is considered to be abnormal, and a second data tag is added, wherein the second data tag is 1; A second updating module, wherein the second updating module is used to update the multiple identification results based on the first data tag and the second data tag.

[0034] Furthermore, the system also includes: A traversal module, the traversal module is used to extract historical fault information by traversing the historical operation log of the power system; A condition setting module, the condition setting module is used to set a fault condition according to the historical fault information; A second simulation module, the second simulation module is used to introduce the fault condition to simulate the digital power twin model and generate multiple simulation results; A second analysis module, wherein the second analysis module is used to analyze the multiple simulation results to generate the power fault simulation data set.

[0035] Furthermore, the system also includes: A decomposition module, the decomposition module is used to decompose the power fault simulation data set according to a time sequence to determine a running time sequence of the power fault simulation data set; A data acquisition module, the data acquisition module is used to extract multiple fault simulation data in the power fault simulation data set in sequence according to the running time sequence, wherein each fault simulation data in the multiple fault simulation data includes fault node data and fault probability data; A node determination module, the node determination module is used to traverse the association between each fault node and other nodes in the multiple fault simulation data to determine multiple fault-related nodes; A third judgment module, the third judgment module is used to judge whether there is abnormal data in the multiple fault-related nodes, and if so, locate the node of the abnormal data and extract the power abnormal data; A fault prediction module is used to perform fault prediction based on the power abnormality data and the fault probability data of the node with abnormal data, and generate the multiple power fault prediction information.

[0036] Furthermore, the system also includes: A second matching module, the second matching module is used to perform fault matching on the plurality of power fault prediction information according to the power fault data in the big data to generate a fault risk level; A second calculation module, the second calculation module is used to perform weighted calculation on the multiple power fault prediction information based on the fault risk level to obtain a fault prediction calculation result; A risk prediction module, the risk prediction module is used to predict the risk of operation failure of the power system based on the fault prediction calculation result, and generate power prediction risk information; A strategy formulation module, wherein the strategy formulation module is used to formulate the power operation dispatching strategy of the power system according to the power forecast risk information.

[0037] Through the above-mentioned detailed description of the power fault calculation and prediction method based on digital twins in this specification, those skilled in the art can clearly know the power fault calculation and prediction system based on digital twins in this embodiment. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0038] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A power fault calculation and prediction method based on digital twins, characterized in that: The method is applied to a power fault calculation prediction system based on digital twins, wherein the power fault calculation prediction system based on digital twins is communicatively connected to a data sensing cloud platform, and the method comprises: Acquire real-time operating parameters of the power system through the data sensing cloud platform; Establishing a digital power twin model based on the real-time operating parameters; Extracting historical fault information of the power system, simulating the historical fault information based on the digital power twin model, and generating a power fault simulation data set; Calculate and obtain multiple power failure prediction information according to the power failure simulation data set; Using the plurality of power fault prediction information to perform prediction analysis of power system operation faults and formulate power operation dispatching strategies; The power system is operated and maintained through the power operation dispatching strategy.

2. The method according to claim 1, characterized in that The real-time operating parameters of the power system are obtained through the data sensing cloud platform, and the method includes: Select multiple sensors and monitoring equipment based on the power system structure to build the data sensing cloud platform; The data sensing cloud platform is used to collect data of the power system in real time to obtain real-time power sensing monitoring data, wherein the real-time power sensing monitoring data includes real-time current monitoring parameters, real-time voltage monitoring parameters, and real-time temperature monitoring parameters; The real-time current monitoring parameters, the real-time voltage monitoring parameters, and the real-time temperature monitoring parameters are cleaned in turn, and the real-time operation parameters of the power system are obtained through aggregation.

3. The method according to claim 2, characterized in that A digital power twin model is established based on the real-time operating parameters, and the method includes: Performing feature extraction on the real-time current monitoring parameter, the real-time voltage monitoring parameter, and the real-time temperature monitoring parameter to generate a feature vector set, wherein the feature vector set includes a current feature vector, a voltage feature vector, and a temperature feature vector; The current characteristic vector, the voltage characteristic vector, and the temperature characteristic vector are used as data labels to correspondingly identify the real-time current monitoring parameters, the real-time voltage monitoring parameters, and the real-time temperature monitoring parameters to obtain multiple identification results; Based on the multiple identification results, deep learning is used for supervised training, and when the training data converges, the construction of the digital power twin model is completed.

4. The method according to claim 3, characterized in that Methods include: Update data based on the real-time status of the power system to obtain actual operating parameters; Obtaining simulation operation parameters through the digital power twin model; Matching the actual operating parameters and the simulation operating parameters respectively, performing fitness analysis according to the matching results, and obtaining parameter fitness; Determine whether the parameter fitness is greater than or equal to a preset threshold value. If so, the operation state of the power system is considered to be normal, and a first data label is added, wherein the first data label is 0; If it is less than, the operation state of the power system is considered to be abnormal, and a second data tag is added, wherein the second data tag is 1; The plurality of identification results are updated based on the first data tag and the second data tag.

5. The method according to claim 1, characterized in that Extracting historical fault information of the power system, simulating the historical fault information based on the digital power twin model, and generating a power fault simulation data set, the method comprising: By traversing the historical operation logs of the power system, historical fault information can be extracted; Setting a fault condition according to the historical fault information; Introducing the fault condition to simulate the digital power twin model and generate multiple simulation results; The multiple simulation results are analyzed to generate the power fault simulation data set.

6. The method according to claim 1, characterized in that The method for calculating and obtaining a plurality of power failure prediction information according to the power failure simulation data set includes: Decomposing the power failure simulation data set according to time sequence to determine the running time sequence of the power failure simulation data set; According to the running time sequence, sequentially extract multiple fault simulation data in the power fault simulation data set, wherein each fault simulation data in the multiple fault simulation data includes fault node data and fault probability data; Traversing the correlation between each fault node and other nodes in the plurality of fault simulation data to determine a plurality of fault-related nodes; Determine whether there is abnormal data in the multiple fault-related nodes, and if so, locate the node with abnormal data and extract the abnormal power data; Fault prediction is performed based on the power abnormality data and the fault probability data of the node with abnormal data to generate the plurality of power fault prediction information.

7. The method according to claim 1, characterized in that The plurality of power fault prediction information are used to perform an estimation analysis of power system operation faults and formulate a power operation dispatching strategy, the method comprising: Perform fault matching on the plurality of power fault prediction information according to the power fault data in the big data to generate a fault risk level; Performing weighted calculation on the plurality of power fault prediction information based on the fault risk level to obtain a fault prediction calculation result; Based on the fault prediction calculation results, the risk of operating faults in the power system is predicted to generate power prediction risk information; The power operation dispatching strategy of the power system is formulated according to the power forecast risk information.

8. The power fault calculation and prediction system based on digital twin is characterized by: The digital twin-based power fault calculation and prediction system is communicatively connected to the data sensing cloud platform, and the system includes: A first parameter acquisition module, the first parameter acquisition module is used to obtain real-time operating parameters of the power system through the data sensing cloud platform; A model building module, wherein the model building module is used to build a digital power twin model based on the real-time operating parameters; A first simulation module, wherein the first simulation module is used to extract historical fault information of the power system, simulate the historical fault information based on the digital power twin model, and generate a power fault simulation data set; A first calculation module, the first calculation module is used to calculate and obtain multiple power fault prediction information according to the power fault simulation data set; A first analysis module, the first analysis module is used to use the plurality of power fault prediction information to perform an estimation analysis of power system operation faults and formulate a power operation dispatching strategy; An operation and maintenance module, wherein the operation and maintenance module is used to perform operation and maintenance on the power system through the power operation and scheduling strategy.

Images