Early warning method and device for electrified area of transformer substation

Abstract

The invention discloses an early warning method and device for a live area of a transformer substation, and relates to the technical field of electric power, in particular to the technical field of transformer substations. The method comprises the following steps: acquiring target data of a live area of a transformer substation; monitoring the electrified area of the transformer substation based on the digital twin model and the target data to obtain a monitoring result; and performing fault early warning according to a monitoring result. The technical problem of low safety of the electrified area of the transformer substation caused by maintenance of the transformer substation based on manual inspection and simple monitoring equipment in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, in particular to the field of substation technology, and specifically to an early warning method and device for a live area of ​​a substation. Background Art

[0002] With the development of modern power systems, substations, as the core hub of power transmission and distribution, play a vital role in the stable operation of the entire power grid in terms of safety and reliability. In substations, since the live areas of substations have the characteristics of high voltage and high current, there are great safety risks in the live areas of substations. Therefore, effective safety warning and fault diagnosis of live areas of substations can not only ensure the stable operation of the power system, but also reduce potential safety risks, which is of great practical significance.

[0003] However, traditional substation operation and maintenance mainly rely on regular manual inspections and simple monitoring equipment. Although this method can detect problems to a certain extent, it is unable to meet the modern power system's requirements for high efficiency and high safety due to its large workload, low efficiency, and inability to monitor and warn of potential faults and anomalies in real time.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The present application provides an early warning method and device for a live area of ​​a substation, so as to at least solve the technical problem in the prior art that maintenance of the substation based on manual inspection and simple monitoring equipment leads to low safety of the live area of ​​the substation.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, an early warning method for a live area of ​​a substation is provided, comprising: obtaining target data of the live area of ​​the substation, wherein the target data includes at least real-time data, historical data, geographic data and equipment status data of the live area of ​​the substation, wherein the real-time data includes at least equipment data and environmental parameters of the live area of ​​the substation at the current moment, and the historical data includes at least equipment data, environmental parameters and fault data of the live area of ​​the substation at historical moments; monitoring the live area of ​​the substation based on a digital twin model and target data to obtain monitoring results, wherein the digital twin model is a virtual model for characterizing the electrical characteristics, physical characteristics, live level and safety distance of internal equipment of the substation and the live area of ​​the substation; and performing fault early warning according to the monitoring results.

[0007] Optionally, the live area of ​​the substation is monitored based on the digital twin model and target data to obtain monitoring results, including: obtaining a state monitoring function, wherein the state monitoring function is used to determine the state change information of preset key parameters of the live area of ​​the substation through an attention mechanism; determining the monitoring results of the live area of ​​the substation according to the digital twin model, target data and the state monitoring function.

[0008] Optionally, a fault warning is performed based on the monitoring results, including: detecting whether the monitoring result is greater than a preset threshold; generating a first prompt message when the monitoring result is greater than the preset threshold, wherein the first prompt message is used to prompt that a fault has occurred in the energized area of ​​the substation; generating a second prompt message when the monitoring result is less than or equal to the preset threshold, wherein the second prompt message is used to indicate that no fault has occurred in the energized area of ​​the substation.

[0009] Optionally, after fault warning is performed according to the monitoring results, the warning method for the live area of ​​the substation also includes: when it is determined according to the monitoring results that a fault occurs in the live area of ​​the substation, obtaining a fault diagnosis function and a fault characteristic, wherein the fault diagnosis function is used to determine the fault state of the live area of ​​the substation, and the fault characteristic includes a first characteristic and a second characteristic, wherein the first characteristic is used to characterize the physical characteristics and operating laws of the live area of ​​the substation when a fault occurs, and the second characteristic is used to characterize the abnormal data characteristics generated when a fault occurs in the live area of ​​the substation based on a deep learning method and / or a machine learning method; determining fault diagnosis information according to the monitoring results, the fault diagnosis function and the fault characteristic, wherein the fault diagnosis information includes at least the cause of the fault and the fault location of the live area of ​​the substation.

[0010] Optionally, after obtaining the target data of the live area of ​​the substation, the early warning method for the live area of ​​the substation also includes: obtaining a prediction function for the live area of ​​the substation, wherein the prediction function is used to predict the state of the live area of ​​the substation in a future time period; and determining the prediction result based on the prediction function, the digital twin model and the target data.

[0011] Optionally, after determining the prediction results according to the prediction function, the digital twin model and the target data, the early warning method for the live area of ​​the substation also includes: determining the maintenance strategy for the live area of ​​the substation according to the prediction results, wherein the maintenance strategy is used to adjust the live area of ​​the substation according to the status of the live area of ​​the substation; obtaining the correlation between each device in the substation and the maintenance strategy, wherein the correlation is used to characterize the degree of adaptation between each device and the maintenance strategy; determining the target strategy for each device according to the correlation, wherein the target strategy for each device is used to set operations for the device when adjusting the live area of ​​the substation.

[0012] Optionally, after determining the target scheme for each device according to the correlation, the early warning method for the energized area of ​​the substation also includes: performing a simulation test of the early warning operation on the digital twin model, wherein the simulation test includes at least a simulation simulation test and an augmented reality simulation test.

[0013] Optionally, the digital twin model is obtained through the following steps: obtaining the physical characteristics of the live area of ​​the substation, wherein the physical characteristics include at least the topological structure, electrical characteristics, and equipment parameters of the live area of ​​the substation; constructing an initial digital twin model based on the target data and the physical characteristics; using historical data of a first historical time period as training samples; using fault data of a second historical time period as training labels, wherein the second historical time period is after the first historical time period; iteratively training the initial digital twin model based on the training samples and training labels to obtain a digital twin model.

[0014] According to another aspect of the present application, an early warning device for a live area of ​​a substation is also provided, including: a first acquisition unit, which acquires target data of the live area of ​​the substation, wherein the target data includes at least real-time data, historical data, geographic data, and equipment status data of the live area of ​​the substation, wherein the real-time data includes at least equipment data and environmental parameters of the live area of ​​the substation at the current moment, and the historical data includes at least equipment data, environmental parameters, and fault data of the live area of ​​the substation at historical moments; a first processing unit, which monitors the live area of ​​the substation based on a digital twin model and target data to obtain monitoring results, wherein the digital twin model is a virtual model for characterizing the electrical characteristics, physical characteristics, live level, and safety distance of internal equipment of the substation and the live area of ​​the substation; a second processing unit, which performs fault early warning according to the monitoring results.

[0015] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned early warning method for the energized area of ​​the substation.

[0016] In the present application, by acquiring target data of the live area of ​​the substation, and then using the trained digital twin model to monitor the live area of ​​the substation in real time, and then obtaining the monitoring results of the live area of ​​the substation based on the digital twin model and the target data, and finally issuing early warnings for faults in the live area of ​​the substation based on the monitoring results, the purpose of real-time monitoring of the live area of ​​the substation and timely early warning of faults is achieved, thereby achieving the technical effect of improving the safety of the live area of ​​the substation, and further solving the technical problem in the prior art of maintaining the substation based on manual inspections and simple monitoring equipment, resulting in low safety of the live area of ​​the substation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a flow chart of an optional early warning method for a live area of ​​a substation according to an embodiment of the present application;

[0019] Figure 2 It is a schematic diagram of an optional early warning device for a live area of ​​a substation according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] It should also be noted that the information and data collected by this application are authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation portals for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or institution through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or institution.

[0023] According to an embodiment of the present application, an embodiment of an early warning method for a live area of ​​a substation is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0024] It should be noted that an intelligent early warning system is used as the execution subject of the early warning method for the live area of ​​the substation in the embodiment of the present application. It is understandable that the early warning method for the live area of ​​the substation provided in the embodiment of the present application can also be executed by other systems or devices, and the embodiment of the present application does not specifically limit this.

[0025] Figure 1 is a flow chart of an optional early warning method for a live area of ​​a substation according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0026] Step S101, obtaining target data of the energized area of ​​the substation.

[0027] In step S101 , the target data includes at least real-time data, historical data, geographic data and equipment status data of the energized area of ​​the substation.

[0028] In step S101, the real-time data includes at least the equipment data and environmental parameters of the live area of ​​the substation at the current moment, and the historical data includes at least the equipment data, environmental parameters and fault data of the live area of ​​the substation at historical moments.

[0029] Optionally, the real-time data may also include voltage, current, safety distance, and equipment live level in the live area of ​​the substation.

[0030] Optionally, the intelligent early warning system collects real-time data of the live area of ​​the substation through sensors and intelligent devices, especially focusing on the status monitoring of key equipment. The collected real-time data is shown in formula (1):

[0031] D t ={(v i (t),i i (t),T i (t),S i (t),L i ,D i )|i=1,2,…,N}(1)

[0032] Among them, D t is the set of all real-time data collected at time t, v i (t) is the voltage of the i-th node, ii (t) is the current of the ith node, T i (t) is the temperature of the ith node, S i (t) is the device status of the ith node, L i is the charge level of the ith node, D i is the safety distance of the ith node, and N is the total number of nodes. The nodes represent the following: various devices in the substation, various connection points, such as the interface between the substation and the transmission line, or other key locations that need to be monitored.

[0033] Optionally, the historical data may also include historical voltage data, historical current data, and historical maintenance records.

[0034] Step S102: monitor the energized area of ​​the substation based on the digital twin model and target data to obtain monitoring results.

[0035] In step S102, the digital twin model is a virtual model used to characterize the electrical characteristics, physical characteristics, live level and safety distance of the internal equipment of the substation and the live area of ​​the substation.

[0036] Optionally, the digital twin model is a virtual model of the substation formed by virtual mapping of the physical entity of the substation. It integrates technologies such as artificial intelligence and machine learning. It can monitor the operating status of the substation in real time by monitoring the changes in the virtual model, and can also warn of potential faults and risks.

[0037] Step S103: issue a fault warning based on the monitoring result.

[0038] Optionally, the intelligent early warning system monitors the energized area of ​​the substation through a digital twin model, obtains monitoring results, and determines whether an early warning is needed based on analysis of the monitoring results.

[0039] It can be seen from the contents of steps S101 to S103 that in the present application, the intelligent early warning system first obtains the target data of the live area of ​​the substation, wherein the target data includes at least the real-time data, historical data, geographic data and equipment status data of the live area of ​​the substation, wherein the real-time data includes at least the equipment data and environmental parameters of the live area of ​​the substation at the current moment, and the historical data includes at least the equipment data, environmental parameters and fault data of the live area of ​​the substation at historical moments, and then the live area of ​​the substation is monitored based on the digital twin model and the target data to obtain the monitoring results, wherein the digital twin model is a virtual model used to characterize the electrical characteristics, physical characteristics, live level and safety distance of the internal equipment of the substation and the live area of ​​the substation, and finally a fault warning is performed according to the monitoring results.

[0040] It can be seen from the above content that in the embodiment of the present application, by acquiring the target data of the live area of ​​the substation, and then using the trained digital twin model to monitor the live area of ​​the substation in real time, and then obtaining the monitoring results of the live area of ​​the substation based on the digital twin model and the target data, and finally warning of faults in the live area of ​​the substation based on the monitoring results, the purpose of real-time monitoring of the live area of ​​the substation and timely warning of faults is achieved, thereby achieving the technical effect of improving the safety of the live area of ​​the substation, and further solving the technical problem of low safety of the live area of ​​the substation due to maintenance of the substation based on manual inspections and simple monitoring equipment in the prior art.

[0041] In an optional embodiment, the intelligent early warning system first obtains a state monitoring function, wherein the state monitoring function is used to determine the state change information of preset key parameters of the energized area of ​​the substation through an attention mechanism, and then determines the monitoring results of the energized area of ​​the substation based on the digital twin model, target data and the state monitoring function.

[0042] Optionally, the intelligent early warning system obtains the state monitoring function g(·), and then determines the monitoring result of the live area of ​​the substation according to the digital twin model, the target data and the state monitoring function. The monitoring result S t The calculation method of is shown in formula (2):

[0043] S t =g(M,I t )(2)

[0044] Among them, S t is the condition monitoring result, g(·) is the condition monitoring function, M is the digital twin model, I t is the target data.

[0045] Optionally, the specific form of the state monitoring function g(·) is implemented based on a deep learning model of the attention mechanism. t , then use convolutional neural network or long short-term memory network to extract time series features in the feature extraction layer, and then combine the attention mechanism in the attention mechanism layer to calculate the weight of each time series feature to improve the attention of key features. Finally, the extracted features are input into the fully connected layer for comprehensive processing and output the status monitoring results.

[0046] From the above content, it can be seen that the intelligent early warning system obtains the monitoring results of the energized area of ​​the substation through the digital twin model, target data and status monitoring function. Among them, the monitoring function is implemented by a deep learning model based on the attention mechanism. The deep learning model of the attention mechanism can improve the monitoring accuracy of the status of key equipment in the substation and provide reliable monitoring result data for subsequent early warnings.

[0047] In an optional embodiment, the intelligent early warning system first detects whether the monitoring result is greater than a preset threshold value, and generates a first prompt message when the monitoring result is greater than the preset threshold value, wherein the first prompt message is used to indicate that a fault has occurred in the energized area of ​​the substation, and generates a second prompt message when the monitoring result is less than or equal to the preset threshold value, wherein the second prompt message is used to indicate that no fault has occurred in the energized area of ​​the substation.

[0048] Optionally, the intelligent early warning system sets an early warning threshold for the live area of ​​the substation. When the monitoring data exceeds the normal range, an alarm is automatically triggered and a detailed alarm report is generated, as shown in formula (3):

[0049]

[0050] Among them, A t It is an alarm signal, 1 means alarm, 0 means normal, S t is the status monitoring result, and T is the warning threshold of the energized area of ​​the substation.

[0051] Optionally, the warning threshold can be combined with a deep learning model of the attention mechanism to dynamically adjust the warning threshold.

[0052] From the above content, it can be seen that the intelligent early warning system determines whether an early warning is needed based on the comparison results between the monitoring results and the preset threshold. The preset threshold is dynamically adjusted using a deep learning model with an attention mechanism. By dynamically updating the preset threshold, the accuracy and timeliness of the early warning can be improved.

[0053] In an optional embodiment, when the intelligent early warning system determines that a fault occurs in the live area of ​​the substation based on the monitoring results, it obtains a fault diagnosis function and a fault characteristic, wherein the fault diagnosis function is used to determine the fault state of the live area of ​​the substation, and the fault characteristic includes a first characteristic and a second characteristic, wherein the first characteristic is used to characterize the physical characteristics and operating laws of the live area of ​​the substation when a fault occurs, and the second characteristic is used to characterize the abnormal data characteristics generated when a fault occurs in the live area of ​​the substation based on deep learning and / or machine learning methods, and then the fault diagnosis information is determined based on the monitoring results, the fault diagnosis function and the fault characteristics, wherein the fault diagnosis information includes at least the cause and location of the fault in the live area of ​​the substation.

[0054] Optionally, the specific form of the fault diagnosis function is implemented based on a hybrid model, which is composed of a physical model and a deep learning model based on an attention mechanism. The physical model is based on the physical characteristics and operating laws of the power system to form a rule-based fault diagnosis model. The deep learning model based on the attention mechanism is a model that uses the attention mechanism to improve the ability to recognize complex fault modes by weighted processing of historical fault data and real-time data.

[0055] Optionally, the specific steps of obtaining fault diagnosis information through the fault diagnosis function h(·) are as follows: first, the state monitoring result S is received at the input layer t , fault feature B based on the physical model, and fault feature L based on machine learning and deep learning. Among them, the extraction of fault feature B is based on the physical characteristics and operating rules of the power system, and the fault feature L is obtained by extracting the features of historical fault data and real-time data through the deep learning model. In the extraction process, the attention mechanism is used to improve the recognition ability of complex fault modes. Finally, the physical model features and deep learning model features are fused in the fusion layer, input to the fully connected layer for comprehensive processing, and output fault diagnosis information.

[0056] Optionally, the intelligent early warning system obtains a fault diagnosis function, and determines fault diagnosis information based on the monitoring result, the fault diagnosis function and the fault characteristics. The calculation method of the fault diagnosis information is shown in formula (4):

[0057] F t =h(S t ,B,L)(4)

[0058] Among them, F t is the fault diagnosis result, h(·) is the fault diagnosis function, S t is the condition monitoring result, B is the fault feature based on the physical model, and L is the fault feature based on machine learning and deep learning.

[0059] Optionally, the self-learning module in the intelligent early warning system can learn and self-optimize by continuously receiving and analyzing new fault data and automatically adjusting the parameters of the model using an online learning algorithm to improve the accuracy and adaptability of fault diagnosis.

[0060] Optionally, the intelligent early warning system can use a fault location algorithm based on a graph neural network to handle the complex network structure of the substation system.

[0061] From the above content, it can be seen that the fault diagnosis function designed based on the hybrid model can improve the accuracy and efficiency of fault diagnosis, and combines machine learning and deep learning algorithms to perform fault diagnosis on the energized area of ​​the substation, thereby improving the accuracy of fault diagnosis. Finally, based on the fault diagnosis information, important information such as the faulty equipment, fault cause, and fault location can be accurately obtained, helping relevant personnel to quickly find the fault point for maintenance.

[0062] In an optional embodiment, the intelligent early warning system obtains a prediction function of the energized area of ​​the substation, wherein the prediction function is used to predict the state of the energized area of ​​the substation in a future time period, and then determines the prediction result based on the prediction function, the digital twin model and the target data.

[0063] Optionally, the prediction results include, but are not limited to, load change information, equipment aging degree, and possibility of failure.

[0064] Optionally, the specific form of the prediction function p(·) can be implemented using a spatiotemporal convolutional neural network and a federated learning framework. First, the digital twin model M and the target data I are received at the input layer. t ,Then the spatiotemporal convolutional neural network is used in the spatiotemporal convolutional layer to extract the temporal and spatial features, and then the federated learning framework is used to make joint predictions in the multi-regional power system, and finally the extracted features are input into the fully connected layer for comprehensive processing, and the prediction results are output.

[0065] Optionally, the spatiotemporal convolutional neural network model can process time series data and spatial data simultaneously, accurately capture the spatiotemporal dynamic changes of the power system, and can consider the spatiotemporal correlation between nodes in the power system to improve the accuracy of the prediction.

[0066] Optionally, the federated learning framework can realize the joint prediction of multi-regional power systems, which can improve the prediction accuracy while protecting data privacy. The federated learning framework allows each region to train the model locally, and can only share the model parameters without transmitting the original data, thereby ensuring data privacy and security.

[0067] Optionally, the prediction result is calculated as shown in formula (5):

[0068] P t =p(M,I t )(5)

[0069] Among them, P t is the prediction result, p(·) is the prediction function of the substation live area, M is the digital twin model, and I t is the target data.

[0070] From the above content, it can be seen that based on the substation digital twin model, prediction function and target data, trend analysis and prediction of the live area of ​​the substation can be carried out, the future equipment aging degree and possible failures can be estimated, and the safety of the live area of ​​the substation can be improved. At the same time, the prediction model using the spatiotemporal convolutional neural network can improve the accuracy of the prediction results and provide reliable data for subsequent maintenance strategies.

[0071] In an optional embodiment, the intelligent early warning system determines a maintenance strategy for the live area of ​​the substation based on the prediction results, wherein the maintenance strategy is used to adjust the live area of ​​the substation based on the status of the live area of ​​the substation, and then obtains the correlation between each device in the substation and the maintenance strategy, wherein the correlation is used to characterize the degree of adaptation between each device and the maintenance strategy, and finally determines a target strategy for each device based on the correlation, wherein the target strategy for each device is used to set operations for the device when adjusting the live area of ​​the substation.

[0072] Optionally, a preventive maintenance strategy generation algorithm based on game theory considers the mutual influence between different equipment and maintenance strategies to optimize the overall maintenance effect, and the strategy generation algorithm based on game theory can find the best solution among multiple maintenance strategies to balance maintenance cost and system reliability.

[0073] Optionally, the intelligent early warning system uses blockchain technology to record detailed data of each maintenance, ensuring the transparency and non-tamperability of the data and providing a reference for future maintenance decisions.

[0074] From the above content, it can be seen that the intelligent early warning system formulates a preliminary preventive maintenance strategy based on the substation prediction results, and then uses the game theory preventive maintenance strategy generation algorithm to consider the mutual influence between different equipment and maintenance strategies, and selects the optimal maintenance strategy for each equipment in the live area of ​​the substation, which can significantly improve the operation and maintenance efficiency and safety of the live area of ​​the substation.

[0075] In an optional embodiment, the intelligent early warning system performs a simulation test of the early warning operation on the digital twin model, wherein the simulation test includes at least a simulation test and an augmented reality simulation test.

[0076] Optionally, the intelligent early warning system uses the digital twin model of the live area of ​​the substation to conduct simulation drills of safety early warning operations to verify the feasibility and effectiveness of the safety early warning plan, and uses augmented reality technology to assist in the simulation drills, providing relevant personnel with real-time visual operation guidance for the live area of ​​the substation, thereby improving the effectiveness and efficiency of the early warning drills.

[0077] From the above content, it can be seen that the intelligent early warning system can verify the feasibility of the early warning by conducting simulation tests and augmented reality simulation tests of the early warning operation of the digital twin model to ensure the effectiveness and accuracy of the digital twin model in practical applications. Moreover, the comprehensive application of these two simulation test methods can improve the reliability of the intelligent early warning system.

[0078] In an optional embodiment, the intelligent early warning system obtains the physical characteristics of the live area of ​​the substation, wherein the physical characteristics include at least the topological structure, electrical characteristics, and equipment parameters of the live area of ​​the substation, and then constructs an initial digital twin model based on the target data and the physical characteristics. Then, the historical data of the first historical time period is used as training samples, and the fault data of the second historical time period is used as training labels, wherein the second historical time period is after the first historical time period. Finally, the initial digital twin model is iteratively trained based on the training samples and training labels to obtain a digital twin model.

[0079] Optionally, the intelligent early warning system builds a digital twin model of the substation based on the collected data of the live area of ​​the substation, covering the real-time data of the internal equipment and area of ​​the substation, the physical characteristics of the historical data, etc. The construction of the initial digital twin model is shown in formula (6):

[0080] M=f(D t ,H,P)(6)

[0081] Among them, M is the digital twin model, D t is real-time data, H is historical data, and P is physical characteristics.

[0082] Optionally, the electrical characteristics, geographic data, equipment status data, live level, and safety distance of the substation's energized area are integrated into the initial digital twin model to ensure the accuracy and completeness of the substation model, with special attention paid to the integration of equipment health status and historical fault data.

[0083] Optionally, the intelligent early warning system uses the historical data of the first historical time period as training samples and the fault data of the second historical time period as training labels, and finally iteratively trains the initial digital twin model according to the training samples and training labels to obtain the final digital twin model.

[0084] Optionally, the operation and maintenance data and experience of the energized area of ​​the substation can be fed back into the digital twin model to continuously optimize the accuracy and reliability of the model and improve the effectiveness of early warning and maintenance.

[0085] From the above content, it can be seen that by integrating multi-source data of the energized area of ​​the substation into the digital twin model, the model covers the electrical and physical characteristics of the internal equipment and areas of the substation, which can ensure the comprehensiveness and accuracy of the data, and continuously optimize the model by training historical data, the accuracy of the model prediction can be improved.

[0086] According to an embodiment of the present application, an embodiment of an early warning device for a live area of ​​a substation is also provided. Figure 2 is a schematic diagram of an optional early warning device for a live area of ​​a substation according to an embodiment of the present application, such as Figure 2 As shown, the early warning device for the live area of ​​the substation includes: a first acquisition unit 201, a first processing unit 202, and a second processing unit 203.

[0087] Optionally, the first acquisition unit 201 is used to acquire target data of the live area of ​​the substation, wherein the target data includes at least real-time data, historical data, geographic data and equipment status data of the live area of ​​the substation, wherein the real-time data includes at least equipment data and environmental parameters of the live area of ​​the substation at the current moment, and the historical data includes at least equipment data, environmental parameters and fault data of the live area of ​​the substation at historical moments; the first processing unit 202 is used to monitor the live area of ​​the substation based on the digital twin model and the target data to obtain monitoring results, wherein the digital twin model is a virtual model used to characterize the electrical characteristics, physical characteristics, live level and safety distance of the internal equipment of the substation and the live area of ​​the substation; the second processing unit 203 is used to provide fault warning based on the monitoring results.

[0088] Optionally, the first processing unit 202 includes: a first acquisition subunit and a first determination subunit. The first acquisition subunit is used to acquire a state monitoring function, wherein the state monitoring function is used to determine the state change information of the preset key parameters of the live area of ​​the substation through the attention mechanism; the first determination subunit is used to determine the monitoring result of the live area of ​​the substation according to the digital twin model, the target data and the state monitoring function.

[0089] Optionally, the second processing unit 203 includes: a first detection subunit, a first generation subunit, and a second generation subunit. The first detection subunit is used to detect whether the monitoring result is greater than a preset threshold; the first generation subunit is used to generate a first prompt message when the monitoring result is greater than the preset threshold, wherein the first prompt message is used to prompt that a fault occurs in the live area of ​​the substation; the second generation subunit is used to generate a second prompt message when the monitoring result is less than or equal to the preset threshold, wherein the second prompt message is used to indicate that no fault occurs in the live area of ​​the substation.

[0090] Optionally, the second processing unit 203 includes: a second acquisition subunit and a second determination subunit. The second acquisition subunit is used to obtain a fault diagnosis function and a fault feature when it is determined that a fault occurs in the live area of ​​the substation according to the monitoring results, wherein the fault diagnosis function is used to determine the fault state of the live area of ​​the substation, and the fault feature includes a first feature and a second feature, wherein the first feature is used to characterize the physical characteristics and operating rules of the live area of ​​the substation when a fault occurs, and the second feature is used to characterize the abnormal data features generated when a fault occurs in the live area of ​​the substation based on a deep learning method and / or a machine learning method; the second determination subunit is used to determine the fault diagnosis information according to the monitoring results, the fault diagnosis function and the fault feature, wherein the fault diagnosis information includes at least the fault cause and the fault location of the live area of ​​the substation.

[0091] Optionally, the first acquisition unit 201 includes: a third acquisition subunit and a third determination subunit. The third acquisition subunit is used to acquire a prediction function of the live area of ​​the substation, wherein the prediction function is used to predict the state of the live area of ​​the substation in a future time period; and the third determination subunit is used to determine the prediction result according to the prediction function, the digital twin model and the target data.

[0092] Optionally, the third determination subunit includes: a first determination module, a first acquisition module, and a second determination module. The first determination module is used to determine the maintenance strategy of the live area of ​​the substation according to the prediction result, wherein the maintenance strategy is used to adjust the live area of ​​the substation according to the state of the live area of ​​the substation; the first acquisition module is used to obtain the correlation between each device in the substation and the maintenance strategy, wherein the correlation is used to characterize the degree of adaptation between each device and the maintenance strategy; the second determination module is used to determine the target strategy of each device according to the correlation, wherein the target strategy of each device is used to set the operation for the device when adjusting the live area of ​​the substation.

[0093] Optionally, the second determination module includes: a first testing submodule, used to perform simulation testing of early warning operations on the digital twin model, wherein the simulation testing includes at least simulation testing and augmented reality simulation testing.

[0094] Optionally, the first processing unit 202 includes: a fourth acquisition subunit, a first construction subunit, a fourth determination subunit, a fifth determination subunit and a first processing subunit. The fourth acquisition subunit is used to acquire the physical characteristics of the live area of ​​the substation, wherein the physical characteristics at least include the topological structure, electrical characteristics, and equipment parameters of the live area of ​​the substation; the first construction subunit is used to build an initial digital twin model according to the target data and the physical characteristics; the fourth determination subunit is used to use the historical data of the first historical time period as a training sample; the fifth determination subunit is used to use the fault data of the second historical time period as a training label, wherein the second historical time period is after the first historical time period; the first processing subunit is used to iteratively train the initial digital twin model according to the training samples and the training labels to obtain the digital twin model.

[0095] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned early warning method for the energized area of ​​the substation.

[0096] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0097] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0098] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0100] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0101] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0102] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An early warning method for live areas of a substation, characterized in that: include: Acquire target data of the live area of ​​the substation, wherein the target data at least includes real-time data, historical data, geographic data and equipment status data of the live area of ​​the substation, wherein the real-time data at least includes equipment data and environmental parameters of the live area of ​​the substation at the current moment, and the historical data at least includes equipment data, environmental parameters and fault data of the live area of ​​the substation at historical moments; Based on the digital twin model and the target data, the live area of ​​the substation is monitored to obtain monitoring results, wherein the digital twin model is a virtual model for characterizing the electrical characteristics, physical characteristics, live level and safety distance of the internal equipment of the substation and the live area of ​​the substation; A fault warning is performed according to the monitoring result.

2. The early warning method for live areas of substations according to claim 1, characterized in that: Based on the digital twin model and the target data, the live area of ​​the substation is monitored to obtain monitoring results, including: Acquire a state monitoring function, wherein the state monitoring function is used to determine state change information of preset key parameters of the live area of ​​the substation through an attention mechanism; The monitoring result of the energized area of ​​the substation is determined according to the digital twin model, the target data and the state monitoring function.

3. The early warning method for live areas of substations according to claim 1, characterized in that: Providing fault warning according to the monitoring results includes: Detecting whether the monitoring result is greater than a preset threshold; When the monitoring result is greater than the preset threshold, generating first prompt information, wherein the first prompt information is used to prompt that a fault occurs in the energized area of ​​the substation; When the monitoring result is less than or equal to the preset threshold, a second prompt information is generated, wherein the second prompt information is used to indicate that no fault occurs in the energized area of ​​the substation.

4. The early warning method for live areas of substations according to claim 1, characterized in that: After the fault warning is performed according to the monitoring result, the early warning method for the live area of ​​the substation further includes: In the case where it is determined according to the monitoring result that a fault occurs in the live area of ​​the substation, a fault diagnosis function and a fault feature are obtained, wherein the fault diagnosis function is used to determine the fault state of the live area of ​​the substation, and the fault feature includes a first feature and a second feature, wherein the first feature is used to characterize the physical characteristics and operating laws of the live area of ​​the substation when a fault occurs, and the second feature is used to characterize the abnormal data features generated when a fault occurs in the live area of ​​the substation based on a deep learning method and / or a machine learning method; Fault diagnosis information is determined according to the monitoring result, the fault diagnosis function and the fault characteristic, wherein the fault diagnosis information at least includes the fault cause and the fault location of the energized area of ​​the substation.

5. The early warning method for live areas of substations according to claim 1, characterized in that: After obtaining target data of the live area of ​​the substation, the early warning method of the live area of ​​the substation further includes: Obtaining a prediction function for the live area of ​​the substation, wherein the prediction function is used to predict the state of the live area of ​​the substation in a future time period; A prediction result is determined according to the prediction function, the digital twin model and the target data.

6. The early warning method for live areas of substations according to claim 5, characterized in that: After determining the prediction result according to the prediction function, the digital twin model and the target data, the early warning method for the energized area of ​​the substation further includes: Determining a maintenance strategy for the live area of ​​the substation according to the prediction result, wherein the maintenance strategy is used to adjust the live area of ​​the substation according to the state of the live area of ​​the substation; Acquire the correlation between each device in the substation and the maintenance strategy, wherein the correlation is used to characterize the degree of adaptation between each device and the maintenance strategy; The target strategy of each device is determined according to the correlation, wherein the target strategy of each device is used to set an operation for the device when the adjustment operation is performed on the energized area of ​​the substation.

7. The early warning method for live areas of substations according to claim 6, characterized in that: After determining the target solution for each device according to the correlation, the early warning method for the live area of ​​the substation further includes: A simulation test of early warning operation is performed on the digital twin model, wherein the simulation test at least includes a simulation test and an augmented reality simulation test.

8. The early warning method for live areas of substations according to claim 1, characterized in that: The digital twin model is obtained by the following steps: Acquire physical characteristics of the live area of ​​the substation, wherein the physical characteristics at least include topological structure, electrical characteristics, and equipment parameters of the live area of ​​the substation; constructing an initial digital twin model according to the target data and the physical properties; Use the historical data of the first historical time period as training samples; Using fault data of a second historical time period as training labels, wherein the second historical time period is after the first historical time period; The initial digital twin model is iteratively trained according to the training samples and the training labels to obtain the digital twin model.

9. An early warning device for live areas of a substation, characterized in that: include: A first acquisition unit acquires target data of a live area of ​​a substation, wherein the target data at least includes real-time data, historical data, geographic data, and equipment status data of the live area of ​​the substation, wherein the real-time data at least includes equipment data and environmental parameters of the live area of ​​the substation at a current moment, and the historical data at least includes equipment data, environmental parameters, and fault data of the live area of ​​the substation at historical moments; A first processing unit monitors the live area of ​​the substation based on the digital twin model and the target data to obtain a monitoring result, wherein the digital twin model is a virtual model for characterizing the electrical characteristics, physical characteristics, live level and safety distance of the internal equipment of the substation and the live area of ​​the substation; The second processing unit performs fault warning according to the monitoring result.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the early warning method for the energized area of ​​the substation as described in any one of claims 1 to 8.

Images