Intelligent substation remote control obstacle positioning method, device, equipment and medium
Through the deep confidence network model, the remote control signal data of the intelligent substation is analyzed, the types of obstacles are identified and the fault points are located, which solves the problem of insufficient positioning accuracy of remote control obstacles and improves the fault maintenance efficiency.
Patent Information
- Application Number
- CN202411031975.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-11-26
AI Technical Summary
The lack of positioning accuracy of obstacles caused by equipment failures, communication failures and other reasons during remote control of intelligent substations affects the safe and stable operation of the substation.
Using a remote control obstacle model based on deep confidence network, by acquiring historical and real-time remote control signal data, analyzing electrical quantity, information quantity, communication link data and electrical signal loop status, constructing a sample set for training, identifying obstacle types and processing them in big data Position the fault point.
It greatly improves the accuracy and maintenance efficiency of fault location and shortens the time for fault maintenance.
Smart Images

Figure CN119025988A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence and power system automation, and in particular to a method, device, equipment and medium for remotely controlling obstacle positioning of an intelligent substation. Background Art
[0002] In recent years, the proportion of smart substations put into operation in my country has gradually increased, which is the main trend of power grid development. Smart substations have been introduced into new power grid systems in large numbers. Sensor technology has been introduced into smart substations, and high-speed network communication technology has been used to realize information sharing between secondary devices, which has improved the operation and maintenance level of relay protection systems. In smart substations, remote control operation is an important means to achieve remote control and automated operation of substations. Through remote control operation, operation and maintenance personnel can remotely control equipment in the substation, such as circuit breakers, disconnectors, etc., in the control room, thereby realizing remote monitoring and adjustment of the substation. This operation mode not only improves the efficiency of operation and maintenance, but also reduces the risk of operation and maintenance.
[0003] However, during the remote control operation, remote control obstacles may occur due to various reasons such as equipment failure, communication failure, improper operation, etc., such as remote control return error, unsuccessful remote control execution, etc. If these obstacles are not located and handled in time, they will have a serious impact on the safe and stable operation of the substation. At present, traditional fault location methods often rely on relatively single fault feature information, such as simple current and voltage changes. In the complex and changeable power system environment, this information may not fully reflect the true situation of the fault, resulting in insufficient positioning accuracy.
[0004] Therefore, how to improve the accuracy of obstacle positioning through intelligent substation remote control has become a technical problem that needs to be solved urgently. Summary of the invention
[0005] The present invention aims to provide a remote control obstacle locating method for an intelligent substation to solve the technical problem of how to improve the accuracy of fault locating, thereby achieving the technical effect of shortening the fault repair time and improving the repair speed.
[0006] In order to solve the above technical problems, an embodiment of the present invention provides a smart substation remote control obstacle positioning method, comprising:
[0007] Acquire the historical remote control signal of the target smart substation, analyze the historical remote control signal during the transmission process, and obtain the electrical quantity data, information quantity data, remote control whole process communication link data and electrical signal loop status data respectively;
[0008] Constructing a sample set according to the electrical quantity data, the information quantity data, the remote control whole process communication link data and the electrical signal loop state data;
[0009] Inputting the sample set into a pre-built remote control obstacle model based on a deep belief network for training, thereby obtaining a trained remote control obstacle model;
[0010] Performing real-time monitoring on the target smart substation and acquiring real-time monitoring data, and if the real-time monitoring data meets a preset fault condition, acquiring a current remote control signal of the target smart substation;
[0011] Analyze the current remote control signal during the transmission process, input the analysis result into the trained remote control obstacle model, and obtain the corresponding obstacle type;
[0012] Big data processing and analysis is performed on the obstacle types to obtain a processed fault location point set.
[0013] As one of the preferred solutions, the step of acquiring the historical remote control signal of the target smart substation and analyzing the historical remote control signal during the transmission process includes:
[0014] Screen and determine the various signal dimensions of the remote control signal during transmission;
[0015] The remote control signal is decomposed into a communication link according to the protocol standard corresponding to each of the signal dimensions, and the communication sub-links corresponding to the remote control signal in each of the signal dimensions are obtained respectively, wherein the communication sub-links at least include a sub-link sent from the dispatching system to the remote control gateway when remote control selection is selected, a sub-link sent from the remote control gateway to the measurement and control device when remote control selection is selected, a sub-link fed back from the measurement and control device to the remote control gateway when remote control selection is selected, a sub-link fed back from the remote control gateway to the dispatching system when remote control selection is selected, a sub-link sent to the remote control gateway when remote control is executed, a sub-link sent from the remote control gateway to the measurement and control device when remote control is executed, a sub-link sent from the measurement and control device to the intelligent terminal when remote control is executed, a sub-link sent from the intelligent terminal to the circuit breaker mechanism when remote control is executed, a sub-link fed back from the circuit breaker mechanism to the intelligent terminal when remote control is executed, a sub-link fed back from the intelligent terminal to the measurement and control device when remote control is executed, a sub-link fed back from the measurement and control device to the remote control gateway when remote control is executed, and a sub-link fed back from the remote control device to the dispatching system when remote control is executed.
[0016] As one of the preferred solutions, the sample set is constructed according to the electrical quantity data, the information quantity data, the remote control whole process communication link data and the electrical signal loop state data, including:
[0017] Classifying all obstacles based on the equipment type of the target smart substation;
[0018] Based on the classification results, the electrical quantity data, the information quantity data, the remote control full process communication link data and the electrical signal loop status data are labeled, and a sample set is constructed with the labeled electrical quantity data, the information quantity data, the remote control full process communication link data and the electrical signal loop status data.
[0019] As one of the preferred solutions, the step of inputting the sample set into a pre-built remote control obstacle model based on a deep belief network for training to obtain a trained remote control obstacle model includes:
[0020] Inputting the sample set into a deep belief network for feature extraction to obtain a feature vector;
[0021] The feature vector and its corresponding Softmax classifier are subjected to classification training of feature quantities and sample labels, and the deep belief network and the trained Softmax classifier are used as a trained remote control obstacle positioning model.
[0022] As one of the preferred solutions, the real-time monitoring of the target smart substation and obtaining the real-time monitoring data, if the real-time monitoring data meets the preset fault condition, obtaining the current remote control signal of the target smart substation, includes:
[0023] Conduct real-time monitoring of electrical parameters, equipment status parameters, and environmental parameters of the target smart substation;
[0024] Based on historical operation and maintenance data, corresponding threshold ranges are set for the electrical parameters, the equipment status parameters, and the environmental parameters. If the electrical parameters, the equipment status parameters, and the environmental parameters are set beyond the threshold ranges, the current remote control signal of the target smart substation is obtained.
[0025] As one of the preferred solutions, the big data processing and analysis of the obstacle type to obtain a processed set of fault location points includes:
[0026] Inputting the obstacle type data into a fault identification model to obtain a fault identification result;
[0027] An analysis is performed based on the fault identification result and the topological structure of the target smart substation to obtain a processed fault location point set.
[0028] As one of the preferred solutions, after analyzing and processing based on the fault identification result and the topological structure of the target smart substation to obtain a processed fault location point set, it also includes:
[0029] Matching the fault location point set with a preset fault maintenance database to generate a corresponding maintenance strategy;
[0030] The maintenance strategy is used to control related control equipment for control, and the control result is returned to the fault maintenance database for storage.
[0031] Another embodiment of the present invention provides a remote control obstacle locating device for a smart substation, comprising:
[0032] An acquisition module is used to acquire the historical remote control signal of the target smart substation, analyze the historical remote control signal during the transmission process, and obtain electrical quantity data, information quantity data, remote control whole process communication link data and electrical signal loop status data respectively;
[0033] A construction module, used to construct a sample set according to the electrical quantity data, the information quantity data, the remote control whole process communication link data and the electrical signal loop state data;
[0034] A training module, used for inputting the sample set into a pre-built remote control obstacle model based on a deep belief network for training, so as to obtain a trained remote control obstacle model;
[0035] A monitoring module, used to monitor the target smart substation in real time and obtain real-time monitoring data, and if the real-time monitoring data meets a preset fault condition, obtain a current remote control signal of the target smart substation;
[0036] An output module, used to analyze the current remote control signal during the transmission process, input the analysis result into the trained remote control obstacle model, and obtain the corresponding obstacle type;
[0037] The analysis module is used to perform big data processing and analysis on the obstacle type to obtain a processed fault location point set.
[0038] Another embodiment of the present invention provides a smart substation remote control obstacle positioning device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the smart substation remote control obstacle positioning method as described above.
[0039] Yet another embodiment of the present invention provides a computer-readable storage medium storing a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the smart substation remote control obstacle positioning method as described above is implemented.
[0040] Compared with the prior art, the embodiments of the present invention have the following advantages:
[0041] 1) The intelligent substation remote control obstacle locating method proposed in the present invention can quickly locate faults and greatly improve maintenance efficiency.
[0042] 2) This method combines remote control obstacle positioning with deep belief network, and uses DBN to convert the input electrical quantity, information quantity and remote control whole process communication link or electrical signal loop status into fault type, which greatly improves the speed of data processing. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 It is a flow chart of a method for remotely controlling obstacle location of a smart substation in one embodiment of the present invention;
[0044] Figure 2 is a schematic diagram of a remote control obstacle locating system in one embodiment of the present invention;
[0045] Figure 3 is a schematic diagram of a remote control selection process in one embodiment of the present invention;
[0046] Figure 4 is a schematic diagram of a remote control execution process in one embodiment of the present invention;
[0047] Figure 5 is a schematic diagram of a remote control obstacle positioning process in one embodiment of the present invention;
[0048] Figure 6 is a schematic diagram of a fitness curve in one embodiment of the present invention;
[0049] Figure 7 is a schematic diagram of the diagnosis results of the training set in one embodiment of the present invention;
[0050] Figure 8 is a schematic diagram of a test set diagnosis result in one embodiment of the present invention;
[0051] Fig. 9 It is a structural schematic diagram of a remote control obstacle locating device for a smart substation in one embodiment of the present invention;
[0052] Fig.10 It is a schematic diagram of a remote-controlled obstacle locating device for a smart substation in one embodiment of the present invention. DETAILED DESCRIPTION
[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0054] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.
[0055] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.
[0056] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.
[0057] An embodiment of the present invention provides a remote control obstacle positioning method for a smart substation. For details, see Figure 1 , Figure 1 The figure shows a flow chart of a smart substation remote control obstacle location method provided in one embodiment of the present invention, which includes steps S1 to S6:
[0058] S1. Obtain the historical remote control signal of the target smart substation, analyze the historical remote control signal during the transmission process, and obtain the electrical quantity data, information quantity data, remote control whole process communication link data and electrical signal loop status data respectively;
[0059] S2, constructing a sample set according to the electrical quantity data, the information quantity data, the remote control whole process communication link data and the electrical signal loop state data;
[0060] S3, inputting the sample set into a pre-built remote control obstacle model based on a deep belief network for training, to obtain a trained remote control obstacle model;
[0061] S4, performing real-time monitoring on the target smart substation and obtaining real-time monitoring data, and if the real-time monitoring data meets a preset fault condition, obtaining a current remote control signal of the target smart substation;
[0062] S5, analyzing the current remote control signal during the transmission process, and inputting the analysis result into the trained remote control obstacle model to obtain the corresponding obstacle type;
[0063] S6. Perform big data processing and analysis on the obstacle type to obtain a processed fault location point set.
[0064] First, in order to facilitate the description of the solution of the present invention, a remote control obstacle positioning system is constructed as follows: Figure 2 As shown in the figure. The system consists of 104 client, obstacle location analysis software and secondary equipment for the whole process of substation remote control. The 104 client simulates the dispatching system and connects to the substation telecontrol gateway via the 104 protocol to realize dispatching-level remote control operation; the obstacle location analysis software connects to the substation control layer network via the MMS protocol to obtain feedback information of the whole process of remote control and multi-type telesignaling information of the substation, and comprehensively realizes the obstacle location of remote control failure.
[0065] Preferably, in an embodiment of the present invention, the acquiring of the historical remote control signal of the target smart substation and analyzing the historical remote control signal in the transmission process include:
[0066] Screen and determine the various signal dimensions of the remote control signal during transmission;
[0067] The remote control signal is decomposed into a communication link according to the protocol standard corresponding to each of the signal dimensions, and the communication sub-links corresponding to the remote control signal in each of the signal dimensions are obtained respectively, wherein the communication sub-links at least include a sub-link sent from the dispatching system to the remote control gateway when remote control selection is selected, a sub-link sent from the remote control gateway to the measurement and control device when remote control selection is selected, a sub-link fed back from the measurement and control device to the remote control gateway when remote control selection is selected, a sub-link fed back from the remote control gateway to the dispatching system when remote control selection is selected, a sub-link sent to the remote control gateway when remote control is executed, a sub-link sent from the remote control gateway to the measurement and control device when remote control is executed, a sub-link sent from the measurement and control device to the intelligent terminal when remote control is executed, a sub-link sent from the intelligent terminal to the circuit breaker mechanism when remote control is executed, a sub-link fed back from the circuit breaker mechanism to the intelligent terminal when remote control is executed, a sub-link fed back from the intelligent terminal to the measurement and control device when remote control is executed, a sub-link fed back from the measurement and control device to the remote control gateway when remote control is executed, and a sub-link fed back from the remote control device to the dispatching system when remote control is executed.
[0068] Specifically, the remote control process includes remote control selection and remote control execution process, wherein the remote control selection process is as follows: Figure 3 As shown in FIG. 1 , it is composed of links p1-p4, where p1 is the sub-link sent from the dispatching system to the telecontrol gateway when remote control is selected, p2 is the sub-link sent from the telecontrol gateway to the measurement and control device when remote control is selected, p3 is the sub-link fed back from the measurement and control device to the telecontrol gateway when remote control is selected, and p4 is the sub-link fed back from the telecontrol gateway to the dispatching system when remote control is selected; the remote control execution process is shown in FIG. Figure 4 As shown, it is composed of p5-p7, where p5 is the sub-link sent to the telecontrol gateway when remote control is executed, p6 is the sub-link sent from the telecontrol gateway to the measurement and control device when remote control is executed, p7 is the sub-link sent from the measurement and control device to the intelligent terminal when remote control is executed, p8 is the sub-link sent from the intelligent terminal to the circuit breaker mechanism when remote control is executed, p9 is the sub-link fed back from the circuit breaker mechanism to the intelligent terminal when remote control is executed, and p 10 It is the sub-link from the intelligent terminal to the measurement and control device during remote control execution. 11 It is the sub-link from the measurement and control device to the telecontrol gateway during remote control execution. 12 It is the sub-link from which the telecontrol device feeds back to the dispatching system during remote control execution.
[0069] Preferably, in an embodiment of the present invention, the step of constructing a sample set according to the electrical quantity data, the information quantity data, the remote control whole process communication link data and the electrical signal loop state data includes:
[0070] Classifying all obstacles based on the equipment type of the target smart substation;
[0071] Based on the classification results, the electrical quantity data, the information quantity data, the remote control full process communication link data and the electrical signal loop status data are labeled, and a sample set is constructed with the labeled electrical quantity data, the information quantity data, the remote control full process communication link data and the electrical signal loop status data.
[0072] Specifically, to achieve remote control positioning, there are a series of complex processes in the middle, and obstacles may occur due to various factors, causing the operation to fail. Specifically, based on the secondary system loop, obstacles can be divided into three categories: system dissatisfaction, failure, and operation lockout.
[0073] The system does not meet the requirements when the synchronous closing is selected. Since the system does not meet the synchronous conditions, the remote control closing is not executed successfully, and the remote control execution process p7 fails. The faults are divided into power failure of the operating power supply, fiber optic disconnection, equipment failure, etc. Specifically, the power failure of the operating power supply will cause the circuit breaker mechanism to fail to work normally. Even if the intelligent terminal sends out the execution command normally, the remote control process cannot be successfully executed, and the remote control execution process p8 fails. The fiber optic disconnection will cause the GOOSE link communication to be interrupted, so that the remote control command cannot be issued normally, and the remote control execution process p9 p 10 Failure; equipment failure includes failure of switches, telecontrol gateways, measurement and control devices, and intelligent terminals. Failure of any of these devices will result in the failure of remote control commands to be issued normally, resulting in failure of remote control operations. Specifically, when the MMS switch fails, the remote control execution process 10 Failure; when the GOOSE switch fails, the remote control execution process p7p 10 Failure; when the telecontrol gateway fails, the remote control execution process p5 p6 p 11 p 12 Failure; when the measurement and control device fails, the remote control execution process p6 p7 p 10 p 11 Failure; when the intelligent terminal fails, the remote control execution process p7 p8 p9 p 10 fail;
[0074] Operation interlock mainly considers equipment maintenance status, remote signal, GOOSE receiving soft pressure plate, intelligent terminal export hard pressure plate, etc. When any of the intelligent terminal, measurement and control device, and telecontrol gateway is in maintenance status, the 104 client will not be able to issue remote control commands normally; when the measurement and control device is in the local status, the remote control execution process p6 p7 p 10 p 11 Failure, when the intelligent terminal is in the local state, remote control execution process p7 p8 p9 p 10 If the remote control gateway fails, the remote control execution process p5 p6 p 11 p 12Failure; when the GOOSE receiving soft pressure plate is not put into operation, the intelligent terminal cannot receive the message sent by the measurement and control device, and the remote control execution process p7 fails; when the intelligent terminal export hard pressure plate is not put into operation, the remote control execution instruction cannot be normally transmitted to the circuit breaker mechanism, and the remote control execution process p8 fails.
[0075] Table 1 shows the states of each feature quantity under three fault conditions. Different samples are obtained according to the states of the feature quantities. A total of 171 groups of samples are obtained, 120 of which are randomly selected as training samples, and the remaining 51 are used as test samples.
[0076] Table 1
[0077]
[0078] Preferably, in an embodiment of the present invention, inputting the sample set into a pre-built remote control obstacle model based on a deep belief network for training to obtain a trained remote control obstacle model includes:
[0079] Inputting the sample set into a deep belief network for feature extraction to obtain a feature vector;
[0080] The feature vector and its corresponding Softmax classifier are subjected to classification training of feature quantities and sample labels, and the deep belief network and the trained Softmax classifier are used as a trained remote control obstacle positioning model.
[0081] The deep belief network (DBN) is a composite model composed of multiple layers of simple learning models. It is composed of several restricted Boltzmann machines (RBM) and a single-layer back propagation neural network (BPNN). It can effectively mine the deep features of data. Among them, RBM is a random network that describes the probability distribution function and energy function of a random network. The joint energy function between the visible layer and the hidden layer is:
[0082]
[0083] In the formula, v i is the state of the i-th neuron in the visible layer; h j is the jth neuron state in the hidden layer; a i and b j are the biases of the i-th neuron in the visible layer and the j-th neuron in the hidden layer respectively; w ij is the weight between the i-th neuron in the visible layer and the j-th neuron in the hidden layer; θ = {w ij ,ai ,b j} are model parameters. According to formula (1), the joint probability distribution between the visible layer and the hidden layer is:
[0084]
[0085] In the formula is the normalization factor. The activation probability calculation formula of the jth hidden layer neuron in the remote control obstacle positioning model is:
[0086]
[0087] Where σ(z) is the sigmoid activation function, σ(z)=(1+exp(-z)) -1 ,in, n v represents the nth visible layer; similarly, the structure of the remote control obstacle positioning model is symmetrical. When the state of the hidden layer is known, the activation state of each visible layer is also conditionally independent. The activation probability calculation formula of the i-th visible layer unit of the remote control obstacle positioning model is:
[0088]
[0089] Where n h represents the nth hidden layer.
[0090] Remote control obstacle positioning process Figure 5 As shown in the figure, after forming a sample set according to the electrical quantity, information quantity and the state of the remote control communication link or electrical signal loop during the whole process, the sample data is input into DBN, and the feature quantity extracted by the DBN model and its corresponding training set sample label are input into the Softmax classifier to perform classification training of the feature quantity and sample label; finally, the test set is input into the remote control obstacle positioning model, and the output result is the corresponding single obstacle type or its multiple obstacle combinations including system non-satisfaction S, fault F, and operation lockout B, so as to verify the correctness of the method and realize remote control obstacle positioning based on the above process.
[0091] Next, the model is verified. The parameters of the DBN-based remote control obstacle positioning system fault diagnosis model are set as follows: population size n = 20, maximum number of iterations Max_Iter = 100. The model is calculated using MATLAB 2018b software, and the calculation results of DBN parameter optimization are shown in the figure. Figure 6 When the optimization algorithm used in this method evolved to the fifth generation, the fitness of the optimal individual parameters reached 94%, and the corresponding optimal parameter combinations C and g were 4.795 and 0.73048 respectively.
[0092] The diagnostic results of the training sample set and the test sample set are as follows: Figure 7 and Figure 8 As shown. There are four types of diagnosis results: 1 corresponds to no fault; 2 corresponds to system unsatisfied; 3 corresponds to fault; 4 corresponds to operation lockout. There are 120 training set samples, 116 samples with correct diagnosis, and the accuracy rate can reach 96%. There are 51 test set samples, 48 samples with correct diagnosis, and the accuracy rate can reach 94%. In the diagnosis results of the test set samples, there were 3 cases where the fault was misdiagnosed as normal operation. Among them, the diagnosis model has a higher accuracy rate for faults, indicating that the model can better extract fault information from the selected fault feature quantity, and also reflects the correctness of selecting the remote control full process communication link or electrical signal loop state as the feature quantity. The diagnosis results show that the fault diagnosis model based on DBN has a good fault diagnosis ability in the case of small samples. DBN can well extract the fault characteristics of the remote control obstacle positioning system and successfully classify the diagnosis samples.
[0093] Preferably, in an embodiment of the present invention, the real-time monitoring of the target smart substation and obtaining real-time monitoring data, if the real-time monitoring data meets a preset fault condition, obtaining a current remote control signal of the target smart substation includes:
[0094] Conduct real-time monitoring of electrical parameters, equipment status parameters, and environmental parameters of the target smart substation;
[0095] Based on historical operation and maintenance data, corresponding threshold ranges are set for the electrical parameters, the equipment status parameters, and the environmental parameters. If the electrical parameters, the equipment status parameters, and the environmental parameters are set beyond the threshold ranges, the current remote control signal of the target smart substation is obtained.
[0096] It should be noted that different preset fault conditions are set for different types of real-time monitoring data. For example, for equipment with a rated voltage of 400kV, its normal operating voltage range can be set to 380kV to 420kV. Voltage exceeding this range is considered abnormal. Considering that instantaneous voltage fluctuations may be caused by normal operation, a certain time delay (such as a few seconds or minutes) can be set to confirm whether the voltage abnormality persists.
[0097] Preferably, in an embodiment of the present invention, the performing big data processing and analysis on the obstacle type to obtain a processed set of fault location points includes:
[0098] Inputting the obstacle type data into a fault identification model to obtain a fault identification result;
[0099] An analysis is performed based on the fault identification result and the topological structure of the target smart substation to obtain a processed fault location point set.
[0100] Specifically, historical data such as past failure records, maintenance records, and equipment replacement records are collected. These data are very important for understanding failure modes and identifying failure precursors. Then, the pre-processed historical data is integrated into the big data platform, and distributed storage and computing resources are used to process massive data. Machine learning algorithms (such as decision trees, random forests, neural networks, etc.) are used to identify failure modes and predict new failure conditions through training models. Based on the model prediction results and real-time data, the specific location or area where the failure occurs is determined.
[0101] Preferably, in an embodiment of the present invention, after analyzing and processing based on the fault identification result and the topological structure of the target smart substation to obtain a processed fault location point set, it also includes:
[0102] Matching the fault location point set with a preset fault maintenance database to generate a corresponding maintenance strategy;
[0103] The maintenance strategy is used to control related control equipment for control, and the control result is returned to the fault maintenance database for storage.
[0104] The beneficial effects of the present invention are:
[0105] 1) The intelligent substation remote control obstacle locating method proposed in the present invention can quickly locate faults and greatly improve maintenance efficiency.
[0106] 2) This method combines remote control obstacle positioning with deep belief network, and uses DBN to convert the input electrical quantity, information quantity and remote control whole process communication link or electrical signal loop status into fault type, which greatly improves the speed of data processing.
[0107] Another embodiment of the present invention provides a remote control obstacle locating device for a smart substation. For details, see Fig. 9 , Fig. 9 The structure diagram of the remote control obstacle locating device for a smart substation provided in one embodiment of the present invention is shown, which includes the following modules: an acquisition module 11, a construction module 12, a training module 13, a monitoring module 14, an output module 15, and an analysis module 16, wherein:
[0108] The acquisition module 11 is used to acquire the historical remote control signal of the target smart substation, analyze the historical remote control signal in the transmission process, and obtain the electrical quantity data, information quantity data, remote control whole process communication link data and electrical signal loop status data respectively;
[0109] A construction module 12, configured to construct a sample set according to the electrical quantity data, the information quantity data, the remote control whole process communication link data and the electrical signal loop state data;
[0110] A training module 13 is used to input the sample set into a pre-built remote control obstacle model based on a deep belief network for training, so as to obtain a trained remote control obstacle model;
[0111] A monitoring module 14 is used to monitor the target smart substation in real time and obtain real-time monitoring data. If the real-time monitoring data meets a preset fault condition, the current remote control signal of the target smart substation is obtained;
[0112] The output module 15 is used to analyze the current remote control signal during the transmission process, and input the analysis result into the trained remote control obstacle model to obtain the corresponding obstacle type;
[0113] The analysis module 16 is used to perform big data processing and analysis on the obstacle type to obtain a processed fault location point set.
[0114] Another embodiment of the present invention provides a remote control obstacle locating device for a smart substation, see Fig.10 , Fig.10 The schematic diagram of the intelligent substation remote control obstacle locating device provided in one embodiment of the present invention is shown, which includes the following modules: a processor 21, a memory 22, and a computer program stored in the memory 22 and configured to be executed by the processor 21. When the processor 21 executes the computer program, the steps in the above-mentioned intelligent substation remote control obstacle locating method embodiment are implemented, for example Figure 1 or, when the processor 21 executes the computer program, the functions of the modules in the above-mentioned device embodiments are implemented, such as the acquisition module 11.
[0115] Exemplarily, the computer program can be divided into one or more modules, and the one or more modules are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the smart substation remote control obstacle locating device. For example, the computer program can be divided into an acquisition module 11, a construction module 12, a training module 13, a monitoring module 14, an output module 15, and an analysis module 16.
[0116] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 21 is the control center of the remote-controlled obstacle locating device for the smart substation, and uses various interfaces and lines to connect various parts of the remote-controlled obstacle locating device for the smart substation.
[0117] The memory 22 can be used to store the computer program and / or module. The processor 21 realizes various functions of the intelligent substation remote control obstacle locating device by running or executing the computer program and / or module stored in the memory 22 and calling the data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0118] Wherein, if the module integrated in the remote control obstacle locating device of the intelligent substation 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 such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.
[0119] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.
[0120] Accordingly, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to perform the steps in the remote control obstacle location method for a smart substation in the above embodiment, for example Figure 1 Steps S1 to S6 described in .
[0121] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.
Claims
1. A remote control obstacle positioning method for a smart substation, characterized in that: The following steps are involved: Acquire the historical remote control signal of the target smart substation, analyze the historical remote control signal during the transmission process, and obtain the electrical quantity data, information quantity data, remote control whole process communication link data and electrical signal loop status data respectively; Constructing a sample set according to the electrical quantity data, the information quantity data, the remote control whole process communication link data and the electrical signal loop state data; Inputting the sample set into a pre-built remote control obstacle model based on a deep belief network for training, thereby obtaining a trained remote control obstacle model; Performing real-time monitoring on the target smart substation and acquiring real-time monitoring data, and if the real-time monitoring data meets a preset fault condition, acquiring a current remote control signal of the target smart substation; Analyze the current remote control signal during the transmission process, input the analysis result into the trained remote control obstacle model, and obtain the corresponding obstacle type; Big data processing and analysis is performed on the obstacle types to obtain a processed fault location point set.
2. The intelligent substation remote control obstacle positioning method according to claim 1 is characterized in that: The acquiring of the historical remote control signal of the target smart substation and analyzing the historical remote control signal in the transmission process includes: Screen and determine the various signal dimensions of the remote control signal during transmission; The remote control signal is decomposed into a communication link according to the protocol standard corresponding to each of the signal dimensions, and the communication sub-links corresponding to the remote control signal in each of the signal dimensions are obtained respectively, wherein the communication sub-links at least include a sub-link sent from the dispatching system to the remote control gateway when remote control selection is selected, a sub-link sent from the remote control gateway to the measurement and control device when remote control selection is selected, a sub-link fed back from the measurement and control device to the remote control gateway when remote control selection is selected, a sub-link fed back from the remote control gateway to the dispatching system when remote control selection is selected, a sub-link sent to the remote control gateway when remote control is executed, a sub-link sent from the remote control gateway to the measurement and control device when remote control is executed, a sub-link sent from the measurement and control device to the intelligent terminal when remote control is executed, a sub-link sent from the intelligent terminal to the circuit breaker mechanism when remote control is executed, a sub-link fed back from the circuit breaker mechanism to the intelligent terminal when remote control is executed, a sub-link fed back from the intelligent terminal to the measurement and control device when remote control is executed, a sub-link fed back from the measurement and control device to the remote control gateway when remote control is executed, and a sub-link fed back from the remote control device to the dispatching system when remote control is executed.
3. The intelligent substation remote control obstacle positioning method according to claim 1 is characterized in that: The constructing of the sample set according to the electrical quantity data, the information quantity data, the remote control whole process communication link data and the electrical signal loop state data comprises: Classifying all obstacles based on the equipment type of the target smart substation; Based on the classification results, the electrical quantity data, the information quantity data, the remote control full process communication link data and the electrical signal loop status data are labeled, and a sample set is constructed with the labeled electrical quantity data, the information quantity data, the remote control full process communication link data and the electrical signal loop status data.
4. The method according to claim 1, characterized in that: The step of inputting the sample set into a pre-built remote control obstacle model based on a deep belief network for training to obtain a trained remote control obstacle model includes: Inputting the sample set into a deep belief network for feature extraction to obtain a feature vector; The feature vector and its corresponding Softmax classifier are subjected to classification training of feature quantities and sample labels, and the deep belief network and the trained Softmax classifier are used as a trained remote control obstacle positioning model.
5. The method according to claim 1, characterized in that The real-time monitoring of the target smart substation and obtaining real-time monitoring data, if the real-time monitoring data meets the preset fault condition, obtaining the current remote control signal of the target smart substation, includes: Conduct real-time monitoring of electrical parameters, equipment status parameters, and environmental parameters of the target smart substation; Based on historical operation and maintenance data, corresponding threshold ranges are set for the electrical parameters, the equipment status parameters, and the environmental parameters. If the electrical parameters, the equipment status parameters, and the environmental parameters are set beyond the threshold ranges, the current remote control signal of the target smart substation is obtained.
6. The method according to claim 1, characterized in that The big data processing and analysis of the obstacle type to obtain a processed fault location point set includes: Inputting the obstacle type data into a fault identification model to obtain a fault identification result; An analysis is performed based on the fault identification result and the topological structure of the target smart substation to obtain a processed fault location point set.
7. The method according to claim 6, characterized in that After analyzing and processing the fault identification result and the topological structure of the target smart substation to obtain a processed fault location point set, the method further includes: Matching the fault location point set with a preset fault maintenance database to generate a corresponding maintenance strategy; The maintenance strategy is used to control related control equipment for control, and the control result is returned to the fault maintenance database for storage.
8. A remote control obstacle locating device for a smart substation, characterized in that: Includes the following modules: An acquisition module is used to acquire the historical remote control signal of the target smart substation, analyze the historical remote control signal during the transmission process, and obtain electrical quantity data, information quantity data, remote control whole process communication link data and electrical signal loop status data respectively; A construction module, used to construct a sample set according to the electrical quantity data, the information quantity data, the remote control whole process communication link data and the electrical signal loop state data; A training module, used for inputting the sample set into a pre-built remote control obstacle model based on a deep belief network for training, so as to obtain a trained remote control obstacle model; A monitoring module, used to monitor the target smart substation in real time and obtain real-time monitoring data, and if the real-time monitoring data meets a preset fault condition, obtain a current remote control signal of the target smart substation; An output module, used to analyze the current remote control signal during the transmission process, input the analysis result into the trained remote control obstacle model, and obtain the corresponding obstacle type; The analysis module is used to perform big data processing and analysis on the obstacle type to obtain a processed fault location point set.
9. A remote control obstacle locating device for a smart substation, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for remotely controlling obstacle positioning of a smart substation as described in any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the smart substation remote control obstacle positioning method as described in any one of claims 1 to 7 is implemented.
