Visual monitoring method, device and equipment for secondary equipment of transformer substation and medium

Abstract

The invention discloses a substation secondary equipment visual monitoring method and device, equipment and a medium. The method comprises the following steps: acquiring an SCD (Substation Configuration Description) file of a target substation and state information of secondary equipment in the target substation; generating an initial secondary equipment model according to the point cloud data corresponding to the secondary equipment and the SCD file; obtaining a secondary signal loop according to the SCD file, and changing the state of the initial secondary equipment model according to the secondary signal loop to obtain a target secondary equipment model; obtaining a state evaluation result and a state trend according to the state information, a state evaluation model and a trend classification rule database; and transmitting the target secondary equipment model, the state evaluation result and the state trend to a pre-configured visual display terminal so as to realize visual display of the secondary equipment. According to the invention, the current state of the secondary equipment can be managed accurately and efficiently.

Description

Technical Field

[0001] The invention belongs to the technical field of secondary equipment detection, and relates to a method, device, equipment and medium for visual monitoring of secondary equipment in a substation. Background Art

[0002] The equipment structure of a substation includes primary equipment and secondary equipment. Primary equipment refers to high-voltage electrical equipment directly used for the production, transmission and distribution of electrical energy, including generators, transformers, circuit breakers, disconnectors, automatic switches, contactors, knife switches, busbars, transmission lines, power cables, reactors, motors, etc. Secondary equipment refers to low-voltage electrical equipment required to monitor, control, regulate and protect the operation of primary equipment and provide operating conditions or production command signals to operation and maintenance personnel, such as fuses, control switches, relays, control cables, etc.

[0003] In the prior art, the operation of secondary equipment is mostly managed through paper documents or electronic documents, and the number of documents is huge and the types are various. Manual management of relevant documents of secondary equipment not only has low management efficiency, but also cannot accurately and efficiently manage the current status of secondary equipment.

[0004] Therefore, how to accurately and efficiently manage the current status of secondary equipment is an urgent problem that needs to be solved. Summary of the invention

[0005] In order to solve the deficiencies in the prior art, the present invention provides a method, device, equipment and medium for visual monitoring of secondary equipment in a substation.

[0006] The present invention adopts the following technical solution.

[0007] A first aspect of the present invention provides a method for visually monitoring secondary equipment in a substation, comprising:

[0008] Obtaining the SCD file of the target substation and the status information of the secondary equipment in the target substation;

[0009] Generate an initial secondary equipment model according to the point cloud data corresponding to the secondary equipment and the SCD file;

[0010] Obtaining a secondary signal loop according to the SCD file, and changing the state of the initial secondary device model according to the secondary signal loop to obtain a target secondary device model;

[0011] Obtaining a state evaluation result and a state trend according to the state information, the state evaluation model, and the trend classification rule database;

[0012] The target secondary equipment model, status evaluation results and status trend are transmitted to a pre-configured visualization display terminal for visualization of the secondary equipment.

[0013] Preferably, generating an initial secondary device model according to the point cloud data corresponding to the secondary device and the SCD file includes:

[0014] Acquire point cloud data corresponding to the secondary device;

[0015] Generate a three-dimensional model corresponding to the secondary device according to the point cloud data;

[0016] Parse the SCD file to obtain infrastructure information and a mapping relationship between secondary equipment and voltage levels, a mapping relationship between secondary equipment and its primary equipment, a mapping relationship between intervals and voltage levels, and a mapping relationship corresponding to virtual terminals of the secondary equipment;

[0017] The basic structure information and each mapping relationship are associated with the three-dimensional model to obtain the initial secondary equipment model.

[0018] Preferably, generating a three-dimensional model corresponding to the secondary device according to the point cloud data includes:

[0019] Apply machine learning algorithms to filter noise from point cloud data to identify and remove error points;

[0020] Use spatial clustering algorithm to simplify point cloud data, reduce the number of points, and keep key features;

[0021] Extract geometric feature point cloud blocks from point clouds using edge detection-based algorithms;

[0022] Combined with the parametric modeling method, the geometric feature point cloud blocks are parameterized and transmitted to the generative adversarial network (GAN). The GAN is used to generate the initial 3D model, so that the shape of each device has a certain degree of variability based on the actual data.

[0023] Functional verification of the initial 3D model through computer-aided engineering (CAE) analysis to ensure that the model meets the standards in terms of physical and electrical characteristics;

[0024] Based on the results of functional verification, the model's features are refined through programmatic design algorithms to ensure that the key functions and characteristics of each device are retained.

[0025] Preferably, the infrastructure information includes substation name, substation description attribute value, voltage level name, voltage level description attribute value, bay name, bay description attribute value, secondary equipment attribute value and secondary equipment information.

[0026] Preferably, obtaining a secondary signal loop according to the SCD file includes:

[0027] Parsing the SCD file to obtain an accident signal, a warning signal, and a position signal;

[0028] Determine a signal sending device, a signal receiving device, and a signal receiving port according to the accident signal, the warning signal, and the position signal;

[0029] The secondary signal loop is obtained by performing network cable loop deduction, electrical diagram analysis and optical cable analysis based on the signal sending device, signal receiving device and signal receiving port.

[0030] Preferably, obtaining the state evaluation result and the state trend according to the state information, the state evaluation model and the trend classification rule database includes:

[0031] Transmitting the state information to a pre-trained state evaluation model to obtain the state evaluation result;

[0032] The current time series data in the state information is extracted, and according to the data type of the current time series data, the target trend classification rule is called from a pre-built trend classification rule database, and the state trend corresponding to the current time series data is obtained according to the target trend classification rule.

[0033] Preferably, the network structure of the state evaluation model includes:

[0034] An input layer, which receives status information of secondary devices;

[0035] Feature selection layer, which applies self-attention mechanism to perform feature weighting on the input state information;

[0036] A multi-layer neural network layer that combines a convolutional neural network (CNN) with a long short-term memory (LSTM). CNN is used to extract spatial features and identify local correlations in state information, while LSTM is used to capture the temporal dependency of state changes to cope with the dynamic characteristics of input data.

[0037] Fully connected layer, the output of CNN and LSTM is integrated into multiple fully connected layers, and nonlinear mapping is performed through activation functions to obtain deeper feature representation;

[0038] The output layer is a Softmax layer, which is used to provide status evaluation results.

[0039] Preferably, the pre-training process of the state evaluation model is:

[0040] Collect equipment data in batches, including data under normal operation and fault conditions;

[0041] Annotate the collected device data;

[0042] Use data augmentation technology to enhance the labeled data, generate more samples, and obtain training sets and validation sets;

[0043] Train the state evaluation model on the training set and use an adaptive learning rate optimizer to dynamically adjust the learning rate according to the loss changes during model training;

[0044] Use validation sets to regularly evaluate the performance of the state evaluation model, and use precision, recall, and F1 value indicators for comprehensive evaluation;

[0045] Based on the results of multiple comprehensive evaluations, the outputs of multiple state evaluation models are combined through an ensemble learning method to enhance the accuracy and reliability of the model state evaluation.

[0046] Preferably, the target trend classification rule includes rule time series data and a classification threshold, and obtaining the state trend corresponding to the current time series data according to the target trend classification rule includes:

[0047] Calculate the current dynamic time warping value of the current time series data and the regular time series data by using the DTW algorithm, and compare the current dynamic time warping value with the classification threshold;

[0048] When the current dynamic time warping value is less than the classification threshold, the state trend is obtained according to a preset trend corresponding to the classification threshold.

[0049] Preferably, the target secondary equipment model, the state evaluation result and the state trend are transmitted to a pre-configured visualization display terminal for visualization of the secondary equipment, including:

[0050] Matching the status evaluation result with a model status color library pre-configured in a visualization display terminal, changing the status color of the target secondary device model according to the matching result, and visually displaying the target secondary device model after the status color change;

[0051] The target secondary equipment model is combined with the state trend, and a hierarchical visual display is performed according to the user's click instructions.

[0052] A second aspect of the present invention provides a visual monitoring device for secondary equipment in a substation, comprising:

[0053] An information acquisition module is used to acquire the SCD file of the target substation and the status information of the secondary equipment in the target substation;

[0054] An initial model generation module, used to generate an initial secondary device model according to the point cloud data corresponding to the secondary device and the SCD file;

[0055] A model state changing module, used for obtaining a secondary signal loop according to the SCD file, and changing the state of the initial secondary device model according to the secondary signal loop to obtain a target secondary device model;

[0056] An information processing module, used to obtain a state evaluation result and a state trend according to the state information, the state evaluation model, and the trend classification rule database;

[0057] The visualization display module is used to transmit the target secondary equipment model, state evaluation results and state trend to a pre-configured visualization display terminal for visualization display of the secondary equipment.

[0058] A third aspect of the present invention provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored computer program, wherein the computer program executes the method for visual monitoring of substation secondary equipment when running.

[0059] A fourth aspect of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the visual monitoring method for substation secondary equipment through the computer program.

[0060] Compared with the prior art, the beneficial effects of the present invention include at least:

[0061] The present invention obtains a target secondary equipment model that can be visualized according to the SCD file. Through the target secondary equipment model, the substation staff can remotely monitor the secondary equipment in real time, thereby improving the efficiency of secondary equipment status management.

[0062] The present invention combines the status evaluation results and status trends with the target secondary equipment model for visual display. Compared with the manual method, it can improve the accuracy of secondary equipment status management. At the same time, it can also display the status of the secondary equipment to the staff in real time, and can handle abnormal conditions such as faults in time.

[0063] When the present invention generates the initial secondary equipment model, the association efficiency and accuracy between the secondary equipment in the substation or between the secondary equipment and other equipment are improved through multi-level information association mapping; in addition, the present invention generates the initial secondary equipment model based on the existing SCD file, and there is no need to make secondary changes to the existing SCD model file, thereby avoiding association errors caused by manual modification.

[0064] The present invention performs network cable loop derivation, electrical diagram analysis and optical cable analysis based on the signal sending device, signal receiving device and signal receiving port to obtain a secondary signal loop. The signal sending device, signal receiving device and signal receiving port are determined based on the accident signal, warning signal and position signal, and query and locate the corresponding signal loop according to the relationship between the signal sending device, signal receiving device and signal receiving port, thereby reducing dependence on the experience and level of the staff, improving work efficiency and also improving management accuracy.

[0065] The present invention adopts the DTW algorithm to perform nonlinear alignment of time series data, allowing the time axis to be stretched and compressed, significantly improving the flexibility and accuracy of trend changes. Through a pre-built trend classification rule database, the DTW algorithm is combined with rule classification to improve the automation and real-time performance of trend identification. Using dynamic classification thresholds as the judgment criteria rather than fixed values ​​enhances the adaptability of the algorithm to different data types and rule complexities, solving the problem that the prior art relies on fixed intervals or linear time alignment methods and has poor robustness to data noise and nonlinear time changes.

[0066] The present invention eliminates the error caused by nonlinear changes in time series data through the DTW algorithm, and can accurately measure the similarity between the current time series data and the regular time series data. The DTW algorithm can process large-scale time series data in a short time, has high robustness to noise data, and can operate stably when there are missing or abnormal data. By calculating the dynamic time warping value and combining it with the classification rule database, the state trend can be intuitively displayed on the visualization terminal, which is convenient for users to quickly understand the device status.

[0067] The present invention determines the similarity between the current time series data and the regular time series data through the dynamic time warping value, and then obtains the state trend. The state trend of the current time series data is analyzed through the trend classification rule to determine the operating state trend of the secondary equipment, and abnormal conditions such as faults can be predicted in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 It is a schematic diagram of the application environment of the visual monitoring method of substation secondary equipment of the present invention;

[0069] Figure 2 It is a flow chart of a visual monitoring method for secondary equipment of a substation according to the present invention;

[0070] Figure 3 It is a schematic diagram of a visual monitoring device for secondary equipment of a substation according to the present invention;

[0071] Figure 4 It is a structural schematic diagram of the electronic device of the present invention. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only embodiments of a part of the present invention, rather than all embodiments. Based on the spirit of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the protection scope of the present invention.

[0073] Embodiment 1 of the present invention provides a visual monitoring method for secondary equipment in a substation, which can be applied to, but not limited to, Figure 1 See the environment shown. Figure 1 The visual processing terminal 101 of the secondary equipment of the substation may be, but is not limited to, a host computer, a desktop computer, a laptop computer, etc. with local computing capabilities. The visual processing terminal 101 of the secondary equipment of the substation may be, but is not limited to, communicating with the data acquisition terminal 102 and the visual display terminal 103 through the network. The visual display terminal 103 may be, but is not limited to, a liquid crystal display screen. The above-mentioned visual processing terminal 101 of the secondary equipment of the substation may include, but is not limited to, a human-computer interaction screen, a processor, and a memory. The above-mentioned processor may be, but is not limited to, used to respond to human-computer interaction operations, perform corresponding operations, or generate corresponding instructions, and send the generated instructions to the visual display terminal 103. The above-mentioned memory is used to store relevant storage data, such as the target secondary equipment model, status evaluation results, and status trend.

[0074] Further preferably, the information may be collected through the data collection terminal 102, for example, the SCD file of the target substation and the status information of the secondary equipment in the target substation may be collected and preprocessed.

[0075] The following steps in the substation secondary equipment visualization monitoring method can be performed on the substation secondary equipment visualization processing terminal 101:

[0076] Obtaining the SCD file of the target substation and the status information of the secondary equipment in the target substation;

[0077] Generate an initial secondary equipment model according to the point cloud data corresponding to the secondary equipment and the SCD file;

[0078] According to the SCD file, a secondary signal loop is obtained, and according to the secondary signal loop, a state of the initial secondary device model is changed to obtain a target secondary device model;

[0079] Obtaining a state evaluation result and a state trend according to the state information, the state evaluation model, and the trend classification rule database;

[0080] The target secondary equipment model, status evaluation results and status trend are transmitted to a pre-configured visualization display terminal to realize visualization display of the secondary equipment.

[0081] Further preferably, the visualization display terminal 103 can obtain the target secondary equipment model, state evaluation result and state trend transmitted by the substation secondary equipment visualization processing terminal 101 and then perform visualization display.

[0082] Based on the above method, a target secondary equipment model that can be visualized is obtained according to the SCD file. Through the target secondary equipment model, the substation staff can remotely monitor the secondary equipment in real time, thereby improving the efficiency of secondary equipment status management. The status evaluation results and status trends are combined with the target secondary equipment model for visualization. Compared with the manual method, it can improve the accuracy of secondary equipment status management. At the same time, it can also display the status of the secondary equipment to the staff in real time, so that abnormal conditions such as faults can be handled in time.

[0083] Optionally, in this embodiment, the above-mentioned substation secondary equipment visualization processing terminal 101 can be a terminal device configured with a target client, which can include but is not limited to at least one of the following: a laptop, a tablet computer, a handheld computer, a PAD, a desktop computer, etc. The target client can be a client that supports providing a visual monitoring application for substation secondary equipment, such as a video client, an instant messaging client, a browser client, an education client, etc. The above-mentioned network can include but is not limited to: a wired network, a wireless network, wherein the wired network includes: a local area network, a metropolitan area network and a wide area network, and the wireless network includes: Bluetooth, WIFI and other networks that realize wireless communication. The above is only an example, and this embodiment does not make any limitation to this.

[0084] As an optional example, this embodiment does not limit the execution subject of the above-mentioned substation secondary equipment visualization monitoring method. Some or all steps of the above-mentioned substation secondary equipment visualization monitoring method can be executed on the substation secondary equipment visualization processing terminal 101. For example, when the substation secondary equipment visualization processing terminal 101 is a desktop computer, some or all steps of the above-mentioned substation secondary equipment visualization monitoring method can be executed on the desktop computer.

[0085] In one embodiment of the present invention, a method for visual monitoring of secondary equipment in a substation is provided. Figure 2 The visual monitoring method for substation secondary equipment includes the following steps S1 to S5:

[0086] S1: Obtain the SCD file of the target substation and the status information of the secondary equipment in the target substation.

[0087] It should be noted that SCD is the abbreviation of substation configuration description in the IEC61850 standard for substations. The SCD file is the system configuration file for the entire station, which is described in the SCL language.

[0088] S2: Generate an initial secondary device model according to the point cloud data corresponding to the secondary device and the SCD file, including:

[0089] S21: Obtaining point cloud data corresponding to the secondary equipment: Specifically, using a laser scanner or 3D photography technology, obtaining high-resolution point cloud data of the secondary equipment in the substation. These equipment may include relays, control switches, fuses, etc.

[0090] S22: Generating a three-dimensional model corresponding to the secondary device according to the point cloud data, including:

[0091] Apply machine learning algorithms (such as random forests or convolutional neural networks) to filter noise from the point cloud data to identify and remove erroneous points.

[0092] A spatial clustering algorithm (such as DBSCAN) is used to simplify the point cloud dataset, reduce the number of points, and keep the key features.

[0093] Extract geometric features such as edges, planes, and surfaces from point clouds using edge detection-based algorithms.

[0094] These characteristics help identify specific secondary device types.

[0095] Combined with computer vision technology, the point cloud blocks of each device are classified through a deep learning model to determine the type of device, such as relays, switches, etc. Compared with the traditional threshold-based point cloud processing method, this method uses machine learning technology to improve accuracy and reduce manual intervention.

[0096] Combined with the parametric modeling method, the geometric feature point cloud blocks are parameterized, and the parameterized geometric feature point cloud blocks are transmitted to the generative adversarial network GAN. By using the generative adversarial network (GAN) to generate the initial model, the shape of each device has a certain variability based on the actual data. The present invention uses the generative adversarial network (GAN) to generate the initial three-dimensional model, so that it conforms to the characteristics of the real world and has creative characteristics, rather than a simple geometric combination.

[0097] Functional verification of the initial 3D model is performed through computer-aided engineering (CAE) analysis to ensure that the model meets the standards in terms of physical and electrical characteristics, so as to foresee functional problems in the early stages of model generation.

[0098] Based on the results of functional verification, the characteristics of the model are refined through programmatic design algorithms (such as L-systems or divergent algorithms) to ensure that the key functions and characteristics of each device are preserved.

[0099] S23: Parse the SCD file to obtain infrastructure information, as well as mapping relationships between secondary devices and voltage levels, mapping relationships between secondary devices and their primary devices, mapping relationships between intervals and voltage levels, and mapping relationships corresponding to virtual terminals of the secondary devices;

[0100] S24: Associating the infrastructure information, each mapping relationship and the three-dimensional model to obtain the initial secondary equipment model.

[0101] The infrastructure information includes substation name, substation description attribute value, voltage level name, voltage level description attribute value, bay name, bay description attribute value, secondary equipment attribute value, and secondary equipment information.

[0102] Exemplarily, through multi-level information association mapping, the association efficiency and accuracy between secondary devices in the substation or between the secondary devices and other devices are improved. In addition, the present invention generates an initial secondary device model based on the existing SCD file, and there is no need to make secondary changes to the existing SCD model file, thereby avoiding association errors caused by manual modification.

[0103] S3: obtaining a secondary signal loop according to the SCD file, and changing the state of the initial secondary device model according to the secondary signal loop to obtain a target secondary device model;

[0104] S31: According to the SCD file, a secondary signal loop is obtained:

[0105] Parsing the SCD file to obtain an accident signal, a warning signal, and a position signal;

[0106] Determine a signal sending device, a signal receiving device, and a signal receiving port according to the accident signal, the warning signal, and the position signal;

[0107] According to the signal sending device, the signal receiving device, and the signal receiving port, network cable loop deduction, electrical diagram analysis, and optical cable analysis are performed to obtain the secondary signal loop.

[0108] For example, in transformer substations and substations, in order to timely discover and analyze faults, quickly handle accidents, and coordinate production in a unified manner, in addition to relying on measuring instruments to monitor the operation of equipment, the staff also uses lighting and sound signal devices to reflect the normal and abnormal operation of equipment, which is a signal circuit. The types of signal circuit signals include accident signals, warning signals, and position signals. Among them, the accident signal is when the circuit breaker trips due to an accident, the relay protection action starts the buzzer to emit a strong sound to attract the attention of the operator, and the circuit breaker position indicator light flashes to indicate the object and nature of the accident; the warning signal is when the equipment fails and an abnormal operating condition occurs, the relay protection action starts the alarm and sounds, and the light sign with the nature of the fault is also lit, which can help the operator find faults and hidden dangers for timely handling; the position signal includes the position signal of the on-load tap changer of the circuit breaker, disconnector, contactor, and ionization transformer.

[0109] In this embodiment, the signal sending device, signal receiving device, and signal receiving port are determined based on the accident signal, warning signal, and position signal, and the query and positioning of the corresponding signal loop is realized according to the relationship between the signal sending device, signal receiving device, and signal receiving port, thereby reducing the dependence on the experience and level of the staff, improving work efficiency, and also improving management accuracy.

[0110] S32: changing the state of the initial secondary device model according to the secondary signal loop to obtain a target secondary device model;

[0111] Determine which secondary devices in the secondary signal loop need to be connected together and how to connect them. Adjust the device position and connection method in the initial secondary device model based on this connection information (signal flow direction, device terminals) to ensure that the model reflects the actual electrical connection relationship. You can also add virtual connecting lines to represent signal loops, such as using virtual wires to connect relays and circuit breakers.

[0112] S4: Obtaining a state evaluation result and a state trend according to the state information, the state evaluation model, and the trend classification rule database, including:

[0113] S41: Transmitting the state information to a pre-trained state evaluation model to obtain the state evaluation result; wherein the state evaluation model is specifically as follows:

[0114] The network structure includes: (1) an input layer that receives status information of secondary devices, such as current, voltage, temperature, humidity, vibration and other parameters collected in real time.

[0115] (2) Feature selection layer: Self-attention mechanism is used to weight input features to highlight important features and reduce the impact of noise. This mechanism enables the model to automatically select the information most relevant to the device status and improve accuracy.

[0116] (3) Multi-layer neural network, convolutional neural network (CNN) combined with long short-term memory network (LSTM). CNN is used for spatial feature extraction and identification of local correlation in state data. It is suitable for processing device state information with spatial characteristics. LSTM processes time series data and captures the time dependency of state changes to cope with the dynamic characteristics of input data.

[0117] (4) Fully connected layer: The outputs of the convolutional layer and the LSTM layer are integrated and enter multiple fully connected layers, where nonlinear mapping is performed through activation functions (such as ReLU) to obtain deeper feature representation.

[0118] (5) The output layer is a Softmax layer, which is used to provide status evaluation results and output possible equipment status categories (such as normal, fault warning, serious fault, etc.).

[0119] Model pre-training:

[0120] Collect long-term equipment data, including labeled data of normal operation and failure conditions, to improve model accuracy;

[0121] Labeling through expert knowledge or historical fault data ensures that all possible equipment operating states are included in the data set;

[0122] Use data enhancement techniques (such as noise addition, time window cutting, signal distortion, etc.) to generate more samples and improve the robustness of the model to different situations;

[0123] Pre-train the model on a large dataset of power equipment so that the model can be fine-tuned on a small dataset;

[0124] Use an adaptive learning rate optimizer (such as Adam or RMSprop) to dynamically adjust the learning rate according to the loss changes during model training to improve convergence speed and model performance;

[0125] Use the validation set to regularly evaluate the performance of the model, using different metrics (such as precision, recall, F1 value) for comprehensive evaluation;

[0126] Based on the results of multiple comprehensive evaluations, the outputs of multiple models are combined through an ensemble learning method to enhance the accuracy and reliability of state evaluation.

[0127] S42: extract the current time series data in the state information, call the target trend classification rule from a pre-built trend classification rule database according to the data type of the current time series data, and obtain the state trend corresponding to the current time series data according to the target trend classification rule.

[0128] The target trend classification rule includes rule time series data and classification thresholds. The state trend corresponding to the current time series data is obtained according to the target trend classification rule, including:

[0129] Calculate the current dynamic time warping value of the current time series data and the regular time series data by using the DTW algorithm, and compare the current dynamic time warping value with the classification threshold to obtain a comparison result;

[0130] Further preferably, the existing technologies mostly rely on fixed intervals or linear time alignment methods, which have poor robustness to data noise and nonlinear time changes. The present invention adopts the DTW algorithm, which can perform nonlinear alignment on time series data, allowing the time axis to be stretched and compressed, significantly improving the flexibility and accuracy of trend changes. Through a pre-built trend classification rule database, the DTW algorithm is combined with rule classification to improve the automation and real-time nature of trend identification. Using a dynamic classification threshold τ as the judgment criterion rather than a fixed value enhances the adaptability of the algorithm to different data types and rule complexities. Specifically as follows:

[0131] Extract the current time series data X from the status information 1 ,x 2 ,...,x n}, the length is n. Call the rule time series data Y from the target trend classification rule database = {y 1 ,y 2 ,...,y m}, length is m. Create a matrix D of size (n+1)×(m+1), and initialize the matrix value to infinity (∞). Initialize the starting point D(0,0) of the matrix to 0, that is, D(0,0)=0. Calculate the local distance of each pair of points: Use Euclidean distance to calculate the distance between the current timing point and the regular timing point: d(x i ,y j ). Fill the calculated local distance into the matrix D(i,j). Fill the matrix according to the dynamic programming rules:

[0132] D(i,j)=d(x i ,y j )+min{D(i-1,j),D(i,j-1),D(i-1,j-1)}

[0133] D(i-1,j) is the path for deleting the current timing point xi, D(i,j-1) is the path for inserting the rule timing point yj, and D(i-1,j-1) is the path for matching xi and yj.

[0134] Through the above recursive calculation, each value D(i,j) in the matrix represents the cumulative distance of the current point (i,j). The value D(n,m) in the lower right corner of the matrix is ​​the total dynamic time warping value (DTW distance) of the two time series. By backtracking from the end point to the starting point, find the set of points (i,j) that the path passes through to obtain the optimal alignment path for the current time series data and the regular time series data. Compare the calculated dynamic time warping value D(n,m) with the classification threshold τ in the target trend classification rule: If D(n,m)<τ, the current time series data conforms to the regular trend, and the corresponding state trend is obtained. If D(n,m)≥τ, the current time series data does not conform to the regular trend.

[0135] The above-mentioned DTW algorithm eliminates the errors caused by nonlinear changes in time series data, and can accurately measure the similarity between the current time series data and the regular time series data. Based on dynamic programming to calculate the cumulative distance, the algorithm complexity is reduced, and large-scale time series data can be processed in a short time. The algorithm has high robustness to noisy data and can run stably when there are missing or abnormal data. By calculating the dynamic time warping value and combining it with the classification rule database, the state trend can be intuitively displayed on the visualization terminal, which is convenient for users to quickly understand the device status.

[0136] When the comparison result is that the current dynamic time warping value is less than the classification threshold, the state trend is obtained according to the preset trend corresponding to the classification threshold.

[0137] Exemplarily, the DTW (Dynamic Time Warping) algorithm is used to obtain the DTW value of the current time series data and the regular time series data. The DTW value can be used to determine the similarity between the current time series data and the regular time series data, and then the state trend can be obtained. During the operation of the secondary equipment, a large amount of high-frequency time series data will be generated over time, and the high-frequency time series data needs to be segmented and counted. In this embodiment, the state trend of the current time series data is analyzed through the trend classification rule to determine the operating state trend of the secondary equipment, and abnormal conditions such as faults can be predicted in advance.

[0138] When the current dynamic time warping value (DTW value) is greater than or equal to the classification threshold, the state category of the device can be determined based on the characteristics of the original time series data corresponding to the DTW value. The DTW value range is divided into different state categories (such as: minor fault, major fault, normal state, etc.), and the corresponding thresholds are defined based on the trained model or historical data.

[0139] A variety of methods can be used, such as decision trees, support vector machines and other traditional classification algorithms to assist in classification.

[0140] The trend of the state can be deduced by comparing the change trend of current data and historical data. Time series analysis methods (such as sliding average, exponential smoothing, etc.) can be used to identify trends and periodicity in time series data. If the DTW value is greater than the threshold, it is interpreted as a possible change in state (possible failure). At this time, combined with the current and historical state information, trend models (such as ARIMA models, climate change models, etc.) are used to predict and model the future state.

[0141] S5: transmitting the target secondary equipment model, status evaluation results and status trend to a pre-configured visualization display terminal to realize visualization display of the secondary equipment, including:

[0142] S51: matching the state evaluation result with a pre-configured model state color library, changing the state color of the target secondary device model according to the matching result, and visually displaying the target secondary device model after the state color change;

[0143] In specific implementation, the status colors are green, yellow, and red;

[0144] Green indicates a good state, yellow indicates a warning state, and red indicates a serious fault state. Each state level can also be subdivided into multiple levels, for example, green can be subdivided into light green, medium green, and dark green, representing different degrees of good state.

[0145] Get the status evaluation result output by the status evaluation model, which may be a numerical value or a classification label.

[0146] According to the status evaluation result, the corresponding color code is searched in the model status color library. If the status evaluation result is a numerical value, it is mapped to the corresponding color interval in the color library according to the numerical value. If the status evaluation result is a classification label, it is directly mapped to the corresponding status color.

[0147] S52: combining the target secondary device model with the state trend, and performing layered visual display according to a user click instruction.

[0148] In specific implementation, one or more curves representing the state change trend are superimposed next to or on the three-dimensional model. The color of the curve can change according to the change of the trend, for example, green is used for an upward trend and red is used for a downward trend. Different line styles (such as dotted lines and solid lines) can be used to distinguish different trends. When the user clicks on a component of the equipment, the interface will display the historical status evaluation results and trend analysis chart of the component. The user can choose to view the status trend within a specific time period, or compare the status changes in different time periods.

[0149] By adopting the above-mentioned embodiment provided by the present invention, a target secondary equipment model that can be visualized is obtained according to the SCD file. Through the target secondary equipment model, the substation staff can remotely monitor the secondary equipment in real time, thereby improving the efficiency of secondary equipment status management; the status evaluation results and status trends are combined with the target secondary equipment model for visualization, which can improve the accuracy of secondary equipment status management compared with manual methods, and at the same time, the status of the secondary equipment can be displayed to the staff in real time, so that abnormal conditions such as faults can be handled in time.

[0150] Embodiment 2 of the present invention provides a visual monitoring device for secondary equipment in a substation, see Figure 3 , the device comprises:

[0151] An information acquisition module 301 is used to generate an initial secondary device model according to the point cloud data corresponding to the secondary device and the SCD file;

[0152] An initial model generation module 302 is used to obtain a secondary signal loop according to the SCD file, and to modify the state of the initial secondary device model according to the secondary signal loop to obtain a target secondary device model;

[0153] A model state changing module 303 is used to obtain a state evaluation result and a state trend according to the state information, the state evaluation model and the trend classification rule database;

[0154] The information processing module 304 is used to transmit the target secondary equipment model, state evaluation results and state trend to a pre-configured visualization display terminal for visualization of the secondary equipment;

[0155] The visualization display module 305 is used to transmit the target secondary equipment model, state evaluation results and state trend to a pre-configured visualization display terminal to perform visualization display of the secondary equipment.

[0156] The visual monitoring device for secondary equipment of a substation in the embodiment of the present invention obtains a target secondary equipment model that can be visually displayed according to the SCD file. Through the target secondary equipment model, the substation staff can remotely monitor the secondary equipment in real time, thereby improving the efficiency of secondary equipment status management; the status evaluation results and status trends are combined with the target secondary equipment model for visual display, which can improve the accuracy of secondary equipment status management compared with manual methods, and can also display the status of the secondary equipment to the staff in real time, so that abnormal conditions such as faults can be handled in time.

[0157] The specific embodiment of the visual monitoring device for substation secondary equipment in the present invention can refer to the example shown in Example 1, which will not be repeated here.

[0158] Embodiment 3 of the present invention provides an electronic device for implementing the above-mentioned visual monitoring method for substation secondary equipment. The electronic device includes a memory and a processor, the memory stores a computer program, and the processor is configured to execute the visual monitoring method for substation secondary equipment of embodiment 1 through the computer program.

[0159] See also Figure 4 The computer system 400 includes a central processing unit CPU 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory ROM 402 or the program loaded from the storage part 408 to the random access memory RAM 403, such as executing the method described in the above embodiment. Various programs and data required for system operation are also stored in the RAM 403. The CPU 401, the ROM 402 and the RAM 403 are connected to each other through a bus 404. The I / O interface 405 is also connected to the bus 404.

[0160] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0161] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit CPU401, various functions defined in the system of the present application are executed.

[0162] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0163] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0164] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0165] Embodiment 4 of the present invention provides a computer-readable storage medium, the computer-readable storage medium includes a stored computer program, wherein when the computer program is run, the visual monitoring method for substation secondary equipment of the above embodiment 1 is executed. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.

[0166] The computer program product or computer program of the present invention includes computer instructions, which are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the visual monitoring method for substation secondary equipment provided in the above-mentioned embodiments.

[0167] In summary, compared with the prior art, the beneficial effects of the present invention at least include:

[0168] The present invention obtains a target secondary equipment model that can be visualized according to the SCD file. Through the target secondary equipment model, the substation staff can remotely monitor the secondary equipment in real time, thereby improving the efficiency of secondary equipment status management.

[0169] The present invention combines the status evaluation results and status trends with the target secondary equipment model for visual display. Compared with the manual method, it can improve the accuracy of secondary equipment status management. At the same time, it can also display the status of the secondary equipment to the staff in real time, and can handle abnormal conditions such as faults in time.

[0170] When the present invention generates the initial secondary equipment model, the association efficiency and accuracy between the secondary equipment in the substation or between the secondary equipment and other equipment are improved through multi-level information association mapping; in addition, the present invention generates the initial secondary equipment model based on the existing SCD file, and there is no need to make secondary changes to the existing SCD model file, thereby avoiding association errors caused by manual modification.

[0171] The present invention performs network cable loop derivation, electrical diagram analysis and optical cable analysis based on the signal sending device, signal receiving device and signal receiving port to obtain a secondary signal loop. The signal sending device, signal receiving device and signal receiving port are determined based on the accident signal, warning signal and position signal, and query and locate the corresponding signal loop according to the relationship between the signal sending device, signal receiving device and signal receiving port, thereby reducing dependence on the experience and level of the staff, improving work efficiency and also improving management accuracy.

[0172] The present invention adopts the DTW algorithm to perform nonlinear alignment of time series data, allowing the time axis to be stretched and compressed, significantly improving the flexibility and accuracy of trend changes. Through a pre-built trend classification rule database, the DTW algorithm is combined with rule classification to improve the automation and real-time performance of trend identification. Using dynamic classification thresholds as the judgment criteria rather than fixed values ​​enhances the adaptability of the algorithm to different data types and rule complexities, solving the problem that the prior art relies on fixed intervals or linear time alignment methods and has poor robustness to data noise and nonlinear time changes.

[0173] The present invention eliminates the error caused by nonlinear changes in time series data through the DTW algorithm, and can accurately measure the similarity between the current time series data and the regular time series data. The DTW algorithm can process large-scale time series data in a short time, has high robustness to noise data, and can operate stably when there are missing or abnormal data. By calculating the dynamic time warping value and combining it with the classification rule database, the state trend can be intuitively displayed on the visualization terminal, which is convenient for users to quickly understand the device status.

[0174] The present invention determines the similarity between the current time series data and the regular time series data through the dynamic time warping value, and then obtains the state trend. The state trend of the current time series data is analyzed through the trend classification rule to determine the operating state trend of the secondary equipment, and abnormal conditions such as faults can be predicted in advance.

[0175] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A visual monitoring method for secondary equipment in a substation, characterized in that: The method comprises: Obtaining the SCD file of the target substation and the status information of the secondary equipment in the target substation; Generate an initial secondary equipment model according to the point cloud data corresponding to the secondary equipment and the SCD file; Obtaining a secondary signal loop according to the SCD file, and changing the state of the initial secondary device model according to the secondary signal loop to obtain a target secondary device model; Obtaining a state evaluation result and a state trend according to the state information, the state evaluation model, and the trend classification rule database; The target secondary equipment model, status evaluation results and status trend are transmitted to a pre-configured visualization display terminal for visualization of the secondary equipment.

2. The visual monitoring method for substation secondary equipment according to claim 1 is characterized in that: Generating an initial secondary equipment model according to the point cloud data corresponding to the secondary equipment and the SCD file, including: Acquire point cloud data corresponding to the secondary device; Generate a three-dimensional model corresponding to the secondary device according to the point cloud data; Parse the SCD file to obtain infrastructure information and a mapping relationship between secondary equipment and voltage levels, a mapping relationship between secondary equipment and its primary equipment, a mapping relationship between intervals and voltage levels, and a mapping relationship corresponding to virtual terminals of the secondary equipment; The basic structure information and each mapping relationship are associated with the three-dimensional model to obtain the initial secondary equipment model.

3. The visual monitoring method for substation secondary equipment according to claim 2 is characterized in that: Generating a three-dimensional model corresponding to the secondary device according to the point cloud data includes: Apply machine learning algorithms to filter noise from point cloud data to identify and remove error points; Use spatial clustering algorithm to simplify point cloud data, reduce the number of points, and keep key features; Extract geometric feature point cloud blocks from point clouds using edge detection-based algorithms; Combined with the parametric modeling method, the geometric feature point cloud blocks are parameterized and transmitted to the generative adversarial network (GAN). The GAN is used to generate the initial 3D model, so that the shape of each device has a certain degree of variability based on the actual data. Functional verification of the initial 3D model through computer-aided engineering (CAE) analysis to ensure that the model meets the standards in terms of physical and electrical characteristics; Based on the results of functional verification, the model's features are refined through programmatic design algorithms to ensure that the key functions and characteristics of each device are retained.

4. The visual monitoring method for substation secondary equipment according to claim 2 is characterized in that: The infrastructure information includes a substation name, a substation description attribute value, a voltage level name, a voltage level description attribute value, a bay name, a bay description attribute value, a secondary equipment attribute value, and secondary equipment information.

5. The visual monitoring method for substation secondary equipment according to claim 1 is characterized in that: A secondary signal loop is obtained according to the SCD file, including: Parsing the SCD file to obtain an accident signal, a warning signal, and a position signal; Determine a signal sending device, a signal receiving device, and a signal receiving port according to the accident signal, the warning signal, and the position signal; The secondary signal loop is obtained by performing network cable loop deduction, electrical diagram analysis and optical cable analysis based on the signal sending device, signal receiving device and signal receiving port.

6. The visual monitoring method for substation secondary equipment according to claim 1 is characterized in that: According to the state information, the state evaluation model, and the trend classification rule database, the state evaluation result and the state trend are obtained, including: Transmitting the state information to a pre-trained state evaluation model to obtain the state evaluation result; The current time series data in the state information is extracted, and according to the data type of the current time series data, the target trend classification rule is called from a pre-built trend classification rule database, and the state trend corresponding to the current time series data is obtained according to the target trend classification rule.

7. The visual monitoring method for substation secondary equipment according to claim 6 is characterized in that: The network structure of the state evaluation model includes: An input layer, which receives status information of secondary devices; Feature selection layer, which applies self-attention mechanism to perform feature weighting on the input state information; A multi-layer neural network layer that combines a convolutional neural network (CNN) with a long short-term memory (LSTM). CNN is used to extract spatial features and identify local correlations in state information, while LSTM is used to capture the temporal dependency of state changes to cope with the dynamic characteristics of input data. Fully connected layer, the output of CNN and LSTM is integrated into multiple fully connected layers, and nonlinear mapping is performed through activation functions to obtain deeper feature representation; The output layer is a Softmax layer, which is used to provide status evaluation results.

8. The visual monitoring method for substation secondary equipment according to claim 6 is characterized by: The pre-training process of the state evaluation model is: Collect equipment data in batches, including data under normal operation and fault conditions; Annotate the collected device data; Use data augmentation technology to enhance the labeled data, generate more samples, and obtain training sets and validation sets; Train the state evaluation model on the training set and use an adaptive learning rate optimizer to dynamically adjust the learning rate according to the loss changes during model training; Use validation sets to regularly evaluate the performance of the state evaluation model, and use precision, recall, and F1 value indicators for comprehensive evaluation; Based on the results of multiple comprehensive evaluations, the outputs of multiple state evaluation models are combined through an ensemble learning method to enhance the accuracy and reliability of the model state evaluation.

9. The visual monitoring method for substation secondary equipment according to claim 6, characterized in that: The target trend classification rule includes rule time series data and classification thresholds. The state trend corresponding to the current time series data is obtained according to the target trend classification rule, including: Calculate the current dynamic time warping value of the current time series data and the regular time series data by using the DTW algorithm, and compare the current dynamic time warping value with the classification threshold; When the current dynamic time warping value is less than the classification threshold, the state trend is obtained according to a preset trend corresponding to the classification threshold.

10. The visual monitoring method for substation secondary equipment according to claim 1, characterized in that: The target secondary equipment model, the status evaluation result and the status trend are transmitted to a pre-configured visualization display terminal for visualization of the secondary equipment, including: Matching the status evaluation result with a model status color library pre-configured in a visualization display terminal, changing the status color of the target secondary device model according to the matching result, and visually displaying the target secondary device model after the status color change; The target secondary equipment model is combined with the state trend, and a hierarchical visual display is performed according to the user's click instructions.

11. A visual monitoring device for secondary equipment in a substation, which implements the method according to any one of claims 1 to 10, characterized in that: The device comprises: An information acquisition module is used to acquire the SCD file of the target substation and the status information of the secondary equipment in the target substation; An initial model generation module, used to generate an initial secondary device model according to the point cloud data corresponding to the secondary device and the SCD file; A model state changing module, used for obtaining a secondary signal loop according to the SCD file, and changing the state of the initial secondary device model according to the secondary signal loop to obtain a target secondary device model; An information processing module, used to obtain a state evaluation result and a state trend according to the state information, the state evaluation model, and the trend classification rule database; The visualization display module is used to transmit the target secondary equipment model, state evaluation results and state trend to a pre-configured visualization display terminal for visualization display of the secondary equipment.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein the computer program executes the visual monitoring method for substation secondary equipment according to any one of claims 1 to 10 when running.

13. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to execute the visual monitoring method for substation secondary equipment according to any one of claims 1 to 10 through the computer program.

Images