Power transformation equipment fault early warning system and method fused with defect detection

Abstract

The invention discloses a power transformation equipment fault early warning system and method fused with defect detection, and relates to the technical field of fault early warning, and the method comprises the steps: obtaining a plurality of operation modes of power transformation equipment, carrying out the mode switching, and collecting a plurality of pieces of real-time operation data; through defect extraction, outputting a plurality of groups of defect feature vectors; carrying out fault event identification according to the multiple groups of defect feature vectors, outputting a matched fault event, and respectively calculating a plurality of corresponding risk indexes; and fusing the plurality of risk indexes, and generating a fault early warning signal according to the fused risk indexes to carry out fault early warning. The technical problems that an existing power transformation equipment fault early warning method only detects a single operation mode or specific defects, and fault early warning is poor in comprehensiveness and accuracy are solved, the real-time operation data under the multiple operation modes are fused, defect extraction and fault event recognition are carried out, and the fault early warning accuracy is improved. And the comprehensiveness and accuracy of fault early warning are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault warning, and in particular to a fault warning system and method for substation equipment integrating defect detection. Background Art

[0002] In modern power systems, substation equipment is an important part of the power grid, and its safe and stable operation is of vital importance. With the continuous increase of power load and the complexity of equipment operating environment, the failure risk faced by substation equipment is also increasing. Therefore, timely and accurate identification of potential failures and taking preventive measures have become the key to ensuring the reliability of the power system.

[0003] However, the existing fault warning methods for substation equipment often only detect a single operating mode or specific defects, lacking comprehensive consideration of different operating modes and multiple defect characteristics, resulting in poor comprehensiveness and accuracy of fault warning. Summary of the invention

[0004] The present application provides a substation equipment fault warning system and method integrating defect detection, which is used to solve the technical problem that the existing substation equipment fault warning method only detects a single operating mode or specific defects, and the comprehensiveness and accuracy of the fault warning are poor.

[0005] The first aspect of the present application provides a fault warning method for substation equipment integrating defect detection, the method comprising: obtaining multiple operating modes of the substation equipment; switching the modes of the substation equipment according to the multiple operating modes, and collecting multiple real-time operating data under the multiple operating modes; extracting defects from the multiple real-time operating data, and outputting multiple groups of defect feature vectors, wherein each operating mode corresponds to a group of defect feature vectors; identifying fault events of the substation equipment according to the multiple groups of defect feature vectors, and outputting matching fault events; under the condition of the matching fault events, respectively calculating multiple risk indicators corresponding to the multiple groups of defect feature vectors; fusing the multiple risk indicators to generate a fused risk indicator, generating a fault warning signal according to the fused risk indicator, and sending it to the host computer of the substation equipment for fault warning.

[0006] The second aspect of the present application provides a substation fault warning system integrating defect detection, the system comprising: an equipment operation mode acquisition module, the equipment operation mode acquisition module is used to acquire multiple operation modes of the substation; a real-time operation data acquisition module, the real-time operation data acquisition module is used to switch the mode of the substation according to the multiple operation modes, and collect multiple real-time operation data under multiple operation modes; a defect feature extraction module, the defect feature extraction module is used to extract defects from the multiple real-time operation data, and output multiple groups of defect feature vectors, wherein each operation mode corresponds to a group of defect feature vectors; a fault event identification module, the fault event identification module is used to identify fault events of the substation according to the multiple groups of defect feature vectors, and output matching fault events; a risk indicator calculation module, the risk indicator calculation module is used to respectively calculate multiple risk indicators corresponding to the multiple groups of defect feature vectors under the condition of the matching fault event; a fault warning module, the fault warning module is used to fuse the multiple risk indicators to generate a fused risk indicator, generate a fault warning signal according to the fused risk indicator, and send it to the host computer of the substation for fault warning.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The present application provides a substation equipment fault warning system and method integrating defect detection, which relate to the technical field of fault warning. The system acquires multiple operating modes of the equipment and switches them to collect real-time operating data, then extracts defects from these data to generate multiple groups of defect feature vectors, analyzes these feature vectors, identifies fault events and calculates corresponding risk indicators, integrates multiple risk indicators to generate comprehensive risk indicators, and issues fault warning signals based on the indicators to ensure timely response to potential faults. The system solves the technical problem that the existing substation equipment fault warning method only detects a single operating mode or specific defects, and the comprehensiveness and accuracy of the fault warning are poor. The system achieves the technical effect of integrating real-time operating data under multiple operating modes, extracting defects and identifying fault events, and improving the comprehensiveness and accuracy of the fault warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1A schematic flow chart of a method for early warning of a fault of a substation equipment integrating defect detection provided in an embodiment of the present application;

[0011] Figure 2 A schematic diagram of the structure of a fault warning system for substation equipment integrating defect detection provided in an embodiment of the present application.

[0012] Explanation of the reference numerals: equipment operation mode acquisition module 11, real-time operation data acquisition module 12, defect feature extraction module 13, fault event identification module 14, risk index calculation module 15, fault warning module 16. DETAILED DESCRIPTION

[0013] The present application provides a substation equipment fault warning system and method integrating defect detection, which is used to solve the technical problem that the existing substation equipment fault warning method only detects a single operating mode or specific defects, and the comprehensiveness and accuracy of the fault warning are poor.

[0014] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0015] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0016] Embodiment 1, as Figure 1 As shown, the present application provides a method for early warning of substation faults integrating defect detection, the method comprising:

[0017] P10: Obtain multiple operating modes of substation equipment.

[0018] Optionally, obtaining multiple operating modes of substation equipment is the first step in the fault warning method, which aims to fully grasp the operating characteristics of substation equipment under different working conditions. First, through in-depth analysis of the design documents, technical manuals and historical operation records of substation equipment, all possible operating modes of the equipment are clarified. These modes may include normal operating mode, emergency operating mode, maintenance mode, etc., each mode corresponds to different operating parameters and states. In this process, special attention should be paid to identifying those special operating modes that are crucial for equipment fault warning, because they often reveal the behavioral characteristics of the equipment under extreme or abnormal conditions.

[0019] Secondly, sensor technology and data acquisition systems are used to monitor the operating status of substation equipment in real time. These sensors can accurately measure key parameters such as voltage, current, temperature, etc. of the equipment, and transmit these data to the central processing unit in real time. By analyzing these data, the operating mode obtained through document analysis can be further verified and refined.

[0020] Next, pattern recognition techniques, such as cluster analysis, decision trees, or neural networks, are used to process the collected operating data. These techniques can extract representative and distinguishing features from a large amount of data, thereby accurately identifying the current operating mode of the substation equipment. For example, cluster analysis can classify similar operating states into the same category to form different operating mode clusters; decision trees gradually determine the operating mode of the equipment through a series of judgment conditions.

[0021] Finally, the identified operation modes are sorted and archived to form a substation equipment operation mode library. This library not only contains all possible operation modes of the equipment, but also records the typical characteristics, parameter ranges and possible fault types in each mode. It provides a solid foundation for subsequent mode switching, data collection, defect extraction and fault identification.

[0022] P20: Switching the mode of the power transformation equipment according to the multiple operation modes, and collecting multiple real-time operation data under the multiple operation modes.

[0023] Specifically, after completing the acquisition of multiple operating modes, the substation equipment needs to be dynamically switched according to the multiple operating modes. By adjusting the working state of the equipment in real time to collect real-time operating data in different modes, a comprehensive fault warning basis is provided.

[0024] First, the implementation of mode switching relies on automated control systems, which usually include embedded controllers and monitoring systems. These systems can automatically identify the current working state according to the set logical conditions and switch to the corresponding operating mode when necessary. For example, when the equipment detects load changes or temperature abnormalities, the system can automatically switch to troubleshooting mode to collect relevant data.

[0025] During the mode switching process, the collected data should cover key operating parameters, such as current, voltage, frequency, temperature, oil level, etc. These parameters can reflect the operating status of the equipment in different modes and help with subsequent fault analysis. Data collection can be achieved through sensors and real-time data acquisition systems to obtain real-time operating data in each operating mode, that is, dynamic data collected when the equipment is actually running. These data are crucial for timely detection of potential faults and will be stored in the database to form a comprehensive operating archive for subsequent defect extraction and fault identification.

[0026] In summary, through flexible mode switching and efficient data collection, comprehensive monitoring of substation equipment can be achieved, ensuring that detailed real-time operating data is collected under different working conditions, providing rich information support for the fault warning system, and making the assessment of equipment health status more accurate and reliable.

[0027] P30: Extract defects from the multiple real-time operation data, and output multiple groups of defect feature vectors, wherein each operation mode corresponds to a group of defect feature vectors.

[0028] It should be understood that after collecting multiple real-time operation data, the next step is to extract defects from these data to generate multiple sets of defect feature vectors. The defect feature vector is a quantitative representation of the potential failure of the equipment, which can reflect the health status of the equipment under different operation modes.

[0029] First, the process of defect extraction usually relies on signal processing and data analysis techniques. Common methods include time domain analysis, frequency domain analysis, and wavelet transform. These techniques can extract representative features from the original real-time data, such as vibration amplitude, frequency components, and waveform characteristics. Through these features, abnormal modes in equipment operation can be identified.

[0030] For each operating mode, the defect extraction process needs to set specific thresholds and algorithms to filter out possible defects from real-time data. For example, in normal operating mode, the feature value should be maintained within a certain range; if the data exceeds this range, it may indicate a potential failure of the equipment. In this case, the system automatically records the corresponding features and forms a defect feature vector.

[0031] Each set of defect feature vectors will correspond to the corresponding operating mode. This organization not only helps in the subsequent fault event identification, but also provides rich contextual information. For example, the feature vectors in a certain operating mode may be closely related to the performance of the equipment under high load, while another set may reflect the health indicators of the equipment in maintenance mode.

[0032] By systematically organizing the defect feature vectors under multiple operating modes, it can provide the necessary data basis for subsequent fault analysis and decision support. This method ensures comprehensive monitoring of the health status of the equipment, helps to identify and handle potential faults in a timely manner, and thus improves the reliability and safety of substation equipment.

[0033] P40: Identify fault events of the substation equipment according to the multiple groups of defect feature vectors, and output matching fault events.

[0034] Furthermore, step P40 of the embodiment of the present application also includes:

[0035] P41: Acquire multiple sets of training data sets, wherein the multiple sets of training data sets include multiple fault event samples, and multiple operating data samples of the substation equipment based on the multiple operating modes under each fault event sample; P42: Perform defect feature convolution on the multiple operating data samples, and output multiple defect feature samples; P43: Establish a mapping network between the multiple fault event samples and the multiple defect feature samples; P44: Construct a fault event recognition machine according to the mapping network, call the fault event recognition machine to match and identify the multiple sets of defect feature vectors, and output matching fault events.

[0036] Specifically, after obtaining multiple groups of defect feature vectors of the substation equipment, fault event recognition is performed, patterns matching known fault events are identified from these feature vectors, and matching fault events are output.

[0037] First, multiple sets of training data sets are obtained. These training data sets consist of multiple fault event samples, each of which contains operation data samples of substation equipment under multiple operation modes. These operation data samples are preprocessed and feature extracted, and can accurately reflect the operation status of the equipment under different fault events. The diversity and representativeness of the training data set are crucial to building an accurate fault event recognition model.

[0038] Next, defect feature convolution is performed on multiple operation data samples, and the defect features in the operation data samples are deeply extracted and encoded using technologies such as convolutional neural networks (CNN). The convolution operation can capture local features in the data, and gradually abstract higher-level feature representations through multi-layer convolution and pooling operations. The output is multiple defect feature samples, which contain feature information of the equipment under different fault events.

[0039] Then, a mapping network between multiple fault event samples and multiple defect feature samples is established. This step builds the mapping relationship between fault events and defect features through machine learning algorithms, such as support vector machines (SVM), neural networks (NN), or deep learning models. The mapping network can learn the complex relationship between fault events and features and achieve accurate classification of new feature vectors.

[0040] Finally, a fault event recognition machine is constructed according to the mapping network. The fault event recognition machine is a trained model that can match and recognize the input defect feature vector and output the matching fault event. In actual applications, the fault event recognition machine is called to process multiple groups of defect feature vectors, and the possible fault events of the equipment are determined according to the classification results in the mapping network.

[0041] Through the above steps, fault event identification not only depends on the accuracy of the data, but also depends on effective model construction and feature extraction technology to ensure that the fault status of the equipment can be accurately identified in different operating modes.

[0042] Further, a mapping network between the multiple fault event samples and the multiple defect feature samples is established. Step P43 of the embodiment of the present application further includes:

[0043] P43-1: The mapping network includes a first coding mapping network and a second association mapping network, and the first coding mapping network is connected to the second association mapping network; P43-2: wherein, the first coding mapping network is used to identify a one-to-many coding mapping relationship between each fault event sample and multiple defect feature samples; P43-3: the second association mapping network is used to identify an association mapping relationship between association relationships between multiple operation data samples under each fault event sample.

[0044] Optionally, when establishing a mapping network between multiple fault event samples and multiple defect feature samples, first, a composite mapping network including a first encoding mapping network and a second association mapping network is constructed. The combination of the two networks aims to fully explore the complex relationship between fault events and defect features and improve the overall recognition capability of the system.

[0045] Specifically, the first encoding mapping network is responsible for identifying the one-to-many encoding mapping relationship between each fault event sample and multiple defect feature samples. This means that for each fault event sample, the first encoding mapping network can generate encoding representations of one or more defect feature samples, which accurately reflect the correspondence between the fault event and the defect feature. This one-to-many mapping relationship reflects the complexity and diversity of fault events, because the same fault event may cause a variety of different defect features. In order to achieve this mapping, encoder structures in deep learning can be used, such as autoencoders or variational autoencoders, which can extract low-dimensional, representative feature codes from high-dimensional data.

[0046] At the same time, the second association mapping network focuses on identifying the association between multiple operating data samples under each fault event sample. This association may be manifested as similarity, dependency, or causality between data. By constructing this association mapping, we can better understand how fault events affect the operating state of the equipment and the intrinsic connection between different operating states. In order to achieve association mapping, technologies such as graph neural networks or attention mechanisms can be used, which can capture the complex relationships between data and generate association matrices or attention weights that reflect these relationships.

[0047] In summary, by establishing a composite structure including the first coding mapping network and the second association mapping network, a deep mapping between fault event samples and defect feature samples can be achieved. This complex mapping relationship not only improves the accuracy of fault identification, but also provides a solid technical foundation for subsequent fault prediction and early warning, thereby enhancing the safety and reliability of substation equipment.

[0048] Furthermore, step P44 of the embodiment of the present application also includes:

[0049] P44-1: The fault event identification machine also includes an adversarial network, which is obtained by training a generator and a discriminator; P44-2: The generator is used to simulate each fault event sample, and the substation equipment generates samples based on multiple defect features of the multiple operating modes; P44-3: The discriminator is used to compare the multiple operating data samples of the multiple operating modes with the multiple defect feature generation samples output by the generator to obtain a comparison loss rate; P44-4: The generator is optimized according to the comparison loss rate until the comparison loss rate is less than the preset comparison loss rate, the generator and the discriminator converge, and the adversarial network is output.

[0050] It should be understood that the construction of the fault event recognition machine further enhances the intelligence of the system, especially by introducing an adversarial network to improve the accuracy and robustness of fault recognition. The adversarial network consists of two main components: a generator and a discriminator. The generator is responsible for generating samples similar to real data, while the discriminator is responsible for evaluating the authenticity of these samples. Through this adversarial training method, the generator and the discriminator compete with each other to continuously improve the recognition accuracy.

[0051] Among them, the function of the generator is to simulate multiple defect feature samples generated based on multiple operating modes under each fault event sample. The generator uses a deep learning model, such as a generative adversarial network (GAN), to generate new samples through input defect features. These samples should not only reflect the potential failures of the equipment, but also simulate the data characteristics under real operating conditions to a certain extent. The discriminator calculates the comparison loss rate by comparing the real operating data samples under multiple operating modes with the defect feature generation samples output by the generator. The comparison loss rate is an indicator to measure the difference between the generated sample and the real sample. The smaller it is, the more similar the generated sample is to the real data. The discriminator improves the recognition accuracy of real data by optimizing its own judgment ability.

[0052] The generator is optimized based on the calculated comparison loss rate. The goal is to continuously adjust the parameters of the generator until the comparison loss rate is lower than the preset threshold, which means that the difference between the samples generated by the generator and the real samples is small enough. In addition, when both the generator and the discriminator reach a convergence state, it indicates that the training of the adversarial network is complete and can effectively generate samples that are highly similar to real data.

[0053] By introducing adversarial networks, the fault event recognition machine can not only generate diverse defect feature samples, but also improve the generalization ability of the model and enhance the ability to identify unknown faults. This process provides stronger intelligent support for the fault warning system of substation equipment, thereby improving the overall operation safety and reliability.

[0054] Furthermore, the adversarial network is obtained by training the generator and the discriminator. Step P44-1 of the embodiment of the present application further includes:

[0055] P44-11: Randomly select an initial alternating step length; P44-12: Perform multiple rounds of alternating training on the generator and the discriminator according to the initial alternating step length to obtain the gradient changes of the generator and the gradient changes of the discriminator; P44-13: Identify the balance between the gradient changes of the generator and the gradient changes of the discriminator. If the balance is less than the preset balance, iteratively optimize the initial alternating step length according to the balance difference.

[0056] In a possible embodiment of the present application, in the process of building an adversarial network, the model is optimized by alternating training of the generator and the discriminator. Specifically, the system first randomly selects an initial alternating step size. The alternating step size refers to the frequency and amplitude of the parameters updated by the generator and the discriminator during the training process. A reasonable initial alternating step size can effectively promote the stability and convergence speed of the training process.

[0057] Next, the generator and the discriminator are trained alternately for multiple rounds according to the initial alternating step length. In each round of training, the generator is first updated to generate new defect feature samples; then, the discriminator updates its parameters to improve the ability to identify real samples and generated samples. During this process, the system records the gradient changes of the generator and the gradient changes of the discriminator. These gradients reflect the learning progress of the model in the current training state and can provide a basis for subsequent optimization.

[0058] Next, identify the balance of the gradient changes of the generator and the discriminator. The balance is an indicator to measure the difference in the learning progress of the two networks. If the learning progress of the generator is too fast and the discriminator cannot keep up, the quality of the samples generated by the generator may decrease, and vice versa. If the balance is less than the preset balance threshold, it indicates that the current training process is not balanced enough. At this time, the initial alternating step size is iteratively optimized according to the difference in balance.

[0059] By dynamically adjusting the alternating step size, the generator and the discriminator can achieve coordinated development, ensuring that the two maintain a good learning balance during the training process. This optimization strategy improves the stability and generation ability of the adversarial network, making the final generated samples more representative, thereby further improving the overall performance and accuracy of the fault event recognition machine.

[0060] Furthermore, step P40 of the embodiment of the present application also includes:

[0061] P44-5: According to the fault event identification machine, a match is performed according to the multiple groups of defect feature vectors to obtain a single matching fault event with a matching degree greater than a preset matching degree; P44-6: Feature association analysis is performed on the multiple groups of defect feature vectors to output feature associations; P44-7: A secondary match is performed in the single matching fault event according to the feature association to obtain a secondary matching fault event; P44-8: The event with the highest matching degree among the secondary matching fault events is output as the matching fault event.

[0062] Specifically, in order to further improve the accuracy and reliability of fault event identification, the fault event identification machine performs a series of detailed matching and analysis operations. First, the identification machine performs a match based on multiple groups of defect feature vectors to obtain fault events with a matching degree greater than a preset matching degree. The core of this step is to use a pre-trained model to compare the defect feature vector with known fault events, thereby screening out potential fault events that meet the conditions. The matching degree is a quantitative indicator that reflects the similarity between the feature vector and the fault event. A higher matching degree indicates that the feature vector has a strong correlation with the fault event.

[0063] Next, feature correlation analysis is performed on multiple groups of defect feature vectors to explore the relationship between each defect feature, and the potential connection between features is revealed through statistical analysis methods (such as correlation analysis or principal component analysis). Feature correlation can help identify which features are most critical to the judgment of fault events and provide a reference for subsequent matching.

[0064] Furthermore, according to the feature correlation obtained by analysis, a secondary match is performed in the fault events that have been matched once. For the fault events that have been screened, the feature correlation is used to further optimize the matching results. Through more refined comparison, more accurate fault events can be identified and the accuracy of identification can be improved. Finally, the event with the highest matching degree in the secondary matching is output as the final matching fault event, ensuring that the recognition machine can provide the most credible fault judgment result, which is convenient for subsequent maintenance and decision-making.

[0065] Through the implementation of these steps, the fault event identification machine can not only realize the preliminary screening of potential faults, but also further improve the accuracy and reliability of the identification results through in-depth analysis and secondary matching, providing strong support for fault warning of substation equipment.

[0066] P50: Under the condition of the matching fault event, a plurality of risk indicators corresponding to the plurality of groups of defect feature vectors are respectively calculated.

[0067] It should be understood that for the identified matching fault events, multiple risk indicators corresponding to multiple groups of defect feature vectors are calculated. The goal of this process is to quantify the impact of potential faults on the safe operation of substation equipment, thereby providing a basis for subsequent risk assessment and decision-making.

[0068] First, the calculation of risk indicators is usually based on key data extracted from defect feature vectors. These feature vectors may include information such as abnormal values ​​of operating parameters, failure frequency, and defect severity. With these data, risk assessment methods in statistics and engineering, such as fault tree analysis (FTA) or failure mode and effect analysis (FMEA), can be used to evaluate the risk level of each defect feature.

[0069] During this process, the system compares each set of defect feature vectors with the preset risk criteria and calculates risk indicators associated with the features. For example, some features may indicate overheating during equipment operation, which can be quantified by deviations from temperature thresholds. Other features may be related to the vibration pattern of the equipment, in which case the corresponding risk can be calculated based on the abnormal values ​​of the vibration frequency. At the same time, the system can also use machine learning algorithms, such as regression analysis or decision trees, to predict risk indicators, and by analyzing historical data, establish a relationship model between defect features and failure risks, and provide more accurate risk assessment results.

[0070] The calculated multiple risk indicators will provide basic data for subsequent risk integration. These indicators not only help identify the current equipment status, but also provide guidance for operators to formulate corresponding maintenance strategies, conduct preventive maintenance in advance, and reduce the probability of failure. Through such risk indicator calculations, the fault event identification system can comprehensively evaluate the operational safety of substation equipment and provide data support for timely decision-making, thereby effectively improving the overall reliability and safety of the equipment.

[0071] P60: Fusing the multiple risk indicators to generate a fused risk indicator, generating a fault warning signal according to the fused risk indicator, and sending the signal to the host computer of the substation equipment for fault warning.

[0072] Furthermore, step P60 of the embodiment of the present application further includes:

[0073] P61: Calculate the mode importance of the multiple operating modes respectively; P62: Perform weight configuration based on the mode importance, fuse the multiple risk indicators according to the configured weights, and generate a fused risk indicator.

[0074] Optionally, a comprehensive fusion risk indicator is generated by fusing multiple risk indicators, and then a fault warning signal is generated and sent to the host computer of the substation equipment to ensure timely response to potential faults.

[0075] First, based on the calculation of multiple risk indicators, it can be found that although these risk indicators each reflect different aspects of equipment failure, direct addition or simple averaging may not accurately reflect the overall risk level. Therefore, the concept of mode importance is introduced to consider the contribution of different operating modes to the risk of equipment failure. The system needs to calculate the mode importance of multiple operating modes separately. Mode importance is an indicator to evaluate the contribution of each operating mode to the overall safety and operating efficiency of the equipment. This process is usually based on historical data analysis and expert knowledge, and determines the relative importance of each mode in fault warning through quantitative methods (such as weight calculation or sensitivity analysis). For example, some modes may show higher sensitivity under specific faults, so their importance is relatively high.

[0076] Next, weights are configured based on the calculated importance of the patterns. This means that when merging risk indicators, risk indicators of different patterns will be assigned different weights to reflect their actual influence in fault warning. In this way, patterns with higher importance will have a greater impact on the final fused risk indicator, while patterns with lower importance will have their influence reduced accordingly.

[0077] Furthermore, the generation process of the fusion risk index involves weighted summing of each risk index according to the configured weights. In this way, the final fusion risk index not only integrates multiple risk factors, but also considers the contribution of different modes to fault warning. This index provides a comprehensive assessment of the equipment operation status and can effectively indicate potential fault risks.

[0078] Finally, based on the generated fusion risk indicators, a fault warning signal is issued and sent to the host computer of the substation equipment. This signal not only reminds operators to pay attention to potential faults, but also triggers automated response measures, such as adjusting equipment operating parameters or starting preventive maintenance procedures. Through this series of steps, the fault warning system can effectively integrate various risk information and provide timely and accurate warnings, greatly improving the safety and operational reliability of substation equipment.

[0079] In summary, the embodiments of the present application have at least the following technical effects:

[0080] This application acquires multiple operating modes of the equipment and switches them to collect real-time operating data, then extracts defects from these data to generate multiple sets of defect feature vectors, identifies fault events and calculates corresponding risk indicators by analyzing these feature vectors, fuses multiple risk indicators to generate a comprehensive risk indicator, and issues a fault warning signal based on the indicator to ensure timely response to potential faults.

[0081] The technical effect of integrating real-time operating data under multiple operating modes to extract defects and identify fault events has been achieved, thereby improving the comprehensiveness and accuracy of fault warning.

[0082] Embodiment 2 is based on the same inventive concept as the method for early warning of power substation faults integrating defect detection in the above embodiment. Figure 2 As shown, the present application provides a substation fault warning system integrating defect detection, and the system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0083] The device operation mode acquisition module 11 is used to acquire multiple operation modes of the power transformation equipment.

[0084] The real-time operation data collection module 12 is used to switch the mode of the power transformation equipment according to the multiple operation modes and collect multiple real-time operation data under the multiple operation modes.

[0085] The defect feature extraction module 13 is used to extract defects from the multiple real-time operation data and output multiple groups of defect feature vectors, wherein each operation mode corresponds to a group of defect feature vectors.

[0086] The fault event identification module 14 is used to identify fault events of the substation equipment according to the multiple groups of defect feature vectors and output matching fault events.

[0087] The risk indicator calculation module 15 is used to respectively calculate a plurality of risk indicators corresponding to the plurality of groups of defect feature vectors under the condition of the matching fault event.

[0088] The fault warning module 16 is used to fuse the multiple risk indicators to generate a fused risk indicator, generate a fault warning signal according to the fused risk indicator, and send it to the host computer of the substation equipment for fault warning.

[0089] Furthermore, the fault event identification module 14 is further configured to perform the following steps:

[0090] Acquire multiple sets of training data sets, the multiple sets of training data sets include multiple fault event samples, and multiple operation data samples of the substation equipment based on the multiple operation modes under each fault event sample; perform defect feature convolution on the multiple operation data samples, and output multiple defect feature samples; establish a mapping network between the multiple fault event samples and the multiple defect feature samples; construct a fault event recognition machine according to the mapping network, call the fault event recognition machine to match and recognize the multiple sets of defect feature vectors, and output matching fault events.

[0091] Furthermore, the fault event identification module 14 is further configured to perform the following steps:

[0092] A mapping network between the multiple fault event samples and the multiple defect feature samples is established, wherein the mapping network includes a first coding mapping network and a second association mapping network, and the first coding mapping network is connected to the second association mapping network; wherein the first coding mapping network is used to identify a one-to-many coding mapping relationship between each fault event sample and multiple defect feature samples; and the second association mapping network is used to identify an association mapping relationship between association relationships between multiple operation data samples under each fault event sample.

[0093] Furthermore, the fault event identification module 14 is further configured to perform the following steps:

[0094] The fault event identification machine also includes an adversarial network, which is obtained by training a generator and a discriminator; the generator is used to simulate that under each fault event sample, the substation equipment generates samples based on multiple defect features of the multiple operating modes; the discriminator is used to compare the multiple operating data samples of the multiple operating modes with the multiple defect feature generation samples output by the generator to obtain a comparison loss rate; the generator is optimized according to the comparison loss rate until the comparison loss rate is less than the preset comparison loss rate, the generator and the discriminator converge, and the adversarial network is output.

[0095] Furthermore, the fault event identification module 14 is further configured to perform the following steps:

[0096] Randomly select an initial alternating step length; perform multiple rounds of alternating training on the generator and the discriminator according to the initial alternating step length to obtain the gradient change of the generator and the gradient change of the discriminator; identify the balance between the gradient change of the generator and the gradient change of the discriminator, and if the balance is less than a preset balance, iteratively optimize the initial alternating step length according to the balance difference.

[0097] Furthermore, the fault event identification module 14 is further configured to perform the following steps:

[0098] According to the fault event identification machine, a match is performed based on the multiple groups of defect feature vectors to obtain a first matching fault event with a matching degree greater than a preset matching degree; feature association analysis is performed on the multiple groups of defect feature vectors to output feature associations; a second match is performed in the first matching fault event based on the feature association to obtain a second matching fault event; and the event with the highest matching degree among the second matching fault events is output as the matching fault event.

[0099] Furthermore, the fault warning module 16 is further configured to perform the following steps:

[0100] The mode importances of the multiple operating modes are calculated respectively; weights are configured according to the mode importances, and the multiple risk indicators are fused according to the configured weights to generate a fused risk indicator.

[0101] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0102] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0103] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A fault early warning method for substation equipment integrating defect detection, characterized in that: The method comprises: Obtain multiple operating modes of substation equipment; Switching the mode of the power transformation equipment according to the multiple operation modes, and collecting multiple real-time operation data under the multiple operation modes; Extracting defects from the plurality of real-time operation data and outputting a plurality of groups of defect feature vectors, wherein each operation mode corresponds to a group of defect feature vectors; Identify fault events of the substation equipment according to the multiple groups of defect feature vectors, and output matching fault events; Under the condition of the matching fault event, respectively calculating a plurality of risk indicators corresponding to the plurality of groups of defect feature vectors; The multiple risk indicators are integrated to generate a fused risk indicator, a fault warning signal is generated according to the fused risk indicator, and the signal is sent to the host computer of the power transformation equipment for fault warning.

2. A method for early warning of power transformation equipment failures integrating defect detection as claimed in claim 1, characterized in that: The method includes: identifying fault events of the substation equipment according to the multiple groups of defect feature vectors and outputting matching fault events. Acquire multiple sets of training data sets, wherein the multiple sets of training data sets include multiple fault event samples and multiple operation data samples of the substation equipment based on the multiple operation modes under each fault event sample; Performing defect feature convolution on the multiple operation data samples, and outputting multiple defect feature samples; Establishing a mapping network between the plurality of fault event samples and the plurality of defect feature samples; A fault event recognition machine is constructed according to the mapping network, and the fault event recognition machine is called to match and recognize the multiple groups of defect feature vectors, and a matching fault event is output.

3. A method for early warning of power transformation equipment failure integrating defect detection as claimed in claim 2, characterized in that: Establishing a mapping network between the multiple fault event samples and the multiple defect feature samples, the mapping network comprising a first coding mapping network and a second association mapping network, wherein the first coding mapping network is connected to the second association mapping network; The first coding mapping network is used to identify a one-to-many coding mapping relationship between each fault event sample and multiple defect feature samples; The second association mapping network is used to identify an association mapping relationship of association relationships between multiple operation data samples under each fault event sample.

4. A method for early warning of power transformation equipment failures integrating defect detection as claimed in claim 2, characterized in that: The fault event recognition machine also includes an adversarial network, which is obtained by training a generator and a discriminator; The generator is used to simulate that under each fault event sample, the substation equipment generates samples based on multiple defect characteristics of the multiple operation modes; The discriminator is used to compare the multiple operation data samples of the multiple operation modes with the multiple defect feature generation samples output by the generator to obtain a comparison loss rate; The generator is optimized according to the comparison loss rate until the comparison loss rate is less than a preset comparison loss rate, the generator and the discriminator converge, and the adversarial network is output.

5. A method for early warning of power transformation equipment failure integrating defect detection as claimed in claim 4, characterized in that: The adversarial network is obtained by training a generator and a discriminator, and the method further includes: Randomly select the initial alternation step size; Perform multiple rounds of alternating training on the generator and the discriminator according to the initial alternating step length to obtain the gradient change of the generator and the gradient change of the discriminator; The balance between the gradient change of the generator and the gradient change of the discriminator is identified, and if the balance is less than a preset balance, the initial alternating step size is iteratively optimized according to the balance difference.

6. A method for early warning of power transformation equipment failures integrating defect detection as claimed in claim 2, characterized in that: The fault event identification machine is called to match and identify the multiple groups of defect feature vectors and output matching fault events, the method comprising: According to the fault event identification machine, a match is performed according to the multiple groups of defect feature vectors to obtain a matching fault event with a matching degree greater than a preset matching degree; Performing feature correlation analysis on the multiple groups of defect feature vectors and outputting feature correlation; Performing a secondary match in the primary matching failure event according to the feature correlation to obtain a secondary matching failure event; The event with the highest matching degree among the secondary matching failure events is output as the matching failure event.

7. A method for early warning of power transformation equipment failures integrating defect detection as claimed in claim 1, characterized in that: The multiple risk indicators are integrated to generate a fused risk indicator, the method comprising: respectively calculating the mode importance of the plurality of operating modes; The weights are configured according to the importance of the modes, and the multiple risk indicators are fused according to the configured weights to generate a fused risk indicator.

8. A fault warning system for substation equipment integrating defect detection, characterized in that: The system comprises: A device operation mode acquisition module, wherein the device operation mode acquisition module is used to acquire multiple operation modes of the substation equipment; A real-time operation data acquisition module, the real-time operation data acquisition module is used to switch the mode of the substation equipment according to the multiple operation modes, and collect multiple real-time operation data under the multiple operation modes; A defect feature extraction module, the defect feature extraction module is used to extract defects from the multiple real-time operation data and output multiple groups of defect feature vectors, wherein each operation mode corresponds to a group of defect feature vectors; A fault event identification module, the fault event identification module is used to identify fault events of the substation equipment according to the multiple groups of defect feature vectors, and output matching fault events; A risk indicator calculation module, wherein the risk indicator calculation module is used to respectively calculate a plurality of risk indicators corresponding to the plurality of groups of defect feature vectors under the condition of the matching fault event; A fault warning module is used to fuse the multiple risk indicators to generate a fused risk indicator, generate a fault warning signal according to the fused risk indicator, and send it to the host computer of the substation equipment for fault warning.

Images