Power equipment detection method and device, computer storage medium and electronic equipment

By acquiring the initial operating parameters of power equipment, using pattern recognition algorithms for feature extraction and verification, and generating fault alarm information, the problem of low efficiency and low accuracy in power equipment fault detection is solved, achieving efficient and accurate fault detection and prediction.

CN118914696APending Publication Date: 2024-11-08STATE GRID BEIJING ELECTRIC POWER CO +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410953672.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-16
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Existing technologies for detecting faults in power equipment are inefficient and inaccurate, failing to meet the actual needs of power systems.

Method used

By acquiring the initial operating parameters of the target power equipment, feature extraction and verification are performed using pattern recognition algorithms to generate fault alarm information, including sensor network data processing, Fourier transform, pattern recognition algorithm training, and fault trend prediction.

Benefits of technology

It improves the efficiency and accuracy of power equipment fault detection, enables real-time monitoring and timely fault diagnosis of power equipment, and ensures the stability and security of the power system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118914696A_ABST
    Figure CN118914696A_ABST
Patent Text Reader

Abstract

The invention discloses a power equipment detection method and device, a computer storage medium and electronic equipment. The method relates to the field of line fault detection or other related fields, and comprises the following steps: obtaining initial operation parameters of target power equipment, and processing the initial operation parameters to obtain equipment operation data; performing feature extraction processing on the equipment operation data by using a pattern recognition algorithm to obtain equipment operation features, and verifying the equipment operation features to obtain a verification result; and when the verification result represents that the target power equipment is abnormal, generating fault alarm information according to the verification result. Through the fault detection method and device, the problems of low detection efficiency and low detection accuracy when fault detection is carried out on the power equipment in the prior art are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of line fault detection or other related fields, and in particular, to a detection method, device, computer storage medium and electronic device for power equipment. Background Art

[0002] In modern power systems, the reliability and stability of transmission and distribution lines are of vital importance. However, due to various external environmental factors and the influence of long-term operation, transmission and distribution lines are prone to various faults, such as aging, loose wiring, further leading to component disconnection, short circuit and ultimately insulation failure. If these faults are not discovered and handled in time, they may cause the power system to collapse, and in severe cases may pose a threat to personnel safety. Therefore, the development of effective fault detection and diagnosis technology has a significant impact on ensuring the stable operation of the power system.

[0003] Among the related technologies, the first method that can be used is the detection method of sensor network monitoring. This method arranges sensors at key locations of the transmission and distribution lines to monitor the operating status of the lines in real time. However, due to the limited coverage of the sensor network, this method cannot comprehensively monitor the status of all equipment; secondly, data preprocessing technology can also be used, but the existing data preprocessing methods are relatively simple and it is difficult to effectively handle complex noise and outliers; then, the operating characteristics of the equipment can be analyzed to identify the type and location of the fault, but the feature extraction and fault identification methods of this method are not precise enough to accurately determine the type and location of the fault of the electrical equipment; finally, based on historical data and failure modes, equipment failures are predicted and preventive maintenance suggestions are proposed, but the accuracy of fault prediction and preventive maintenance suggestions in this method is not high and cannot meet the actual needs of the power system.

[0004] With regard to the problems of low detection efficiency and low detection accuracy when performing fault detection on power equipment in related technologies, no effective solution has been proposed so far. Summary of the invention

[0005] The main purpose of the present application is to provide a detection method, device, computer storage medium and electronic device for electric equipment to solve the problems of low detection efficiency and low detection accuracy when performing fault detection on electric equipment in related technologies.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a detection method for electric power equipment is provided. The method comprises: obtaining initial operating parameters of the target electric power equipment, processing the initial operating parameters, and obtaining equipment operating data; performing feature extraction processing on the equipment operating data using a pattern recognition algorithm to obtain equipment operating features, and verifying the equipment operating features to obtain verification results; when the verification results indicate that the target electric power equipment is abnormal, generating fault alarm information according to the verification results.

[0007] Furthermore, obtaining the initial operating parameters of the target power equipment includes: receiving a device detection request, activating a sensor network within the target power equipment according to the device detection request, wherein the device detection request refers to a request for performing fault detection on the target power equipment, and the sensor network includes at least a current transformer, a voltage transformer, a temperature sensor, and a vibration sensor; when the sensor network operates based on the device detection request, receiving operating parameters collected by the sensor network to obtain initial operating parameters.

[0008] Furthermore, the initial operating parameters are processed to obtain the equipment operating data, including: dividing the initial operating parameters according to the time series to obtain M time domain operating parameters, where M is a positive integer; performing Fourier transform processing on the M time domain operating parameters to obtain M frequency domain operating parameters, inputting the M frequency domain operating parameters into a filter, and outputting M processed frequency domain operating parameters; performing inverse Fourier transform processing on the M processed frequency domain operating parameters to obtain M processed time domain operating parameters, and the M processed time domain operating parameters constitute the equipment operating data.

[0009] Furthermore, the equipment operation data is subjected to feature extraction processing using a pattern recognition algorithm to obtain equipment operation characteristics, including: obtaining a preset state list, wherein the preset state list includes N equipment states of the target power equipment, and N is a positive integer; training the pattern recognition algorithm according to the preset state list to obtain a target recognition algorithm; and the equipment operation data is subjected to feature extraction processing using the target recognition algorithm to obtain N operation characteristics, and the N operation characteristics constitute the equipment operation characteristics.

[0010] Furthermore, the equipment operation characteristics are verified to obtain the verification results, including: obtaining a fault mode feature library, wherein the fault mode feature library contains N fault modes associated with N equipment states and an operation threshold value of each fault mode; matching the N operation characteristics contained in the equipment operation characteristics with the N fault modes to obtain N groups of features to be processed, and comparing the operation characteristics and the operation threshold values ​​in each group of features to be processed; if there is a target operation characteristic that does not meet any of the N operation thresholds, determining the fault area according to the target operation characteristic, and forming a verification result by the fault area and the fault mode associated with the target operation characteristic; when all N operation characteristics meet the N operation thresholds, determining the verification result as a result that the target power equipment is normal.

[0011] Furthermore, generating fault alarm information based on the verification result includes: calculating the difference between the target operating characteristic and the corresponding operating threshold to obtain the operating difference, and generating first fault information when the operating difference is greater than a first difference threshold, and determining fault alarm information based on the first fault information, wherein the first fault information indicates that the target power equipment has a minor fault; generating second fault information when the operating difference is greater than a second difference threshold, and determining fault alarm information based on the second fault information, wherein the first difference threshold is less than the second difference threshold, and the second fault information indicates that the target power equipment has a severe fault.

[0012] Furthermore, after generating fault alarm information according to the verification results, the method also includes: obtaining historical operation data and historical fault modes of the target power equipment in the historical time period, and forming a sample training set with the historical operation data and historical fault modes; obtaining a preset fault trend prediction model, and using the sample training set to train the preset fault detection model to obtain a fault trend prediction model; inputting the equipment operation data into the fault trend prediction model, outputting the fault trend information, and sending the fault trend information and fault alarm information to maintenance personnel.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a detection device for electric power equipment is provided. The device comprises: a first acquisition unit, used to acquire the initial operating parameters of the target electric power equipment, process the initial operating parameters, and obtain the equipment operating data; a processing unit, used to perform feature extraction processing on the equipment operating data using a pattern recognition algorithm, obtain the equipment operating characteristics, and verify the equipment operating characteristics to obtain the verification results; a generation unit, used to generate fault alarm information according to the verification results when the verification results indicate that the target electric power equipment is abnormal.

[0014] According to another aspect of an embodiment of the present invention, a computer storage medium is provided. The computer storage medium is used to store a program. When the program is executed, the device where the computer storage medium is located is controlled to execute a method for detecting an electric power device.

[0015] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising one or more processors and a memory; the memory stores computer-readable instructions, and the processor is used to execute the computer-readable instructions, wherein a detection method for electrical equipment is executed when the computer-readable instructions are executed.

[0016] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, a detection method for an electric power device is executed.

[0017] Through the present application, the following steps are adopted: obtaining the initial operating parameters of the target power equipment, processing the initial operating parameters, and obtaining the equipment operating data; using a pattern recognition algorithm to perform feature extraction processing on the equipment operating data to obtain equipment operating characteristics, and verifying the equipment operating characteristics to obtain verification results; when the verification result indicates that the target power equipment is abnormal, generating fault alarm information according to the verification result, thereby solving the problems of low detection efficiency and low detection accuracy in fault detection of power equipment in the related technology, by obtaining the equipment operating data after preprocessing of the target power equipment, using a pattern recognition algorithm to perform feature extraction processing on the equipment operating data to obtain equipment operating characteristics, and then determining the verification result according to the equipment operating characteristics, and using the verification result to judge the fault condition of the target power equipment. If the target power equipment is abnormal, fault alarm information can be generated according to the verification result, thereby achieving the effect of improving the efficiency and accuracy of verifying the power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 is a flow chart of a detection method for electric power equipment provided in an embodiment of the present application;

[0020] Figure 2 is a schematic diagram of a method for determining a verification result provided in an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of a detection device for electric power equipment provided according to an embodiment of the present application;

[0022] Figure 4is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 interchanged where appropriate, so that the embodiments of the present invention 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 device 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 units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0027] It should be noted that the collected information used in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse to use it.

[0028] The present invention is described below in conjunction with preferred implementation steps. Figure 1 is a flow chart of a detection method for electric power equipment provided in an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0029] Step S101, acquiring initial operating parameters of a target power device, and processing the initial operating parameters to obtain device operating data.

[0030] Specifically, the target power equipment may be a high-voltage power transmission and transformation electrical equipment, and the initial operating parameters may be data collected by a sensor network installed on the high-voltage power transmission and transformation electrical equipment, for example, the initial operating parameters may be voltage, current, power, temperature, pressure, frequency, etc. In order to perform feature extraction processing on the initial operating parameters, and then identify the device state of the above-mentioned target power equipment based on the extracted features, it is necessary to perform preprocessing operations on the initial operating parameters, for example, denoising, data cleaning, abnormal value detection and processing, etc., on the initial operating parameters, and then obtain the device operation data.

[0031] Step S102, using a pattern recognition algorithm to perform feature extraction processing on the equipment operation data to obtain equipment operation features, and verifying the equipment operation features to obtain verification results.

[0032] Specifically, after processing the initial operating parameters and obtaining the equipment operating data, a pattern recognition algorithm can be used to extract features from the equipment operating data to identify the equipment operating characteristics that characterize the operating status of the target electrical equipment, and compare and verify the characteristics with the fault modes in the preset fault mode feature library to determine whether the target electrical equipment has a fault problem.

[0033] Step S103: when the verification result indicates that the target power equipment is abnormal, generate fault alarm information according to the verification result.

[0034] Specifically, if the verification result indicates that there is an equipment failure in the target electrical equipment, the verification result can be processed to determine the location information of the fault area in the target electrical equipment and the severity of the fault, and finally generate fault alarm information and push the fault alarm information.

[0035] The detection method of electric power equipment provided in the embodiment of the present application obtains the initial operating parameters of the target electric power equipment, processes the initial operating parameters, and obtains the equipment operating data; uses a pattern recognition algorithm to perform feature extraction processing on the equipment operating data to obtain the equipment operating characteristics, and verifies the equipment operating characteristics to obtain a verification result; when the verification result indicates that the target electric power equipment is abnormal, fault alarm information is generated according to the verification result, which solves the problems of low detection efficiency and low detection accuracy in fault detection of electric power equipment in the related technology, obtains the equipment operating data after preprocessing of the target electric power equipment, uses a pattern recognition algorithm to perform feature extraction processing on the equipment operating data to obtain the equipment operating characteristics, and then determines the verification result according to the equipment operating characteristics, and uses the verification result to judge the fault condition of the target electric power equipment. If the target electric power equipment is abnormal, fault alarm information can be generated according to the verification result, thereby achieving the effect of improving the efficiency and accuracy of verifying the electric power equipment.

[0036] The initial operating parameters can be acquired by a sensor network set on the power equipment. Optionally, in the detection method of power equipment provided in an embodiment of the present application, acquiring the initial operating parameters of the target power equipment includes: receiving a device detection request, activating the sensor network in the target power equipment according to the device detection request, wherein the device detection request refers to a request for fault detection on the target power equipment, and the sensor network includes at least a current transformer, a voltage transformer, a temperature sensor and a vibration sensor; when the sensor network operates based on the device detection request, receiving the operating parameters collected by the sensor network to obtain the initial operating parameters.

[0037] Specifically, when obtaining the operating parameters of the target power equipment, it is first necessary to receive the equipment detection request issued by the monitoring system, and then extract the specific requirements of fault detection from the equipment detection request, for example, obtaining the equipment name, equipment type and equipment location of the power equipment to be detected. After identifying the relevant information of the target power equipment, the sensor network in the target power equipment is activated, wherein the sensor network contains a variety of sensors that can collect different types of parameters, for example, the current transformer can measure the current magnitude and phase, and can also monitor the load condition of the electrical line; the voltage transformer can measure and record the voltage level; the temperature sensor can monitor the temperature change during the operation of the equipment; the vibration sensor can detect the vibration during the operation of the equipment.

[0038] Optionally, after the sensor network is activated, various types of operating parameters can be collected and used as initial operating parameters. This embodiment collects operating parameters of power equipment through the sensor network, thereby improving the safety and reliability of the power system and the accuracy of fault detection.

[0039] In order to eliminate periodic noise and abnormal values ​​in the initial operating parameters, optionally, in the detection method of the electric power equipment provided in the embodiment of the present application, the initial operating parameters are processed to obtain the equipment operating data, including: dividing the initial operating parameters according to the time series to obtain M time domain operating parameters, where M is a positive integer; performing Fourier transform processing on the M time domain operating parameters to obtain M frequency domain operating parameters, inputting the M frequency domain operating parameters into the filter, and outputting M processed frequency domain operating parameters; performing inverse Fourier transform processing on the M processed frequency domain operating parameters to obtain M processed time domain operating parameters, and the M processed time domain operating parameters constitute the equipment operating data.

[0040] Specifically, when processing data, it is first necessary to divide the initial operating parameters of the target power equipment according to the time series, and cut the continuous operating data into multiple discrete time periods, each of which contains a certain number of sample points. For example, if the target power equipment runs continuously for 24 hours, you can choose each hour as a time period, and then get 24 time domain operating parameters.

[0041] Optionally, a Fourier transform is performed on each time domain operating parameter to obtain multiple frequency domain operating parameters, wherein the Fourier transform is a mathematical tool for converting a time domain signal into a frequency domain signal, which can reveal the distribution of data at different frequencies. After obtaining the frequency domain operating parameters, these parameters need to be filtered. For example, a low-pass filter can retain the low-frequency components in the frequency domain operating parameters and remove the high-frequency components, while a band-pass filter can simultaneously retain the frequency components within a certain range. Therefore, a variety of filters can be selected to process the frequency domain operating parameters. After the filter processing, multiple processed frequency domain operating parameters can be obtained, and finally these parameters need to be converted back to the time domain, that is, the processed frequency domain operating parameters need to be inversely Fourier transformed to convert the frequency domain signal back to the time domain signal, so that the time sequence changes of the operating state of the processed equipment can be observed, and finally these parameters are aggregated to obtain the operating data of the target power equipment in the entire time period. This embodiment pre-processes the initial operating parameters by using Fourier transform to eliminate periodic noise and outliers, which can not only provide a deeper understanding of the operating state of the equipment, but also optimize the performance and reliability of the equipment through frequency domain analysis and filtering.

[0042] The equipment operation characteristics can be obtained by processing with a pattern recognition algorithm. Optionally, in the detection method for electric power equipment provided in an embodiment of the present application, a pattern recognition algorithm is used to perform feature extraction processing on the equipment operation data to obtain the equipment operation characteristics, including: obtaining a preset state list, wherein the preset state list includes N equipment states of the target electric power equipment, and N is a positive integer; training the pattern recognition algorithm according to the preset state list to obtain a target recognition algorithm; using the target recognition algorithm to perform feature extraction processing on the equipment operation data to obtain N operation characteristics, and the N operation characteristics constitute the equipment operation characteristics.

[0043] Specifically, after obtaining the equipment operation data by Fourier transform, the pattern recognition algorithm can be used to extract its features. First, a preset status list containing multiple equipment states of the target power equipment needs to be obtained. For example, the list contains equipment states of excessive load current and thermal damage. Then, the pattern recognition algorithm is trained using the preset status list to obtain a target recognition algorithm, wherein the pattern recognition algorithm can be, for example, a support vector machine model, a neural network model, and a decision tree model.

[0044] When the target recognition algorithm is used to perform feature extraction processing on the equipment operation data, key features can be accurately extracted based on the information of the target electrical equipment in different states. For example, if the temperature of the target electrical equipment does not exceed 25°C when it is in normal operation, when the target recognition algorithm is used to extract features, if there is temperature data exceeding 25°C in the equipment operation data, it can be used as an operation feature, that is, the data is determined as the equipment operation feature. This embodiment realizes accurate recognition and feature extraction of the equipment operation state by constructing a target recognition algorithm, thereby providing strong data support for equipment fault prevention.

[0045] Figure 2 is a schematic diagram of a method for determining a verification result according to an embodiment of the present application, such as Figure 2 As shown, optionally, in the detection method of the electric power equipment provided in the embodiment of the present application, the equipment operation characteristics are verified, and the verification result obtained includes:

[0046] Step S201: obtaining a fault mode feature library, wherein the fault mode feature library contains N fault modes associated with N types of device states and an operating threshold value for each fault mode.

[0047] Step S202, matching N operation characteristics included in the equipment operation characteristics with N fault modes to obtain N groups of characteristics to be processed, and comparing the operation characteristics and operation thresholds in each group of characteristics to be processed.

[0048] Step S203: If there is a target operation characteristic that does not satisfy any of the N operation thresholds, determine the fault area according to the target operation characteristic, and form a verification result by the fault area and the fault mode associated with the target operation characteristic.

[0049] Step S204: When the N operating characteristics all satisfy the N operating thresholds, the verification result is determined as a result that the target power equipment has no abnormality.

[0050] Specifically, in order to ensure the safe, stable and efficient operation of power equipment, verification can be performed based on a preset fault mode feature library, where the fault mode feature library contains multiple fault modes, for example, the fault mode may be abnormal temperature, excessive pressure, current fluctuation, voltage instability, etc., and each fault mode is set with a corresponding operating threshold, which can be determined based on the design parameters and historical operating data of the equipment.

[0051] Optionally, all operating features in the equipment operating features are matched with the fault modes contained in the fault mode feature library, that is, the fault mode corresponding to each operating feature is confirmed, and then the operating feature is compared with the operating threshold of the corresponding fault mode to determine whether each operating feature exceeds the corresponding operating threshold. If there is at least one operating feature that exceeds the corresponding operating threshold, the fault area can be determined based on the correlation between this feature and the fault mode. After further analyzing the fault mode related to the fault area in the fault mode feature library, a verification result is constructed, wherein the verification result can include not only detailed information on the fault area, but also the cause of the fault and recommended countermeasures.

[0052] If the collected operating characteristics all meet the corresponding operating thresholds, it can be considered that the target power equipment is operating normally and without abnormalities, and the verification result will be determined as "the target power equipment has no abnormalities", thereby avoiding unnecessary intervention and waste of resources. This embodiment verifies the equipment operating characteristics of the target power equipment using the fault mode feature library, which can achieve real-time monitoring and timely fault diagnosis of the power equipment, greatly improve the operating efficiency and safety of the equipment, and at the same time, provide strong data support and decision-making basis for the maintenance and optimization of the power system.

[0053] Fault alarm information may include multiple types. Optionally, in the detection method of electric power equipment provided in an embodiment of the present application, generating fault alarm information based on the verification result includes: calculating the difference between the target operating characteristic and the corresponding operating threshold to obtain the operating difference, and when the operating difference is greater than the first difference threshold, generating the first fault information, and determining the fault alarm information based on the first fault information, wherein the first fault information indicates that the target electric power equipment has a minor fault; when the operating difference is greater than the second difference threshold, generating the second fault information, and determining the fault alarm information based on the second fault information, wherein the first difference threshold is less than the second difference threshold, and the second fault information indicates that the target electric power equipment has a severe fault.

[0054] Specifically, in order to accurately determine the fault severity of the target power equipment, a judgment can be made based on the difference between the target operating characteristics and the operating threshold. First, the difference between the target operating characteristics and the corresponding operating threshold is calculated to obtain an operating difference that characterizes the deviation between the current state of the equipment and the expected operating state. If the calculated operating difference is greater than the first difference threshold, it indicates that the difference is small, and the equipment may have a minor fault, which only requires timely attention and maintenance. At this time, the first fault information can be generated; conversely, if the operating difference is greater than the second difference threshold, it indicates that the target power equipment may have a serious fault, and immediate measures need to be taken to prevent potential system interruptions, and the second fault information is generated. Optionally, fault alarm information including detailed information such as fault type, location, and time can be generated based on the second fault information so that operators can respond quickly.

[0055] It should be noted that, according to the severity of the fault, the fault alarm information can be promptly transmitted to the relevant responsible personnel through different communication channels, and then the staff can quickly assess the situation, formulate a maintenance plan, and perform necessary troubleshooting measures after receiving the fault alarm information. This embodiment can ensure the stability and safety of the target power equipment when supplying power by determining the fault degree of the target power equipment.

[0056] In order to predict equipment failure conditions of target power equipment, optionally, in the detection method for power equipment provided in an embodiment of the present application, after generating fault alarm information based on the verification results, the method further includes: obtaining historical operation data and historical failure modes of the target power equipment in a historical time period, and forming a sample training set with the historical operation data and the historical failure modes; obtaining a preset fault trend prediction model, and using the sample training set to train the preset fault detection model to obtain a fault trend prediction model; inputting the equipment operation data into the fault trend prediction model, outputting fault trend information, and sending the fault trend information and fault alarm information to maintenance personnel.

[0057] Specifically, in order to achieve fault prediction of target power equipment, a fault detection model can be constructed using a machine learning model or a deep learning model. First, an effective sample training set needs to be constructed. At this time, operation data and fault records can be collected from the historical database of the target power equipment, that is, historical operation data and historical fault modes are obtained. After data preprocessing, the sample training set is composed of historical operation data and historical fault modes. The historical operation data can be obtained from the operation and maintenance log of the target power equipment, and may include the current, voltage, temperature, etc. of the equipment. It should be noted that the sample training set can also be split into a training set and a test set. The training set is used for model training, and the test set is used to evaluate the performance of the model, so as to ensure that the sample training set fully reflects the fault conditions of the equipment under different operating conditions, so as to improve the generalization ability of the model.

[0058] Optionally, a model suitable for power equipment fault prediction can be selected, for example, a machine learning algorithm (such as random forest, support vector machine, etc.), a deep learning model (such as convolutional neural network, recurrent neural network, etc.), or a prediction model based on time series, etc. Then, the preset fault detection model is trained using the sample training set, and the prediction accuracy of the model is improved by adjusting the model parameters and optimizing the algorithm, and finally a fault trend prediction model is obtained.

[0059] Optionally, the operating data of the target power equipment collected in real time is input into the above-mentioned trained fault trend prediction model. At this time, the model can predict the possible fault trends of the equipment in the future by analyzing these data, and generate fault trend information based on the fault trends. For example, this information may include the type of fault, the time when it may occur, and the severity of the fault, etc., and then send the fault trend information and the detected fault alarm information to the maintenance personnel through some communication channels (such as email, text message, application push, etc.) so that they can take preventive or maintenance measures in time. This embodiment uses the fault trend prediction model to predict the fault trend of power equipment, which can more effectively monitor the operating status of the equipment, discover and handle potential faults in advance, and thus improve the reliability and safety of the power equipment.

[0060] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0061] The present application also provides a detection device for electric equipment. It should be noted that the detection device for electric equipment in the present application can be used to execute the detection method for electric equipment provided in the present application. The detection device for electric equipment provided in the present application is introduced below.

[0062] Figure 3 is a schematic diagram of a detection device for electric power equipment provided according to an embodiment of the present application, such as Figure 3 As shown, the device includes: a first acquisition unit 30, a processing unit 31, and a generation unit 32.

[0063] The first acquisition unit 30 is used to acquire initial operating parameters of the target power equipment and process the initial operating parameters to obtain equipment operating data;

[0064] The processing unit 31 is used to perform feature extraction processing on the equipment operation data using a pattern recognition algorithm to obtain equipment operation features, and verify the equipment operation features to obtain verification results;

[0065] The generating unit 32 is configured to generate fault alarm information according to the verification result when the verification result indicates that the target power equipment is abnormal.

[0066] The detection device for electric power equipment provided in the embodiment of the present application obtains the initial operating parameters of the target electric power equipment through the first acquisition unit 30, processes the initial operating parameters, and obtains the equipment operating data; the processing unit 31 uses the pattern recognition algorithm to perform feature extraction processing on the equipment operating data to obtain the equipment operating characteristics, and verifies the equipment operating characteristics to obtain the verification result; the generation unit 32 generates fault alarm information according to the verification result when the verification result indicates that the target electric power equipment is abnormal, thereby solving the problems of low detection efficiency and low detection accuracy in fault detection of electric power equipment in the related technology, by obtaining the equipment operating data after preprocessing of the target electric power equipment, using the pattern recognition algorithm to perform feature extraction processing on the equipment operating data to obtain the equipment operating characteristics, and then determining the verification result according to the equipment operating characteristics, and using the verification result to judge the fault condition of the target electric power equipment. If the target electric power equipment is abnormal, the fault alarm information can be generated according to the verification result, thereby achieving the effect of improving the efficiency and accuracy of verifying the electric power equipment.

[0067] Optionally, in the detection device of the power equipment provided in the embodiment of the present application, the first acquisition unit 30 includes: a first receiving module, used to receive a device detection request, and activate the sensor network in the target power equipment according to the device detection request, wherein the device detection request refers to a request for fault detection on the target power equipment, and the sensor network includes at least a current transformer, a voltage transformer, a temperature sensor and a vibration sensor; a second receiving module, used to receive operating parameters collected by the sensor network when the sensor network operates based on the device detection request, and obtain initial operating parameters.

[0068] Optionally, in the detection device of the electric power equipment provided in the embodiment of the present application, the first acquisition unit 30 includes: a division module, used to divide the initial operating parameters according to the time series to obtain M time domain operating parameters, where M is a positive integer; a first processing module, used to perform Fourier transform processing on the M time domain operating parameters to obtain M frequency domain operating parameters, input the M frequency domain operating parameters into the filter, and output M processed frequency domain operating parameters; a second processing module, used to perform inverse Fourier transform processing on the M processed frequency domain operating parameters to obtain M processed time domain operating parameters, and the M processed time domain operating parameters constitute the equipment operating data.

[0069] Optionally, in the detection device of the electric power equipment provided in the embodiment of the present application, the processing unit 31 includes: a first acquisition module, used to obtain a preset state list, wherein the preset state list contains N equipment states of the target electric power equipment, and N is a positive integer; a training module, used to train the pattern recognition algorithm according to the preset state list to obtain a target recognition algorithm; and a third processing module, used to perform feature extraction processing on the equipment operation data using the target recognition algorithm to obtain N operation features, and the N operation features constitute the equipment operation features.

[0070] Optionally, in the detection device of the electric power equipment provided in the embodiment of the present application, the processing unit 31 includes: a second acquisition module, used to acquire a fault mode feature library, wherein the fault mode feature library contains N fault modes associated with N equipment states and an operating threshold value of each fault mode; a matching module, used to match the N operating features contained in the equipment operating features with the N fault modes to obtain N groups of features to be processed, and compare the operating features and operating thresholds in each group of features to be processed; a first determination module, used to determine the fault area according to the target operating feature if there is a target operating feature that does not meet any of the N operating thresholds, and the verification result is composed of the fault area and the fault mode associated with the target operating feature; a second determination module, used to determine the verification result as a result that the target electric power equipment is normal when all N operating features meet the N operating thresholds.

[0071] Optionally, in the detection device of the power equipment provided in the embodiment of the present application, the processing unit 31 includes: a calculation module, used to calculate the difference between the target operating characteristic and the corresponding operating threshold to obtain the operating difference, and when the operating difference is greater than the first difference threshold, generate first fault information, and determine the fault alarm information based on the first fault information, wherein the first fault information indicates that the target power equipment has a minor fault; a generation module, used to generate second fault information when the operating difference is greater than the second difference threshold, and determine the fault alarm information based on the second fault information, wherein the first difference threshold is less than the second difference threshold, and the second fault information indicates that the target power equipment has a severe fault.

[0072] Optionally, in the detection device of the power equipment provided in the embodiment of the present application, the device also includes: a second acquisition unit, used to obtain historical operation data and historical failure modes of the target power equipment in a historical time period after generating fault alarm information according to the verification result, and the historical operation data and historical failure modes constitute a sample training set; a third acquisition unit, used to obtain a preset fault trend prediction model, and use the sample training set to train the preset fault detection model to obtain a fault trend prediction model; an input unit, used to input the equipment operation data into the fault trend prediction model, output fault trend information, and send the fault trend information and fault alarm information to maintenance personnel.

[0073] The detection device of the above-mentioned electric power equipment includes a processor and a memory. The above-mentioned first acquisition unit 30, processing unit 31, generation unit 32, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0074] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the problems of low detection efficiency and low detection accuracy in fault detection of power equipment in related technologies can be solved by adjusting kernel parameters.

[0075] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0076] An embodiment of the present invention provides a computer storage medium, which is used to store a program. When the program is running, the device where the computer storage medium is located is controlled to execute a detection method for electric power equipment.

[0077] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application, such as Figure 4As shown, an embodiment of the present invention provides an electronic device, the electronic device 40 includes a processor, a memory, and a program stored in the memory and executable on the processor, the processor is used to execute computer-readable instructions, wherein the computer-readable instructions execute a detection method for power equipment when they are executed. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0078] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of a detection method for electric power equipment in each embodiment of the present application.

[0079] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0080] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0081] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0082] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0083] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0084] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0085] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0086] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0087] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for detecting electric power equipment, characterized in that: include: Acquire initial operating parameters of the target power equipment, and process the initial operating parameters to obtain equipment operating data; Using a pattern recognition algorithm to perform feature extraction processing on the equipment operation data to obtain equipment operation features, and verifying the equipment operation features to obtain verification results; When the verification result indicates that the target electric power equipment is abnormal, fault alarm information is generated according to the verification result.

2. The method according to claim 1, characterized in that Obtaining the initial operating parameters of the target power equipment includes: receiving a device detection request, and activating a sensor network in the target power device according to the device detection request, wherein the device detection request refers to a request for fault detection of the target power device, and the sensor network includes at least a current transformer, a voltage transformer, a temperature sensor, and a vibration sensor; In a case where the sensor network operates based on the device detection request, the operating parameters collected by the sensor network are received to obtain the initial operating parameters.

3. The method according to claim 1, characterized in that: The initial operating parameters are processed to obtain equipment operating data including: Dividing the initial operating parameters according to the time series to obtain M time domain operating parameters, where M is a positive integer; Performing Fourier transform processing on the M time-domain operating parameters to obtain M frequency-domain operating parameters, inputting the M frequency-domain operating parameters into a filter, and outputting M processed frequency-domain operating parameters; The M processed frequency domain operation parameters are subjected to inverse Fourier transform processing to obtain M processed time domain operation parameters, and the M processed time domain operation parameters constitute the equipment operation data.

4. The method according to claim 1, characterized in that: The equipment operation data is subjected to feature extraction processing using a pattern recognition algorithm, and the equipment operation features obtained include: Obtaining a preset state list, wherein the preset state list includes N device states of the target power device, where N is a positive integer; Training the pattern recognition algorithm according to the preset state list to obtain a target recognition algorithm; The target recognition algorithm is used to perform feature extraction processing on the equipment operation data to obtain N operation features, and the N operation features constitute the equipment operation features.

5. The method according to claim 1, characterized in that The equipment operation characteristics are verified, and the verification results include: Acquire a fault mode feature library, wherein the fault mode feature library contains N fault modes associated with N device states and an operating threshold value of each fault mode; Matching N operation characteristics included in the equipment operation characteristics with N fault modes to obtain N groups of to-be-processed characteristics, and comparing the operation characteristics and operation thresholds in each group of to-be-processed characteristics; If there is a target operation feature that does not satisfy any of the N operation thresholds, determine the fault area according to the target operation feature, and the fault area and the fault mode associated with the target operation feature constitute the verification result; In a case where the N operating characteristics all satisfy the N operating thresholds, the verification result is determined as a result that there is no abnormality in the target power equipment.

6. The method according to claim 5, characterized in that Generating fault alarm information according to the verification result includes: Calculating a difference between the target operation characteristic and a corresponding operation threshold to obtain an operation difference, generating first fault information when the operation difference is greater than a first difference threshold, and determining the fault alarm information based on the first fault information, wherein the first fault information indicates that the target power equipment has a minor fault; When the operating difference is greater than a second difference threshold, second fault information is generated, and the fault alarm information is determined based on the second fault information, wherein the first difference threshold is less than the second difference threshold, and the second fault information indicates that the target power equipment is severely faulty.

7. The method according to claim 1, characterized in that After generating fault alarm information according to the verification result, the method further includes: Acquire historical operation data and historical failure modes of the target power equipment in a historical time period, and form a sample training set with the historical operation data and the historical failure modes; Obtaining a preset fault trend prediction model, and using the sample training set to train the preset fault detection model to obtain a fault trend prediction model; The equipment operation data is input into the fault trend prediction model, fault trend information is output, and the fault trend information and the fault alarm information are sent to maintenance personnel.

8. A detection device for electric power equipment, characterized in that: include: A first acquisition unit, configured to acquire initial operating parameters of a target power device, and process the initial operating parameters to obtain device operating data; A processing unit, configured to perform feature extraction processing on the device operation data using a pattern recognition algorithm to obtain device operation features, and verify the device operation features to obtain verification results; A generating unit is used to generate fault alarm information according to the verification result when the verification result indicates that the target power equipment has an abnormality.

9. A computer storage medium, characterized in that The computer storage medium is used to store a program, wherein when the program is executed, the device where the computer storage medium is located is controlled to execute the detection method for electric power equipment according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the detection method of the electrical equipment described in any one of claims 1 to 7.