A power equipment step-by-step state evaluation method and system
By using multi-sensor data processing and machine learning models, the problem of incomplete power equipment condition assessment has been solved, enabling differentiated and refined assessment and visualization of equipment health status, thereby improving the safety and reliability of the power system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XI AN JIAOTONG UNIV
- Filing Date
- 2024-05-31
- Publication Date
- 2026-07-03
AI Technical Summary
Existing technologies cannot fully reflect the health status of different components of power equipment and are difficult to detect hidden defects, resulting in incomplete and unreliable equipment condition assessments.
The system uses multiple sensors to acquire raw signals from power equipment, forms a feature matrix through data preprocessing and feature recognition, performs status assessment and classification by combining machine learning models, and displays the health status of the equipment through a visual interface.
It enables comprehensive and detailed condition assessment of power equipment, quickly and accurately reflects real-time equipment status information, and improves the pertinence and efficiency of operation and maintenance work.
Smart Images
Figure CN118606838B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of power system main equipment condition assessment, specifically relating to a method and system for step-by-step condition assessment of power equipment. Background Technology
[0002] With the development of modern society, the scale of the power system required for national life and production is constantly increasing, and the requirements for power quality and power safety are also becoming more and more stringent. The power system consists of electrical equipment such as generators, transformers, circuit breakers, and transmission equipment. The safety and reliability of electrical equipment is the foundation for the normal operation of the power system.
[0003] Currently, domestic and international research institutions, equipment operators, and manufacturers have conducted extensive research on the condition assessment of power equipment, achieving rich results in assessment methods and standard development. However, due to the complex structure, high integration, and complex and variable operating environment of power system equipment, which is frequently affected by adverse external conditions, the difficulty of equipment condition assessment and fault diagnosis has greatly increased. Current condition assessment methods and applications are insufficient to comprehensively and reliably monitor equipment operation. Most current condition assessment methods are based on single or limited condition parameters, failing to comprehensively reflect the health status of different components and making it difficult to detect some hidden defects. Therefore, condition assessment methods need to be able to monitor and assess the operating status of power equipment as comprehensively as possible, and to conduct differentiated and refined evaluation and diagnosis of the health status of different structural components of the equipment, thereby realizing the condition assessment of power system equipment. Summary of the Invention
[0004] The purpose of this invention is to provide a method and system for step-by-step condition assessment of power equipment, so as to overcome the problem that the existing technology cannot fully reflect the health status of different components of the equipment.
[0005] A method for step-by-step condition assessment of power equipment includes the following steps:
[0006] S1, Collect the raw signals of the power equipment to be monitored based on the characteristics of the power equipment to be monitored;
[0007] S2, perform data preprocessing on the acquired raw signal, perform state feature identification on the preprocessed raw signal, and obtain the feature matrix of the power equipment to be monitored.
[0008] S3. Based on the obtained feature matrix, perform condition assessment and classification of the power equipment to be monitored, and obtain the condition assessment results and classification results of the equipment to be monitored.
[0009] Preferably, different sensors are used to simultaneously acquire the raw signals of different types of power equipment to be monitored.
[0010] Preferably, the acquired raw signals are preprocessed, and the processing steps include: abnormal data detection and deletion, automatic filling of missing data, and filtering and smoothing of noisy data.
[0011] Preferably, in the process of assessing the status of the power equipment to be monitored based on the acquired feature matrix, the real-time health status of the equipment is determined based on the current input feature matrix, and then the future status changes of the power equipment to be monitored are predicted based on the current input feature matrix and historical status data.
[0012] Preferably, the obtained status assessment results and classification results of the monitored equipment are visualized.
[0013] Preferably, the visualization includes a two-level page display. The first level displays the health status of all power equipment to be monitored, showing the type, number, and real-time status of each equipment. The real-time status is divided into three states: normal, abnormal, and dangerous. The second level page displays the specific status information of the equipment, including the real-time health status of each component. If there is an abnormality or abnormal risk, the location of the abnormality and the degree of abnormal danger are displayed.
[0014] Preferably, a threshold comparison method is used to compare and analyze the features in the feature matrix, and supervised machine learning is used to train a regression model to predict future health status.
[0015] A step-by-step condition assessment system for power equipment includes a data acquisition unit, a data preprocessing unit, and an assessment unit.
[0016] The data acquisition unit is used to acquire the raw signals of the power equipment to be monitored.
[0017] The data preprocessing unit preprocesses the acquired raw signals, identifies the state features of the preprocessed raw signals, and obtains the feature matrix of the power equipment to be monitored.
[0018] The assessment unit performs status assessment and classification of the power equipment to be monitored based on the acquired feature matrix, and obtains the status assessment results and classification results of the equipment to be monitored.
[0019] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the power equipment step-by-step condition assessment method described above.
[0020] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the power equipment step-by-step condition assessment method described above.
[0021] Compared with the prior art, the present invention has the following beneficial technical effects:
[0022] This invention provides a method for hierarchical status assessment of power equipment. The method involves collecting raw signals from the power equipment under monitoring based on its characteristics; preprocessing the acquired raw signals; identifying state features of the preprocessed raw signals to obtain a feature matrix of the power equipment under monitoring; and then assessing and classifying the status of the power equipment based on the obtained feature matrix to obtain the status assessment results and classification results. This invention, through comprehensive perception of power equipment status indicators and hierarchical status assessment at the back end, can quickly and accurately reflect the real-time status information of the equipment, providing timely and reliable guidance information for operation and maintenance personnel, and contributing to the safe and reliable operation of the power system.
[0023] The preferred method utilizes a wealth of available sensors and digital signal analysis systems, enabling comprehensive perception of equipment status. By leveraging a large amount of status parameter information to assess equipment status, the accuracy is effectively improved. This method employs a hierarchical evaluation approach to assess the health status of power equipment, enabling differentiated and refined assessment of real-time equipment status. It intuitively reflects the structural units and degree of abnormality in the equipment, facilitating rapid and targeted maintenance work by staff. Attached Figure Description
[0024] Figure 1 This is a flowchart of the power equipment step-by-step condition assessment method in an embodiment of the present invention;
[0025] Figure 2 This is a flowchart of the data cleaning and feature extraction process in an embodiment of the present invention;
[0026] Figure 3 This is a waveform diagram of the vibration signal of the high-voltage circuit breaker after preprocessing in an embodiment of the present invention;
[0027] Figure 4 This is the three-layer neural network model structure in the embodiment of the present invention;
[0028] Figure 5 This is a prediction response error diagram in an embodiment of the present invention;
[0029] Figure 6 This is a first-level interface diagram of the visual user interface designed in this embodiment of the invention;
[0030] Figure 7 This is a second-level interface diagram of the visual user interface designed in this embodiment of the invention;
[0031] Figure 8 This is a comparison chart of the average response time under abnormal conditions between the present invention and the traditional method. Detailed Implementation
[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0034] like Figure 1 As shown, this invention provides a step-by-step condition assessment method for power equipment, applicable to all locations with voltage and current transformation, energy receiving and energy distribution functions, such as power plants, substations, and terminal stations. The method specifically includes the following steps:
[0035] S1, Collect the raw signals of the power equipment to be monitored based on the characteristics of the power equipment to be monitored;
[0036] S2, perform data preprocessing on the acquired raw signal, perform state feature identification on the preprocessed raw signal, and obtain the feature matrix of the power equipment to be monitored.
[0037] S3. Based on the obtained feature matrix, perform condition assessment and classification of the power equipment to be monitored, and obtain the condition assessment results and classification results of the equipment to be monitored.
[0038] The power equipment to be monitored in this application refers to primary equipment in the power system, including but not limited to high-voltage circuit breakers, transformers, disconnect switches, and contactors.
[0039] In specific embodiments of this application, different sensors are used to simultaneously acquire raw signals from different types of power equipment to be monitored. For example, for power equipment in the power system that requires real-time status monitoring (i.e., power equipment to be monitored), corresponding sensors are selected based on the characteristics and key signal types of the power equipment to be monitored. Different equipment are referred to as equipment A, equipment B, ..., equipment X. The sensors connected to each equipment to collect signals are referred to as sensor A1, sensor A2, ..., sensor An, sensor B1, sensor B2, ..., sensor Bn, and sensor X1, sensor X2, ..., sensor Xn.
[0040] The sensors used in this application include electrical signal sensors and non-electrical signal sensors, which monitor electrical and non-electrical signals during the operation of power equipment. Specifically, they include voltage transformers, current sensors, acceleration vibration sensors, linear displacement sensors, wireless temperature sensors, etc., which can measure and transmit signals such as circuit voltage, circuit current, mechanical vibration, contact stroke, and temperature rise changes of power equipment.
[0041] The raw signals acquired by different sensors are centrally processed. The signals from different sensors are transmitted to the signal processor through a multi-input interface unit. The signal processor then performs data preprocessing on the acquired feature signals.
[0042] The acquired raw signals are preprocessed, and the processing steps include: abnormal data detection and deletion, automatic filling of missing data, and filtering and smoothing of noisy data.
[0043] Further calculations are performed on the preprocessed raw signal to form the signal characteristic matrix of the device:
[0044] Maximum signal value:
[0045] g max =max(x(t))
[0046] Signal average value:
[0047]
[0048] Signal standard deviation:
[0049]
[0050] Where x(t) represents the preprocessed time-varying signal, t s t represents the start time of the time-varying signal. e The term represents the end time of a time-varying signal. In addition to the time-domain characteristics of the signal mentioned above, the frequency-domain and time-frequency-domain characteristics obtained through wavelet transform, Fourier transform, and other processing should also be included. The calculated characteristic quantities should be selected based on actual needs. Let the characteristic quantity be denoted as g. 1X =gaveX ,g 2X =g maxX ,g 3X =g stdX …then the characteristic matrix can be denoted as G X = [g1,g2,g3,...], where the subscript X represents the feature quantity or feature matrix of device X.
[0051] The status assessment of the power equipment to be monitored is carried out based on the obtained feature matrix. The specific process is as follows: identify abnormal data in the feature matrix, determine the source of abnormal data (specifically the original signal of the abnormal data and the corresponding equipment to be monitored), judge the degree of abnormality, determine the danger level of the abnormal situation, and judge the potential future abnormal risks.
[0052] In the process of assessing the status of the power equipment to be monitored based on the acquired feature matrix, the real-time health status of the equipment is determined based on the current input feature matrix, and then the future status changes of the power equipment to be monitored are predicted based on the current input feature matrix and historical status data.
[0053] The status assessment and classification results of the monitored equipment are visualized. The visualization user interface is divided into two levels. The first level displays the health status of all monitored power equipment, showing the type, number, and real-time status of each equipment. The real-time status is divided into three states: normal, abnormal, and dangerous. Each equipment can be clicked to enter the second level page. The second level page displays the specific status information of the equipment, including the real-time health status of each component. If there is an abnormality or abnormal risk, the location of the abnormality and the degree of abnormal danger are displayed.
[0054] Example
[0055] For critical power equipment in a power system requiring real-time status monitoring, corresponding sensors are selected based on the equipment's characteristics and key signal types. In this embodiment, four devices require status assessment: Device A is a high-voltage circuit breaker, model ZW-32-12F; Device B is another high-voltage circuit breaker, model ZW-32-12F; Device C is a transformer, model SCB11-630kVA / 10; and Device D is a disconnecting switch, model GN19-12. The sensors connected to Device A are: an acceleration sensor A1 installed at the end of the insulator; an acceleration sensor A2 installed at the operating mechanism; a current sensor A3 installed at the opening and closing coils; and a wireless temperature sensor A4 installed at the contact point. Device B has the same model as Device A and uses the same sensors, only the numbers are changed to B1, B2, B3, and B4. The sensors connected to Device C are: an acceleration sensor C1 installed on the tank wall; a current sensor C2 installed on the transformer core's external grounding wire conduit; and a wireless temperature sensor installed on the transformer casing. The sensors connected to device D include: an ultrasonic sensor installed in the housing of the disconnect switch.
[0056] The acquired raw signals undergo data cleaning and feature extraction. In this embodiment, the raw signals acquired by the sensors are uniformly transmitted to the signal processor. At this point, the signals contain abnormal data and noise interference. The pre-written program in the signal processor can perform preliminary processing on the signals. Only the data cleaning and feature extraction process of signal processing B is described in detail. Figure 2 As shown, sensors A1, A2, and A3 collect time-varying vibration signals a1 and a2, and current signal a3, respectively, while A4 collects the temperature a4 at a single point. First, the collected raw signals undergo signal preprocessing. For the time-varying signals a1, a2, and a3, outlier detection based on the Laida criterion, data completion based on a Markov process, and data smoothing based on digital filtering are performed sequentially to obtain cleaned data a'1, a'2, and a'3. Since a4 is a single data point, only outlier detection is required; if the data is abnormal, it is corrected to obtain the corrected data a'4. Figure 3 The waveform of a'1 is shown.
[0057] After processing, the signals a'1 and a'2 are subjected to wavelet packet transform to calculate the change index and kurtosis of the wavelet packet energy spectrum, respectively, yielding feature quantities g1, g2, g3, and g4. Taking g1 as an example, the wavelet packet energy spectrum feature extraction method is as follows: First, the processed vibration signal a'1 is decomposed into n-level wavelet components, where n = 3 in this example. Let f... j Let f represent the response signal at the j-th decomposition node in the n-th layer. j The calculation formula is:
[0058] E j=Σ|f j | 2 j=2 0 ,2 1 ,...,2 n
[0059] To prevent inconvenience caused by excessively large values in the calculation process, the energy spectrum is further normalized. The energy ratio I of each frequency band in the last layer of the wavelet packet energy spectrum is:
[0060]
[0061] The energy ratio I characterizes the dynamic characteristics of energy distribution. Under normal circumstances, the baseline energy ratio is I0. The energy change index is calculated as a characteristic quantity g1. The closer the energy change index is to 1, the better the operating condition. The calculation method for g1 is as follows:
[0062]
[0063] Taking g2 as an example, the spectral kurtosis is calculated as follows:
[0064]
[0065] Where m is the number of sampling points, a' 1i This represents the data value of the i-th sampling point. s is the mean and s is the standard deviation.
[0066] The same method can be used to calculate g3 and g4. For the processed current signal a'3, the peak operating current g5 and the interruption time g6 are easily obtained. The temperature rise g7 can be obtained by subtracting the ambient temperature from the temperature signal a'4. Thus, all the required characteristic quantities are obtained, forming the characteristic matrix G of device A. A =[g1,g2,g3,g4,g5,g6,g7], input into the next level state evaluation model, the feature matrix G of other devices B G C G D The calculation method and G A The calculation process is the same, but the specific calculation formula is modified according to the specific sensor and feature parameter requirements.
[0067] Based on the equipment feature matrix calculated in the above steps, and combined with historical data, real-time status evaluation and future health status prediction of the equipment are performed. A threshold comparison method is used to compare and analyze the features in the feature matrix. Simultaneously, supervised machine learning is used to train a regression model for future health status prediction. Machine learning algorithms can be selected from regression trees, support vector machines, neural networks, etc. This embodiment uses a three-layer neural network as an example for prediction. Figure 4This is a three-layer neural network model. Historical feature vectors are input into the model as input signals, and the predicted response is obtained after training. Figure 5 To predict the response error map, the observation error at each point is within 1%, demonstrating good predictive performance and high reliability and accuracy. The model's predictive performance is evaluated by comparing the previous prediction results with the real-time input state variables. An adaptive augmentation algorithm is then used to adjust the model parameters to improve prediction accuracy.
[0068] Based on the quantitative assessment results and the condition prediction results, the equipment condition is evaluated in a differentiated and refined manner, and reflected on the visual user interface. In this embodiment, the condition characteristic quantity of the high-voltage circuit breaker of equipment B is abnormal. Tracing the source of the characteristic quantity, it is found that the vibration signal measured at the insulator terminal of equipment B is abnormal. Further analysis by the machine learning model detects that the abnormality type is fatigue of the tripping spring. Figure 6 and Figure 7 This is the visual user interface used in the embodiments. Figure 6 The primary user interface displays the equipment type, model, and brief real-time status information of all devices performing status monitoring. Based on changes in the power system's equipment management, devices in the interface can be modified or deleted, or new devices can be added. Clicking the details option will take you to the secondary interface for device details. Figure 7 The interface displays a secondary interface, specifically showing detailed information and real-time status of device B. Users can intuitively see the device model, real-time status, ambient temperature and pressure, operating time, and historical warnings. The status details display the health status of switching wear, insulation, mechanical components, operating mechanisms, and other indicators. In this embodiment, the trip spring of device B is fatigued and requires maintenance; the mechanical components section is flashing, the status bar shows an anomaly, and the details section displays the specific anomaly, greatly facilitating maintenance work. The bottom of the page also allows users to examine the evaluation effect of the status assessment model.
[0069] like Figure 8 As shown, the present invention demonstrates the efficiency of monitoring and maintaining the equipment in this embodiment. The present invention can quickly and accurately determine the abnormal conditions of the equipment, and differentiate and refine the display of the abnormal parts and severity of the abnormalities. This is of great significance for enhancing the reliability of power system operation and improving the operation and maintenance efficiency of equipment.
[0070] In another embodiment of the present invention, a power equipment step-by-step condition assessment system is provided, including a data acquisition unit, a data preprocessing unit, and an assessment unit:
[0071] The data acquisition unit is used to acquire the raw signals of the power equipment to be monitored.
[0072] The data preprocessing unit preprocesses the acquired raw signals, identifies the state features of the preprocessed raw signals, and obtains the feature matrix of the power equipment to be monitored.
[0073] The assessment unit performs status assessment and classification of the power equipment to be monitored based on the acquired feature matrix, and obtains the status assessment results and classification results of the equipment to be monitored.
[0074] In another embodiment of the present invention, a terminal device is provided, the terminal device including a processor and a memory, the memory being used to store a computer program, the computer program including program instructions, and the processor being used to execute the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to achieve corresponding method flows or corresponding functions. The processor described in this embodiment can be used in the operation of a power equipment step-by-step state assessment method, including the following steps: acquiring the original signals of the power equipment to be monitored based on its characteristics; performing data preprocessing on the acquired original signals, identifying state features of the preprocessed original signals, and obtaining a feature matrix of the power equipment to be monitored; performing state assessment and classification of the power equipment to be monitored based on the obtained feature matrix, and obtaining the state assessment result and classification result of the power equipment to be monitored.
[0075] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory). This computer-readable storage medium is a memory device in a terminal device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and extended storage media supported by the terminal device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device.
[0076] One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the power equipment step-by-step condition assessment method in the above embodiments; one or more instructions in the computer-readable storage medium are loaded and executed by the processor to perform the following steps: acquiring the original signals of the power equipment to be monitored based on the characteristics of the power equipment to be monitored; performing data preprocessing on the acquired original signals, identifying the state features of the preprocessed original signals, and obtaining the feature matrix of the power equipment to be monitored; performing condition assessment and classification of the power equipment to be monitored based on the obtained feature matrix, and obtaining the condition assessment result and classification result of the power equipment to be monitored.
[0077] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0078] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0079] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0080] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
Claims
1. A method of stepwise condition assessment of an electrical power equipment, characterized by, Includes the following steps: S1, Collect the raw signals of the power equipment to be monitored based on the characteristics of the power equipment to be monitored; S2, perform data preprocessing on the acquired raw signal, perform state feature identification on the preprocessed raw signal, and obtain the feature matrix of the power equipment to be monitored. S3. Based on the acquired feature matrix, perform state assessment and classification of the power equipment to be monitored to obtain the state assessment results and classification results of the equipment to be monitored. In the process of assessing the status of the power equipment to be monitored based on the acquired feature matrix, the real-time health status of the equipment is determined based on the current input feature matrix, and then the future status changes of the power equipment to be monitored are predicted based on the current input feature matrix and historical status data. Visualize the status assessment and classification results of the monitored equipment; The visualization includes a two-level page display. The first level displays the health status of all power equipment to be monitored, showing the type, number, and real-time status of each device. The real-time status is divided into three states: normal, abnormal, and dangerous. The second-level page displays the device's specific status information, including the real-time health status of each component. If there are any abnormalities or risks, it shows the location of the abnormality and the degree of danger.
2. The method of claim 1, wherein, Different sensors are used to simultaneously acquire raw signals from different types of electrical equipment to be monitored.
3. The method of claim 1, wherein, The acquired raw signals are preprocessed, and the processing steps include: abnormal data detection and deletion, automatic filling of missing data, and filtering and smoothing of noisy data.
4. The method of claim 1, wherein, A threshold comparison method is used to compare and analyze the features in the feature matrix, and supervised machine learning is used to train a regression model to predict future health status.
5. A power equipment stepwise condition assessment system, characterized by, It includes a data acquisition unit, a data preprocessing unit, and an evaluation unit: The data acquisition unit is used to acquire the raw signals of the power equipment to be monitored. The data preprocessing unit preprocesses the acquired raw signals, identifies the state features of the preprocessed raw signals, and obtains the feature matrix of the power equipment to be monitored. The assessment unit performs status assessment and classification of the power equipment to be monitored based on the acquired feature matrix, and obtains the status assessment results and classification results of the equipment to be monitored. In the process of assessing the status of the power equipment to be monitored based on the acquired feature matrix, the real-time health status of the equipment is determined based on the current input feature matrix, and then the future status changes of the power equipment to be monitored are predicted based on the current input feature matrix and historical status data. Visualize the status assessment and classification results of the monitored equipment; The visualization includes a two-level page display. The first level displays the health status of all power equipment to be monitored, showing the type, number, and real-time status of each device. The real-time status is divided into three states: normal, abnormal, and dangerous. The second-level page displays the device's specific status information, including the real-time health status of each component. If there are any abnormalities or risks, it shows the location of the abnormality and the degree of danger.
6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the power equipment step-by-step condition assessment method as described in any one of claims 1 to 4.
7. A computer-readable storage medium storing a computer program, wherein the computer program comprises the following steps of: receiving a request for a resource from a client; determining whether the client is authorized to access the resource; and if the client is authorized to access the resource, providing the resource to the client. The computer program, when executed by a processor, implements the steps of the power equipment step-by-step state evaluation method according to any one of claims 1 to 4.