Electric power inspection method, intelligent inspection robot, storage medium and program product

Abstract

The invention provides an electric power inspection method, an intelligent inspection robot, a storage medium and a program product, and relates to the technical field of electric power inspection. The method comprises the steps that after operation related data, collected by a plurality of sensors, of power equipment are obtained, target weighted weights corresponding to the sensors are obtained through a weight determination process, and the weight determination process comprises the steps that according to the operation related data collected by the sensors, initial weighted weights corresponding to the sensors are determined; determining the confidence coefficient of the operation related data according to the initial weighted weight and the change trend of the operation related data in the recent set duration; according to the confidence coefficient, adjusting the initial weighting weight to obtain a target weighting weight corresponding to the sensor; based on the target weighted weights corresponding to the sensors, performing weighted fusion on the operation related data corresponding to the plurality of sensors to obtain inspection sensing data corresponding to the power equipment; and determining whether the power equipment is abnormal or not according to the inspection sensing data so as to comprehensively and accurately inspect the power.

Description

Technical Field

[0001] The present application relates to the technical field of electric power inspection, and in particular to an electric power inspection method, an intelligent inspection robot, a storage medium and a program product. Background Art

[0002] In the field of traditional power inspection, manual inspection has always been dominant. This inspection method relies on the intuitive observation and experience judgment of inspectors, which is not only labor-intensive but also inefficient. Since manual inspection is limited by the physical strength, attention and professional knowledge level of inspectors, the reliability and accuracy of inspection results are often difficult to guarantee. Especially in some complex or dangerous environments, manual inspection faces great challenges.

[0003] In order to solve the above problems, and as the intelligent inspection robot technology has developed rapidly in recent years and has gradually been applied to the field of industrial inspection to realize partially automated inspection functions, the existing power inspection can be achieved by setting a camera on the intelligent inspection robot. During the inspection process, the camera can be used to collect the appearance image of the power equipment, and the power equipment can be detected based on the collected appearance image to determine whether it is abnormal, thereby realizing the automation and intelligence of the power inspection.

[0004] However, although intelligent inspection robots have improved the efficiency and reliability of power inspections to a certain extent, they still cannot meet the needs of comprehensive and accurate inspections. Summary of the invention

[0005] The present application provides a power inspection method, an intelligent inspection robot, a storage medium and a program product for comprehensive and accurate power inspection.

[0006] In a first aspect, the present application provides a power inspection method, comprising:

[0007] Acquire operation-related data of the power equipment collected by multiple sensors;

[0008] The target weighted weight corresponding to each sensor in the plurality of sensors is obtained through a weight determination process, and the weight determination process includes: determining an initial weighted weight corresponding to the sensor according to the operation-related data collected by the sensor; determining the confidence of the operation-related data according to the initial weighted weight and the change trend of the operation-related data within a recent set time period; adjusting the initial weighted weight according to the confidence to obtain the target weighted weight corresponding to the sensor;

[0009] Based on the target weights corresponding to each of the multiple sensors, the operation-related data corresponding to the multiple sensors are weightedly fused to obtain the inspection perception data corresponding to the power equipment;

[0010] Based on the inspection sensing data, determine whether the power equipment is abnormal and obtain the inspection results of the power equipment.

[0011] In a possible implementation, determining the initial weight corresponding to the sensor according to the operation-related data collected by the sensor includes:

[0012] Calculate quality assessment indicators of operation-related data acquired by sensors;

[0013] Quantify the quality assessment indicators to obtain the quantitative score of the sensor;

[0014] According to the quantitative score, the initial weight corresponding to the sensor is determined.

[0015] In a possible implementation, the confidence level of the operation-related data is determined according to the initial weighted weight and the change trend of the operation-related data within a recent set time period, including:

[0016] Through the Bayesian probability model, the confidence level of the operation-related data is determined based on the initial weighted weights and the changing trend of the operation-related data within the most recent set time period.

[0017] In a possible implementation, adjusting the initial weight according to the confidence level to obtain the target weight corresponding to the sensor includes:

[0018] According to the confidence level, an exponential decay function is used to adjust the initial weighted weight to obtain the target weighted weight corresponding to the sensor.

[0019] In a possible implementation, based on the target weighted weights corresponding to each sensor in the multiple sensors, weighted fusion is performed on the operation-related data corresponding to the multiple sensors to obtain the inspection perception data corresponding to the power equipment, including:

[0020] Adopting adaptive filtering algorithm to reduce noise of operation-related data corresponding to multiple sensors, the adaptive filtering algorithm selects corresponding filtering parameters according to the type of operation-related data by combining wavelet transform and Kalman filter;

[0021] Perform multi-scale feature extraction on the operation-related data after noise reduction to obtain multiple key information features;

[0022] Map multiple key information features to a unified feature space to obtain feature alignment results;

[0023] Based on the target weights corresponding to each sensor in multiple sensors, the feature alignment results are weighted fused to obtain the inspection perception data corresponding to the power equipment.

[0024] In a possible implementation, determining whether the power equipment is abnormal based on the inspection sensing data and obtaining the inspection result of the power equipment includes:

[0025] The inspection sensing data is input into a preset anomaly detection model, which is a convolutional neural network or a recurrent neural network;

[0026] Based on the anomaly detection model, determine whether the power equipment is abnormal and obtain the inspection results of the power equipment.

[0027] In a possible implementation, it further includes:

[0028] If the power equipment is abnormal, determine the abnormal level of the power equipment according to the power equipment;

[0029] Based on the abnormality level, determine the alarm information corresponding to the abnormality level;

[0030] Transmit alarm information to the remote monitoring center.

[0031] In a possible implementation, it further includes:

[0032] Generate inspection reports based on operation-related data and inspection results;

[0033] Send inspection reports to the remote monitoring center.

[0034] In a possible implementation, it further includes:

[0035] Construct an inspection semantic map based on inspection perception data. The inspection semantic map includes information on traversable areas, dangerous areas, and obstacles.

[0036] Determine the inspection terrain distribution based on inspection perception data and inspection semantic map;

[0037] According to the inspection terrain distribution, the inspection path of the inspection equipment is determined, and the chassis and posture of the inspection equipment are adjusted. The inspection equipment is equipped with a deformable chassis and a posture adjustment structure.

[0038] In a possible implementation, determining the inspection path of the inspection equipment according to the inspection terrain distribution includes:

[0039] Based on the path planning algorithm, the inspection path of the inspection equipment is determined according to the inspection terrain distribution. The path planning algorithm integrates the global path planning optimization strategy and the local path planning optimization strategy.

[0040] In a possible implementation, when multiple inspection devices cooperate with each other to perform power inspection, the method further includes:

[0041] Obtain the inspection location of other inspection equipment;

[0042] Based on the path planning algorithm, the next inspection location is determined according to the inspection terrain distribution and the inspection locations of other inspection equipment.

[0043] In a possible implementation, it further includes:

[0044] According to the inspection sensing data, the movement mode of the inspection equipment is determined, and the movement mode reflects the movement state of the inspection equipment that is adaptively adjusted according to the inspection sensing data;

[0045] Based on the motion mode, the inspection equipment is controlled to move on the inspection path.

[0046] In a second aspect, the present application provides a power inspection device, comprising:

[0047] An acquisition module, used to acquire operation-related data of the power equipment collected by multiple sensors;

[0048] The first determination module is used to obtain the target weighted weight corresponding to each sensor of the multiple sensors through a weight determination process, and the weight determination process includes: determining the initial weighted weight corresponding to the sensor according to the operation related data collected by the sensor; determining the confidence of the operation related data according to the initial weighted weight and the change trend of the operation related data within a recent set time period; adjusting the initial weighted weight according to the confidence to obtain the target weighted weight corresponding to the sensor;

[0049] A fusion module is used to perform weighted fusion on the operation-related data corresponding to the multiple sensors based on the target weights corresponding to each sensor in the multiple sensors, so as to obtain the inspection perception data corresponding to the power equipment;

[0050] The second determination module is used to determine whether the power equipment is abnormal based on the inspection sensing data and obtain the inspection result of the power equipment.

[0051] In a possible implementation manner, the first determining module is specifically configured to:

[0052] Calculate quality assessment indicators of operation-related data acquired by sensors;

[0053] Quantify the quality assessment indicators to obtain the quantitative score of the sensor;

[0054] According to the quantitative score, the initial weight corresponding to the sensor is determined.

[0055] In a possible implementation manner, the first determining module is specifically configured to:

[0056] Through the Bayesian probability model, the confidence level of the operation-related data is determined based on the initial weighted weights and the changing trend of the operation-related data within the most recent set time period.

[0057] In a possible implementation manner, the first determining module is specifically configured to:

[0058] According to the confidence level, an exponential decay function is used to adjust the initial weighted weight to obtain the target weighted weight corresponding to the sensor.

[0059] In a possible implementation, the fusion module is specifically used for:

[0060] Adopting adaptive filtering algorithm to reduce noise of operation-related data corresponding to multiple sensors, the adaptive filtering algorithm selects corresponding filtering parameters according to the type of operation-related data by combining wavelet transform and Kalman filter;

[0061] Perform multi-scale feature extraction on the operation-related data after noise reduction to obtain multiple key information features;

[0062] Map multiple key information features to a unified feature space to obtain feature alignment results;

[0063] Based on the target weights corresponding to each sensor in multiple sensors, the feature alignment results are weighted fused to obtain the inspection perception data corresponding to the power equipment.

[0064] In a possible implementation manner, the second determining module is specifically configured to:

[0065] The inspection sensing data is input into a preset anomaly detection model, which is a convolutional neural network or a recurrent neural network;

[0066] Based on the anomaly detection model, determine whether the power equipment is abnormal and obtain the inspection results of the power equipment.

[0067] In a possible implementation manner, the power inspection device further includes a processing module, and the processing module is specifically used to:

[0068] If the power equipment is abnormal, determine the abnormal level of the power equipment according to the power equipment;

[0069] Based on the abnormality level, determine the alarm information corresponding to the abnormality level;

[0070] Transmit alarm information to the remote monitoring center.

[0071] In a possible implementation manner, the processing module is specifically used for:

[0072] Generate inspection reports based on operation-related data and inspection results;

[0073] Send inspection reports to the remote monitoring center.

[0074] In a possible implementation manner, the processing module is further configured to:

[0075] Construct an inspection semantic map based on inspection perception data. The inspection semantic map includes information on traversable areas, dangerous areas, and obstacles.

[0076] Determine the inspection terrain distribution based on inspection perception data and inspection semantic map;

[0077] According to the inspection terrain distribution, the inspection path of the inspection equipment is determined, and the chassis and posture of the inspection equipment are adjusted. The inspection equipment is equipped with a deformable chassis and a posture adjustment structure.

[0078] In a possible implementation manner, the processing module is further configured to:

[0079] Based on the path planning algorithm, the inspection path of the inspection equipment is determined according to the inspection terrain distribution. The path planning algorithm integrates the global path planning optimization strategy and the local path planning optimization strategy.

[0080] In a possible implementation, when multiple inspection devices cooperate with each other to perform power inspection, the processing module is further used to:

[0081] Obtain the inspection location of other inspection equipment;

[0082] Based on the path planning algorithm, the next inspection location is determined according to the inspection terrain distribution and the inspection locations of other inspection equipment.

[0083] In a possible implementation manner, the processing module is further configured to:

[0084] According to the inspection sensing data, the movement mode of the inspection equipment is determined, and the movement mode reflects the movement state of the inspection equipment that is adaptively adjusted according to the inspection sensing data;

[0085] Based on the motion mode, the inspection equipment is controlled to move on the inspection path.

[0086] In a third aspect, the present application provides an intelligent inspection robot, comprising: a memory, a processor;

[0087] Memory stores computer-executable instructions;

[0088] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0089] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed, they are used to implement the above first aspect and / or various possible implementations of the first aspect.

[0090] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed, implements the above first aspect and / or various possible implementations of the first aspect.

[0091] The electric power inspection method, intelligent inspection robot, storage medium and program product provided by the present application relate to the technical field of electric power inspection. The method includes: obtaining operation-related data of electric power equipment collected by multiple sensors; obtaining the target weighted weight corresponding to each sensor in the multiple sensors through a weight determination process, and the weight determination process includes: determining the initial weighted weight corresponding to the sensor according to the operation-related data collected by the sensor; determining the confidence of the operation-related data according to the initial weighted weight and the change trend of the operation-related data within the recent set time; adjusting the initial weighted weight according to the confidence to obtain the target weighted weight corresponding to the sensor; based on the target weighted weight corresponding to each sensor in the multiple sensors, weighted fusion is performed on the operation-related data corresponding to the multiple sensors to obtain the inspection perception data corresponding to the electric power equipment; determining whether the electric power equipment is abnormal according to the inspection perception data, and obtaining the inspection result of the electric power equipment. The present application obtains operation data of different dimensions of the power equipment by acquiring operation-related data of the power equipment respectively collected by multiple sensors; determines the initial weighted weight corresponding to the sensor according to the operation-related data collected by the sensor, and determines the confidence of the operation-related data according to the determined initial weighted weight and the change trend of the operation-related data within the most recent set time, and then adjusts the initial weighted weight according to the confidence to obtain the target weighted weight, so that the target weighted weight can be adaptively adjusted according to the change trend of the operation-related data within the most recent set time, so as to provide a more accurate weighted weight for subsequent weighted fusion; performs weighted fusion on the operation-related data respectively corresponding to the multiple sensors according to the target weighted weight corresponding to each sensor in the multiple sensors, and obtains the inspection perception data of the power equipment, wherein the inspection perception data fuses the operation-related data of different dimensions; determines whether there is an abnormality in the power equipment based on the inspection perception data, and obtains an accurate and comprehensive inspection result of the power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0093] Figure 1 Schematic diagram of the power inspection method provided in this application Figure 1 ;

[0094] Figure 2 A schematic diagram of a power inspection system corresponding to the power inspection method provided in an embodiment of the present application;

[0095] Figure 3 A schematic diagram of the structure of the power inspection device provided for this application;

[0096] Figure 4 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application.

[0097] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0098] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0099] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, 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.

[0100] The inspection of traditional power equipment and industrial facilities mainly relies on manual labor, which has problems such as high workload, low efficiency and poor reliability. In recent years, intelligent inspection robots have gradually been used in industrial inspections, replacing manual inspections with cameras, temperature sensors and other equipment to achieve partial automation of inspection functions. However, the information collected by a single sensor is limited, and it is often difficult to comprehensively and accurately evaluate the operating status of power equipment.

[0101] In response to the above problems, this application proposes a multi-sensor fusion power inspection method, which integrates the operation-related data of power equipment collected by different sensors to achieve multi-dimensional monitoring of power equipment, thereby improving the recognition accuracy and intelligence level of the inspection method.

[0102] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0103] Figure 1 Schematic diagram of the power inspection method provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0104] S101. Acquire operation-related data of electric power equipment collected by a plurality of sensors.

[0105] The operation-related data include operation status data and operation environment data. The operation status data reflects the operation status of the power equipment itself, and the operation environment data reflects the external environment in which the power equipment is located.

[0106] The multiple sensors include two or more of the following sensors: infrared temperature measurement module, camera, lidar, ultrasonic sensor, gas sensor, vibration sensor and spectral analysis sensor; wherein, infrared temperature measurement module: used to obtain surface temperature distribution map of power equipment and identify potential hot spots of power equipment; camera: used to obtain visible light image of power equipment; lidar: used to obtain three-dimensional point cloud data of power equipment; ultrasonic sensor: used to detect obstacles in the inspection area and measure the distance between the obstacles and the power equipment; gas sensor: used to detect the concentration of specific gas in the inspection area; vibration sensor: used to detect the vibration of power equipment during operation; spectral analysis sensor: used to identify the material composition and state in the inspection area.

[0107] S102. Obtain target weights corresponding to each sensor in a plurality of sensors through a weight determination process. The weight determination process includes: determining an initial weight corresponding to the sensor based on operation-related data collected by the sensor; determining the confidence of the operation-related data based on the initial weight and the change trend of the operation-related data within a recent set time period; and adjusting the initial weight based on the confidence to obtain the target weight corresponding to the sensor.

[0108] In this step, it can be understood that after obtaining the operation-related data of the power equipment collected by multiple sensors respectively, it is necessary to determine the weighted weight of the fused operation-related data. Specifically, first, the initial weighted weight corresponding to the sensor needs to be determined based on the operation-related data obtained in step S101; secondly, the confidence of the operation-related data is determined based on the initial weighted weight and the change trend of the operation-related data within the recent set time period, for example, based on the change trend of the initial weighted weight and the operation-related data within the recent week, wherein the confidence refers to a quantitative assessment of the credibility of the operation-related data, reflecting the possibility that the operation-related data reflects the true operating status of the power equipment; and then the initial weighted weight is adjusted according to the confidence to obtain the target weighted weight corresponding to the sensor.

[0109] S103: Based on the target weighted weight corresponding to each sensor in the multiple sensors, weighted fusion is performed on the operation-related data corresponding to the multiple sensors to obtain the inspection perception data corresponding to the power equipment.

[0110] In this step, it can be understood that the inspection perception data obtained is a fusion of the operation-related data corresponding to multiple sensors, and the fusion of the operation-related data corresponding to multiple sensors needs to be performed according to the target weighting weights corresponding to each sensor.

[0111] For example, based on the target weighted weights corresponding to each sensor among multiple sensors, weighted fusion is performed on the operation-related data corresponding to the multiple sensors to obtain the inspection perception data corresponding to the power equipment, including: using an adaptive filtering algorithm to perform denoising on the operation-related data corresponding to the multiple sensors, the adaptive filtering algorithm selects corresponding filtering parameters according to the type of operation-related data through a combination of wavelet transform and Kalman filter; multi-scale feature extraction is performed on the operation-related data after denoising to obtain multiple key information features; the multiple key information features are mapped to a unified feature space to obtain a feature alignment result; based on the target weighted weights corresponding to each sensor among multiple sensors, the feature alignment results are weighted fused to obtain the inspection perception data corresponding to the power equipment.

[0112] This example can effectively improve the quality and availability of the operation-related data by performing noise reduction and feature mapping operations on the operation-related data before weighted fusion, providing a more accurate and reliable data basis for subsequent weighted fusion, thereby improving the accuracy and reliability of the inspection results.

[0113] S104. Determine whether the power equipment is abnormal based on the inspection sensing data and obtain the inspection result of the power equipment.

[0114] In this step, it can be understood that the inspection sensing data determined in S103 is used to determine whether the power equipment is abnormal, thereby obtaining the inspection result of the power equipment. This means that the inspection result obtained includes whether the power equipment is abnormal.

[0115] In some embodiments, determining whether the power equipment is abnormal based on the inspection perception data and obtaining the inspection results of the power equipment includes: inputting the inspection perception data into a preset anomaly detection model, where the anomaly detection model is a convolutional neural network or a recurrent neural network; determining whether the power equipment is abnormal based on the anomaly detection model and obtaining the inspection results of the power equipment.

[0116] In some embodiments, it can be understood that to obtain the inspection results of the power equipment, the inspection perception data must first be input into a preset anomaly detection model. The anomaly detection model can be a convolutional neural network that is good at processing spatial features, or a recurrent neural network that is good at analyzing time series.

[0117] The anomaly detection model can automatically detect abnormal data that deviates from normal operation by learning and identifying the operating data of the power equipment during normal operation. For example, when the transformer of the power equipment is locally overheated, the convolutional neural network can capture the spatial abnormal characteristics of the temperature distribution; and when the vibration frequency of the power equipment gradually increases abnormally, the recurrent neural network can identify this abnormal trend in the time series. Finally, based on the analysis results of the anomaly detection model, it is determined whether the power equipment is abnormal and the inspection results of the power equipment are obtained. Compared with the traditional power inspection method, this method can detect potential faults of power equipment more accurately and timely, and improve the operational reliability of the power system.

[0118] The embodiment of the present application obtains operation-related data of the power equipment collected by multiple sensors respectively, so as to obtain operation data of different dimensions of the power equipment; determines the initial weighted weight corresponding to the sensor according to the operation-related data collected by the sensor, and determines the confidence of the operation-related data according to the determined initial weighted weight and the change trend of the operation-related data within the most recent set time, and then adjusts the initial weighted weight according to the confidence to obtain the target weighted weight, so that the target weighted weight can be adaptively adjusted according to the change trend of the operation-related data within the most recent set time, so as to provide a more accurate weighted weight for subsequent weighted fusion; according to the target weighted weight corresponding to each sensor in the multiple sensors, the operation-related data corresponding to the multiple sensors are weightedly fused to obtain the inspection perception data of the power equipment, wherein the inspection perception data fuses the operation-related data of different dimensions; based on the inspection perception data, determines whether there is an abnormality in the power equipment, and obtains an accurate and comprehensive inspection result of the power equipment.

[0119] On the basis of the above embodiment, the initial weighted weight corresponding to the sensor is determined according to the operation-related data collected by the sensor, including: calculating the quality assessment index of the operation-related data collected by the sensor; quantifying the quality assessment index to obtain a quantitative score of the sensor; and determining the initial weighted weight corresponding to the sensor according to the quantitative score.

[0120] In this embodiment, it can be understood that when determining the initial weighted weight corresponding to the sensor, the quality of the operation-related data collected by the sensor needs to be considered, that is, the quality evaluation index of the operation-related data collected by the sensor needs to be calculated. This is because different sensors are easily affected by factors such as their own performance and environmental interference, resulting in differences in the quality of the collected operation-related data. Among them, the quality evaluation index is a standard for quantitatively evaluating the quality of the operation-related data collected by the sensor, such as signal-to-noise ratio, data consistency, integrity, etc. The quantitative score of the sensor is obtained by quantifying the quality evaluation index. The quantitative score can understand the reliability of the operation-related data collected by different sensors, thereby giving a higher weight to the operation-related data with good quality and a lower weight to the operation-related data with poor quality, so as to ensure that the fused inspection perception data is more accurate and reliable, and to improve the accuracy of abnormal detection of power equipment.

[0121] Further, in some embodiments, the step of determining the confidence of the operation-related data according to the initial weighted weight and the change trend of the operation-related data within the most recent set time described in S102 includes: determining the confidence of the operation-related data according to the initial weighted weight and the change trend of the operation-related data within the most recent set time through a Bayesian probability model. The Bayesian probability model provides a method for updating probability estimates based on existing knowledge and new observation data.

[0122] In the above embodiment, it can be understood that the Bayesian probability model dynamically determines the confidence of the operation-related data based on the initial weighted weight and the change trend of the operation-related data within the most recent set time. For example, if the initial weighted weight corresponding to a sensor is high, and the operation-related data collected by the sensor remains stable within the most recent set time, the confidence of the operation-related data can be increased; conversely, if the operation-related data collected by the sensor fluctuates greatly within the most recent set time, the confidence of the operation-related data can be reduced.

[0123] The embodiment of the present application introduces a Bayesian probability model to dynamically adjust the confidence level of operation-related data collected by different sensors, thereby improving the reliability of inspection perception data.

[0124] Based on the above embodiment, the initial weighted weight is adjusted according to the confidence level to obtain the target weighted weight corresponding to the sensor, including: according to the confidence level, using an exponential decay function to adjust the initial weighted weight to obtain the target weighted weight corresponding to the sensor.

[0125] In this embodiment, it can be understood that when the confidence is brought into the exponential decay function, the higher the confidence, the larger the result of the exponential decay function. The result of the determined exponential decay function is multiplied by the initial weighted weight to obtain the target weighted weight corresponding to the sensor. The reason is that if the operation-related data has a very high confidence, then the embodiment of the present application hopes that the operation-related data will have a greater impact on the inspection perception data. Therefore, the embodiment of the present application uses an exponential decay function to convert the high confidence into a larger weight adjustment factor, thereby increasing the weight of the corresponding operation-related data.

[0126] The embodiment of the present application uses an exponential decay function to adjust the initial weighted weight, which can enhance the influence of high-confidence operation-related data on the inspection perception data and reduce the influence of low-confidence operation-related data on the inspection perception data, thereby improving the reliability of the inspection perception data.

[0127] Furthermore, the power inspection method provided in the above embodiment also includes: if the power equipment is abnormal, determining the abnormal level of the power equipment according to the power equipment; determining the alarm information corresponding to the abnormal level based on the abnormal level; and transmitting the alarm information to the remote monitoring center. It can be understood that if S104 determines that the power equipment is abnormal, it is necessary to determine the abnormal level of the power equipment according to the abnormal power equipment, wherein the abnormal level is used to evaluate the severity, potential risks and response measures required for the abnormal power equipment. Among them, the abnormal level can be set according to the actual situation.

[0128] In one implementation, the abnormality levels are divided into level I, level II, level III, and level IV, and the urgency of the abnormality level is inversely proportional to the level number.

[0129] For example, assuming that the temperature of the generator stator winding is slightly higher than the normal value but does not exceed the alarm threshold, it can be determined that the abnormality level of the generator is Level III; the lightning arrester counter shows that there has been an action recently, but the leakage current is normal, then the abnormality level of the lightning arrester can be determined to be Level IV; there is a slight abnormal vibration when the motor is running, but the bearing temperature is normal, then the abnormality level of the motor can be determined to be Level III.

[0130] After determining the abnormality level, determine the alarm information corresponding to the abnormality level. This means that different abnormality levels correspond to different alarm messages. Assuming that the abnormality level is level I, the corresponding alarm message is to repair the abnormal power equipment immediately; the abnormality level is level IV, and the corresponding alarm message is to check the abnormal power equipment regularly.

[0131] Furthermore, the alarm information is transmitted to the remote monitoring center, so that the staff of the remote monitoring center can timely report the alarm information and deal with abnormal power equipment as soon as possible to ensure the safe operation of the power equipment and the safety of the power system. The specific implementation method of transmitting the alarm information to the remote monitoring center can be selected according to actual needs.

[0132] In one implementation, the alarm information is transmitted to the remote monitoring center in a single-channel communication mode. This single-channel communication mode requires fewer hardware resources, making it less expensive than a multi-channel communication mode.

[0133] In another implementation, the alarm information is transmitted to the remote monitoring center in a multi-channel communication mode, wherein the multi-channel communication mode includes time division multiplexing, frequency division multiplexing, parallel transmission, etc. This multi-channel communication mode can improve the efficiency of alarm information transmission and improve the reliability of the alarm information received by the remote monitoring center.

[0134] Furthermore, the power inspection method provided in the above embodiment also includes: generating an inspection report according to the operation-related data and the inspection results; and sending the inspection report to a remote monitoring center.

[0135] In this embodiment, it can be understood that the generation of the inspection report requires the collection of the operation-related data obtained in S101 and the inspection results obtained in S104, and the data analysis of the operation-related data and the inspection results, such as the use of time series analysis, statistical analysis, anomaly analysis and other techniques to conduct in-depth analysis of the operation-related data and the inspection results to identify the operating status and potential hidden dangers of the power equipment. Then, the in-depth analysis results are filled into the preset inspection report template to generate the inspection report. Finally, the generated inspection report is sent to the remote monitoring center. It should be noted that the principle of sending the inspection report to the remote monitoring center is similar to that of transmitting the alarm information to the remote monitoring center, so the embodiment of the present application will not be repeated here.

[0136] The embodiment of the present application generates a corresponding inspection report by analyzing operation-related data and inspection results, and sends the generated inspection report to a remote monitoring center, so that the operation and maintenance personnel of the power equipment can clearly know the status of the power equipment, help the operation and maintenance personnel to formulate wise maintenance strategies, and avoid accidents.

[0137] On the basis of the above embodiments, the power inspection method provided by the above embodiments also includes: constructing an inspection semantic map based on inspection perception data, the inspection semantic map including passable areas, dangerous areas and obstacle information; determining the inspection terrain distribution based on the inspection perception data and the inspection semantic map; determining the inspection path of the inspection equipment based on the inspection terrain distribution, and adjusting the chassis and posture of the inspection equipment, the inspection equipment is equipped with a deformable chassis and a posture adjustment structure.

[0138] Among them, the specific implementation method of constructing the inspection semantic map based on the inspection perception data can be selected according to the actual situation.

[0139] For example, the inspection perception data is imported into the map generation model, and the map generation model will automatically output the constructed inspection semantic map, wherein the map generation model can be a visual simultaneous positioning and map construction algorithm based on feature points, or a visual simultaneous positioning and map construction algorithm based on the direct method. It should be noted that the type of map generation model is not limited in the embodiments of the present application.

[0140] After the inspection semantic map is determined, the inspection terrain distribution is determined based on the inspection perception data and the inspection semantic map, wherein the inspection terrain distribution includes different terrain types and their distribution within the inspection area.

[0141] Next, the inspection path of the inspection device is determined according to the determined inspection terrain distribution. The inspection path is the movement path of the inspection device in the inspection area, and the movement path is affected by the inspection terrain distribution in the inspection area.

[0142] Among them, the inspection path of the inspection equipment is determined according to the inspection terrain distribution, including: based on the path planning algorithm, the inspection path of the inspection equipment is determined according to the inspection terrain distribution, and the path planning algorithm integrates the global path planning optimization strategy and the local path planning optimization strategy. It can be understood that the path planning algorithm requires multi-level algorithms to collaborate to determine the inspection path of the inspection equipment. Specifically, firstly, the global path planning optimization strategy is used to generate a reference path covering the inspection area according to the inspection terrain distribution. The reference path must meet global optimization indicators such as the shortest total distance; at the same time, the local path planning optimization strategy is introduced to perceive the local terrain changes in real time and adjust the parameters of the reference path to obtain the inspection path.

[0143] The type of inspection equipment is not limited in the embodiments of the present application, and the inspection equipment may be an inspection robot.

[0144] Furthermore, the inspection equipment is also equipped with a deformable chassis and a posture adjustment structure. The deformable chassis refers to the bottom support structure of the inspection equipment, which can dynamically adjust its shape according to the distribution conditions of the inspection terrain. For example, the chassis can be extended or the wheelbase can be changed to enable the inspection equipment to adapt to narrow spaces or environments with many obstacles. This deformable chassis can significantly improve the passability and stability of the inspection equipment.

[0145] The posture adjustment structure means that the inspection equipment can actively adjust its own posture, such as adjusting the tilt angle, center of gravity position, etc. of the inspection equipment to cope with irregular inspection ground.

[0146] In summary, the embodiments of the present application can significantly improve the safety and economy of inspection equipment when inspecting complex terrain through the above-mentioned method.

[0147] Furthermore, when multiple inspection devices cooperate with each other to perform power inspection, the power inspection method also includes: obtaining the inspection position of other inspection devices; based on the path planning algorithm, determining the next inspection position according to the inspection terrain distribution and the inspection position of other inspection devices.

[0148] When multiple inspection devices need to collaborate to complete power inspections, it is necessary to obtain the inspection locations of other inspection devices, and then use the path planning algorithm to combine the inspection terrain distribution and the real-time locations of other inspection devices to determine the optimal next inspection location for the current device. Specifically, the path planning algorithm generates an inspection path by considering the inspection terrain distribution. At the same time, in order to avoid conflicts or repeated inspections between multiple inspection devices, the path planning algorithm will also dynamically adjust the next inspection location of the current inspection device based on the current inspection locations of other inspection devices.

[0149] The embodiment of the present application can significantly improve the efficiency of power inspection by utilizing multiple inspection devices for collaborative inspection.

[0150] In some embodiments, the power inspection method provided in the embodiments of the present application also includes: determining a motion mode of the inspection equipment based on the inspection perception data, the motion mode reflecting the motion state of the inspection equipment adaptively adjusted according to the inspection perception data; based on the motion mode, controlling the inspection equipment to move on the inspection path. Specifically, the motion mode is a motion strategy that the inspection equipment adaptively selects based on the perception data, such as using a track mode on flat ground and switching to a four-wheel drive mode in rugged terrain. Based on the determined motion mode, the inspection equipment is controlled to move safely and efficiently on the inspection path. In this way, the inspection equipment can flexibly respond to complex and changing environments to ensure the smooth completion of the inspection tasks.

[0151] Next, an example will be given to illustrate how to use the power inspection system corresponding to the power inspection method provided by the present application. Figure 2 Schematic diagram of a power inspection system corresponding to the power inspection method provided in the embodiment of the present application. Figure 2 As shown, the system includes the following parts:

[0152] 1. Inspection equipment:

[0153] Autonomous navigation function: Based on lidar and ultrasonic sensors, it can realize autonomous positioning and path planning, and can autonomously avoid obstacles and reach the designated inspection location.

[0154] Stability design: four-wheel drive or crawler design is adopted to adapt to complex industrial environments.

[0155] 2. Sensor module:

[0156] Infrared temperature measurement module: includes infrared thermal imager and temperature sensor, used to measure the surface temperature of power equipment and identify potential hot spots of power equipment.

[0157] HD camera: captures HD images of power equipment in real time, combines image recognition algorithms to perform appearance inspection, and identifies surface defects such as cracks and corrosion on power equipment.

[0158] Vibration sensor: detects the vibration of power equipment and analyzes whether the power equipment is operating normally.

[0159] Gas sensor: used to monitor whether there is gas leakage around electrical equipment, especially suitable for monitoring substations and oil-immersed equipment.

[0160] 3. Data processing module:

[0161] Data fusion algorithm: Kalman filtering and other data fusion algorithms are used to integrate infrared temperature measurement data, high-definition image data, vibration data and gas data to generate a comprehensive power equipment status report.

[0162] Fault identification model: Based on machine learning models, such as SVM or decision tree, fault identification of power equipment is performed to determine whether the power equipment is in an abnormal state based on the joint features of different sensor data.

[0163] 4. Control module:

[0164] Autonomous inspection control: The inspection equipment conducts autonomous inspections according to the inspection path, relying on the navigation system to identify and avoid obstacles.

[0165] Real-time warning: When the data of a certain sensor reaches the abnormal threshold, a warning signal is automatically issued, and the alarm information corresponding to the warning signal is sent to the operation and maintenance personnel through the communication module.

[0166] 5. User monitoring terminal:

[0167] Real-time monitoring: Operation and maintenance personnel can view the data collected by inspection equipment and the operating status of power equipment in real time through the monitoring terminal.

[0168] Report generation: Automatically generate inspection reports based on the collected data, including power equipment health scores and operating status assessments.

[0169] Furthermore, in combination with an embodiment of appearance and temperature monitoring of electric power equipment, implementation details of the above system are further elaborated.

[0170] Example: Appearance and temperature monitoring of power equipment

[0171] 1. Inspection preparation:

[0172] Intelligent inspection equipment, such as inspection robots, are deployed in a substation. The intelligent inspection equipment is equipped with infrared temperature measurement modules, high-definition cameras and vibration sensors, and can set inspection routes.

[0173] 2. Autonomous inspection process:

[0174] The intelligent inspection equipment uses lidar to achieve autonomous navigation according to the set inspection route, and collects temperature, image and vibration data of substation equipment in real time along the way.

[0175] 3. Data Fusion:

[0176] The data processing module fuses and analyzes the infrared temperature measurement data with the images collected by the high-definition camera to check whether there are overheating areas on the surface of the power equipment and identify whether the power equipment has defects such as surface cracks or corrosion.

[0177] If the temperature data exceeds the set threshold, an early warning will be automatically triggered and a temperature abnormality report will be sent to the monitoring terminal.

[0178] In summary, the multi-sensor fusion power inspection system provided in the embodiment of the present application can realize autonomous inspection, multi-dimensional data collection and fault warning of power equipment, has high inspection efficiency and accuracy, reduces the workload of manual inspection, and improves the level of intelligence of power equipment management.

[0179] Furthermore, in the embodiments of the present application, through the fault identification model of multi-dimensional data fusion and machine learning, the inspection equipment can accurately identify potential faults of power equipment and issue timely warnings, thereby improving the monitoring efficiency and safety of power equipment.

[0180] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0181] Figure 3 The schematic diagram of the structure of the power inspection device provided in this application is as follows: Figure 3 As shown, the power inspection device 300 provided in this embodiment includes:

[0182] An acquisition module 301 is used to acquire operation-related data of the power equipment collected by multiple sensors;

[0183] The first determination module 302 is used to obtain the target weighted weight corresponding to each sensor of the multiple sensors through a weight determination process, and the weight determination process includes: determining the initial weighted weight corresponding to the sensor according to the operation related data collected by the sensor; determining the confidence of the operation related data according to the initial weighted weight and the change trend of the operation related data within a recent set time period; adjusting the initial weighted weight according to the confidence to obtain the target weighted weight corresponding to the sensor;

[0184] A fusion module 303 is used to perform weighted fusion on the operation-related data corresponding to the multiple sensors based on the target weighted weights corresponding to each sensor in the multiple sensors, so as to obtain the inspection perception data corresponding to the power equipment;

[0185] The second determination module 304 is used to determine whether the power equipment is abnormal based on the inspection sensing data and obtain the inspection result of the power equipment.

[0186] In a possible implementation manner, the first determining module 302 is specifically configured to:

[0187] Calculate quality assessment indicators of operation-related data acquired by sensors;

[0188] Quantify the quality assessment indicators to obtain the quantitative score of the sensor;

[0189] According to the quantitative score, the initial weight corresponding to the sensor is determined.

[0190] In a possible implementation manner, the first determining module 302 is specifically configured to:

[0191] Through the Bayesian probability model, the confidence level of the operation-related data is determined based on the initial weighted weights and the changing trend of the operation-related data within the most recent set time period.

[0192] In a possible implementation manner, the first determining module 302 is specifically configured to:

[0193] According to the confidence level, an exponential decay function is used to adjust the initial weighted weight to obtain the target weighted weight corresponding to the sensor.

[0194] In a possible implementation, the fusion module 303 is specifically configured to:

[0195] Adopting adaptive filtering algorithm to reduce noise of operation-related data corresponding to multiple sensors, the adaptive filtering algorithm selects corresponding filtering parameters according to the type of operation-related data by combining wavelet transform and Kalman filter;

[0196] Perform multi-scale feature extraction on the operation-related data after noise reduction to obtain multiple key information features;

[0197] Map multiple key information features to a unified feature space to obtain feature alignment results;

[0198] Based on the target weights corresponding to each sensor in multiple sensors, the feature alignment results are weighted fused to obtain the inspection perception data corresponding to the power equipment.

[0199] In a possible implementation manner, the second determining module 304 is specifically configured to:

[0200] The inspection sensing data is input into a preset anomaly detection model, which is a convolutional neural network or a recurrent neural network;

[0201] Based on the anomaly detection model, determine whether the power equipment is abnormal and obtain the inspection results of the power equipment.

[0202] In a possible implementation manner, the power inspection device further includes a processing module (not shown), which is specifically configured to:

[0203] If the power equipment is abnormal, determine the abnormal level of the power equipment according to the power equipment;

[0204] Based on the abnormality level, determine the alarm information corresponding to the abnormality level;

[0205] Transmit alarm information to the remote monitoring center.

[0206] In a possible implementation manner, the processing module is specifically used for:

[0207] Generate inspection reports based on operation-related data and inspection results;

[0208] Send inspection reports to the remote monitoring center.

[0209] In a possible implementation manner, the processing module is further configured to:

[0210] Construct an inspection semantic map based on inspection perception data. The inspection semantic map includes information on traversable areas, dangerous areas, and obstacles.

[0211] Determine the inspection terrain distribution based on inspection perception data and inspection semantic map;

[0212] According to the inspection terrain distribution, the inspection path of the inspection equipment is determined, and the chassis and posture of the inspection equipment are adjusted. The inspection equipment is equipped with a deformable chassis and a posture adjustment structure.

[0213] In a possible implementation manner, the processing module is further configured to:

[0214] Based on the path planning algorithm, the inspection path of the inspection equipment is determined according to the inspection terrain distribution. The path planning algorithm integrates the global path planning optimization strategy and the local path planning optimization strategy.

[0215] In a possible implementation, when multiple inspection devices cooperate with each other to perform power inspection, the processing module is further used to:

[0216] Obtain the inspection location of other inspection equipment;

[0217] Based on the path planning algorithm, the next inspection location is determined according to the inspection terrain distribution and the inspection locations of other inspection equipment.

[0218] In a possible implementation manner, the processing module is further configured to:

[0219] According to the inspection sensing data, the movement mode of the inspection equipment is determined, and the movement mode reflects the movement state of the inspection equipment that is adaptively adjusted according to the inspection sensing data;

[0220] Based on the motion mode, the inspection equipment is controlled to move on the inspection path.

[0221] The electric power inspection device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0222] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the processing module can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0223] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more microprocessors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module above is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0224] Figure 4 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 4 As shown, the electronic device 400 provided in the embodiment of the present application may include: a processor 401, and a memory 402 communicatively connected to the processor, wherein:

[0225] Memory stores computer-executable instructions;

[0226] The processor executes the computer-executable instructions stored in the memory to implement the method described in the foregoing method embodiment.

[0227] It should be understood that the processor 401 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The memory 402 may include a high-speed random access memory (RAM), and may also include non-volatile storage NVM (non-volatile memory), such as at least one disk storage, and can also be a USB flash drive, a mobile hard disk, a read-only memory, a disk or an optical disk, etc.

[0228] Optionally, the electronic device 400 may further include a communication interface 404. In a specific implementation, if the communication interface 404, the memory 402 and the processor 401 are implemented independently, the communication interface 404, the memory 402 and the processor 401 may be interconnected through a bus and communicate with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0229] Optionally, in a specific implementation, if the communication interface 404, the memory 402 and the processor 401 are integrated on a chip, the communication interface 404, the memory 402 and the processor 401 can communicate through an internal interface.

[0230] An embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed, they are used to implement the method described in any of the aforementioned embodiments.

[0231] It is understood that the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0232] An exemplary computer-readable storage medium is coupled to a processor so that the processor can read information from the computer-readable storage medium and write information to the computer-readable storage medium. Of course, the computer-readable storage medium can also be an integral part of the processor. The processor and the computer-readable storage medium can be located in an ASIC. Of course, the processor and the computer-readable storage medium can also exist in an electronic device as discrete components.

[0233] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a computer-readable storage medium, including a number of instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application.

[0234] An embodiment of the present application also provides a computer program product, including a computer program, which implements the method described in any of the above embodiments when executed.

[0235] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0236] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0237] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0238] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0239] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A power inspection method, characterized in that: include: Acquire operation-related data of the power equipment collected by multiple sensors; Obtaining a target weighted weight corresponding to each sensor of the plurality of sensors through a weight determination process, wherein the weight determination process includes: determining an initial weighted weight corresponding to the sensor according to operation-related data collected by the sensor; determining the confidence of the operation-related data according to the initial weighted weight and the change trend of the operation-related data within a recent set time period; adjusting the initial weighted weight according to the confidence to obtain a target weighted weight corresponding to the sensor; Based on the target weighted weights corresponding to each sensor in the multiple sensors, weighted fusion is performed on the operation-related data corresponding to the multiple sensors to obtain the inspection perception data corresponding to the power equipment; Based on the inspection sensing data, determine whether the power equipment is abnormal, and obtain the inspection result of the power equipment.

2. The method according to claim 1, characterized in that: The step of determining the initial weight corresponding to the sensor according to the operation-related data collected by the sensor includes: Calculating quality assessment indicators of operation-related data collected by the sensor; Quantifying the quality assessment index to obtain a quantitative score of the sensor; An initial weight corresponding to the sensor is determined according to the quantitative score.

3. The method according to claim 1, characterized in that Determining the confidence level of the operation-related data according to the initial weighted weight and the change trend of the operation-related data within a recent set time period includes: The confidence level of the operation-related data is determined through a Bayesian probability model according to the initial weighted weight and a change trend of the operation-related data within a recent set time period.

4. The method according to claim 1, characterized in that: The step of adjusting the initial weight according to the confidence level to obtain the target weight corresponding to the sensor includes: According to the confidence, an exponential decay function is used to adjust the initial weighted weight to obtain the target weighted weight corresponding to the sensor.

5. The method according to any one of claims 1 to 4, characterized in that The step of performing weighted fusion on the operation-related data corresponding to the multiple sensors based on the target weighted weights corresponding to each sensor in the multiple sensors to obtain the inspection perception data corresponding to the power equipment includes: An adaptive filtering algorithm is used to perform noise reduction processing on the operation-related data respectively corresponding to the multiple sensors, wherein the adaptive filtering algorithm selects corresponding filtering parameters according to the type of the operation-related data by combining wavelet transform and Kalman filter; Perform multi-scale feature extraction on the operation-related data after noise reduction to obtain multiple key information features; Mapping the multiple key information features to a unified feature space to obtain a feature alignment result; Based on the target weighted weights corresponding to each sensor in the multiple sensors, the feature alignment results are weightedly fused to obtain the inspection perception data corresponding to the power equipment.

6. The method according to any one of claims 1 to 4, characterized in that The determining whether the electric power equipment is abnormal according to the inspection sensing data and obtaining the inspection result of the electric power equipment includes: Inputting the inspection sensing data into a preset anomaly detection model, wherein the anomaly detection model is a convolutional neural network or a recurrent neural network; Based on the abnormality detection model, it is determined whether the power equipment is abnormal, and an inspection result of the power equipment is obtained.

7. The method according to any one of claims 1 to 4, characterized in that Also includes: If the electric power equipment is abnormal, determining the abnormality level of the electric power equipment according to the electric power equipment; Based on the abnormality level, determining alarm information corresponding to the abnormality level; The alarm information is transmitted to a remote monitoring center.

8. The method according to any one of claims 1 to 4, characterized in that Also includes: Generate an inspection report based on the operation-related data and the inspection results; The inspection report is sent to a remote monitoring center.

9. The method according to any one of claims 1 to 4, characterized in that Also includes: Constructing an inspection semantic map according to the inspection perception data, wherein the inspection semantic map includes passable areas, dangerous areas and obstacle information; Determining inspection terrain distribution according to the inspection perception data and the inspection semantic map; According to the inspection terrain distribution, the inspection path of the inspection equipment is determined, and the chassis and posture of the inspection equipment are adjusted. The inspection equipment is equipped with a deformable chassis and a posture adjustment structure.

10. The method according to claim 9, characterized in that Determining the inspection path of the inspection equipment according to the inspection terrain distribution includes: Based on a path planning algorithm, the inspection path of the inspection device is determined according to the inspection terrain distribution. The path planning algorithm integrates a global path planning optimization strategy and a local path planning optimization strategy.

11. The method according to claim 9, characterized in that When multiple inspection devices cooperate with each other to perform power inspection, the method further includes: Obtain the inspection location of other inspection equipment; Based on a path planning algorithm, the next inspection position is determined according to the inspection terrain distribution and the inspection positions of the other inspection equipment.

12. The method according to claim 9, characterized in that Also includes: Determine a motion mode of the inspection device according to the inspection sensing data, wherein the motion mode reflects a motion state of the inspection device adaptively adjusted according to the inspection sensing data; Based on the motion pattern, the inspection device is controlled to move on the inspection path.

13. A power inspection device, characterized in that: include: An acquisition module, used to acquire operation-related data of the power equipment collected by multiple sensors; A first determination module is used to obtain a target weighted weight corresponding to each sensor of the plurality of sensors through a weight determination process, wherein the weight determination process includes: determining an initial weighted weight corresponding to the sensor according to operation-related data collected by the sensor; determining the confidence of the operation-related data according to the initial weighted weight and the change trend of the operation-related data within a recent set time period; and adjusting the initial weighted weight according to the confidence to obtain a target weighted weight corresponding to the sensor; A fusion module, configured to perform weighted fusion on the operation-related data corresponding to the multiple sensors based on the target weighted weights corresponding to each sensor in the multiple sensors, so as to obtain the inspection perception data corresponding to the power equipment; The second determination module is used to determine whether the power equipment is abnormal based on the inspection sensing data and obtain the inspection result of the power equipment.

14. An intelligent inspection robot, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed, they are used to implement the method according to any one of claims 1 to 12.

16. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 12 when being executed.

Images