Fault hidden danger identification method based on multiple sensors and rail-mounted inspection robot

Abstract

The invention provides a fault hidden danger identification method based on multiple sensors and a rail-mounted inspection robot. The method comprises the following steps: the on-rail inspection robot extracts the type attribute based on a high-definition image of target electrical equipment, screens out a plurality of detection sensors according to the type attribute, and determines the confidence priority coefficient of each detection sensor; controlling each detection sensor to detect the target electrical equipment so as to obtain multiple groups of detection data, and determining the fault probability of the target electrical equipment according to the multiple groups of detection data and the corresponding confidence priority coefficients; and determining the target electrical equipment of which the fault probability is higher than a first probability threshold as fault hidden danger equipment, and outputting the fault hidden danger equipment to related personnel. According to the invention, the detection sensor of a proper type can be selected according to the type of the electrical equipment, and fusion processing can be carried out on multiple groups of detection data obtained through detection according to the confidence priority coefficient of each detection sensor so as to obtain a more accurate fault probability of the target electrical equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of inspection robots, and in particular to a multi-sensor based fault hidden danger identification method and a rail-hanging inspection robot. Background Art

[0002] The use of rail-mounted inspection robots to inspect electrical equipment is an emerging inspection technology. The rail-mounted inspection robots can conveniently detect faults in the electrical equipment below through the aerial track without interfering with the passage of personnel, equipment, etc. below.

[0003] Existing rail inspection robots are usually equipped with only one fault detection sensor, such as an infrared camera, which mainly acquires infrared images of electrical equipment and determines whether the electrical equipment has potential faults based on temperature. However, practice has shown that relying on only one detection sensor to detect potential faults in electrical equipment cannot ensure the credibility of the fault detection results. How to further improve the accuracy of electrical equipment fault detection is a technical problem that needs to be solved at present. Summary of the invention

[0004] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a fault hidden danger identification method based on multiple sensors, a rail inspection robot, an electronic device, a computer storage medium and a computer program product.

[0005] The present invention provides a method for identifying potential fault hazards based on multiple sensors, the method comprising the following steps: The rail inspection robot takes a high-definition image of the target electrical equipment, extracts the type attribute of the target electrical equipment based on the high-definition image, selects and obtains a number of detection sensors according to the type attribute, and determines the confidence priority coefficient of each detection sensor; Controlling each of the detection sensors to detect the target electrical equipment to obtain multiple groups of detection data, and determining the failure probability of the target electrical equipment according to the multiple groups of detection data and the corresponding confidence priority coefficients; The target electrical equipment whose failure probability is higher than a first probability threshold is determined as a potential failure equipment, and the information is output to relevant personnel.

[0006] Optionally, the rail inspection robot captures a high-definition image of the target electrical equipment, including: The rail inspection robot receives the inspection scheduling task sent by the server, and obtains the target electrical equipment that needs to be inspected, as well as the distribution location and inspection order of each target electrical equipment from the inspection scheduling task analysis; An inspection path is determined according to the distribution positions and the inspection order, and the inspection path includes various inspection points. When the inspection point is reached, a high-definition camera is controlled to capture a high-definition image of the target electrical equipment corresponding to the inspection point.

[0007] Optionally, extracting and deriving a type attribute of the target electrical device based on the high-definition image includes: Extracting from the high-definition image a first high-definition image corresponding to the target electrical device and a second high-definition image corresponding to a plurality of associated electrical devices that are electrically connected to the target electrical device; Extracting first feature data of the target electrical device from the first high-definition image, and extracting second feature data of each of the associated electrical devices from the second high-definition image; Using a classification model to classify the first feature data, to obtain a first type attribute of the target electrical equipment and a corresponding confidence probability; If the confidence probability is higher than the second probability threshold, determining the first type attribute as the type attribute of the target electrical device; If the confidence probability is lower than the second probability threshold, a large classification model is used to perform secondary classification processing on the first feature data and each of the second feature data to obtain the second type attribute of the target electrical equipment, and the second type attribute is determined as the type attribute of the target electrical equipment.

[0008] Optionally, the screening to obtain a plurality of detection sensors according to the type attribute and determining a confidence priority coefficient of each of the detection sensors includes: According to the type attribute, a preset comparison table is analyzed to screen out a corresponding number of the detection sensors; The detection history data of each detection sensor on the target electrical device is obtained, the detection accuracy is calculated according to the detection history data, and the confidence priority coefficient of each detection sensor is determined according to the detection accuracy.

[0009] Optionally, determining the failure probability of the target electrical equipment according to the multiple groups of detection data and the corresponding confidence priority coefficients includes: Performing fault analysis on each group of detection data based on preset evaluation criteria to obtain corresponding fault sub-probability; Each fault sub-probability is multiplied by the corresponding confidence priority coefficient and then weighted fusion is performed to obtain the fault probability of the target electrical equipment.

[0010] Optionally, determining the target electrical equipment whose failure probability is higher than a first probability threshold as a potential failure equipment and outputting the information to relevant personnel includes: Determine the first probability threshold of the corresponding target electrical device according to the type attribute; The target electrical equipment whose failure probability is higher than a first probability threshold is determined as a potential failure equipment, and the information is output to relevant personnel.

[0011] The present invention also provides a rail inspection robot, the device comprising a plurality of detection sensors, a processing device, and a storage device, the processing device calls and runs a computer program in the storage device to implement the following steps; The rail inspection robot takes a high-definition image of the target electrical equipment, extracts the type attribute of the target electrical equipment based on the high-definition image, selects and obtains a number of detection sensors according to the type attribute, and determines the confidence priority coefficient of each detection sensor; Controlling each of the detection sensors to detect the target electrical equipment to obtain multiple groups of detection data, and determining the failure probability of the target electrical equipment according to the multiple groups of detection data and the corresponding confidence priority coefficients; The target electrical equipment whose failure probability is higher than a first probability threshold is determined as a potential failure equipment, and the information is output to relevant personnel.

[0012] The present invention also provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute any of the methods described above.

[0013] The present invention also provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, any of the above methods is executed.

[0014] The present invention also provides a computer program product, which includes a computer program stored in a computer storage medium, and when the computer program is executed by a processor of an electronic device, it implements any of the methods described above.

[0015] The present invention configures a rail inspection robot with a variety of detection sensors, and can select appropriate types of detection sensors according to the type of electrical equipment. It can also fuse multiple groups of detection data obtained according to the confidence priority coefficient of each detection sensor to obtain a more accurate failure probability of the target electrical equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a schematic diagram of a fault hidden danger identification method based on multiple sensors disclosed in an embodiment of the present invention.

[0018] Figure 2 It is a schematic diagram of a rail-hanging inspection robot disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0020] See also Figure 1 The embodiment of the present invention discloses a method for identifying potential fault hazards based on multiple sensors, the method comprising the following steps: The rail inspection robot takes a high-definition image of the target electrical equipment, extracts the type attribute of the target electrical equipment based on the high-definition image, selects and obtains a number of detection sensors according to the type attribute, and determines the confidence priority coefficient of each detection sensor; Controlling each of the detection sensors to detect the target electrical equipment to obtain multiple groups of detection data, and determining the failure probability of the target electrical equipment according to the multiple groups of detection data and the corresponding confidence priority coefficients; The target electrical equipment whose failure probability is higher than a first probability threshold is determined as a potential failure equipment, and the information is output to relevant personnel.

[0021] The present invention adopts a rail-hanging inspection robot to inspect the electrical equipment in the area. The rail-hanging inspection robot is equipped with a variety of detection sensors, including but not limited to high-definition cameras, infrared cameras, current transformers, voltage transformers, temperature sensors, magnetoresistive current sensors (anisotropic magnetoresistance effect (AMR), giant magnetoresistance (GMR) and tunnel magnetoresistance (TMR) sensors, etc.). The rail-hanging inspection robot first controls the high-definition camera to capture a high-definition image of the target electrical equipment, and extracts the type attribute of the target electrical equipment from the captured high-definition image. The target electrical equipment is, for example, a power transformer, a motor, an electrical control device, etc.; according to the type attribute, a number of detection sensors suitable for the target electrical equipment can be screened and the confidence priority coefficients of these detection sensors can be determined. Then, each detection sensor is controlled to detect the target electrical equipment to obtain multiple groups of detection data, and the failure probability of the target electrical equipment is determined according to the multiple groups of detection data and the confidence priority coefficients determined above. If the failure probability of the target electrical equipment is higher than the probability threshold, it is determined as a fault potential equipment and output to relevant personnel. Based on this, relevant personnel can remotely or on-sitely process the fault potential equipment in advance, thereby reducing the losses caused by equipment failure.

[0022] The basic structure of the rail-hanging inspection robot and its rail in the present invention can completely adopt the existing technology, and the present invention does not limit this.

[0023] Optionally, the rail inspection robot captures a high-definition image of the target electrical equipment, including: The rail inspection robot receives the inspection scheduling task sent by the server, and obtains the target electrical equipment that needs to be inspected, as well as the distribution location and inspection order of each target electrical equipment from the inspection scheduling task analysis; An inspection path is determined according to the distribution positions and the inspection order, and the inspection path includes various inspection points. When the inspection point is reached, a high-definition camera is controlled to capture a high-definition image of the target electrical equipment corresponding to the inspection point.

[0024] In this embodiment, a rail-hanging inspection robot docking station can be set in the inspected area, and multiple rail-hanging inspection robots are on standby in the docking station and can also be charged in the docking station. When there is a need for inspection, the server will generate a corresponding inspection scheduling task and send it to the most suitable rail-hanging inspection robot. The rail-hanging inspection robot analyzes the received inspection scheduling task to obtain the target electrical equipment that needs to be inspected this time, as well as the distribution position and inspection order of these target electrical equipment in the inspected area. The rail-hanging inspection robot can determine the optimal inspection path based on the distribution position and inspection order of each target electrical equipment. Of course, the determination of the inspection path also needs to consider the layout of the track, which will not be described in detail. When the rail-hanging inspection robot runs to each inspection point, it can control the high-definition camera to capture the high-definition image of the target electrical equipment corresponding to the inspection point.

[0025] Optionally, extracting and deriving a type attribute of the target electrical device based on the high-definition image includes: Extracting from the high-definition image a first high-definition image corresponding to the target electrical device and a second high-definition image corresponding to a plurality of associated electrical devices that are electrically connected to the target electrical device; Extracting first feature data of the target electrical device from the first high-definition image, and extracting second feature data of each of the associated electrical devices from the second high-definition image; Using a classification model to classify the first feature data, to obtain a first type attribute of the target electrical equipment and a corresponding confidence probability; If the confidence probability is higher than the second probability threshold, determining the first type attribute as the type attribute of the target electrical device; If the confidence probability is lower than the second probability threshold, a large classification model is used to perform secondary classification processing on the first feature data and each of the second feature data to obtain the second type attribute of the target electrical equipment, and the second type attribute is determined as the type attribute of the target electrical equipment.

[0026] In this embodiment, the high-definition image captured by the high-definition camera includes the target electrical device and several associated electrical devices that are electrically connected to the target electrical device. The sub-images corresponding to the target electrical device and the associated electrical devices, i.e., the first high-definition image and the second high-definition images, are respectively extracted from the high-definition image. The first high-definition image and the second high-definition images are then subjected to feature extraction, i.e., the first feature data of the target electrical device and the second feature data of the associated electrical devices are obtained.

[0027] At the same time, the present invention constructs two types of attribute classification models, namely the above-mentioned classification model and the classification large model. The classification model is a small model, which uses commonly used SVM, naive Bayes and other algorithms to classify the first feature data. The classification calculation of the small model is relatively simple and the classification speed is fast; the classification large model is constructed based on the general large model. The general large model is, for example, ChatGPT, BERT large model, KIMI, Tongyi Qianwen, etc. The classification large model can perform comprehensive analysis on multiple data, especially semantic analysis, and the classification accuracy is higher, but the amount of calculation will increase significantly. It should be noted that it is necessary to first use the sorted small sample data to lightly train the general large model, that is, to obtain the above-mentioned classification large model by fine-tuning the general large model.

[0028] First, use a small model, i.e., a classification model, to classify the first characteristic data of the target electrical equipment to obtain the first type attribute and the corresponding confidence probability. If the confidence probability is higher than the second probability threshold, it means that the characteristics of the target electrical equipment are very obvious, and the credibility of the classification result of the classification model is high enough. At this time, the first type attribute can be directly determined as the type attribute of the target electrical equipment. If the confidence probability is lower than the second probability threshold, it means that the characteristics of the target electrical equipment are not obvious enough, and the credibility of the classification result of the classification model is not high enough. At this time, it is necessary to use a large classification model to perform secondary classification processing on the first characteristic data of the target electrical equipment and the second characteristic data of each associated electrical equipment to obtain the second type attribute. Since the second type attribute is determined by the large classification model based on the first characteristic data of the target electrical equipment and the second characteristic data of each associated electrical equipment, it has a higher credibility than the above-mentioned first type attribute obtained by the classification model, so the second type attribute can be determined as the type attribute of the target electrical equipment.

[0029] Therefore, the present invention determines the confidence probability obtained by analyzing the small model, i.e., the classification model, and decides whether to further use the large model, i.e., the classification large model for secondary classification, thereby significantly improving the overall classification efficiency of the type attributes of the target electrical equipment.

[0030] It should be noted that the second probability threshold is preferably a dynamic value. Specifically: the number of electrical equipment around the target electrical equipment is first detected based on the first high-definition image. When the number of surrounding electrical equipment is larger, the area of ​​the target electrical equipment is larger, and the first feature data that can be extracted is smaller. The confidence probability at this time is higher, and the larger the second probability threshold is correspondingly set. On the contrary, when the number of surrounding electrical equipment is smaller, the second probability threshold is set to be smaller.

[0031] Optionally, the screening to obtain a plurality of detection sensors according to the type attribute and determining a confidence priority coefficient of each of the detection sensors includes: According to the type attribute, a preset comparison table is analyzed to screen out a corresponding number of the detection sensors; The detection history data of each detection sensor on the target electrical device is obtained, the detection accuracy is calculated according to the detection history data, and the confidence priority coefficient of each detection sensor is determined according to the detection accuracy.

[0032] In this embodiment, since different types of electrical equipment have different fault types, different fault types can be detected and identified by corresponding types of detection sensors. For example: Power transformer: Fault types include insulation aging, partial discharge, overheating, etc. Detection methods include diagnostic rules such as gas chromatography analysis (DGA), furfural content (HPLC), polarization current (PDC), and recovery voltage (RVM).

[0033] Power distribution networks and industrial systems: Fault types include electrical anomalies such as partial discharge, breakdown, etc. Monitoring technology involves current sensors and voltage sensors.

[0034] Inside electrical equipment: Fault types may include abnormal temperature rise caused by conductive circuit failure, overload, etc. It can be detected by infrared detection technology.

[0035] Electrical control equipment: Fault types may include abnormal signal display, the condition of buttons, contactors, thermal relays and fuses, etc. Detection can be performed through image recognition technology.

[0036] Therefore, a comparison table is pre-constructed, which includes a plurality of detection sensors corresponding to different types of electrical equipment. After the type attribute of the target electrical equipment is determined, a number of detection sensors can be determined by querying the comparison table.

[0037] At the same time, the detection history data of each detection sensor on the target electrical equipment is obtained. The detection history data can be recorded during the actual inspection process or during the test phase. The detection history data includes multiple successful records and failed records of fault detection of the target electrical equipment using the corresponding type of detection sensor. Based on this, the detection accuracy can be calculated, and then the confidence priority coefficient for each detection sensor is determined according to the detection accuracy.

[0038] Obviously, the higher the detection accuracy, the higher the corresponding confidence priority coefficient.

[0039] Optionally, determining the failure probability of the target electrical equipment according to the multiple groups of detection data and the corresponding confidence priority coefficients includes: Performing fault analysis on each group of detection data based on preset evaluation criteria to obtain corresponding fault sub-probability; Each fault sub-probability is multiplied by the corresponding confidence priority coefficient and then weighted fusion is performed to obtain the fault probability of the target electrical equipment.

[0040] In this embodiment, after obtaining the detection data of the target electrical equipment transmitted by each detection sensor, each group of detection data can be subjected to fault analysis according to the preset evaluation criteria, thereby obtaining the fault sub-probability based on the detection result of the detection sensor. The preset evaluation criteria include the determination criteria set for various fault types of the target electrical equipment, for example, if the temperature exceeds 70°C, it is determined that the fault probability is high, and if the temperature does not exceed 35°C, it is determined that the fault probability is low. Finally, each fault sub-probability is multiplied by the corresponding confidence priority coefficient and then weighted fusion calculation is performed to obtain the fault probability of the target electrical equipment.

[0041] Optionally, determining the target electrical equipment whose failure probability is higher than a first probability threshold as a potential failure equipment and outputting the information to relevant personnel includes: Determine the first probability threshold of the corresponding target electrical device according to the type attribute; The target electrical equipment whose failure probability is higher than a first probability threshold is determined as a potential failure equipment, and the information is output to relevant personnel.

[0042] In this embodiment, the first probability thresholds of different types of target electrical devices in the present invention are different, and the first probability thresholds can be preset. Specifically, a comprehensive evaluation is first performed on the importance of the target electrical device in the entire electrical network in the area and the self-adjustment / self-correction capability of the target electrical device, and a higher first probability threshold is set for those target electrical devices with low importance and / or high self-adjustment / self-correction capability, while a lower first probability threshold is set for those target electrical devices with high importance and / or low self-adjustment / self-correction capability. Such a setting can reduce unnecessary warnings.

[0043] See also Figure 2 As shown, an embodiment of the present invention further provides a rail inspection robot, the device includes a plurality of detection sensors, a processing device, and a storage device, the processing device calls and runs a computer program in the storage device to implement the following steps; The rail inspection robot takes a high-definition image of the target electrical equipment, extracts the type attribute of the target electrical equipment based on the high-definition image, selects and obtains a number of detection sensors according to the type attribute, and determines the confidence priority coefficient of each detection sensor; Controlling each of the detection sensors to detect the target electrical equipment to obtain multiple groups of detection data, and determining the failure probability of the target electrical equipment according to the multiple groups of detection data and the corresponding confidence priority coefficients; The target electrical equipment whose failure probability is higher than a first probability threshold is determined as a potential failure equipment, and the information is output to relevant personnel.

[0044] An embodiment of the present invention further provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method described in any of the above embodiments.

[0045] An embodiment of the present invention further provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in any of the above embodiments is executed.

[0046] An embodiment of the present invention further provides a computer program product, which includes a computer program stored in a computer storage medium, and when the computer program is executed by a processor of an electronic device, the method described in any of the above embodiments is implemented.

[0047] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0048] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0049] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0050] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for identifying potential fault hazards based on multiple sensors, characterized in that: The method comprises the following steps: The rail inspection robot takes a high-definition image of the target electrical equipment, extracts the type attribute of the target electrical equipment based on the high-definition image, selects and obtains a number of detection sensors according to the type attribute, and determines the confidence priority coefficient of each detection sensor; Controlling each of the detection sensors to detect the target electrical equipment to obtain multiple groups of detection data, and determining the failure probability of the target electrical equipment according to the multiple groups of detection data and the corresponding confidence priority coefficients; The target electrical equipment whose failure probability is higher than a first probability threshold is determined as a potential failure equipment, and the information is output to relevant personnel.

2. The method for identifying potential fault hazards based on multiple sensors according to claim 1, characterized in that: The rail inspection robot captures high-definition images of target electrical equipment, including: The rail inspection robot receives the inspection scheduling task sent by the server, and obtains the target electrical equipment that needs to be inspected, as well as the distribution location and inspection order of each target electrical equipment from the inspection scheduling task analysis; An inspection path is determined according to the distribution positions and the inspection order, and the inspection path includes various inspection points. When the inspection point is reached, a high-definition camera is controlled to capture a high-definition image of the target electrical equipment corresponding to the inspection point.

3. The method for identifying potential fault hazards based on multiple sensors according to claim 1, characterized in that: Extracting and obtaining the type attribute of the target electrical equipment based on the high-definition image includes: Extracting from the high-definition image a first high-definition image corresponding to the target electrical device and a second high-definition image corresponding to a plurality of associated electrical devices that are electrically connected to the target electrical device; Extracting first feature data of the target electrical device from the first high-definition image, and extracting second feature data of each of the associated electrical devices from the second high-definition image; Using a classification model to classify the first feature data, to obtain a first type attribute of the target electrical equipment and a corresponding confidence probability; If the confidence probability is higher than the second probability threshold, determining the first type attribute as the type attribute of the target electrical device; If the confidence probability is lower than the second probability threshold, a large classification model is used to perform secondary classification processing on the first feature data and each of the second feature data to obtain the second type attribute of the target electrical equipment, and the second type attribute is determined as the type attribute of the target electrical equipment.

4. The method for identifying potential fault hazards based on multiple sensors according to claim 3, characterized in that: A plurality of detection sensors are obtained by screening according to the type attribute, and a confidence priority coefficient of each of the detection sensors is determined, including: According to the type attribute, a preset comparison table is analyzed to screen out a corresponding number of the detection sensors; The detection history data of each detection sensor on the target electrical device is obtained, the detection accuracy is calculated according to the detection history data, and the confidence priority coefficient of each detection sensor is determined according to the detection accuracy.

5. The method for identifying potential fault hazards based on multiple sensors according to claim 4, characterized in that: Determining the failure probability of the target electrical equipment according to the multiple groups of detection data and the corresponding confidence priority coefficients includes: Performing fault analysis on each group of detection data based on preset evaluation criteria to obtain corresponding fault sub-probability; Each fault sub-probability is multiplied by the corresponding confidence priority coefficient and then weighted fusion is performed to obtain the fault probability of the target electrical equipment.

6. A multi-sensor based fault potential identification method according to any one of claims 1 to 5, characterized in that: Determining the target electrical equipment whose failure probability is higher than a first probability threshold as a potential failure equipment, and outputting the result to relevant personnel, includes: Determine the first probability threshold of the corresponding target electrical device according to the type attribute; The target electrical equipment whose failure probability is higher than a first probability threshold is determined as a potential failure equipment, and the information is output to relevant personnel.

7. A rail inspection robot, the device comprising a plurality of detection sensors, a processing device, and a storage device, characterized in that: The processing device calls and runs the computer program in the storage device to implement the following steps: The rail inspection robot takes a high-definition image of the target electrical equipment, extracts the type attribute of the target electrical equipment based on the high-definition image, selects and obtains a number of detection sensors according to the type attribute, and determines the confidence priority coefficient of each detection sensor; Controlling each of the detection sensors to detect the target electrical equipment to obtain multiple groups of detection data, and determining the failure probability of the target electrical equipment according to the multiple groups of detection data and the corresponding confidence priority coefficients; The target electrical equipment whose failure probability is higher than a first probability threshold is determined as a potential failure equipment, and the information is output to relevant personnel.

8. An electronic device comprising: A memory storing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-6.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is executed.

10. A computer program product, comprising a computer program stored in a computer storage medium, characterized in that: When the computer program is executed by a processor of an electronic device, the method according to any one of claims 1 to 6 is implemented.

Images