Self-protection method and device of overhead line inspection robot in harsh environment

Abstract

The application provides a self-protection method and device of a hanging rail inspection robot for a harsh environment, the method comprising: using a high-definition camera to shoot high-definition image data of a first target device in an inspection area, obtaining a running state feature of the first target device based on the high-definition image data; determining an abnormal condition of the first target device based on the running state feature, and determining a danger level according to the abnormal condition; when the danger level is higher than a target danger level, controlling the high-definition camera to enter a self-protection mode, and switching to use a radar detector to inspect the first target device. When the analysis of the abnormal condition of the target device will cause a damage risk to the high-definition camera of the hanging rail inspection robot, the high-definition camera is controlled to enter the self-protection mode, so that the damage of the equipment is avoided.

Description

Technical Field

[0001] This invention relates to the field of inspection robot technology, and more specifically, to a method and device for self-protection of a rail-mounted inspection robot in harsh environments. Background Technology

[0002] Inspection robots are divided into track-mounted and non-track-mounted types. Track-mounted robots are further divided into ground track-mounted and suspended track-mounted types. Due to limitations such as the placement of equipment in the inspection area and the reserved space in the passageway, suspended track-mounted inspection robots (rail-mounted intelligent inspection robots) run along suspended tracks, do not rely on the ground environment, can climb slopes autonomously, and are equipped with a liftable gimbal and high-definition camera, making them very suitable for inspection in narrow or complex areas.

[0003] However, existing rail-mounted inspection robots lack the ability to make self-protection decisions in harsh environments and cannot adjust their self-protection strategies according to the actual harsh conditions, resulting in an inability to balance the completion of inspection tasks and the integrity of inspection equipment. This invention aims to improve upon this technical problem. Summary of the Invention

[0004] In order to solve the technical problems existing in the background art, the present invention provides a method, device, electronic equipment, computer storage medium and computer program product for the self-protection of a rail-mounted inspection robot in harsh environments.

[0005] This invention provides a self-protection method for a rail-mounted inspection robot in harsh environments, the method comprising the following steps:

[0006] High-definition cameras are used to capture high-definition image data of the first target device in the inspection area, and the operating status characteristics of the first target device are extracted based on the high-definition image data.

[0007] Based on the operational status characteristics, the abnormal situation of the first target device is determined, and the danger level is determined based on the abnormal situation;

[0008] When the danger level is higher than the target danger level, the high-definition camera is controlled to enter the self-protection mode, and the radar detector is switched to inspect the first target device.

[0009] Optionally, the step of using a high-definition camera to capture high-definition image data of the first target device in the inspection area, and extracting the operating status characteristics of the first target device based on the high-definition image data, includes:

[0010] Use a high-definition camera to capture the first high-definition image data of the inspection area;

[0011] Based on this inspection task, the appearance feature data and inspection items of the first target device are determined, and the first target device is identified in the first high-definition image data based on the appearance feature data.

[0012] The first target device is captured by a high-definition camera as a second high-definition image, and the operating status characteristics of the first target device are extracted from the second high-definition image data based on the inspection items.

[0013] Optionally, determining the abnormal situation of the first target device based on the operating status characteristics, and determining the danger level based on the abnormal situation, includes:

[0014] The first anomaly analysis model is used to analyze the operating state features to obtain several abnormal situations, and to segment the operating state features to obtain operating state sub-features corresponding to each of the abnormal situations.

[0015] Each of the aforementioned abnormal situations and the corresponding operational state sub-features are input into the second anomaly analysis model, and the second anomaly analysis model outputs the predicted danger level;

[0016] The first anomaly analysis model is trained based on a first set of training data, each of which contains sub-features of the operating status of the first target device and corresponding anomaly labeling data. The second anomaly analysis model is trained based on a second set of training data, each of which contains sub-features of the operating status of the first target device, lens damage data, and corresponding hazard labeling data.

[0017] Optionally, when the acquisition distance of the operating status feature is higher than a preset distance, determining the abnormal situation of the first target device based on the operating status feature includes:

[0018] Based on the aforementioned operational status characteristics, the anomaly type and corresponding first anomaly degree of the first target device are determined.

[0019] A second target device is determined based on a preset association relationship and is associated with the anomaly type of the first target device. The anomaly coefficient of the first target device is predicted based on the operating status characteristics of the second target device. The second target device is closer to the rail-mounted inspection robot than the first target device.

[0020] The second anomaly degree is calculated using the anomaly degree coefficient and the first anomaly degree, and the anomaly situation is determined based on the anomaly type and the second anomaly degree.

[0021] Optionally, predicting the anomaly coefficient of the first target device based on the operating state characteristics of the second target device includes:

[0022] The operating status characteristics of the second target device and the preset correlation relationship are input into the anomaly coefficient prediction model to obtain the predicted anomaly coefficient.

[0023] The anomaly coefficient prediction model is obtained by fine-tuning a pre-trained large model.

[0024] Optionally, controlling the high-definition camera to enter self-protection mode includes:

[0025] The system controls the shutdown of the high-definition camera and uses a protective cover to protect it, as well as switches to use a radar detector to inspect the first target device.

[0026] The present invention also provides a self-protection device for a rail-mounted inspection robot in harsh environments, the device comprising a status extraction module, a hazard level analysis module, and a protection processing module;

[0027] The status extraction module is used to capture high-definition image data of the first target device in the inspection area using a high-definition camera, and extract the operating status characteristics of the first target device based on the high-definition image data.

[0028] The hazard level analysis module is used to determine the abnormal situation of the first target equipment based on the operating status characteristics, and to determine the hazard level based on the abnormal situation.

[0029] The protection processing module is used to control the high-definition camera to enter self-protection mode when the danger level is higher than the target danger level, and to switch to using a radar detector to inspect the first target device.

[0030] The present invention also provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute the method as described in any of the preceding claims.

[0031] The present invention also provides a computer storage medium storing a computer program that, when executed by a processor, performs the method described in any of the preceding claims.

[0032] The present invention also provides a computer program product comprising a computer program stored in a computer storage medium, wherein the computer program, when executed by a processor of an electronic device, implements the method described in any of the preceding claims.

[0033] This invention performs image inspection of the first target device under normal circumstances. When an anomaly is detected in the first target device that may damage the high-definition camera of the rail-mounted inspection robot, the high-definition camera is controlled to perform self-protection, thereby avoiding damage to the high-definition camera by fast-moving floating objects, acidic gases, etc. in harsh environments. Moreover, a radar detector with better self-protection capabilities is switched to inspect the first target device, ensuring that the inspection task can be completed smoothly and improving the inspection quality. Attached Figure Description

[0034] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is a schematic diagram of a self-protection method for a rail-mounted inspection robot in harsh environments, as disclosed in an embodiment of the present invention.

[0036] Figure 2 This is a schematic diagram of a self-protection device for a rail-mounted inspection robot in harsh environments, as disclosed in an embodiment of the present invention. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0038] Please see Figure 1 This invention discloses a self-protection method for a rail-mounted inspection robot in harsh environments, the method comprising the following steps:

[0039] High-definition cameras are used to capture high-definition image data of the first target device in the inspection area, and the operating status characteristics of the first target device are extracted based on the high-definition image data.

[0040] Based on the operational status characteristics, the abnormal situation of the first target device is determined, and the danger level is determined based on the abnormal situation;

[0041] When the danger level is higher than the target danger level, the high-definition camera is controlled to enter the self-protection mode, and the radar detector is switched to inspect the first target device.

[0042] The rail-mounted inspection robot of this invention is equipped with at least two inspection devices: a high-definition camera and a radar detector. The high-definition camera can provide high-resolution images, enabling more accurate inspection of the first target device. The radar detector's detection resolution is lower than that of the high-definition camera. However, the radar detector is more adaptable to harsh environments, while the high-definition camera is easily affected by floating debris and acidic gases in harsh environments. For example, fast-moving floating debris in harsh environments can scratch the lens of the high-definition camera, and acidic gases can damage the coating on the lens. To address these technical problems, this invention uses a high-definition camera to capture high-definition image data of the first target device in the inspection area. Based on the captured high-definition image data, the operating status characteristics of the first target device are extracted. Then, based on these operating status characteristics, abnormal conditions of the first target device are determined, and the danger level of the first target device to the high-definition camera of the rail-mounted inspection robot is determined according to the existing abnormal conditions. When the danger level is higher than the target danger level, it indicates that the high-definition camera of the rail-mounted inspection robot is susceptible to damage from the abnormal condition. In this case, the high-definition camera is immediately controlled to enter self-protection mode, and the radar detector is simultaneously switched to inspect the first target device.

[0043] Therefore, under normal circumstances, the present invention performs image inspection on the first target device. When an abnormality is found in the first target device and the abnormality poses a risk of damage to the high-definition camera of the rail-mounted inspection robot, the high-definition camera is controlled to perform self-protection, thereby avoiding damage to the high-definition camera by fast-moving floating objects, acidic gases, etc. in harsh environments. Moreover, a radar detector with better self-protection capabilities is switched to inspect the first target device, ensuring that the inspection task can be completed smoothly and improving the inspection quality.

[0044] Optionally, the step of using a high-definition camera to capture high-definition image data of the first target device in the inspection area, and extracting the operating status characteristics of the first target device based on the high-definition image data, includes:

[0045] Use a high-definition camera to capture the first high-definition image data of the inspection area;

[0046] Based on this inspection task, the appearance feature data and inspection items of the first target device are determined, and the first target device is identified in the first high-definition image data based on the appearance feature data.

[0047] The first target device is captured by a high-definition camera as a second high-definition image, and the operating status characteristics of the first target device are extracted from the second high-definition image data based on the inspection items.

[0048] In this embodiment, the rail-mounted inspection robot receives an inspection task from the server. The task includes the appearance feature data of the first target device to be inspected and specific inspection items. The robot can then identify the first target device from the first high-definition image data captured by the high-definition camera within the inspection area based on the appearance feature data. As it approaches the first target device further, it captures a second high-definition image of the device. Based on the analyzed inspection items, the robot extracts the operating status characteristics of the first target device from the second high-definition image data. These operating status characteristics include, for example, gas leakage characteristics, exhaust emission characteristics, and operating speed.

[0049] Optionally, determining the abnormal situation of the first target device based on the operating status characteristics, and determining the danger level based on the abnormal situation, includes:

[0050] The first anomaly analysis model is used to analyze the operating state features to obtain several abnormal situations, and to segment the operating state features to obtain operating state sub-features corresponding to each of the abnormal situations.

[0051] Each of the aforementioned abnormal situations and the corresponding operational state sub-features are input into the second anomaly analysis model, and the second anomaly analysis model outputs the predicted danger level;

[0052] The first anomaly analysis model is trained based on a first set of training data, each of which contains sub-features of the operating status of the first target device and corresponding anomaly labeling data. The second anomaly analysis model is trained based on a second set of training data, each of which contains sub-features of the operating status of the first target device, lens damage data, and corresponding hazard labeling data.

[0053] In this embodiment, the present invention constructs two models: a first anomaly analysis model and a second anomaly analysis model. The first anomaly analysis model is used to perform anomaly analysis on the extracted operational status characteristics of the first target device to identify several anomalies, such as gas leakage or abnormal exhaust gas color. The second anomaly analysis model is used to analyze the danger level posed by the anomaly to the lens of the high-definition camera based on the anomaly and its corresponding operational status sub-features. Different danger levels represent, for example, whether the amount or concentration of leaked acidic gas will damage the lens of the high-definition camera, and the probability of such damage.

[0054] Among them, the running state sub-features are derived from the running state features based on the corresponding abnormal situations.

[0055] Optionally, when the acquisition distance of the operating status feature is higher than a preset distance, determining the abnormal situation of the first target device based on the operating status feature includes:

[0056] Based on the aforementioned operational status characteristics, the anomaly type and corresponding first anomaly degree of the first target device are determined.

[0057] A second target device is determined based on a preset association relationship and is associated with the anomaly type of the first target device. The anomaly coefficient of the first target device is predicted based on the operating status characteristics of the second target device. The second target device is closer to the rail-mounted inspection robot than the first target device.

[0058] The second anomaly degree is calculated using the anomaly degree coefficient and the first anomaly degree, and the anomaly situation is determined based on the anomaly type and the second anomaly degree.

[0059] In this embodiment, in order to further reduce the damage to the high-definition camera of the rail-mounted inspection robot caused by abnormal target equipment, the rail-mounted inspection robot can acquire the operating status characteristics of the target equipment in advance. However, due to factors such as shooting angle and obstruction between equipment, the acquired operating status characteristics may be incomplete or lack confidence.

[0060] To address this technical problem, this invention first determines the anomaly type and corresponding first anomaly degree of the first target device based on its extracted operational status characteristics. Next, it acquires the operational status characteristics of a second target device closer to the rail-mounted inspection robot than the first target device. Based on the operational status characteristics of the second target device, it predicts the anomaly degree coefficient of the first target device. This anomaly degree coefficient represents the impact on the first target device indirectly analyzed under the anomaly conditions of the second target device. For example, a certain anomaly in the second target device may also cause or exacerbate a gas leak in the first target device. The influence relationship between these anomalies can be predicted in advance, and corresponding preset correlations can be established. Finally, a second anomaly degree is calculated using the anomaly degree coefficient and the first anomaly degree; for example, the second anomaly degree = the first anomaly degree multiplied by the anomaly degree coefficient. The anomaly condition of the target device is then determined based on the anomaly type and the second anomaly degree.

[0061] Optionally, predicting the anomaly coefficient of the first target device based on the operating state characteristics of the second target device includes:

[0062] The operating status characteristics of the second target device and the preset correlation relationship are input into the anomaly coefficient prediction model to obtain the predicted anomaly coefficient.

[0063] The anomaly coefficient prediction model is obtained by fine-tuning a pre-trained large model.

[0064] In this embodiment, the present invention obtains an anomaly coefficient prediction model by fine-tuning a pre-trained large model. Then, using this anomaly coefficient prediction model, in-depth analysis is performed on the aforementioned operating state characteristics of the second target device and preset correlation relationships to derive the corresponding anomaly coefficient. The preset correlation relationships can be unstructured data, such as a description of the mutual influence between the second target device and the first target device on certain anomaly types.

[0065] Pre-trained large models, such as BERT and GPT series models, are constructed based on the Transformer architecture. These large models are pre-trained on large-scale text datasets to learn the basic rules of language and rich semantic information. Then, they are fine-tuned using constructed training data samples to obtain the anomaly coefficient prediction model of this invention.

[0066] Each training data point includes the operational status characteristics of the second target device, the operational status characteristics of the first target device, and the corresponding impact level label.

[0067] Optionally, controlling the high-definition camera to enter self-protection mode includes:

[0068] The system controls the shutdown of the high-definition camera and uses a protective cover to protect it, as well as switches to use a radar detector to inspect the first target device.

[0069] In this embodiment, the self-protection of the high-definition camera adopts a shutdown and protective cover approach. The protective cover can be a shell protecting the camera's lens or even its body. In self-protection mode, the protective cover activates to cover the camera's lens or even its body, isolating it from harsh environments and thus protecting the high-definition camera. In normal inspection mode, the protective cover is in a retracted state, which does not affect the use of the high-definition camera to perform image recognition-based inspection of the first target device in the inspection area. Of course, when the protective cover is in the retracted state, the radar detector is also in a shutdown or low-power mode.

[0070] See Figure 2As shown, this embodiment of the invention also provides a self-protection device for a rail-mounted inspection robot in harsh environments. The device includes a status extraction module, a hazard level analysis module, and a protection processing module; characterized in that:

[0071] The status extraction module is used to capture high-definition image data of the first target device in the inspection area using a high-definition camera, and extract the operating status characteristics of the first target device based on the high-definition image data.

[0072] The hazard level analysis module is used to determine the abnormal situation of the first target equipment based on the operating status characteristics, and to determine the hazard level based on the abnormal situation.

[0073] The protection processing module is used to control the high-definition camera to enter self-protection mode when the danger level is higher than the target danger level, and to switch to using a radar detector to inspect the first target device.

[0074] This invention also provides an electronic device, including: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute the method as described in any of the preceding embodiments.

[0075] This invention also provides a computer storage medium storing a computer program, which is executed by a processor to perform the method described in any of the preceding embodiments.

[0076] This invention also provides a computer program product comprising a computer program stored in a computer storage medium, wherein the computer program, when executed by a processor of an electronic device, implements the method described in any of the preceding embodiments.

[0077] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0078] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0079] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0080] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for self-protection of a hanging rail inspection robot against harsh environments, characterized in that: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps:

2. The self-protection method of the hanging rail inspection robot for harsh environment according to claim 1, characterized in that: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the following steps: The method comprises the 3. The self-protection method of the hanging rail inspection robot for harsh environment according to claim 1, characterized in that: The anomaly coefficient of the first target device is predicted based on the operating state characteristics of the second target device, including: The operating status characteristics of the second target device and the preset correlation relationship are input into the anomaly coefficient prediction model to obtain the predicted anomaly coefficient. The anomaly coefficient prediction model is obtained by fine-tuning a pre-trained large model.

4. The self-protection method of the hanging rail inspection robot in a harsh environment according to claim 3, characterized in that: Controlling the high-definition camera to enter self-protection mode includes: The system controls the shutdown of the high-definition camera and uses a protective cover to protect it, as well as switches to use a radar detector to inspect the first target device.

5. A self-protection device for a rail-mounted inspection robot in harsh environments, the device being used to implement the method described in any one of claims 1-4, comprising a state extraction module, a hazard level analysis module, and a protection processing module; characterized in that: The status extraction module is used to capture high-definition image data of the first target device in the inspection area using a high-definition camera, and extract the operating status characteristics of the first target device based on the high-definition image data. The hazard level analysis module is used to determine the abnormal situation of the first target equipment based on the operating status characteristics, and to determine the hazard level based on the abnormal situation. The protection processing module is used to control the high-definition camera to enter self-protection mode when the danger level is higher than the target danger level, and to switch to using a radar detector to inspect the first target device.

6. An electronic device, comprising: Memory containing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to perform the method as described in any one of claims 1-4.

7. A computer storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to perform the method as described in any one of claims 1-4.

8. A computer program product, the computer program product comprising a computer program stored in a computer storage medium, characterized in that: When the computer program is executed by the processor of the electronic device, it implements the method as described in any one of claims 1-4.

Images