Rail transit vehicle intelligent maintenance auxiliary system based on artificial intelligence

Abstract

The invention discloses a rail transit vehicle intelligent maintenance auxiliary system based on artificial intelligence. The system comprises a maintenance mode acquisition module, a first acquisition module, a second acquisition module, a data processing module and an information sending module. The maintenance mode acquisition module is used for acquiring maintenance modes, and the maintenance modes comprise on-orbit maintenance and derail maintenance; the first acquisition module is used for acquiring on-orbit maintenance related information during on-orbit maintenance; the second acquisition module is used for acquiring derailment maintenance related information during derailment maintenance; the data processing module is used for processing the on-orbit maintenance related information and the derailment maintenance related information to generate on-orbit maintenance auxiliary information and derailment maintenance auxiliary information; and the information sending module is used for sending the on-orbit maintenance auxiliary information and the derail maintenance auxiliary information to a preset receiving terminal. The rail transit vehicle can be better assisted in maintenance operation.

Description

Technical Field

[0001] The present invention relates to the field of auxiliary systems, and particularly to an intelligent maintenance auxiliary system for rail transit vehicles based on artificial intelligence. Background Art

[0002] With the acceleration of the urbanization process, rail transit plays an increasingly crucial role in people's daily travel, and the safety and reliability of its operation have attracted much attention.

[0003] On the one hand, the rail transit network is constantly expanding, the lines are becoming more complex, and the operation frequency of vehicles has increased sharply. This has accelerated the wear and aging of vehicle components, and the probability of faults has also risen accordingly. The traditional maintenance mode mainly relies on manual experience. Maintenance personnel rely on visual observation and simple tool detection to judge faults and maintenance requirements. This method is not only inefficient, but also difficult to accurately locate the root cause of problems in the face of complex faults, and it is easy to miss potential hazards, resulting in incomplete maintenance, which in turn affects the reuse of vehicles and operation safety.

[0004] On the other hand, the maintenance scenarios of rail transit vehicles are diverse, including on-track maintenance and derailment maintenance. During on-track maintenance, it is necessary to quickly and safely complete the operation within a limited time window without affecting the normal operation of the line, which has extremely high requirements for the setting of protection measures and the deployment of maintenance personnel; derailment maintenance involves high-risk operations such as large equipment hoisting. Once there are problems such as steel cable breakage, hoisting imbalance or personnel safety accidents, it will not only cause serious economic losses, but also delay the restoration of line operation, bringing great inconvenience to citizens' travel.

[0005] Therefore, a rail transit vehicle maintenance auxiliary system is needed for maintenance assistance. For this reason, an intelligent maintenance auxiliary system for rail transit vehicles based on artificial intelligence is proposed. Summary of the Invention

[0006] The technical problem to be solved by the present invention is: how to solve the problems of low maintenance efficiency and certain potential safety hazards in the existing maintenance auxiliary system, and provide an intelligent maintenance auxiliary system for rail transit vehicles based on artificial intelligence.

[0007] The present invention solves the above technical problems through the following technical solutions. The present invention includes a maintenance method acquisition module, a first acquisition module, a second acquisition module, a data processing module and an information sending module;

[0008] The maintenance method acquisition module is used to acquire maintenance methods, and the maintenance methods include on-track maintenance and derailment maintenance;

[0009] The first acquisition module is used to acquire relevant information for on-track maintenance during on-track maintenance;

[0010] The second acquisition module is used to acquire information related to derailment maintenance during derailment maintenance;

[0011] The data processing module is used to process the information related to on-rail maintenance and the information related to derailment maintenance to generate on-rail maintenance auxiliary information and derailment maintenance auxiliary information;

[0012] The information sending module is used to send the on-rail maintenance auxiliary information and the derailment maintenance auxiliary information to a preset receiving terminal.

[0013] Furthermore, the specific process of the first acquisition module for acquiring information related to on-rail maintenance is as follows:

[0014] During on-rail maintenance, maintenance personnel need to set up a protection sign, on which a position sensing device and an angle acquisition device are set to acquire the position and placement angle of the protection sign;

[0015] At the same time, maintenance personnel need to wear a position sensing device to acquire the real-time position of the maintenance personnel;

[0016] At the same time, acquire the maintenance reason information and the real-time number of maintenance personnel;

[0017] That is, the information related to track maintenance includes the position of the protection sign, the placement angle, the real-time position of the maintenance personnel, the maintenance reason information and the real-time number of maintenance personnel;

[0018] The data processing module processes the position of the protection sign, the placement angle, the real-time position of the maintenance personnel, the maintenance reason information and the real-time number of maintenance personnel to generate on-rail maintenance auxiliary information;

[0019] The on-rail maintenance auxiliary information includes protection sign prompt information and personnel prompt information.

[0020] Furthermore, the process of obtaining the placement angle is as follows:

[0021] Two inclination sensors are set at the side position of the protection sign to acquire the inclination information of the protection sign in real time, and mark it as the first inclination and the second inclination;

[0022] A collection frequency is preset, and multiple first inclinations and multiple second inclinations are collected according to the preset collection frequency to obtain multiple first inclinations and multiple second inclinations, and the multiple first inclinations and multiple second inclinations form the placement angle information.

[0023] Furthermore, the process of obtaining the protection sign prompt information is as follows:

[0024] Extract the collected placement angle, and extract multiple first inclinations and multiple second inclinations from the placement angle;

[0025] Process multiple first inclination angles. First, detect whether there is a first inclination angle among the multiple first inclination angles that differs from the preset standard inclination angle by more than a first preset range (for example, there is a first inclination angle that differs from the preset standard inclination angle by more than 20%). When there is a first inclination angle that differs from the preset standard inclination angle by more than the preset range, a protective identification prompt message is generated. Calculate the average value of the multiple first inclination angles. When the average value of the multiple first inclination angles differs from the preset standard inclination angle by more than a second preset range, a protective identification prompt message is also generated. At this time, the specific content of the protective identification prompt message is that there is a possibility of overturning of the protective identification and the angle needs to be adjusted;

[0026] Perform the same processing on multiple second inclination angles as on the multiple first inclination angles to determine whether to generate a protective identification prompt message. At this time, the specific content of the protective identification prompt message is that there is a possibility of overturning of the protective identification and the angle needs to be adjusted;

[0027] Extract the position of the protective identification, and then collect the position of the rail transit vehicle that needs to be repaired. Collect its center point and mark it as the reference point;

[0028] Mark the position of the protective identification as A1 and the reference point as A2. Real-time monitor the distance information between the position A1 of the protective identification and the reference point A2 to obtain the evaluation distance. When the evaluation distance information is less than the preset standard placement distance, a protective identification prompt message is generated. At this time, the specific content of the protective identification prompt message is that the placement position of the protective identification is abnormal and the position needs to be readjusted to ensure the warning effect;

[0029] Collect the evaluation distance at a preset frequency. When the evaluation distance collected at the preset frequency is constantly changing and the change amplitude is greater than the preset value, a protective identification prompt message is generated. At this time, the specific content of the protective identification prompt message is that the protective identification has abnormal displacement.

[0030] Furthermore, the specific acquisition process of the personnel prompt message is as follows:

[0031] Extract the real-time position of the maintenance personnel, the maintenance reason information, and the real-time number of maintenance personnel from the rail maintenance related information;

[0032] Import the maintenance reason information into the preset database. Retrieve the standard number of maintenance personnel from the preset database. When the difference between the real-time number of maintenance personnel and the standard number of maintenance personnel is less than 0 or greater than the preset value a, a personnel prompt message is generated;

[0033] Then collect the distance information between the real-time position of the maintenance personnel and the reference point A2 to obtain the personnel distance information. When the personnel distance information is greater than the preset value for more than the preset duration, a personnel prompt message is generated;

[0034] Collect the distances between all personnel performing maintenance tasks. When the distance between any two personnel performing maintenance tasks is greater than a preset value, a personnel prompt message is generated.

[0035] Collect the maintenance task information assigned to the maintenance personnel, and extract the task execution time point from the maintenance task information. When there is a preset duration remaining until the task execution time point, extract the distance information between all maintenance personnel performing maintenance tasks. When there is distance information greater than the preset value, a personnel prompt message is generated.

[0036] Furthermore, when the second collection module performs derailment maintenance, the specific process of collecting derailment maintenance-related information is as follows:

[0037] Before hoisting a derailed rail transit vehicle, detect the hoisting steel cable to obtain hoisting steel cable information.

[0038] During the hoisting process, collect real-time hoisting images.

[0039] The hoisting steel cable information and the real-time hoisting images constitute derailment maintenance-related information.

[0040] Furthermore, the process of obtaining the hoisting steel cable information is as follows:

[0041] Use the magnetic particle inspection method to detect the steel cable, that is, magnetize the steel cable, then spray magnetic powder on its surface. After spraying, collect the number of areas where the adsorbed magnetic powder area is greater than the preset value and the number of areas where the length is greater than the preset length. When the area of a region where the adsorbed magnetic powder area is greater than the preset value and the length is greater than the preset length, only record one. Calculate the sum of the number of areas where the adsorbed magnetic powder area is greater than the preset value and the number of areas where the length is greater than the preset length to obtain the abnormal regions and the number of abnormal regions, that is, the first abnormal information.

[0042] At the same time, also use the ultrasonic inspection method to detect the steel cable to obtain the steel cable abnormal regions and the number of steel cable abnormal regions, that is, the second abnormal information.

[0043] The process of obtaining the real-time hoisting images is as follows: On the hoisting path, a safety area is set, and image acquisition equipment is set in the safety area to collect the image information in the safety area during the process of hoisting the rail transit vehicle in real time, that is, the real-time hoisting images are obtained.

[0044] Furthermore, the derailment maintenance auxiliary information includes hoisting steel cable auxiliary information and hoisting process auxiliary information.

[0045] The process of obtaining the hoisting steel cable auxiliary information is as follows:

[0046] Extract the obtained hoisting cable information, and extract the first abnormal information and the second abnormal information from it;

[0047] When the number of abnormal areas of the first abnormal information or the number of abnormal areas of the second abnormal information is greater than the preset value m1, hoisting cable auxiliary information is generated;

[0048] When the number of abnormal areas of the first abnormal information and the number of abnormal areas of the second abnormal information are both less than the preset value m2 but greater than 0, extract the abnormal areas of the first abnormal information and the abnormal areas of the second abnormal information. When the abnormal areas of the first abnormal information and the abnormal areas of the second abnormal information are different areas, hoisting cable auxiliary information is generated. At this time, the content of the hoisting cable auxiliary information is that there is an abnormality in the hoisting cable.

[0049] The acquisition process of the hoisting process auxiliary information is as follows:

[0050] Extract the obtained real-time hoisting image, and import the human body recognition model into the real-time hoisting image. When a human body model is recognized in the safe area, hoisting process auxiliary information is generated. At this time, the hoisting process auxiliary information is that there is an abnormal person in the safe area and needs to be driven away;

[0051] Then process the real-time hoisting image. During the hoisting process, by analyzing the real-time image, the hoisting speed and the release speed are obtained;

[0052] When either the hoisting speed or the release speed is greater than the preset value, hoisting process auxiliary information is generated. At this time, the content of the hoisting process auxiliary information is that the hoisting speed / release speed is too fast and needs to be adjusted.

[0053] The present invention has the following advantages compared with the prior art: This rail transit vehicle intelligent maintenance assistance system based on artificial intelligence has a stronger targeted maintenance method. It can clearly distinguish between on-rail maintenance and derailment maintenance methods, and collect relevant information for different maintenance methods through the first acquisition module and the second acquisition module respectively, making the maintenance assistance more targeted and meeting the needs of different maintenance scenarios.

[0054] The safety guarantee for on-rail maintenance is higher. Precise monitoring of protective signs is carried out. By setting position sensing devices and angle acquisition devices on the protective signs, the position and placement angle of the protective signs are collected in real time, and situations such as abnormal angles, abnormal positions, and abnormal displacements of the protective signs can be detected in time, generating corresponding prompt information to ensure the warning effect of the protective signs and providing safety guarantee for maintenance operations.

[0055] The management of maintenance personnel is more efficient. Maintenance personnel wear position sensing devices, and the system can collect their real-time positions. Combining the maintenance reason information with the real-time number of maintenance personnel, multi-dimensional management of maintenance personnel can be carried out. For example, according to the standard number of maintenance personnel in the preset database, abnormal situations in the number of personnel can be detected in a timely manner; the distance between maintenance personnel and the reference point and the distance between personnel can also be monitored to avoid danger to personnel or affecting the maintenance efficiency. At the same time, when approaching the task execution time point, personnel are reminded to take their positions to ensure the smooth progress of the maintenance task.

[0056] The risk of derailment maintenance is controllable. In derailment maintenance, magnetic particle testing and ultrasonic testing are used to detect the lifting steel cable, and information such as the abnormal area and the number of abnormal areas of the steel cable can be comprehensively obtained. By analyzing this information, potential safety hazards of the steel cable can be detected in a timely manner. When the number of abnormal areas reaches a certain level or the abnormal areas of different testing methods are different, auxiliary information of the lifting steel cable is generated to indicate that there is an abnormality in the lifting steel cable, effectively reducing the risk during the lifting process. An image acquisition device is set in the safe area of the lifting path to collect image information during the process of lifting the rail transit vehicle in real time. Using a human recognition model, abnormal personnel in the safe area can be detected in a timely manner and auxiliary information is generated to remind them to be driven away; by analyzing the real-time lifting image, the lifting speed and release speed are obtained. When the speed exceeds the preset value, a prompt message is generated to remind to adjust the speed, ensuring the safe and stable progress of the lifting process and making this system more worthy of promotion and use. Brief Description of the Drawings

[0057] Figure 1 It is the system block diagram of the present invention. Detailed Embodiment

[0058] The embodiments of the present invention will be described in detail below. These embodiments are implemented on the premise of the technical solution of the present invention, and detailed implementation manners and specific operation processes are given. However, the protection scope of the present invention is not limited to the following embodiments.

[0059] As Figure 1 shown, this embodiment provides a technical solution: an intelligent maintenance assistance system for rail transit vehicles based on artificial intelligence, including a maintenance method acquisition module, a first acquisition module, a second acquisition module, a data processing module, and an information sending module;

[0060] The maintenance method acquisition module is used to collect maintenance methods, and the maintenance methods include on-track maintenance and derailment maintenance;

[0061] The first acquisition module is used to collect information related to on-track maintenance during on-track maintenance;

[0062] The second acquisition module is used to collect information related to derailment maintenance during derailment maintenance;

[0063] The data processing module is used to process the information related to on-orbit maintenance and the information related to derailment maintenance to generate the auxiliary information for on-orbit maintenance and the auxiliary information for derailment maintenance;

[0064] The information sending module is used to send the auxiliary information for on-orbit maintenance and the auxiliary information for derailment maintenance to a preset receiving terminal.

[0065] The first acquisition module is used to collect the information related to on-orbit maintenance during on-orbit maintenance. The specific process is as follows:

[0066] During on-orbit maintenance, the maintenance personnel need to set up a protection sign, on which a position sensing device and an angle acquisition device are set up to collect the position and placement angle of the protection sign;

[0067] At the same time, the maintenance personnel need to wear a position sensing device to collect the real-time position of the maintenance personnel;

[0068] At the same time, collect the maintenance reason information and the real-time number of maintenance personnel;

[0069] That is, the information related to track maintenance includes the position of the protection sign, the placement angle, the real-time position of the maintenance personnel, the maintenance reason information and the real-time number of maintenance personnel;

[0070] The data processing module processes the position of the protection sign, the placement angle, the real-time position of the maintenance personnel, the maintenance reason information and the real-time number of maintenance personnel to generate the auxiliary information for on-orbit maintenance;

[0071] The auxiliary information for on-orbit maintenance includes the protection sign prompt information and the personnel prompt information.

[0072] The process of obtaining the placement angle is as follows:

[0073] Two inclination sensors are set at the side position of the protection sign to collect the inclination information of the protection sign in real time, and mark it as the first inclination and the second inclination;

[0074] A collection frequency is preset, and multiple first inclinations and multiple second inclinations are collected according to the preset collection frequency to obtain multiple first inclinations and multiple second inclinations. The multiple first inclinations and multiple second inclinations form the placement angle information;

[0075] The above collection process covers various aspects such as the position of the protection sign, the placement angle, the real-time position of the maintenance personnel, the maintenance reason information, and the real-time number of maintenance personnel. These information comprehensively reflect the situation at the on-orbit maintenance site, from the safety signs in the maintenance environment to the actual situation of the maintenance personnel, providing a rich and comprehensive data basis for subsequent data processing and auxiliary information generation, and helping to accurately control and analyze the entire maintenance process.

[0076] According to the characteristics and requirements of the on-orbit maintenance scenario, key information closely related to maintenance safety and efficiency was selected for collection. For example, the position and angle of the protective signs are directly related to the warning effect and safety at the maintenance site, while the position and number of maintenance personnel are closely related to the execution and coordination of maintenance operations. This targeted collection can better meet the actual needs of on-orbit maintenance and enhance the practicality of the maintenance assistance system.

[0077] Multi-sensor real-time monitoring: By setting two tilt sensors on the side of the protective sign, the first tilt angle and the second tilt angle are collected in real time. This multi-sensor setting method can obtain the tilt angle information of the protective sign from different angles, avoiding the limitations that may exist in a single sensor, improving the accuracy and reliability of the collected data, and being able to more comprehensively and accurately reflect the placement angle state of the protective sign.

[0078] Preset the collection frequency and collect the tilt angle information multiple times according to this frequency to obtain multiple first tilt angles and second tilt angles. Multiple collections can effectively reduce the influence of accidental factors on the collection results. Through comprehensive analysis of a large amount of data, the changing trend of the placement angle of the protective sign can be grasped more accurately, providing more reliable data support for subsequent judgment of whether there are abnormalities in the protective sign, and further enhancing the accuracy and stability of the system's monitoring of the protective sign state.

[0079] The auxiliary information generated based on the accurately collected data can help maintenance personnel timely understand potential risks and problems at the maintenance site, such as abnormal situations of protective signs and the rationality of personnel arrangements, etc., so as to make more scientific and reasonable decisions, ensure the safety and efficiency of maintenance work, improve the intelligent level and management efficiency of on-orbit maintenance of the entire rail transit vehicle, and then better assist the rail transit vehicle.

[0080] The process of obtaining the protective sign prompt information is as follows:

[0081] Extract the collected placement angles, and extract multiple first tilt angles and multiple second tilt angles from the placement angles;

[0082] Process the multiple first tilt angles. First, detect whether there is a first tilt angle among the multiple first tilt angles that differs from the preset standard tilt angle by more than the first preset amplitude (such as a first tilt angle that differs from the preset standard tilt angle by more than 20%). When there is a first tilt angle that differs from the preset standard tilt angle by more than the preset amplitude, generate the protective sign prompt information, calculate the average value of the multiple first tilt angles, and when the average value of the multiple first tilt angles differs from the preset standard tilt angle by more than the second preset amplitude, also generate the protective sign prompt information. At this time, the specific content of the protective sign prompt information is that the protective sign may tip over and needs to be adjusted in angle;

[0083] Perform the same processing on multiple second inclination angles as on multiple first inclination angles to determine whether to generate a protective sign prompt message. At this time, the specific content of the protective sign prompt message is that there is a possibility of the protective sign tipping over and the angle needs to be adjusted;

[0084] Extract the position of the protective sign, then collect the position of the rail transit vehicle that needs to be repaired, and mark the center point of it as the reference point;

[0085] Mark the position of the protective sign as A1 and the reference point as A2. Monitor the distance information between the position A1 of the protective sign and the reference point A2 in real time to obtain the evaluation distance. When the evaluation distance information is less than the preset standard placement distance, a protective sign prompt message is generated. At this time, the specific content of the protective sign prompt message is that the placement position of the protective sign is abnormal and needs to be readjusted to ensure the warning effect;

[0086] Collect the evaluation distance at a preset frequency. When the evaluation distance collected at the preset frequency changes continuously and the change range is greater than the preset value, a protective sign prompt message is generated. At this time, the specific content of the protective sign prompt message is that the protective sign has abnormal displacement;

[0087] The first preset amplitude: Suppose it is set to 20%. That is, when the absolute value of the difference between a certain first inclination angle and the standard inclination angle of 5° exceeds 5°×20% = 1°, the mechanism for generating the protective sign prompt message will be triggered, prompting the maintenance personnel that there may be a sudden change in the inclination angle of the protective sign in a single direction due to reasons such as external force collision and local settlement of soft foundation, and attention and adjustment are required.

[0088] The second preset amplitude: For example, it is set to 10%. When the average value of the calculated multiple first inclination angles differs from the standard inclination angle of 5° by more than 5°×10% = 0.5°, it means that the protective sign may have a slow tilting trend as a whole due to factors such as wind blowing and cumulative influence of small vibrations, and the angle also needs to be adjusted in time to ensure the warning effect.

[0089] The standard placement distance: Based on the type and size of the maintenance vehicle and the required space range for maintenance operations, and considering the visible range and warning distance of the protective sign itself, the standard placement distance is set to 10 meters from the center point of the maintenance vehicle. This can not only ensure that the protective sign will not hinder the entry and movement of maintenance personnel and tools due to being too close to the vehicle, but also prevent passing vehicles from ignoring the warning and being unable to make avoidance preparations in advance due to being too far away.

[0090] Preset Frequency: For the acquisition frequency of the evaluation distance, considering factors such as the duration of maintenance operations and the frequency of factors that may affect the position of the warning signs, it can be set to collect data once every 5 minutes. If during a 30-minute maintenance operation, the system continuously monitors at this frequency and once it is found that the evaluation distances collected consecutively gradually decrease, such as from the initial 10 meters to 8 meters and then 7 meters, it will promptly prompt that there is an abnormal displacement of the warning sign, which may be caused by being hit by passing large equipment or being pushed by slight vibrations of the track. The maintenance personnel need to fix it immediately;

[0091] Through the above process, ensure that the angle of the warning sign is compliant and guarantee the warning effectiveness:

[0092] By processing the multiple first inclinations and second inclinations collected by the two inclination sensors set on the warning sign, not only detect the deviation of a single inclination from the preset standard inclination, but also calculate the average value and compare it with the standard. This multi-angle and multi-dimensional analysis method can comprehensively and accurately judge whether there is an overturning risk for the warning sign. Once an abnormal inclination is found, a prompt message will be generated in a timely manner to prompt the maintenance personnel to adjust the angle, ensuring that the warning sign is always in the best warning state, stably playing the role of warning passing vehicles and pedestrians, and avoiding safety accidents caused by the invalidation of the warning due to the inclination of the sign.

[0093] Two judgment criteria are adopted, that is, the deviation of a single inclination exceeds the first preset amplitude and the difference between the average value and the preset standard inclination exceeds the second preset amplitude, which increases the rigor and reliability of the judgment. Different judgment conditions can cope with various possible actual situations, whether it is an individual inclination mutation caused by external force impact at a certain moment or the overall inclination gradually deviating from the standard due to long-term environmental factors, all can be accurately captured, effectively reducing the misjudgment rate, and ensuring the correctness of the warning sign angle to the greatest extent.

[0094] Precisely control the position of the warning sign and enhance the on-site safety;

[0095] Mark the position of the warning sign as A1 and set the center point of the maintenance vehicle as the reference point A2. Continuously monitor the evaluation distance between the two and compare it with the preset standard placement distance. When the evaluation distance is less than the standard value, a prompt message will be generated immediately to remind the maintenance personnel to readjust the position. This process is like installing a precise "navigator" for the warning sign, ensuring that it is within the specified safe and effective warning range at any time, preventing improper placement, such as being too close to the maintenance vehicle and affecting the maintenance operation space, or being too far away to effectively warn approaching vehicles, thereby improving the safety of the entire maintenance site.

[0096] Displacement Monitoring and Dynamic Prevention and Control: Collect and evaluate distances at a preset frequency, and judge whether there is abnormal displacement of the protection signs by observing the changing trend of the distances. If it is found that the distances are constantly changing, it means that the protection signs may be displaced due to external forces during the maintenance process, ground vibrations and other factors. At this time, prompt information is generated in a timely manner, allowing maintenance personnel to detect and take measures to fix the signs immediately. This dynamic monitoring mechanism can actively prevent potential safety hazards, nip risks in the bud, and create a continuous and stable safety environment for on-orbit maintenance operations.

[0097] Comprehensively improve the intelligent level of maintenance assistance to facilitate efficient maintenance;

[0098] The entire process of obtaining the prompt information of the protection signs relies on a large amount of real-time data collected by sensors. From multi-angle inclination data to dynamic position data, through rigorous algorithms and comparison and analysis with preset standards, highly targeted prompt information is generated for maintenance personnel. Maintenance personnel do not need to rely on subjective experience to judge the status of the protection signs. They only need to make scientific decisions to adjust the protection signs quickly based on the clear prompts given by the system, greatly improving the accuracy and efficiency of maintenance decisions.

[0099] The system automatically and continuously monitors various parameters of the protection signs, and immediately issues prompt information once abnormalities occur, overcoming problems such as long time intervals and omissions that may exist in manual inspections. Whether it is during late night, early morning and other periods when personnel are prone to fatigue, or when maintenance tasks are busy and manpower is scarce, it can ensure that the protection signs are always under the intelligent monitoring of the system, build a safety defense line for on-orbit maintenance work, and comprehensively improve the intelligent management level of rail transit vehicle maintenance.

[0100] The specific process of obtaining the personnel prompt information is as follows:

[0101] Extract the real-time location of maintenance personnel, maintenance reason information and the number of real-time maintenance personnel from the information related to track maintenance;

[0102] Import the maintenance reason information into the preset database, retrieve the standard number of maintenance personnel from the preset database, and generate personnel prompt information when the difference between the real-time number of maintenance personnel and the standard number of maintenance personnel is less than 0 or greater than the preset value a;

[0103] Then collect the distance information between the real-time location of the maintenance personnel and the reference point A2 to obtain the personnel distance information, and generate personnel prompt information when the personnel distance information is greater than the preset value for a preset duration;

[0104] At the same time, collect the distances between all personnel performing maintenance tasks. When there is a distance greater than the preset value between the personnel distances of all personnel performing maintenance tasks, personnel prompt information is generated;

[0105] Collect the maintenance task information assigned to the maintenance personnel, extract the task execution time point from the maintenance task information. When there is a preset duration remaining until the task execution time point, extract the personnel distance information of all maintenance personnel performing the maintenance tasks. When there is personnel distance information greater than the preset value, generate personnel prompt information;

[0106] Personnel quantity control based on the maintenance reason. By importing the maintenance reason into the preset database to retrieve the standard number of maintenance personnel, and then comparing with the real-time number of maintenance personnel, it can accurately judge whether the current manpower allocation is reasonable. For example, when dealing with complex circuit fault maintenance, the database gives a standard configuration of 8 professional maintenance personnel based on past similar maintenance cases and professional standards. If the real-time number of on-site personnel is 6, the difference is less than 0, and the system generates prompt information to prompt timely dispatch of additional personnel to avoid maintenance delays caused by insufficient manpower; conversely, if there are 12 personnel on-site, exceeding the reasonable number by a large margin, it may cause overcrowding and chaotic division of labor at the scene. The system prompts to optimize the personnel arrangement to ensure the efficient and smooth progress of the maintenance process.

[0107] Optimizing the personnel layout through real-time position monitoring. Collect the distance information between the real-time positions of the maintenance personnel and the reference point A2. When the personnel distance is too large for a preset duration, such as in a maintenance task of replacing a key component, the preset distance is 15 meters from the reference point, and the preset duration is 10 minutes. If a maintenance personnel exceeds this range for 10 minutes, the system prompts the personnel to stay away from the key operation area, facilitating the management personnel to adjust the personnel positions in a timely manner, ensuring that the maintenance personnel concentrate on the effective operation range, avoiding poor cooperation caused by personnel dispersion, and improving the overall maintenance efficiency.

[0108] Strengthen team cooperation and reduce safety risks;

[0109] Monitoring the personnel distance to prevent collision risks: Collect the distances between all maintenance personnel performing the maintenance tasks. Once it is found that the personnel distance is greater than the preset value, for example, when performing fine equipment maintenance in a narrow rail car, the preset personnel distance is 2 meters. If the distance between two people reaches 3 meters, it may lead to inconvenient communication, difficult tool transfer, and is also prone to collisions when personnel move. At this time, generate prompt information to remind the maintenance personnel to maintain a reasonable distance, ensure the close and safe team cooperation, and reduce the probability of accidental accidents caused by personnel negligence.

[0110] Personnel control for tasks approaching execution: extract the task execution time point in the maintenance task information, and check the personnel distance information when there is a preset time left before the task is executed. For example, 5 minutes before the critical operation of track connection, the preset distance between key personnel is 3 meters. If it is found that the distance between some personnel is too far at this time, prompt information will be provided to remind personnel to quickly take their positions and work closely together to ensure that all personnel work together at the critical moment of the task, avoid affecting the maintenance quality and progress due to the failure of personnel to arrive in time, and ensure that the maintenance task is completed on time and safely.

[0111] When performing derailment maintenance, the specific process of the second collection module collecting information related to derailment maintenance is as follows:

[0112] Before lifting and derailing a rail transit vehicle, inspect the lifting steel cable and obtain the lifting steel cable information;

[0113] During the hoisting process, real-time hoisting images are collected;

[0114] The hoisting cable information and real-time hoisting images constitute the derailment maintenance related information.

[0115] The process of obtaining the hoisting cable information is as follows:

[0116] Use magnetic particle detection method to detect steel cable, that is, magnetize the steel cable, and then spray magnetic powder on its surface. After spraying, collect the number of areas with magnetic powder adsorption area greater than the preset value and the number of areas with length greater than the preset length. When the area of ​​a region with magnetic powder adsorption area greater than the preset value and the length greater than the preset length is greater than the preset length, only one is recorded, and the sum of the number of areas with magnetic powder adsorption area greater than the preset value and the number of areas with length greater than the preset length is calculated to obtain abnormal areas and the number of abnormal areas, that is, the first abnormal information;

[0117] At the same time, the ultrasonic detection method is used to detect the steel cable, and the abnormal area of ​​the steel cable and the number of abnormal areas of the steel cable are obtained, that is, the second abnormal information;

[0118] The acquisition process of the real-time hoisting image is as follows: a safety area is set on the hoisting path, and an image acquisition device is set in the safety area to collect image information in the safety area during the hoisting of the rail transit vehicle in real time, that is, to obtain the real-time hoisting image;

[0119] The lifting cables are inspected by multiple methods to ensure the safety of lifting. The magnetic particle inspection method is used. After the cables are magnetized and sprayed with magnetic powder, the area with adsorbed magnetic powder and a length greater than the preset length is carefully collected. For example, in a subway vehicle derailment maintenance scenario, the preset adsorbed magnetic powder area value is 5 square centimeters and the length value is 3 centimeters. When an area with an adsorbed magnetic powder area of ​​8 square centimeters and a length of 4 centimeters is detected in a certain section of the cable, it is accurately marked as an abnormal area. By rigorously calculating the number of such abnormal areas, that is, the first abnormal information, it is possible to accurately detect subtle defects on the surface of the cable caused by wear, rust, etc., which provides a key basis for evaluating the carrying capacity of the cable in advance and judging whether it is suitable for lifting operations, effectively avoiding lifting accidents caused by hidden dangers of the cable itself.

[0120] Ultrasonic testing is used simultaneously to detect abnormalities in the steel cable from the internal structure level. This method can penetrate the steel cable and detect deep problems that are difficult to detect with the naked eye, such as internal steel wire breakage and uneven twisting, and obtain the abnormal area and number of the steel cable, that is, the second abnormal information. Complementary to magnetic particle testing, the steel cable condition is comprehensively checked internally and externally, which greatly improves the accuracy of the safety performance assessment of the steel cable, ensuring that the lifting is only started when the steel cable condition meets the standards, ensuring that the lifting process of the derailed vehicle is foolproof.

[0121] Real-time image acquisition strengthens the monitoring of the entire hoisting process. Image acquisition equipment is set up in the safe area of ​​the hoisting path to collect image information in real time during the entire process of hoisting rail transit vehicles. This is like installing "eyes" for the hoisting operation. Managers can instantly see the actual situation of each stage such as vehicle lifting, translation, and lowering. Regardless of day or night, or in complex weather, they can clearly grasp the dynamics of the site. For example, during nighttime repairs, real-time images can accurately observe key details such as whether the hoisting cable is vertical and whether the vehicle's posture in the air is stable, so that possible deflection, shaking, and other problems can be discovered and corrected in a timely manner to ensure that the hoisting operation is carried out strictly in accordance with standard procedures.

[0122] Based on real-time images, on the one hand, the human body recognition model can be used to quickly detect unrelated personnel who break into the safe area. Once the human body model is recognized, auxiliary information of the lifting process is immediately generated to prompt them to leave and avoid casualties. On the other hand, the lifting speed and release speed are obtained through image analysis and processing. When the speed exceeds the preset value, the operator is reminded to adjust in time to prevent risks such as uneven force on the steel cable and vehicle collision with surrounding facilities due to excessive speed, thereby ensuring the safety and orderly progress of the lifting operation in all aspects.

[0123] The derailment maintenance auxiliary information includes hoisting cable auxiliary information and hoisting process auxiliary information;

[0124] The process of obtaining the auxiliary information of the hoisting cable is as follows:

[0125] Extract the acquired hoisting cable information, and extract the first abnormal information and the second abnormal information therefrom;

[0126] When the number of abnormal areas of the first abnormal information and the number of abnormal areas of the second abnormal information are both greater than the preset value m1, auxiliary information of the hoisting cable is generated;

[0127] When the number of abnormal areas of the first abnormal information and the number of abnormal areas of the second abnormal information are both less than the preset value m2 but greater than 0, the abnormal areas of the first abnormal information and the abnormal areas of the second abnormal information are extracted. When the abnormal areas of the first abnormal information and the abnormal areas of the second abnormal information are different areas, auxiliary information of the lifting steel cable is generated. At this time, the content of the auxiliary information of the lifting steel cable is that there is an abnormality in the lifting steel cable.

[0128] The process of obtaining auxiliary information during the lifting process is as follows:

[0129] Extract the acquired real-time hoisting image, import the human body recognition model into the real-time hoisting image, and generate auxiliary information of the hoisting process when the human body model is recognized in the safe area. At this time, the auxiliary information of the hoisting process indicates that there are abnormal people in the safe area and they need to be driven away.

[0130] Then the real-time hoisting image is processed, and the hoisting speed and release speed are obtained by analyzing the real-time image during the hoisting process;

[0131] When either the lifting speed or the releasing speed is greater than a preset value, auxiliary information of the lifting process is generated. At this time, the content of the auxiliary information of the lifting process is that the lifting speed / releasing speed is too fast and needs to be adjusted;

[0132] The above process quantitatively evaluates and promptly warns of major hidden dangers. By setting a clear preset value m1 to compare the number of abnormal areas of the first abnormal information and the second abnormal information, when any one of them exceeds this value, the system immediately generates auxiliary information for the hoisting cable. For example, at a light rail vehicle derailment maintenance site, m1 is preset to 3. If the magnetic particle detection finds 4 areas where the adsorption area and length of magnetic particles exceed the standard, or the ultrasonic detection detects 5 internal abnormal areas, it means that there is a serious safety risk for the steel cable, which may break during the hoisting process. At this time, the timely warning can allow the maintenance team to decisively suspend the operation and replace the steel cable, eliminating accidents from the source and ensuring the stability of the hoisting foundation.

[0133] Carefully identify potential risks and take preventive measures. For the situation where the number of abnormal areas is less than the preset value m2 (assuming m2 = 2) but greater than 0, further analyze the locations of the abnormal areas. If the abnormal areas detected by different detection methods are different, it indicates that although there are no large - scale serious defects in the steel cable, scattered small problems have occurred, such as local minor wear and individual wire slight poor stranding. If these small problems accumulate or when the force is uneven, they may also trigger major failures. The generated auxiliary information for the lifting steel cable can guide maintenance personnel to carry out targeted maintenance, reinforcement or enhanced monitoring of the steel cable in advance, nip the risks in the bud, and ensure the smooth progress of subsequent lifting operations.

[0134] Monitor the lifting process in real - time to escort the dynamic safety on - site;

[0135] Using the human body recognition model imported into the real - time lifting image, as long as a human body model is recognized within the safe area, auxiliary information for the lifting process is instantly generated to remind to drive away abnormal personnel. At busy rail transit maintenance sites, there are often other staff or irrelevant passers - by shuttling. If someone accidentally enters the lifting safety area and stays under the lifted heavy object, the consequences would be unthinkable. This intelligent recognition and instant warning mechanism can eliminate potential personnel safety hazards in the first time and ensure the safety of personnel at the lifting site.

[0136] The speed control is accurate and efficient: By analyzing the real - time image to obtain the lifting speed and release speed, and comparing them with the preset values. Once the overspeed situation is detected, auxiliary information is immediately generated to require adjustment. For example, when lifting a heavier subway car body, the preset lifting speed is 0.5 meters per second. If due to operation errors or equipment failures, the speed soars to 1 meter per second, the excessive speed will cause the steel cable to bear a huge impact load, and may also make the car body swing greatly in the air and collide with surrounding facilities. Precise speed control can effectively avoid such dangers and ensure the smooth and orderly progress of the lifting process.

[0137] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present invention, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0138] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0139] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. An artificial intelligence-based intelligent maintenance auxiliary system for rail transit vehicles, characterized in that: It includes a maintenance mode acquisition module, a first acquisition module, a second acquisition module, a data processing module and an information sending module; The maintenance mode collection module is used to collect maintenance modes, which include on-track maintenance and off-track maintenance; The first collection module is used to collect information related to on-orbit maintenance during on-orbit maintenance; The second collection module is used for collecting information related to derailment maintenance during derailment maintenance; The data processing module is used to process the on-track maintenance related information and the derailment maintenance related information to generate on-track maintenance auxiliary information and derailment maintenance auxiliary information; The information sending module is used to send the on-track maintenance auxiliary information and the derailment maintenance auxiliary information to a preset receiving terminal.

2. The rail transit vehicle intelligent maintenance auxiliary system based on artificial intelligence according to claim 1 is characterized in that: The specific process of the first acquisition module collecting information related to on-orbit maintenance is as follows: When performing on-orbit maintenance, maintenance personnel need to set up protective signs, on which position sensors and angle acquisition devices are installed to collect the position and placement angle of the protective signs. At the same time, maintenance personnel need to wear position sensing equipment to collect their real-time location; At the same time, information on maintenance reasons and the number of real-time maintenance personnel are collected; That is, the track maintenance related information includes the location of the protection signs, the placement angle, the real-time location of the maintenance personnel, the maintenance reason information and the real-time number of maintenance personnel; The data processing module processes the location and placement angle of the protection signs, the real-time location of the maintenance personnel, the maintenance reason information and the real-time number of maintenance personnel to generate on-orbit maintenance auxiliary information; On-orbit maintenance auxiliary information includes protection sign prompt information and personnel prompt information.

3. The rail transit vehicle intelligent maintenance auxiliary system based on artificial intelligence according to claim 2 is characterized in that: The process of obtaining the placement angle is as follows: Two inclination sensors are arranged on the side of the protection mark to collect the inclination information of the protection mark in real time and mark it as the first inclination and the second inclination; A collection frequency is preset, and the first inclination angle and the second inclination angle are collected multiple times according to the preset collection frequency to obtain multiple first inclination angles and multiple second inclination angles, which constitute the placement angle information.

4. The rail transit vehicle intelligent maintenance auxiliary system based on artificial intelligence according to claim 3 is characterized by: The process of obtaining the protection mark prompt information is as follows: Extracting the collected placement angles, and extracting a plurality of first inclination angles and a plurality of second inclination angles from the placement angles; Processing the multiple first inclination angles, first detecting whether there is a first inclination angle among the multiple first inclination angles that differs from the preset standard inclination angle by more than a first preset amplitude, generating protection mark prompt information when there is a first inclination angle that differs from the preset standard inclination angle by more than a preset amplitude, calculating the average of the multiple first inclination angles, and also generating protection mark prompt information when the average of the multiple first inclination angles differs from the preset standard inclination angle by more than a second preset amplitude; The plurality of second inclination angles are processed in the same manner as the plurality of first inclination angles to determine whether to generate protection mark prompt information; Extract the location of the protection sign, then collect the location of the rail transit vehicle that needs to be repaired, collect its center point and mark it as the reference point; The position of the protection mark is marked as A1, and the reference point is marked as A2. The distance information between the protection mark position A1 and the reference point A2 is monitored in real time to obtain the evaluation distance. When the evaluation distance information is less than the preset standard placement distance, the protection mark prompt information is generated; The assessment distance is collected at a preset frequency, and when the assessment distance collected at the preset frequency gradually decreases, a protective sign prompt message is generated.

5. The rail transit vehicle intelligent maintenance auxiliary system based on artificial intelligence according to claim 4 is characterized in that: The specific process of obtaining the personnel prompt information is as follows: Extract the real-time location of maintenance personnel, maintenance reason information and the real-time number of maintenance personnel from track maintenance related information; Import the maintenance reason information into the preset database, retrieve the standard maintenance personnel quantity from the preset database, and generate personnel prompt information when the difference between the real-time maintenance personnel quantity and the standard maintenance personnel quantity is less than 0 or greater than the preset value a; Then collect the distance information between the real-time position of the maintenance personnel and the reference point A2 to obtain the personnel distance information. When the personnel distance information is greater than the preset value for a preset time, the personnel prompt information is generated; At the same time, the distance between all personnel performing maintenance tasks is collected. When the distance between all personnel performing maintenance tasks is greater than a preset value, a personnel prompt information is generated; Collect the maintenance task information assigned to the maintenance personnel, extract the task execution time point from the maintenance task information, and when there is a preset time left before the task execution time point, extract the personnel distance information of all maintenance personnel performing the maintenance task. When there is personnel distance information greater than the preset value, generate personnel prompt information.

6. The rail transit vehicle intelligent maintenance auxiliary system based on artificial intelligence according to claim 1 is characterized in that: When performing derailment maintenance, the specific process of the second collection module collecting information related to derailment maintenance is as follows: Before lifting and derailing a rail transit vehicle, inspect the lifting steel cable and obtain the lifting steel cable information; During the hoisting process, real-time hoisting images are collected; The lifting cable information and real-time lifting images constitute the derailment maintenance related information.

7. The rail transit vehicle intelligent maintenance auxiliary system based on artificial intelligence according to claim 6 is characterized by: The process of obtaining the hoisting cable information is as follows: Use magnetic particle detection method to detect steel cable, that is, magnetize the steel cable, and then spray magnetic powder on its surface. After spraying, collect the number of areas with magnetic powder adsorption area greater than the preset value and the number of areas with length greater than the preset length. When the area of ​​a region with magnetic powder adsorption area greater than the preset value and the length greater than the preset length is greater than the preset length, only one is recorded, and the sum of the number of areas with magnetic powder adsorption area greater than the preset value and the number of areas with length greater than the preset length is calculated to obtain abnormal areas and the number of abnormal areas, that is, the first abnormal information; At the same time, the ultrasonic detection method is used to detect the steel cable, and the abnormal area of ​​the steel cable and the number of abnormal areas of the steel cable are obtained, that is, the second abnormal information; The process of acquiring the real-time hoisting image is as follows: a safety area is set up on the hoisting path, and an image acquisition device is set up in the safety area to collect image information in the safety area in real time during the hoisting of the rail transit vehicle, that is, to obtain the real-time hoisting image.

8. The rail transit vehicle intelligent maintenance auxiliary system based on artificial intelligence according to claim 7 is characterized in that: The derailment maintenance auxiliary information includes hoisting cable auxiliary information and hoisting process auxiliary information; The process of obtaining the auxiliary information of the hoisting cable is as follows: Extract the acquired hoisting cable information, and extract the first abnormal information and the second abnormal information therefrom; When the number of abnormal areas of the first abnormal information and the number of abnormal areas of the second abnormal information are both greater than the preset value m1, auxiliary information of the hoisting cable is generated; When the number of abnormal areas of the first abnormal information and the number of abnormal areas of the second abnormal information are both less than the preset value m2 but greater than 0, the abnormal areas of the first abnormal information and the abnormal areas of the second abnormal information are extracted. When the abnormal areas of the first abnormal information and the abnormal areas of the second abnormal information are different areas, auxiliary information of the hoisting cable is generated; The process of obtaining auxiliary information during the lifting process is as follows: Extract the acquired real-time hoisting image, import the human body recognition model into the real-time hoisting image, and generate auxiliary information of the hoisting process when the human body model is recognized in the safe area; Then the real-time hoisting image is processed, and the hoisting speed and release speed are obtained by analyzing the real-time image during the hoisting process; When either the lifting speed or the releasing speed is greater than a preset value, auxiliary information of the lifting process is generated.

Images