Rail transit fault diagnosis system based on machine learning

Through a machine learning-based rail transit fault diagnosis system, the cable car's stress and speed changes at the tower are analyzed, and the cable car's bumps and retention problems in rainy days are solved, improving the accuracy of fault diagnosis and passenger experience.

CN118529098BActive Publication Date: 2024-11-22TAI ZHOU LI FAN KE JI YOU XIAN GONG SI
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411000648.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-11-22
Estimated Expiration
2044-07-25

AI Technical Summary

Technical Problem

In rainy days, the increase in resistance of the cable car when passing through the tower leads to bumps and retention, and it is difficult for the existing technology to accurately diagnose faults, especially between towers with different distances from the initial and end points, which affects the riding experience.

Method used

Design a rail transit fault diagnosis system based on machine learning, including data acquisition module, tower analysis module, resistance diagnosis module and output module. Through force sensors, speed evaluation modules, timing units, camera units and humidity sensors, analyzing the cable car in the tower The force, speed changes and resistance factors at the location can be judged to determine the safety factor of the cable car and reduce the error detection.

Benefits of technology

Effectively analyze the specific speed changes and drag factors of the cable car at the tower, reduce fault misdetection, and improve the accuracy of fault diagnosis and passenger experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118529098B_ABST
    Figure CN118529098B_ABST
Patent Text Reader

Abstract

The present invention discloses a rail transit fault diagnosis system based on machine learning, including a data acquisition module, a tower analysis module, a resistance diagnosis module and an output module. The data acquisition module is used to collect the operation system data of the cableway; the tower analysis module is used to detect the cableway track near the tower; the resistance diagnosis module is used to diagnose the track resistance factor, and the output module is used to output maintenance information to maintenance personnel. The present invention solves the problem of speed change caused by wear when the cable car passes through the tower in rainy days. The tower analysis module is used to obtain the specific speed change of the cable car when passing the tower, and the operation analysis module is used to obtain the traction and angle parameters of the main influencing factors causing the speed change. Finally, the cable car safety factor analysis module is used to diagnose the safety parameters to reduce the possibility of false detection of cable car speed faults. The present invention has the characteristics of strong fault analysis capability and high fault monitoring accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of traffic management, and in particular to a rail transit fault diagnosis system based on machine learning. Background Art

[0002] With the development of mountain tourism, a new type of rail transportation tool - cable car has gradually come into people's view. Large cable cars are an important means of transportation in large scenic spots. They greatly save people's time for climbing mountains, allowing people to have more time to arrange in the scenic spots. At the same time, when riding in a cable car, people can enjoy the scenery outside through the cable car window and get a better angle to take pictures of the scenic spot.

[0003] However, the comfort of cable car operation largely determines the visual experience of passengers. Therefore, it is of great significance to monitor the operation of large cable cars. Existing technologies can detect mechanical problems that occur during the operation of cable cars and monitor the operation of cable cars in real time. However, in rainy weather scenarios, when the cable car runs to the tower, the resistance caused by the ropes involved near the tower and the cable car passing through the tower will be magnified, resulting in certain bumps and stagnation when the cable car passes through the tower, affecting the passengers' riding experience. Even if the operation problems of the cable car can be diagnosed by detecting the speed changes of the cable car when passing through the tower, the possibility of causing a fault will also be significantly different when the cable car passes through towers with different distances from the initial point and the end point. Therefore, it is necessary to design a rail transit fault diagnosis system based on machine learning with strong fault analysis capabilities and high fault monitoring accuracy. Summary of the invention

[0004] The purpose of the present invention is to provide a rail transit fault diagnosis system based on machine learning to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a rail transit fault diagnosis system based on machine learning, comprising a data acquisition module, a tower analysis module, a resistance diagnosis module and an output module, wherein the data acquisition module is used to collect the operation system data of the cableway; the tower analysis module is used to detect the cableway track near the tower; the resistance diagnosis module is used to diagnose the track resistance factor, and the output module is used to output maintenance information to maintenance personnel;

[0006] The tower analysis module includes a force sensor detection module and a cable car speed assessment module. The force sensor detection module is used to detect the force applied to the cable car when it runs to the tower; the cable car speed assessment module is used to monitor the running speed of the cable car.

[0007] The force sensor detection module includes an upward force sensor subunit and a downward force sensor subunit, wherein the upward force sensor subunit is used to detect the force applied when the upward cable car runs to the tower; the downward force sensor subunit is used to detect the force applied when the downward cable car runs to the tower;

[0008] The resistance diagnosis module includes a cable car safety factor analysis module, and the cable car safety factor analysis module is used to analyze the safety factor of the cableway operation system.

[0009] According to the above technical solution, the data acquisition module includes an operation data acquisition module and a drive data acquisition module. The operation data acquisition module is used to collect the operation data of the cableway; the drive data collection module is used to collect the driving wheel data of the traction cableway.

[0010] According to the above technical solution, the tower analysis module also includes a timing unit, a camera unit and a humidity sensor unit. The timing unit is used to time when the cable car runs to the tower; the camera unit is used to take real-time photos of the cableway operation system; and the humidity sensor unit is used to detect weather humidity.

[0011] According to the above technical solution, the timing unit includes an upward timing subunit and a downward timing subunit. The upward timing subunit is used to time when the upward cable car runs to the tower; the downward timing subunit is used to time when the downward cable car runs to the tower.

[0012] According to the above technical solution, the resistance diagnosis module also includes an operation analysis module, which is used to analyze the resistance factors generated by the operation of the cable car. The operation analysis module includes an inclination detection submodule and a traction analysis submodule. The inclination detection submodule is used to monitor the inclination of the ropes at both ends of the tower in real time; the traction analysis submodule is used to detect the real-time traction of the driving wheels on the cable car at different towers.

[0013] According to the above technical solution, the operation method of the rail transit fault diagnosis system mainly includes the following steps:

[0014] Step S1: the data acquisition module collects the operation data of the cable car through the operation data acquisition module, and collects the driving wheel data of the traction cable car through the driving data acquisition module;

[0015] Step S2: the tower analysis module monitors the operation of the cable car through a camera unit arranged on the tower, and obtains the average speed of the cable car when it is running on the tower through a force sensor detection module and a timing unit;

[0016] Step S3: When the humidity sensor unit detects that the humidity reaches the humidity standard corresponding to rainy days, the resistance diagnosis module starts fault detection. When the cable car speed evaluation module detects that the real-time operating speed of the cable car is not within the normal operating speed range, it is determined that the cable car operation needs to be diagnosed, and the diagnostic information is transmitted to the resistance diagnosis module;

[0017] Step S4: the resistance diagnosis module receives the diagnosis information and analyzes the resistance factors generated by the operation of the cable car through the operation analysis module;

[0018] Step S5: The inclination detection module detects the inclination of the ropes at the two ends of the tower to determine whether the angle change of the ropes at both ends of the tower has an adverse effect on the operation of the cable car. If it is determined that there is a risk of failure, the fault information of the rope wear is transmitted to the output module;

[0019] Step S6: The traction force analysis submodule calculates and analyzes the traction force of the driving wheel on the cable car near each tower to determine whether the change in the traction force on the cable car has an adverse effect on the operation of the cable car; the cable car safety factor analysis module comprehensively considers the inclination change at both ends of the tower and the traction force on the cable car to infer whether the safety factor of the cableway operation system is within the safety range. If it is within the safety range, the abnormal speed is determined to be a misdiagnosis; if it is not within the safety range, the abnormal speed is determined to be related to the internal structure failure of the cable car, and the internal structure inspection information of the cable car is transmitted to the output module;

[0020] Step S7: The system outputs the fault information to the scenic spot staff through the output module.

[0021] According to the above technical solution, in step S2, when the upward force sensor subunit set on the upward rope tower detects the force, the upward timing subunit starts timing. When the upward force sensor subunit detects that the force disappears, the upward timing subunit counts the timing time t at this time as the running time of the cable car on the tower. The length of each tower is L, and the average speed of the cable car on the tower is .

[0022] According to the above technical solution, in step S3, the cable car speed assessment module obtains the normal operating speed of the cable car on the rope through the camera unit. When the cable car runs to the tower, the cable car running speed is 1 meter below the tower. When the cable car runs to the tower, the cable car running speed is 1 meter above the tower. If , the cable car speed evaluation module determines that the cable car operation needs to be diagnosed, where λ1 is the slowest speed change ratio parameter and λ2 is the fastest speed change ratio parameter.

[0023] According to the above technical solution, step S5 further includes:

[0024] Step S51: When the upward force sensor subunit disposed on the upward rope tower detects the force, the upward timing subunit starts timing;

[0025] Step S52: When the upward force sensor subunit detects that the force disappears, the upward timing subunit continues to time for 0.1 seconds and then stops, and the inclination detection submodule sets the angle α° between the rope above the tower and the tower at this time as the maximum angle between the rope above the tower and the tower;

[0026] Step S53: When the downlink force sensor subunit disposed on the downlink rope tower detects the force, the downlink timing subunit starts timing;

[0027] Step S54: when the downward force sensor subunit detects that the force disappears, the downward timing subunit continues to time for 0.1 seconds and then stops, and the inclination detection submodule sets the angle β° between the rope below the tower and the tower at this time as the maximum angle between the rope below the tower and the tower;

[0028] Step S55: The change in the angle of the cableway when passing through the tower , the maximum tilt change angle that ensures safety when the cableway passes through the tower is θ1, and the minimum tilt change angle that ensures safety when passing through the tower is θ2. , it is determined that the rope erection of the tower has a failure risk.

[0029] According to the above technical solution, step S6 further includes:

[0030] Step S61: The cableway has a total of n towers. When n is an odd number, and The traction force between the two towers is the smallest; when n is an even number, the The actual traction force on the front and rear of the tower is the smallest, and the actual traction force on the tower is statistically , where f is the resistance of the cable car passing through each ropeway, and the actual traction f (n) between each tower is different. , then the cableway is judged to have a risk of failure, where f1 is the minimum traction force for the cable car to safely pass through the tower, and f2 is the maximum traction force for the cable car to safely pass through the tower.

[0031] Step S62: Setting a safety factor A for the cable car passing through the tower. ,like , then the abnormal speed of the cable car when passing the tower is judged to be a misdiagnosis, where the safety parameter A can detect whether there is a problem with the cable car operation system, A0 is the minimum value of the cable car operation safety factor, and K is the unit conversion parameter.

[0032] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention analyzes the cable car operation system to solve the problem of speed changes caused by wear when the cable car passes through the tower in rainy days, obtains the specific speed changes of the cable car when passing the tower through the tower analysis module, and obtains the traction and angle parameters, which are the main influencing factors causing the speed changes, through the operation analysis module to determine whether there is an adverse effect on the cable car operation, and finally diagnoses the safety parameters through the cable car safety factor analysis module to reduce the possibility of false detection of cable car speed failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0034] Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] Please refer to Figure 1 The present invention provides a technical solution: a rail transit fault diagnosis system based on machine learning, comprising:

[0037] Data acquisition module, tower analysis module, resistance diagnosis module and output module. The data acquisition module is used to collect the operating system data of the cableway; the tower analysis module is used to detect the cableway track near the tower; the resistance diagnosis module is used to diagnose the track resistance factors; and the output module is used to output maintenance information to maintenance personnel.

[0038] The tower analysis module includes a force sensor detection module and a cable car speed evaluation module. The force sensor detection module is used to detect the force applied to the cable car when it runs to the tower; the cable car speed evaluation module is used to monitor the running speed of the cable car.

[0039] The force sensor detection module includes an upward force sensor subunit and a downward force sensor subunit. The upward force sensor subunit is used to detect the force when the upward cable car runs to the tower; the downward force sensor subunit is used to detect the force when the downward cable car runs to the tower;

[0040] The resistance diagnosis module includes a cable car safety factor analysis module, which is used to analyze the safety factor of the cableway operation system.

[0041] The present invention analyzes the cable car operation system to solve the problem of speed change caused by wear when the cable car passes through the tower in rainy days. The tower analysis module is used to obtain the specific speed change of the cable car when passing the tower, and the operation analysis module is used to obtain the traction and angle parameters that are the main influencing factors causing the speed change, to determine whether the cable car operation is adversely affected. Finally, the cable car safety factor analysis module is used to diagnose the safety parameters to reduce the possibility of false detection of cable car speed faults.

[0042] The data collection module includes an operation data collection module and a drive data collection module. The operation data collection module is used to collect the operation data of the ropeway; the drive data collection module is used to collect the driving wheel data of the traction ropeway operation.

[0043] The tower analysis module also includes a timing unit, a camera unit and a humidity sensor unit. The timing unit is used to time when the cable car runs to the tower; the camera unit is used to take real-time photos of the cableway operation system; and the humidity sensor unit is used to detect weather humidity.

[0044] The timing unit comprises an upward timing subunit and a downward timing subunit. The upward timing subunit is used for timing when the upward cable car runs to the tower; the downward timing subunit is used for timing when the downward cable car runs to the tower.

[0045] The resistance diagnosis module also includes an operation analysis module, which is used to analyze the resistance factors generated by the operation of the cable car. The operation analysis module includes an inclination detection submodule and a traction analysis submodule. The inclination detection submodule is used to monitor the inclination of the ropes at both ends of the tower in real time; the traction analysis submodule is used to detect the real-time traction of the driving wheels on the cable car at different towers.

[0046] In a preferred embodiment, the operation method of the rail transit fault diagnosis system mainly includes the following steps:

[0047] Step S1: the data acquisition module collects the operation data of the cable car through the operation data acquisition module, and collects the driving wheel data of the traction cable car through the driving data acquisition module;

[0048] Step S2: the tower analysis module monitors the operation of the cable car through a camera unit arranged on the tower, and obtains the average speed of the cable car when it is running on the tower through a force sensor detection module and a timing unit;

[0049] Step S3: When the humidity sensor unit detects that the humidity reaches the humidity standard corresponding to rainy days, the resistance diagnosis module starts fault detection. When the cable car speed evaluation module detects that the real-time operating speed of the cable car is not within the normal operating speed range, it is determined that the cable car operation needs to be diagnosed, and the diagnostic information is transmitted to the resistance diagnosis module;

[0050] Step S4: the resistance diagnosis module receives the diagnosis information and analyzes the resistance factors generated by the operation of the cable car through the operation analysis module;

[0051] Step S5: The inclination detection module detects the inclination of the ropes at the two ends of the tower to determine whether the angle change of the ropes at both ends of the tower has an adverse effect on the operation of the cable car. If it is determined that there is a risk of failure, the fault information of the rope wear is transmitted to the output module;

[0052] Step S6: The traction force analysis submodule calculates and analyzes the traction force of the driving wheel on the cable car near each tower to determine whether the change in the traction force on the cable car has an adverse effect on the operation of the cable car; the cable car safety factor analysis module comprehensively considers the inclination change at both ends of the tower and the traction force on the cable car to infer whether the safety factor of the cableway operation system is within the safety range. If it is within the safety range, the abnormal speed is determined to be a misdiagnosis; if it is not within the safety range, the abnormal speed is determined to be related to the internal structure failure of the cable car, and the internal structure inspection information of the cable car is transmitted to the output module;

[0053] Step S7: The system outputs the fault information to the scenic spot staff through the output module.

[0054] In step S2 of this embodiment, when the upward force sensor subunit disposed on the upward rope tower detects the force, the upward timing subunit starts timing. When the upward force sensor subunit detects that the force disappears, the upward timing subunit counts the timing time t at this time as the running time of the cable car on the tower. The length of each tower is L, and the average speed of the cable car on the tower is .

[0055] In step S3 of this embodiment, the cable car speed assessment module obtains the normal operating speed of the cable car on the rope through the camera unit. When the cable car runs to the tower and is 1 meter below, the cable car running speed is V1. When the cable car runs to the tower and is 1 meter above, the cable car running speed is V2. , the cable car speed evaluation module determines that the cable car operation needs to be diagnosed, where λ1 is the slowest speed change ratio parameter and λ2 is the fastest speed change ratio parameter.

[0056] In this embodiment, step S5 further includes:

[0057] Step S51: When the upward force sensor subunit disposed on the upward rope tower detects the force, the upward timing subunit starts timing;

[0058] Step S52: When the upward force sensor subunit detects that the force disappears, the upward timing subunit continues to time for 0.1 seconds and then stops, and the inclination detection submodule sets the angle α° between the rope above the tower and the tower at this time as the maximum angle between the rope above the tower and the tower;

[0059] Step S53: When the downlink force sensor subunit disposed on the downlink rope tower detects the force, the downlink timing subunit starts timing;

[0060] Step S54: when the downward force sensor subunit detects that the force disappears, the downward timing subunit continues to time for 0.1 seconds and then stops, and the inclination detection submodule sets the angle β° between the rope below the tower and the tower at this time as the maximum angle between the rope below the tower and the tower;

[0061] Step S55: The change in the angle of the cableway when passing through the tower , the maximum tilt change angle that ensures safety when the cableway passes through the tower is θ1, and the minimum tilt change angle that ensures safety when passing through the tower is θ2. , it is determined that the rope erection of the tower has a failure risk.

[0062] The angle between the rope between the cable car and the tower and the tower will change significantly as the distance between the cable car and the tower decreases. When the cable car is at the end of the rope below the tower, the angle between the rope below the tower and the tower is the largest. When the cable car is at the initial end of the rope above the tower, the angle between the rope above the tower and the tower is the largest.

[0063] The conditions are almost the same when the cable car goes up and down through the tower.

[0064] Since the ropes near the tower are greatly deformed due to the gravity of the cable car, the toughness of the ropes near the tower decreases after long-term operation, and they will age and wear out, causing the angle of the cable car to change too much when passing the tower. Passengers are subjected to greater bumps, resulting in a poor viewing experience. The inclination detection submodule detects the angle between the rope and the tower after the cable car passes the tower, and effectively diagnoses whether the cable car is bumped when passing the tower due to the change in rope angle.

[0065] Since the speed change when the cable car contacts the tower is difficult to detect, the tower analysis module is used to obtain the running speed of the cable car on the tower and the running speed of the cable car when it is close to the tower. This can effectively detect the speed change caused by the force applied to the cable car at the tower, thereby diagnosing the fault.

[0066] In this embodiment, step S6 further includes:

[0067] Step S61: The cableway has a total of n towers. When n is an odd number, and The traction force between the two towers is the smallest; when n is an even number, the The actual traction force on the front and rear of the tower is the smallest, and the actual traction force on the tower is statistically , where f is the resistance of the cable car passing through each ropeway, and the actual traction f (n) between each tower is different. , then the cableway is judged to have a risk of failure, where f1 is the minimum traction force for the cable car to safely pass through the tower, and f2 is the maximum traction force for the cable car to safely pass through the tower;

[0068] Due to Newton's third law, the traction force applied upward by the driving wheel above the cableway and the traction force applied downward by the driving wheel below the cableway are the same. When n is an odd number, and The traction force between the two towers is the smallest. The actual traction force on the tower , No. The actual traction force on the tower .

[0069] Step S62: Setting a safety factor A for the cable car passing through the tower. ,like , then the abnormal speed of the cable car when passing the tower is judged to be a misdiagnosis, where the safety parameter A can detect whether there is a problem with the cable car operation system, A0 is the minimum value of the cable car operation safety factor, and K is the unit conversion parameter.

[0070] The speed of the cable car passing through the tower is affected by the changing angle of the cable car passing through the tower and the change in traction force. The upper and lower drive wheels provide mutual traction F, which is transmitted to the cableway between each tower through ropes. Each time a tower is passed, part of the traction force will be consumed by the resistance of the tower. Therefore, the farther the tower is from the drive wheel that provides traction, the smallest the actual traction force is. At this time, the running speed of the cable car will gradually show a trend of first decreasing and then increasing when only the traction force change is considered. The cableway is set between the mountains. In order to reduce the experience of passengers when the cable car is running, the cableway is set up in a streamlined shape. Streamline is an external shape of an object, usually manifested as a smooth and regular surface without large ups and downs and sharp edges. The closer the tower is to the drive wheel, the greater the angle change on both sides of the tower; the farther the tower is from the drive wheel, the smaller the angle change on both sides of the tower. At this time, the running speed of the cable car will gradually show a trend of first increasing and then decreasing when only the angle change is considered.

[0071] When the cable car is subjected to strong traction when passing through the tower, the angle change has a great resistance to the cable car; when the cable car is subjected to weak traction when passing through the tower, the angle change has a small resistance to the cable car. The cable car safety factor analysis module can minimize the occurrence of false detection problems in which the actual operating speed of the monitored cable car is not within the normal range even though the traction force and the rope angle changes are within the safety range.

[0072] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0073] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A rail transit fault diagnosis system based on machine learning, characterized by: It includes a data acquisition module, a tower analysis module, a resistance diagnosis module and an output module. The data acquisition module is used to collect the operation system data of the cableway; the tower analysis module is used to detect the cableway track near the tower; the resistance diagnosis module is used to diagnose the track resistance factor, and the output module is used to output maintenance information to maintenance personnel; The tower analysis module includes a force sensor detection module and a cable car speed assessment module. The force sensor detection module is used to detect the force applied to the cable car when it runs to the tower; the cable car speed assessment module is used to monitor the running speed of the cable car. The force sensor detection module includes an upward force sensor subunit and a downward force sensor subunit, wherein the upward force sensor subunit is used to detect the force applied when the upward cable car runs to the tower; the downward force sensor subunit is used to detect the force applied when the downward cable car runs to the tower; The resistance diagnosis module includes a cable car safety factor analysis module, and the cable car safety factor analysis module is used to analyze the safety factor of the cableway operation system.

2. The rail transit fault diagnosis system based on machine learning according to claim 1, characterized in that: The data collection module includes an operation data collection module and a drive data collection module. The operation data collection module is used to collect the operation data of the cableway; the drive data collection module is used to collect the driving wheel data of the traction cableway.

3. The rail transit fault diagnosis system based on machine learning according to claim 2 is characterized in that: The tower analysis module also includes a timing unit, a camera unit and a humidity sensor unit. The timing unit is used to time when the cable car runs to the tower; the camera unit is used to take real-time photos of the cableway operation system; and the humidity sensor unit is used to detect weather humidity.

4. The rail transit fault diagnosis system based on machine learning according to claim 3 is characterized in that: The timing unit includes an upward timing subunit and a downward timing subunit. The upward timing subunit is used to time when the upward cable car runs to the tower; the downward timing subunit is used to time when the downward cable car runs to the tower.

5. The rail transit fault diagnosis system based on machine learning according to claim 4 is characterized in that: The resistance diagnosis module also includes an operation analysis module, which is used to analyze the resistance factors generated by the operation of the cable car. The operation analysis module includes an inclination detection submodule and a traction analysis submodule. The inclination detection submodule is used to monitor the inclination of the ropes at both ends of the tower in real time; the traction analysis submodule is used to detect the real-time traction of the driving wheels on the cable car at different towers.

6. The rail transit fault diagnosis system based on machine learning according to claim 5 is characterized in that: The operation method of the rail transit fault diagnosis system mainly includes the following steps: Step S1: the data acquisition module collects the operation data of the cable car through the operation data acquisition module, and collects the driving wheel data of the traction cable car through the driving data acquisition module; Step S2: the tower analysis module monitors the operation of the cable car through a camera unit arranged on the tower, and obtains the average speed of the cable car when it is running on the tower through a force sensor detection module and a timing unit; Step S3: When the humidity sensor unit detects that the humidity reaches the humidity standard corresponding to rainy days, the resistance diagnosis module starts fault detection. When the cable car speed evaluation module detects that the real-time operating speed of the cable car is not within the normal operating speed range, it is determined that the cable car operation needs to be diagnosed, and the diagnostic information is transmitted to the resistance diagnosis module; Step S4: the resistance diagnosis module receives the diagnosis information and analyzes the resistance factors generated by the operation of the cable car through the operation analysis module; Step S5: The inclination detection module detects the inclination of the ropes at the two ends of the tower to determine whether the angle change of the ropes at both ends of the tower has an adverse effect on the operation of the cable car. If it is determined that there is a risk of failure, the fault information of the rope wear is transmitted to the output module; Step S6: The traction force analysis submodule calculates and analyzes the traction force of the driving wheel on the cable car near each tower to determine whether the change in the traction force on the cable car has an adverse effect on the operation of the cable car; the cable car safety factor analysis module comprehensively considers the inclination change at both ends of the tower and the traction force on the cable car to infer whether the safety factor of the cableway operation system is within the safety range. If it is within the safety range, the abnormal speed is determined to be a misdiagnosis; if it is not within the safety range, the abnormal speed is determined to be related to the internal structure failure of the cable car, and the internal structure inspection information of the cable car is transmitted to the output module; Step S7: The system outputs the fault information to the scenic spot staff through the output module.

7. The rail transit fault diagnosis system based on machine learning according to claim 6 is characterized in that: In step S2, when the upward force sensor subunit set on the upward rope tower detects the force, the upward timing subunit starts timing. When the upward force sensor subunit detects that the force disappears, the upward timing subunit counts the timing time t at this time as the running time of the cable car on the tower. The length of each tower is L, and the average speed of the cable car on the tower is .

8. The rail transit fault diagnosis system based on machine learning according to claim 7 is characterized in that: In step S3, the cable car speed assessment module obtains the normal operating speed of the cable car on the rope through the camera unit. When the cable car runs to the tower, the cable car running speed is V1 at 1 meter below. When the cable car runs to the tower, the cable car running speed is V2 at 1 meter above. , the cable car speed evaluation module determines that the cable car operation needs to be diagnosed, where λ1 is the slowest speed change ratio parameter and λ2 is the fastest speed change ratio parameter.

9. The rail transit fault diagnosis system based on machine learning according to claim 8, characterized in that: The step S5 further comprises: Step S51: When the upward force sensor subunit disposed on the upward rope tower detects the force, the upward timing subunit starts timing; Step S52: When the upward force sensor subunit detects that the force disappears, the upward timing subunit continues to time for 0.1 seconds and then stops, and the inclination detection submodule sets the angle α° between the rope above the tower and the tower at this time as the maximum angle between the rope above the tower and the tower; Step S53: When the downlink force sensor subunit disposed on the downlink rope tower detects the force, the downlink timing subunit starts timing; Step S54: when the downward force sensor subunit detects that the force disappears, the downward timing subunit continues to time for 0.1 seconds and then stops, and the inclination detection submodule sets the angle β° between the rope below the tower and the tower at this time as the maximum angle between the rope below the tower and the tower; Step S55: The change in the angle of the cableway when passing through the tower , the maximum tilt change angle that ensures safety when the cableway passes through the tower is θ1, and the minimum tilt change angle that ensures safety when passing through the tower is θ2. , it is determined that the rope erection of the tower has a failure risk.

10. The rail transit fault diagnosis system based on machine learning according to claim 9, characterized in that: The step S6 further comprises: Step S61: The cableway has a total of n towers. When n is an odd number, and The traction force between the two towers is the smallest; when n is an even number, the The actual traction force on the front and rear of the tower is the smallest, and the actual traction force on the tower is statistically , where f is the resistance of the cable car passing through each ropeway, and the actual traction f (n) between each tower is different. , then the cableway is judged to have a risk of failure, where f1 is the minimum traction force for the cable car to safely pass through the tower, and f2 is the maximum traction force for the cable car to safely pass through the tower; Step S62: Setting a safety factor A for the cable car passing through the tower. ,like , then the abnormal speed of the cable car when passing the tower is judged to be a misdiagnosis, where the safety parameter A can detect whether there is a problem with the cable car operation system, A0 is the minimum value of the cable car operation safety factor, and K is the unit conversion parameter.