Rail transit fault detection method and system

Abstract

The invention discloses a rail transit fault detection method and system, and relates to the technical field of rail transit fault detection.A data detection and collection module is responsible for collecting rail use and train operation conditions in a current detection area and a current detection period by using sensing and collection technologies; the track wear state reflecting unit is responsible for calculating and outputting a track wear degree GM, the fault probability predicting unit is responsible for calculating and outputting a fault probability predicted value YG, and the fault maintenance priority evaluating unit is responsible for calculating and outputting a maintenance priority GWP. According to the invention, by optimizing data collection and processing, the fault detection accuracy is improved, the maintenance priority evaluation and the established closed-loop feedback mechanism are scientifically maintained, and the fault detection efficiency is improved. The application of the method and the system is helpful for improving the safety and the stability of the rail transit, and provides a powerful guarantee for the rapid development of the urban rail transit system.

Description

Technical Field

[0001] The present invention relates to the technical field of rail transit fault detection, and in particular to a rail transit fault detection method and system. Background Art

[0002] With the rapid development of urban rail transit systems, the safety and stability of rail transit have become crucial factors. The rail transit system needs to ensure that trains run safely and efficiently in a complex operating environment and avoid any failures that may cause accidents or delays. Therefore, the development of efficient and accurate fault detection methods and technologies is of great significance to ensure the safe operation of the rail transit system.

[0003] However, existing technologies often rely on limited data sources and manual processing, resulting in incomplete data collection and untimely processing, which makes it difficult to accurately reflect the true status of the track. Due to problems with data collection and processing, fault detection in existing technologies often has errors, making it difficult to accurately predict and warn of faults. In addition, existing technologies often lack scientific maintenance priority assessment methods, resulting in unreasonable allocation of maintenance resources and unable to effectively ensure the safety and stability of the track. Existing technologies often lack a closed-loop feedback mechanism and cannot be adjusted and optimized in real time according to maintenance results and changes in track status. Summary of the invention

[0004] The purpose of the present invention is to provide a rail transit fault detection method to solve the problems raised in the above background technology.

[0005] To achieve the above-mentioned object, the present invention provides a rail transit fault detection method as follows, including a method for timely detection and maintenance adjustment of rail transit faults, including a data detection and collection module, a fault assessment and maintenance module and a maintenance plan formulation and execution module, wherein the fault assessment and maintenance module includes a unit for reflecting the track wear state, a unit for predicting the fault probability and a unit for assessing the fault maintenance priority;

[0006] The specific implementation is as follows:

[0007] Data detection and collection module: responsible for using sensing and collection technology to collect information about the current detection area and the use of tracks and train operations during the current detection cycle;

[0008] Track wear status reflection unit: responsible for receiving the current detection area and the track usage and train operation status during the current detection cycle, and using The calculation formula calculates the output track wear GM;

[0009] Failure probability prediction unit: responsible for using the track wear GM as the basis The calculation formula calculates the output fault probability prediction value YG;

[0010] Fault maintenance priority assessment unit: responsible for using the fault probability prediction value YG to The calculation formula calculates the output maintenance priority GWP;

[0011] Maintenance plan formulation and execution module: based on the maintenance priority GWP, the tracks in the current inspection area are ranked and maintenance plans are formulated and executed;

[0012] The equipment used in the data detection and collection module includes track pressure sensors, train weight sensors, and data acquisition and processing equipment;

[0013] The equipment used by the fault assessment and maintenance module includes computing and analysis equipment;

[0014] The equipment used in the maintenance plan formulation and execution module includes maintenance and monitoring equipment, track grinding machines, and track inspection vehicles.

[0015] Preferably, the calculation formula of the track wear state reflecting unit is as follows:

[0016]

[0017] WP = WT / ZT;

[0018] in:

[0019] GM is the track wear;

[0020] SY is the average daily usage times, which reflects the average daily usage times of the track in the current fault detection cycle;

[0021] L is the track length;

[0022] Z is the average train load, which reflects the average weight of all trains running on the track during the current fault detection cycle;

[0023] YC is the average daily running number, which reflects the average number of trains running on the track every day during the current fault detection cycle;

[0024] WP is the track maintenance frequency;

[0025] WT is the maintenance days, ZT is the fault detection cycle days;

[0026] m is the wear resistance coefficient of the track material;

[0027] To evaluate the effect of maintenance on slowing down track wear, track materials with a high wear coefficient m require less maintenance to maintain a good condition;

[0028] A high GM value reflects that the track is severely worn;

[0029] A low GM value indicates that the track is less worn.

[0030] Preferably, the calculation formula of the rail material wear resistance coefficient m is as follows:

[0031]

[0032] GG fanlt =SG / T;

[0033] k is a constant used to adjust the overall scale of the formula, and the value of k is a positive number;

[0034] JM is the initial wear resistance of the track material, which is known data and reflects the wear resistance of the track material under initial conditions;

[0035] SM is the service life of the track material;

[0036] WC is the maintenance cost;

[0037] GG fanlt is the historical failure probability;

[0038] SG is the actual number of failures, and T is the historical period;

[0039] a and b are both weight coefficients, and both are positive numbers less than 1;

[0040] a is used to adjust the influence of service life on the wear resistance coefficient m of the track material;

[0041] b is used to adjust the influence of failure probability on the wear resistance coefficient m of the track material.

[0042] Preferably, the calculation formula of the predicted failure probability unit is as follows:

[0043]

[0044] in:

[0045] YG is the predicted value of failure probability;

[0046] GM last time is the track wear degree of the previous cycle;

[0047] GM×(SY+Z) reflects the stability of the track under heavy load and high frequency use conditions;

[0048] To assess the wear of track per unit length;

[0049] JT is the time interval, which reflects the interval between the last fault detection cycle and the current fault detection cycle;

[0050] A high YG value indicates a high probability of track failure;

[0051] A low YG value indicates a low probability of track failure.

[0052] Preferably, the calculation formula for evaluating the fault maintenance priority unit is as follows:

[0053]

[0054] in:

[0055] GWP is the maintenance priority;

[0056] CL is the regional daily traffic volume, which reflects the daily traffic volume in the area where the track is located during the current fault detection cycle;

[0057] GM avg is the average track wear, GM avg Reflects the average degree of wear of all rails in the current fault detection cycle;

[0058] GM max is the maximum wear of the track, GM min is the minimum track wear, GM max and GM min Respectively reflect the maximum and minimum extent of all rail wear in the current fault detection cycle;

[0059] The increase in daily traffic volume CL in the central area means that the bearing pressure of the track increases, and the risk of wear and failure also increases accordingly. The historical failure probability GG fanlt The increase reflects the existing problems and hidden dangers in the track maintenance history;

[0060] The product term 10 in is specifically a magnification factor, which is intended to amplify the results of the maintenance priority GWP to quickly identify high priority tracks.

[0061] Preferably, the average track wear GM avg The calculation formula is as follows:

[0062] GM avg =(GM 1 +GM 2 +GM 3 +......+GM n ) / n;

[0063] n is the total number of orbits;

[0064] GM 1 is the wear degree of the first track, GM 2 is the wear degree of the second track, GM 3 is the wear degree of the third track, GM n is the wear degree of the nth track.

[0065] Preferably, based on the maintenance priority GWP, the fault maintenance adjustment after the maintenance priority GWP of all tracks in the current detection area is calculated and output is as follows:

[0066] First, the result values ​​are sorted according to the maintenance priority GWP of all tracks in the current detection area;

[0067] Secondly, the maintenance priority GWP is ranked from high to low

[0068] If the maintenance priority GWP is in the front of the median, that is, the track with a large result value, the maintenance frequency should be increased and the number of train operations should be reduced;

[0069] If the maintenance priority GWP is on a track that is later than the median value, that is, a track with a small result value, the maintenance frequency should be reduced and the number of train operations should be increased.

[0070] Preferably, before performing the calculation of the fault maintenance priority assessment unit for any track, the track wear GM of all tracks in the current detection area must be calculated and output, and then the calculated data of each track must be input into the fault maintenance priority assessment unit for calculation.

[0071] The present invention also provides a rail transit fault detection system, which solves the problems raised in the above background technology, including a data detection and collection module, a fault assessment and maintenance module, and a maintenance plan formulation and execution module.

[0072] The data detection and collection module is used to collect the use of tracks and train operation conditions in the current detection area and the current detection cycle;

[0073] The fault assessment and maintenance module is used to calculate and output the track wear GM, the fault probability prediction value YG, and the maintenance priority GWP in sequence;

[0074] The maintenance plan formulation and execution module is used to rank the tracks in the current inspection area and formulate and execute maintenance plans according to the maintenance priorities GWP.

[0075] Compared with the prior art, the present invention has the following beneficial effects:

[0076] 1. The present invention realizes the comprehensive collection of track usage data, train operation data and track material data by introducing advanced sensor technology and data acquisition equipment, and uses big data analysis and processing technology to pre-process and analyze the collected data to improve the accuracy and reliability of the data.

[0077] 2. The present invention is based on a unit reflecting the track wear state and a unit predicting the probability of failure, and uses a calculation formula to accurately calculate the track wear GM and the predicted value of the probability of failure YG, thereby realizing real-time monitoring and early warning of rail transit failures, and introducing new variables, including the track wear GM of the previous cycle last time and the time interval JT between two detections to further improve the accuracy of fault detection. Afterwards, the fault maintenance priority evaluation unit is used to comprehensively consider the failure probability, traffic flow, historical failure rate, and the relative difference between the wear of the track and its average value and the maximum and minimum values ​​to scientifically evaluate the maintenance priority of the track. The evaluation results are used to achieve the purpose of reasonable allocation of maintenance resources, ensure timely maintenance of high-priority tracks, and improve the safety and stability of the tracks.

[0078] 3. The present invention forms a closed-loop feedback mechanism by feeding back maintenance results and changes in track status to the data collection module, and adjusts and optimizes algorithm formulas and detection strategies in real time based on the feedback results, thereby improving rail transit fault detection and the overall performance and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 This is a method flow chart of the rail transit fault detection method and system;

[0080] Figure 2 Schematic diagram of the overall structure of the rail transit fault detection method and system;

[0081] Figure 3 This is a schematic diagram of the structure of the fault assessment and maintenance module of the present invention;

[0082] Figure 4 This is a schematic diagram of the adjustment of the rating maintenance strategy for the maintenance priority GWP in the present invention. DETAILED DESCRIPTION

[0083] 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.

[0084] The present rail transit fault detection method and system are different from the existing rail transit fault detection methods and systems. The existing rail transit fault detection methods and systems are not only inefficient, but also difficult to achieve real-time monitoring and early warning of track status, and thus difficult to form a circular feedback mechanism. The present algorithm unit effectively solves the problems and shortcomings of the existing technology by optimizing data collection and processing, improving fault detection accuracy, scientifically evaluating maintenance priorities, and establishing a closed-loop feedback mechanism. The application of this method and system will help improve the safety and stability of rail transit and provide strong guarantees for the rapid development of urban rail transit systems.

[0085] For example, see Figures 1 to 4 , This implementation provides a rail transit fault detection method, including a method for timely detection and maintenance adjustment of rail transit faults, including a data detection and collection module, a fault assessment and maintenance module and a maintenance plan formulation and execution module, wherein the fault assessment and maintenance module includes a unit for reflecting the track wear state, a unit for predicting the probability of faults and a unit for assessing the priority of fault maintenance;

[0086] The specific implementation is as follows:

[0087] Data detection and collection module: responsible for using sensing and collection technology to collect information about the current detection area and the use of tracks and train operations during the current detection cycle;

[0088] Track wear status reflection unit: responsible for receiving the current detection area and the track usage and train operation status during the current detection cycle, and using The calculation formula calculates the output track wear GM;

[0089] Failure probability prediction unit: responsible for using the track wear GM as the basis The calculation formula calculates the output fault probability prediction value YG;

[0090] Fault maintenance priority assessment unit: responsible for using the fault probability prediction value YG to The calculation formula calculates the output maintenance priority GWP;

[0091] Maintenance plan formulation and execution module: based on the maintenance priority GWP, the tracks in the current inspection area are ranked and maintenance plans are formulated and executed;

[0092] The equipment used in the data detection and collection module includes track pressure sensors, train weight sensors, and data acquisition and processing equipment;

[0093] The equipment used in the fault assessment and maintenance module includes computing and analysis equipment;

[0094] The equipment used in the maintenance plan formulation and execution module includes maintenance and monitoring equipment, track grinding machines, and track inspection vehicles.

[0095] See also Figures 1 to 4 ,This implementation provides a rail transit fault detection system including a data detection and collection module, a fault assessment and maintenance module, and a maintenance plan formulation and execution module.

[0096] In this embodiment, the system forms a complete rail transit fault detection and maintenance system through the cooperation of three algorithm units, combined with the three operation results of GM, YG and GWP. Through this system, timely detection and maintenance of rail transit faults can be achieved to ensure the safety and stability of rail transit. Specifically, GM is the track wear, which is an important parameter reflecting the current state of the track. The track wear is affected by many factors, including the average daily usage times SY, track length L, average train load Z, average daily operation times YC and track material wear resistance coefficient m. In addition, track maintenance frequency WP will also affect the wear. This is because regular maintenance can slow down the wear rate of the track. By comprehensively considering these factors, GM can calculate the track wear more accurately, thereby providing guidance for subsequent fault prediction and maintenance. GWP is the maintenance priority, and this value can evaluate the maintenance priority of different tracks, thereby providing the system with a scientific and reasonable basis for maintenance decision-making. At the same time, this evaluation result can also indirectly affect the track maintenance frequency WP and the average daily operation times YC in GM by affecting maintenance decisions, thereby forming a closed-loop feedback mechanism, so that the calculation results of GMP are fed back to the calculation of GM and YG, so that the three algorithms of this system play a vital role in the rail transit fault detection method and system. They not only have significant beneficial effects on their own, but also improve the overall performance and safety of the rail transit system through mutual correlation and cyclic influence.

[0097] See also Figures 1 to 4 , the calculation formula reflecting the track wear state unit is as follows:

[0098]

[0099] WP = WT / ZT;

[0100] in:

[0101] GM is the track wear;

[0102] SY is the average daily usage times, which reflects the average daily usage times of the track in the current fault detection cycle;

[0103] L is the track length;

[0104] Z is the average train load, which reflects the average weight of all trains running on the track during the current fault detection cycle;

[0105] YC is the average daily running number, which reflects the average number of trains running on the track every day during the current fault detection cycle;

[0106] WP is the track maintenance frequency;

[0107] WT is the maintenance days, ZT is the fault detection cycle days;

[0108] m is the wear resistance coefficient of the track material;

[0109] To evaluate the effect of maintenance on slowing down track wear, track materials with a high wear coefficient m require less maintenance to maintain a good condition;

[0110] A high GM value reflects that the track is severely worn;

[0111] A low GM value reflects that the track is lightly worn;

[0112] The calculation formula of rail material wear resistance coefficient m is as follows:

[0113]

[0114] GG fanlt =SG / T;

[0115] k is a constant used to adjust the overall scale of the formula, and the value of k is a positive number;

[0116] JM is the initial wear resistance of the track material, which is known data and reflects the wear resistance of the track material under initial conditions;

[0117] SM is the service life of the track material;

[0118] WC is the maintenance cost;

[0119] GG fanlt is the historical failure probability;

[0120] SG is the actual number of failures, and T is the historical period;

[0121] a and b are both weight coefficients, and both are positive numbers less than 1;

[0122] a is used to adjust the influence of service life on the wear resistance coefficient m of the track material;

[0123] b is used to adjust the influence of failure probability on the wear resistance coefficient m of the track material.

[0124] In this embodiment: First, in this algorithm unit The calculation part is intended to comprehensively consider the frequency of track use reflected by the product of the average daily use times SY and the track length L, as well as the influence of the average train load Z and the average daily running times YC on track wear. The square root operation is to smooth the data so that the results are more in line with the actual situation and convenient for subsequent calculations. As the main component of the track wear GM, the results of this part of the calculation directly reflect the degree of track wear caused by use and are the key indicators for evaluating the track status.

[0125] The calculation part is specifically the wear coefficient m of the track material divided by the track maintenance frequency WP, which aims to evaluate the effect of maintenance on slowing down track wear. Track materials with high wear coefficient m require fewer maintenance times to maintain a good condition. This part of the calculation, as a subtraction in the formula, reflects the effect of maintenance on slowing down track wear, which helps to more comprehensively evaluate the wear of the track.

[0126] In the calculation of the wear resistance coefficient m of the track material, a is the weight coefficient, which is used to adjust the influence of the service life on the wear resistance coefficient m of the track material. The value range of a usually depends on the relative importance of the track material service life SM and the maintenance cost WC in the wear resistance assessment. If the track material service life SM is the main consideration, the value of a will be relatively large. If the maintenance cost WC is the main consideration, the value of a will be relatively small. Generally speaking, the value range of a is a positive number and is usually less than 1, thereby ensuring that other factors in the formula can also affect the wear resistance coefficient m of the track material. b is also a weight coefficient, which is used to adjust the influence of the failure probability on the wear resistance coefficient m of the track material. The value range of b also depends on the historical failure probability GG fanlt The relative importance of wear resistance assessment is that if the historical failure probability GG fanlt is the main consideration, the value of b will be relatively large. If the historical failure probability GG fanlt It is not a major consideration. The value of b can be relatively small. Similar to a, the value range of b is usually a positive number and is usually less than 1 to ensure that other factors in the formula can also affect the wear resistance coefficient m of the track material.

[0127] The parameters in the track wear status unit of this algorithm include the average daily usage times SY, track length L, average train load Z, average daily running times YC, track material wear coefficient m, and track maintenance frequency WP. The combined calculation of these parameters directly reflects the track usage intensity and load conditions. By comprehensively considering these parameters, the track wear degree can be accurately calculated, thereby accurately evaluating the current state of the track;

[0128] The calculation result of this algorithm unit helps to timely detect the wear of the track. For severely worn tracks, maintenance and replacement can be arranged as a priority to ensure the safe operation of rail transit. The track maintenance frequency WP is an important parameter in the track wear status unit, which reflects the maintenance investment in the track. By combining the wear degree and the track maintenance frequency WP, a more scientific and reasonable maintenance plan can be formulated, and the optimized maintenance strategy can avoid excessive maintenance and insufficient maintenance, which can not only save maintenance costs but also ensure the long-term stable operation of the track. Timely track wear GM evaluation helps to discover potential safety hazards, and by accurately evaluating the track wear, the system can promptly discover and deal with these hazards, thereby ensuring the safety and stability of train operation.

[0129] See also Figures 1 to 4 , the calculation formula for predicting the failure probability unit is as follows:

[0130]

[0131] in:

[0132] YG is the predicted value of failure probability;

[0133] GM last time is the track wear degree of the previous cycle;

[0134] GM×(SY+Z) reflects the stability of the track under heavy load and high frequency use conditions;

[0135] To assess the wear of track per unit length;

[0136] JT is the time interval, which reflects the interval between the last fault detection cycle and the current fault detection cycle;

[0137] A high YG value indicates a high probability of track failure;

[0138] A low YG value indicates a low probability of track failure.

[0139] In this embodiment, firstly, the calculation part of "GM×(SY+Z)" combines the track wear GM with the average daily usage times YC and the average train load Z, aiming to evaluate the failure risk of the track when it is subjected to a greater load. As an important factor in the calculation of the failure probability prediction value YG, this part reflects the stability of the track under heavy load and high frequency of use, which helps to predict potential failures.

[0140] The calculation part specifically uses the track wear GM of the previous cycle last time Divided by the time interval JT between two inspections, it aims to evaluate the wear rate and wear trend. This part of the calculation is a subtraction of the failure probability prediction value YG, reflecting the impact of track wear rate on failure probability, which helps to predict future failure conditions;

[0141] The prediction failure probability unit of this algorithm introduces the track wear degree GM of the previous cycle on the basis of the track wear state unit. last time and the time interval between two tests JT, these two parameters are crucial to predicting the failure probability prediction value YG;

[0142] By comprehensively considering these parameters, this algorithm unit can calculate the fault probability prediction value YG and issue an early warning before the fault occurs, which provides the system with sufficient time to prepare and respond, thereby reducing the impact of the fault on the rail transit system;

[0143] According to the changes in the predicted value of the failure probability YG, the system can dynamically adjust the maintenance plan. Specifically, when the predicted value of the failure probability YG is high, the maintenance frequency and intensity can be increased. When the predicted value of the failure probability YG is low, the maintenance investment can be appropriately reduced. This dynamic adjustment strategy helps to ensure that necessary maintenance measures are taken before a failure occurs, which can save maintenance costs and improve the stability and reliability of the system.

[0144] In addition, by accurately predicting the fault probability prediction value YG, the system can more accurately determine which tracks need priority maintenance and which tracks can temporarily postpone maintenance. This accurate prediction strategy helps avoid unnecessary maintenance operations and improves maintenance efficiency. At the same time, it can also ensure that high-priority tracks are maintained in a timely manner, reducing train delays and shutdowns caused by track failures.

[0145] See also Figures 1 to 4 , the calculation formula for evaluating the fault maintenance priority unit is as follows:

[0146]

[0147] in:

[0148] GWP is the maintenance priority;

[0149] CL is the regional daily traffic volume, which reflects the daily traffic volume in the area where the track is located during the current fault detection cycle;

[0150] GM avg is the average track wear, GM avg Reflects the average degree of wear of all rails in the current fault detection cycle;

[0151] GM max is the maximum wear of the track, GM min is the minimum track wear, GM max and GM min Respectively reflect the maximum and minimum extent of all rail wear in the current fault detection cycle;

[0152] The increase in daily traffic volume CL in the central area means that the bearing pressure of the track increases, and the risk of wear and failure also increases accordingly. The historical failure probability GG fanlt The increase reflects the existing problems and hidden dangers in the track maintenance history;

[0153] The product term 10 in is specifically an amplification factor, which is intended to amplify the results of the maintenance priority GWP to quickly identify high-priority tracks;

[0154] Average track wear GM avg The calculation formula is as follows:

[0155] GM avg =(GM 1 +GM 2 +GM 3 +......+GM n ) / n;

[0156] n is the total number of orbits;

[0157] GM 1 is the wear degree of the first track, GM 2 is the wear degree of the second track, GM 3 is the wear degree of the third track, GM n is the wear degree of the nth track.

[0158] In this embodiment, the algorithm unit first The product of the calculation part is intended to determine the maintenance priority GWP by comprehensively considering the failure risk, traffic importance and historical failure conditions of the track. As one of the main components of the maintenance priority GWP, this part of the calculation reflects the importance and failure risk of the track in traffic and is a key factor in evaluating maintenance priority;

[0159] The calculation part evaluates the relative difference between the current track wear GM and the overall wear level by comparing the difference between the average value of the track and the current track wear GM to the maximum and minimum values ​​of wear. This calculation, as one of the components of the maintenance priority GWP, reflects the relative severity of track wear and helps to identify the track that needs the most maintenance among multiple tracks. The "×10" calculation is a simple magnification factor, which is designed to make the results of the maintenance priority GWP more significant, so as to facilitate the rapid identification of high-priority tracks in practical applications. The magnification factor makes the results of the maintenance priority GWP more intuitive and easy to understand, which helps to respond quickly in actual maintenance decisions.

[0160] The fault maintenance priority evaluation unit in this algorithm unit combines the fault probability prediction value YG, the regional daily traffic volume CL, and the historical fault probability GG fanlt The maintenance priority GWP is comprehensively evaluated based on multiple factors such as the relative difference between the track wear GM and its average value and the maximum and minimum values. By evaluating the maintenance priority GWP, the system can allocate maintenance resources more scientifically. For high-priority tracks, maintenance and replacement can be arranged first, and for low-priority tracks, maintenance plans can be appropriately postponed. This strategy helps to ensure the effective use of maintenance resources;

[0161] This algorithm unit can reduce train delays and outages caused by track failures by giving priority to maintaining high-priority tracks, which is crucial to improving the overall operating efficiency of the rail transit system. By optimizing the maintenance priority evaluation strategy, it can reduce the impact of failures on the rail transit system and improve the stability and reliability of the system, which helps to improve passenger satisfaction and travel efficiency.

[0162] In addition, a scientific and reasonable maintenance priority assessment strategy can help enhance the overall stability of the rail transit system. By prioritizing the maintenance of key components and wearing parts, it can reduce the probability of system failure and enhance system stability, which in turn helps to improve the safety and reliability of the rail transit system, which is of great significance for protecting the lives and property of passengers.

[0163] See also Figures 1 to 4 , based on the maintenance priority GWP, and the maintenance priority GWP of all tracks in the current detection area are calculated and output, the fault maintenance adjustment is as follows:

[0164] First, the result values ​​are sorted according to the maintenance priority GWP of all tracks in the current detection area;

[0165] Secondly, the maintenance priority GWP is ranked from high to low

[0166] If the maintenance priority GWP is in the front of the median, that is, the track with a large result value, the maintenance frequency should be increased and the number of train operations should be reduced;

[0167] If the maintenance priority GWP is on a track that is later than the median value, that is, a track with a small result value, the maintenance frequency should be reduced and the number of train operations should be increased.

[0168] In this embodiment, the result GWP of evaluating the fault maintenance priority unit can be fed back to the unit reflecting the track wear state, affecting the setting of the track maintenance frequency WP, thereby forming a closed-loop feedback mechanism. This mechanism helps to continuously optimize the maintenance strategy and improve the maintenance effect. According to the change of the maintenance priority GWP, the train operation plan can be dynamically adjusted, including reducing the number of train operations on high-priority tracks and adjusting the operation time period to reduce the probability of failure. By evaluating the cyclic impact of the fault maintenance priority unit on the unit reflecting the track wear state, the rail transit system can better adapt to changes in the external environment and fluctuations in the internal state, thereby maintaining the stability and safety of the system. In addition, by reflecting the track wear state unit and predicting the fault probability unit, the wear degree and fault probability of the track can be accurately quantified, providing a scientific basis for formulating maintenance plans. Such accurate evaluation helps to avoid excessive maintenance and insufficient maintenance, thereby improving maintenance efficiency and reducing costs.

[0169] Specifically, according to the maintenance priority GWP calculated by the fault maintenance priority unit, the maintenance plan can be dynamically adjusted to ensure that high-priority tracks are maintained in a timely manner. This dynamic adjustment mechanism helps to adapt to changes in track status and changes in operating requirements, thereby improving the safety and stability of the track. By regularly adjusting the maintenance plan in real time, maintenance resources can be reasonably allocated to ensure efficient use of resources. This optimized resource allocation helps to reduce maintenance costs and improve maintenance efficiency.

[0170] This unit will also regularly adjust the maintenance plan in real time, and adjust the number of train trips and operating speed parameters according to the track status and operating needs. This adjustment helps to improve the operating efficiency of the track while ensuring safety and meet the growing traffic needs. Through accurate evaluation and dynamic adjustment of maintenance plans, potential safety hazards can be discovered and dealt with in a timely manner to prevent major accidents.

[0171] In summary, combining the maintenance priority GWP calculated by the unit reflecting the track wear status, the unit predicting the failure probability, and the unit evaluating the failure maintenance priority and making regular real-time adjustments to the maintenance plan has multiple beneficial effects such as accurately evaluating the track status, dynamically adjusting the maintenance plan, optimizing resource allocation, improving the track operation efficiency, and preventing major accidents. This maintenance mechanism helps to improve the long-term safe operation level of the track and reduce maintenance costs.

[0172] For example 2, please refer to Figures 1 to 4 Before any track is calculated in the fault maintenance priority evaluation unit, the track wear GM of all tracks in the current detection area must be calculated and output, and then the calculated data of each track must be input into the fault maintenance priority evaluation unit for calculation.

[0173] In this embodiment, the average track wear GM is involved in evaluating the fault maintenance priority unit. avg Therefore, a mechanism is set up to calculate and output the track wear GM of all tracks in the current detection area one by one before evaluating the fault maintenance priority unit, and then calculate the maintenance priority GWP of each track. This mechanism can also achieve the purpose of outputting the maintenance priority GWP of the tracks in the current detection area at the same time, thereby speeding up the priority ranking evaluation of the tracks and ensuring the smooth progress of rail transit fault detection.

[0174] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A rail transit fault detection method, characterized in that: A method for timely detection and maintenance adjustment of rail transit faults, characterized in that it includes a data detection and collection module, a fault assessment and maintenance module, and a maintenance plan formulation and execution module, wherein the fault assessment and maintenance module includes a track wear state reflection unit, a fault probability prediction unit, and a fault maintenance priority assessment unit; The specific implementation is as follows: Data detection and collection module: responsible for using sensing and collection technology to collect information about the current detection area and the use of tracks and train operations during the current detection cycle; Track wear status reflection unit: responsible for receiving the current detection area and the track usage and train operation status in the current detection cycle, and calculating and outputting the track wear degree GM; Prediction failure probability unit: responsible for calculating and outputting the predicted failure probability value YG based on the track wear GM; Fault maintenance priority evaluation unit: responsible for calculating and outputting the maintenance priority GWP based on the fault probability prediction value YG; Maintenance plan formulation and execution module: Based on the maintenance priority GWP, the tracks in the current inspection area are ranked and maintenance plans are formulated and executed.

2. A rail transit fault detection method according to claim 1, characterized in that: The equipment used in the data detection and collection module includes track pressure sensors, train weight sensors, and data acquisition and processing equipment; The equipment used by the fault assessment and maintenance module includes computing and analysis equipment; The equipment used by the maintenance plan formulation and execution module includes maintenance and monitoring equipment, track grinding machines, and track inspection vehicles.

3. A rail transit fault detection method according to claim 2, characterized in that: The calculation formula of the track wear state unit is as follows: WP = WT / ZT; in: GM is the track wear; SY is the average daily usage times, which reflects the average daily usage times of the track in the current fault detection cycle; L is the track length; Z is the average train load, which reflects the average weight of all trains running on the track during the current fault detection cycle; YC is the average daily running number, which reflects the average number of trains running on the track every day during the current fault detection cycle; WP is the track maintenance frequency; WT is the maintenance days, ZT is the fault detection cycle days; m is the wear resistance coefficient of the track material; To evaluate the effect of maintenance on slowing down track wear, track materials with a high wear coefficient m require less maintenance to maintain a good condition; A high GM value reflects that the track is severely worn; A low GM value indicates that the track is lightly worn.

4. A rail transit fault detection method according to claim 3, characterized in that: The calculation formula of the rail material wear resistance coefficient m is as follows: GG fanlt =SG / T; k is a constant used to adjust the overall scale of the formula, and the value of k is a positive number; JM is the initial wear resistance of the track material, which is known data and reflects the wear resistance of the track material under initial conditions; SM is the service life of the track material; WC is the maintenance cost; GG fanlt is the historical failure probability; SG is the actual number of failures, and T is the historical period; a and b are both weight coefficients, and both are positive numbers less than 1; a is used to adjust the influence of service life on the wear resistance coefficient m of the track material; b is used to adjust the influence of failure probability on the wear resistance coefficient m of the track material.

5. A rail transit fault detection method according to claim 4, characterized in that: The calculation formula of the predicted failure probability unit is as follows: in: YG is the predicted value of failure probability; GM lasttime is the track wear degree of the previous cycle; GM×(SY+Z) reflects the stability of the track under heavy load and high frequency use conditions; To assess the wear of track per unit length; JT is the time interval, which reflects the interval between the last fault detection cycle and the current fault detection cycle; A high YG value indicates a high probability of track failure; A low YG value indicates a low probability of track failure.

6. A rail transit fault detection method according to claim 5, characterized in that: The calculation formula for evaluating the fault maintenance priority unit is as follows: in: GWP is the maintenance priority; CL is the regional daily traffic volume, which reflects the daily traffic volume in the area where the track is located during the current fault detection cycle; GM avg is the average wear of the track, GM avg Reflects the average degree of wear of all rails in the current fault detection cycle; GM max is the maximum wear of the track, GM min is the minimum track wear, GM max and GM min Respectively reflect the maximum and minimum extent of all rail wear in the current fault detection cycle; The increase in daily traffic volume CL in the central area means that the bearing pressure of the track increases, and the risk of wear and failure also increases accordingly. The historical failure probability GG fanlt The increase reflects the existing problems and hidden dangers in the track maintenance history; The product term 10 in is a magnification factor that is intended to amplify the maintenance priority GWP results to quickly identify high priority tracks.

7. A rail transit fault detection method according to claim 6, characterized in that: The average track wear GM avg The calculation formula is as follows: GM avg =(GM1+GM2+GM3+......+GM n ) / n; n is the total number of orbits; GM1 is the wear degree of the first track, GM2 is the wear degree of the second track, GM3 is the wear degree of the third track, and GM n is the wear degree of the nth track.

8. A rail transit fault detection method according to claim 6, characterized in that: Based on the maintenance priority GWP, the fault maintenance adjustment after the maintenance priority GWP of all tracks in the current detection area is calculated and output is as follows: First, the result values ​​are sorted according to the maintenance priority GWP of all tracks in the current detection area; Secondly, the maintenance priority GWP is ranked from high to low If the maintenance priority GWP is in the front of the median, that is, the track with a large result value, the maintenance frequency should be increased and the number of train operations should be reduced; If the maintenance priority GWP is on a track that is later than the median value, that is, a track with a small result value, the maintenance frequency should be reduced and the number of train operations should be increased.

9. A rail transit fault detection method according to claim 7, characterized in that: Before any track performs calculations in the fault maintenance priority assessment unit, it is necessary to calculate and output the track wear GM of all tracks in the current detection area, and then input the calculated data of each track into the fault maintenance priority assessment unit for calculation.

10. The detection system used in the rail transit fault detection method according to claim 1, characterized in that: It includes data detection and collection module, fault assessment and maintenance module and maintenance plan formulation and execution module; The data detection and collection module is used to collect the use of tracks and train operation conditions in the current detection area and the current detection cycle; The fault assessment and maintenance module is used to calculate and output the track wear GM, the fault probability prediction value YG, and the maintenance priority GWP in sequence; The maintenance plan formulation and execution module is used to rank the tracks in the current inspection area and formulate and execute maintenance plans according to the maintenance priorities GWP.

Images