Rail system reliability determination method and device

Abstract

The invention discloses a method and a device for determining the reliability of a track system. The method comprises the following steps: acquiring multi-source track state detection data of a target track line; based on the multi-source track state detection data, defect information reflecting the abnormal state of the track component is identified and obtained; dividing the target track line into a plurality of continuous unit sections, and for each unit section, based on the defect information, respectively calculating a steel rail component defect rate, a fastener component defect rate and a track plate or mortar layer component defect rate; adopting a Weibull distribution model to respectively calculate the reliability of each part in the preset working time; and determining the reliability of the track system in the corresponding unit section based on the calculated reliability of each component. Reliability evaluation of the track system and components thereof can be realized, and safe and reliable operation of a line is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of high-speed railway engineering technology, and in particular to a method and apparatus for determining the reliability of track systems. Background Technology

[0002] This section is intended to provide background or context for the embodiments of the invention set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section.

[0003] As the operating hours of high-speed railways increase, the track system, as the core load-bearing structure for train operation, has an increasingly prominent impact on operational safety and efficiency due to its long-term performance and reliability. Ballastless track, with its excellent stability and smoothness, has become the mainstream track structure for high-speed railways.

[0004] To ensure the safe and reliable operation of facilities, reliability assessment and predictive maintenance technologies have received widespread attention. Existing research on track system reliability mainly focuses on two approaches: first, analyzing structural reliability under specific environmental conditions based on simulation models and theoretical assumptions; second, evaluating the overall reliability level of the system using reliability theory models based on historical operation and maintenance statistics.

[0005] However, the aforementioned existing technological approaches still have limitations. Simulation methods struggle to fully reflect the complex long-term operating conditions of actual railway lines; while methods based on historical statistics rely heavily on maintenance records, failing to adequately represent the physical damage to track components. Currently, the railway industry has accumulated high-precision dynamic detection data on track geometry, surface images, and internal damage through equipment such as integrated inspection vehicles, patrol vehicles, and flaw detectors. This data directly reflects the microscopic physical state of the track system. However, existing technologies struggle to effectively utilize this multi-source dynamic detection data to accurately assess the reliability of the track system and its components, resulting in the inability to precisely locate vulnerable sections and impacting subsequent track system maintenance decisions. Summary of the Invention

[0006] This invention provides a method for determining the reliability of a track system, used to assess the reliability of the track system and its components, ensuring the safe and reliable operation of the line. The method includes:

[0007] Acquire multi-source track condition detection data for the target track line;

[0008] Based on multi-source track condition detection data, defect information reflecting abnormal conditions of track components is identified;

[0009] The target track line is divided into multiple continuous unit segments. For each unit segment, based on the defect information, the defect rate of rail components, the defect rate of fastener components, and the defect rate of track slab or mortar layer components are calculated respectively.

[0010] Based on the calculated defect rates of rail components, fastener components, and track slab or mortar layer components, the reliability of each component within the preset working time is calculated using the Weibull distribution model.

[0011] Based on the calculated reliability of each component, the reliability of the track system within the corresponding unit section is determined.

[0012] This invention also provides a track system reliability determination device for assessing the reliability of track systems and their components, ensuring the safe and reliable operation of the line. The device includes:

[0013] The data acquisition module is used to acquire multi-source track status detection data of the target track line;

[0014] The defect information identification module is used to identify defect information reflecting abnormal conditions of track components based on multi-source track condition detection data.

[0015] The component defect rate calculation module is used to divide the target track line into multiple continuous unit segments. For each unit segment, based on the defect information, the defect rate of rail components, fastener components, and track slab or mortar layer components are calculated respectively.

[0016] The component reliability calculation module is used to calculate the reliability of each component within a preset working time based on the calculated defect rates of rail components, fastener components, and track slab or mortar layer components, using the Weibull distribution model.

[0017] The track system reliability calculation module is used to determine the reliability of the track system within the corresponding unit section based on the calculated reliability of each component.

[0018] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for determining the reliability of an orbital system.

[0019] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for determining the reliability of an orbital system.

[0020] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method for determining the reliability of an orbital system.

[0021] In this embodiment of the invention, multi-source track condition detection data of the target track line is acquired; based on the multi-source track condition detection data, defect information reflecting abnormal states of track components is identified; the target track line is divided into multiple continuous unit segments; for each unit segment, based on the defect information, the defect rates of rail components, fastener components, and track slab or mortar layer components are calculated; based on the calculated defect rates of rail components, fastener components, and track slab or mortar layer components, the reliability of each component within a preset working time is calculated using the Weibull distribution model; based on the calculated reliability of each component, the reliability of the track system within the corresponding unit segment is determined. In the above process, the embodiments of the present invention acquire multi-source track condition detection data of the target track line and identify defect information reflecting the abnormal state of each component, providing a data basis for subsequent evaluation reflecting physical damage. Furthermore, by dividing the target track line into multiple continuous unit segments and calculating the defect rate of different components such as rails, fasteners, track slabs, or mortar layers for each segment based on defect information, a refined evaluation of the micro-state of the components is achieved. On this basis, the reliability of each component within a preset working time is calculated using the Weibull distribution model, quantifying the defect rate into reliability. Finally, based on the calculated reliability of each component, the reliability of the track system within the corresponding unit segment is determined, realizing the conversion from component-level reliability to system-level reliability. This enables precise location of weak reliability sections, providing direct and quantitative technical support for preventive maintenance and precise repair decisions of the track system. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0023] Figure 1 This is a flowchart of the method for determining the reliability of a track system in an embodiment of the present invention;

[0024] Figure 2 This is a flowchart illustrating the calculation of the defect rate of rail components in an embodiment of the present invention;

[0025] Figure 3 This is a flowchart illustrating the calculation of the defect rate of fastener components in an embodiment of the present invention;

[0026] Figure 4 This is a flowchart for calculating the defect rate of track slab or mortar layer components in an embodiment of the present invention;

[0027] Figure 5 This is a schematic diagram of the track system reliability determination device in an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0029] Figure 1 This is a flowchart of a method for determining the reliability of an orbital system according to an embodiment of the present invention. The method includes:

[0030] Step 101: Obtain multi-source track status detection data for the target track line;

[0031] Step 102: Based on multi-source track condition detection data, identify defect information reflecting abnormal conditions of track components;

[0032] Step 103: Divide the target track line into multiple continuous unit segments. For each unit segment, calculate the defect rate of rail components, fastener components, and track slab or mortar layer components based on the defect information.

[0033] Step 104: Based on the calculated defect rates of rail components, fastener components, and track slab or mortar layer components, the reliability of each component within the preset working time is calculated using the Weibull distribution model.

[0034] Step 105: Based on the calculated reliability of each component, determine the reliability of the track system within the corresponding unit section.

[0035] Each step is explained in detail below.

[0036] In step 101, multi-source track status detection data of the target track line are acquired.

[0037] In a specific embodiment, the multi-source track condition detection data includes track geometric condition detection data, track shortwave condition and vehicle dynamic response detection data, track component appearance image detection data, and rail internal damage detection data. The corresponding acquisition methods are as follows:

[0038] Track geometry condition detection data acquisition: Using the track geometry detection system mounted on the high-speed integrated inspection train, the geometric parameters such as track elevation, track alignment, track gauge, level, and triangular pits are continuously measured and acquired at the train's normal operating speed.

[0039] Track short-wave condition and vehicle dynamic response detection data acquisition: Using a vehicle axle box acceleration detection system installed on the same high-speed integrated inspection train, the vertical and lateral vibration acceleration signals of the axle boxes are collected in real time during train operation. Through time-frequency domain analysis of these signals, track impact index and rail corrugation index, among other track short-wave condition vehicle dynamic response indices, are calculated. These indices can effectively identify short-wave irregularities on the rail surface, such as poor weld joints and rail corrugation defects.

[0040] Track component appearance image inspection data acquisition: Utilizing the track condition inspection system mounted on the integrated inspection vehicle. This system employs a high-resolution linear scan camera combined with an infrared laser light source to continuously acquire high-definition two-dimensional images of the rail surface, track slab surface, and fasteners. Through built-in computer vision algorithms, the images are automatically analyzed and identified, enabling the detection of appearance defects such as rail surface scratches, track slab cracks or spalling, and missing or damaged fasteners. It also associates each identified defect with precise track mileage location information.

[0041] Data acquisition for internal rail damage detection: A multi-channel ultrasonic flaw detection system is used on a rail flaw detection vehicle. The vehicle is self-powered. Multiple ultrasonic probes at different angles are arranged on its underside to emit ultrasonic waves into the rail and receive the reflected echoes. By analyzing the B-scan images formed from the echo signals, the system effectively identifies and locates internal rail damage such as core defects, cracks, and holes, and provides information on the type, size, and location of the damage.

[0042] The above four types of detection data together constitute multi-source track condition detection data. They comprehensively and directly depict the real-time physical condition of the track system and its key components from four dimensions: geometric smoothness, dynamic response characteristics, surface visual condition, and internal structural integrity, providing a data foundation for subsequent defect identification and reliability assessment.

[0043] In step 102, based on multi-source track condition detection data, defect information reflecting abnormal conditions of track components is identified.

[0044] Before identifying defect information reflecting abnormal states of track components based on multi-source track condition detection data, the process includes:

[0045] The multi-source orbital condition detection data is deduplicated to eliminate duplicate records of the same physical defect in different detection data.

[0046] In a specific embodiment, the defect information includes track short-wave irregularities, apparent defects, and internal defects. Track short-wave irregularities are identified based on detection data reflecting the vehicle's dynamic response; apparent defects of rails, track slabs, and fasteners are identified based on analysis of track and component appearance image data; and internal defects of rails are identified based on analysis of rail internal condition detection data.

[0047] In step 103, the target track line is divided into multiple continuous unit segments. For each unit segment, based on the defect information, the defect rate of rail components, the defect rate of fastener components, and the defect rate of track slab or mortar layer components are calculated respectively.

[0048] Figure 2 This is a flowchart illustrating the calculation of the defect rate of rail components in an embodiment of the present invention. In one embodiment, the calculation of the defect rate of rail components includes:

[0049] Step 201: Based on the defect information, obtain the first number of rail defects marked as repairable and the second number of rail defects marked as unrepairable within the unit segment.

[0050] Step 202: Calculate the first defect rate based on the ratio of the first quantity to the unit segment length;

[0051] Step 203: Calculate the second defect rate based on the ratio of the second quantity to the number of rail strands in the unit section;

[0052] Step 204: Determine the defect rate of the rail components based on the first defect rate and the second defect rate.

[0053] In a specific embodiment, taking a high-speed railway section as an example, the rail defect information of this section was identified through multi-source data in the most recent inspection cycle as follows: Based on image recognition, a rail surface scratch was found (marked as repairable). Based on axle box acceleration analysis, a significant rail corrugation section was identified (marked as repairable). Based on ultrasonic testing, a nuclear flaw with an equivalent size exceeding the limit was detected inside the left rail (marked as unrepairable, requiring rail replacement).

[0054] Based on the above defect information statistics, the number of rail defects marked as repairable (first quantity) is 2; the number of rail defects marked as unrepairable (second quantity) is 1.

[0055] Repairable defect rate (first defect rate) = number of defects / segment length statistics.

[0056] Unrepairable defect rate (second defect rate) = number of defects / number of rail strands. This section includes the left and right rails.

[0057] The total defect rate of rail components is a combination of the two types of defect rates mentioned above. In this embodiment, the comprehensive defect rate of rail components in this section is obtained by weighting or summing, and is used as input for the subsequent Weibull distribution model. Through this process, the detection results (scratches, corrugations, and nuclear defects) with three different physical meanings—image, vibration, and ultrasonic—are uniformly quantified into a defect rate index characterizing the failure probability of the rail in this section.

[0058] Figure 3 This is a flowchart illustrating the calculation of the fastener component defect rate in an embodiment of the present invention. In one embodiment, calculating the fastener component defect rate includes:

[0059] Step 301: Based on the defect information, obtain the number of fastener defects within the unit section;

[0060] Step 302: Calculate the fastener component defect rate based on the ratio of the number of defective fasteners to the total number of fasteners in the unit section.

[0061] In a specific embodiment, for the same unit section, the total number of fasteners is determined to be 154 sets according to the design drawings. Based on the defect information provided by the inspection image recognition system, a total of 1 broken fastener spring clip and 1 damaged pad were identified in this section. The total number of fastener defects in this section is 2.

[0062] According to the fastener defect rate calculation formula: λ_fastener = N_fastener / N_total, where N_total is the total number of fasteners in this section, 154 sets. Substituting, we get: λ_fastener = 2 / 154 ≈ 0.013. This value indicates that the average probability of a defect in each fastener within this section is approximately 0.013. Thus, the apparent defects (broken spring clips, damaged pads) identified by image recognition are quantified into a unified probability index.

[0063] Figure 4 This is a flowchart illustrating the calculation of the defect rate of track slab or mortar layer components in an embodiment of the present invention. In one embodiment, calculating the defect rate of track slab or mortar layer components includes:

[0064] Step 401: Based on the defect information, obtain the number of defects in the track slab or mortar layer within the unit section;

[0065] Step 402: Calculate the defect rate of the track slab or mortar layer components based on the ratio of the number of defects in the track slab or mortar layer to the length of the unit section.

[0066] In a specific embodiment, the rail defect rate is calculated by summing two cases. For repairable defects, it is calculated based on the number of defects per 100 meters: if the appearance system detects one rail corrugation on the rail surface at a certain location, and the surface system detects one impact defect and preliminarily infers it to be rail abrasion, then the corresponding defect rate is:

[0067]

[0068] For cases that are irreparable (requiring rail replacement), the calculation is based on the number of rails: for example, if a crack appears in a left rail, the defect rate for that 100-meter section of rail is... This will directly lead to the track system failing to meet reliability standards. The calculation of rail defect rate relies on the rail surface, appearance, and internal damage detection system, and the detection deviation needs to exclude repeated locations detected within the same ten-day period. Defects detected at the same location in different ten-day periods are considered as multiple locations.

[0069] Fastener defect rate The calculation is based on the number of defects per 100 meters of the line: 154 sets of fasteners are used per 100 meters (intervals of 0.65m; if the interval is 0.6m, then there are 167 sets). If one fastener has a crack or a damaged backing plate, the corresponding defect rate for that fastener is... Its calculations rely on a fastener defect detection system.

[0070] The defect rate of the mortar layer, track slab, track bed slab, and base is calculated using the number of defects per 100 meters. The calculation of the defect rate relies on the Level III deviation of the track geometry smoothness detection system and the track slab surface defect detection system.

[0071] The above process enables the degradation of completely different types of components, such as rails, fasteners, and track slabs, to be measured using the common indicator of defect rate, laying the foundation for system-level reliability calculation.

[0072] In step 104, based on the calculated defect rates of rail components, fastener components, and track slab or mortar layer components, the reliability of each component within the preset working time is calculated using the Weibull distribution model.

[0073] In one embodiment, the reliability of each component within a preset operating time is calculated using the Weibull distribution model, including:

[0074] The scale parameters of the Weibull distribution are determined based on the defect rate corresponding to each component.

[0075] By substituting the scale parameter and the preset working time into the Weibull distribution reliability function, the reliability of the corresponding component within the preset working time can be calculated.

[0076] In a specific embodiment, the defect rate of each component of the track system changes with its service time, so its distribution is no longer an exponential distribution, but follows a Weibull distribution. That is, when each component is in the "early failure period" (defect rate decreases over time, such as during the break-in period of a new product) or the "wear and tear failure period" (defect rate increases over time, such as during the aging of mechanical parts), the defect rate... The reliability is no longer constant. In this case, the Weibull distribution needs to be used to describe the reliability (the exponential distribution is a special case of the Weibull distribution). The relationship between the defect rate and the scale parameter and shape parameter of the Weibull distribution is as follows:

[0077]

[0078] In one embodiment, the reliability of the corresponding component within a preset operating time is calculated according to the following Weibull distribution reliability function:

[0079] ;

[0080] in, Let t represent the reliability of the i-th component, and t represent the preset operating time. The shape parameter is used to characterize the changing trend of the track defect rate; Let be the scale parameter of the i-th component. Early failure period (defect rate decreases over time); : Random failure period (defect rate is constant, degenerates into an exponential distribution, at this time) Wear and tear failure period (defect rate increases over time);

[0081] In a specific embodiment, considering the current service life of high-speed railways, they may be in a period of occasional failures. Therefore, for the various components of the ballastless track system, .

[0082]

[0083] Therefore, if the defect rate at a certain time t is known... It can be calculated by combining the above formula. Then substitute it into the reliability formula.

[0084] For example, in a 100m long track section, if a fastener breaks in the fifth year of operation, what is its defect rate? , and thus Then the reliability of this segment in the 5th year is The reliability in the 10th year is .

[0085] However, due to the differences in the track foundation of each section of each line (such as roadbed, bridges, tunnels, curves, etc.), the probability of defects occurring varies significantly at different locations. Therefore, the dimensional parameters... There will also be significant differences. Therefore, we divide the sections according to their length. If each segment is 100m long, then the scale parameters are... It will become This makes the reliability assessment of the orbital system more practically significant.

[0086] In a specific embodiment, long-term operation leads to a gradual increase in system defects year by year. The transition from an accidental failure period to a wear-out failure period needs to be predicted based on the long-term accumulation of defects. For example, the defect rates of a certain component of the orbital system in year N and year N+1 were tracked and obtained. as well as Then we can get two equations:

[0087]

[0088] Solving for each yields and Afterwards, if In the N+1 year, the component at that location will enter the wear and tear failure period, and its reliability will change significantly.

[0089] In step 105, the reliability of the track system within the corresponding unit section is determined based on the calculated reliability of each component.

[0090] In one embodiment, the reliability of the track system within the corresponding unit segment is determined based on the calculated reliability of each component, including:

[0091] The reliability of the track system within the corresponding unit section is obtained by multiplying the reliability of the rail components, the reliability of the fastener components, and the reliability of the track slab or mortar layer components.

[0092] In a specific embodiment, the reliability of the orbital system can be expressed as:

[0093] ;

[0094] For the reliability of the orbital system; Let be the reliability of the i-th component; n is the number of components.

[0095] If the lifetimes of each component follow an exponential distribution, and other methods such as dynamic Bayesian networks, Wiener processes, and Gamma processes exist, then:

[0096]

[0097] The system's defect rate; Let be the defect rate of the i-th component.

[0098] In reliability calculations for tandem systems, the reliability of each component is equally important, and the track system is an approximate tandem system. Therefore, based on the above method and the Weibull distribution function, a reliability assessment formula for ballastless track systems is proposed:

[0099] During the period of occasional failure:

[0100]

[0101] n represents the number of units in which the line is divided into 100m sections.

[0102] Early failure period and deterioration failure period:

[0103] ;

[0104] in, Let the reliability of the j-th unit segment be , Let be the scale parameter of the j-th unit segment, and be . Let be the scale parameter of the i-th component in the j-th unit segment. The shape parameters of the i-th component in the j-th unit segment.

[0105] By calculating and comparing the reliability of the track system in different unit sections, weak reliability sections can be accurately located, and high-risk sections with relatively low reliability levels can be identified. Combining the specific reliability values ​​of each component, the dominant factors leading to the low reliability of these sections are further analyzed, thereby effectively improving the efficiency of maintenance resource utilization and the level of track safety assurance.

[0106] This invention also provides a track system reliability determination device, as described in the following embodiments. Since the principle by which this device solves the problem is similar to that of the track system reliability determination method, the implementation of this device can refer to the implementation of the track system reliability determination method; repeated details will not be elaborated further.

[0107] Figure 5 This is a schematic diagram of a track system reliability determination device according to an embodiment of the present invention. The device includes:

[0108] Data acquisition module 501 is used to acquire multi-source track status detection data of the target track line;

[0109] The defect information identification module 502 is used to identify defect information reflecting abnormal states of track components based on multi-source track condition detection data.

[0110] The component defect rate calculation module 503 is used to divide the target track line into multiple continuous unit segments. For each unit segment, based on the defect information, the defect rate of rail components, fastener components, and track slab or mortar layer components are calculated respectively.

[0111] The component reliability calculation module 504 is used to calculate the reliability of each component within a preset working time based on the calculated defect rates of rail components, fastener components, and track slab or mortar layer components, using the Weibull distribution model.

[0112] The track system reliability calculation module 505 is used to determine the reliability of the track system within the corresponding unit section based on the calculated reliability of each component.

[0113] In one embodiment, the data acquisition module 501 is further configured to:

[0114] The multi-source orbital condition detection data is deduplicated to eliminate duplicate records of the same physical defect in different detection data.

[0115] In one embodiment, the component defect rate calculation module 503 is specifically used for:

[0116] Based on the defect information, obtain the first number of rail defects marked as repairable and the second number of rail defects marked as unrepairable within the unit segment.

[0117] The first defect rate is calculated based on the ratio of the first quantity to the unit segment length.

[0118] The second defect rate is calculated based on the ratio of the second quantity to the number of rail strands within the unit section;

[0119] The defect rate of rail components is determined based on the first defect rate and the second defect rate.

[0120] In one embodiment, the component defect rate calculation module 503 is specifically used for:

[0121] Based on defect information, obtain the number of fastener defects within the unit section;

[0122] The fastener defect rate is calculated based on the ratio of the number of defective fasteners to the total number of fasteners in the unit section.

[0123] In one embodiment, the component defect rate calculation module 503 is specifically used for:

[0124] Based on the defect information, obtain the number of defects in the track slab or mortar layer within the unit section.

[0125] The defect rate of the track slab or mortar layer component is calculated based on the ratio of the number of defects in the track slab or mortar layer to the length of the unit section.

[0126] In one embodiment, the component reliability calculation module 504 is specifically used for:

[0127] The scale parameters of the Weibull distribution are determined based on the defect rate corresponding to each component.

[0128] By substituting the scale parameter and the preset working time into the Weibull distribution reliability function, the reliability of the corresponding component within the preset working time can be calculated.

[0129] In one embodiment, the component reliability calculation module 504 is specifically used for:

[0130] The reliability of the corresponding component within the preset operating time is calculated using the following Weibull distribution reliability function:

[0131] ;

[0132] in, Let t represent the reliability of the i-th component, and t represent the preset operating time. The shape parameter is used to characterize the changing trend of the track defect rate; Let be the scale parameter of the i-th component.

[0133] In one embodiment, the orbital system reliability calculation module 505 is specifically used for:

[0134] The reliability of the track system within the corresponding unit section is obtained by multiplying the reliability of the rail components, the reliability of the fastener components, and the reliability of the track slab or mortar layer components.

[0135] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for determining the reliability of an orbital system.

[0136] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for determining the reliability of an orbital system.

[0137] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method for determining the reliability of an orbital system.

[0138] In this embodiment of the invention, multi-source track condition detection data of the target track line is acquired; based on the multi-source track condition detection data, defect information reflecting abnormal states of track components is identified; the target track line is divided into multiple continuous unit segments; for each unit segment, based on the defect information, the defect rates of rail components, fastener components, and track slab or mortar layer components are calculated; based on the calculated defect rates of rail components, fastener components, and track slab or mortar layer components, the reliability of each component within a preset working time is calculated using the Weibull distribution model; based on the calculated reliability of each component, the reliability of the track system within the corresponding unit segment is determined. In the above process, the embodiments of the present invention acquire multi-source track condition detection data of the target track line and identify defect information reflecting the abnormal state of each component, providing a data basis for subsequent evaluation reflecting physical damage. Furthermore, by dividing the target track line into multiple continuous unit segments and calculating the defect rate of different components such as rails, fasteners, track slabs, or mortar layers for each segment based on defect information, a refined evaluation of the micro-state of the components is achieved. On this basis, the reliability of each component within a preset working time is calculated using the Weibull distribution model, quantifying the defect rate into reliability. Finally, based on the calculated reliability of each component, the reliability of the track system within the corresponding unit segment is determined, realizing the conversion from component-level reliability to system-level reliability. This enables precise location of weak reliability sections, providing direct and quantitative technical support for preventive maintenance and precise repair decisions of the track system.

[0139] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0140] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0141] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0142] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0143] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for determining the reliability of an orbital system, characterized in that, include: Acquire multi-source track condition detection data for the target track line; Based on multi-source track condition detection data, defect information reflecting abnormal conditions of track components is identified; The target track line is divided into multiple continuous unit segments. For each unit segment, based on the defect information, the defect rate of rail components, the defect rate of fastener components, and the defect rate of track slab or mortar layer components are calculated respectively. Based on the calculated defect rates of rail components, fastener components, and track slab or mortar layer components, the reliability of each component within the preset working time is calculated using the Weibull distribution model. Based on the calculated reliability of each component, the reliability of the track system within the corresponding unit section is determined.

2. The method as described in claim 1, characterized in that, Before identifying defect information reflecting abnormal states of track components based on multi-source track condition detection data, the process includes: The multi-source orbital condition detection data is deduplicated to eliminate duplicate records of the same physical defect in different detection data.

3. The method as described in claim 1, characterized in that, The calculation of the defect rate of rail components includes: Based on the defect information, obtain the first number of rail defects marked as repairable and the second number of rail defects marked as unrepairable within the unit segment. The first defect rate is calculated based on the ratio of the first quantity to the unit segment length. The second defect rate is calculated based on the ratio of the second quantity to the number of rail strands within the unit section; The defect rate of rail components is determined based on the first defect rate and the second defect rate.

4. The method as described in claim 1, characterized in that, The calculation of fastener component defect rate includes: Based on defect information, obtain the number of fastener defects within the unit section; The fastener defect rate is calculated based on the ratio of the number of defective fasteners to the total number of fasteners in the unit section.

5. The method as described in claim 1, characterized in that, Calculate the defect rate of track slabs or mortar layer components, including: Based on the defect information, obtain the number of defects in the track slab or mortar layer within the unit section. The defect rate of the track slab or mortar layer component is calculated based on the ratio of the number of defects in the track slab or mortar layer to the length of the unit section.

6. The method as described in claim 1, characterized in that, The reliability of each component within the preset operating time is calculated using the Weibull distribution model, including: The scale parameters of the Weibull distribution are determined based on the defect rate corresponding to each component. By substituting the scale parameter and the preset working time into the Weibull distribution reliability function, the reliability of the corresponding component within the preset working time can be calculated.

7. The method as described in claim 6, characterized in that, The reliability of the corresponding component within the preset operating time is calculated using the following Weibull distribution reliability function: ； in, Let t represent the reliability of the i-th component, and t represent the preset operating time. The shape parameter is used to characterize the changing trend of the track defect rate; Let be the scale parameter of the i-th component.

8. The method as described in claim 1, characterized in that, Based on the calculated reliability of each component, the reliability of the track system within the corresponding unit section is determined, including: The reliability of the track system within the corresponding unit section is obtained by multiplying the reliability of the rail components, the reliability of the fastener components, and the reliability of the track slab or mortar layer components.

9. A device for determining the reliability of a track system, characterized in that, include: The data acquisition module is used to acquire multi-source track status detection data of the target track line; The defect information identification module is used to identify defect information reflecting abnormal conditions of track components based on multi-source track condition detection data. The component defect rate calculation module is used to divide the target track line into multiple continuous unit segments. For each unit segment, based on the defect information, the defect rate of rail components, fastener components, and track slab or mortar layer components are calculated respectively. The component reliability calculation module is used to calculate the reliability of each component within a preset working time based on the calculated defect rates of rail components, fastener components, and track slab or mortar layer components, using the Weibull distribution model. The track system reliability calculation module is used to determine the reliability of the track system within the corresponding unit section based on the calculated reliability of each component.

10. The apparatus as claimed in claim 9, characterized in that, The data acquisition module is also used for: The multi-source orbital condition detection data is deduplicated to eliminate duplicate records of the same physical defect in different detection data.

11. The apparatus as claimed in claim 9, characterized in that, The component defect rate calculation module is specifically used for: Based on the defect information, obtain the first number of rail defects marked as repairable and the second number of rail defects marked as unrepairable within the unit segment. The first defect rate is calculated based on the ratio of the first quantity to the unit segment length. The second defect rate is calculated based on the ratio of the second quantity to the number of rail strands within the unit section; The defect rate of rail components is determined based on the first defect rate and the second defect rate.

12. The apparatus as claimed in claim 9, characterized in that, The component defect rate calculation module is specifically used for: Based on defect information, obtain the number of fastener defects within the unit section; The fastener defect rate is calculated based on the ratio of the number of defective fasteners to the total number of fasteners in the unit section.

13. The apparatus as claimed in claim 9, characterized in that, The component defect rate calculation module is specifically used for: Based on the defect information, obtain the number of defects in the track slab or mortar layer within the unit section. The defect rate of the track slab or mortar layer component is calculated based on the ratio of the number of defects in the track slab or mortar layer to the length of the unit section.

14. The apparatus as claimed in claim 9, characterized in that, The component reliability calculation module is specifically used for: The scale parameters of the Weibull distribution are determined based on the defect rate corresponding to each component. By substituting the scale parameter and the preset working time into the Weibull distribution reliability function, the reliability of the corresponding component within the preset working time can be calculated.

15. The apparatus as claimed in claim 14, characterized in that, The component reliability calculation module is specifically used for: The reliability of the corresponding component within the preset operating time is calculated using the following Weibull distribution reliability function: ； in, Let t represent the reliability of the i-th component, and t represent the preset operating time. The shape parameter is used to characterize the changing trend of the track defect rate; Let be the scale parameter of the i-th component.

16. The apparatus as claimed in claim 9, characterized in that, The track system reliability calculation module is specifically used for: The reliability of the track system within the corresponding unit section is obtained by multiplying the reliability of the rail components, the reliability of the fastener components, and the reliability of the track slab or mortar layer components.

17. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 8.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 8.

19. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 8.

Images