Rail transit vehicle inventory dynamic optimization method and device based on life correction

Abstract

The application provides a kind of track traffic tool inventory dynamic optimization method and device based on life correction, the method includes: obtaining the use frequency of track traffic tool, single use duration and inventory balance;Based on the use frequency and single use duration, the cumulative use index of track traffic tool is determined;In each inventory check period, the life reference value of track traffic tool is reduced and corrected using the cumulative use index, to obtain the tool life attenuation coefficient;Based on the tool life attenuation coefficient, the inventory balance is converted to obtain the life equivalent inventory;In the case where the life equivalent inventory is lower than the safety threshold, a replenishment signal is triggered and the procurement quantity of the next period is adjusted.The method effectively solves the problem of inventory overstock or implicit shortage caused by ignoring the individual wear differences of track traffic tools, realizes the precise dynamic adjustment of procurement quantity, significantly reduces the inventory backlog cost and guarantees the continuity of track traffic operation.

Description

Technical Field

[0001] This invention relates to the field of rail transit vehicle operation and maintenance management technology, and in particular to a method and apparatus for dynamic optimization of rail transit vehicle inventory based on lifespan correction. Background Technology

[0002] In the operation and maintenance management of rail transit vehicles, tool life prediction and inventory optimization are key aspects of ensuring operational safety and controlling costs. However, existing management methods mainly rely on fixed usage cycles and simple periodic inventory checks, which have significant limitations.

[0003] First, in terms of lifespan prediction, existing technologies mostly rely on the total number of times the tool has been used or a preset fixed cycle for assessment, failing to fully consider the periodic fluctuations in usage intensity faced by the tool in actual operation and the complex fatigue characteristics inherent in its materials. This simplified assessment model results in insufficient accuracy in lifespan prediction, making it difficult to accurately reflect the tool's remaining service life.

[0004] Secondly, regarding inventory optimization, existing solutions typically make replenishment decisions based on static inventory level thresholds, ignoring the changes in consumption rates caused by varying operating conditions at different stages of tool use. Due to the lack of dynamic awareness of actual consumption, traditional inventory management is highly susceptible to fluctuations in inventory data, making precise dynamic adjustments impossible. This can lead to resource waste from over-purchasing or operational risks due to inventory shortages.

[0005] Therefore, there is an urgent need for a management method that can combine the actual fatigue characteristics of tools with changes in usage intensity to achieve high-precision life prediction and dynamic inventory optimization. Summary of the Invention

[0006] This invention provides a method and apparatus for dynamic optimization of rail transit vehicle inventory based on lifespan correction, which solves the problem in the prior art that the lifespan prediction accuracy is insufficient and the inventory optimization cannot achieve precise dynamic adjustment due to the neglect of the complex fatigue characteristics and usage intensity changes of the tools in actual use, thereby achieving precise dynamic adjustment of the procurement quantity.

[0007] On one hand, this invention provides a method for dynamic optimization of rail transit vehicle inventory based on lifespan correction, comprising: obtaining the number of times a rail transit vehicle is used, the duration of a single use, and the remaining inventory; determining the cumulative usage index of the rail transit vehicle based on the number of uses and the duration of a single use; within each inventory counting cycle, using the cumulative usage index to reduce and correct the reference value of the rail transit vehicle's lifespan to obtain a tool lifespan decay coefficient; calculating the remaining inventory based on the tool lifespan decay coefficient to obtain a lifespan-equivalent inventory quantity; and triggering a replenishment signal and adjusting the purchase quantity for the next cycle when the lifespan-equivalent inventory quantity is lower than a safety threshold.

[0008] Further, determining the cumulative usage index of the rail transit vehicle based on the number of uses and the duration of a single use includes: performing paired statistics on the number of uses and the duration of a single use to obtain phased usage data; calculating the average usage load based on the phased usage data to obtain basic usage intensity data; weighting and fusing the basic usage intensity data with the micro-fatigue superposition rate coefficient to obtain fatigue-corrected usage intensity; and periodically accumulating the fatigue-corrected usage intensity to obtain the cumulative usage index.

[0009] Further, the step of obtaining the micro-fatigue superposition rate coefficient includes: obtaining the material properties and category parameters of the rail transit vehicle; determining the instantaneous usage intensity data for each usage cycle based on the number of uses and the duration of a single use; performing time series smoothing on the instantaneous usage intensity data to obtain smoothed usage intensity data; determining the fatigue accumulation factor for each usage cycle based on the smoothed usage intensity data and the material properties; performing linear calculation based on the fatigue accumulation factor and the number of uses to obtain a fatigue correction coefficient; and determining the micro-fatigue superposition rate coefficient based on the fatigue correction coefficient and the category parameters.

[0010] Further, determining the fatigue accumulation factor for each service cycle based on the smoothed use strength data and the material properties includes: calculating the material stress response value for each service cycle based on the smoothed use strength data and the hardness data in the material properties; extracting the material toughness in the material properties and determining the local fatigue increment for each service cycle based on the material stress response value; calculating the periodic fatigue accumulation amount based on the local fatigue increment and the single use duration of each service cycle; and determining the fatigue accumulation factor based on the periodic fatigue accumulation amount.

[0011] Further, determining the local fatigue increment for each service cycle by combining the material stress response value includes: extracting material toughness parameters based on the material properties; calculating the stress distribution correction amount of the material in each service cycle based on the material toughness parameters and the material stress response value for each service cycle; and determining the local fatigue increment by using the stress distribution correction amount and the smoothed service strength data for each service cycle.

[0012] Furthermore, the step of obtaining the fatigue-corrected usage intensity by weighted fusion of the basic usage intensity data and the micro-fatigue superposition rate coefficient includes: obtaining a preset weight coefficient; and linearly combining the basic usage intensity data and the corresponding micro-fatigue superposition rate coefficient for each usage cycle according to the preset weight coefficient to obtain the fatigue-corrected usage intensity.

[0013] Furthermore, the step of triggering a replenishment signal and adjusting the purchase quantity for the next cycle when the lifetime equivalent inventory is lower than the safety threshold includes: determining the serial number of the target rail transit vehicle when the lifetime equivalent inventory is lower than the safety threshold; triggering a replenishment signal through the serial number to obtain a first replenishment purchase quantity; analyzing the combined consumption of the target rail transit vehicle based on the first replenishment purchase quantity to obtain combined consumption data; and adjusting the first replenishment purchase quantity using the combined consumption data to obtain a second replenishment purchase quantity, which serves as the purchase quantity for the next inventory counting cycle.

[0014] Further, the step of analyzing the combined consumption of the target rail transit vehicle based on the first replenishment purchase quantity to obtain combined consumption data includes: establishing a sorting sequence according to the tool category and replenishment batch based on the first replenishment purchase quantity; mapping the sorting sequence to the number of times the target rail transit vehicle is used within its usage cycle, and determining the active phase of the target rail transit vehicle according to the usage order and frequency; calculating the cumulative consumption of the target rail transit vehicle in different phases based on the active phase of the target rail transit vehicle, forming phased consumption data; mapping the phased consumption data to the associated rail transit vehicles within the rail transit combination configuration according to the rail transit vehicle combination configuration, and dynamically overlaying the mapped phased consumption data to generate the combined consumption data.

[0015] Furthermore, the step of dynamically overlaying the mapped phased consumption data to generate the combined consumption data includes: determining the consumption rate of the rail transit vehicle corresponding to the first replenishment purchase quantity; calculating the active contribution value of the target rail transit vehicle based on the rail transit vehicle combination configuration and the consumption rate; weighting the mapped phased consumption data based on the active contribution value, and accumulating and overlaying the weighted phased consumption data on the rail transit vehicle combination configuration dimension to obtain the combined consumption data.

[0016] Secondly, the present invention also provides a dynamic optimization device for rail transit vehicle inventory based on lifespan correction, comprising: a data acquisition module for acquiring the number of times rail transit vehicles are used, the duration of a single use, and the remaining inventory; an index determination module for determining the cumulative usage index of the rail transit vehicles based on the number of uses and the duration of a single use; a coefficient correction module for reducing and correcting the lifespan reference value of the rail transit vehicles using the cumulative usage index in each inventory counting cycle to obtain a tool lifespan decay coefficient; an inventory conversion module for converting the remaining inventory based on the tool lifespan decay coefficient to obtain a lifespan-equivalent inventory quantity; and a replenishment control module for triggering a replenishment signal and adjusting the purchase quantity for the next cycle when the lifespan-equivalent inventory quantity is lower than a safety threshold.

[0017] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the dynamic optimization method for rail transit vehicle inventory based on lifetime correction as described above.

[0018] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the dynamic optimization method for rail transit vehicle inventory based on lifetime correction as described above.

[0019] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the dynamic optimization method for rail transit vehicle inventory based on lifetime correction as described above.

[0020] This invention provides a dynamic inventory optimization method for rail transit vehicles based on lifespan correction. It obtains the usage frequency, single usage duration, and remaining inventory of rail transit vehicles, and determines a cumulative usage index based on the usage frequency and single usage duration. Then, within each inventory counting cycle, the cumulative usage index is used to reduce the reference lifespan of the rail transit vehicles, resulting in a lifespan decay coefficient. This coefficient is then used to adjust the remaining inventory to obtain a lifespan-equivalent inventory level. When the lifespan-equivalent inventory level falls below a safety threshold, a replenishment signal is triggered, and the procurement quantity for the next cycle is adjusted. This method effectively solves the problem of inflated inventory or hidden shortages caused by ignoring individual wear differences in rail transit vehicles by converting traditional static inventory levels into lifespan-equivalent inventory levels that reflect true support capabilities. It ensures that replenishment decisions are based on the actual remaining lifespan rather than simple quantity statistics, ultimately achieving precise dynamic adjustment of procurement quantities, significantly reducing inventory backlog costs, and ensuring the continuity of rail transit operations. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in this 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 some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating the dynamic optimization method for rail transit vehicle inventory based on lifespan correction provided in an embodiment of the present invention.

[0023] Figure 2This is a schematic diagram illustrating the change of the cumulative usage index of rail transit vehicles with usage cycle provided in the embodiments of the present invention.

[0024] Figure 3 This is a schematic diagram of the structure of the dynamic optimization device for rail transit vehicle inventory based on lifespan correction provided in an embodiment of the present invention.

[0025] Figure 4 This is a schematic diagram of the physical structure of the electronic device provided in the embodiment of the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0027] Figure 1 The diagram illustrates a flowchart of the dynamic optimization method for rail transit vehicle inventory based on lifespan correction provided in an embodiment of the present invention.

[0028] like Figure 1 As shown, the method includes: S110, obtaining the number of times the rail transit vehicle is used, the duration of each use, and the remaining inventory; S120, determining the cumulative usage index of the rail transit vehicle based on the number of uses and the duration of each use; S130, within each inventory counting cycle, using the cumulative usage index to reduce and correct the reference value of the rail transit vehicle's lifespan to obtain a tool lifespan decay coefficient; S140, calculating the remaining inventory based on the tool lifespan decay coefficient to obtain a lifespan-equivalent inventory quantity; S150, triggering a replenishment signal and adjusting the purchase quantity for the next cycle when the lifespan-equivalent inventory quantity is lower than a safety threshold.

[0029] The following will provide a detailed description of steps S110-S150 and related steps.

[0030] S110, obtain the number of times rail transit vehicles are used, the duration of each use, and the remaining inventory.

[0031] In this step, automated data acquisition equipment deployed at the rail transit vehicle management site is used to acquire real-time or periodic status data of rail transit vehicles, including at least the number of times they are used, the duration of each use, and the remaining inventory.

[0032] Among them, rail transit tools refer to various hand tools, power tools, or specialized testing instruments used in the manufacturing, inspection, and maintenance of rail transit vehicles. Number of uses refers to the cumulative frequency of rail transit tools being taken out and put into use within the statistical period. Single usage duration refers to the duration from the start of timing when a rail transit tool is taken out until the timing stops when it is returned. Inventory balance refers to the current available quantity of this type of rail transit tool in the warehouse.

[0033] In practice, radio frequency identification (RFID) tags or integrated wireless sensing modules can be installed on each rail vehicle. When a worker retrieves a tool from the tool cabinet, the sensor automatically records a usage event and starts an internal timer. When the tool is returned to its designated location, the timer stops, and the duration and frequency of the event are linked and transmitted to the central management system via a wireless network. Simultaneously, the inventory management system updates inventory levels in real time by scanning the tag array within the tool cabinet.

[0034] Status data can be acquired through event-triggered real-time uploads or periodic aggregation collection at preset time intervals (such as hourly or daily) to ensure the timeliness and completeness of the data.

[0035] S120, Based on the number of uses and the duration of each use, determine the cumulative usage index of the rail transit vehicle.

[0036] In this step, the collected status data undergoes in-depth processing to quantify the actual wear and tear of the rail transit vehicle. The cumulative usage index is a dimensionless value or a composite index with a time dimension that characterizes the total workload borne by the rail transit vehicle during its life cycle. Its value is directly related to the fatigue state of the rail transit vehicle.

[0037] Specifically, the usage frequency and duration of each usage session within the same statistical period are first paired and statistically analyzed to form phased usage data. Subsequently, the average usage load is calculated based on the phased usage data to obtain basic usage intensity data, which reflects the current average workload level of rail transit vehicles.

[0038] To more accurately simulate material fatigue characteristics, a micro-fatigue superposition rate coefficient is introduced. This coefficient is a correction factor calculated based on the tool's material properties and usage frequency, used to characterize the cumulative damage effect of micro-stress cycles on the lifespan of rail transit vehicles. The basic service strength data is weighted and fused with the micro-fatigue superposition rate coefficient to obtain the fatigue-corrected service strength. Finally, the fatigue-corrected service strengths for all cycles from historical data to the present are cumulatively calculated to obtain the cumulative service index.

[0039] The cumulative usage index not only considers the length of time used, but also incorporates the micro-fatigue damage caused by the frequency of use, making it a more accurate reflection of the tool's true aging degree than simply accumulating time.

[0040] S130, within each inventory counting cycle, the cumulative usage index is used to reduce and correct the reference value of the rail transit vehicle's lifespan to obtain the tool lifespan decay coefficient.

[0041] In this step, the dynamic life assessment logic is executed. The inventory counting cycle refers to a pre-defined time window used to settle inventory status and assess the lifespan of rail transit vehicles, such as every 3 days or weekly. The lifespan reference value refers to the theoretical total service life of different models of rail transit vehicles under standard operating conditions, usually expressed in standard hours. The tool lifespan decay coefficient is a proportional value between 0 and 1, used to characterize the proportion of the current remaining lifespan of the rail transit vehicle to its initial lifespan, or the rate at which its lifespan is consumed.

[0042] In practice, at the end of each inventory counting cycle, the cumulative usage index calculated within that cycle is read. This cumulative usage index is compared with a preset loss model to calculate the reduction in the lifespan of the rail transit vehicles within the current inventory counting cycle. Subsequently, the lifespan reference value from the previous inventory counting cycle is deducted and corrected using this reduction to update the current vehicle lifespan degradation coefficient.

[0043] If a rail transit vehicle operates under high load, its cumulative usage index increases rapidly, resulting in a large reduction in the life reference value. Consequently, the obtained tool life attenuation coefficient will decrease significantly, indicating that the tool's lifespan is being consumed at an accelerated rate. Conversely, if a rail transit vehicle operates under low load, the attenuation coefficient will change less.

[0044] In addition, this step can also be combined with environmental monitoring data. If it is detected that the rail transit vehicle is used in a high temperature or high humidity environment, the life decay coefficient of the vehicle can be further reduced to reflect the accelerated decay effect of environmental factors on life.

[0045] S140, the remaining inventory is calculated based on the tool life decay coefficient to obtain the life-equivalent inventory.

[0046] This step transforms traditional quantity-based inventory into capacity-based inventory. Life-equivalent inventory refers to the total remaining usable life of all existing rail vehicles of the same type in the warehouse, converted to standard time units. Life-equivalent inventory addresses the problem of traditional inventory management focusing solely on quantity while neglecting condition and remaining life.

[0047] Specifically, the current inventory balance (i.e., the number of rail transit tools) is obtained, and the tool life decay coefficient corresponding to each individual or batch of rail transit tools in stock is read. The inventory balance is multiplied by the standard life reference value of a single tool, and then multiplied by the corresponding tool life decay coefficient to calculate the total effective working time that the current inventory can actually provide, i.e., the life-equivalent inventory quantity.

[0048] For example, if there are 10 rail transit vehicles in inventory, but after long-term use, their average tool life degradation coefficient is only 0.6, then the equivalent inventory size is only equivalent to the total lifespan of 6 brand-new rail transit vehicles. Through this calculation, managers can intuitively grasp the actual guarantee capacity of the inventory.

[0049] S150, if the lifetime equivalent inventory is lower than the safety threshold, a replenishment signal is triggered and the purchase quantity for the next cycle is adjusted.

[0050] In this step, intelligent decision-making and feedback control are implemented. The safety threshold refers to the minimum warning line set for the equivalent inventory level to ensure the continuity of rail transit production or maintenance operations. It can be set based on the expected maximum demand and safety redundancy within a future procurement cycle.

[0051] In practice, the lifetime-equivalent inventory level is monitored in real time and compared with a safety threshold. Once the lifetime-equivalent inventory level is detected to be lower than the safety threshold, a replenishment signal is immediately generated. The replenishment signal includes the tool serial number that needs to be replenished and the urgency information.

[0052] Subsequently, the procurement quantity adjustment process is initiated: First, a first replenishment procurement quantity is calculated based on the current shortage, which is the quantity required to basically fill the gap; next, the combined consumption of this rail transit vehicle with other related tools is analyzed, that is, considering the pattern of rail transit vehicles being used in sets and consumed in combination during actual operation, combined consumption data is obtained; finally, the first replenishment procurement quantity is corrected using the combined consumption data to obtain the second replenishment procurement quantity. The second replenishment procurement quantity serves as the final execution procurement quantity for the next inventory counting cycle and is issued to the procurement execution module.

[0053] In this way, not only is timely replenishment based on lifespan status achieved, but also complete sets of tools are kept idle due to shortages of single rail transit vehicles, or inventory backlogs caused by blind replenishment, thus achieving dynamic optimal allocation of inventory.

[0054] In this embodiment, by acquiring the number of times rail transit vehicles are used, the duration of each use, and the remaining inventory, a cumulative usage index is determined based on the number of uses and the duration of each use. Then, within each inventory counting cycle, the reference lifespan of the rail transit vehicles is reduced using the cumulative usage index to obtain a tool lifespan decay coefficient. This coefficient is then used to calculate the remaining inventory, resulting in a lifespan-equivalent inventory level. When the lifespan-equivalent inventory level falls below a safety threshold, a replenishment signal is triggered, and the procurement quantity for the next cycle is adjusted. This method effectively solves the problem of inflated inventory or hidden shortages caused by ignoring individual wear and tear differences in rail transit vehicles by converting traditional static inventory levels into lifespan-equivalent inventory levels that reflect true support capabilities. It ensures that replenishment decisions are based on the actual remaining lifespan rather than simple quantity statistics, ultimately achieving precise dynamic adjustment of procurement quantities, significantly reducing inventory backlog costs, and ensuring the continuity of rail transit operations.

[0055] Based on the above embodiments, the process of determining the cumulative usage index in step S120 will be described in detail below.

[0056] Based on the number of uses and the duration of a single use, the cumulative usage index of rail transit vehicles is determined, including: pairing and statistically analyzing the number of uses and the duration of a single use to obtain phased usage data; calculating the average usage load based on the phased usage data to obtain basic usage intensity data; weighting and fusing the basic usage intensity data with the micro-fatigue superposition rate coefficient to obtain fatigue-corrected usage intensity; and accumulating the fatigue-corrected usage intensity over a period of time to obtain the cumulative usage index.

[0057] The process is straightforward: first, the collected usage frequency and individual usage duration are paired and statistically analyzed to obtain phased usage data. Specifically, all usage events occurring within a preset time window (i.e., a usage phase, such as a work shift, a day, or a week) are summarized. The total number of uses within the preset time window is then mapped and correlated with the individual usage duration corresponding to each operation within that window, forming structured phased usage data. This phased usage data not only records the frequency of rail transit use but also fully preserves the duration characteristics of each use, providing fundamental data support for subsequent assessments of the overall load distribution of rail transit within that phase.

[0058] Subsequently, the average usage load is calculated based on the phased usage data, thus obtaining the basic usage intensity data. During this process, the distribution pattern of single usage duration and the density of usage frequency in the phased usage data are analyzed to estimate the average workload borne by the rail transit vehicle per unit time or per number of uses within that phase. Basic usage intensity data is a macroscopic indicator reflecting the average operating intensity of the rail transit vehicle within a specific phase, embodying the basic wear trend caused by routine use, but it does not yet consider the cumulative fatigue effect at the microscopic level of the materials.

[0059] To compensate for the inability of simple macroscopic statistics to reflect microscopic material damage, this embodiment uses a weighted fusion of basic service strength data and micro-fatigue superposition rate coefficient to obtain fatigue-corrected service strength. The micro-fatigue superposition rate coefficient is a dynamic correction factor calculated based on tool material properties, historical stress states, and environmental factors. It characterizes the superimposed damage effect of micro-stress cycles on tool life during continuous use.

[0060] In practice, a preset weighting ratio is obtained, and the basic usage intensity data reflecting macroscopic load is linearly combined with the micro-fatigue superposition rate coefficient reflecting microscopic fatigue characteristics. If the rail transit vehicle is in a state of high-frequency start-stop or high-load fluctuation, the micro-fatigue superposition rate coefficient will increase, thus significantly improving the value of fatigue correction usage intensity after weighted fusion. Fatigue correction usage intensity is a comprehensive indicator that includes both the actual working load information of the rail transit vehicle and the correction of material fatigue characteristics, and can more realistically reflect the actual wear and tear of the rail transit vehicle at the current stage.

[0061] Finally, the fatigue correction usage intensity is accumulated over time to obtain the cumulative usage index. Using time as the axis, the fatigue correction usage intensity calculated for each usage cycle (e.g., daily, weekly, or monthly) since the rail transit vehicle was put into service is summed. As the usage cycle increases, the summed value shows an increasing trend, and its growth rate directly depends on the magnitude of the fatigue correction usage intensity within each cycle, ultimately yielding the cumulative usage index.

[0062] The cumulative usage index ultimately forms a total value that changes dynamically over time, comprehensively and quantitatively representing the total amount of fatigue damage suffered by rail transit vehicles throughout their entire lifespan. Compared to traditional statistical methods based solely on total usage time, the cumulative usage index in this embodiment can more sensitively capture the accelerated wear and tear on tool life caused by high-intensity use and micro-fatigue accumulation, providing a highly accurate basis for subsequent lifespan prediction and inventory optimization.

[0063] In one specific embodiment Figure 2This diagram illustrates the variation of the cumulative usage index of a rail transit vehicle provided in an embodiment of the present invention with the usage period.

[0064] Figure 2 The vertical axis represents the cumulative usage index, and the horizontal axis represents the usage period. The three main curves in the figure represent different safety level indicators: Safety lock value curve (blue): indicates that when the cumulative usage index reaches this value, strict safety control or shutdown of the rail transit vehicle is required to prevent potential risks; Safety color mark curve (purple): indicates that when the cumulative usage index is within this range, the vehicle can still be used, but its status needs to be monitored; Safety alarm value curve (dark purple): indicates that when the cumulative usage index exceeds this value, a warning signal should be triggered to prompt the user to perform maintenance or inspection.

[0065] according to Figure 2 It can be seen that the cumulative usage index gradually increases with the increase in usage cycle, and the interval between the curves of different safety levels reflects the hierarchical management space of rail transit vehicle use safety. Based on this curve, environmental correction can be carried out by combining load factor and environmental factors, thereby forming a dynamic environmental correction model to realize dynamic monitoring and maintenance decision-making of the vehicle's operating status.

[0066] This embodiment realizes a complete calculation chain from basic data statistics to micro-fatigue correction, and then to full-cycle accumulation, ensuring that the obtained cumulative usage index can accurately reflect the true health status of rail transit vehicles.

[0067] Based on the above embodiments, the process of obtaining the micro-fatigue superposition rate coefficient will be described in detail below.

[0068] The steps for obtaining the micro-fatigue superposition rate coefficient include: acquiring the material properties and category parameters of the rail transit vehicle; determining the instantaneous usage intensity data for each usage cycle based on the number of uses and the duration of a single use; performing time series smoothing on the instantaneous usage intensity data to obtain smoothed usage intensity data; determining the fatigue accumulation factor for each usage cycle based on the smoothed usage intensity data and material properties; performing linear calculations based on the fatigue accumulation factor and the number of uses to obtain the fatigue correction coefficient; and determining the micro-fatigue superposition rate coefficient based on the fatigue correction coefficient and category parameters.

[0069] Specifically, the material properties and category parameters of rail transit vehicles are first obtained from the basic information database or embedded electronic tags. Material properties refer to the inherent physical and mechanical properties of the metals or composite materials that constitute the rail transit vehicle, including but not limited to hardness, toughness, elastic modulus, and fatigue limit. These properties determine the inherent ability of the rail transit vehicle to resist deformation and fracture. Category parameters refer to the classification identifiers set according to the specific functional uses of the rail transit vehicle in rail transit operations (such as fastening, cutting, measuring, or impact). Different categories of tools have different fatigue sensitivity benchmarks due to their different stress modes.

[0070] Subsequently, based on the number of uses and the duration of each use, instantaneous usage intensity data for each usage cycle is determined. Specifically, each independent usage event (i.e., the process from pickup to return) is considered as an analysis unit. Combining the duration of each use event with the usage frequency density within the usage cycle, the dynamic load intensity borne by the rail transit vehicle at any given moment is calculated, i.e., instantaneous usage intensity data. Instantaneous usage intensity data reflects the immediate stress state of the rail transit vehicle at each specific operation moment, and can capture instantaneous stress changes caused by short-term high-load impacts or frequent start-stops.

[0071] Preferably, each inventory counting cycle comprises at least 3 and no more than 5 consecutive usage cycles, and the time interval between inventory counting cycles is limited to 1-7 days. This configuration ensures that the inventory counting process covers not only short-term tool usage but also tool consumption over a longer period. Each usage cycle represents a specific operational phase or task cycle. Assuming a tool's usage cycle is 1 day, then each inventory counting cycle will contain 3 to 5 consecutive usage cycles, representing a time period of 3 to 5 days.

[0072] The time interval for each inventory counting cycle is limited to 1-7 days. This time interval is set to ensure an appropriate frequency of inventory data updates, while also considering the actual operational pace and counting costs. Shorter time intervals allow for faster responses to inventory changes but may increase counting costs; longer time intervals reduce the burden of frequent counting. If the time interval is set to 3 days, it means that each inventory counting cycle consists of 3 consecutive working days. During these 3 days, tool usage data is collected, and then the inventory is counted and adjusted.

[0073] Considering potential operational fluctuations, sensor noise, or atypical sporadic data spikes in actual operations, this embodiment performs time-series smoothing on instantaneous usage intensity data to obtain smoothed usage intensity data. During this process, moving average or low-pass filtering algorithms are used to denoise continuous instantaneous usage intensity data along the time axis, eliminating abnormal abrupt changes and retaining effective signals reflecting the long-term stress trends of rail transit vehicles. The resulting smoothed usage intensity data eliminates random interference, more realistically and continuously characterizing the stable stress levels of rail transit vehicles across different usage cycles, providing reliable input for subsequent material response analysis.

[0074] Next, based on the smoothed service strength data and material properties, the fatigue accumulation factor for each service cycle is determined. The smoothed external strength data is mapped using the material's physical properties (such as hardness and toughness) to simulate the microscopic damage evolution process of the material's internal crystal structure under cyclic stress. By comparing the matching relationship between the smoothed service strength data and material properties, the ratio of microcrack initiation or propagation within the material per unit cycle under the current stress environment is calculated; this is the fatigue accumulation factor. The fatigue accumulation factor quantifies the degree of irreversible fatigue damage accumulated in each cycle for a specific material under a specific smoothed strength.

[0075] After obtaining the fatigue accumulation factor, a linear calculation is performed based on the fatigue accumulation factor and the number of uses to obtain the fatigue correction coefficient. In practice, the fatigue accumulation factor for each use cycle is multiplied by the actual number of uses corresponding to that use cycle and then summed to establish a linear correlation model between the total fatigue damage and the frequency of use. The fatigue correction coefficient is an intermediate variable that amplifies the microscopic damage factor of a single cycle to the macroscopic dimension of the frequency of use, reflecting the total amount of fatigue damage correction caused by repeated use within the statistical period.

[0076] Finally, the micro-fatigue superposition rate coefficient is determined based on the fatigue correction coefficient and the category parameter. In this step, the category parameter is introduced as the final adjustment factor to differentiate the adjustments for different functional types of rail transit vehicles. For example, for impact-type rail transit vehicles, the category parameter amplifies the influence weight of the fatigue correction coefficient to reflect their higher micro-fatigue sensitivity; while for measurement-type rail transit vehicles, the category parameter may reduce this weight.

[0077] By weighting and fusing the fatigue correction coefficient with the category parameters or mapping them through a lookup table, the micro-fatigue superposition rate coefficient is finally output. As a dynamically changing dimensionless value, the micro-fatigue superposition rate coefficient comprehensively reflects the superposition effect of the material nature of the rail transit vehicle, its actual stress history, usage frequency, and vehicle type on micro-fatigue damage. It will be used to subsequently correct the basic service strength, thereby achieving high-precision calibration of the rail transit vehicle's life assessment.

[0078] This embodiment constructs a complete calculation logic that starts from material properties, goes through instantaneous strength capture, data smoothing and denoising, micro-damage simulation, frequency linear accumulation and category differentiation correction, and ensures that the obtained micro-fatigue superposition rate coefficient can scientifically and accurately characterize the real fatigue state of rail transit vehicles under complex working conditions.

[0079] Based on the above embodiments, the process of determining the fatigue accumulation factor will be described in detail below.

[0080] Based on the smoothed service strength data and material properties, the fatigue accumulation factor for each service cycle is determined, including: calculating the material stress response value for each service cycle based on the smoothed service strength data and the hardness data in the material properties; extracting the material toughness from the material properties and combining it with the material stress response value to determine the local fatigue increment for each service cycle; calculating the periodic fatigue accumulation based on the local fatigue increment and the single service duration for each service cycle; and determining the fatigue accumulation factor based on the periodic fatigue accumulation.

[0081] The process is straightforward: first, based on the smoothing use intensity data and the hardness data from the material properties, the material stress response values ​​for each service cycle are calculated. Hardness data is a physical quantity characterizing the surface resistance of rail vehicle materials to localized plastic deformation or indentation, directly reflecting the material's rigidity under stress. The material stress response value refers to the actual stress level generated within the rail vehicle material when subjected to external smoothing use intensity.

[0082] In practice, the smoothed service strength data obtained in the previous steps (i.e., the continuous stress trend after noise reduction) is used as the external load input, and mechanical mapping is performed in conjunction with hardness data extracted from the material property database. Since materials with different hardnesses produce different internal stress distributions under the same external strength, the smoothed service strength is corrected and transformed using hardness data to simulate the true stress response state inside the material. The material stress response value eliminates the error of estimation based solely on external loads, and more accurately reflects the actual mechanical load borne by the material itself during the current cycle.

[0083] Subsequently, material toughness was extracted from the material properties and, combined with the previously calculated material stress response values, the local fatigue increment for each service cycle was determined. Material toughness refers to the material's ability to absorb energy and undergo plastic deformation before fracture, and is a key indicator of a material's resistance to crack propagation. Local fatigue increment refers to the amount of new, minute damage to the material's microstructure (such as grain boundaries and dislocations) caused by stress cycling within the current service cycle.

[0084] Specifically, the process begins by extracting precise material toughness parameters based on material properties. Next, based on the material toughness parameters and the material stress response values ​​for each service cycle, the stress distribution correction is calculated. This correction reflects the stress redistribution phenomenon occurring in high-stress concentration areas due to the material's toughness; that is, tough materials can alleviate stress concentration through local yielding, while brittle materials cannot. Subsequently, the local fatigue increment is determined by combining the stress distribution correction with smoothed service strength data for each service cycle. If the material has high toughness and a large stress distribution correction, the local fatigue increment will decrease accordingly; conversely, if the material has low toughness or severe stress concentration, the local fatigue increment will increase significantly. This step achieves a refined transformation from macroscopic stress to microscopic damage increment.

[0085] Next, the cumulative periodic fatigue is calculated based on the local fatigue increment and the duration of each use cycle. The cumulative periodic fatigue refers to the total fatigue damage accumulated by the tool within a complete use cycle, taking into account the duration factor.

[0086] In practical implementation, considering that fatigue damage is related not only to the intensity of a single stress (i.e., the local fatigue increment) but also to the duration of the stress, this embodiment correlates the local fatigue increment determined in the previous step with the single usage duration recorded within the service cycle, for example, considering the nonlinear amplification effect of duration on damage accumulation. By integrating or weighting the microscopic incremental indicators over time, the periodic fatigue accumulation within the service cycle is obtained. The periodic fatigue accumulation comprehensively reflects the overall fatigue damage accumulation effect caused by the continuous operation of the rail transit vehicle under specific intensity within the current service cycle.

[0087] Finally, the fatigue accumulation factor is determined based on the cyclic fatigue accumulation. The fatigue accumulation factor is a normalized or standardized ratio coefficient used to characterize the rate or efficiency of fatigue damage accumulation per unit cycle under current material properties and operating conditions.

[0088] Specifically, the calculated cyclic fatigue accumulation is compared or mapped using a preset baseline damage threshold or standard cyclic damage value to determine the fatigue accumulation factor. A larger cyclic fatigue accumulation indicates rapid material damage under current conditions, leading to a corresponding increase in the fatigue accumulation factor and suggesting a need for greater lifespan reduction. Conversely, a smaller accumulation factor results in a smaller accumulation factor. This fatigue accumulation factor, as a core intermediate variable, is passed to the next stage of the process to calculate the fatigue correction coefficient in conjunction with the number of uses, ultimately influencing the generation of the micro-fatigue stacking rate coefficient.

[0089] This embodiment abandons the traditional rough estimation that relies solely on empirical coefficients. Instead, it is based on the actual physical mechanisms of material hardness and toughness, combined with smoothed actual stress data and duration information, to achieve digital reconstruction and precise quantification of the micro-fatigue accumulation process of rail transit vehicles, significantly improving the physical reliability and prediction accuracy of the life assessment model.

[0090] Based on the above embodiments, the process for determining the local fatigue increment will be described in detail below.

[0091] The local fatigue increment for each service cycle is determined by combining the material stress response value, including: extracting material toughness parameters based on material properties; calculating the stress distribution correction amount for the material in each service cycle based on the material toughness parameters and the material stress response value for each service cycle; and determining the local fatigue increment by using the stress distribution correction amount and the smoothed service strength data for each service cycle.

[0092] The process is straightforward: first, material toughness parameters are extracted based on material properties. These material properties are a set of fundamental physical attributes pre-stored in the vehicle's archives or embedded chips. Material toughness parameters are quantitative indicators specifically extracted from this set of fundamental physical attributes, characterizing a material's ability to absorb energy and undergo plastic deformation without fracturing under stress. Material toughness parameters reflect a material's inherent potential to resist crack propagation and alleviate stress concentration.

[0093] In practice, the material identification of the rail transit vehicle (such as a specific grade of alloy steel, composite material, etc.) is read, a pre-set material mechanics database is called, and the corresponding material toughness parameters (such as impact toughness value or fracture toughness coefficient) are matched and extracted. The material toughness parameters, as the core basis for subsequent stress correction, determine the material's "buffering" ability when facing external loads.

[0094] Subsequently, based on the material toughness parameters and the material stress response values ​​for each service period, the stress distribution correction amount for the material during each service period is calculated. The material stress response value is a numerical value reflecting the nominal stress level within the material, calculated in the previous steps based on the external smoothing service strength and material hardness. The stress distribution correction amount is a correction value characterizing the redistribution or attenuation of the actual internal stress distribution due to the material's toughness.

[0095] Specifically, under the same nominal stress response value, high-toughness materials can reduce the stress peak through localized micro-plastic flow, thus making the stress distribution more uniform, while low-toughness materials tend to maintain higher stress concentration. Therefore, coupling the material toughness parameter with the material stress response value in calculations yields a significant stress reduction effect if the material toughness parameter is high, and a smaller or even near-zero stress distribution correction if the material toughness parameter is low. Through this calculation, a stress distribution correction that dynamically reflects the degree to which the material's own properties "self-regulate" the internal stress field can be obtained. This stress distribution correction quantifies the offsetting or optimizing effect of toughness on nominal stress.

[0096] Finally, the local fatigue increment is determined by the stress distribution correction and the smoothed service intensity data for each service cycle. The smoothed service intensity data is the external load data, after time-series processing, representing the stable stress trend of the tool within that cycle. The local fatigue increment is the additional fatigue amount that actually acts on the material's microstructure and leads to damage accumulation within the service cycle, taking into account both the external load intensity and the internal stress redistribution effect.

[0097] In practice, the corrected internal stress state (reflected by the stress distribution correction) is comprehensively mapped with the external smoothed service strength data. The stress distribution correction is used to perform a weighted or nonlinear transformation on the smoothed service strength data, eliminating ineffective stress components that are "digested" by material toughness, retaining only the effective stress components that are truly sufficient to cause micro-lattice slip or microcrack initiation. The resulting local fatigue increment is no longer simply a function of the external load, but rather the net damage result after the interplay between the external load and the material's inherent toughness. If the smoothed service strength is high but the material toughness is high and the stress distribution correction is large, the local fatigue increment will be significantly suppressed; conversely, if the material toughness is insufficient, even with a moderate smoothed service strength, the local fatigue increment may remain at a high level.

[0098] This embodiment extracts material toughness parameters, calculates stress distribution corrections, and deeply integrates them with smoothing usage strength data. It successfully transforms macroscopic stress data into local fatigue increments that can truly reflect the evolution of microscopic damage in materials. This ensures that the subsequent calculations of periodic fatigue accumulation and the final cumulative usage index can accurately reflect the life differences of tools made of different materials under the same working conditions, greatly improving the scientificity and accuracy of rail transit vehicle life assessment.

[0099] Based on the above embodiments, the process of obtaining fatigue correction strength will be described in detail below.

[0100] The fatigue-corrected usage intensity is obtained by weighting and fusing the basic usage intensity data with the micro-fatigue superposition rate coefficient. This includes: obtaining the preset weight coefficient; and linearly combining the basic usage intensity data and the corresponding micro-fatigue superposition rate coefficient for each usage cycle according to the preset weight coefficient to obtain the fatigue-corrected usage intensity.

[0101] Specifically, the first step is to obtain preset weighting coefficients. These preset weighting coefficients are a set of numerical parameters pre-set during system initialization or according to a specific application scenario. They define the relative contribution ratios of basic usage intensity data and micro-fatigue superposition rate coefficients to the final result. The preset weighting coefficients reflect the relative importance of macroscopic statistical load and micro-fatigue effect in the current evaluation model.

[0102] In practice, preset weighting coefficients are read from the configuration database or management terminal. These preset weighting coefficients typically consist of two components: one corresponding to the weight of the basic usage intensity data, such as representing the dominance of macroscopic load; and the other corresponding to the weight of the micro-fatigue superposition rate coefficient, such as representing the sensitivity to micro-fatigue correction. The sum of these two components is usually kept constant (e.g., normalized to 1) to ensure dimensional consistency of the fusion results.

[0103] The preset weighting coefficients can be dynamically adjusted based on historical failure statistics of rail transit vehicles, expert experience, or risk preferences for different vehicle categories. For example, for precision rail transit vehicles with high fatigue sensitivity, a higher micro-fatigue superposition rate coefficient weight can be obtained to amplify the impact of micro-damage on the final assessment; while for rough rail transit vehicles that are mainly affected by wear, a higher basic service intensity data weight can be obtained.

[0104] Subsequently, based on the basic usage intensity data for each usage cycle and the corresponding micro-fatigue superposition rate coefficient, a linear combination is performed according to preset weight coefficients to obtain the fatigue-corrected usage intensity. The linear combination refers to the mathematical operation of multiplying two or more variables by their corresponding weight coefficients and then summing the resulting products, with the aim of constructing a comprehensive evaluation index.

[0105] Specifically, for each independent usage cycle, the basic usage intensity data that has been calculated within that cycle is first extracted. The basic usage intensity data represents the average macroscopic operating load of the rail transit vehicle within that cycle. At the same time, the micro-fatigue superposition rate coefficient generated synchronously within that cycle is extracted. The micro-fatigue superposition rate coefficient represents the superposition and amplification effect of micro-fatigue damage of the material under the operating conditions of that cycle.

[0106] Next, the basic usage intensity data is multiplied by the component corresponding to macroscopic load in the preset weighting coefficients to obtain the first weighted component; simultaneously, the micro-fatigue superposition rate coefficient is multiplied by the component corresponding to micro-fatigue in the preset weighting coefficients to obtain the second weighted component. Finally, the first weighted component and the second weighted component are summed to generate the fatigue-corrected usage intensity for this usage cycle.

[0107] Through this linear combination method, the obtained fatigue-corrected service strength not only retains the information of the actual workload reflected by the basic service strength data, but also deeply integrates the material internal damage accumulation characteristics revealed by the micro-fatigue superposition rate coefficient.

[0108] If a rail transit vehicle, despite low usage frequency (low basic usage intensity data) within a certain service life, experiences high-frequency start-stop or severe vibration leading to an extremely high micro-fatigue superposition rate coefficient, the final fatigue-corrected service intensity will remain at a high level after being weighted by highly weighted micro-coefficients, thus accurately predicting potential fatigue failure risks. Conversely, if the rail transit vehicle operates under low load for extended periods, even with a certain basic usage intensity data, an extremely low micro-fatigue superposition rate coefficient will result in a correspondingly lower fused fatigue-corrected service intensity, avoiding overestimation of the vehicle's lifespan.

[0109] This embodiment successfully integrates macroscopic load data and microscopic fatigue coefficients by obtaining flexible and configurable preset weighting coefficients and strictly executing linear combination operations based on the preset weighting coefficients. This ensures that the cumulative usage index can accurately and dynamically reflect the true health status and remaining life trend of rail transit vehicles under complex and variable operating conditions.

[0110] Based on the above embodiments, the process of triggering a replenishment signal and adjusting the purchase quantity for the next cycle in step S150 will be described in detail below.

[0111] When the lifetime equivalent inventory level is lower than the safety threshold, a replenishment signal is triggered and the purchase quantity for the next cycle is adjusted. This includes: determining the serial number of the target rail transit vehicle when the lifetime equivalent inventory level is lower than the safety threshold; triggering a replenishment signal using the serial number to obtain the first replenishment purchase quantity; analyzing the combined consumption of the target rail transit vehicle based on the first replenishment purchase quantity to obtain combined consumption data; and adjusting the first replenishment purchase quantity using the combined consumption data to obtain the second replenishment purchase quantity, which serves as the purchase quantity for the next inventory counting cycle.

[0112] The process is straightforward: first, when the life-equivalent inventory falls below a safety threshold, the serial number of the target rail vehicle is determined. The life-equivalent inventory refers to the total inventory value after converting the remaining lifespan of all similar rail vehicles in the current warehouse into the standard new parts quantity. The safety threshold is a pre-set inventory warning line, used to identify the minimum life-equivalent reserve required to maintain normal operation. The target rail vehicle refers to the specific type or batch of rail vehicles that is causing the inventory level to fall below the warning line. The serial number is a unique identifier assigned to each target rail vehicle, used to accurately track the vehicle's model, batch, and historical status in the logistics and management system.

[0113] In practice, the inventory database is traversed to identify rail transit vehicle categories with insufficient current lifespan-equivalent inventory, and the specific target rail transit vehicle is located. Subsequently, the serial number of the target rail transit vehicle is extracted. This serial number will serve as the data index for all subsequent replenishment operations, ensuring that replenishment instructions accurately point to the specific rail transit vehicle that needs to be replenished, and avoiding model confusion or mis-issuance.

[0114] Next, a replenishment signal is triggered via the sequence number, and the first replenishment purchase quantity is obtained accordingly. The replenishment signal is an automated request instruction sent by the system to the procurement management module or an external supplier, containing information on the rail transit vehicles urgently needing replenishment. The first replenishment purchase quantity is a preliminary suggested purchase quantity calculated based on the current inventory gap, typically only considering filling the current shortfall below a safety threshold.

[0115] Specifically, a replenishment signal containing a serial number is constructed and sent to the procurement execution unit. After parsing the signal, the receiving end quickly calculates the first replenishment purchase quantity based on the difference between the current lifetime equivalent inventory and the safety threshold, combined with the preset minimum ordering unit. The first replenishment purchase quantity is mainly intended to solve the immediate problem and quickly restore the inventory level above the safety line, but it does not fully consider the complex fluctuations in actual consumption.

[0116] Subsequently, the combined consumption of the target rail transit vehicles was analyzed based on the initial replenishment procurement volume to obtain combined consumption data. Combined consumption refers to the comprehensive consumption pattern of the target rail transit vehicles when used in combination across different operating scenarios, lines, or shifts within a specific time period. It reflects the non-linear consumption characteristics of the target rail transit vehicles in actual operation (such as concentrated consumption during peak hours and accelerated losses under specific operating conditions). The combined consumption data is a dataset formed by quantifying and statistically analyzing the aforementioned consumption patterns, including information such as consumption rate, fluctuation coefficient, and related influencing factors.

[0117] In practice, historical operational records are reviewed, with a focus on analyzing consumption patterns related to the time period or business scenario covered by the first replenishment purchase. This involves identifying whether the target rail transit vehicle has a strong coupling relationship with other tools in actual application (e.g., a certain type of fastener is always consumed in conjunction with a specific cutting tool), or whether there are periodic concentrated replacement phenomena. Through in-depth analysis of these combined consumption patterns, detailed combined consumption data is generated. This data reveals potential biases in the first replenishment purchase volume calculated solely based on inventory differences, such as whether it underestimates the concentrated demand during the upcoming major overhaul period or overestimates actual consumption during the off-season.

[0118] Finally, the first replenishment purchase quantity is adjusted using the combined consumption data to obtain the second replenishment purchase quantity, which is then used as the purchase quantity for the next inventory counting cycle. The second replenishment purchase quantity is the final purchase order quantity after adjustments based on actual consumption patterns. The next inventory counting cycle refers to the time interval from the current moment until the next formal inventory count and settlement.

[0119] Specifically, combined consumption data is used as a correction factor to dynamically adjust the first replenishment purchase quantity. If the combined consumption data indicates high-intensity combined operations or an accelerating consumption trend in the future cycle, the purchase quantity will be increased upwards, making the second replenishment purchase quantity greater than the first replenishment purchase quantity to reserve sufficient safety margin. Conversely, if the data shows that consumption is trending towards flattening or that alternative solutions exist, the purchase quantity will be decreased downwards to avoid inventory backlog and capital tied up. The second replenishment purchase quantity generated after this refined adjustment not only fills the current inventory gap but also accurately matches the actual future operational needs. Finally, this second replenishment purchase quantity is locked as the execution purchase quantity for the next inventory counting cycle and sent to the supply chain system to generate orders.

[0120] This embodiment ensures accurate replenishment by introducing serial numbers, quickly responds to inventory crises using the first replenishment purchase quantity, and further calibrates the purchase quantity a second time using combined consumption data, ultimately outputting a scientifically reasonable second replenishment purchase quantity. This realizes an intelligent replenishment strategy that moves from "passive replenishment" to "proactive prediction," effectively solving problems such as inaccurate purchase quantities and large inventory fluctuations caused by ignoring the combined consumption characteristics of tools in traditional replenishment models. It significantly improves the response speed and resource allocation efficiency of the rail transit tool supply chain.

[0121] Based on the above embodiments, the process of obtaining combined consumption data will be described in detail below.

[0122] The combined consumption of the target rail transit vehicles is analyzed based on the first replenishment purchase volume to obtain combined consumption data, including: establishing a sorting sequence according to vehicle type and replenishment batch based on the first replenishment purchase volume; mapping the sorting sequence to the number of times the target rail transit vehicles are used within their usage cycle, and determining the active phase of the target rail transit vehicles according to the usage order and frequency; calculating the cumulative consumption of the target rail transit vehicles in different phases based on the active phases of the target rail transit vehicles to form phased consumption data; mapping the phased consumption data to the associated rail transit vehicles within the rail transit vehicle combination configuration according to the rail transit vehicle combination configuration, and dynamically overlaying the mapped phased consumption data to generate combined consumption data.

[0123] The mapped phased consumption data is dynamically overlaid to generate combined consumption data, including: determining the consumption rate of the rail transit vehicle corresponding to the first replenishment purchase quantity; calculating the active contribution value of the target rail transit vehicle based on the combination configuration and consumption rate of the rail transit vehicle; weighting the mapped phased consumption data based on the active contribution value, and accumulating and overlaying the weighted phased consumption data on the rail transit vehicle combination configuration dimension to obtain combined consumption data.

[0124] The process is straightforward: first, a sorting sequence is established based on the initial replenishment purchase quantity, categorized by tool type and replenishment batch. The initial replenishment purchase quantity is the preliminary calculated recommended purchase quantity. Tool type refers to the functional classification of rail transit vehicles, such as bogie components and traction system components. Replenishment batch refers to a specific purchase order batch triggered by the current inventory alert. The sorting sequence is a logical queue formed by arranging the purchase demands of different batches within the same category according to chronological order or priority.

[0125] In practice, the details of the rail transit vehicles included in the first replenishment purchase are analyzed, categorized into the corresponding vehicle types, and their respective replenishment batches are marked. Subsequently, an ordered sequence is constructed based on the timestamp of batch generation or the degree of urgency. This sequence not only reflects the order of replenishment but also implies the expected timeline for the deployment of this type of rail transit vehicle in the near future.

[0126] Next, the sorted sequence is mapped to the number of times the target rail transit vehicle is used within its service life, and the active phase of the target rail transit vehicle is determined according to the order and frequency of use. Here, the target rail transit vehicle is the specific tool whose consumption patterns need to be analyzed. The service life is the entire life cycle of the rail transit vehicle from its commissioning to its scrapping or major overhaul. The number of uses is the statistical count of the number of operations performed by the rail transit vehicle within its service life. The order of use is the logical sequence in which the rail transit vehicle is called up at different points in time. The frequency is the intensity of use of the rail transit vehicle per unit of time. The active phase is the time interval in its life cycle during which the rail transit vehicle exhibits specific high-intensity or specific usage patterns, such as the "break-in period," "high-load operation period," and "aging and deterioration period." Specifically, the expected deployment time in the sorted sequence is aligned and mapped with historical or predicted usage data. By analyzing the distribution of the mapped data, periods with closely spaced usage sequences and significantly higher-than-average frequencies are identified and defined as active phases. For example, if a batch of rail transit vehicles is expected to be deployed intensively during the upcoming Spring Festival travel rush, and the usage frequency is extremely high during this period, then this time period is marked as the "peak active phase" for that rail transit vehicle. This process transforms static procurement quantities into dynamic time characteristics.

[0127] Subsequently, based on the active phases of the target rail transit vehicle, the cumulative consumption of the vehicle in different phases is calculated, forming phased consumption data. The cumulative consumption is the total lifespan loss of the rail transit vehicle due to factors such as wear and fatigue within a specific active phase. The phased consumption data is a structured dataset recording the cumulative consumption of the rail transit vehicle in each active phase, reflecting the non-linear characteristics of rail transit vehicle consumption.

[0128] In practice, for each identified active phase, a pre-set consumption model or historical statistical data is invoked to calculate the cumulative consumption within that phase. For example, during a "high-load operation period," the consumption per unit time may be much higher than during a "stable operation period." The calculation results from each phase are integrated to generate phased consumption data. This phased consumption data provides a detailed description of "how" and "how much" the rail transit vehicle consumes in different segments of its lifecycle.

[0129] Next, according to the rail transit vehicle combination configuration, the phased consumption data is mapped to the associated rail transit vehicles within the rail transit combination configuration. Here, rail transit vehicle combination configuration refers to a fixed combination scheme in a rail transit operation scenario where multiple rail transit vehicles must be used together or have a strong coupling relationship, such as the matching of "wheels" and "brake shoes," or the coordination of "pantograph" and "overhead contact maintenance tools." Associated rail transit vehicles refer to other tools in the combination configuration that have a collaborative working relationship with the target rail transit vehicle.

[0130] Specifically, the process involves reading a predefined rail transit vehicle combination configuration table and identifying all associated rail transit vehicles in the same configuration group as the target rail transit vehicle. Then, the phased consumption data of the target rail transit vehicle is projected or associated with these associated rail transit vehicles. The logic behind this step is that, in a combined configuration, the activity of the primary vehicle often implies that the supporting vehicles are also in a correspondingly active state, and their consumption is synchronous or related in both time and intensity dimensions.

[0131] Finally, the mapped, phased consumption data is dynamically overlaid to generate combined consumption data. Dynamic overlay refers to the process of weighted fusion and accumulation of phased consumption data from multiple rail transit vehicles based on the coordination intensity and real-time operating conditions among them. Combined consumption data is a data indicator reflecting the overall consumption trend and total amount of the entire vehicle combination under a specific configuration.

[0132] To achieve more precise dynamic overlay, this embodiment is further refined into the following three sub-steps.

[0133] The first sub-step involves determining the consumption rate of the rail transit vehicle in each active phase, based on the phased consumption data established earlier. The consumption rate refers to the rate at which the lifespan of the rail transit vehicle is depleted per unit time or unit number of operations.

[0134] The second sub-step involves calculating the active contribution value of the target rail transit vehicle within the combined configuration, based on the collaborative relationships and consumption rates of each vehicle. Collaborative relationships describe the degree of mutual influence among rail transit vehicles within the configuration, such as master-slave or parallel relationships. The active contribution value is a quantitative indicator that represents the driving weight or influence coefficient of the target rail transit vehicle's current active state on the overall combined consumption. If a rail transit vehicle is in a high-consumption-rate active phase and occupies a core position in the configuration, its active contribution value will be higher.

[0135] The third sub-step involves weighting the mapped phased consumption data based on the active contribution value, and then accumulating and superimposing the weighted phased consumption data across the rail transit vehicle combination configuration dimension to obtain combined consumption data. Specifically, the active contribution value is used as a weighting coefficient to adjust the phased consumption data mapped from the associated rail transit vehicles to reflect the actual impact of the target rail transit vehicles. Subsequently, the weighted and corrected phased consumption values ​​of all rail transit vehicles within the combined configuration are accumulated and superimposed on the same time axis or operating cycle to obtain combined consumption data.

[0136] The combined consumption data generated in this embodiment is no longer simply the sum of the consumption of individual rail transit vehicles, but fully considers the pairing logic between rail transit vehicles, the synchronicity of active phases, and the driving effect of core vehicles on overall consumption. For example, when the target rail transit vehicle enters a high-wear active phase, its high-activity contribution value will amplify the expected consumption of other supporting vehicles in the combination, thus showing a significant peak in the combined consumption data.

[0137] This embodiment identifies active phases by establishing a sorting sequence, constructs phased consumption data, and dynamically overlays it using a mechanism for combined configuration of rail transit vehicles and active contribution values. This successfully generates high-precision combined consumption data, which can truly reflect the linkage consumption characteristics of rail transit vehicles under complex formations and variable operating conditions. This lays a data foundation for adjusting the first replenishment purchase quantity using the combined consumption data to obtain a more accurate second replenishment purchase quantity.

[0138] In some other embodiments, the method for obtaining the tool life decay coefficient further includes: within each inventory counting cycle, using a neural network algorithm to construct a life prediction model for the cumulative usage index, thereby obtaining a rail transit tool life prediction model. Specifically, the life prediction model construction involves: obtaining historical cumulative usage data of rail transit tools based on the cumulative usage index; dividing the historical cumulative usage data into a dataset to obtain a model training set and a model test set; training the model on the model training set using a convolutional neural network algorithm to generate a rail transit tool life pre-model; using the model test set to perform model optimization iterations on the rail transit tool life pre-model, thereby generating a rail transit tool life prediction model; predicting the tool life based on the historical cumulative usage data using the rail transit tool life prediction model to obtain rail transit tool life prediction data; and adjusting the tool life reference value of the previous usage cycle based on the rail transit tool life prediction data to obtain an updated tool life decay coefficient.

[0139] Specifically, within each inventory counting cycle, a tool life prediction model is constructed based on a neural network algorithm to accurately predict the remaining lifespan of rail transit vehicles. First, historical cumulative usage data is used as input to the model, including usage frequency, usage time, and environmental factors. This data is preprocessed, standardized, or normalized to adapt to the input requirements of the neural network model. In the neural network design, a convolutional neural network is applied to the feature extraction layer to extract latent features from historical usage data. For example, through convolutional and pooling layers, the model can identify different usage patterns and workloads of the tools. Next, non-linear features are introduced into the model through activation functions (such as ReLU), thereby enhancing the model's fitting ability. Fully connected layers further fuse the features extracted by the convolutional layers, and optimization algorithms (such as Adam and SGD) are used to adjust the model parameters, ultimately outputting the remaining lifespan of the rail transit vehicle. The model output layer uses a linear activation function to ensure that the output is a continuous value, representing the remaining working time or remaining usage cycle of the rail transit vehicle.

[0140] Before building a predictive model, the historical accumulated data needs to be divided into training, validation, and test sets. A suitable ratio is 70%:15%:15%, where the training set is used for model training, the validation set for hyperparameter tuning, and the test set for final model evaluation. During training, the model continuously adjusts its weights and biases through forward and backpropagation, thereby improving prediction accuracy.

[0141] After initial model training, the model's predictive ability is evaluated using a test set. If the model's performance on the test set is unsatisfactory, optimization and hyperparameter adjustments are made as needed. Optimization may involve adjusting the convolutional kernel size, pooling method, learning rate, etc., to achieve higher predictive accuracy. The trained and optimized neural network model can predict the remaining lifespan of rail transit vehicles based on historical cumulative usage data. Based on the predicted remaining lifespan, the reference lifespan value for rail transit vehicles is further revised. In the previous usage cycle, based on the predicted remaining lifespan data, the reference lifespan value of the rail transit vehicle can be reduced to obtain an updated vehicle lifespan degradation coefficient. This ensures that the lifespan of rail transit vehicles more accurately reflects their actual usage, avoiding overuse or premature replacement.

[0142] Corresponding to the dynamic optimization method for rail transit vehicle inventory based on lifespan correction described in the above embodiments, the present invention also provides a dynamic optimization device for rail transit vehicle inventory based on lifespan correction.

[0143] Specifically, Figure 3 A schematic diagram of the structure of the dynamic optimization device for rail transit vehicle inventory based on lifespan correction provided in an embodiment of the present invention is shown.

[0144] like Figure 3 As shown, the device includes: a data acquisition module 310, used to acquire the number of times rail transit vehicles are used, the duration of each use, and the remaining inventory; an index determination module 320, used to determine the cumulative usage index of the rail transit vehicles based on the number of uses and the duration of each use; a coefficient correction module 330, used to reduce and correct the reference life value of the rail transit vehicles using the cumulative usage index in each inventory counting cycle to obtain a tool life attenuation coefficient; an inventory conversion module 340, used to convert the remaining inventory based on the tool life attenuation coefficient to obtain a life-equivalent inventory quantity; and a replenishment control module 350, used to trigger a replenishment signal and adjust the purchase quantity for the next cycle when the life-equivalent inventory quantity is lower than a safety threshold.

[0145] In this embodiment, the data acquisition module 310 acquires the number of times rail transit vehicles are used, the duration of each use, and the remaining inventory. The index determination module 320 determines the cumulative usage index of the rail transit vehicles based on the number of uses and the duration of each use. Then, the coefficient correction module 330 uses the cumulative usage index to reduce the reference value of the lifespan of the rail transit vehicles in each inventory counting cycle to obtain the tool lifespan decay coefficient. The inventory conversion module 340 converts the remaining inventory based on the tool lifespan decay coefficient to obtain the lifespan-equivalent inventory. Thus, the replenishment control module 350 triggers a replenishment signal and adjusts the purchase quantity for the next cycle when the lifespan-equivalent inventory is lower than the safety threshold. This device effectively solves the problem of inflated inventory or hidden shortages caused by ignoring the individual wear differences of rail transit vehicles by converting the traditional static inventory balance into a lifespan-equivalent inventory that reflects the true guarantee capacity. It ensures that replenishment decisions are based on the actual remaining lifespan rather than simple quantity statistics, ultimately achieving accurate dynamic adjustment of the purchase quantity, significantly reducing inventory backlog costs and ensuring the continuity of rail transit operations.

[0146] It should be noted that the rail transit vehicle inventory dynamic optimization device based on lifespan correction provided in this embodiment of the invention can be referred to in correspondence with the rail transit vehicle inventory dynamic optimization method based on lifespan correction described in the above embodiments, and will not be repeated here.

[0147] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a dynamic optimization method for rail transit vehicle inventory based on lifespan correction. This method includes: obtaining the number of times the rail transit vehicle is used, the duration of each use, and the remaining inventory; determining the cumulative usage index of the rail transit vehicle based on the number of uses and the duration of each use; in each inventory counting cycle, using the cumulative usage index to reduce and correct the reference value of the rail transit vehicle's lifespan to obtain a tool lifespan decay coefficient; calculating the remaining inventory based on the tool lifespan decay coefficient to obtain a lifespan-equivalent inventory quantity; and triggering a replenishment signal and adjusting the purchase quantity for the next cycle when the lifespan-equivalent inventory quantity is lower than a safety threshold.

[0148] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0149] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the dynamic optimization method for rail transit vehicle inventory based on lifespan correction provided by the above methods. The method includes: obtaining the number of times rail transit vehicles are used, the duration of each use, and the remaining inventory; determining the cumulative usage index of the rail transit vehicles based on the number of uses and the duration of each use; in each inventory counting cycle, using the cumulative usage index to reduce and correct the lifespan reference value of the rail transit vehicles to obtain a tool lifespan decay coefficient; calculating the remaining inventory based on the tool lifespan decay coefficient to obtain a lifespan-equivalent inventory quantity; and triggering a replenishment signal and adjusting the purchase quantity for the next cycle when the lifespan-equivalent inventory quantity is lower than a safety threshold.

[0150] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the above-described method for dynamic optimization of rail transit vehicle inventory based on lifespan correction. The method includes: obtaining the number of times a rail transit vehicle is used, the duration of a single use, and the remaining inventory; determining a cumulative usage index for the rail transit vehicle based on the number of uses and the duration of a single use; in each inventory counting cycle, using the cumulative usage index to reduce and correct the lifespan reference value of the rail transit vehicle to obtain a tool lifespan decay coefficient; calculating the remaining inventory based on the tool lifespan decay coefficient to obtain a lifespan-equivalent inventory quantity; and triggering a replenishment signal and adjusting the purchase quantity for the next cycle when the lifespan-equivalent inventory quantity is lower than a safety threshold.

[0151] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0152] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for dynamic optimization of rail transit vehicle inventory based on lifespan correction, characterized in that, include: Obtain information on the number of times rail transit vehicles are used, the duration of each use, and the remaining inventory. Based on the number of uses and the duration of each use, the cumulative usage index of the rail transit vehicle is determined; Within each inventory counting cycle, the cumulative usage index is used to reduce and correct the reference value of the rail transit vehicle's lifespan to obtain the vehicle's lifespan decay coefficient. The remaining inventory is calculated based on the tool life decay coefficient to obtain the life-equivalent inventory. If the lifetime equivalent inventory level falls below the safety threshold, a replenishment signal is triggered and the purchase quantity for the next cycle is adjusted.

2. The method for dynamic optimization of rail transit vehicle inventory based on lifespan correction according to claim 1, characterized in that, The determination of the cumulative usage index of the rail transit vehicle based on the number of uses and the duration of each use includes: The usage frequency and the duration of each single usage are paired and statistically analyzed to obtain stage usage data; The average usage load is calculated based on the usage data of the aforementioned stage to obtain the basic usage intensity data; The fatigue-corrected service strength is obtained by weighting and fusing the basic service strength data with the micro-fatigue superposition rate coefficient. The fatigue correction intensity is accumulated over time to obtain the cumulative usage index.

3. The method for dynamic optimization of rail transit vehicle inventory based on lifespan correction according to claim 2, characterized in that, The steps for obtaining the micro-fatigue superposition rate coefficient include: Obtain the material properties and category parameters of the rail transit vehicle; Based on the number of uses and the duration of a single use, determine the instantaneous usage intensity data for each usage cycle; Time series smoothing is performed on the instantaneous usage intensity data to obtain smoothed usage intensity data; Based on the smooth use strength data and the material properties, the fatigue accumulation factor for each use cycle is determined; The fatigue correction coefficient is obtained by linear calculation based on the fatigue accumulation factor and the number of uses; The micro-fatigue superposition rate coefficient is determined based on the fatigue correction coefficient and the category parameter.

4. The method for dynamic optimization of rail transit vehicle inventory based on lifespan correction according to claim 3, characterized in that, The step of determining the fatigue accumulation factor for each service cycle based on the smooth service strength data and the material properties includes: Based on the smooth use strength data and the hardness data in the material properties, calculate the material stress response value for each use cycle; Extract the material toughness from the material properties, and combine it with the material stress response value to determine the local fatigue increment for each service cycle; The cumulative amount of periodic fatigue is calculated based on the local fatigue increment and the duration of a single use in each use cycle. The fatigue accumulation factor is determined based on the cumulative periodic fatigue amount.

5. The method for dynamic optimization of rail transit vehicle inventory based on lifespan correction according to claim 4, characterized in that, The determination of the local fatigue increment for each service cycle based on the material stress response value includes: Extract material toughness parameters based on the aforementioned material properties; Based on the material toughness parameters and the material stress response values ​​for each service period, calculate the stress distribution correction amount of the material in each service period; The local fatigue increment is determined by the stress distribution correction amount and the smoothed service intensity data for each service cycle.

6. The method for dynamic optimization of rail transit vehicle inventory based on lifespan correction according to claim 2, characterized in that, The step of weighting and fusing the basic usage intensity data with the micro-fatigue superposition rate coefficient to obtain the fatigue-corrected usage intensity includes: Obtain the preset weight coefficients; Based on the basic usage intensity data for each usage cycle and the corresponding micro-fatigue superposition rate coefficient, the fatigue correction usage intensity is obtained by linearly combining the data according to the preset weight coefficient.

7. The method for dynamic optimization of rail transit vehicle inventory based on lifespan correction according to claim 1, characterized in that, The step of triggering a replenishment signal and adjusting the purchase quantity for the next cycle when the lifetime equivalent inventory level is lower than a safety threshold includes: If the lifetime equivalent inventory is lower than the safety threshold, determine the serial number of the target rail vehicle; The replenishment signal is triggered by the serial number to obtain the first replenishment purchase quantity; Based on the first replenishment procurement quantity, the combined consumption of the target rail transit vehicle is analyzed to obtain combined consumption data; The first replenishment purchase quantity is adjusted using the combined consumption data to obtain the second replenishment purchase quantity, which is used as the purchase quantity for the next inventory counting cycle.

8. The method for dynamic optimization of rail transit vehicle inventory based on lifespan correction according to claim 7, characterized in that, The step of analyzing the combined consumption of the target rail transit vehicle based on the first replenishment purchase quantity to obtain combined consumption data includes: Based on the first replenishment purchase quantity, establish a sorting sequence according to tool category and replenishment batch; The sorting sequence is mapped to the number of times the target rail transit vehicle is used within its usage cycle, and the active phase of the target rail transit vehicle is determined according to the usage order and frequency. Based on the active phase of the target rail transit vehicle, the cumulative consumption of the target rail transit vehicle in different phases is calculated to form phased consumption data; According to the rail transit vehicle combination configuration, the phased consumption data is mapped to the associated rail transit vehicles within the rail transit combination configuration, and the mapped phased consumption data is dynamically superimposed to generate the combined consumption data.

9. The method for dynamic optimization of rail transit vehicle inventory based on lifespan correction according to claim 8, characterized in that, The step of dynamically overlaying the mapped, staged consumption data to generate the combined consumption data includes: Determine the consumption rate of the rail transit vehicles corresponding to the first replenishment purchase quantity; The active contribution value of the target rail transit vehicle is calculated based on the combination configuration of rail transit vehicles and the consumption rate. The mapped phased consumption data is weighted based on the active contribution value, and the weighted phased consumption data is accumulated and superimposed on the rail transit vehicle combination configuration dimension to obtain the combined consumption data.

10. A dynamic optimization device for rail transit vehicle inventory based on lifespan correction, characterized in that, include: The data acquisition module is used to acquire the number of times rail transit vehicles are used, the duration of each use, and the remaining inventory. An index determination module is used to determine the cumulative usage index of the rail transit vehicle based on the number of uses and the duration of a single use. The coefficient correction module is used to reduce and correct the reference value of the life of rail transit vehicles by the cumulative usage index in each inventory counting cycle, so as to obtain the tool life decay coefficient. The inventory conversion module is used to convert the remaining inventory based on the tool's lifespan decay coefficient to obtain the lifespan-equivalent inventory. The replenishment control module is used to trigger a replenishment signal and adjust the purchase quantity for the next cycle when the lifetime equivalent inventory is lower than the safety threshold.

Images