Rail transit operation and maintenance resource dynamic scheduling optimization method, system, equipment and medium

Abstract

The invention relates to the technical field of rail transit, and discloses a rail transit operation and maintenance resource dynamic scheduling optimization method, system and device and a medium. The method comprises the following steps: acquiring multi-source data, and performing data preprocessing on the multi-source data to obtain equipment health state estimation and real-time passenger flow distribution; performing digital twin modeling based on equipment health state estimation and real-time passenger flow distribution to obtain an equipment health prediction model and an operation and resource model; establishing a multi-objective optimization model based on the equipment health prediction model and the job and resource model; and solving the multi-objective optimization model to generate an operation and maintenance resource scheduling optimization scheme. According to the method, deep analysis and integrated processing are carried out on multi-source data, an equipment health prediction model and a job and resource model are established, data are accessed in real time, an operation and maintenance resource scheduling optimization scheme is generated by utilizing constraint conditions of a multi-objective optimization model and a multi-objective optimization method and is output and executed, and integrated modeling of job, resources and constraints is realized. And cross-professional and multi-resource dynamic scheduling optimization is realized.

Description

Technical Field

[0001] This invention relates to the field of rail transit technology, and in particular to a method, system, equipment and medium for dynamic scheduling and optimization of rail transit operation and maintenance resources. Background Technology

[0002] Currently, rail transit operation and maintenance scheduling primarily relies on static maintenance plans and manual dispatching, lacking real-time consideration of the dynamic changes in equipment health status and passenger flow. In complex network conditions and high-passenger-flow scenarios, traditional methods struggle to respond promptly to sudden faults, easily leading to uneven allocation of maintenance resources, mismatched spare parts, empty runs by personnel, and excessively long average repair times. Furthermore, existing systems do not adequately consider constraints related to work windows (maintenance windows), section interlocks, and cross-disciplinary collaborative operations, resulting in low efficiency during emergency repairs or multi-disciplinary joint maintenance, increasing potential risks to train safety and punctuality. Summary of the Invention

[0003] The main objective of this invention is to provide a method, system, equipment, and medium for dynamic scheduling and optimization of rail transit operation and maintenance resources, aiming to solve at least one of the aforementioned technical problems.

[0004] In a first aspect, embodiments of the present invention provide a method for dynamic scheduling and optimization of rail transit operation and maintenance resources, including:

[0005] Acquire multi-source data, perform data preprocessing on the multi-source data, and obtain equipment health status estimation and real-time passenger flow distribution;

[0006] Based on the equipment health status estimation and real-time passenger flow distribution, digital twin modeling is performed to obtain the equipment health prediction model and the operation and resource model;

[0007] A multi-objective optimization model is established based on the equipment health prediction model and the operation and resource model.

[0008] Solve the multi-objective optimization model to generate an optimization scheme for operation and maintenance resource scheduling.

[0009] In some embodiments, acquiring multi-source data and performing data preprocessing on the multi-source data to obtain equipment health status estimates and real-time passenger flow distribution includes:

[0010] The data is collected from multiple sources based on the physical system of rail transit; wherein, the multiple sources of data include vehicle equipment operation monitoring data, train scheduling data, signal and train control data, passenger flow data, environmental information and sensor data;

[0011] The multi-source data is spatiotemporally aligned and noise-processed to obtain equipment health status estimates and real-time passenger flow distribution.

[0012] In some embodiments, performing spatiotemporal alignment and noise processing on the multi-source data to obtain equipment health status estimates and real-time passenger flow distribution includes:

[0013] The multi-source data is uniformly encoded and cleaned to obtain processed data;

[0014] Based on the extended Kalman filter and the processed data, data fusion and state estimation are performed to obtain equipment health status estimates and real-time passenger flow distribution.

[0015] In some embodiments, the step of performing digital twin modeling based on the equipment health status estimate and real-time passenger flow distribution to obtain an equipment health prediction model and an operation and resource model includes:

[0016] Based on the equipment health status estimation and real-time passenger flow distribution, the real-time operation status of the subway is modeled to obtain the equipment health prediction model.

[0017] Based on the equipment health status estimation and real-time passenger flow distribution, the operation and maintenance resources are modeled to obtain the operation and resource model.

[0018] In some embodiments, the step of modeling the real-time operating status of the subway based on the equipment health status estimate and real-time passenger flow distribution to obtain an equipment health prediction model includes:

[0019] Based on the equipment health status estimation combined with historical failure rate data and equipment remaining life prediction data, an equipment failure probability distribution model is established.

[0020] Establish a passenger flow impact model based on real-time passenger flow distribution;

[0021] Based on the equipment failure probability distribution model and the operation impact model, an equipment health prediction model is obtained.

[0022] In some embodiments, establishing a multi-objective optimization model based on the equipment health prediction model and the job and resource model includes:

[0023] Constraints are constructed based on the equipment health prediction model and the operation and resource model; wherein, the constraints include time constraints, space constraints and resource constraints;

[0024] Construct an objective function based on the equipment health prediction model and the operation and resource model;

[0025] A multi-objective optimization model is established based on the constraints and objective function.

[0026] In some embodiments, the method further includes:

[0027] The operational resource scheduling optimization scheme was implemented to obtain actual operational results;

[0028] The model parameters are adjusted based on the actual operational results; wherein the model parameters include extended Kalman filter parameters, failure rate distribution, travel time distribution, and objective function weights.

[0029] Secondly, embodiments of the present invention provide a dynamic scheduling and optimization system for rail transit operation and maintenance resources, comprising:

[0030] The data acquisition module is used to acquire multi-source data, perform data preprocessing on the multi-source data, and obtain equipment health status estimates and real-time passenger flow distribution.

[0031] The digital twin modeling module is used to perform digital twin modeling based on the equipment health status estimate and real-time passenger flow distribution to obtain an equipment health prediction model and an operation and resource model.

[0032] The optimization modeling module is used to establish a multi-objective optimization model based on the equipment health prediction model and the operation and resource model.

[0033] The optimization scheme generation module is used to solve the multi-objective optimization model and generate an optimization scheme for operation and maintenance resource scheduling.

[0034] Thirdly, embodiments of the present invention provide an electronic device, including:

[0035] One or more processors;

[0036] Memory, used to store one or more programs;

[0037] When the one or more programs are executed by the one or more processors, the one or more processors implement any of the methods described above.

[0038] Fourthly, embodiments of the present invention provide a computer-readable medium on which a computer program is stored, the computer program being executed by a processor to implement the steps of any of the methods described above.

[0039] This invention provides a dynamic scheduling optimization method for rail transit operation and maintenance resources, comprising: acquiring multi-source data; preprocessing the multi-source data to obtain equipment health status estimates and real-time passenger flow distribution; performing digital twin modeling based on the equipment health status estimates and real-time passenger flow distribution to obtain an equipment health prediction model and an operation and resource model; establishing a multi-objective optimization model based on the equipment health prediction model and the operation and resource model; solving the multi-objective optimization model to generate an operation and maintenance resource scheduling optimization scheme. This invention performs in-depth analysis and integrated processing of multi-source data from the physical system, establishes an equipment health prediction model and an operation and resource model, accesses physical system data in real time, utilizes the constraints of the multi-objective optimization model and multi-objective optimization methods to generate and execute an operation and maintenance resource scheduling optimization scheme, thus achieving a closed loop of "physical system-twin system-decision optimization," integrated modeling of operations, resources, and constraints, and uniformly considering constraints such as personnel, spare parts, maintenance windows, and section interlocks, thereby realizing dynamic scheduling optimization across disciplines and multiple resources. Attached Figure Description

[0040] Figure 1 A flowchart illustrating a dynamic scheduling optimization method for rail transit operation and maintenance resources provided in an embodiment of the present invention;

[0041] Figure 2 This is a flowchart illustrating the implementation methods of the present invention.

[0042] Figure 3 This is a flowchart illustrating the dynamic scheduling process of rail transit operation and maintenance resources based on digital twins, as described in an embodiment of the present invention.

[0043] Figure 4 A structural block diagram of a dynamic scheduling and optimization system for rail transit operation and maintenance resources provided in an embodiment of the present invention;

[0044] Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present invention.

[0045] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0046] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0047] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0048] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0049] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0050] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0051] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0052] This invention provides a method for dynamic scheduling and optimization of rail transit operation and maintenance resources. Figure 1 This is a flowchart illustrating a dynamic scheduling optimization method for rail transit operation and maintenance resources provided in an embodiment of the present invention.

[0053] As one embodiment of the present invention, such as Figure 1 As shown, the dynamic scheduling and optimization method for rail transit operation and maintenance resources includes:

[0054] Step S100: Acquire multi-source data, perform data preprocessing on the multi-source data, and obtain equipment health status estimation and real-time passenger flow distribution;

[0055] Step S200: Based on the equipment health status estimate and real-time passenger flow distribution, perform digital twin modeling to obtain the equipment health prediction model and the operation and resource model;

[0056] Step S300: Establish a multi-objective optimization model based on the equipment health prediction model and the operation and resource model;

[0057] Step S400: Solve the multi-objective optimization model to generate an operation and maintenance resource scheduling optimization scheme.

[0058] It should be noted that the execution subject in this embodiment can be an electronic device, which can be a computer device with data processing function, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment, a computer device is used as an example for explanation.

[0059] It is understood that the method proposed in this embodiment is a dynamic scheduling optimization method for rail transit operation and maintenance resources based on digital twins. It aims to address the shortcomings of related technologies in areas such as the disconnect between equipment health prediction and passenger flow impact, insufficient dynamic scheduling capabilities, and lack of robustness to uncertainty, thereby achieving efficient resource allocation and comprehensive management of operational risks. The digital twin system can be composed of a data-information-knowledge management layer, a digital twin-simulation layer, and a strategy layer. The digital twin system performs in-depth analysis and integrated processing of multi-source sensing data from the physical system, transforming the data into information and knowledge. It then applies the constructed physical model and algorithms to simulate various operational scenarios and emergency situations, assessing potential risks and hazards in the system, and formulating corresponding control strategies to act on the physical system.

[0060] In some embodiments, acquiring multi-source data and preprocessing the multi-source data to obtain equipment health status estimates and real-time passenger flow distribution includes: collecting multi-source data based on the rail transit physical system; wherein the multi-source data includes vehicle equipment operation monitoring data, train scheduling data, signal and train control data, passenger flow data, environmental information, and sensor data; and performing spatiotemporal alignment and noise processing on the multi-source data to obtain equipment health status estimates and real-time passenger flow distribution.

[0061] In some embodiments, spatiotemporal alignment and noise processing are performed on the multi-source data to obtain equipment health status estimates and real-time passenger flow distribution, including: uniformly encoding and cleaning the multi-source data to obtain processed data; and performing data fusion and status estimation based on extended Kalman filtering and the processed data to obtain equipment health status estimates and real-time passenger flow distribution.

[0062] Specifically, multi-source data is collected, including Supervisory Control and Data Acquisition (SCADA) data, Signaling / Train Control System (CBTC) data, Automatic Flow Control (AFC) data, Automatic Train Service (ATS) data, field sensor / Internet of Things (IoT) data, and environmental information. Data from different time scales and spatial coordinates are uniformly encoded and cleaned. Extended Kalman Filter (EKF) is used to process the sensor data to obtain equipment health status estimates and real-time passenger flow distribution.

[0063] For example, the multi-source data acquisition objects include six core data categories, corresponding to different aspects of the rail transit system. Among them, Supervisory Control and Data Acquisition (SCADA) data originates from the Supervisory Control and Data Acquisition system, covering real-time operating parameters (e.g., voltage, current, temperature, pressure) of equipment such as power supply, signaling, ventilation, and elevators, reflecting the physical state of the equipment and serving as the basis for fault diagnosis. Signal / Train Control (CBTC) data originates from the Communication-Based Train Control system, including train position, speed, intervals, and signal status, ensuring safe train operation and providing core data on train dynamics. Passenger Flow System (AFC) data originates from the Automatic Fare Collection system, including entry and exit gate records and ticketing data (e.g., passenger flow, peak hours, OD passenger flow distribution), reflecting passenger behavior and serving as the basis for passenger flow analysis.

[0064] For example, Train Operation Scheduling (ATS) data originates from the Automatic Train Supervision system and includes train timetables, actual operation diagrams, delay information, and dispatching instructions. This data correlates train plans with actual operations and is used to evaluate efficiency and optimize scheduling. Field sensor / Internet of Things (IoT) data comes from various sensors deployed on tracks, in stations, and in carriages (e.g., vibration sensors, temperature and humidity sensors, cameras, infrared detectors), supplementing details not covered by SCADA (e.g., track settlement, carriage congestion) to achieve "ubiquitous sensing." Environmental information comes from meteorological data (e.g., rainfall, high temperatures), geological data (e.g., ground subsidence), and surrounding traffic data, analyzing the impact of external factors on the system (e.g., heavy rain may cause signal failures or a surge in passenger flow).

[0065] Specifically, such as Figure 2 and Figure 3As shown, data preprocessing involves real-time data collection from physical systems (including SCADA for equipment operation monitoring, ATS for train dispatching, CBTC for signaling systems, AFC for passenger flow data, and environmental and inventory data). The data includes passenger flow data, vehicle equipment operation monitoring data, signaling and train control data, environmental information, and sensor data. Data from different time scales and spatial coordinates is uniformly encoded and cleaned, and extended Kalman filtering (EKF) is used to process the sensor data. Under complex noise and nonlinear conditions, multi-source sensor data is filtered to eliminate noise, generate predicted values, and obtain optimal estimates of the health status and operating parameters of key equipment, providing reliable support for fault detection, health monitoring, and predictive maintenance.

[0066] For example, for data such as train speed and voltage with input control such as traction, braking commands, and switching operations, the state equation is established using formula (1). ω represents disturbances and uncertainties that the model fails to capture, such as air resistance and slippage in train speed prediction; and sudden load fluctuations, regenerative braking, and electromagnetic interference in grid voltage prediction. For variables such as humidity and temperature without input control, the state equation can be established using formula (2). In this case, ω represents the random fluctuations of the environment itself. The covariance update formula is used to update the magnitude of the "uncertainty" of the system state during the prediction stage, so that the filter can reasonably balance "believing the model" or "believing the measurement" in subsequent updates. The prior estimated covariance matrix can provide a basis for determining the next predicted value. The covariance update formula is shown in formula (3):

[0067] (1)

[0068] (2)

[0069] (3)

[0070] Where f represents the state transition matrix of the physical system; This represents the predicted prior state value at time k; This represents the posterior state prediction at time k-1; Indicates input control; ω k-1 Indicates process noise; Let represent the prior estimate covariance matrix at time k; Let represent the posterior estimated covariance matrix at time k-1; The first-order Jacobian of the state equation; This represents the process noise covariance matrix.

[0071] In one example, by establishing standardized data models, such as spatiotemporal coordinate transformation, unified equipment IDs, and standardized indicator definitions, multi-source data is mapped to the same data platform. Data cleaning can handle noise and missing values ​​through methods such as filtering, interpolation, and anomaly detection to ensure data availability. Rail transit systems are dynamic nonlinear systems, and the Extended Kalman Filter (EKF) is a classic algorithm for state estimation in nonlinear systems (achieved through linearization approximation). Data fusion and state estimation combine predictive models such as equipment degradation models, passenger flow prediction models, and real-time observation data, and through prediction-correction iteration, output the optimal state estimate.

[0072] For example, equipment health status estimation: Based on SCADA and IoT sensor data such as vibration and temperature, combined with the equipment's physical degradation model such as motor life curve, noise is filtered out by EKF, and the equipment's health index such as remaining life and failure probability is calculated in real time to achieve predictive maintenance (rather than passive repair).

[0073] For example, real-time passenger flow distribution: By integrating AFC data (total number of passengers entering and leaving the station), IoT camera data (crowding in carriages / platforms), and ATS train location data, the passenger flow prediction model is dynamically corrected through EKF, for example, taking into account the impact of train delays on passenger evacuation, and outputting a refined real-time passenger flow distribution, such as the number of people in each area of ​​the platform and the crowding in the carriages.

[0074] In some embodiments, digital twin modeling is performed based on the equipment health status estimate and real-time passenger flow distribution to obtain an equipment health prediction model and an operation and resource model, including: modeling the real-time operation status of the subway based on the equipment health status estimate and real-time passenger flow distribution to obtain an equipment health prediction model; and modeling operation and maintenance resources based on the equipment health status estimate and real-time passenger flow distribution to obtain an operation and resource model.

[0075] In some embodiments, the real-time operation status of the subway is modeled based on the equipment health status estimate and real-time passenger flow distribution to obtain an equipment health prediction model, including: establishing an equipment failure probability distribution model based on the equipment health status estimate combined with historical failure rate data and equipment remaining life prediction data; establishing a passenger flow impact model based on real-time passenger flow distribution; and obtaining an equipment health prediction model based on the equipment failure probability distribution model and the operation impact model.

[0076] It should be noted that in this embodiment, various equipment monitoring data and passenger flow information need to be accessed in real time within the digital twin system; the digital twin system automatically generates a candidate job list and constraints, runs a rolling optimization module to obtain a resource allocation plan; tasks are assigned to personnel and vehicles for execution, and feedback information is collected for model correction. This approach is suitable for daily maintenance and emergency repair scenarios involving multiple lines and disciplines.

[0077] Understandably, reference Figure 3 , Figure 3 This study demonstrates a digital twin-based approach to rail transit operation and maintenance resource scheduling. The bottom layer is the physical system, including Supervisory Control and Data Acquisition (SCADA), Automatic Train Service (ATS), Signalling System (CBTC), Passenger Flow Data (AFC), and environmental and inventory information. The middle layer is the digital twin system, which establishes equipment health prediction models, passenger flow prediction models, and operation and resource models, and integrates physical system data in real time. The top layer is the decision-making layer, which uses generated constraints and multi-objective optimization methods to formulate scheduling schemes and output execution results. Overall, this achieves a closed loop of "physical system - digital twin system - decision optimization."

[0078] Specifically, such as Figure 2 and Figure 3 As shown, digital twin modeling involves constructing an equipment health prediction model: Through remaining useful life (RUL) prediction, failure rate λ(t), and vibration / temperature rise characteristic diagnosis, the probability distribution of equipment failure is obtained. Based on FMECA, Heinrich's law, and equipment criticality, risk weights are assigned to different operations. Operation and resource modeling includes operation information such as location, skill requirements, time windows, duration, section interlock attributes, and spare parts requirements; personnel resources such as skill matrices, shift times, working hour limits, location, and attendance costs; and the location and available time periods of maintenance vehicles and track maintenance vehicles. Spare parts resources include warehouse location, current inventory, in-transit quantity, and replenishment time.

[0079] Specifically, the modeling process of digital twins includes two parts: first, modeling the real-time operating status of the subway, and second, modeling the existing operation and maintenance resources.

[0080] For example, 1) Modeling the real-time operation status of the subway: First, it is necessary to process the data collected by the sensors of various equipment in the subway operation, and analyze the probability distribution of equipment failure based on historical failure rate data and equipment remaining life prediction data. Second, it is necessary to detect passenger flow and establish a model of the impact of operations on passenger delays and congestion.

[0081] (1) Common historical failure rates follow three types of curves: exponential distribution, Weibull distribution, and log-normal distribution. The failure rate function and the equipment survival probability function are shown below:

[0082] ① Exponential distribution

[0083] (4)

[0084] (5)

[0085] ②Weibull distribution

[0086] (6)

[0087] (7)

[0088] ③ Log-normal distribution

[0089] (8)

[0090] (9)

[0091] If the device is still running at time t0, then the conditional density of the remaining lifetime (RUL) is:

[0092] (10)

[0093] The probability of a failure occurring in the next H hours:

[0094] (11)

[0095] Based on the above historical failure rate analysis and remaining life analysis, and according to the observed value s obtained from equipment operation monitoring, t This is used to determine whether equipment maintenance is required.

[0096] Convert the prior failure rate into the prior odds:

[0097] (12)

[0098] Among them, P prior This indicates the probability of a failure occurring in the next operating cycle.

[0099] The likelihood ratio represents the "relative probability" of a sensor malfunction occurring given a given piece of evidence *s*, between the possibility of a malfunction and the possibility of no malfunction. The likelihood ratio can be estimated using historical data annotations.

[0100] (13)

[0101] Where TPR represents the sensor observation value reached in the event of a fault. t The ratio; LR(s) is the likelihood ratio when sensor evidence s appears.

[0102] The posterior probability obtained by combining the prior probability and the device's monitoring sensors is:

[0103] (14)

[0104] When p post If the value is continuously greater than 0.6, it is determined that the equipment needs to be operated.

[0105] For example, 2) Job and maintenance resource modeling: quantifying job information and maintenance resources into variables. This mainly includes three parts: set variables, input parameters, and decision variables.

[0106] ① Set: Station / location is S; job is J, job location is loc(j)∈S. Interlocked section / conflict zone is B, job belongs to section b(j)∈B. Time slot (step size Δ minutes) is T={1,…,|T|}. Skill type is K; personnel is R. Spare parts category is P; warehouse is W.

[0107] ② Input parameters: [a j b j ]∈T represents the allowed start time window for job j; d j ∈N represents the duration; r jk ∈N represents the number of people required for skill k in task j; q jp ∈N represents the quantity of spare part p required by task j; skillr k ∈{0,1} indicates whether person r possesses skill k; shiftr t ∈{0,1} indicates whether personnel r is on duty at time t; Hr indicates the upper limit of working hours for personnel r; Swp indicates the current inventory of product category p in warehouse w; Lws indicates the lead time for resupply from warehouse w to delivery station s.

[0108] ③ Decision variable: x jt ∈{0,1} indicates whether operation j starts in slot t; g jt ∈{0,1} indicates whether job j is being executed in slot t; u rjt ∈Z≥0 indicates whether personnel r is assigned to task j within time t; ∈Z≥0 indicates that the quantity of product type p is transferred from warehouse w by operation j.

[0109] For example, 3) The impact model of operations on passenger congestion and delays. The impact model of operations on passenger congestion and delays:

[0110] (15)

[0111] Where 'a' represents the monetized cost per unit delay time; 'n' represents the number of passengers entering the station after the most recent train departure; and 'T' represents the number of passengers entering the station after the most recent train departure. f Indicates the time of the most recent departure; T di Indicates the time when passenger i enters the station; t j This indicates the approximate time delay caused by a hypothetical task.

[0112] In one example, equipment health prediction modeling: Based on preprocessed data, combined with historical failure rate distributions (exponential distribution, Weibull distribution, log-normal distribution, formulas (4)-(9)), the remaining lifespan (RUL, formulas (10)-(11)) and failure probability of the equipment are calculated. Whether the equipment needs maintenance is determined by Bayesian updates (prior odds formula (12), likelihood ratio formula (13), and posterior probability formula (14)): when the posterior probability p... post When the value is continuously greater than 0.6, a candidate job list is generated.

[0113] In one example, passenger flow impact modeling: Based on AFC data and IoT sensors (e.g., cameras), an impact model of the operation on passenger delays and congestion is established (Formula (15)), and the monetization cost of passenger flow delays is quantified (e.g., cost per unit delay time × number of affected people).

[0114] In this embodiment, the deep coupling of equipment health prediction and passenger flow prediction during digital twin implementation combines RUL prediction and failure rate evolution, enabling scheduling objectives to simultaneously consider safety and service level. Furthermore, the integrated modeling of operational resources and constraints uniformly considers limitations such as personnel, spare parts, maintenance windows, and section interlocks, thereby achieving dynamic scheduling optimization across disciplines and multiple resources.

[0115] In some embodiments, establishing a multi-objective optimization model based on the equipment health prediction model and the operation and resource model includes: constructing constraints based on the equipment health prediction model and the operation and resource model; wherein the constraints include time constraints, space constraints, and resource constraints; constructing an objective function based on the equipment health prediction model and the operation and resource model; and establishing a multi-objective optimization model based on the constraints and the objective function.

[0116] Specifically, such as Figure 3 As shown, constraint generation involves generating a work permit time schedule based on traffic organization rules and track maintenance plans. This ensures that personnel possess the necessary skills. Time and continuity constraints limit total personnel working hours and guarantee travel time between tasks. It also prevents mutually exclusive tasks from occurring simultaneously in the same section. Finally, it ensures that necessary spare parts are available in a timely manner.

[0117] Specifically, such as Figure 3 As shown, the optimization model is implemented. The objective function is to minimize the overall cost, including equipment downtime, passenger delays, personnel attendance / overtime costs, travel costs, and material allocation costs. Decision variables include whether the task is executed, personnel allocation, task start and end times, and spare parts allocation. Multi-objective optimization employs a weighted approach, unifying reliability and economy.

[0118] For example, optimization modeling and constraint generation

[0119] (1) Constraint generation:

[0120] ① Job time window and continuous occupation:

[0121] (16)

[0122] ②Section Interlocking:

[0123] (17)

[0124] ③Skills coverage and personnel availability:

[0125] The number of workers needs to meet the personnel requirements:

[0126] (18)

[0127] Workers will be selected from those currently on duty.

[0128] (19)

[0129] The assignment time is less than the maximum assignment time limit:

[0130] (20)

[0131] ④ Spare parts and pre-delivery preparation:

[0132] (twenty one)

[0133] (2) Objective function:

[0134] ① Expected risk of not performing the task:

[0135] (twenty two)

[0136] ② The direct costs of operations include the cost of downtime, the cost of passenger traffic, and the cost of spare parts consumption.

[0137] (twenty three)

[0138] in, Indicates the direct cost of the task; Indicates the weight of the operation stoppage cost; This represents the loss caused by the operational interruption time t resulting from task j; Indicates the weighting of passenger delay costs; This indicates the loss caused to passengers by operation j within time t; Indicates the cost weight of spare parts consumption; This represents the consumption cost of spare parts p from warehouse w at site s.

[0139] ③ Personnel costs include employee wages, overtime pay, and travel expenses.

[0140] (twenty four)

[0141] in, Indicates personnel costs; Indicates the weight of personnel costs; This represents the salary of the person r who works during time t. This represents the cost of overtime per hour for employee r; Indicates overtime hours for employees; Indicates the weight of travel expense costs; This refers to the travel expenses of personnel (r). This indicates whether person r moves from s to s' within time t.

[0142] The objective function is shown in equation (25). When the objective function reaches its minimum, an optimization scheme for scheduling operation and maintenance resources is generated.

[0143] (25)

[0144] in, This indicates the weight of the loss caused by not performing the task.

[0145] If the task is not performed, then e j =0, and will bear the expected risk; if the operation is performed, then e j =1.

[0146] W = (w rel w dt w pax w att w travel w part ) are the weights of different costs in the objective function.

[0147] In some embodiments, the method further includes: executing the operation and maintenance resource scheduling optimization scheme to obtain actual operating results; adjusting model parameters according to the actual operating results; wherein the model parameters include extended Kalman filter parameters, failure rate distribution, travel time distribution, and objective function weights.

[0148] Specifically, such as Figure 2 As shown, the execution and feedback process involves sending scheduling plans to the dispatching system and mobile terminals, completing personnel check-in, progress reporting, and risk alerts. Execution deviations (such as delays, material shortages, and personnel absences) are fed back in real time to calibrate model parameters and travel time distribution, and to dynamically adjust the target weights of reliability priority and cost priority based on execution feedback.

[0149] For example, adjust the model parameters based on the actual running results:

[0150] First initialize wk (k∈{rel, dt, pax, att, travel, part})=1. Solve the optimization model, execute the results of the optimization model, and calculate the proportion of each cost. Let the proportion of each cost in the previous period be:

[0151] (26)

[0152] Give each item an expected percentage At the end of each cycle, the weights are updated using multiplication to obtain new weights. :

[0153] (27)

[0154] In one example, execution deviations such as job delays, personnel absences, and spare parts shortages are collected and transmitted back to the digital twin system in real time. Dynamic correction model: Based on the feedback data, the EKF filter parameters, failure rate distribution, travel time distribution, and objective function weights are adjusted (Formulas (26)-(27)) to ensure that the next round of optimization is more in line with the actual scenario.

[0155] This embodiment provides a method for dynamic scheduling optimization of rail transit operation and maintenance resources, including: acquiring multi-source data; preprocessing the multi-source data to obtain equipment health status estimates and real-time passenger flow distribution; performing digital twin modeling based on the equipment health status estimates and real-time passenger flow distribution to obtain an equipment health prediction model and an operation and resource model; establishing a multi-objective optimization model based on the equipment health prediction model and the operation and resource model; solving the multi-objective optimization model to generate an operation and maintenance resource scheduling optimization scheme. This embodiment performs in-depth analysis and integrated processing of multi-source data from the physical system, establishes an equipment health prediction model and an operation and resource model, accesses physical system data in real time, and uses the constraints of the multi-objective optimization model and multi-objective optimization methods to generate and execute an operation and maintenance resource scheduling optimization scheme. This achieves a closed loop of "physical system-twin system-decision optimization," integrated modeling of operations, resources, and constraints, and unified consideration of constraints such as personnel, spare parts, maintenance windows, and section interlocks, thereby realizing dynamic scheduling optimization across disciplines and multiple resources.

[0156] Reference Figure 4 , Figure 4 This is a structural block diagram of an embodiment of the dynamic scheduling and optimization system for rail transit operation and maintenance resources of the present invention. Figure 4 As shown, the dynamic scheduling and optimization system for rail transit operation and maintenance resources includes:

[0157] Data acquisition module 10 is used to acquire multi-source data, perform data preprocessing on the multi-source data, and obtain equipment health status estimation and real-time passenger flow distribution;

[0158] The digital twin modeling module 20 is used to perform digital twin modeling based on the equipment health status estimation and real-time passenger flow distribution to obtain an equipment health prediction model and an operation and resource model.

[0159] The optimization modeling module 30 is used to establish a multi-objective optimization model based on the equipment health prediction model and the operation and resource model.

[0160] The optimization scheme generation module 40 is used to solve the multi-objective optimization model and generate an operation and maintenance resource scheduling optimization scheme.

[0161] In this embodiment, the dynamic scheduling and optimization system for rail transit operation and maintenance resources performs in-depth analysis and integrated processing of multi-source data from the physical system, establishes equipment health prediction models and operation and resource models, accesses data from the physical system in real time, and generates and executes operation and maintenance resource scheduling optimization schemes using the constraints of multi-objective optimization models and multi-objective optimization methods. The system achieves a closed loop of "physical system-twin system-decision optimization", integrates operation, resource and constraint modeling, and uniformly considers constraints such as personnel, spare parts, maintenance windows, and section interlocks, thereby realizing dynamic scheduling and optimization across disciplines and multiple resources.

[0162] It should be noted that technical details not described in detail in this embodiment of the dynamic scheduling and optimization system for rail transit operation and maintenance resources can be found in any embodiment of the present invention applied to the dynamic scheduling and optimization method for rail transit operation and maintenance resources as described above, and will not be repeated here.

[0163] Based on the same inventive concept, embodiments of the present invention also provide an electronic device. Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, which, when executed by the one or more processors, enable the one or more processors to implement any of the dynamic scheduling optimization methods for rail transit operation and maintenance resources described in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, configured to enable information interaction between the processor and the memory.

[0164] The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus).

[0165] In some embodiments, the processor 101, memory 102, and I / O interface 103 are interconnected via bus 104, and thus connected to other components of the computing device.

[0166] In some embodiments, the one or more processors 101 include a field-programmable gate array.

[0167] This invention also provides a computer-readable medium. The computer-readable medium stores a computer program, which, when executed by a processor, implements the steps of any of the dynamic scheduling optimization methods for rail transit operation and maintenance resources described in the above embodiments. The computer-readable storage medium can be volatile or non-volatile.

[0168] This invention also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the above-described dynamic scheduling optimization method for rail transit operation and maintenance resources.

[0169] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0170] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0171] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0172] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0173] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0174] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0175] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0176] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0177] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0178] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

Claims

1. A method for dynamic scheduling and optimization of rail transit operation and maintenance resources, characterized in that, include: Acquire multi-source data, perform data preprocessing on the multi-source data, and obtain equipment health status estimation and real-time passenger flow distribution; Based on the equipment health status estimation and real-time passenger flow distribution, digital twin modeling is performed to obtain the equipment health prediction model and the operation and resource model; A multi-objective optimization model is established based on the equipment health prediction model and the operation and resource model. Solve the multi-objective optimization model to generate an optimization scheme for operation and maintenance resource scheduling.

2. The method as described in claim 1, characterized in that, The process of acquiring multi-source data, performing data preprocessing on the multi-source data, and obtaining equipment health status estimates and real-time passenger flow distribution includes: The data is collected from multiple sources based on the physical system of rail transit; wherein, the multiple sources of data include vehicle equipment operation monitoring data, train scheduling data, signal and train control data, passenger flow data, environmental information and sensor data; The multi-source data is spatiotemporally aligned and noise-processed to obtain equipment health status estimates and real-time passenger flow distribution.

3. The method as described in claim 2, characterized in that, The process of performing spatiotemporal alignment and noise processing on the multi-source data to obtain equipment health status estimates and real-time passenger flow distribution includes: The multi-source data is uniformly encoded and cleaned to obtain processed data; Based on the extended Kalman filter and the processed data, data fusion and state estimation are performed to obtain equipment health status estimates and real-time passenger flow distribution.

4. The method as described in claim 1, characterized in that, The process of performing digital twin modeling based on the equipment health status estimate and real-time passenger flow distribution to obtain an equipment health prediction model and an operation and resource model includes: Based on the equipment health status estimation and real-time passenger flow distribution, the real-time operation status of the subway is modeled to obtain the equipment health prediction model. Based on the equipment health status estimation and real-time passenger flow distribution, the operation and maintenance resources are modeled to obtain the operation and resource model.

5. The method as described in claim 4, characterized in that, The process of modeling the real-time operation status of the subway based on the equipment health status estimate and real-time passenger flow distribution to obtain an equipment health prediction model includes: Based on the equipment health status estimation combined with historical failure rate data and equipment remaining life prediction data, an equipment failure probability distribution model is established. Establish a passenger flow impact model based on real-time passenger flow distribution; Based on the equipment failure probability distribution model and the operation impact model, an equipment health prediction model is obtained.

6. The method as described in claim 1, characterized in that, The establishment of a multi-objective optimization model based on the equipment health prediction model and the operation and resource model includes: Constraints are constructed based on the equipment health prediction model and the operation and resource model; wherein, the constraints include time constraints, space constraints and resource constraints; Construct an objective function based on the equipment health prediction model and the operation and resource model; A multi-objective optimization model is established based on the constraints and objective function.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: The operational resource scheduling optimization scheme was implemented to obtain actual operational results; The model parameters are adjusted based on the actual operational results; wherein the model parameters include extended Kalman filter parameters, failure rate distribution, travel time distribution, and objective function weights.

8. A dynamic scheduling and optimization system for rail transit operation and maintenance resources, characterized in that, include: The data acquisition module is used to acquire multi-source data, perform data preprocessing on the multi-source data, and obtain equipment health status estimates and real-time passenger flow distribution. The digital twin modeling module is used to perform digital twin modeling based on the equipment health status estimate and real-time passenger flow distribution to obtain an equipment health prediction model and an operation and resource model. The optimization modeling module is used to establish a multi-objective optimization model based on the equipment health prediction model and the operation and resource model. The optimization scheme generation module is used to solve the multi-objective optimization model and generate an optimization scheme for operation and maintenance resource scheduling.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images