A rail transit dispatching control integrated index verification method and system

Abstract

The application relates to the technical field of rail transit, and provides a rail transit scheduling control integrated index verification method and system. Real running data collected by train running equipment and a scheduling control system in a field test section and simulation running data generated by a digital twin simulation system are acquired. Based on the aligned real state data and the simulation state data, real data variance and simulation data variance are determined, and real data confidence coefficients and simulation data confidence coefficients are determined accordingly. The real state data and the simulation state data are weighted and processed according to the corresponding confidence coefficients, and virtual-real fusion running state data is obtained. The tracking interval, the line passing capacity, the punctuality rate and the train plan adjustment response time are calculated based on the virtual-real fusion running state data, and are compared with preset verification thresholds, so that index verification results are generated. The method takes into account the realness of field data and the scene supplementing effect of simulation data, and improves the reliability of index verification results.

Description

Technical Field

[0001] This application relates to the field of rail transit dispatching technology, specifically to an integrated indicator verification method and system for rail transit dispatching and control. Background Technology

[0002] As regional rail transit networks continue to expand, the operational organization of rail transit systems becomes increasingly complex. The connection between train operation and dispatching is becoming closer, and traditional decentralized system verification methods are no longer sufficient to fully reflect the actual operational performance of integrated dispatching and control systems. Therefore, before deploying relevant systems for demonstration or engineering applications, it is necessary to conduct relatively accurate verification of their operational performance. Verification of integrated rail transit dispatching and control systems typically focuses on indicators such as train following intervals, line capacity, punctuality rate, and response time to train schedule adjustments. These indicators reflect the system's performance in operational organization, capacity utilization, train punctuality, and disturbance handling, and are important criteria for determining whether the system meets application requirements.

[0003] Existing verification methods typically include laboratory testing and field trials. Laboratory testing facilitates setting different operating conditions and allows for repeated verification, but differences may still exist between the test environment and actual field operating conditions. Field trials can reflect real-world line and equipment conditions, but are limited by factors such as test sections, test vehicles, and operational safety, resulting in a limited range of operating scenarios that cannot fully reflect the system's performance under complex conditions.

[0004] Therefore, in the demonstration and verification process of the integrated rail transit dispatch and control system, if the verification basis cannot simultaneously take into account the characteristics of on-site operation and the testing needs of multiple scenarios, it is easy to lead to the verification results of the indicators being incomplete and lacking credibility, which in turn affects the judgment of the actual application effect of the system. Summary of the Invention

[0005] This application aims to address the problems in the prior art by providing a highly reliable method and system for verifying indicators of integrated rail transit dispatching and control.

[0006] To achieve the above objectives, the first aspect of this application provides a method for verifying virtual-real fusion indicators of integrated rail transit dispatching and control, comprising:

[0007] Acquire real operational data collected by train operation equipment and dispatch control system in the field test section. The real operational data includes train position data, train speed data, train arrival and departure time data, equipment status data, and train schedule adjustment and processing data. Acquire simulation operation data generated by the digital twin simulation system, the simulation operation data including simulated train operation data, simulated road network status data, simulated disturbance data, and simulated scheduling processing data; Based on train identification, line section, sampling time and status type, the real operation data and the simulated operation data are aligned to obtain aligned real status data and simulated status data. The variances of the real data and the simulation data are calculated based on the aligned real state data and simulation state data, respectively. The confidence coefficients of the real data and the simulation data corresponding to the aligned real running data are determined according to the real data variances and the simulation data variances. According to the confidence coefficient of the real data and the confidence coefficient of the simulation data, the aligned real state data and the simulation state data are weighted and fused to obtain virtual-real fusion operation state data. The virtual-real fusion operation state data includes fused train position, fused train speed, fused train arrival and departure time, fused equipment status and fused scheduling processing status. Based on the virtual-real fusion operation status data, the operation verification indicators of the integrated rail transit dispatch and control system are calculated. The operation verification indicators include tracking interval, line capacity, punctuality rate, and train schedule adjustment response time. Based on the comparison results between the operational verification indicators and the preset verification thresholds, the indicator verification results of the integrated rail transit dispatch and control system are generated.

[0008] Optionally, the line section includes the station area and the operating section between adjacent stations, and the status type includes train operation status, network equipment status and disturbance handling status; The process of aligning the real operation data and the simulated operation data based on train identification, line section, sampling time, and state type yields aligned real state data and simulated state data, including: According to the sampling time, the real running data and the simulated running data are time-aligned to obtain a time-aligned dataset at the same sampling time. In the time-aligned dataset, the train position data, train speed data, and train arrival and departure time data in the real operation data are aligned with the simulated train operation data in the simulated operation data according to the train identifier, so as to obtain the real state data and simulated state data corresponding to the train operation state. In the time-aligned dataset, according to the operating intervals between station areas and adjacent stations, the equipment status data in the real operating data is spatially aligned with the simulated road network status data in the simulated operating data to obtain the real status data and simulated status data corresponding to the road network equipment status. In the time-aligned dataset, according to the time and location of the disturbance, the equipment status data and driving plan adjustment processing data in the real operation data are aligned with the simulated disturbance data and simulated scheduling processing data in the simulation operation data to obtain the real state data and simulation state data corresponding to the disturbance processing state. Based on the real and simulated state data corresponding to the train operation status, the real and simulated state data corresponding to the road network equipment status, and the real and simulated state data corresponding to the disturbance handling status, aligned real and simulated state data are obtained.

[0009] Optionally, the step of calculating the variance of the real data and the variance of the simulation data based on the aligned real state data and simulation state data respectively includes: The real train position sequence, real train speed sequence, and real train arrival and departure time sequence are extracted from the real state data corresponding to the train operation state, and the simulated train position sequence, simulated train speed sequence, and simulated train arrival and departure time sequence are extracted from the simulated state data corresponding to the train operation state. Extract the real equipment status sequence from the real status data corresponding to the road network equipment status, and extract the simulated road network status sequence from the simulated status data corresponding to the road network equipment status. The real disturbance processing state sequence is extracted from the real state data corresponding to the disturbance processing state, and the simulated disturbance processing state sequence is extracted from the simulated state data corresponding to the disturbance processing state. Both the real disturbance processing state sequence and the simulated disturbance processing state sequence include the disturbance occurrence time, the end time of train operation adjustment plan preparation, and the time of dispatch command issuance. Within the same sampling period, the aligned real state data and simulated state data are normalized to obtain a real normalized state sequence and a simulated normalized state sequence. Variance statistics are performed on the real normalized state sequence to obtain the real sub-variance corresponding to each state type. Variance statistics are also performed on the simulated normalized state sequence to obtain the simulated sub-variance corresponding to each state type. Based on the true sub-variance corresponding to each state type, the true data variance corresponding to each state type is determined, and based on the simulation sub-variance corresponding to each state type, the simulation data variance corresponding to each state type is determined.

[0010] Optionally, determining the confidence coefficient of the real data corresponding to the real running data and the confidence coefficient of the simulation data corresponding to the simulation running data based on the variance of the real data and the variance of the simulation data includes: For the variance of the real data and the variance of the simulated data under the same state type, the confidence coefficient of the real data is determined according to the following formula. :

[0011] Will The confidence coefficient of the simulation data is determined; in, The variance of the actual data. Let V be the variance of the simulation data.

[0012] Optionally, the step of weightedly fusing the aligned real-state data and the simulated-state data according to the confidence coefficients of the real data and the simulation data to obtain virtual-real fusion operating state data includes: From the aligned real-state data, extract the real-state field values ​​under the same sampling time, the same state type, and the train identifier and / or space identifier corresponding to the state type, and determine the real-state field values ​​as real-state quantities. ; Extract the simulation state field value corresponding to the real state field value from the aligned simulation state data, and determine the simulation state field value as the simulation state quantity. ; The weighted fusion is performed according to the following formula:

[0013] in, This is a fusion state quantity; the spatial identifier includes station identifiers or section identifiers; The fused state quantities are associated and stored according to sampling time, state type, train identifier, and spatial identifier to obtain the virtual-real fused operation state data; The virtual-real fusion operation status data includes fused train location data, fused train speed data, fused train arrival and departure time data, fused equipment status data, and fused scheduling and processing status data; The fusion scheduling processing status data includes the time of disturbance occurrence, the time of completion of train operation adjustment plan preparation, and the time of issuance of scheduling command.

[0014] Optionally, after obtaining the virtual-real fusion operation status data, the method further includes: Based on the fused train position data and fused train speed data from the previous sampling time, the train position and train speed at the current sampling time are predicted to obtain the predicted operating status at the current sampling time. The measurement residual is calculated based on the field observation data at the current sampling time and the predicted operating status; wherein, the field observation data is the actual operating data collected by the train operation equipment and the dispatch control system at the current sampling time; The predicted operating state is corrected based on the measurement residuals to obtain updated fused train position data and fused train speed data; The updated fusion train location data, the updated fusion train speed data, the fusion train arrival and departure time data, the fusion equipment status data, and the fusion scheduling processing status data are used together as virtual-real fusion operation status data for calculating the operation verification indicators.

[0015] Optionally, the fused train position data includes the position of the train's front end, the position of the train's rear end, and the direction of travel; The calculated tracking interval includes: Based on the fused train position data in the virtual-real fusion operation status data, determine the first... The train was at The position of the rear of the vehicle at the next sampling time; Based on the fused train position data and fused train speed data in the virtual-real fusion operation status data, determine the train immediately following the train in operation. The arrival time when the front of the train reaches the aforementioned rear position; According to the arrival time and the first The time difference between the sampling times determines the first... Train and the The train was at Tracking interval at the next sampling time ; The minimum tracking interval between a single pair of tracking trains is determined according to the following formula:

[0016] The minimum tracking interval of all tracking train pairs on the field test section is compared to obtain the global minimum tracking interval, and the global minimum tracking interval is used as the tracking interval.

[0017] Optionally, the throughput capacity of the computing line includes: Based on the global minimum tracking interval Calculate the peak hour parallel operation map throughput capacity :

[0018] Based on the fused train arrival and departure times data in the virtual-real fusion operation status data and the preset train stopping plan, the total number of train pairs is determined. Number of trains stopping at Osaka Station And obtain the deduction coefficient for trains stopping at major stations. and preset capacity utilization coefficient ; Based on the peak hour parallel operation schedule capacity, the total number of train pairs, the number of train pairs stopping at major stations, and the deduction coefficient for trains stopping at major stations, the mixed train capacity is determined according to the following formula. :

[0019] Based on the hybrid train throughput capacity and capacity utilization coefficient The throughput capacity is determined according to the following formula. :

[0020] The passage capacity is referred to as the line passage capacity.

[0021] Optionally, The calculation of punctuality rate includes: Based on the fused train arrival and departure time data in the virtual-real fusion operation status data, the train arrival and departure events are determined; Based on the planned operation diagram in the digital twin simulation system, determine the planned arrival and departure times corresponding to the train arrival and departure events; Based on the deviation between the actual arrival and departure times of the train arrival and departure events and the planned arrival and departure times, it is determined whether the train arrival and departure events are on time. The on-time rate is determined based on the number of on-time train arrivals and departures and the total number of train arrivals and departures. The calculation of the driving plan adjustment response time includes: Based on the fusion scheduling processing status data in the virtual-real fusion operation status data, determine the time when the disturbance that makes the train trip plan infeasible occurs, the time when the train trip adjustment plan is completed, and the time when the scheduling command is issued. The time difference between the completion time of the train operation adjustment plan and the time of the disturbance occurrence is determined as the train operation plan adjustment time; the time difference between the issuance time of the dispatching command and the completion time of the train operation adjustment plan is determined as the comprehensive dispatching scheme preparation time. The response time for adjusting the train schedule is determined based on the sum of the train schedule adjustment time and the comprehensive scheduling scheme preparation time.

[0022] The second aspect of this application provides a virtual-real fusion index verification system, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the above-mentioned virtual-real fusion index verification method for integrated rail transit dispatching and control.

[0023] Compared with the prior art, this application has the following beneficial effects: By introducing real operational data collected from the field test section and simulated operational data generated by the digital twin simulation system, the real operational data reflects the actual operation of trains, equipment, and dispatching control systems in the field test section, while the simulated operational data supplements operational scenarios that are difficult to fully represent in field tests. By assigning appropriate weights based on the fluctuations of the two types of data, data with higher stability can have a larger proportion in subsequent calculations, thus obtaining more suitable virtual-real integrated operational status data for indicator verification. Based on this virtual-real integrated operational status data, tracking intervals, line capacity, punctuality rate, and train schedule adjustment response time are calculated, balancing the authenticity of field data with the scenario supplementation role of simulation data. This reduces the impact of insufficient samples when using field data alone, and also reduces the impact of deviations from field conditions when using simulation data alone, thereby improving the credibility of the indicator verification results of the integrated rail transit dispatching and control system. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application 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 application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart illustrating a method provided in an embodiment of this application. Detailed Implementation

[0026] To facilitate understanding of this application, the following description will be more comprehensive and detailed in conjunction with the accompanying drawings and preferred embodiments, but the scope of protection of this application is not limited to the following specific embodiments.

[0027] Unless otherwise defined, all technical terms used herein have the same meaning as commonly understood by those skilled in the art. The technical terms used herein are for the purpose of describing particular embodiments only and are not intended to limit the scope of this application.

[0028] Please see Figure 1 One embodiment of the present invention provides a method for verifying virtual-real fusion indicators of integrated rail transit dispatching and control, comprising the following steps: S1. Obtain real operational data collected by train operation equipment and dispatch control system in the field test section. Real operational data includes train position data, train speed data, train arrival and departure time data, equipment status data, and train schedule adjustment and processing data.

[0029] In this step, the field test section is a verification section equipped with train operation equipment and a dispatching control system. The train operation equipment collects the train's position, speed, arrival and departure times during operation. The dispatching control system collects the status of stations, sections, and related train operation equipment, and records the train schedule adjustment process after a disturbance occurs. The train schedule adjustment processing data includes the time of disturbance occurrence, the time the train schedule adjustment plan is completed, the time the dispatching command is issued, and the corresponding processing status. This forms the real operating data under the field operating conditions.

[0030] S2. Obtain simulation operation data generated by the digital twin simulation system. The simulation operation data includes simulated train operation data, simulated road network status data, simulated disturbance data, simulated scheduling and processing data, and planned operation diagram data.

[0031] In this step, the digital twin simulation system simulates the operation of lines, stations, trains, and scheduling rules to generate a simulated operating scenario corresponding to the on-site test section. Simulated train operation data includes the simulated train's position, speed, direction of travel, arrival and departure times, and tracking relationships. Simulated network status data includes the simulated line sections, station areas, and equipment occupancy status. Simulated disturbance data includes equipment failures, train delays, section restrictions, or other events affecting the execution of the train operation plan. Simulated scheduling data includes train operation plan adjustment schemes, scheduling commands, and processing times generated in the simulation environment.

[0032] S3. Align the real operation data and the simulated operation data according to the train identification, line section, sampling time and status type to obtain the aligned real status data and simulated status data.

[0033] In this step, train identifiers are used to match the same train or corresponding operational task in real-world and simulated operational data. Line sections are used to distinguish between station areas corresponding to the data or operational sections between adjacent stations. Sampling times are used to unify the time base between real-world and simulated operational data. State types are used to distinguish between train operational status, network equipment status, and disturbance handling status. After alignment, real-world and simulated state data are consistent in terms of object, time, space, and state.

[0034] S4. Calculate the variance of the real data and the variance of the simulation data based on the aligned real state data and simulation state data respectively, and determine the confidence coefficient of the real data corresponding to the real running data and the confidence coefficient of the simulation data corresponding to the simulation running data based on the real data variance and the simulation data variance.

[0035] In this step, statistical analysis is performed on the aligned real-state data and simulated-state data separately. For numerical data such as train position, train speed, and arrival / departure times, normalization and variance statistics are directly performed within the same sampling period. For equipment status and disturbance handling status, numerical processing is first performed according to the meaning of the status, followed by normalization and variance statistics. The variance of the real data is used to characterize the degree of fluctuation in the real-state data. The variance of the simulated data is used to characterize the degree of fluctuation in the simulated-state data.

[0036] The variances of real and simulated data are used as the basis for calculating the confidence coefficients. Data with smaller variances correspond to higher confidence levels, while data with larger variances correspond to lower confidence levels. The confidence coefficients for real and simulated data are used to assign weights to real and simulated state data during the fusion process, adjusting the data fusion result according to the stability of the data.

[0037] S5. Based on the confidence coefficients of the real data and the simulation data, the aligned real state data and simulation state data are weighted and fused to obtain virtual-real fusion operation state data. The virtual-real fusion operation state data includes fused train position, fused train speed, fused train arrival and departure time, fused equipment status, and fused scheduling processing status.

[0038] In this step, under the same sampling time, the same line section, and the same state type, the real state data is multiplied by the real data confidence coefficient, and the simulated state data is multiplied by the simulated data confidence coefficient. The two results are then combined to obtain the virtual-real fused operational state data. After train operation state fusion, the fused train position, fused train speed, and fused train arrival and departure times are obtained. After network equipment state fusion, the fused equipment state is obtained. After disturbance handling state fusion, the fused scheduling handling state is obtained.

[0039] S6. Based on the virtual and real integrated operation status data, calculate the operation verification indicators of the integrated rail transit dispatch and control system. The operation verification indicators include tracking interval, line throughput capacity, punctuality rate, and response time for train schedule adjustment.

[0040] S7. Based on the comparison results between the operation verification indicators and the preset verification thresholds, generate the indicator verification results of the integrated rail transit dispatch and control system.

[0041] In this step, the tracking interval, line capacity, punctuality rate, and train schedule adjustment response time are compared with their respective preset verification thresholds. If the tracking interval meets the preset interval requirement, line capacity meets the preset capacity requirement, punctuality rate meets the preset punctuality requirement, and train schedule adjustment response time meets the preset response time requirement, a verification result for the corresponding indicator is generated. If any indicator fails to meet its corresponding threshold, the failed indicator and its corresponding virtual-real fusion operation status data are recorded, and an indicator verification result is generated.

[0042] In this embodiment, real operational data is collected from a field test section, and simulated operational data is generated through a digital twin simulation system. The two types of data are then aligned, variance analyzed, confidence coefficients determined, and weighted and fused to form unified verification data from the field and simulated operational states. Calculating tracking intervals, line capacity, punctuality rate, and train schedule adjustment response time based on the fused virtual and real operational data reduces the problems of insufficient scenario coverage when relying solely on field data and deviations from field operational states when relying solely on simulated data, thereby improving the credibility of the indicator verification results.

[0043] In one embodiment, data alignment includes time alignment, train status alignment, spatial status alignment, and disturbance handling status alignment.

[0044] Specifically, the line section includes the station area and the operating section between adjacent stations. The status types include train operation status, network equipment status, and disturbance handling status.

[0045] First, the real-world and simulated-world data are time-aligned according to the sampling time to obtain a time-aligned dataset at the same sampling time. If the sampling times are not exactly the same, they can be matched to adjacent sampling times according to a preset time tolerance.

[0046] In the time-aligned dataset, the train position data, train speed data, and train arrival and departure time data in the real operation data are aligned with the simulated train operation data in the simulation operation data according to the train identifier, so as to obtain the real state data and simulation state data corresponding to the train operation state.

[0047] In the time-aligned dataset, the equipment status data in the real operation data is spatially aligned with the simulated road network status data in the simulation operation data according to the operating interval between station areas and adjacent stations, so as to obtain the real status data and simulation status data corresponding to the road network equipment status.

[0048] In the time-aligned dataset, based on the time and location of the disturbance, the equipment status data and train schedule adjustment processing data from the real-world operational data are aligned with the simulated disturbance data and simulated scheduling processing data from the simulated operational data to obtain the real-world and simulated-world state data corresponding to the disturbance processing state. This allows for the separate acquisition of real-world and simulated-world state data corresponding to train operation status, network equipment status, and disturbance processing state, facilitating subsequent variance calculation and fusion processing based on state type.

[0049] In addition, for device status data, if the fused status quantity is a continuous value, the fused status quantity is converted into the corresponding fused device status data according to the preset status threshold or the maximum confidence state.

[0050] In one embodiment, the variance of the real data and the variance of the simulated data are determined separately according to the state type.

[0051] Specifically, the real train position sequence, real train speed sequence, and real train arrival and departure time sequence are extracted from the real state data corresponding to the train operation state, and the simulated train position sequence, simulated train speed sequence, and simulated train arrival and departure time sequence are extracted from the simulated state data corresponding to the train operation state.

[0052] The system extracts real device state sequences from the actual state data corresponding to the road network device states, and extracts simulated road network state sequences from the simulated state data corresponding to the road network device states. Device states that are not numerical are converted into numerical sequences according to preset encoding rules.

[0053] The actual disturbance handling state sequence is extracted from the real state data corresponding to the disturbance handling state, and the simulated disturbance handling state sequence is extracted from the simulated state data corresponding to the disturbance handling state. Both the actual disturbance handling state sequence and the simulated disturbance handling state sequence include the time of disturbance occurrence, the time of completion of train operation adjustment plan preparation, and the time of issuance of dispatch command.

[0054] Among them, the time from the occurrence of the disturbance to the end of the train operation adjustment plan is used to determine the time for adjusting the train operation plan, the time from the end of the train operation adjustment plan to the issuance of the dispatch order is used to determine the time for forming the dispatch order, and the time from the occurrence of the disturbance to the issuance of the dispatch order is used to determine the total response time for handling the disturbance.

[0055] Within the same sampling period, the aligned real-state data and simulated-state data are normalized to obtain real-normalized state sequences and simulated-normalized state sequences. Variance statistics are then performed on the real-normalized state sequences to obtain the real sub-variance for each state type; similarly, variance statistics are performed on the simulated-normalized state sequences to obtain the simulated sub-variance for each state type. The real data variance for each state type is determined based on the real sub-variance, and the simulated data variance for each state type is determined based on the simulated sub-variance. The real data variance and simulated data variance are used for subsequent confidence coefficient calculations, ensuring that different state types are weighted accordingly during virtual-real fusion.

[0056] Specifically, the weighted summation of the true sub-variances corresponding to each field under the same state type yields the true data variance corresponding to that state type; the weighted summation of the simulation sub-variances corresponding to each field under the same state type yields the simulation data variance corresponding to that state type.

[0057] In one embodiment, the confidence coefficients of the real data corresponding to the actual running data and the confidence coefficients of the simulation data corresponding to the simulation running data are determined based on the variance of the real data and the variance of the simulation data.

[0058] Specifically, the variances of the real data and the simulated data under the same state type are compared, and the confidence coefficient of the real data is determined according to the following formula:

[0059] in, The confidence coefficient is the actual data. The variance of the actual data. This represents the variance of the simulation data.

[0060] The confidence coefficient of the simulation data is: ; When the variance of the actual data is small The weight of real-state data increases during fusion; when the variance of simulation data is small... The weight of simulated state data increases during fusion. This method adjusts the fusion weight of data of the same state type according to fluctuations in both real and simulated data.

[0061] In addition, when both the variance of the real data and the variance of the simulated data are 0, the confidence coefficients of both the real data and the simulated data are set to 0.5; or a preset positive number is added to the denominator.

[0062] In one embodiment, the aligned real-state data and simulated-state data are weighted and fused according to the confidence coefficients of the real data and the simulation data to obtain virtual-real fusion operating state data.

[0063] Specifically, from the aligned real-state data, the real-state field values ​​under the same sampling time, the same state type, and the corresponding train identifier and / or space identifier are extracted, and these real-state field values ​​are determined as real-state quantities. From the aligned simulation state data, extract the simulation state field values ​​corresponding to the actual state field values, and determine the simulation state field values ​​as simulation state variables. Spatial signage includes station signage or section signage.

[0064] Weighted fusion is performed according to the following formula:

[0065] in, For fusion state variables, The confidence coefficient is the actual data. is the confidence coefficient for the simulation data.

[0066] After obtaining the fused state data, it is associated and stored according to sampling time, state type, train identifier, and spatial identifier to form virtual-real fused operational state data. The virtual-real fused operational state data includes fused train location data, fused train speed data, fused train arrival and departure time data, fused equipment status data, and fused scheduling processing status data. Among these, the fused scheduling processing status data includes the time of disturbance occurrence, the time of completion of the train operation adjustment plan, and the time of issuance of the scheduling command.

[0067] In this embodiment, field-level fusion ensures a correspondence between the real and simulated state quantities at each sampling time and for each state type. The fused data retains the actual operational characteristics of the field-collected data while utilizing simulation data to address the insufficient scene coverage in the field test section.

[0068] In one embodiment, after obtaining the virtual-real fusion operation status data, the fusion train position data and fusion train speed data are also updated based on the on-site observation data.

[0069] Specifically, based on the fused train position data and fused train speed data from the previous sampling time, the train position and train speed at the current sampling time are predicted to obtain the predicted operating status at the current sampling time. The predicted operating status can include the predicted train position and the predicted train speed.

[0070] Preferably, if there is a delay, missing data or noise exceeding a preset range in the actual train position data or actual train speed data at the current sampling time, the train position and train speed at the current sampling time are predicted based on the fused train position data and fused train speed data from the previous sampling time.

[0071] The measurement residual is calculated based on the field observation data and predicted operating status at the current sampling time. The field observation data refers to the actual operating data collected by the train operation equipment and dispatch control system at the current sampling time. The measurement residual is used to characterize the deviation between the current field observation data and the predicted operating status.

[0072] The measurement residual can be expressed as follows:

[0073] in, For the first Measurement residuals at the next sampling time This is the on-site observation data at the current sampling time. To predict the operating status based on the current sampling time predicted from the previous sampling time, For observation functions.

[0074] The predicted operating status is corrected based on the measurement residuals to obtain updated fused train position and speed data. The update process can be represented as follows:

[0075] in, The updated running status, To correct the gain.

[0076] The updated fused train location data, updated fused train speed data, fused train arrival and departure time data, fused equipment status data, and fused dispatching processing status data are used together as virtual-real fused operational status data for calculating operational verification indicators. This processing allows for further correction of train operational status using on-site observation data after weighted fusion, reducing the impact of prediction bias on tracking interval and track capacity calculations.

[0077] In one embodiment, the fused train position data includes the position of the front of the train, the position of the rear of the train, and the direction of travel, and the tracking interval is calculated based on the fused train position data and the fused train speed data.

[0078] Specifically, based on the fused train position data in the virtual-real fusion operational status data, the first... The train was at The position of the rear of the vehicle at the next sampling time. Then, based on the immediately following... By fusing train position data and train speed data, the train's position and speed data are determined. The train's locomotive reached the... The arrival time at the rear of the train. Compare this arrival time with the... The time difference between the sampling times is determined as the first sampling time. Train and the The train was at Tracking interval at each sampling time: ; The minimum tracking interval between a single pair of trains is obtained by taking the minimum tracking interval time at each sampling time for the same pair of trains.

[0079] The minimum tracking interval of all tracking train pairs on the field test section was compared to obtain the global minimum tracking interval:

[0080] in, This is the set of all tracking train pairs on the field test section. The global minimum tracking interval is calculated. As the tracking interval, this indicator reflects the train running interval under the closest tracking conditions in the field test section.

[0081] In one embodiment, the line capacity is determined based on the global minimum tracking interval, train operation structure, and capacity utilization factor.

[0082] Specifically, based on the global minimum tracking interval Calculate the peak hour parallel operation plan throughput capacity. If In minutes, the peak hour parallel operation plan throughput capacity is:

[0083] in, This is to determine the throughput capacity of the parallel operation plan during peak hours.

[0084] Based on the fused train arrival and departure times data in the virtual-real integrated operation status data and the preset train stopping plan, the total number of train pairs is determined. Number of trains stopping at Osaka Station (i.e., the number of trains stopping at major stations), and obtain the deduction coefficient for trains stopping at major stations. and preset capacity utilization coefficient .

[0085] The throughput capacity of mixed trains is determined based on the peak hour parallel operation schedule capacity, total number of train pairs, number of train pairs stopping at major stations, and deduction coefficient for trains stopping at major stations:

[0086] in, To accommodate mixed train throughput capacity, This is a deduction factor for trains stopping at major stations. The number of trains stopping at major stations. This represents the total number of train pairs.

[0087] The used throughput capacity is determined based on the mixed train throughput capacity and the capacity utilization factor:

[0088] in, To use the pass capability, This is the capability utilization factor. The capability will be used. As a measure of line capacity. This method calculates line capacity by simultaneously considering minimum headway, train stopping structure, and actual capacity utilization.

[0089] In one embodiment, the on-time rate is determined based on the integrated train arrival and departure time data and the planned operation schedule, and the train schedule adjustment response time is determined based on the integrated scheduling processing status data.

[0090] Specifically, train arrival and departure events are determined based on the fused train arrival and departure time data in the virtual-real integrated operation status data. The planned arrival and departure times corresponding to the train arrival and departure events are determined based on the planned operation diagram in the digital twin simulation system. The actual arrival and departure times of the train arrival and departure events are compared with the planned arrival and departure times to obtain the arrival and departure time deviations. If the arrival and departure time deviations meet the preset on-time judgment conditions, the train arrival and departure event is determined as an on-time event.

[0091] On-time performance is determined by the following formula:

[0092] in, For punctuality rate, The number of train arrivals and departures on time. This represents the total number of train arrival and departure events.

[0093] The response time for adjusting the train schedule is determined based on the disturbance occurrence time, the train schedule adjustment plan completion time, and the dispatch command issuance time from the integrated scheduling processing status data. The time difference between the train schedule adjustment plan completion time and the disturbance occurrence time is defined as the train schedule adjustment time.

[0094] in, Adjusting the driving schedule The end time for the preparation of the train operation adjustment plan. The time when the disturbance occurs.

[0095] The time difference between the issuance of the dispatch order and the completion of the train operation adjustment plan is defined as the time for compiling the comprehensive dispatching scheme.

[0096] in, For the time required to develop a comprehensive scheduling plan, This refers to the time when the scheduling command is issued.

[0097] The response time for adjusting the train schedule is determined by summing the time for adjusting the train schedule and the time for compiling the comprehensive dispatching plan.

[0098] in, Adjust the response time for the train schedule. This response time represents the processing time from the moment a disturbance makes the train schedule infeasible until the dispatch command is issued and completed.

[0099] This application also proposes a virtual-real fusion index verification system, including a processor and a memory. The memory stores a computer program, which, when executed by the processor, implements the aforementioned virtual-real fusion index verification method for integrated rail transit scheduling and control. When this program or instructions are executed by the processor, they implement the various steps of the above-described method embodiments and achieve the same technical effects; therefore, to avoid repetition, they will not be described again here.

[0100] This application also provides a readable storage medium storing a program or instructions that, when executed by a processor, implement the various processes of the above-described method embodiments and achieve the same technical effects. To avoid repetition, these will not be described again here.

[0101] The processor can be the processor in the aforementioned system. Readable storage media include computer-readable storage media, such as computer read-only memory, random access memory, magnetic disks, or optical disks.

[0102] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0103] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as a read-only memory). The device includes a number of instructions in a ROM (random access memory), RAM (magnetic disk), or optical disk to cause a computer device to execute the methods described in the various embodiments of this application.

[0104] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A virtual-real fusion index verification method for integrated rail transit dispatching control, characterized in that, include: Acquire real operational data collected by train operation equipment and dispatch control system in the field test section. The real operational data includes train position data, train speed data, train arrival and departure time data, equipment status data, and train schedule adjustment and processing data. Acquire simulation operation data generated by the digital twin simulation system, the simulation operation data including simulated train operation data, simulated road network status data, simulated disturbance data, and simulated scheduling processing data; Based on train identification, line section, sampling time and status type, the real operation data and the simulated operation data are aligned to obtain aligned real status data and simulated status data. The variances of the real data and the simulation data are calculated based on the aligned real state data and simulation state data, respectively. The confidence coefficients of the real data and the simulation data corresponding to the aligned real running data are determined according to the real data variances and the simulation data variances. According to the confidence coefficient of the real data and the confidence coefficient of the simulation data, the aligned real state data and the simulation state data are weighted and fused to obtain virtual-real fusion operation state data. The virtual-real fusion operation state data includes fused train position, fused train speed, fused train arrival and departure time, fused equipment status and fused scheduling processing status. Based on the virtual-real fusion operation status data, the operation verification indicators of the integrated rail transit dispatch and control system are calculated. The operation verification indicators include tracking interval, line capacity, punctuality rate, and train schedule adjustment response time. Based on the comparison results between the operational verification indicators and the preset verification thresholds, the indicator verification results of the integrated rail transit dispatch and control system are generated.

2. The virtual-real fusion index verification method for rail transit dispatching control integration according to claim 1, characterized in that, The line section includes the station area and the operating section between adjacent stations, and the status types include train operation status, road network equipment status and disturbance handling status. The process of aligning the real operation data and the simulated operation data based on train identification, line section, sampling time, and state type yields aligned real state data and simulated state data, including: According to the sampling time, the real running data and the simulated running data are time-aligned to obtain a time-aligned dataset at the same sampling time. In the time-aligned dataset, the train position data, train speed data, and train arrival and departure time data in the real operation data are aligned with the simulated train operation data in the simulated operation data according to the train identifier, so as to obtain the real state data and simulated state data corresponding to the train operation state. In the time-aligned dataset, according to the operating intervals between station areas and adjacent stations, the equipment status data in the real operating data is spatially aligned with the simulated road network status data in the simulated operating data to obtain the real status data and simulated status data corresponding to the road network equipment status. In the time-aligned dataset, according to the time and location of the disturbance, the equipment status data and driving plan adjustment processing data in the real operation data are aligned with the simulated disturbance data and simulated scheduling processing data in the simulation operation data to obtain the real state data and simulation state data corresponding to the disturbance processing state. Based on the real and simulated state data corresponding to the train operation status, the real and simulated state data corresponding to the road network equipment status, and the real and simulated state data corresponding to the disturbance handling status, aligned real and simulated state data are obtained.

3. The virtual-real fusion index verification method for rail transit dispatching control integration according to claim 2, characterized in that, The calculation of the variance of the real data and the variance of the simulation data based on the aligned real state data and simulation state data respectively includes: The real train position sequence, real train speed sequence, and real train arrival and departure time sequence are extracted from the real state data corresponding to the train operation state, and the simulated train position sequence, simulated train speed sequence, and simulated train arrival and departure time sequence are extracted from the simulated state data corresponding to the train operation state. Extract the real equipment status sequence from the real status data corresponding to the road network equipment status, and extract the simulated road network status sequence from the simulated status data corresponding to the road network equipment status. The real disturbance processing state sequence is extracted from the real state data corresponding to the disturbance processing state, and the simulated disturbance processing state sequence is extracted from the simulated state data corresponding to the disturbance processing state. Both the real disturbance processing state sequence and the simulated disturbance processing state sequence include the disturbance occurrence time, the end time of train operation adjustment plan preparation, and the time of dispatch command issuance. Within the same sampling period, the aligned real state data and simulated state data are normalized to obtain a real normalized state sequence and a simulated normalized state sequence. Variance statistics are performed on the real normalized state sequence to obtain the real sub-variance corresponding to each state type. Variance statistics are also performed on the simulated normalized state sequence to obtain the simulated sub-variance corresponding to each state type. Based on the true sub-variance corresponding to each state type, the true data variance corresponding to each state type is determined, and based on the simulation sub-variance corresponding to each state type, the simulation data variance corresponding to each state type is determined.

4. The virtual-real fusion index verification method for rail transit dispatching control integration according to claim 3, characterized in that, The step of determining the confidence coefficient of the real data corresponding to the real running data and the confidence coefficient of the simulation data corresponding to the simulation running data based on the variance of the real data and the variance of the simulation data includes: The real data confidence coefficient is determined according to the following formula for the real data variance and the simulation data variance under the same state type : Will The confidence coefficient of the simulation data is determined; wherein, is the variance of the real data, is the variance of the simulated data.

5. The virtual-real fusion index verification method for rail transit dispatching control integration according to claim 4, characterized in that, The step of weightedly fusing the aligned real-state data and the simulated-state data according to the confidence coefficients of the real data and the simulation data to obtain virtual-real fusion operating state data includes: From the aligned real-state data, extract the real-state field values ​​under the same sampling time, the same state type, and the train identifier and / or space identifier corresponding to the state type, and determine the real-state field values ​​as real-state quantities. ; Extract the simulation state field value corresponding to the real state field value from the aligned simulation state data, and determine the simulation state field value as the simulation state quantity. ; The weighted fusion is performed according to the following formula: in, This is a fusion state quantity; the spatial identifier includes station identifiers or section identifiers; The fused state quantities are associated and stored according to sampling time, state type, train identifier, and spatial identifier to obtain the virtual-real fused operation state data; The virtual-real fusion operation status data includes fused train location data, fused train speed data, fused train arrival and departure time data, fused equipment status data, and fused scheduling and processing status data; The fusion scheduling processing status data includes the time of disturbance occurrence, the time of completion of train operation adjustment plan preparation, and the time of issuance of scheduling command.

6. The method for verifying the virtual-real fusion index of integrated rail transit dispatching and control according to claim 5, characterized in that, After obtaining the virtual-real fusion operation status data, the following is also included: Based on the fused train position data and fused train speed data from the previous sampling time, the train position and train speed at the current sampling time are predicted to obtain the predicted operating status at the current sampling time. The measurement residual is calculated based on the field observation data at the current sampling time and the predicted operating status; wherein, the field observation data is the actual operating data collected by the train operation equipment and the dispatch control system at the current sampling time; The predicted operating state is corrected based on the measurement residuals to obtain updated fused train position data and fused train speed data; The updated fusion train location data, the updated fusion train speed data, the fusion train arrival and departure time data, the fusion equipment status data, and the fusion scheduling processing status data are used together as virtual-real fusion operation status data for calculating the operation verification indicators.

7. The method for verifying the virtual-real fusion index of integrated rail transit dispatching and control according to claim 5 or 6, characterized in that, The fused train position data includes the position of the train's front end, the position of the train's rear end, and the direction of travel. The calculated tracking interval includes: Based on the fused train position data in the virtual-real fusion operation status data, determine the first... The train was at The position of the rear of the vehicle at the next sampling time; Based on the fused train position data and fused train speed data in the virtual-real fusion operation status data, determine the train immediately following the train in operation. The arrival time when the front of the train reaches the aforementioned rear position; According to the arrival time and the first The time difference between the sampling times determines the first... Train and the The train was at Tracking interval at the next sampling time ; The minimum tracking interval between a single pair of tracking trains is determined according to the following formula: The minimum tracking interval of all tracking train pairs on the field test section is compared to obtain the global minimum tracking interval, and the global minimum tracking interval is used as the tracking interval.

8. The method for verifying the virtual-real fusion index of integrated rail transit dispatching and control according to claim 7, characterized in that, The throughput capacity of the computing line includes: Based on the global minimum tracking interval Calculate the peak hour parallel operation map throughput capacity : Based on the fused train arrival and departure times data in the virtual-real fusion operation status data and the preset train stopping plan, the total number of train pairs is determined. Number of trains stopping at Osaka Station And obtain the deduction coefficient for trains stopping at major stations. and preset capacity utilization coefficient ; Based on the peak hour parallel operation schedule capacity, the total number of train pairs, the number of train pairs stopping at major stations, and the deduction coefficient for trains stopping at major stations, the mixed train capacity is determined according to the following formula. : Based on the hybrid train throughput capacity and capacity utilization coefficient The throughput capacity is determined according to the following formula. : The passage capacity is referred to as the line passage capacity.

9. The method for verifying the virtual-real fusion index of integrated rail transit dispatching and control according to claim 5 or 6, characterized in that, The calculation of punctuality rate includes: Based on the fused train arrival and departure time data in the virtual-real fusion operation status data, the train arrival and departure events are determined; Based on the planned operation diagram in the digital twin simulation system, determine the planned arrival and departure times corresponding to the train arrival and departure events; Based on the deviation between the actual arrival and departure times of the train arrival and departure events and the planned arrival and departure times, it is determined whether the train arrival and departure events are on time. The on-time rate is determined based on the number of on-time train arrivals and departures and the total number of train arrivals and departures. The calculation of the driving plan adjustment response time includes: Based on the fusion scheduling processing status data in the virtual-real fusion operation status data, determine the time when the disturbance that makes the train trip plan infeasible occurs, the time when the train trip adjustment plan is completed, and the time when the scheduling command is issued. The time difference between the completion time of the train operation adjustment plan and the time of the disturbance occurrence is determined as the train operation plan adjustment time; the time difference between the issuance time of the dispatching command and the completion time of the train operation adjustment plan is determined as the comprehensive dispatching scheme preparation time. The response time for adjusting the train schedule is determined based on the sum of the train schedule adjustment time and the comprehensive scheduling scheme preparation time.

10. A virtual-real fusion index verification system, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the virtual-real fusion index verification method for integrated rail transit dispatch and control as described in any one of claims 1 to 9.

Images