A method, device, equipment and storage medium for evaluating and optimizing the transport efficiency of a high-speed train operation plan

Abstract

The present application provides a method, device, equipment, and storage medium for optimizing the transport efficiency evaluation of a high-speed railway train operation plan. The method obtains the operation plan of a high-speed railway train and the passenger occupancy rate of each train; based on the operation plan of the high-speed railway train and the passenger occupancy rate of each train, an optimized operation plan and its transport efficiency evaluation value are determined through an evaluation model; wherein the evaluation model includes a two-dimensional wavelet packet decomposition module and a convolutional neural network; the decomposition function of the two-dimensional wavelet packet decomposition module is Daubechies4, and the two-dimensional wavelet packet decomposition module is used to convert the characteristic vectors of all trains in the operation plan into multi-channel data; the convolutional neural network is used to evaluate the transport efficiency based on the multi-channel data and the passenger occupancy rate of each train. The method accurately evaluates the transport efficiency based on the operation plan of the high-speed railway train and the passenger occupancy rate of each train, obtains the optimized operation plan, realizes the automatic optimization of the transport efficiency evaluation of the high-speed railway train operation plan, and improves the optimization efficiency and accuracy.

Description

Technical Field

[0001] The present application relates to the field of rail transit technology, and in particular to a method, device, equipment, and storage medium for evaluating and optimizing the transportation efficiency of a high-speed train operation plan. Background Art

[0002] In the high-speed railway operation organization and planning system, train operation plan design is a key link in balancing supply and demand. Optimizing train operation plans must not only align with passenger travel patterns and improve the quality of railway transportation services, but also fully utilize transportation resources and increase railway network capacity utilization. Adjusting and optimizing these plans is a complex, systematic process.

[0003] In previous studies on train operation plan optimization, the relevant optimization methods for train operation plans can be divided into three categories: comprehensive optimization of route design and frequency setting, comprehensive optimization of stop planning and frequency setting, and comprehensive optimization of route design, frequency setting, and stop planning. In order to evaluate the degree of consistency between capacity allocation and travel demand, passenger flow distribution is integrated into the train operation plan optimization process to evaluate the effectiveness of train operation. However, due to the complex travel choice behavior and influencing factors of passenger flow demand, the traditional passenger flow distribution process is difficult to accurately depict passenger travel route choices and train passenger flow distribution. In the actual transportation organization process, train capacity utilization is usually estimated based on manual experience and train pre-sales.

[0004] This method is not only inefficient but also lacks accuracy. Summary of the Invention

[0005] In order to solve one of the above-mentioned technical defects, the present application provides a method, device, equipment and storage medium for evaluating and optimizing the transportation efficiency of a train operation plan.

[0006] In a first aspect, the present application provides a method for optimizing the transport efficiency of a high-speed train operation plan, the method comprising:

[0007] Obtain the operation plan of high-speed railway trains and the passenger occupancy rate of each train;

[0008] Based on the high-speed railway train operation plan and the passenger load factor of each train, the evaluation model is used to determine the optimized operation plan and its transportation efficiency evaluation value;

[0009] Among them, the evaluation model includes a two-dimensional wavelet packet decomposition module and a convolutional neural network;

[0010] The decomposition function of the two-dimensional wavelet packet decomposition module is Daubechies4, and the two-dimensional wavelet packet decomposition module is used to convert the characteristic vectors of all trains in the operation plan into multi-channel data;

[0011] Convolutional neural networks are used to evaluate transport efficiency based on multi-channel data and the passenger load factor of each train;

[0012] The convolutional neural network is trained based on multiple historical train operation plans and their train occupancy rates to construct a mapping relationship and conduct transportation efficiency evaluation.

[0013] In a second aspect of the present application, a device for evaluating and optimizing the transport efficiency of a high-speed train operation plan is provided, the device comprising:

[0014] An acquisition module is used to obtain the operation plan of high-speed railway trains and the passenger occupancy rate of each train;

[0015] An optimization module is used to determine the optimized operation plan and its transport efficiency evaluation value through an evaluation model based on the operation plan of high-speed railway trains and the passenger load factor of each train;

[0016] Among them, the evaluation model includes a two-dimensional wavelet packet decomposition module and a convolutional neural network;

[0017] The decomposition function of the two-dimensional wavelet packet decomposition module is Daubechies4, and the two-dimensional wavelet packet decomposition module is used to convert the characteristic vectors of all trains in the operation plan into multi-channel data;

[0018] Convolutional neural networks are used to evaluate transport efficiency based on multi-channel data and the passenger load factor of each train;

[0019] The convolutional neural network is trained based on multiple historical train operation plans and their train occupancy rates to construct a mapping relationship and conduct transportation efficiency evaluation.

[0020] In a third aspect of the present application, an electronic device is provided, comprising:

[0021] Memory;

[0022] processor; and

[0023] computer programs;

[0024] The computer program is stored in the memory and is configured to be executed by the processor to implement the method as described in the first aspect above.

[0025] In a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored; the computer program is executed by a processor to implement the method described in the first aspect above.

[0026] The present application provides a method, device, equipment, and medium for optimizing the transport efficiency evaluation of a train operation plan. The method includes: obtaining the operation plan of a high-speed railway train and the passenger occupancy rate of each train; determining the optimized operation plan and its transport efficiency evaluation value through an evaluation model based on the operation plan of the high-speed railway train and the passenger occupancy rate of each train; wherein the evaluation model includes a two-dimensional wavelet packet decomposition module and a convolutional neural network; the decomposition function of the two-dimensional wavelet packet decomposition module is Daubechies4, and the two-dimensional wavelet packet decomposition module is used to convert the characteristic vectors of all trains in the operation plan into multi-channel data; the convolutional neural network is used to evaluate the transport efficiency based on the multi-channel data and the passenger occupancy rate of each train; wherein the convolutional neural network is trained based on multiple historical operation plans and their train passenger occupancy rates, constructs a mapping relationship, and performs transport efficiency evaluation. The method of the present application can accurately evaluate the transport efficiency based on the operation plan of the high-speed railway train and the passenger occupancy rate of each train, and then obtains the optimized operation plan, thereby realizing the automatic optimization of the transport efficiency evaluation of the high-speed railway train operation plan and improving the optimization efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0028] Figure 1 A flow chart of a method for evaluating and optimizing the transport efficiency of a high-speed train operation plan provided in an embodiment of the present application;

[0029] Figure 2 A schematic diagram of the principle of an evaluation model provided in an embodiment of the present application;

[0030] Figure 3 A schematic diagram of the division of a railway network provided in an embodiment of the present application;

[0031] Figure 4 A schematic diagram of the structure of a high-speed train operation plan transportation efficiency evaluation and optimization device provided in an embodiment of the present application;

[0032] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the technical solutions and advantages of the embodiments of the present application more clearly understood, the exemplary embodiments of the present application are further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, and are not an exhaustive list of all the embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other unless they conflict.

[0034] In the process of realizing the present application, the inventors found that in previous studies on the optimization of train operation plans, the relevant optimization methods of train operation plans can be divided into three categories: comprehensive optimization of route design and frequency setting, comprehensive optimization of stop planning and frequency setting, and comprehensive optimization of route design, frequency setting and stop planning. In order to evaluate the degree of consistency between capacity allocation and travel demand, passenger flow distribution will be integrated into the process of train operation plan optimization to evaluate the effect of train operation. However, due to the complexity of travel choice behavior and influencing factors of passenger flow demand, the traditional passenger flow distribution process is difficult to accurately portray passenger travel route selection and train passenger flow distribution. In the actual transportation organization process, the train capacity utilization is usually estimated based on manual experience and train pre-sale situation. This method is not only inefficient, but also lacks accuracy.

[0035] In response to the above problems, an embodiment of the present application provides a method, device, equipment, and medium for optimizing the transport efficiency evaluation of a train operation plan. The method includes: obtaining the operation plan of a high-speed railway train and the passenger occupancy rate of each train; determining the optimized operation plan and its transport efficiency evaluation value through an evaluation model based on the operation plan of the high-speed railway train and the passenger occupancy rate of each train; wherein the evaluation model includes a two-dimensional wavelet packet decomposition module and a convolutional neural network; the decomposition function of the two-dimensional wavelet packet decomposition module is Daubechies4, and the two-dimensional wavelet packet decomposition module is used to convert the characteristic vectors of all trains in the operation plan into multi-channel data; the convolutional neural network is used to evaluate the transport efficiency based on the multi-channel data and the passenger occupancy rate of each train; wherein the convolutional neural network is trained based on multiple historical operation plans and their train passenger occupancy rates, constructs a mapping relationship, and performs transport efficiency evaluation. The method of the present application can accurately evaluate the transport efficiency based on the operation plan of the high-speed railway train and the passenger occupancy rate of each train, and then obtains an optimized operation plan, thereby realizing the automatic optimization of the transport efficiency evaluation of the high-speed railway train operation plan and improving the optimization efficiency and accuracy.

[0036] To accurately assess the transport efficiency of train operation plans, improve supply-demand compatibility, and enhance capacity resource utilization, this embodiment provides a method for optimizing the transport efficiency of high-speed rail train operation plans. This method designs a comprehensive, multi-dimensional transport efficiency evaluation index system focused on railway supply-demand efficiency and benefits. It also uses historical operational big data to map the characteristics of trains in train operation plans to their transport efficiency, accurately estimating train operation plans.

[0037] 1. Transportation efficiency evaluation index system

[0038] Since the optimal design of train operation plans needs to consider the benefits of both the supply and demand sides of the railway, and there is a mutually coordinated and constrained relationship between them, the evaluation of the transportation efficiency of the operation plans requires the construction of the user transportation efficiency evaluation index system shown in Table 1 from both the supply and demand aspects.

[0039] Table 1

[0040]

[0041] (1) Service level evaluation is to evaluate the quality of train services provided to passengers. Evaluation indicators are designed mainly from aspects such as accessibility and convenience, including passenger arrival and departure volume, service frequency, OD coverage, direct transfer ratio, etc., to measure the quality of passenger travel.

[0042] (2) Operational efficiency evaluation is an evaluation of the operational efficiency and transport capacity utilization of trains from the perspective of railway operating enterprises. It mainly includes transport capacity configuration, running distance, number of cars, passenger occupancy rate, speed coefficient, operation efficiency, etc., which is used to measure the transport organization efficiency of the operation plan.

[0043] (3) Capacity utilization is an evaluation of the utilization rate of resources in the operation plan from the perspective of railway network transport resources, mainly including the number of trains passing through the section, the number of trains originating and terminating at the station, and the section capacity utilization rate.

[0044] In order to take into account the efficiency and benefits of both the supply and demand sides of the railway, the train occupancy rate is selected as the main indicator for evaluating transportation efficiency. The higher the train occupancy rate, the higher the supply and demand adaptability and the better the capacity allocation effect.

[0045] 2. Characteristics of trains in the operation plan

[0046] If the railway network , then the plan is launched .

[0047] in, is the set of stations in the railway network, is the set of intervals in the railway network.

[0048] For train identification, .

[0049] For trains The total number of stations along the route, For trains Meet at the station. , For trains in the operation plan The first station along the route, For trains in the operation plan The second station along the way, Trains in the operation plan The first stations.

[0050] For trains of A collection of stop signs for the passing stations, If the train If the train stops at the first station, ;otherwise, If the train If the train stops at the second station, ;otherwise, If the train In the If the number of stations is less than 1, ;otherwise, .

[0051] For trains Capacity, For trains The departure time.

[0052] The characteristics of the trains in the operation plan include:

[0053] (1) Opening a path

[0054] Since each train has a different route, in order to ensure dimensional consistency, the railway network stations are sorted. If a train passes through a station, it is recorded as 1, otherwise it is recorded as 0.

[0055] (2) Stop signs

[0056] Similarly, for the sequenced railway network stations, if the train stops at the station, it is recorded as 1, otherwise, it is recorded as 0.

[0057] (3) Train capacity

[0058] Since the capacity of trains of different models varies greatly, in order to standardize the process, the maximum capacity of all models is set to , then the train Capacity converted to ,for The standardized value of .

[0059] (4) Departure time

[0060] The processing of the departure time is to convert the departure time into the proportion of the whole day time period, that is, ,for The standardized value of .

[0061] So, the train The eigenvector of can be expressed as , the characteristic vectors of all trains in the operation plan can be expressed as .

[0062] in, For the launch plan The total number of trains in .

[0063] Based on this, see Figure 1 The implementation process of the high-speed train operation plan transportation efficiency evaluation optimization method provided in this embodiment is as follows:

[0064] 101, obtain the operation plan of high-speed railway trains and the passenger occupancy rate of each train.

[0065] 102. Based on the operation plan of high-speed railway trains and the passenger occupancy rate of each train, the optimized operation plan and its transportation efficiency evaluation value are determined through the evaluation model.

[0066] Among them, the evaluation model includes a two-dimensional wavelet packet decomposition module and a convolutional neural network.

[0067] 1. Two-dimensional wavelet packet decomposition module

[0068] The decomposition function of the two-dimensional wavelet packet decomposition module is Daubechies4, and the two-dimensional wavelet packet decomposition module is used to implement the wavelet packet decomposition process, that is, the two-dimensional wavelet packet decomposition module is used to convert the characteristic vectors of all trains in the operation plan into multi-channel data.

[0069] For example, the two-dimensional wavelet packet decomposition module reduces the instability of the original signal by decomposing it into several sub-signals during the wavelet packet decomposition process. Wavelet packet decomposition is based on the spatial decomposition principle of multi-resolution analysis, which decomposes the space into several wavelet packet subspaces based on the spatial scale factor. Simultaneously, the low-frequency subspace (scale space) and high-frequency subspace (detail space) are subdivided into different frequencies, improving the time-frequency resolution of both low- and high-frequency bands, thereby obtaining better frequency-domain localization information than that achieved by wavelet decomposition.

[0070] The two-dimensional wavelet packet decomposition module has two decomposition layers, which can convert the feature vectors of all trains in the input operation plan into multi-channel data. The two-dimensional wavelet packet decomposition module selects the function Daubechies4 as the decomposition process function of the wavelet packet decomposition, and the two-dimensional multi-channel data generated by the decomposition can be used as the input of the convolutional neural network.

[0071] 2. Convolutional Neural Networks

[0072] Convolutional neural networks are used to evaluate transportation efficiency based on multi-channel data and the passenger load factor of each train.

[0073] Among them, the convolutional neural network is trained based on multiple historical operation plans and their train occupancy rates to construct mapping relationships and conduct transportation efficiency evaluation.

[0074] Convolutional neural networks are a type of feedforward neural network with a deep structure that incorporates convolutional computations and can learn from multidimensional data. They consist of an input layer, hidden layers, and an output layer. Hidden layers primarily include two types of feature extraction layers: convolutional layers and sampling layers (or pooling layers), as well as fully connected layers.

[0075] Based on the two-dimensional multi-channel data generated by the two-dimensional wavelet packet decomposition module in the evaluation model, the convolutional neural network in the evaluation model has three convolutional layers, each of which has The convolution kernel and the number of channels are , the activation function is a linear rectifier unit; the pooling function uses average pooling, and the last layer of the network is a fully connected layer; the loss function and optimization function of the convolutional neural network are mean square error and Adam algorithm respectively.

[0076] That is, the convolutional neural network includes: input layer, hidden layer and output layer.

[0077] Hidden layers include: convolutional layers, pooling layers, and fully connected layers.

[0078] There are 3 convolutional layers, each with The convolution kernel is , and the activation function is a linear rectification unit.

[0079] The pooling function of the pooling layer is the average pooling function.

[0080] The loss function of the convolutional neural network is the mean square error function, and the optimization function is the Adam algorithm.

[0081] In addition, in order to maximize the transport efficiency of the train operation plan, the convolutional neural network uses the overall passenger load factor level of the train operation plan as the optimization target in the transportation efficiency evaluation, based on the evaluated passenger load factor of the running trains. , we can calculate the overall passenger load factor level of the operation plan as Since transportation efficiency is maximization-oriented, in order to adapt to the minimization-oriented goal of the train operation plan optimization model, the train operation plan adjustment optimization goal is adjusted. Therefore, the objective function of transportation efficiency evaluation is: .

[0082] in, For train identification, To launch the plan, for The target value, For trains The total number of stations along the route, For trains The station sign of the route, , For trains Capacity, For interval Mileage, is the interval identifier, For trains For the The station area, , For station signs, For trains in the operation plan The first stations, For trains in the operation plan The first stations, train occupancy rate.

[0083] The constraints for preliminary evaluation of transport efficiency are: capacity allocation constraints, interval throughput capacity constraints, number of trains departing and terminating at stations, basic diagram constraints, departure and terminating time constraints, train capacity constraints, and service frequency constraints.

[0084] 1) Capacity allocation constraints

[0085] The upper limit of railway network capacity can be expressed in terms of train kilometers. The calculation coefficient of train mileage is determined by the marshaling capacity :If the train For a single train, ;otherwise, Then the capacity allocation constraint is: .

[0086] in, For trains The calculation coefficient of kilometers, Set an upper limit for the railway network's capacity allocation (i.e. the upper limit on the number of kilometers of EMUs available for use in the railway network).

[0087] 2) Interval passing capacity constraints

[0088] Affected by railway traffic safety factors, the number of sections passed per unit time (per day or per hour) The number of trains entering the section must meet the corresponding capacity limit. The number of trains is , then the interval passing capacity constraint is: .

[0089] in, , is the interval set of the railway network, To enter the interval throughout the day The number of trains, For interval The upper limit of passing ability.

[0090] 3) Constraints on the number of trains originating and terminating at a station

[0091] The capacity of trains originating and terminating at a station is affected by many factors, such as the station grade, the nature of technical operations, the number of trains arriving and departing from the station, and the distribution of train depots (sections). When designing a train operation plan, the number of trains originating and terminating at each station cannot exceed the upper limit of its capacity. The number of trains departing from , the number of arriving trains is equal to , must meet their origin and destination capabilities respectively The constraint, that is, the number of trains originating and terminating at a station is: , .

[0092] in, , is the set of stations in the railway network, For trains in the operation plan The first station along the route, For trains in the operation plan The first stations, For the station The starting and ending capacity limit.

[0093] If the station If the train cannot start and end at the destination, .

[0094] 4) Basic graph constraints

[0095] The trains in the operation plan must be selected from the alternative trains in the basic operation diagram within the diagram period. Therefore, the basic diagram constraints are: .

[0096] in, is the train set of the basic operation diagram, .

[0097] 5) Time constraints for departure and arrival

[0098] The departure and arrival times of trains should be within the operating period. Assuming that the full-day operating period is , then the departure and arrival time constraints are: .

[0099] in, The starting time of the all-day operation period. The end time of the all-day operation period. , For trains The departure time, For trains In the The arrival time of each station.

[0100] If a given train In the interval Running time , and at the station The sum of the start-stop additional time and the stop time , you can determine the train Arrival time at stations along the way and departure time .

[0101] in, For station signs, .

[0102] 6) Train capacity constraints

[0103] The train models selected in the train operation plan must meet the actual EMU models, so the train formation must meet the feasible capacity set of the equipped models, that is, the train capacity constraint is: .

[0104] in, To equip the vehicle model with a fixed number of people, .

[0105] 7) Service frequency constraints

[0106] To meet the travel needs of passengers from the station to the departure station, the service of each station must meet a certain service level, that is, it must have a certain service frequency lower limit. Therefore, the frequency of stops at each station must meet this lower limit constraint, that is, the service frequency constraint is: .

[0107] in, For the station The lower limit of service frequency, For trains With the station The associated identifier of train At the station Stop ,otherwise .

[0108] When executing step 102, the characteristic vectors of all trains in the operation plan are a two-dimensional matrix, that is, , the passenger load factor of each train is represented as a one-dimensional label vector, that is In step 102, see Figure 2 Based on the characteristic vectors of all trains in the operation plan, the evaluation model uses a two-dimensional wavelet packet decomposition process to convert them into multi-channel data. The evaluation model then uses a convolutional neural network to train the mapping between the operation plan's operating elements and train passenger load factors, thereby evaluating the plan's transport efficiency and obtaining an efficiency evaluation value. Finally, the optimized operation plan and its transport efficiency evaluation value are determined based on the efficiency evaluation value.

[0109] It should be noted that the above is a theoretical explanation of the implementation process of step 102. The operation plan is a general concept. Depending on the specific implementation situation, the operation plan can be a high-speed train operation plan, a neighboring train operation plan, or other specific operation plans. In other words, the two-dimensional wavelet packet decomposition module in the evaluation model processes the operation plan, and the specific operation plan is not limited. Based on the specific implementation requirements, the accurate operation plan can be input into the two-dimensional wavelet packet decomposition module of the evaluation model.

[0110] In specific implementation, the implementation details of step 102 are as follows:

[0111] 102-1, the feature vectors of all trains in the high-speed railway operation plan are converted into multi-channel data through the two-dimensional wavelet packet decomposition module .

[0112] in, A plan for the operation of high-speed railway trains.

[0113] In other words, the operation plan of high-speed railway trains will be Input the two-dimensional wavelet packet decomposition module in the evaluation model, and use the two-dimensional wavelet packet decomposition module to decompose the input Convert the feature vectors of all trains into multi-channel data .

[0114] 102-2, through convolutional neural network, based on Carry out transport efficiency pre-evaluation based on the passenger load factor of each train to obtain the efficiency evaluation value . Determine the current solution , determine the target value of the current solution , determine the optimal solution , determine the target value of the optimal solution , determine the number of iterations , determine the current temperature .

[0115] in, is the preset initial temperature.

[0116] For example, through convolutional neural networks, the objective function Get performance evaluation value .

[0117] 102-3, according to Construct a neighborhood train operation plan.

[0118] In step 102-3, The target train in is processed as follows to obtain the operation plan of the neighboring trains:

[0119] Suspended trains

[0120] Suspension of operation The first target train.

[0121] Among them, the first target train is a single train, and its passenger occupancy rate is lower than , is the preset first ratio value, such as .

[0122] That is to say, for the current solution If the passenger occupancy rate of a single train is lower than (such as 25%), the train will be suspended.

[0123] Changing train capacity

[0124] 1. The second target train is The probability of this is adjusted to a longer train with a smaller capacity.

[0125] in, is the preset first probability value, such as The second target train is a long train or a multiple train, and its passenger load factor is Inside, is the preset second ratio value, is the preset third ratio value, ,like , .

[0126] 2. The third target train is The probability is adjusted to a single train.

[0127] in, is the preset second probability value, ,like The third target train is a long train or a multiple train, and its passenger load factor is lower than .

[0128] That is to say, for the current solution For long trains or multiple trains, if the passenger load factor is within a certain low range, Inside (such as ), then with a certain probability (e.g. 0.7) Adjust to a longer train with smaller capacity; if the passenger occupancy rate is lower than a certain threshold (such as 40%), then with a certain probability (such as 0.9) adjusted to a single train.

[0129] Add additional trains

[0130] For long trains / multiple trains with load factors above a certain threshold, or short trains where additional trains are not possible, check the basic chart to see if there are peak-line train pairs (independent peak-line trains require the entire route to be opened) that are close to the train's high-utilization section at adjacent time points. If so, add the corresponding trains.

[0131] Therefore, increase The train corresponding to the fourth target train in .

[0132] Among them, the fourth target train is a long train or a double-unit train or a short train that cannot be increased, and its passenger load factor is higher than , It is a preset fourth ratio value, and at the same time, there are peak line pairs corresponding to the high utilization section of the fourth target train at adjacent time points in the basic diagram.

[0133] The train corresponding to the added fourth target train is the train corresponding to the peak line pair corresponding to the high utilization section of the fourth target train at adjacent time points in the basic diagram.

[0134] Adjust stops

[0135] For the station If the lower limit constraint of service frequency is to be met, the principle of temporal and spatial uniformity of the distribution of train stops at stations is adopted. Under the premise of no operation conflict, trains with low stopover frequency are selected to add stops, and the arrival and departure times of trains along the route are updated.

[0136] Therefore, adjust The arrival and departure times of the fifth target train along the way.

[0137] Among them, the stations along the route of the fifth target train include the target station, and the target station meets the service frequency constraint.

[0138] The service frequency constraint is: ,in, For train identification, To launch the plan, For the station The lower limit of service frequency, For trains With the station The associated identifier of train At the station Stop ,otherwise .

[0139] Adjust the operating section

[0140] For trains with low occupancy rates, the starting and ending points of the extended section will be determined and the train operation section will be adjusted based on the capacity constraints of the starting and ending points near the starting and ending stations and the section.

[0141] Therefore, according to the interval through capacity constraint adjustment The section where the sixth target train runs.

[0142] Among them, the passenger occupancy rate of the sixth target train was lower than , is the preset fifth ratio value.

[0143] The interval passing capacity constraint is: .

[0144] in, is the interval identifier, , is the interval set of the railway network, To enter the interval throughout the day The number of trains, For interval The upper limit of passing ability.

[0145] It should be noted that this embodiment does not limit the above 、 、 、 The relationship between the values ​​can be completely the same, partially the same, or completely different. Similarly, this embodiment does not limit the above 、 、 、 The relationship between the values ​​can be completely the same, partially the same, or completely different. .

[0146] 102-4, the feature vectors of all trains in the neighborhood train operation plan are converted into multi-channel data through the two-dimensional wavelet packet decomposition module .

[0147] in, For the The iteration is to construct the neighborhood train operation plan.

[0148] In other words, the operation plan of the neighboring trains will be Input the two-dimensional wavelet packet decomposition module in the evaluation model, and use the two-dimensional wavelet packet decomposition module to decompose the input Convert the feature vectors of all trains into multi-channel data .

[0149] 102-5, through convolutional neural network, based on Carry out transport efficiency pre-evaluation based on the passenger load factor of each train to obtain the efficiency evaluation value .

[0150] For example, through convolutional neural networks, the objective function Get performance evaluation value .

[0151] 102-6, Determine the evaluation difference .

[0152] 102-7, if , then update ,renew ,renew ,renew .

[0153] like but , then update ,renew .

[0154] in, is the natural exponential function, is a random function.

[0155] 102-8, .

[0156] 102-9, if based on and If the termination condition is not met, re-execute The step of constructing the operation plan of the neighboring train (i.e. step 102-3) and the subsequent steps are cyclically performed. and If the termination conditions are met, the optimized operation plan is , and the transport efficiency evaluation value of the optimized operation plan is .

[0157] Specifically, if , it is determined that the termination condition is not met.

[0158] in, The total number of preset iterations.

[0159] like , then update ,renew .like , then it is determined that the termination condition is not met. If , then it is determined that the termination condition is met.

[0160] in, is the temperature drop ratio, is the preset end temperature.

[0161] In the specific implementation, step 102 will be based on the railway network , all-day operating hours , high-speed railway train operation plan , the train set of the basic operation diagram , the upper limit of railway network capacity configuration ,station The maximum capacity of the origin and destination 、Train at the station The sum of the start-stop additional time and the stop time , service frequency lower limit , interval The upper limit of the passing ability ,train Calculation coefficient of kilometers , initial temperature , termination temperature , the total number of iterations , temperature drop ratio , the passenger load factor of each train, and the optimized operation plan is obtained through the evaluation model and its transport efficiency evaluation value

[0162] Train formation calculation coefficient , algorithm initial temperature and termination temperature , the number of inner loop iterations , temperature drop ratio .

[0163] In addition, the high-speed railway train operation plan in the high-speed railway train operation plan transportation efficiency evaluation optimization method provided in this embodiment is pre-compiled. The high-speed railway train operation plan transportation efficiency evaluation optimization method provided in this embodiment can directly obtain the compiled high-speed railway train operation plan. The process of compiling the high-speed railway train operation plan is as follows:

[0164] 201, determine the complete set of passenger train operation plans for the designated lines or areas in the next chart period.

[0165] When executing step 201, the complete set of passenger train operation plans for the designated lines or areas in the next schedule period can be determined based on the pre-input passenger travel demand estimate data, combined with the passenger train operation plan for the current schedule period, and comprehensive consideration of new plans, suspension plans, and adjustment plans.

[0166] Furthermore, the core of high-speed train operation plan development lies in determining whether the current set of operation plans meets the constraints of the HHTPV (High-feasibility High-speed Train Plan Validation) framework. The passenger trains corresponding to the current set of operation plans can be divided into two categories. One category involves passenger trains that have been confirmed to operate and have already been mapped on the timetable. This set of operation plans is called a fixed-operation passenger train operation plan set. For newly built high-speed rail lines, this type of operation plan primarily involves established operations that must be executed on the line, such as benchmark trains or important trains that originate or terminate at key hub stations and pass through the line. Although these trains are not initially mapped on the timetable during high-speed train operation plan development, their importance requires them to be confirmed and mapped at the outset. For non-newly built high-speed rail lines, in addition to the above situations, this type of operation plan mainly includes passenger train operation plans that have been laid out in the operation diagram and have not been cancelled in the current diagram period.

[0167] Another type is a set of alternative passenger train operation plans. When high-speed train operation plans are initially compiled, these plans are not yet fully mapped on the timetable. The number of such plans can exceed the actual number of trains required and the railway network's carrying capacity. By setting up redundant alternative operation plans, the compilation process can be more flexible and iterative. Furthermore, during the compilation process, the alternative train operation plans can be adjusted based on actual conditions to obtain a more optimal plan.

[0168] It's important to note that, to more accurately optimize the operation plan selection process, a certain degree of redundancy is implemented in the initialization of the set of alternative operation plans. This redundancy allows for fine-tuning of the alternative train operation plans based on actual conditions during the compilation process, ultimately resulting in a more optimal overall operation plan. In practice, the number of redundant operation plans should be appropriately set based on actual conditions to ensure flexibility and efficiency in the compilation process.

[0169] In summary, the complete set of passenger train operation plans for the designated lines or areas in the next chart period determined in step 201 .

[0170] in, A collection of passenger train operation plans that run regularly on designated lines or in designated areas.

[0171] , A set of trains that meet preset conditions in the passenger train operation plan for a specified line or area. It is a collection of passenger train operation plans that have been completed in the operation diagram for a specified line or area and have not been cancelled in the current diagram period.

[0172] , It is a set of passenger train operation plans for the specified line or area in the current chart period. A collection of passenger train operation plans for designated lines or areas with planned suspension of service.

[0173] A set of alternative passenger train operation plans for designated routes or regions in the next chart period. , A collection of new passenger train operation plans.

[0174] It should be noted that, in the operation plan sets of this embodiment and subsequent embodiments, it is allowed that the basic operation information of the train plans are the same but the sequence numbers are different.

[0175] 202. Based on the basic data of the railway network, determine the basic constraints of the HHTPV framework.

[0176] When executing step 202, based on the designated line or area for which the operation plan is prepared, the topological connectivity of the railway network can be comprehensively considered according to the pre-input basic data of the railway network, the traffic capacity of the key sections and stations (yards) can be estimated, the basic parameters of the HHTPV framework can be calculated, and the basic constraints of the HHTPV framework can be determined. The basic constraints are static constraints of the HHTPV framework.

[0177] Therefore, in specific implementation, the implementation process of step 202 is:

[0178] 202-1, based on the basic data of the railway network and the topological connectivity of the railway network, the upper limit of the section's capacity, the upper limit of the station's capacity, the station's stopping capacity limit, and the limit of each train type in the section are calculated.

[0179] 202-2, based on the upper limit of the section's throughput capacity, the upper limit of the station's throughput capacity, the station's stop capacity limit, and the limit of each train type in the section, determine the passage restriction constraints and train type restriction constraints of each section, and the passage restriction constraints and stop restriction constraints of each station.

[0180] 1. Limit constraints on the interval

[0181] Among them, the passing restriction of any interval is , is the interval identifier, For train identification, A complete set of passenger train operation plans for designated routes or areas for the next chart period. For trains In the interval passed tag parameters, For trains The enable parameter, For interval The upper limit of passing ability.

[0182] is 0 or 1, Indicates train In the interval go through, Indicates train Not in range go through.

[0183] is 0 or 1, Indicates train Not enabled, Indicates train Enable.

[0184] 2. Train type restrictions in the section

[0185] The train type restriction constraint in any section is , is the train type identifier, For trains Train type The marker parameter, interval Train type Limited quantity.

[0186] For trains The type of train.

[0187] Affected by the combined effects of operational planning and throughput capacity limitations.

[0188] 3. Station pass restrictions

[0189] The passing restriction constraint for any station is , For station signs, For trains At the station passed tag parameters, For the station The upper limit of passing ability.

[0190] is 0 or 1, Indicates train At the station go through, Indicates train Not at the station go through.

[0191] 4. Station stop restrictions

[0192] The stop restriction constraint at any station is , For trains At the station The marking parameters of the stop, For the station The stop capacity limit value.

[0193] is 0 or 1, Indicates train At the station Stop, Indicates train Not at the station Stop.

[0194] Steps 201 and 202 are the pre-processing stage for compiling the high-speed railway train operation plan. In this stage, the basic constraints of the HHTPV framework are determined and the complete set of passenger train operation plans for the designated lines or regions in the next diagram period is generated.

[0195] 203 , initialize the HHTPV framework based on the constraint conditions.

[0196] The constraint conditions are determined based on the basic constraints and the dynamic threshold constraint set.

[0197] Step 203 is the initialization process of the HHTPV framework. In step 203, the HHTPV framework is initialized according to the constraints of the HHTPV framework in the current state, and the preparation work of the HHTPV framework is completed.

[0198] The constraint conditions include the basic constraints obtained in step 202 and the dynamic threshold constraint set obtained in step 205 .

[0199] In step 205 , an iterative process of the operation diagram coordination phase is performed, and the iterative process obtains the latest train operation constraints, which constitute a continuously updated dynamic threshold constraint set.

[0200] 204. Generate a running plan in the current state based on the optimization strategy, the optimization adjustment direction of the running plan, and the complete set of passenger train running plans for the designated lines or areas in the next chart period.

[0201] Step 204 is the process of optimizing the operation plan. This process is based on the optimization strategy input in advance and the optimization adjustment direction of the operation plan (the optimization adjustment direction of the operation plan is the adjustment feedback information obtained by iterative feedback in the process of the plan preparation stage). The alternative passenger train operation plans are optimized to generate the operation plan under the current status.

[0202] In addition, this embodiment does not restrict the preferred strategy, which can be determined according to actual needs. If the actual demand is passenger demand (such as the minimum number of train stops), then under the constraint of meeting passenger demand, with the minimum number of train stops as the goal, the preferred strategy is determined as .

[0203] in, For train identification, A complete set of passenger train operation plans for designated routes or areas for the next chart period. For station signs, is the set of stations in the railway network, For trains At the station The marking parameters of the stop.

[0204] In addition to the aforementioned optimization strategies, weighted multi-objective optimization strategies can also be proposed based on the optimization objectives of various operation plans. For example, objectives such as minimizing train stops, evenly distributing stops, and rationally assigning train types can be weighted as multiple objectives to form a multi-objective optimization strategy. In reality, the objectives of optimization strategies are complex, and some cannot be numerically quantified. In such cases, manual optimization strategies can be employed based on specific circumstances, with professionals selecting the optimal operation plan based on actual conditions to ensure its rationality.

[0205] Steps 203 and 204 are the high-speed railway train operation plan preparation phase. During this phase, the HHTPV framework is initialized, the operation plan optimization process is iterated, and the passenger train operation plan is gradually optimized to finally produce the operation plan in the current HHTPV framework state.

[0206] 205. Within the HHTPV framework, the set of operation plans in the current state is verified, and the operation plan of high-speed railway trains is compiled based on the verification results.

[0207] The verification includes constraint verification and feasibility verification, so the implementation process of step 205 is: within the HHTPV framework, constraint verification is performed on the set of operation plans in the current state.

[0208] If constraint validation fails, then:

[0209] 1) Update the operation plan and optimize the adjustment direction.

[0210] 2) Re-execute the step of generating the current state of the operation plan (i.e., step 204) and subsequent steps based on the optimization strategy, the optimization adjustment direction of the operation plan, and the complete set of passenger train operation plans for the designated lines or areas in the next chart period.

[0211] If the constraint validation passes, then:

[0212] 1) Pre-draw the operation diagram for the set of operation plans in the current state and generate the operation diagram pre-drawing results.

[0213] During the pre-layout process, the timetable can be pre-drawn based on the set of current operation plans generated during the plan preparation phase. To ensure both accuracy and efficiency, a passenger train operation constraint model can be established, allowing the pre-layout process to be automated through a computer program, improving the efficiency of the entire process. In practice, since the pre-layout process is intended to verify the high feasibility of the operation plan, some constraints on the actual timetable can be relaxed to reduce the complexity of the plan, minimize resource consumption during the verification process, and improve verification efficiency.

[0214] 2) Conduct feasibility verification based on the preliminary layout results of the operation diagram.

[0215] The feasibility verification process can be implemented based on the conflict judgment of the operation diagram, such as judging whether the set of operation plans under the current state is feasible based on the results of the operation diagram pre-layout.

[0216] 3) If the feasibility verification fails, the dynamic threshold constraint set is updated, and the step of initializing the HHTPV framework based on the constraint conditions (ie, step 203 ) and subsequent steps are re-executed.

[0217] If the feasibility verification is passed, the operation plan set in the current state will be determined as the operation plan for the compiled high-speed railway train.

[0218] For example, if the feasibility verification fails, new dynamic threshold constraints are generated through operation diagram conflict analysis, forming a new dynamic threshold constraint set, introducing the HHTPV framework, and re-executing the plan preparation phase process until the final highly feasible passenger train operation plan is generated. The final highly feasible passenger train operation plan is the compiled high-speed railway train operation plan.

[0219] If the feasibility verification passes, there are no train operation conflicts. The current set of operation plans is now a highly feasible passenger train operation plan, which is the final high-speed train operation plan. This high-speed train operation plan satisfies the constraints of the HHTPV framework and is highly feasible. It can be incorporated into the subsequent railway passenger operation organization process, providing efficient and safe travel services for passengers.

[0220] The process of updating the dynamic threshold constraint set is as follows: perform conflict analysis on the operation diagram according to the pre-layout result of the operation diagram, and Updates the dynamic threshold constraint set.

[0221] in, For train identification, A complete set of passenger train operation plans for designated routes or areas for the next chart period. is the train type identifier, is the set of train types, is the interval identifier, is the interval set of the railway network, is the dynamic threshold constraint identifier in the dynamic threshold constraint set, Dynamic threshold constraint Belong to the interval The marker parameter, For trains In the interval passed tag parameters, For trains Train type The marker parameter, Dynamic threshold constraint For train types The constraint weighting, For trains The enable parameter, Dynamic threshold constraint limit value.

[0222] is 0 or 1, Represents a dynamic threshold constraint Belong to the interval , Represents a dynamic threshold constraint Does not belong to the interval. It allows constraints to be managed in multiple related sections, thereby alleviating train conflicts in multiple section management and expanding the scope of constraints.

[0223] , that is, the interval consists of partially ordered station pairs.

[0224] It is a train type set, that is, a train category subdivision set, which allows subdivision based on train grade, train speed, and whether it is a benchmark train.

[0225] With dynamic threshold constraints Limit value By cooperating, the ability to control and manage multiple types of trains can be achieved.

[0226] The iterative update process of the dynamic threshold constraint set in this step is a crucial component of the HHTPV framework. Its core function is to verify the high feasibility of the train operation plan. By dynamically controlling the carrying capacity of the train operation plan for each line section, combined with the operation plan optimization process in step 204, a set of mathematical programming problems for optimizing the passenger train operation plan can be constructed and solved within the closed-loop iterative process in step 205. Simultaneously, verification is performed using dynamic threshold constraints to ensure that the high-speed railway train operation plan meets the constraints of the current constraint combination.

[0227] The dynamic threshold constraint generation process utilizes a closed-loop iterative mechanism. First, a pre-planned operation diagram is created based on the current operation plan. A conflict detection algorithm is then used to identify sections with irreconcilable conflicts. Dynamic threshold adjustments are then performed for these problematic sections. Existing threshold constraint limit parameters are revised, targeted grouping threshold constraints are added to eliminate conflicting operation plan combinations, and redundant threshold constraints generated in previous iterations are cleared. After multiple rounds of iterations of "scheme optimization-conflict detection-threshold constraint adjustment," a highly feasible operation plan—the one for high-speed trains—is ultimately generated that meets both transport capacity constraints and adheres to the optimization mechanism.

[0228] This constraint has different application characteristics in different scenarios. For non-core lines or regions, the threshold parameter settings for relevant intervals can be simplified to quickly complete feasibility judgments and improve the efficiency of plan preparation. For core lines or regions, grouping constraints can be refined based on dimensions such as train speed and vehicle type composition. Multi-level threshold constraints can be used to accurately control the combination characteristics of train operation plans, ensuring the high feasibility of high-speed rail train operation plans.

[0229] After the dynamic threshold constraint set initializes the HHTPV framework in step 203, the dynamic threshold constraint set remains unchanged in step 204 (i.e., the dynamic threshold constraint set is fixed during the operation plan optimization process in step 204). However, during the iteration process in step 205, it will be dynamically adjusted based on the results of the operation diagram pre-layout.

[0230] In addition, by adjusting Make Equal to 1, the parameters can be reduced, that is, corresponding to the new constraint But keep This constraint can be made more consistent with the physical meaning of train operation. In practical applications, and The value of should be reasonably set according to the characteristics of the train type to ensure the effectiveness of the constraint.

[0231] Step 205 is the coordinated phase of high-speed train operation plan compilation. This phase verifies the current set of operation plans against the constraints of the HHTPV framework to determine whether they meet the constraints. If so, the process proceeds to the pre-layout phase. If not, a new operation plan with optimal adjustment directions is generated based on the adjustment feedback from the HHTPV framework. Step 204 and subsequent steps are repeated until the constraints of the HHTPV framework are met.

[0232] During the pre-diagram drawing phase, the current set of train operation plans can be pre-drawn to determine their feasibility. For infeasible plans, a new set of dynamic threshold constraints is generated through diagram conflict determination. The HHTPV framework is then introduced, and step 203 and subsequent steps are re-executed until a final, highly feasible passenger train operation plan is generated. This final, highly feasible passenger train operation plan serves as the compiled high-speed railway train operation plan.

[0233] The high-speed train operation plan compilation process provided in this embodiment can be applied to any railway network structure. However, to ensure efficient execution and accurate results of high-speed train operation plan compilation, the railway network can be rationally divided and transformed to enable targeted verification of operation plans involving specific lines or regions. Although railway network division reduces the verification scope of the HHTPV framework, the feasibility of train operation plans outside the verification scope can still be evaluated by combining the static constraints of the HHTPV framework with dynamic threshold constraints.

[0234] The division of the railway network should be based on practical conditions to ensure that the resulting network structure maintains a certain degree of independence while also enabling effective interaction with other railway network structures. When dividing the railway network, the following factors should be considered. First, the core lines or regions for which the operation plan is compiled must be fully preserved to ensure that the operation plan is fully and accurately verified for feasibility within the core lines or regions. Second, lines connected to the core lines or regions but not involved in cross-line operation in the operation plan can be directly removed from the railway network to reduce computational complexity, as they are not required for high feasibility verification of the operation plan. Finally, for lines connected to the core lines or regions with cross-line operation in the operation plan, simplified high feasibility verification of the involved operation plan is required based on the carrying capacity of the relevant lines and actual train operation conditions. Therefore, basic connections with the core lines or regions should be retained, namely, intermediate stations on other lines in the route should be removed, and connections with the core lines or regions should be established through virtual sections to ensure high feasibility of the relevant operation plan.

[0235] Figure 3 A schematic diagram showing the division of a railway network, Figure 3 The "road network" here refers to the railway network. Figure 3 The core section of the operation plan is shown, which is composed of Line A from Station A1 to Station A7. Figure 3 The complete road network in the simplification process is used to generate the converted railway network (i.e. Figure 3The result of the conversion network in the conversion network is shown in Figure 2. Line B, Line C, Line D, and Line E represent four lines connected to Line A. Through the connection between Line A and other lines, the interaction between Line A and other lines can be realized. For Line B, assuming that there is no train operation plan in the current map or the next map period, crossing the line from Station A4 to Station B1, Line B in the conversion network can be deleted. For Line C, assuming that there is a cross-line train operation plan, crossing the line from Station A5 to Station C1 and Station C3, and the final related operation plan uses C5 as the starting and ending stations, Line C in the conversion network is retained, of which Station C1 and Station C5 are retained to fully model the related operation plan. Because Line C is not the core line for the compilation of this operation plan, the structure of Line C is simplified in the conversion network, and only the connection relationship with Line A is retained to reduce the amount of calculation. Furthermore, within the HHTPV framework's operational workflow, dynamic threshold constraints for the interval between Station C1 and Station A7, and the virtual interval between Station A7 and Station C5, ensure the high feasibility of cross-line train operation plans to Line C. For Lines D and E, assuming a train operation plan exists that passes through Station D3 and originates and terminates at Station E1 or Station E5, Lines D and E are retained in the conversion network, with Stations D3, E1, and E5 retained to fully model the relevant operation plan. Within the HHTPV framework's operational workflow, dynamic threshold constraints for the corresponding virtual intervals ensure the high feasibility of the relevant train operation plan.

[0236] The high-speed railway train operation plan compilation process is divided into three phases. After the preprocessing phase, the latter two phases are iterated repeatedly. Specifically, in the preprocessing phase, passenger demand estimate data is input to determine the complete set of passenger train operation plans. Basic railway network data is input to determine the basic constraints of the HHTPV framework. In the plan compilation phase, the iteration process begins, the HHTPV framework is initialized, and passenger train operation plans are repeatedly optimized to obtain the current operation plan. In the timetable coordination phase, the timetable pre-drawing process is executed to determine whether the operation plan generated in the plan compilation phase can be drawn on the timetable. If not, the timetable conflict judgment is performed to calculate the stations or sections where conflicts may occur. Based on the corresponding topological structure, a new combination of dynamic threshold constraints for high-speed trains is generated and introduced into the HHTPV framework. Otherwise, the final operation plan is compiled, resulting in the high-speed railway train operation plan.

[0237] The high-speed railway train operation plan compilation process provided in this embodiment is based on the basic data of the railway network to determine the basic constraints of the HHTPV framework; the HHTPV framework is initialized based on the basic constraints, the operation plan set in the current state is verified within the HHTPV framework, and the compiled operation plan is determined based on the verification results, thereby realizing automatic verification of the operation plan and improving compilation efficiency.

[0238] In addition, based on the verification of the rationality of the operation plan, the railway passenger timetable can be generated, which is equivalent to the optimization of the entire chain. The main considerations for the generation of the railway passenger timetable are:

[0239] The passenger flow information of the current station is used to learn the passenger flow heat, obtain the passenger flow heat of the current station, determine the local area where the current station is located, and construct a local heat matrix based on the passenger flow heat of other stations corresponding to the local area where the current station is located.

[0240] Perform eigenvalue decomposition on the local heat matrix to obtain the heat learning features corresponding to the local area where the current station is located. This heat learning feature is used to generate the initial passenger schedule for the current station. The station's intra-station scheduling coupling degree is determined based on the passenger flow heat and passenger adjustment ratio at the current station.

[0241] Determining the station scheduling coupling degree of the current station specifically includes:

[0242] Based on a preset coupling degree extraction cycle, trend values ​​of the passenger flow heat change trend and the passenger transport adjustment trend are collected respectively to obtain a passenger flow heat trend value sequence and a passenger transport adjustment trend value sequence;

[0243] After normalizing the passenger flow heat trend value sequence and the passenger transport adjustment trend value sequence, a coupling degree analysis is performed based on the passenger flow heat trend value sequence and the passenger transport adjustment trend value sequence to obtain the station scheduling coupling degree of the current station.

[0244] In specific implementation, the coupling degree extraction period can be mapped based on the current passenger flow density. In some embodiments, the coupling degree extraction period can be fixed to a constant value of 6h, and then the Pearson correlation coefficient between the passenger flow heat trend value sequence and the passenger adjustment trend value sequence can be used as the intra-station scheduling coupling degree.

[0245] The initial passenger transport timetable is dynamically updated based on the intra-station scheduling coupling degree and the inter-station scheduling coupling degree to generate an optimized passenger transport timetable.

[0246] In order to address the problems of insufficient dynamic response, difficulty in multi-disciplinary collaboration and low computing efficiency caused by the independent operation of passenger flow forecasting, train adjustment, seat allocation and timetable compilation in traditional methods, a modular collaborative system for passenger transport, transportation, scheduling and vehicle operations is constructed, and a closed-loop process of "adjustment plan generation → dynamic timetable generation → operation evaluation → feedback optimization" is established, using standardized interfaces to achieve lightweight data interaction.

[0247] The high-speed rail train operation plan transportation efficiency evaluation optimization method provided in this embodiment starts from the efficiency and benefits of both the supply and demand sides of the railway, selects the transportation efficiency evaluation index system constructed by the overall passenger occupancy rate level of the operation plan, and can conduct multi-dimensional evaluation of the transportation efficiency of the operation plan from aspects such as service level, operational efficiency and capacity utilization.

[0248] The evaluation model designs a two-dimensional feature matrix based on the operation elements of the operation plan, uses a two-dimensional wavelet packet decomposition module to decompose the two-dimensional wavelet packet, converts it into multi-channel data, and uses a convolutional neural network to evaluate the transportation efficiency.

[0249] When evaluating transport efficiency, the overall passenger load factor level is used as the optimization target for the operation plan. Constraints such as capacity allocation, transport organization, and service level are comprehensively considered. Based on the results of the transport efficiency evaluation, the operation plan for neighborhood trains is constructed and solved.

[0250] The high-speed rail train operation plan transport efficiency evaluation optimization method provided in this embodiment can improve the accuracy of operation plan transport efficiency evaluation. The high-speed rail train operation plan transport efficiency evaluation optimization method provided in this embodiment comprehensively extracts the operation plan characteristic elements based on historical operation big data, deeply explores the mapping and correlation between the operation elements of the train operation plan and between the operation elements and transport efficiency, realizes the estimation of the passenger load factor distribution of the operation trains, and improves the accuracy of the operation plan transport efficiency evaluation.

[0251] The high-speed train operation plan transport efficiency evaluation and optimization method provided in this embodiment can improve the supply and demand adaptability of the operation plan. The high-speed train operation plan transport efficiency evaluation and optimization method provided in this embodiment uses operation plan transport efficiency pre-evaluation technology to obtain the distribution of the supply and demand adaptability of the operation plan, designs corresponding operation factor adjustment strategies based on the supply and demand adaptability distribution, and uses an iterative algorithm to continuously optimize the operation plan to improve the supply and demand adaptability of the operation plan.

[0252] The high-speed train operation plan transport efficiency evaluation and optimization method provided in this embodiment can optimize transport organization efficiency. This embodiment provides a high-speed train operation plan transport efficiency evaluation and optimization method by constructing an operation plan transport efficiency pre-evaluation model to accurately and quantitatively evaluate the operation plan's transport efficiency, providing a reference basis for operation plan optimization design. Simultaneously, based on this model, the operation plan optimization method is designed to achieve intelligent decision-making for train operation plans, optimize train operation implementation results, effectively reduce manual workload, and optimize transport organization efficiency.

[0253] This embodiment provides a method for optimizing the transport efficiency evaluation of a high-speed train operation plan, which obtains the operation plan of a high-speed train and the passenger load factor of each train; based on the operation plan of the high-speed train and the passenger load factor of each train, an optimized operation plan and its transport efficiency evaluation value are determined through an evaluation model; wherein the evaluation model includes a two-dimensional wavelet packet decomposition module and a convolutional neural network; the decomposition function of the two-dimensional wavelet packet decomposition module is Daubechies4, and the two-dimensional wavelet packet decomposition module is used to convert the feature vectors of all trains in the operation plan into multi-channel data; the convolutional neural network is used to evaluate the transport efficiency based on the multi-channel data and the passenger load factor of each train; wherein the convolutional neural network is trained based on multiple historical operation plans and their train passenger load factors, a mapping relationship is constructed, and the transport efficiency evaluation is performed. The method of this embodiment can accurately evaluate the transport efficiency based on the operation plan of the high-speed train and the passenger load factor of each train, and then obtain an optimized operation plan, thereby realizing automatic optimization of the transport efficiency evaluation of the high-speed train operation plan and improving the optimization efficiency and accuracy.

[0254] Based on the same inventive concept of the high-speed train operation plan transportation efficiency evaluation optimization method, this embodiment provides a high-speed train operation plan transportation efficiency evaluation optimization device, see Figure 4 , the device comprises:

[0255] The acquisition module 401 is used to obtain the operation plan of high-speed railway trains and the passenger occupancy rate of each train.

[0256] The optimization module 402 is used to determine the optimized operation plan and its transportation efficiency evaluation value through the evaluation model according to the operation plan of the high-speed railway trains and the passenger occupancy rate of each train obtained by the acquisition module 401.

[0257] Among them, the evaluation model includes a two-dimensional wavelet packet decomposition module and a convolutional neural network.

[0258] The decomposition function of the two-dimensional wavelet packet decomposition module is Daubechies4, and the two-dimensional wavelet packet decomposition module is used to convert the characteristic vectors of all trains in the operation plan into multi-channel data.

[0259] Convolutional neural networks are used to evaluate transportation efficiency based on multi-channel data and the passenger load factor of each train.

[0260] Among them, the convolutional neural network is trained based on multiple historical operation plans and their train occupancy rates to construct mapping relationships and conduct transportation efficiency evaluation.

[0261] The optimization module 402 is used to convert the feature vectors of all trains in the high-speed railway operation plan into multi-channel data through a two-dimensional wavelet packet decomposition module. .in, A plan for the operation of high-speed railway trains.

[0262] Through convolutional neural networks, based on Carry out transport efficiency pre-evaluation based on the passenger load factor of each train to obtain the efficiency evaluation value . Determine the current solution , determine the target value of the current solution , determine the optimal solution , determine the target value of the optimal solution , determine the number of iterations , determine the current temperature .in, is the preset initial temperature.

[0263] according to Construct a neighborhood train operation plan.

[0264] The characteristic vectors of all trains in the neighborhood train operation plan are converted into multi-channel data through the two-dimensional wavelet packet decomposition module .in, For the The iteration is to construct the neighborhood train operation plan.

[0265] Through convolutional neural networks, based on Carry out transport efficiency pre-evaluation based on the passenger load factor of each train to obtain the efficiency evaluation value .

[0266] Determine the assessment difference .

[0267] like , then update ,renew ,renew ,renew .like but , then update ,renew .in, is the natural exponential function, is a random function.

[0268] .

[0269] If based on and If the termination condition is not met, re-execute Steps and subsequent steps for constructing the operation plan of the neighborhood train. and If the termination conditions are met, the optimized operation plan is , and the transport efficiency evaluation value of the optimized operation plan is .

[0270] Among them, according to Construct a neighborhood train operation plan, including:

[0271] right The target train in is processed as follows to obtain the operation plan of the neighboring trains:

[0272] Suspension of operation The first target train is a single train, and its passenger load factor is lower than , is the preset first ratio value.

[0273] Will The second target train is The probability of adjusting to a longer train with smaller capacity. is the preset first probability value. The second target train is a long train or a multiple train, and its passenger occupancy rate is Inside, is the preset second ratio value, is the preset third ratio value, .

[0274] Will The third target train is The probability of is adjusted to a single train. is the preset second probability value, The third target train is a long train or a multiple train, and its passenger load factor is lower than .

[0275] Increase The train corresponding to the fourth target train in . Among them, the fourth target train is a long train or a double-unit train or a short train that cannot be increased, and its passenger load factor is higher than , It is a preset fourth ratio value, and at the same time, there are peak line pairs corresponding to the high utilization section of the fourth target train at adjacent time points in the basic diagram.

[0276] Adjustment The arrival and departure times of the fifth target train along the route. The stations along the route of the fifth target train include the target station, and the target station meets the service frequency constraint. The service frequency constraint is: ;in, For train identification, To launch the plan, For the station The lower limit of service frequency, For trains With the station The associated identifier of train At the station Stop ,otherwise .

[0277] Adjustment based on interval passing capacity constraints The sixth target train runs in the following sections. Among them, the passenger occupancy rate of the sixth target train is lower than , is the preset fifth ratio value. The interval passing capacity constraint is: ;in, is the interval identifier, , is the interval set of the railway network, To enter the interval throughout the day The number of trains, For interval The upper limit of passing ability.

[0278] Among them, the objective function of transportation efficiency evaluation is: .

[0279] in, For train identification, To launch the plan, for The target value, For trains The total number of stations along the route, For trains The station sign of the route, For trains Capacity, For interval Mileage, is the interval identifier, For trains For the The station area, , For station signs, For trains in the operation plan The first stations, For trains in the operation plan The first stations, train occupancy rate.

[0280] The constraints for preliminary evaluation of transport efficiency are: capacity allocation constraints, interval throughput capacity constraints, number of trains departing and terminating at stations, basic diagram constraints, departure and terminating time constraints, train capacity constraints, and service frequency constraints.

[0281] Among them, the capacity allocation constraint is: .in, For trains The calculation coefficient of kilometers, Place a cap on rail network capacity.

[0282] The interval passing capacity constraint is: .in, , is the interval set of the railway network, To enter the interval throughout the day The number of trains, For interval The upper limit of passing ability.

[0283] The number of trains originating and terminating at a station is constrained as follows: , .in, , is the set of stations in the railway network, For trains in the operation plan The first station along the route, For trains in the operation plan The first stations, For the station The starting and ending capacity limit.

[0284] The basic graph constraints are: .in, is the train set of the basic operation diagram, .

[0285] The departure and arrival time constraints are: .in, The starting time of the all-day operation period. The end time of the all-day operation period. , For trains The departure time, For trains In the The arrival time of each station.

[0286] The train capacity constraints are: .in, To equip the vehicle model with a fixed number of people, .

[0287] The service frequency constraint is: .in, For the station The lower limit of service frequency, For trains With the station The associated identifier of train At the station Stop ,otherwise .

[0288] Among them, if , it is determined that the termination condition is not met. Among them, The total number of preset iterations.

[0289] like , then update ,renew .like , then it is determined that the termination condition is not met. If , then it is determined that the termination condition is met. Among them, is the temperature drop ratio, is the preset end temperature.

[0290] Among them, the convolutional neural network includes: input layer, hidden layer and output layer.

[0291] Hidden layers include: convolutional layers, pooling layers, and fully connected layers.

[0292] There are 3 convolutional layers, each with The convolution kernel is , and the activation function is a linear rectification unit.

[0293] The pooling function of the pooling layer is the average pooling function.

[0294] The loss function of the convolutional neural network is the mean square error function, and the optimization function is the Adam algorithm.

[0295] The process of compiling the high-speed railway train operation plan is as follows:

[0296] Determine the complete set of passenger train operation plans for the designated lines or areas in the next chart period.

[0297] Based on the basic data of the high-speed railway network, a highly feasible high-speed railway operation plan is determined to verify the basic constraints of the HHTPV framework.

[0298] The HHTPV framework is initialized based on the constraints, which are determined based on the basic constraints and the dynamic threshold constraint set.

[0299] Based on the optimization strategy, the optimization adjustment direction of the operation plan and the complete set of passenger train operation plans for the designated lines or areas in the next diagram period, the operation plan under the current status is generated.

[0300] Within the HHTPV framework, the set of operation plans under the current status is verified, and the operation plan of high-speed railway trains is compiled based on the verification results.

[0301] On the basis of verifying the rationality of the operation plan, the railway passenger timetable can be generated, which is equivalent to the optimization of the entire chain. The main considerations for generating the railway passenger timetable are:

[0302] The passenger flow information of the current station is used to learn the passenger flow heat, obtain the passenger flow heat of the current station, determine the local area where the current station is located, and construct a local heat matrix based on the passenger flow heat of other stations corresponding to the local area where the current station is located.

[0303] Perform eigenvalue decomposition on the local heat matrix to obtain the heat learning features corresponding to the local area where the current station is located. This heat learning feature is used to generate the initial passenger schedule for the current station. The station's intra-station scheduling coupling degree is determined based on the passenger flow heat and passenger adjustment ratio at the current station.

[0304] Determining the station scheduling coupling degree of the current station specifically includes:

[0305] Based on a preset coupling degree extraction cycle, trend values ​​of the passenger flow heat change trend and the passenger transport adjustment trend are collected respectively to obtain a passenger flow heat trend value sequence and a passenger transport adjustment trend value sequence;

[0306] After normalizing the passenger flow heat trend value sequence and the passenger transport adjustment trend value sequence, a coupling degree analysis is performed based on the passenger flow heat trend value sequence and the passenger transport adjustment trend value sequence to obtain the station scheduling coupling degree of the current station.

[0307] In specific implementation, the coupling degree extraction period can be mapped based on the current passenger flow density. In some embodiments, the coupling degree extraction period can be fixed to a constant value of 6h, and then the Pearson correlation coefficient between the passenger flow heat trend value sequence and the passenger adjustment trend value sequence can be used as the intra-station scheduling coupling degree.

[0308] The initial passenger transport timetable is dynamically updated based on the intra-station scheduling coupling degree and the inter-station scheduling coupling degree to generate an optimized passenger transport timetable.

[0309] In order to address the problems of insufficient dynamic response, difficulty in multi-disciplinary collaboration and low computing efficiency caused by the independent operation of passenger flow forecasting, train adjustment, seat allocation and timetable compilation in traditional methods, a modular collaborative system for passenger transport, transportation, scheduling and vehicle operations is constructed, and a closed-loop process of "adjustment plan generation → dynamic timetable generation → operation evaluation → feedback optimization" is established, using standardized interfaces to achieve lightweight data interaction.

[0310] The device provided in this embodiment accurately evaluates the transport efficiency based on the operation plan of high-speed railway trains and the passenger occupancy rate of each train, and then obtains an optimized operation plan, thereby realizing automatic optimization of the transport efficiency evaluation of the high-speed railway train operation plan and improving optimization efficiency and accuracy.

[0311] Based on the same inventive concept of the high-speed train operation plan transportation efficiency evaluation optimization method, this embodiment provides an electronic device, such as Figure 5 As shown, it includes: a memory 501, a processor 502, and a computer program.

[0312] The computer program is stored in the memory 501 and is configured to be executed by the processor 502 to implement the above-mentioned high-speed rail train operation plan transportation efficiency evaluation optimization method.

[0313] Specifically,

[0314] Obtain the high-speed rail train operation plan and the passenger load factor of each train.

[0315] According to the operation plan of high-speed railway trains and the passenger occupancy rate of each train, the optimized operation plan and its transportation efficiency evaluation value are determined through the evaluation model.

[0316] Among them, the evaluation model includes a two-dimensional wavelet packet decomposition module and a convolutional neural network.

[0317] The decomposition function of the two-dimensional wavelet packet decomposition module is Daubechies4, and the two-dimensional wavelet packet decomposition module is used to convert the characteristic vectors of all trains in the operation plan into multi-channel data.

[0318] Convolutional neural networks are used to evaluate transportation efficiency based on multi-channel data and the passenger load factor of each train.

[0319] Among them, the convolutional neural network is trained based on multiple historical operation plans and their train occupancy rates to construct mapping relationships and conduct transportation efficiency evaluation.

[0320] Among them, according to the high-speed railway train operation plan and the passenger occupancy rate of each train, the optimized high-speed railway train operation plan and its transportation efficiency evaluation value are determined through the evaluation model, including:

[0321] The feature vectors of all trains in the high-speed railway operation plan are converted into multi-channel data through the two-dimensional wavelet packet decomposition module .in, A plan for the operation of high-speed railway trains.

[0322] Through convolutional neural networks, based on Carry out transport efficiency pre-evaluation based on the passenger load factor of each train to obtain the efficiency evaluation value . Determine the current solution , determine the target value of the current solution , determine the optimal solution , determine the target value of the optimal solution , determine the number of iterations , determine the current temperature .in, is the preset initial temperature.

[0323] according to Construct a neighborhood train operation plan.

[0324] The characteristic vectors of all trains in the neighborhood train operation plan are converted into multi-channel data through the two-dimensional wavelet packet decomposition module .in, For the The iteration is to construct the neighborhood train operation plan.

[0325] Through convolutional neural networks, based on Carry out transport efficiency pre-evaluation based on the passenger load factor of each train to obtain the efficiency evaluation value .

[0326] Determine the assessment difference .

[0327] like , then update ,renew ,renew ,renew .like but , then update ,renew .in, is the natural exponential function, is a random function.

[0328] .

[0329] If based on and If the termination condition is not met, re-execute Steps and subsequent steps for constructing the operation plan of the neighborhood train. and If the termination conditions are met, the optimized operation plan is , and the transport efficiency evaluation value of the optimized operation plan is .

[0330] Among them, according to Construct a neighborhood train operation plan, including:

[0331] right The target train in is processed as follows to obtain the operation plan of the neighboring trains:

[0332] Suspension of operation The first target train is a single train, and its passenger load factor is lower than , is the preset first ratio value.

[0333] Will The second target train is The probability of adjusting to a longer train with smaller capacity. is the preset first probability value. The second target train is a long train or a multiple train, and its passenger occupancy rate is Inside, is the preset second ratio value, is the preset third ratio value, .

[0334] Will The third target train is The probability of is adjusted to a single train. is the preset second probability value, The third target train is a long train or a multiple train, and its passenger load factor is lower than .

[0335] Increase The train corresponding to the fourth target train in . Among them, the fourth target train is a long train or a double-unit train or a short train that cannot be increased, and its passenger load factor is higher than , It is a preset fourth ratio value, and at the same time, there are peak line pairs corresponding to the high utilization section of the fourth target train at adjacent time points in the basic diagram.

[0336] Adjustment The arrival and departure times of the fifth target train along the route. The stations along the route of the fifth target train include the target station, and the target station meets the service frequency constraint. The service frequency constraint is: ;in, For train identification, To launch the plan, For the station The lower limit of service frequency, For trains With the station The associated identifier of train At the station Stop ,otherwise .

[0337] Adjustment based on interval passing capacity constraints The sixth target train runs in the following sections. Among them, the passenger occupancy rate of the sixth target train is lower than , is the preset fifth ratio value. The interval passing capacity constraint is: ;in, is the interval identifier, , is the interval set of the railway network, To enter the interval throughout the day The number of trains, For interval The upper limit of passing ability.

[0338] Among them, the objective function of transportation efficiency evaluation is: .

[0339] in, For train identification, To launch the plan, for The target value, For trains The total number of stations along the route, For trains The station sign of the route, For trains Capacity, For interval Mileage, is the interval identifier, For trains For the The station area, , For station signs, For trains in the operation plan The first stations, For trains in the operation plan The first stations, train occupancy rate.

[0340] The constraints for preliminary evaluation of transport efficiency are: capacity allocation constraints, interval throughput capacity constraints, number of trains departing and terminating at stations, basic diagram constraints, departure and terminating time constraints, train capacity constraints, and service frequency constraints.

[0341] Among them, the capacity allocation constraint is: .in, For trains The calculation coefficient of kilometers, Place a cap on rail network capacity.

[0342] The interval passing capacity constraint is: .in, , is the interval set of the railway network, To enter the interval throughout the day The number of trains, For interval The upper limit of passing ability.

[0343] The number of trains originating and terminating at a station is constrained as follows: , .in, , is the set of stations in the railway network, For trains in the operation plan The first station along the route, For trains in the operation plan The first stations, For the station The starting and ending capacity limit.

[0344] The basic graph constraints are: .in, is the train set of the basic operation diagram, .

[0345] The departure and arrival time constraints are: .in, The starting time of the all-day operation period. The end time of the all-day operation period. , For trains The departure time, For trains In the The arrival time of each station.

[0346] The train capacity constraints are: .in, To equip the vehicle model with a fixed number of people, .

[0347] The service frequency constraint is: .in, For the station The lower limit of service frequency, For trains With the station The associated identifier of train At the station Stop ,otherwise .

[0348] Among them, if , it is determined that the termination condition is not met. Among them, The total number of preset iterations.

[0349] like , then update ,renew .like , then it is determined that the termination condition is not met. If , then it is determined that the termination condition is met. Among them, is the temperature drop ratio, is the preset end temperature.

[0350] Among them, the convolutional neural network includes: input layer, hidden layer and output layer.

[0351] Hidden layers include: convolutional layers, pooling layers, and fully connected layers.

[0352] There are 3 convolutional layers, each with The convolution kernel is , and the activation function is a linear rectification unit.

[0353] The pooling function of the pooling layer is the average pooling function.

[0354] The loss function of the convolutional neural network is the mean square error function, and the optimization function is the Adam algorithm.

[0355] The process of compiling the high-speed railway train operation plan is as follows:

[0356] Determine the complete set of passenger train operation plans for the designated lines or areas in the next chart period.

[0357] Based on the basic data of the high-speed railway network, a highly feasible high-speed railway operation plan is determined to verify the basic constraints of the HHTPV framework.

[0358] The HHTPV framework is initialized based on the constraints, which are determined based on the basic constraints and the dynamic threshold constraint set.

[0359] Based on the optimization strategy, the optimization adjustment direction of the operation plan and the complete set of passenger train operation plans for the designated lines or areas in the next diagram period, the operation plan under the current status is generated.

[0360] Within the HHTPV framework, the set of operation plans under the current status is verified, and the operation plan of high-speed railway trains is compiled based on the verification results.

[0361] On the basis of verifying the rationality of the operation plan, the railway passenger timetable can be generated, which is equivalent to the optimization of the entire chain. The main considerations for generating the railway passenger timetable are:

[0362] The passenger flow information of the current station is used to learn the passenger flow heat, obtain the passenger flow heat of the current station, determine the local area where the current station is located, and construct a local heat matrix based on the passenger flow heat of other stations corresponding to the local area where the current station is located.

[0363] Perform eigenvalue decomposition on the local heat matrix to obtain the heat learning features corresponding to the local area where the current station is located. This heat learning feature is used to generate the initial passenger schedule for the current station. The station's intra-station scheduling coupling degree is determined based on the passenger flow heat and passenger adjustment ratio at the current station.

[0364] Determining the station scheduling coupling degree of the current station specifically includes:

[0365] Based on a preset coupling degree extraction cycle, trend values ​​of the passenger flow heat change trend and the passenger transport adjustment trend are collected respectively to obtain a passenger flow heat trend value sequence and a passenger transport adjustment trend value sequence;

[0366] After normalizing the passenger flow heat trend value sequence and the passenger transport adjustment trend value sequence, a coupling degree analysis is performed based on the passenger flow heat trend value sequence and the passenger transport adjustment trend value sequence to obtain the station scheduling coupling degree of the current station.

[0367] In specific implementation, the coupling degree extraction period can be mapped based on the current passenger flow density. In some embodiments, the coupling degree extraction period can be fixed to a constant value of 6h, and then the Pearson correlation coefficient between the passenger flow heat trend value sequence and the passenger adjustment trend value sequence can be used as the intra-station scheduling coupling degree.

[0368] The initial passenger transport timetable is dynamically updated based on the intra-station scheduling coupling degree and the inter-station scheduling coupling degree to generate an optimized passenger transport timetable.

[0369] In order to address the problems of insufficient dynamic response, difficulty in multi-disciplinary collaboration and low computing efficiency caused by the independent operation of passenger flow forecasting, train adjustment, seat allocation and timetable compilation in traditional methods, a modular collaborative system for passenger transport, transportation, scheduling and vehicle operations is constructed, and a closed-loop process of "adjustment plan generation → dynamic timetable generation → operation evaluation → feedback optimization" is established, using standardized interfaces to achieve lightweight data interaction.

[0370] The electronic device provided in this embodiment has a computer program on which a processor executes to accurately evaluate the transport efficiency based on the operation plan of high-speed railway trains and the passenger occupancy rate of each train, thereby obtaining an optimized operation plan, thereby realizing automatic optimization of the transport efficiency evaluation of the high-speed railway train operation plan and improving optimization efficiency and accuracy.

[0371] Based on the same inventive concept as the method for evaluating and optimizing the transportation efficiency of a high-speed train operation plan, this embodiment provides a computer-readable storage medium having a computer program stored thereon. The computer program is executed by a processor to implement the method for evaluating and optimizing the transportation efficiency of a high-speed train operation plan.

[0372] Specifically,

[0373] Obtain the high-speed rail train operation plan and the passenger load factor of each train.

[0374] According to the operation plan of high-speed railway trains and the passenger occupancy rate of each train, the optimized operation plan and its transportation efficiency evaluation value are determined through the evaluation model.

[0375] Among them, the evaluation model includes a two-dimensional wavelet packet decomposition module and a convolutional neural network.

[0376] The decomposition function of the two-dimensional wavelet packet decomposition module is Daubechies4, and the two-dimensional wavelet packet decomposition module is used to convert the characteristic vectors of all trains in the operation plan into multi-channel data.

[0377] Convolutional neural networks are used to evaluate transportation efficiency based on multi-channel data and the passenger load factor of each train.

[0378] Among them, the convolutional neural network is trained based on multiple historical operation plans and their train occupancy rates to construct mapping relationships and conduct transportation efficiency evaluation.

[0379] Among them, according to the high-speed railway train operation plan and the passenger occupancy rate of each train, the optimized high-speed railway train operation plan and its transportation efficiency evaluation value are determined through the evaluation model, including:

[0380] The feature vectors of all trains in the high-speed railway operation plan are converted into multi-channel data through the two-dimensional wavelet packet decomposition module .in, A plan for the operation of high-speed railway trains.

[0381] Through convolutional neural networks, based on Carry out transport efficiency pre-evaluation based on the passenger load factor of each train to obtain the efficiency evaluation value . Determine the current solution , determine the target value of the current solution , determine the optimal solution , determine the target value of the optimal solution , determine the number of iterations , determine the current temperature .in, is the preset initial temperature.

[0382] according to Construct a neighborhood train operation plan.

[0383] The characteristic vectors of all trains in the neighborhood train operation plan are converted into multi-channel data through the two-dimensional wavelet packet decomposition module .in, For the The iteration is to construct the neighborhood train operation plan.

[0384] Through convolutional neural networks, based on Carry out transport efficiency pre-evaluation based on the passenger load factor of each train to obtain the efficiency evaluation value .

[0385] Determine the assessment difference .

[0386] like , then update ,renew ,renew ,renew .like but , then update ,renew .in, is the natural exponential function, is a random function.

[0387] .

[0388] If based on and If the termination condition is not met, re-execute Steps and subsequent steps for constructing the operation plan of the neighborhood train. and If the termination conditions are met, the optimized operation plan is , and the transport efficiency evaluation value of the optimized operation plan is .

[0389] Among them, according to Construct a neighborhood train operation plan, including:

[0390] right The target train in is processed as follows to obtain the operation plan of the neighboring trains:

[0391] Suspension of operation The first target train is a single train, and its passenger load factor is lower than , is the preset first ratio value.

[0392] Will The second target train is The probability of adjusting to a longer train with smaller capacity. is the preset first probability value. The second target train is a long train or a multiple train, and its passenger occupancy rate is Inside, is the preset second ratio value, is the preset third ratio value, .

[0393] Will The third target train is The probability of is adjusted to a single train. is the preset second probability value, The third target train is a long train or a multiple train, and its passenger load factor is lower than .

[0394] Increase The train corresponding to the fourth target train in . Among them, the fourth target train is a long train or a double-unit train or a short train that cannot be increased, and its passenger load factor is higher than , It is a preset fourth ratio value, and at the same time, there are peak line pairs corresponding to the high utilization section of the fourth target train at adjacent time points in the basic diagram.

[0395] Adjustment The arrival and departure times of the fifth target train along the route. The stations along the route of the fifth target train include the target station, and the target station meets the service frequency constraint. The service frequency constraint is: ;in, For train identification, To launch the plan, For the station The lower limit of service frequency, For trains With the station The associated identifier of train At the station Stop ,otherwise .

[0396] Adjustment based on interval passing capacity constraints The sixth target train runs in the following sections. Among them, the passenger occupancy rate of the sixth target train is lower than , is the preset fifth ratio value. The interval passing capacity constraint is: ;in, is the interval identifier, , is the interval set of the railway network, To enter the interval throughout the day The number of trains, For interval The upper limit of passing ability.

[0397] Among them, the objective function of transportation efficiency evaluation is: .

[0398] in, For train identification, To launch the plan, for The target value, For trains The total number of stations along the route, For trains The station sign of the route, For trains Capacity, For interval Mileage, is the interval identifier, For trains For the The station area, , For station signs, For trains in the operation plan The first stations, For trains in the operation plan The first stations, train occupancy rate.

[0399] The constraints for preliminary evaluation of transport efficiency are: capacity allocation constraints, interval throughput capacity constraints, number of trains departing and terminating at stations, basic diagram constraints, departure and terminating time constraints, train capacity constraints, and service frequency constraints.

[0400] Among them, the capacity allocation constraint is: .in, For trains The calculation coefficient of kilometers, Place a cap on rail network capacity.

[0401] The interval passing capacity constraint is: .in, , is the interval set of the railway network, To enter the interval throughout the day The number of trains, For interval The upper limit of passing ability.

[0402] The number of trains originating and terminating at a station is constrained as follows: , .in, , is the set of stations in the railway network, For trains in the operation plan The first station along the route, For trains in the operation plan The first stations, For the station The starting and ending capacity limit.

[0403] The basic graph constraints are: .in, is the train set of the basic operation diagram, .

[0404] The departure and arrival time constraints are: .in, The starting time of the all-day operation period. The end time of the all-day operation period. , For trains The departure time, For trains In the The arrival time of each station.

[0405] The train capacity constraints are: .in, To equip the vehicle model with a fixed number of people, .

[0406] The service frequency constraint is: .in, For the station The lower limit of service frequency, For trains With the station The associated identifier of train At the station Stop ,otherwise .

[0407] Among them, if , it is determined that the termination condition is not met. Among them, The total number of preset iterations.

[0408] like , then update ,renew .like , then it is determined that the termination condition is not met. If , then it is determined that the termination condition is met. Among them, is the temperature drop ratio, is the preset end temperature.

[0409] Among them, the convolutional neural network includes: input layer, hidden layer and output layer.

[0410] Hidden layers include: convolutional layers, pooling layers, and fully connected layers.

[0411] There are 3 convolutional layers, each with The convolution kernel is , and the activation function is a linear rectification unit.

[0412] The pooling function of the pooling layer is the average pooling function.

[0413] The loss function of the convolutional neural network is the mean square error function, and the optimization function is the Adam algorithm.

[0414] The process of compiling the high-speed railway train operation plan is as follows:

[0415] Determine the complete set of passenger train operation plans for the designated lines or areas in the next chart period.

[0416] Based on the basic data of the high-speed railway network, a highly feasible high-speed railway operation plan is determined to verify the basic constraints of the HHTPV framework.

[0417] The HHTPV framework is initialized based on the constraints, which are determined based on the basic constraints and the dynamic threshold constraint set.

[0418] Based on the optimization strategy, the optimization adjustment direction of the operation plan and the complete set of passenger train operation plans for the designated lines or areas in the next diagram period, the operation plan under the current status is generated.

[0419] Within the HHTPV framework, the set of operation plans under the current status is verified, and the operation plan of high-speed railway trains is compiled based on the verification results.

[0420] On the basis of verifying the rationality of the operation plan, the railway passenger timetable can be generated, which is equivalent to the optimization of the entire chain. The main considerations for generating the railway passenger timetable are:

[0421] The passenger flow information of the current station is used to learn the passenger flow heat, obtain the passenger flow heat of the current station, determine the local area where the current station is located, and construct a local heat matrix based on the passenger flow heat of other stations corresponding to the local area where the current station is located.

[0422] Perform eigenvalue decomposition on the local heat matrix to obtain the heat learning features corresponding to the local area where the current station is located. This heat learning feature is used to generate the initial passenger schedule for the current station. The station's intra-station scheduling coupling degree is determined based on the passenger flow heat and passenger adjustment ratio at the current station.

[0423] Determining the station scheduling coupling degree of the current station specifically includes:

[0424] Based on a preset coupling degree extraction cycle, trend values ​​of the passenger flow heat change trend and the passenger transport adjustment trend are collected respectively to obtain a passenger flow heat trend value sequence and a passenger transport adjustment trend value sequence;

[0425] After normalizing the passenger flow heat trend value sequence and the passenger transport adjustment trend value sequence, a coupling degree analysis is performed based on the passenger flow heat trend value sequence and the passenger transport adjustment trend value sequence to obtain the station scheduling coupling degree of the current station.

[0426] In specific implementation, the coupling degree extraction period can be mapped based on the current passenger flow density. In some embodiments, the coupling degree extraction period can be fixed to a constant value of 6h, and then the Pearson correlation coefficient between the passenger flow heat trend value sequence and the passenger adjustment trend value sequence can be used as the intra-station scheduling coupling degree.

[0427] The initial passenger transport timetable is dynamically updated based on the intra-station scheduling coupling degree and the inter-station scheduling coupling degree to generate an optimized passenger transport timetable.

[0428] In order to address the problems of insufficient dynamic response, difficulty in multi-disciplinary collaboration and low computing efficiency caused by the independent operation of passenger flow forecasting, train adjustment, seat allocation and timetable compilation in traditional methods, a modular collaborative system for passenger transport, transportation, scheduling and vehicle operations is constructed, and a closed-loop process of "adjustment plan generation → dynamic timetable generation → operation evaluation → feedback optimization" is established, using standardized interfaces to achieve lightweight data interaction.

[0429] The computer-readable storage medium provided in this embodiment has a computer program on which a processor executes to accurately evaluate the transport efficiency based on the operation plan of high-speed railway trains and the passenger occupancy rate of each train, thereby obtaining an optimized operation plan, thereby realizing automatic optimization of the transport efficiency evaluation of the high-speed railway train operation plan and improving optimization efficiency and accuracy.

[0430] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application may be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0431] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0432] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0433] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0434] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the features. Throughout the description of this application, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0435] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0436] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for optimizing the transport efficiency of a high-speed train operation plan, characterized in that: The method comprises: Obtain the operation plan of high-speed railway trains and the passenger occupancy rate of each train; Based on the high-speed railway train operation plan and the passenger load factor of each train, the evaluation model is used to determine the optimized operation plan and its transportation efficiency evaluation value; Wherein, the evaluation model includes a two-dimensional wavelet packet decomposition module and a convolutional neural network; The decomposition function of the two-dimensional wavelet packet decomposition module is Daubechies4, and the two-dimensional wavelet packet decomposition module is used to convert the characteristic vectors of all trains in the operation plan into multi-channel data; The convolutional neural network is used to evaluate transportation efficiency based on multi-channel data and the passenger load factor of each train; The convolutional neural network is trained based on multiple historical train operation plans and their train occupancy rates to construct a mapping relationship and evaluate transportation efficiency. The process of compiling a high-speed railway train operation plan is as follows: Determine the complete set of passenger train operation plans for the designated routes or areas in the next chart period; Based on the basic data of the high-speed railway network, a highly feasible high-speed railway operation plan is determined to verify the basic constraints of the HHTPV framework. The specific implementation process includes: Based on the basic data of the railway network and the topological connectivity of the railway network, the upper limit of the section's capacity, the upper limit of the station's capacity, the station's stopping capacity limit, and the limit of each train type within the section are calculated; According to the upper limit of the section's throughput capacity, the upper limit of the station's throughput capacity, the station's stop capacity limit, and the limit of each train type in the section, the passage restriction constraints and train type restriction constraints of each section, the passage restriction constraints and stop restriction constraints of each station are determined; Among them, the passing restriction of any interval is , is the interval identifier, For train identification, A complete set of passenger train operation plans for designated routes or areas for the next chart period. For trains In the interval passed tag parameters, For trains The enable parameter, For interval The upper limit of the passing capacity; is 0 or 1, Indicates train In the interval go through, Indicates train Not in range go through; is 0 or 1, Indicates train Not enabled, Indicates train Enable; The train type restriction constraint in any section is , is the train type identifier, For trains Train type The marker parameter, interval Train type The limit of For trains The type of train; Affected by the combined effects of operational planning and through-capacity limitations; The passing restriction constraint for any station is , For station signs, For trains At the station passed tag parameters, For the station The upper limit of the passing capacity; is 0 or 1, Indicates train At the station go through, Indicates train Not at the station go through; The stop restriction constraint at any station is , For trains At the station The marking parameters of the stop, For the station The stopping capacity limit value; is 0 or 1, Indicates train At the station Stop, Indicates train Not at the station Stop Initializing the HHTPV framework based on constraint conditions; wherein the constraint conditions are determined according to the basic constraint and the dynamic threshold constraint set; Generate a running plan in the current state based on the optimization strategy, the optimization adjustment direction of the running plan and the complete set of passenger train running plans for the designated line or area in the next chart period; Within the HHTPV framework, the set of operation plans under the current status is verified, and the operation plan of high-speed railway trains is compiled based on the verification results.

2. The method according to claim 1, characterized in that The step of determining the optimized high-speed railway train operation plan and its transport efficiency evaluation value through an evaluation model based on the high-speed railway train operation plan and the passenger occupancy rate of each train includes: The feature vectors of all trains in the high-speed railway operation plan are converted into multi-channel data through a two-dimensional wavelet packet decomposition module ;in, The operation plan of the high-speed railway train; Through convolutional neural networks, based on Carry out transport efficiency pre-evaluation based on the passenger load factor of each train to obtain the efficiency evaluation value ; Determine the current solution , determine the target value of the current solution , determine the optimal solution , determine the target value of the optimal solution , determine the number of iterations , determine the current temperature ;in, is the preset initial temperature; according to Constructing the operation plan of neighborhood trains; The characteristic vectors of all trains in the neighborhood train operation plan are converted into multi-channel data through the two-dimensional wavelet packet decomposition module ;in, For the The iteration is the constructed neighborhood train operation plan; Through convolutional neural networks, based on Carry out transport efficiency pre-evaluation based on the passenger load factor of each train to obtain the efficiency evaluation value ; Determine the assessment difference ; like , then update ,renew ,renew ,renew ;like but , then update ,renew ;in, is the natural exponential function, is a random function; ； If based on and If the termination condition is not met, the Construct the operation plan steps and subsequent steps of the neighborhood train; if and If the termination conditions are met, the optimized operation plan is , and the transport efficiency evaluation value of the optimized operation plan is .

3. The method according to claim 2, characterized in that The basis Construct a neighborhood train operation plan, including: right The target train in is processed as follows to obtain the operation plan of the neighboring trains: Suspension of operation The first target train is a single train, and its passenger load factor is lower than , is the preset first proportional value; Will The second target train is The probability of adjusting to a longer train with smaller capacity; among them, is the preset first probability value; the second target train is a long train or a multiple train, and its passenger occupancy rate is Inside, is the preset second ratio value, is the preset third ratio value, ; Will The third target train is The probability of is adjusted to a single train; among them, is the preset second probability value, The third target train is a long train or a multiple train, and its passenger load factor is lower than ; Increase The train corresponding to the fourth target train in the 4th target train; wherein the fourth target train is a long train or a double-unit train or a short train that cannot be increased in marshaling, and its passenger load factor is higher than , is a preset fourth ratio value, and at the same time, there is a peak line train pair corresponding to the fourth target train high utilization section at adjacent time points in the basic diagram; Adjustment The arrival and departure times of the fifth target train along the way; wherein the stations along the way of the fifth target train include the target station, and the target station satisfies the service frequency constraint; the service frequency constraint is: ;in, For train identification, To launch the plan, For the station The lower limit of service frequency, For trains With the station The associated identifier of train At the station Stop ,otherwise ; Adjustment based on interval passing capacity constraints The section where the sixth target train runs; among them, the passenger occupancy rate of the sixth target train is lower than , is the preset fifth ratio value; the interval passing capacity constraint is: ;in, is the interval identifier, , is the interval set of the railway network, To enter the interval throughout the day The number of trains, For interval The upper limit of passing ability.

4. The method according to claim 1, wherein The objective function for transport efficiency evaluation is: ; in, For train identification, To launch the plan, for The target value, For trains The total number of stations along the route, For trains The station sign of the route, For trains Capacity, For interval Mileage, is the interval identifier, For trains For the The station area, , For station signs, For trains in the operation plan The first stations, For trains in the operation plan The first stations, train occupancy rate; The constraints for transport efficiency pre-assessment are: capacity allocation constraints, interval throughput constraints, number of trains departing and arriving at stations, basic diagram constraints, departure and arrival time constraints, train capacity constraints, and service frequency constraints. Among them, the capacity allocation constraint is: ;in, For trains The calculation coefficient of kilometers, allocating a capacity cap to the rail network; The interval passing capacity constraint is: ;in, , is the interval set of the railway network, To enter the interval throughout the day The number of trains, For interval The upper limit of the passing capacity; The number of trains originating and terminating at a station is constrained as follows: , ;in, , is the set of stations in the railway network, For trains in the operation plan The first station along the route, For trains in the operation plan The first stations, For the station The starting and ending capacity limit; The basic graph constraints are: ;;in, is the train set of the basic operation diagram, ; The departure and arrival time constraints are: ;in, The starting time of the all-day operation period. The end time of the all-day operation period. , For trains The departure time, For trains In the Arrival time at each station; The train capacity constraints are: ;in, To equip the vehicle model with a fixed number of people, ; The service frequency constraint is: ;in, For the station The lower limit of service frequency, For trains With the station The associated identifier of train At the station Stop ,otherwise .

5. The method according to claim 2, characterized in that like , it is determined that the termination condition is not met; among them, is the preset total number of iterations; like , then update ,renew ;like , then it is determined that the termination condition is not met. If , then it is determined that the termination condition is met; among them, is the temperature drop ratio, is the preset end temperature.

6. The method according to claim 1 or 2, characterized in that The convolutional neural network includes: an input layer, a hidden layer and an output layer; The hidden layer includes: a convolutional layer, a pooling layer and a fully connected layer; There are three convolutional layers, each of which has The convolution kernel of , the activation function is a linear rectification unit; The pooling function of the pooling layer is an average pooling function; The loss function of the convolutional neural network is the mean square error function, and the optimization function is the Adam algorithm.

7. An electronic device, characterized in that: include: Memory; processor; as well as computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that A computer program is stored thereon; the computer program is executed by a processor to implement the method according to any one of claims 1 to 6.

Images