Group plan and train operation plan adjustment optimization method under disturbance condition

Abstract

The invention provides a group plan and train operation plan adjustment method and device under a disturbance condition, equipment and a medium. Relates to the technical field of computer traffic application. Comprising the following steps: constructing the group interval time and the group grouping and group solution time based on a preset heavy haul railway train operation constraint model to obtain a multi-target planning operation diagram adjustment model; carrying out random initialization processing on a genetic population of the multi-objective planning operation diagram adjustment model to obtain a plurality of train group solution group operation plans, then carrying out optimization updating, constructing a non-dominated sorting genetic algorithm with an elitist strategy to carry out optimization iteration on a Pareto optimal solution set, and carrying out optimization iteration on the Pareto optimal solution set; obtaining a group plan and train operation plan adjustment scheme under the optimal disturbance condition; and outputting the group plan and the train operation plan under the optimal disturbance condition according to the group train special operation line to obtain a train operation diagram under the optimal adjustment scheme of the group plan and the train operation plan. According to the method, the problems of low disturbance adjustment speed and long station capacity occupation time of the heavy-load train under the group plan are solved, and the safe and stable operation of the group train is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of computer traffic applications, and more particularly, to a method for adjusting and optimizing group plans and train operation plans under disturbance conditions. Background Art

[0002] In the existing technical field of computer traffic applications, heavy-haul railway trains run at high speeds and high densities, and are easily affected by various internal and external interference factors of the railway system. Under the influence of these factors, heavy-haul railways are highly vulnerable, and it is extremely easy to cause the train operation to deviate from the original operation plan, resulting in disorder of train operation order, decline in equipment capacity, etc. In severe cases, it may even lead to accidents endangering train operation safety, which is not conducive to the train operation organization of heavy-haul trains at stations. Therefore, there is an urgent need for a method for adjusting and optimizing group plans and train operation plans under disturbance conditions to solve the problems of slow disturbance adjustment speed of heavy-haul trains under group plans and long occupation time of station capacity, and to ensure the safety and stability of group train operation. Summary of the Invention

[0003] The purpose of the present invention is to provide a method for adjusting and optimizing group plans and train operation plans under disturbance conditions to improve the above problems. To achieve the above purpose, the technical solutions adopted by the present invention are as follows:

[0004] In a first aspect, the present application provides a method for adjusting and optimizing group plans and train operation plans under disturbance conditions, including:

[0005] Obtain train operation information and dedicated operation lines for group trains, where the train operation information includes group interval time, group formation and dissolution time, etc.;

[0006] Construct the group interval time and the group formation and dissolution time based on a preset heavy-haul railway train operation constraint model to obtain an operation diagram adjustment model for multi-objective programming;

[0007] Randomly initialize the population of the operation diagram compilation model for multi-objective programming to obtain multiple train group formation and dissolution operation models;

[0008] Perform Pareto optimal solution for the multiple train operation adjustment models to obtain a Pareto optimal solution set;

[0009] Based on the Pareto optimal solution set, determine whether to optimize and update the Pareto optimal solution set. When optimizing and updating the Pareto optimal solution set, construct a non-dominated elite strategy genetic algorithm, and optimize and iterate the Pareto optimal solution set based on the non-dominated elite strategy genetic algorithm to obtain an optimal operation adjustment timetable, and lay out the optimal heavy-haul railway group train adjustment operation diagram according to the timetable.

[0010] In a second aspect, the present application further provides an apparatus for adjusting and optimizing a group plan and a train operation plan under disturbance conditions, including:

[0011] An acquisition module for acquiring train operation information and dedicated operation lines for group trains, where the train operation information includes group interval time, group formation and dissolution time, etc.;

[0012] A first construction module for constructing the group interval time and the group formation and dissolution time based on a preset heavy-haul railway train operation constraint model to obtain an operation diagram adjustment model for multi-objective programming;

[0013] A second construction module for randomly initializing the population of the operation diagram compilation model for multi-objective programming to obtain multiple train group formation and dissolution operation models;

[0014] A third construction module for performing Pareto optimal solution on the multiple train operation adjustment models to obtain a Pareto optimal solution set;

[0015] A fourth construction module for determining whether to optimize and update the Pareto optimal solution set based on the Pareto optimal solution set. When optimizing and updating the Pareto optimal solution set, a non-dominated sorting genetic algorithm with an elite strategy is constructed, and the Pareto optimal solution set is optimized and iterated based on the non-dominated elite strategy genetic algorithm to obtain an optimal operation adjustment time table, and an optimal heavy-haul railway group train adjustment operation diagram is drawn according to the time table;

[0016] In a third aspect, the present application further provides an equipment for adjusting and optimizing a group plan and a train operation plan under disturbance conditions, including:

[0017] A memory for storing a computer program;

[0018] A processor for implementing the steps of the method for adjusting the operation diagram of group trains under disturbance conditions when executing the computer program.

[0019] In a fourth aspect, the present application further provides a readable storage medium, on which a computer program is stored, and the computer program realizes the steps of the above-mentioned method for adjusting the operation diagram based on group trains when executed by a processor.

[0020] The beneficial effects of the present invention are:

[0021] The present invention constructs a running diagram compilation model for multi-objective programming by introducing a group heavy-haul railway train operation constraint model and a non-dominated elitist strategy genetic algorithm under disturbance conditions. The group heavy-haul railway train operation constraint model is used to construct the group interval time, the group splitting and merging time, etc., and then the population of the running diagram compilation model for multi-objective programming is initialized. Subsequently, Pareto optimal solution and the non-dominated elitist strategy genetic algorithm are used for optimization to obtain the optimal operation adjustment timetable and draw the adjusted running diagram, thereby obtaining the optimal adjusted operation diagram of the heavy-haul railway group trains under disturbance conditions, solving the problems of slow disturbance adjustment speed and long station capacity occupation time of the heavy-haul trains under the group plan, and ensuring the safety and stability of the group train operation.

[0022] Other features and advantages of the present invention will be described in the following specification. Moreover, some of them will become apparent from the specification or can be understood by implementing the embodiments of the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written specification, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0024] Figure 1 It is a schematic diagram of the operation process of the group trains at the station disclosed in the embodiments of the present invention;

[0025] Figure 2 It is a schematic diagram of the process of the group plan and train operation plan adjustment method under disturbance conditions described in the embodiments of the present invention;

[0026] Figure 3 It is a schematic diagram of chromosome coding described in the embodiments of the present invention; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. Components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the detailed description of the embodiments of the present invention provided in the drawings below is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0028] It should be noted that similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present invention, terms such as "first" and "second" are only used for descriptive distinction and cannot be construed as indicating or implying relative importance.

[0029] Embodiment 1:

[0030] This embodiment provides a method for adjusting and optimizing group plans and train operation plans under disturbance conditions.

[0031] Among them, the group plan is a plan proposed for the grouping and ungrouping stations, group size, unit train group type, parking order of unit trains on arrival and departure lines, and grouping order within group trains through train group operation collaborative control and transportation organization technologies.

[0032] The train operation plan is a detailed plan for aspects such as the time arrangement, route planning, stop arrangements of train operations, and the reasonable allocation of relevant transportation resources.

[0033] Unit train: A general term for the existing heavy-haul train forms in heavy-haul railways.

[0034] Group train: A train formed by virtual connection of two or more unit trains through train group operation collaborative control technology.

[0035] Grouping: The process in which unit trains are virtually connected and combined into group trains through train group operation collaborative control technology at a station and then depart from the station.

[0036] Ungrouping: The process in which a group train is decomposed into unit trains or partial group trains through train group operation collaborative control technology at a station.

[0037] Please refer to Figure 1, the figure shows the processes of grouping and ungrouping. C1, C2, and C3 are three unit trains departing from the same originating station. They are grouped into a group train Q1 at the originating station and then run. Among them, C1 and C2 have the same final destination. When reaching the final destination of C3, C3 ungroups and enters the arrival and departure tracks of the station. The existing train C4 at the station regrouped with C1 and C2 into the group train Q1 and then continues to run.

[0038] See Figure 2 、 Figure 3 , the figure shows that the method includes steps S1 to S7, including:

[0039] S1: Obtain the train operation disturbance situation and get the disturbance adjustment means.

[0040] In this step, when the passing capacity of a certain section of the line fails completely, the real-time adjustment problem of one-way train operation is studied. As Figure 2 shown, at time h1, due to some fault interference, the two main lines of section 3 are completely interrupted. A total of 6 trains, including 2 group trains and 2 unit trains, cannot continue to run according to the scheduled requirements. To ensure the safety of train operation under interference conditions, all 6 trains should stop before entering the interrupted section. Due to the station capacity limit, the number of trains waiting to avoid at each station cannot exceed its capacity. There are only 4 available tracks at Station 2 and Station 3 respectively. The present invention will decide how to arrange the stop plans of trains at Station 2 and Station 3 to ensure safety and minimize train delays. Assume that the interference is restored at time h2. The present invention also needs to decide the departure order and time of the 6 trains to minimize the impact of the interference.

[0041] S2: Based on the preset operation adjustment constraint model for heavy-haul railway trains under the loss of section capacity, construct the group interval time and the group grouping and ungrouping time to obtain an operation diagram adjustment model for multi-objective programming;

[0042] To clarify the specific acquisition method of the operation diagram adjustment model for multi-objective programming, steps S21 to S25 are included in step S2, specifically:

[0043] S21: Obtain the original planned train timetables of all trains;

[0044] S22: Calculate based on the arrival time of the train at the first station and the preset arrival time of the train at the second station to obtain the train running time between sections;

[0045] S23: Take the shortest train delay time and the least number of train grouping and ungrouping times as the objective functions, and construct based on the preset different group train tracking constraints and the preset grouping and ungrouping time constraints to obtain an operation adjustment constraint model for heavy-haul railway trains under the group plan;

[0046] In this step, the formula for the shortest train delay time is as follows:

[0047]

[0048] In the above formula (1): MinZ1 represents the minimum value of the delay time Z1; tr i D j represents the adjusted arrival time of train i at station j; represents the scheduled arrival time of train i at station j, tr i F j represents the adjusted departure time of train i at station j; represents the scheduled departure time of train i at station j.

[0049] The formula for the minimum number of times of splitting and recombining train groups is as follows:

[0050]

[0051] In the above formula (2): MinZ2 represents the minimum value of the number of times of splitting and recombining train groups Z2; is a 0-1 variable, indicating whether trains i and i' perform recombination operation at station j. If yes, it is 1; otherwise, it is 0; —— is a 0-1 variable, indicating whether trains i and i' perform splitting operation at station j. If yes, it is 1; otherwise, it is 0.

[0052] The formula for the tracking constraint of different group trains is as follows:

[0053] In a heavy-haul railway, in an automatic block section, a minimum tracking interval time needs to be satisfied between two trains running in tracking within the section. However, the minimum tracking interval times for tracking trains of different grades are different. For example, there are differences in the minimum tracking interval times for tracking ordinary freight trains and ten-thousand-ton freight trains. This constraint is as follows:

[0054] Within the group:

[0055]

[0056] For trains with a front-back relationship, the minimum tracking interval time between groups also needs to be satisfied, including the tracking intervals between group trains and group trains, group trains and unit trains, and unit trains and unit trains.

[0057]

[0058] In the above formulas (3)-(6): q(u,v) is a 0-1 variable, indicating whether the u-th train and the v-th train are in a front-back relationship of group trains; ω iis a 0-1 variable, indicating whether the i-th train is a unit train in a group train. If it is, it is 1; otherwise, it is 0. represents the minimum interval tracking time between unit trains within a group; represents the minimum interval tracking time between group trains; represents the minimum interval tracking time between a group train and a unit train; represents the minimum interval tracking time between unit trains;

[0059] The formula for the time constraint of the group train grouping is as follows:

[0060]

[0061] In the above formula (7), The above formula (7) represents that after an interval interruption occurs, the group train is allowed to ungroup at the station, and the stop time of the group train must be greater than the ungrouping operation time.

[0062] The formula for the time constraint of the group train ungrouping is as follows:

[0063]

[0064] In the above formula (8), The above formula (8) represents that after an interval interruption occurs, the unit trains staying at the same station can be grouped into a group train, and the stop time of the train must be greater than the grouping operation time.

[0065] In the above formulas (7) and (8): is a 0-1 variable, indicating whether train i stops at station j. Then I com represents the combined grouping time of the group train: I dec represents the ungrouping time of the decomposed group train: T start represents the start time of the perturbation; T end represents the end time of the perturbation;

[0066] The train operation adjustment constraint model under the group plan for a heavy-haul railway also includes: train running time between intervals constraint, departure interval time constraint at stations for trains, arrival interval time constraint at stations for trains, minimum operation time constraint at stations for trains, constraint for overtaking behavior of trains running in the same direction at stations, number constraint of arrival and departure lines at stations, running restriction constraint in the perturbed interval, passing rule constraint, train operation constraint during the skylight time, and train no-stop and train must-stop constraint.

[0067] The station interval time constraints include the consecutive train departure interval time constraints in the same direction, the non-simultaneous arrival and departure interval time constraints of trains in the same direction, the non-simultaneous arrival and departure interval time constraints of trains in the same direction, and the grouping and ungrouping operation constraints are only considered for trains whose planned arrival time is later than the disturbance occurrence time; all trains operate according to the planned train operation diagram before the disturbance.

[0068] S24: Based on the heavy-haul railway train operation constraint model, construct the group interval time, the group grouping and ungrouping time, the train running time between stations, and the train stop time to obtain a train diagram operation adjustment model for multi-objective programming.

[0069] S3: Randomly initialize the population of the multi-objective programming train operation diagram adjustment model to obtain multiple train operation line adjustment model solving algorithms;

[0070] The population consists of multiple individuals, and the train operation line adjustment model consists of a train timetable and the number of grouping and ungrouping times of the train group.

[0071] To clarify the specific acquisition method of the multiple train operation line adjustment solving algorithms, steps S3 includes S31 to S36, specifically:

[0072] S31: Encode the initial operation timetable into a chromosome and input it into the train operation diagram adjustment model. Step S31 includes:

[0073] S311: Obtain the initial operation timetable indicators, including the initial arrival and departure times of trains, the running time between stations of trains, the train operation interval time, etc., as shown in Table 1 and Table 2. Table 1 shows the arrival and departure times of some trains at each station in the initial timetable; Table 2 shows the interval time between trains;

[0074] Table 1

[0075]

[0076] Table 2

[0077] Train tracking interval Time / min In-group unit trains 3 Between-group trains 15 Between group and unit trains 13 Between unit trains 12

[0078] S312: Obtain the initial grouping state of the train. Obtain the grouping scale, the number of grouped trains, the number of ordinary trains, the grouping plan, etc. according to the train number;

[0079] S313: Encode the arrival time, departure time, and ungrouping and grouping status of all ordinary trains and grouped trains in the initial operation timetable into a chromosome:

[0080] R = {R N |t1, t2,..., t M}

[0081] Among them, R represents the set of adjusted operation time of trains, including the arrival time, departure time and ungrouping / grouping status of trains at each station, t1 represents the arrival / departure time and ungrouping / grouping status of trains at the first station, M represents the total number of stations, and N represents the total number of trains.

[0082] S32: Calculate the preset population to obtain random train arrival / departure times and train ungrouping / grouping status;

[0083] In this step, Python introduces random numbers and defines the function "generate random timetable function" to randomly generate train arrival / departure times and ungrouping / grouping status.

[0084] S33: Solve the number of grouped trains, the number of ordinary trains, the number of stations and the random train arrival / departure times in the initial train timetable to obtain the train timetable;

[0085] Specifically, step S33 includes S331 to S335:

[0086] S331: Obtain the train time window;

[0087] S332: Generate the number of grouped trains and the number of ordinary trains to obtain a new grouped and ordinary train timetable;

[0088] S333: Generate the number of stations to obtain the random time of each station;

[0089] S334: Generate the train time window to obtain the time when the train arrives at the station;

[0090] S335: Construct according to the new grouped and ordinary train timetable, the random time of each station, the time when the train arrives at the station and the random train arrival / departure times to obtain the train timetable.

[0091] S34: Judge the train timetable and train grouping status according to the heavy-haul railway train operation adjustment constraint model. When both the train timetable and the train ungrouping / grouping status meet the heavy-haul railway train operation diagram adjustment constraint model, obtain the initial solution;

[0092] In this step, traverse all the constraint conditions through Python code to judge whether the train timetable and train grouping status meet. If any one of the constraint conditions is not met, return "False"; if all the constraint conditions are met, return "True" to obtain an initial feasible solution.

[0093] S35: Based on the obtained initial solution, obtain multiple train operation line adjustment models.

[0094] S4: Perform Pareto optimal solution for the multiple train operation line adjustment models to obtain a Pareto optimal solution set;

[0095] To clarify the specific obtaining method of the Pareto optimal solution set, steps S4 includes S41 to S44, specifically:

[0096] S41: Construct a fitness function according to the objective function, and define the domination relationship of solutions based on the fitness function;

[0097] Specifically, the fitness function is expressed as:

[0098]

[0099] In the above formula (9), f1(x) and f2(x) are both fitness functions, and p1(x), p2(x), p3(x) are the adjustment degree values of the fitness function;

[0100] Specifically, define the domination relationship between solution R and R' as that when and only when any one of the following 2 conditions is satisfied: ① f1(R) < f1(R'); ② f1(R) = f1(R'), f2(R) ≤ f2(R'), then R dominates R';

[0101] S42: Input the non-dominated solutions into the preset Pareto solution set;

[0102] S43: Calculate the chromosomes of the Pareto solution set based on the multiple individuals and the first objective function value of the preset individual to obtain the crowding degree between the chromosome and the adjacent chromosome;

[0103] In this embodiment, since the absolute time difference between genes can directly reflect the difference degree between chromosome individuals under this coding method, the sum of the distances between each chromosome individual and its adjacent individuals is calculated as its crowding degree. At the same time, the distances between the start and end individuals and their adjacent individuals are regarded as infinity to ensure that they have better crowding degrees at the boundaries, and ensure that the adjustment of the train arrival time is always not later than the latest arrival time of the last train.

[0104] For chromosome R N = t1, t2,..., t M , the distance between genes is |t n-n′+1 -t n-n′ |, and the crowding degree is ∞ + |t1 - t2| + |t2 - t3| +... + |t M-M′ -t M | + ∞. The larger the crowding degree value, the higher the density of the position where the individual is located, there are more individuals in the surrounding solution space, and it has higher diversity.

[0105] S5. Optimize the chromosomes using a genetic algorithm based on non-dominated solutions and the crowding degree of adjacent chromosomes;

[0106] Specifically, step S5 includes:

[0107] S51. Calculate the fitness value of each chromosome individual based on the fitness function, and calculate the probability of each chromosome individual being selected from the fitness value:

[0108] Specifically, use the roulette wheel selection method for the selection operation. The probability of each chromosome being selected is

[0109] where popsize represents the population size, and f b (x a ) represents the fitness value of chromosome individual x a ;

[0110] S52. Randomly select two chromosome individuals for crossover operation based on the genetic algorithm, and exchange some gene segments in the chromosomes to generate new chromosome individuals.

[0111] Specifically, set the crossover probability of the chromosome individuals to a fixed value. The fixed crossover probability is Pc;

[0112] In this embodiment, crossover operation is performed based on the chromosome individuals to generate new individuals. Since there is a correlation between the arrival and departure times of each station of the group train and the ordinary train in the train operation timetable, step S52 uses partial mapping for the crossover operation;

[0113] S53. Based on the new chromosomes, traverse the crossover segments of the two new chromosomes, find the duplicate values in the crossover segments compared with the original chromosomes, and replace them;

[0114] S54. Randomly select genes in two new chromosome individuals for mutation operation, and exchange some gene segments in the chromosomes to generate new chromosome individuals. Set the mutation probability of the chromosome individuals to a fixed value. The fixed mutation probability is Pm;

[0115] In this embodiment, gene mutation specifically means increasing or decreasing the arrival and departure times of the ordinary train and the group train by a certain number of minutes;

[0116] S6: Generate a new population based on the elitist strategy through the above crossover and mutation operations;

[0117] Specifically, step S6 includes:

[0118] S61: Connect the parent and offspring populations into a larger candidate population;

[0119] S62: Perform non-dominated sorting based on the fitness function and crowding distance;

[0120] S63: After performing fast non-dominated sorting, select the same number of individuals as the number of individuals in the initial population to enter the new population;

[0121] Connecting the initial population and the newly generated population into a larger population is a strategy to implement elitism in the fast non-dominated sorting algorithm. Through connection, it helps to retain the optimal solution and maintain the diversity of the population;

[0122] S7. Based on the preset dispersion degree E ξ and the preset maximum number of iterations to determine whether the chromosome is the optimal solution;

[0123] In this embodiment, calculate the dispersion degree E and the number of iterations gen of the candidate population. When E is less than E ξ or the number of iterations gen reaches the maximum number of iterations maxgen, then decode the optimized chromosome to obtain the optimal train operation adjustment plan; otherwise, increment the number of iterations by one, and loop through steps S4 - S7.

[0124] In this embodiment, it is assumed that the section from Longgong to Beidaniu is interrupted for 60 minutes at 1:30. Part of the train timetable of the optimal group plan is shown in Table 3:

[0125] Table 3

[0126]

[0127] Based on this embodiment, it can be seen that the total train delay time is 2629 minutes, and the number of group formation and dissolution is both 2. Train 10003 is the first affected train, and two group trains are disturbed. Therefore, to meet the train tracking time, the delay time of 10003 is long. The group train composed of 20007 and 2000 is dissolved at Station 3 and stops on the arrival and departure track. After the fault ends, it continues to run in a group. Due to the limitation of the number of arrival and departure tracks, the group train composed of 20009 and 20011 is selected to be detained on the arrival and departure track of Station 2. Train 10005 is affected by the change of the group plan and stops at Station 2.

Claims

1. A method for adjusting and optimizing group plan and train operation plan under disturbance conditions, characterized in that: include: Acquire train operation information and group train dedicated operation lines, wherein the train operation information includes group interval time and group train grouping and disassembly time, etc.; The group interval time and the group train group solution are constructed based on a preset heavy-haul railway train operation constraint model to obtain a multi-objective planning train operation diagram adjustment model; Performing random initialization processing on the genetic population of the operation diagram adjustment model of the multi-objective programming to obtain multiple train group solution operation plans; Performing Pareto optimal solutions on the multiple train operation adjustment schemes to obtain a Pareto optimal solution set; For the Pareto optimal solution set, determine whether to optimize and update the Pareto solution set. When updating the Pareto solution set, establish a non-dominated sorting genetic algorithm with an elite strategy to optimize and iterate the Pareto optimal solution set until the iteration termination condition is met, and obtain the optimal group plan and train operation plan adjustment plan under the disturbance condition. According to the method of laying out the special running line for group trains, the group plan and the train running plan under the optimal disturbance conditions are output, and the train running diagram under the optimal adjustment scheme of the group plan and the train running plan is obtained.

2. The method for adjusting and optimizing group plan and train operation plan under disturbance conditions according to claim 1 is characterized in that the group interval and the group train grouping and ungrouping time are constructed based on a preset heavy-haul railway train operation constraint model to obtain a multi-objective planning operation diagram adjustment model, including: Get the original planned train schedule for all trains; Calculating based on the arrival time of the train at the first station and the preset arrival time of the train at the second station to obtain the train section running time; Taking the shortest train delay time and the least number of train group ungrouping as the objective function, a model of heavy-duty railway group planning and train operation plan adjustment constraint model under interference conditions is constructed based on the preset different group train tracking interval constraints and the preset group ungrouping time constraints. Based on the heavy-duty railway group plan and train operation plan adjustment constraint model under the interference conditions, the group interval time, the group group ungrouping time, the train section running time, the train group ungrouping times and the train delay time are constructed to obtain a multi-objective planning train operation diagram adjustment model.

3. The method for adjusting and optimizing group plans and train operation plans under disturbance conditions according to claim 2 is characterized in that the genetic population of the multi-objective train operation diagram adjustment model is randomly initialized to obtain an adjustment plan for the operation line of the disturbed train, and the genetic population is composed of multiple chromosomes, including: Encoding the initial operation schedule into chromosomes and inputting the chromosomes into the train operation diagram adjustment model; Calculate the preset population to obtain random train arrival and departure times and train disbanding population status; Solving the number of group trains in the initial train schedule, the number of ordinary trains in the initial train schedule, the number of stations and the random train arrival and departure times to obtain a train schedule; Solving the number of group trains in the train timetable, the number of ordinary trains in the train timetable, and the number of stations to obtain the train degrouping group state; The train schedule and train group status are judged according to the heavy-haul railway train operation adjustment constraint model, and when the train schedule and train group status both satisfy the heavy-haul railway train operation diagram adjustment constraint model, an initial solution is obtained; Based on the initial solution, a running line adjustment model of the disturbed train is obtained.

4. The method for adjusting and optimizing group plan and train operation plan under disturbance conditions according to claim 3 is characterized in that, based on the non-dominated solution and the congestion degree of adjacent chromosomes, a genetic algorithm is used to optimize the chromosomes, including: Calculating the fitness value of the chromosome individual based on the fitness function, and calculating the probability of the chromosome individual being selected according to the fitness value; Based on the genetic algorithm, two chromosome individuals are randomly selected for crossover operation, and some gene fragments in the chromosomes are exchanged to generate new chromosome individuals; Based on the new chromosome, traverse the intersection segments of the two new chromosomes, find the duplicate values ​​in the intersection segment and the original chromosome and replace them; The genes in two new chromosome individuals are randomly selected for mutation operation, and some gene fragments in the chromosomes are exchanged to generate new chromosome individuals. The mutation probability of the chromosome individuals is set to a fixed value, and the fixed crossover probability is Pm.

5. The method for adjusting and optimizing group plan and train operation plan under disturbance conditions according to claim 4 is characterized in that, through the crossover and mutation operations, a new population is generated based on an elite strategy, including: connecting the parent and offspring populations into a larger candidate population; Performing non-dominated sorting based on the fitness function and the crowding distance; After performing a fast non-dominated sort, select a number of individuals that is consistent with the number of individuals in the initial population to enter the new population; The discrete degree and the number of iterations of the candidate population are calculated to determine whether the discrete degree or the number of iterations meets the preset discrete degree or the number of iterations. If not, the iteration is continued. If the preset discrete degree or the number of iterations is met, the iteration is terminated, and the optimal train operation adjustment plan is obtained after decoding the optimized chromosome.

6. The method for adjusting and optimizing the group plan and train operation plan under disturbance conditions according to claim 1 is characterized in that the optimal train schedule is output according to the group train dedicated operation line to obtain a heavy-duty railway train operation diagram under disturbance conditions, including: Obtaining the departure time of a group train, wherein the departure time of the group train includes the departure time of the first train and the departure time of the last train of the group; Calculate according to the group interval time, the group train grouping and ungrouping plan, the preset train grouping and ungrouping station, and the preset group train grouping and ungrouping time to obtain the grouping and ungrouping and operation plan of the train; The train is scheduled according to a preset train schedule model to obtain an updated train schedule; According to the departure time of the first train of the group, the departure time of the last train of the group, and the group interval time, a dedicated running line for group trains is obtained; The optimal group plan and train schedule and the updated train number are solved again according to the preset group train dedicated running line to obtain the running diagram of the train adjustment under the optimal disturbance condition.

7. A device for adjusting and optimizing group plan and train operation plan under disturbance conditions, comprising: An acquisition module is used to acquire train operation information and group train dedicated operation lines, wherein the train operation information includes group interval time and group grouping and grouping release time, etc.; A first construction module is used to construct the group interval time and the group grouping and grouping time based on a preset heavy-haul railway train operation constraint model to obtain a multi-objective planning operation diagram adjustment model; The second construction module randomly initializes the initial population of the multi-objective planning operation diagram compilation model to obtain a train group solution operation model; A third building module is used to perform Pareto optimal solutions on the multiple train operation adjustment models to obtain a Pareto optimal solution set; The fourth construction module is used to determine whether to optimize and update the Pareto optimal solution set based on the Pareto optimal solution set. When optimizing and updating the Pareto optimal solution set, a non-dominated sorting genetic algorithm with an elite strategy is constructed. The Pareto optimal solution set is optimized and iterated based on the non-dominated sorting genetic algorithm with an elite strategy to obtain an optimal operation adjustment timetable, and an optimal heavy-load railway group train adjustment operation diagram is obtained according to the timetable.

8. The group plan and train operation plan adjustment and optimization device under disturbance conditions is characterized by: include: Memory for storing computer programs; A processor is used to implement the steps of the method for adjusting the operation diagram of the group train under the disturbance condition when executing the computer program.

9. A readable storage medium, characterized in that: a computer program is stored on the readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned operation diagram adjustment method based on group trains are implemented.

Images