A train operation timetable optimization method, device, equipment and medium

Abstract

The application discloses a train operation timetable optimization method and device, equipment and medium, and relates to the technical field of train operation control. The method comprises the following steps: acquiring a current operation timetable of a maglev train, and generating an initial population comprising a plurality of individuals by using a genetic algorithm based on the current operation timetable; each individual is a timetable adjustment amount generated within a preset reasonable range; the fitness value of each individual is calculated based on the timetable adjustment amount corresponding to each individual and by using a target function; the fitness value represents the total energy consumption of the maglev train under the corresponding candidate operation timetable; the individuals in the current population are subjected to genetic operation according to the fitness value, and a new generation population is generated; for the new generation population, the step of calculating the fitness value of each individual based on the timetable adjustment amount corresponding to each individual and by using the target function is restarted until a preset termination condition is met, and the current operation timetable is optimized based on the individual with the optimal fitness value in the final population.

Description

Technical Field

[0001] This invention relates to the field of train operation control technology, and in particular to a method, apparatus, equipment and medium for optimizing train timetables. Background Technology

[0002] With the rapid development of urban rail transit and high-speed maglev trains, traction energy consumption during train operation has become a significant factor affecting operating costs and green, low-carbon development. How to reduce total system energy consumption while ensuring operational safety, punctuality, and service levels has become a key research focus in the rail transit operation field. Compared to traditional wheel-rail trains that rely on mechanical friction transmission, maglev trains rely on electromagnetic drive systems to simultaneously handle train propulsion and levitation maintenance. Their energy requirements exhibit significantly different characteristics, with traction energy consumption accounting for a higher proportion, approximately 50% to 60% of the total system energy consumption. Therefore, effectively reducing the energy consumption of maglev trains is of great significance for reducing system operating costs, improving energy efficiency, and promoting the green and low-carbon development of rail transit.

[0003] When a train brakes, it generates regenerative braking energy. This energy is prioritized for supplying the train's own auxiliary systems, with the remainder fed back to the power grid and used by trains accelerating within the same power supply area, thereby reducing the external power supply demand of the traction substation. However, existing train timetables mostly focus on punctuality and transport capacity, lacking consideration for the spatiotemporal complementarity of regenerative braking energy between trains. This results in regenerative energy generated by a braking train not being fully absorbed by a train accelerating. A large amount of regenerative energy is wasted as heat through energy-consuming resistors, leading to uneven energy distribution and high total energy consumption of the substation.

[0004] In summary, how to adjust train timetables to maximize the spatiotemporal matching of regenerative braking energy and reduce the total energy consumption of the system is a problem that needs to be solved. Summary of the Invention

[0005] In view of this, the purpose of this invention is to provide a train timetable optimization method, apparatus, device, and medium, capable of adjusting train timetables to maximize the spatiotemporal matching utilization of regenerative braking energy and reduce the total system energy consumption. The specific solution is as follows: Firstly, this application discloses a method for optimizing train timetables, including: Obtain the current operating timetable of the maglev train, and based on the current operating timetable, use a genetic algorithm to generate an initial population including multiple individuals; wherein each individual is a timetable adjustment amount generated within a preset reasonable range; The fitness value of each individual is calculated based on the timetable adjustment amount corresponding to each individual and using an objective function; the fitness value is used to characterize the total energy consumption of the maglev train. Genetic operations are performed on individuals in the current population based on the fitness values ​​to generate a new generation of the population. For the new generation population, the process jumps back to the step of adjusting the timetable based on each individual and calculating the fitness value of each individual using the objective function, until the preset termination condition is met. Then, the current running timetable is optimized based on the individual with the best fitness value in the final population to obtain the optimized running timetable.

[0006] Optionally, the timetable adjustment includes peak-hour departure interval adjustment and off-peak-hour departure interval adjustment; Accordingly, the generation of an initial population comprising multiple individuals using a genetic algorithm includes: Based on the existing departure intervals in the current operating timetable; Within a pre-defined reasonable range, multiple sets of gene sequences consisting of peak-hour departure interval adjustments and off-peak departure interval adjustments are randomly generated to serve as multiple individuals in the initial population.

[0007] Optionally, the step of adjusting the timetable for each individual and calculating the fitness value for each individual using the objective function includes: Based on the timetable adjustment amount corresponding to each individual, a corresponding candidate operating timetable is generated, and the train operation process is simulated based on the candidate operating timetable to obtain the operating energy consumption simulation results. Based on the simulation results of the operating energy consumption, the fitness value of each individual is calculated using the objective function; Accordingly, the optimization of the current running timetable based on the individual with the best fitness value in the final population to obtain an optimized running timetable includes: The candidate running timetable corresponding to the individual with the best fitness value in the final population is used as the optimized running timetable.

[0008] Optionally, generating a corresponding candidate running timetable based on the timetable adjustment amount for each individual includes: Obtain the driving pattern data corresponding to the current operating timetable; the driving pattern data includes at least the number of trips, peak period division, and off-peak period division; For each individual, based on the train operation data and according to the peak-hour departure interval adjustment amount and off-peak-hour departure interval adjustment amount corresponding to each individual, the departure time of each maglev train is determined sequentially during the corresponding peak and off-peak periods. Based on the determined departure time and the inter-station travel time, the arrival and departure times of each maglev train at each station are determined, and a candidate timetable for each individual is obtained.

[0009] Optionally, the step of simulating train operation based on the candidate timetable to obtain simulation results of operating energy consumption includes: The candidate runtime schedule is input into a pre-built simulator; The simulator is used to simulate the train operation process based on the candidate timetable to obtain simulation results of operating energy consumption, including operating status, train traction energy consumption, substation energy consumption, regenerative braking energy utilization, and transmission line losses.

[0010] Optionally, the objective function includes a first objective function and a second objective function; the first objective function is constructed based on the total energy consumption of each traction substation, and the second objective function is constructed based on the total energy consumption of each traction substation and a preset penalty coefficient. Accordingly, the step of calculating the fitness value of each individual based on the simulation results of the operating energy consumption and using the objective function includes: For the current individual, obtain the train running time under the corresponding candidate timetable, and determine whether the train running time is within the preset running time constraint range; If the train running time is within the running time constraint range, then the fitness value of the current individual is calculated based on the running energy consumption simulation results and using the first objective function; If the train running time is not within the running time constraint range, the fitness value of the current individual is calculated based on the running energy consumption simulation results and using the second objective function.

[0011] Optionally, the substation energy consumption of the traction substation is determined based on a preset train operation energy consumption model; wherein, the train operation energy consumption model is constructed based on train traction energy consumption, regenerative braking energy, and transmission line losses.

[0012] Optionally, the calculation process for the substation energy consumption of the traction substation includes: The train's traction energy consumption is determined by multiplying the maximum traction force of the maglev train at the current speed by the current speed. The regenerative braking energy feedback is determined based on the product of regenerative braking efficiency, train current, and train voltage. The difference between the train traction energy consumption and the regenerative braking feedback energy is determined, and the substation energy consumption of the traction substation is determined based on the sum of the difference result and the transmission line loss.

[0013] Optionally, the train travel time is determined based on the sum of the inter-station travel time of each maglev train at each station and the train travel interval.

[0014] Optionally, the genetic operations include selection, crossover, and mutation.

[0015] Optionally, the step of performing genetic operations on individuals in the current population based on the fitness value to generate a new generation population includes: Sort the individuals in the current population according to the fitness values; Based on the sorting results, a selection operation is performed on the individuals in the current population, and a crossover operation is performed on the selected individuals according to a preset crossover ratio, and a mutation operation is performed according to a preset mutation ratio, so as to generate a new generation population with the same number of individuals as the current population.

[0016] Optionally, the preset termination condition includes at least one of the following conditions: The difference in optimal fitness values ​​between two adjacent generations is less than a preset convergence threshold; The optimal fitness value of the population remains stagnant for more than the preset stagnation generation threshold. The total number of iterations in the population reaches the preset maximum number of generations.

[0017] Secondly, this application discloses a train timetable optimization device, comprising: The population initialization module is used to obtain the current operating timetable of the maglev train and, based on the current operating timetable, use a genetic algorithm to generate an initial population including multiple individuals; wherein, each individual is a timetable adjustment amount generated within a preset reasonable range; The calculation module is used to calculate the fitness value of each individual based on the timetable adjustment amount corresponding to each individual and using the objective function; the fitness value is used to characterize the total energy consumption of the maglev train. The genetic operation module is used to perform genetic operations on individuals in the current population based on the fitness value to generate a new generation of population. The iterative optimization module is used to jump back to the step of adjusting the timetable based on the timetable for each individual and calculating the fitness value of each individual using the objective function for the new generation population, until the preset termination condition is met, and optimize the current running timetable based on the individual with the best fitness value in the final population to obtain the optimized running timetable.

[0018] Thirdly, this application discloses an electronic device, including: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of the aforementioned train timetable optimization method.

[0019] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the aforementioned train timetable optimization method.

[0020] As can be seen, this application obtains the current operating timetable of the maglev train and, based on the current operating timetable, uses a genetic algorithm to generate an initial population including multiple individuals; wherein each individual is a timetable adjustment amount generated within a preset reasonable range; the fitness value of each individual is calculated based on the timetable adjustment amount corresponding to each individual and using an objective function; the fitness value is used to characterize the total energy consumption of the maglev train; genetic operations are performed on the individuals in the current population according to the fitness value to generate a new generation population; for the new generation population, the process jumps back to the step of calculating the fitness value of each individual based on the timetable adjustment amount corresponding to each individual and using an objective function, until a preset termination condition is met, and the current operating timetable is optimized based on the individual with the best fitness value in the final population to obtain an optimized operating timetable.

[0021] Beneficial Effects: This application obtains the current train timetable and generates multiple individuals in the initial population based on timetable adjustments within a preset reasonable range. It calculates the total energy consumption of each individual under the corresponding timetable adjustment using an objective function as its fitness value. Furthermore, it iteratively optimizes the population using genetic operations such as selection, crossover, and mutation until a preset termination condition is met. The current timetable is then optimized based on the individual with the optimal fitness value. This transforms the energy consumption optimization problem of the train timetable into a global optimization problem with total energy consumption as the optimization objective. It can efficiently perform global searches under multi-variable and multi-constraint conditions without relying on complex and precise mathematical modeling. It fully leverages the complementary characteristics of regenerative braking energy between trains in time and space, effectively reducing the total energy consumption of train operation while ensuring constraints such as train running time, thereby improving the energy utilization efficiency and green, low-carbon operation level of the rail transit system. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0023] Figure 1 This is a flowchart of a train timetable optimization method disclosed in this application; Figure 2This application discloses a specific method for optimizing train timetables. Figure 3 Here is a flowchart of a timetable optimization genetic algorithm disclosed in this application; Figure 4 This is a schematic diagram illustrating the principle of a train timetable optimization method disclosed in this application; Figure 5 This is a schematic diagram of a train timetable optimization device disclosed in this application; Figure 6 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0025] When a train brakes, it generates regenerative braking energy. This energy can be prioritized for the train's own auxiliary systems, with the remainder fed back to the power grid and used by trains accelerating within the same power supply area, thereby reducing the external power supply demand of the traction substation. However, existing train timetables mostly focus on punctuality and transport capacity, lacking consideration for the spatiotemporal complementarity of regenerative braking energy between trains. This results in regenerative energy generated by a braking train being difficult for a train accelerating to fully absorb, with a large amount of regenerative energy being wasted as heat through energy-consuming resistors, leading to uneven energy distribution and high total energy consumption of the substation. To address this, this application discloses a train timetable optimization method, apparatus, equipment, and medium that can adjust the train timetable to maximize the spatiotemporal matching utilization of regenerative braking energy and reduce the total system energy consumption.

[0026] See Figure 1 As shown in the figure, this application discloses a train timetable optimization method, which includes: Step S11: Obtain the current operating timetable of the maglev train, and based on the current operating timetable, use a genetic algorithm to generate an initial population including multiple individuals; wherein each individual is a timetable adjustment amount generated within a preset reasonable range.

[0027] First, it should be noted that the maglev train in this embodiment can specifically be a high-speed maglev train. A high-speed maglev train refers to a maglev rail transit system with a maximum operating speed of not less than 400 km / h. It relies on electromagnetic force to achieve levitation, guidance, and propulsion. Compared with traditional wheel-rail trains, high-speed maglev trains have the following significant characteristics: there is no mechanical contact between the train and the track; the running resistance is mainly air resistance; energy consumption increases non-linearly with increasing speed; the train has high traction power, with a single train's traction power reaching several megawatts; and the train generates high regenerative braking energy during braking, resulting in a large instantaneous power feedback to the traction power grid. These characteristics make the traction energy consumption of high-speed maglev trains significantly higher than that of traditional wheel-rail trains, accounting for approximately 50%-60% of the total operating cost. Optimizing its timetable is crucial for reducing system energy consumption. Furthermore, high-speed maglev trains operate at high speeds and have large station spacing, resulting in a large number of trains operating simultaneously within the same power supply section. This provides significant potential for spatiotemporal matching and utilization of regenerative braking energy between trains, and more space for energy complementarity through optimized departure intervals. Therefore, this application is particularly applicable to energy-saving optimization of the timetable for high-speed maglev trains.

[0028] The current operating timetable can be the actual planned operating timetable currently being run by the maglev train. Specifically, it can include station names along the line, planned arrival and departure times for each maglev train at each station, and train distribution information for each time period throughout the day. Simultaneously, data on the expected train operation patterns that the current timetable should achieve can also be obtained, such as the total number of trains per day, the expected peak-hour departure intervals, and the expected off-peak-hour departure intervals. This data can then be used as a basis for generating candidate operating timetables during the subsequent optimization process.

[0029] Specifically, the timetable adjustment includes peak-hour departure interval adjustment and off-peak departure interval adjustment; correspondingly, the generation of an initial population consisting of multiple individuals using a genetic algorithm includes: using the existing departure interval in the current operating timetable as a benchmark; randomly generating multiple sets of gene sequences composed of peak-hour departure interval adjustment and off-peak departure interval adjustment within a preset reasonable range, as multiple individuals in the initial population.

[0030] It is understandable that peak and off-peak periods are pre-defined based on passenger flow characteristics of train routes, such as morning peak hours (e.g., 7:00-9:00), evening peak hours (e.g., 17:00-19:00), and other off-peak periods. In this embodiment, each feasible solution (also referred to as an individual or gene sequence) consists of a set of peak-hour departure interval adjustments and off-peak-hour departure interval adjustments, and a single time variable within each feasible solution is called a gene. That is, the departure interval adjustments corresponding to the arrival and departure times of trains at each station are encoded as gene sequences, thereby constructing the solution space of the genetic algorithm. During initialization, for example, 50 feasible solutions can be generated in the first generation, meaning each generation of the population can contain 50 sets of feasible solutions; each set of feasible solutions includes peak-hour and off-peak departure interval adjustments randomly generated within a reasonable range. For example, peak-hour departure interval adjustments can be randomly generated within a preset operational constraint range, and off-peak departure interval adjustments can also be randomly generated within the corresponding operational constraint range. It is understandable that the population size can also be flexibly set to other values ​​according to the actual situation such as the line size, the number of variables and computing resources. This embodiment does not make specific limitations on this.

[0031] Furthermore, the preset reasonable range can be set according to operational needs and passenger flow organization requirements. In one specific implementation, the adjustment range of the departure interval can be limited to within ±10 seconds, that is, the adjustment amount of the departure interval during peak hours and off-peak hours will not exceed 10 seconds. For example, if the current morning peak departure interval is 330 seconds, the adjusted morning peak departure interval can be randomly selected between 320 seconds and 340 seconds; if the current off-peak departure interval is 418 seconds, the adjusted off-peak departure interval can be randomly selected between 408 seconds and 428 seconds. In this way, because the adjustment range is small, the optimized timetable will not affect passenger travel plans and passenger flow organization, ensuring the stability of the timetable and the level of passenger service.

[0032] Furthermore, the initial population generation process also includes generating multiple gene sequences while keeping the total operating time and total number of trains constant. That is, although the departure intervals at different times are adjusted, the total operating time and total number of trains throughout the day remain unchanged to ensure that the optimized timetable does not affect the feasibility of the operational plan. It is understood that the timetable optimization in this embodiment, based on a given inter-station operating time constraint, achieves a balance between optimal regenerative braking energy and train operation strategy by optimizing peak-hour and off-peak departure intervals. This application, by adjusting peak-hour and off-peak departure intervals, rationally configures the train operation sequence, enabling the regenerative braking energy generated by trains in braking state to match, as much as possible, in time and space with that of trains in acceleration state. The regenerative braking energy generated by braking trains is preferentially supplied to the train's own air conditioning, lighting, and other auxiliary systems; the remaining portion is fed back to the power grid and supplied to trains in acceleration state within the same power supply area for absorption and utilization. If there is still energy remaining and the power grid is equipped with an energy storage device, the remaining energy is stored in the energy storage device; otherwise, the remaining energy will be converted into heat energy and lost through energy-consuming devices such as high-resistance resistors. Therefore, by optimizing the timetable to improve the utilization rate of regenerative braking energy, the external power supply demand of the traction substation can be effectively reduced, thereby minimizing the overall energy consumption.

[0033] It should be noted that, in order to calculate the optimal timetable more quickly and accurately, comparative experiments can be conducted on heuristic algorithms such as genetic algorithms and particle swarm optimization, as well as numerical algorithms such as brute-force search, when determining the optimization algorithm. After comparing the experimental results, this application ultimately adopts the genetic algorithm. The genetic algorithm is an optimization algorithm based on swarm intelligence theory. It is a stochastic global search computational model developed based on the mechanism of biological evolution in nature. It searches for the optimal solution by simulating the natural evolution process. It has advantages such as good versatility, ease of implementation, and fast convergence speed. Moreover, it does not rely on a complex mathematical modeling process and has good global search capability and multi-objective optimization capability. It is particularly suitable for the multi-variable, multi-constraint timetable optimization problem addressed in this application.

[0034] Step S12: Based on the timetable adjustment amount corresponding to each individual, calculate the fitness value of each individual using the objective function; the fitness value is used to characterize the total energy consumption of the maglev train.

[0035] In this embodiment, the total energy consumption of each entity under the corresponding timetable adjustment is calculated using an objective function as its fitness value. Specifically, the step of calculating the fitness value of each entity based on the timetable adjustment for each entity using an objective function includes: generating a corresponding candidate operating timetable based on the timetable adjustment for each entity, and performing train operation simulation based on the candidate operating timetable to obtain the operating energy consumption simulation results; and calculating the fitness value of each entity based on the operating energy consumption simulation results using an objective function. That is, the algorithm calculates the corresponding full-day timetable as a candidate operating timetable for each feasible solution, and then uses simulation to evaluate the train operation process under the candidate operating timetable, thereby obtaining the fitness value corresponding to each feasible solution, i.e., the calculation result of the objective function, thus realizing a comprehensive evaluation of each feasible solution from the aspects of energy consumption and time.

[0036] The step of generating a corresponding candidate timetable based on the timetable adjustment amount for each individual includes: acquiring the train operation pattern data corresponding to the current timetable; the train operation pattern data includes at least the number of trains, peak period division, and off-peak period division; for each individual, based on the train operation pattern data and according to the peak period departure interval adjustment amount and off-peak period departure interval adjustment amount corresponding to each individual, determining the departure time of each maglev train in the corresponding peak period and off-peak period in sequence; based on the determined departure time and combined with the inter-station travel time, determining the arrival time and departure time of each maglev train at each station, and obtaining the candidate timetable corresponding to each individual.

[0037] Specifically, the train operation data can include the total number of trains per day, the division of peak and off-peak periods (e.g., morning peak, evening peak, and start and end times of each off-peak period). For each individual in the population, the peak-hour departure interval adjustment corresponding to that individual is first superimposed on the existing peak-hour departure interval baseline to obtain the adjusted peak-hour departure interval; similarly, the off-peak departure interval adjustment is superimposed on the existing off-peak departure interval baseline to obtain the adjusted off-peak departure interval. Then, within the corresponding peak and off-peak periods, the departure times of each train are arranged sequentially from the first train according to the adjusted departure interval. Finally, starting from the departure times of each train, and combining the given inter-station travel time and stop time, the arrival and departure times of each maglev train at each station are recursively obtained, thereby generating the candidate timetable for the entire day for that individual. It can be seen that the generation process of this candidate timetable does not change the total travel time, stop time, or turnaround time of the trains; it only adjusts the departure intervals during peak and off-peak periods.

[0038] Furthermore, the step of simulating train operation based on the candidate timetable to obtain simulation results of operating energy consumption includes: inputting the candidate timetable into a pre-built simulator; and using the simulator to simulate train operation based on the candidate timetable to obtain simulation results of operating energy consumption including operating status, train traction energy consumption, substation energy consumption, regenerative braking energy utilization, and transmission line losses.

[0039] It should be noted that the simulator is a pre-established tool for simulating train operation. Its input is a candidate timetable, and its output is various energy consumption indicators of the train under that timetable. Specifically, based on basic data such as the maglev line structure, station distribution, speed-limited sections, and train traction / braking performance parameters, the simulator simulates the operation of each train throughout the day and at various times. It calculates the speed trajectory, traction / braking force changes, instantaneous power, and other operating status information of each train between stations, and accordingly calculates energy consumption indicators such as train traction energy consumption, substation energy consumption, regenerative braking energy utilization, and transmission line losses. The simulator's input data includes the candidate timetable, such as station names, planned arrival times, and planned departure times; it also includes the expected train operation patterns, such as the number of trains, the expected peak-hour departure intervals, and the expected off-peak-hour departure intervals; in addition, the simulation process also requires operating parameters such as train current, train voltage, regenerative braking efficiency, and line speed limits.

[0040] Furthermore, it should be further explained that the objective function includes a first objective function and a second objective function; the first objective function is constructed based on the sum of the substation energy consumption of each traction substation, and the second objective function is constructed based on the sum of the substation energy consumption of each traction substation and a preset penalty coefficient; correspondingly, the step of calculating the fitness value of each individual based on the operational energy consumption simulation results and using the objective function includes: for the current individual, obtaining the train running time under the corresponding candidate timetable, and determining whether the train running time is within a preset running time constraint range; if the train running time is within the running time constraint range, then calculating the fitness value of the current individual based on the operational energy consumption simulation results and using the first objective function; if the train running time is not within the running time constraint range, then calculating the fitness value of the current individual based on the operational energy consumption simulation results and using the second objective function.

[0041] In other words, this application checks whether the train running time meets the given inter-station running time constraint while calculating the fitness value. If the running time exceeds the allowable range, a penalty term is added to the objective function, thereby constructing a multi-objective fitness function that includes constraints on the number of trains, operating energy consumption, and train interval safety. Specifically, the expression of the objective function is as follows: ; in, .

[0042] In the formula, M opt This represents the value of the objective function, i.e., the fitness value of an individual; p is the number of traction substations; E sub E represents the substation energy consumption of the traction substation. sub,i T represents the substation energy consumption of the i-th traction substation; run It refers to the train travel time; T lb This is the lower limit of train running time; T ub This is the upper limit of train running time; D run It is a penalty coefficient based on the specified train running time constraint, D run,i This represents the penalty term corresponding to the i-th traction substation; u re Indicates regenerative braking state; I t It is the train current; V t It is the train voltage; f re It is the regenerative braking efficiency; f[v(t)] is the maximum traction force of the train at the current speed v(t); E loss is the transmission line loss; n is the number of trains.

[0043] From the above expression, it can be seen that when the train running time Trun is within the running time constraint range [T lb T ub Within this timeframe, the first objective function is adopted, namely, the substation energy consumption E of each traction substation. sub,i The sum of these values ​​is used as the fitness value for that individual; when the train running time Trun is not within the running time constraint range [T lb T ub When the energy consumption of each traction substation is within a certain range, a second objective function is adopted, which is to superimpose a pre-set penalty coefficient D onto the total energy consumption of each traction substation. run The constructed penalty term significantly degrades the fitness value of individuals that violate the running time constraint, thereby gradually eliminating them during the iterative optimization process and ensuring that the final output optimized timetable meets the basic requirements of train operation safety, punctuality rate and timetable stability.

[0044] Furthermore, the substation energy consumption of the traction substation is determined based on a preset train operation energy consumption model; wherein, the train operation energy consumption model is constructed based on train traction energy consumption, regenerative braking energy, and transmission line losses. In this embodiment, a train operation energy consumption model can be pre-established based on train traction energy consumption, regenerative braking energy, and transmission line losses to calculate the substation energy consumption of each traction substation. The train operation energy consumption model is the aforementioned E sub .

[0045] Specifically, the calculation process for the substation energy consumption of the traction substation includes: determining the train traction energy consumption based on the product of the maximum traction force of the maglev train at the current speed and the current speed; determining the regenerative braking feedback energy based on the product of the regenerative braking utilization efficiency, the train current, and the train voltage; determining the difference between the train traction energy consumption and the regenerative braking feedback energy; and determining the substation energy consumption of the traction substation based on the sum of the difference result and the transmission line loss.

[0046] That is, such as E sub As shown in the expression, the first term on the right side of the equation is the integral of the product of the maximum traction force f[v(t)] at the current speed v(t) and the current speed v(t) over the train's running time, representing the train's traction energy consumption; the second term is the regenerative braking state u. re Regenerative braking efficiency f re With train current I t (t), Train voltage V t (t) The product of the integral results represents the regenerative braking feedback energy. When the train is in regenerative braking state, the product of the train current and the train voltage is the instantaneous regenerative braking power, which is then multiplied by the regenerative braking utilization efficiency f. re This yields the actual regenerative braking feedback power that can be recycled; the third term E los s represents transmission line losses. Subtracting the regenerative braking energy from the train traction energy consumption and adding the transmission line losses yields the substation energy consumption E of the traction substation. sub .

[0047] It should be noted that the train travel time is determined based on the sum of the inter-station travel time of each maglev train and the train interval. The inter-station travel time refers to the time it takes for a train to travel from one station to the next, and the train interval, or departure interval, represents the time difference between the departures of two adjacent trains at the same station.

[0048] That is, the constraints of the above objective function are: ; ; ; In the formula, m represents the number of trains operating between stations, and n represents the number of trains; T run,i T represents the train's travel time between stations. run,s ΔT represents the current train travel time between stations. run,i This refers to the fluctuation range of train travel time between stations; ST run,i For train intervals; ST run,s For existing train intervals; ΔST run,iThis refers to the floating range of train intervals.

[0049] It can be seen that the train travel time T run The inter-station travel time T of n maglev trains on the operating section between m stations run,i With train interval ST run,i The sum is determined; the train travel time between stations T run,i Based on the existing train travel time T between stations run,s Based on this, its floating range ΔT run,i Limited to 0 to 5 seconds; train interval ST run,i Based on the existing train operation interval ST run,s Based on this, its floating range ΔST run,i The time is limited to between 0 and 30 seconds. These constraints ensure that adjustments to train running times and intervals during the optimization process remain within a safe and reasonable range, preventing the optimized timetable from deviating too much from the existing operational plan.

[0050] Step S13: Perform genetic operations on individuals in the current population based on the fitness values ​​to generate a new generation of population.

[0051] In this embodiment, the genetic operations include selection, crossover, and mutation. Selection is used to weed out individuals in the population based on their fitness values, ensuring that individuals with higher fitness values ​​(i.e., lower total energy consumption) are more likely to be retained and participate in reproduction. Crossover involves partially exchanging genes between the gene sequences of two selected parent individuals according to a preset crossover ratio to produce offspring individuals with the superior genes of both parents, thereby expanding the search range of the solution space. Mutation randomly perturbs individual genes (i.e., individual departure interval adjustments) in the individual gene sequence according to a preset mutation ratio to maintain population diversity and prevent the algorithm from prematurely falling into local optima. Furthermore, an elite preservation strategy can be incorporated into the genetic operations, where several individuals with the best fitness values ​​in the current population are directly copied to the next generation without crossover or mutation, preventing the optimal individuals from being destroyed during the genetic operations and thus accelerating the convergence speed of the algorithm.

[0052] Step S14: For the new generation population, jump back to the step of adjusting the timetable based on the timetable for each individual and calculating the fitness value of each individual using the objective function, until the preset termination condition is met, and optimize the current running timetable based on the individual with the best fitness value in the final population to obtain the optimized running timetable.

[0053] In this embodiment, after each new generation of population is generated, the fitness value of each individual in the new generation population is recalculated, and the genetic operation is performed again. This process is repeated until the preset termination condition is met.

[0054] In a specific implementation, optimizing the current timetable based on the individual with the best fitness value in the final population to obtain an optimized timetable includes: using the candidate timetable corresponding to the individual with the best fitness value in the final population as the optimized timetable. That is, after the iteration terminates, the individual with the best fitness value (i.e., the minimum total energy consumption) is selected from the final population, and the peak-hour departure interval adjustment amount and off-peak-hour departure interval adjustment amount corresponding to this individual are applied to the current timetable. The resulting candidate timetable is the train timetable scheme that satisfies the optimal energy saving requirement, and it is output.

[0055] As can be seen, this application obtains the current train timetable and generates multiple individuals in the initial population based on timetable adjustments within a preset reasonable range. It uses an objective function to calculate the total energy consumption of each individual under the corresponding timetable adjustment as its fitness value, and employs genetic algorithms such as selection, crossover, and mutation to iteratively optimize the population until a preset termination condition is met. The current timetable is then optimized based on the individual with the optimal fitness value. This transforms the energy consumption optimization problem of the train timetable into a global optimization problem with total energy consumption as the optimization objective. It can efficiently perform global searches under multi-variable and multi-constraint conditions without relying on complex and precise mathematical modeling, fully leveraging the complementary characteristics of regenerative braking energy between trains in time and space. Under the premise of ensuring constraints such as train running time, it effectively reduces the total energy consumption of train operation, improving the energy utilization efficiency and green, low-carbon operation level of the rail transit system.

[0056] See Figure 2 and Figure 3 As shown, this application discloses a specific method for optimizing train timetables. Compared to the previous embodiment, this embodiment further explains and optimizes the technical solution. Specifically, it includes: Step S21: Obtain the current operating timetable of the maglev train, and based on the current operating timetable, use a genetic algorithm to generate an initial population including multiple individuals; wherein each individual is a timetable adjustment amount generated within a preset reasonable range.

[0057] In this embodiment, 50 feasible solutions can be generated in the initial stage during the initialization process. Each set of feasible solutions includes peak-hour departure interval adjustment amount and off-peak-hour departure interval adjustment amount randomly generated within a reasonable range. The specific initialization process can be referred to the corresponding content disclosed in the previous embodiment, and will not be repeated here.

[0058] Step S22: Based on the timetable adjustment amount corresponding to each individual, calculate the fitness value of each individual using the objective function; the fitness value is used to characterize the total energy consumption of the maglev train.

[0059] Step S23: Sort the individuals in the current population according to the fitness values.

[0060] In this embodiment, after calculating the fitness value of each individual in the current population, the 50 feasible solutions in the population can be sorted in order of fitness value from best to worst (i.e., in order of total energy consumption from smallest to largest). The sorting result reflects the degree of energy saving effect of the candidate running timetables corresponding to each feasible solution and serves as the basis for subsequent selection operations.

[0061] Step S24: Based on the sorting results, perform a selection operation on the individuals in the current population, and perform a crossover operation on the selected individuals according to a preset crossover ratio and a mutation operation according to a preset mutation ratio to generate a new generation population with the same number of individuals as the current population.

[0062] In this embodiment, a selection operation is performed based on the ranking results, giving individuals ranked higher a greater probability of entering the mating pool. In the genetic operations, the crossover and mutation ratios can be set to 0.8 and 0.2, respectively; that is, the preset crossover ratio is 0.8 and the preset mutation ratio is 0.2. After selection, crossover, and mutation operations, a new generation population containing 50 entirely new feasible solutions is obtained, meaning the number of individuals in the new generation population is the same as the number of individuals in the current population. Furthermore, an elite retention strategy can be combined, directly retaining the individual with the best fitness value in the current population into the new generation population to accelerate convergence and ensure the monotonicity of the optimization process.

[0063] Step S25: For the new generation population, jump back to the step of adjusting the timetable based on the timetable for each individual and calculating the fitness value of each individual using the objective function, until the preset termination condition is met, and optimize the current running timetable based on the individual with the best fitness value in the final population to obtain the optimized running timetable.

[0064] In this embodiment, it should be noted that the preset termination condition includes at least one of the following conditions: the difference between the optimal fitness values ​​of two adjacent generations of the population is less than a preset convergence threshold; the number of generations in which the optimal fitness value of the population has stagnated continuously exceeds a preset stagnation generation threshold; or the total number of iterations of the population reaches a preset maximum number of generations. That is, this application needs to repeatedly execute the above steps of calculating fitness values ​​and genetic operations until the calculated feasible solution meets one of the following three conditions: First, the difference between the optimal fitness values ​​of two adjacent generations of the population is within 0.001, that is, the difference between the optimal fitness values ​​of two adjacent generations of the population is less than a preset convergence threshold, at which point the algorithm can be considered to have converged; Second, the optimal fitness value of the population has stagnated for more than 20 generations, that is, the number of generations in which the optimal fitness value of the population has stagnated continuously exceeds a preset stagnation generation threshold, at which point it is difficult to obtain a better solution by continuing iteration; Third, the total number of generations of the population does not exceed 200, that is, when the total number of iterations of the population reaches the preset maximum number of generations 200, the process is forcibly terminated to control computational overhead. That is, the preset convergence threshold can be set to 0.001, the preset stagnation generation threshold can be set to 20 generations, and the preset maximum generation can be set to 200 generations. The above values ​​can also be flexibly adjusted according to the actual optimization accuracy and computing resource requirements. This embodiment does not make specific limitations on this.

[0065] For more detailed processing procedures of steps S21 and S22, please refer to the relevant content disclosed in the foregoing embodiments, which will not be repeated here.

[0066] As can be seen, this embodiment sorts individuals in the population according to their fitness values, performs selection operations based on the sorting results, and then performs crossover and mutation operations according to preset crossover and mutation ratios respectively. Combined with the elite retention strategy and multiple termination conditions, it can significantly accelerate the convergence speed of the genetic algorithm while ensuring the quality of the solution, and quickly and accurately calculate the train timetable that satisfies the energy-saving optimum.

[0067] To facilitate understanding of the technical solution and its beneficial effects, the following describes the complete implementation process of the train timetable optimization method disclosed in this application, taking the timetable optimization process of a high-speed maglev line during a typical operating period as an example.

[0068] First, the current timetable and related input data for the high-speed maglev line are obtained. The input data includes planned train timetable data, such as station names, planned arrival times, and planned departure times; it also includes data on the expected train operation patterns, such as the number of trains, expected peak-hour departure intervals, and off-peak departure intervals; in addition, it includes data for energy consumption simulation, such as train current, train voltage, regenerative braking efficiency, maglev line structure, station distribution, speed-limited sections, and train traction / braking performance parameters. In this application example, the line has a total of 153 trains per day, with a peak-hour interval of 330 seconds (34 trains during the morning peak and 31 trains during the evening peak); and an off-peak interval of 418 seconds (61 and 27 trains respectively during the two off-peak periods). This optimization will adjust the peak-hour and off-peak train intervals, with the adjustment range limited to ±10 seconds.

[0069] Next, based on the existing peak-hour headway of 330 seconds and off-peak headway of 418 seconds, 50 gene sequences composed of peak-hour and off-peak headway adjustments were randomly generated within a preset reasonable range of plus or minus 10 seconds, serving as the initial 50 individuals in the population. For each individual, the departure time of each train was determined sequentially during the morning peak, evening peak, and off-peak periods according to its corresponding headway adjustment. The arrival and departure times of each maglev train at each station were then recursively derived by combining the station travel time, generating a corresponding candidate timetable for the entire day. The candidate timetable was input into a pre-built simulator, which calculated the operating status, traction energy consumption, substation energy consumption, regenerative braking energy utilization, and line loss of all trains. Subsequently, the fitness value of each individual was calculated. If the train travel time exceeded the limited travel time constraint range, a penalty term based on a penalty coefficient was added to the objective function. Based on this, the 50 feasible solutions are sorted according to their fitness values ​​and a selection operation is performed. Crossover is performed at a crossover ratio of 0.8, and mutation is performed at a mutation ratio of 0.2. An elite retention strategy is then used to generate a new generation of population. This process is repeated iteratively until the difference in the optimal fitness values ​​between adjacent generations is within 0.001, the optimal fitness value of the population stagnates for more than 20 generations, or the total number of generations of the population reaches 200. The optimized timetable corresponding to the individual with the best fitness value in the final population is then output. A comparison of the train intervals between the existing timetable and the optimized timetable is shown in Table 1.

[0070] Table 1. Comparison of headway between existing and optimized timetables

[0071] As shown in Table 1, after optimization using the train timetable optimization method disclosed in this application, the headway during the morning and evening peak hours is adjusted from 330 seconds to 337 seconds, and the headway during the two off-peak hours is adjusted from 418 seconds to 413 seconds. The number of trains in each time period remains unchanged, with a total of 153 trains per day. Furthermore, the adjustment value of the headway in each time period is limited to within 10 seconds. Further, by rationally redistributing departure intervals between peak and off-peak hours, accelerating and braking trains achieve energy complementarity in time and space, reducing ineffective energy loss during off-peak hours, thereby improving the energy utilization efficiency and power supply stability of the entire maglev transportation system. Table 2 shows a comparison of the total regenerative braking utilization time between the existing timetable and the optimized timetable.

[0072] Table 2 Comparison of total regenerative braking utilization time between existing and optimized timetables

[0073] As shown in Table 2, after adopting the optimized timetable, the weighted value of the total regenerative braking utilization time increased from 2,689,215 in the existing timetable to 2,874,521, which significantly increased the total regenerative braking utilization time. This increase in total time leads to a higher utilization rate of regenerative braking, thereby reducing energy consumption. The estimated energy saving ratio is approximately 1.79%. Specifically... Figure 4 As shown, Figure 4 This is a schematic diagram illustrating the principle of a train timetable optimization method provided in this application embodiment. This method improves the utilization rate of regenerative braking energy and reduces the load on substations through timetable optimization. The optimized timetable ensures that the total daily train operating time and number of trains remain unchanged, requiring only adjustments to the train intervals, with the adjustments limited to within 10 seconds, thus avoiding any impact on passenger flow.

[0074] As can be seen, the train timetable optimization method disclosed in this application can optimize train departure intervals during peak and off-peak hours without changing the total train travel time, stop time, and turnaround time. This allows for the rational allocation of train running sequences, ensuring that the regenerative energy generated by braking trains is absorbed by simultaneously accelerating trains, while unused energy is preferentially stored in energy storage devices in the power grid. This effectively reduces the external power supply demand of substations, minimizes overall energy consumption, and improves the greenness and operational economy of the high-speed maglev transportation system. Furthermore, the method disclosed in this application can be combined with big data analytics to achieve real-time monitoring and dynamic adjustment of train operating status. For example, during peak hours, train intervals can be appropriately shortened to allow accelerating and braking trains to complement each other in time and space; while during off-peak hours, intervals can be appropriately extended to reduce ineffective energy loss, thereby further improving the energy utilization efficiency and power supply stability of the entire maglev transportation system.

[0075] See Figure 5 As shown in the figure, this application discloses a train timetable optimization device, which includes: Population initialization module 11 is used to obtain the current operating timetable of the maglev train and, based on the current operating timetable, use a genetic algorithm to generate an initial population including multiple individuals; wherein, each individual is a timetable adjustment amount generated within a preset reasonable range; Calculation module 12 is used to calculate the fitness value of each individual based on the timetable adjustment amount corresponding to each individual and using an objective function; the fitness value is used to characterize the total energy consumption of the maglev train. Genetic operation module 13 is used to perform genetic operations on individuals in the current population based on the fitness value to generate a new generation of population; The iterative optimization module 14 is used to jump back to the step of adjusting the timetable based on the timetable for each individual and calculating the fitness value of each individual using the objective function for the new generation population, until the preset termination condition is met, and optimize the current running timetable based on the individual with the best fitness value in the final population to obtain the optimized running timetable.

[0076] As can be seen, this application obtains the current train timetable and generates multiple individuals in the initial population based on timetable adjustments within a preset reasonable range. It uses an objective function to calculate the total energy consumption of each individual under the corresponding timetable adjustment as its fitness value, and employs genetic algorithms such as selection, crossover, and mutation to iteratively optimize the population until a preset termination condition is met. The current timetable is then optimized based on the individual with the optimal fitness value. This transforms the energy consumption optimization problem of the train timetable into a global optimization problem with total energy consumption as the optimization objective. It can efficiently perform global searches under multi-variable and multi-constraint conditions without relying on complex and precise mathematical modeling, fully leveraging the complementary characteristics of regenerative braking energy between trains in time and space. Under the premise of ensuring constraints such as train running time, it effectively reduces the total energy consumption of train operation, improving the energy utilization efficiency and green, low-carbon operation level of the rail transit system.

[0077] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the train timetable optimization method performed by the electronic device disclosed in any of the foregoing embodiments.

[0078] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0079] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0080] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored on it include operating system 221, computer program 222 and data 223, etc., and the storage method can be temporary storage or permanent storage.

[0081] The operating system 221 manages and controls the various hardware devices and computer programs 222 on the electronic device 20 to enable the processor 21 to perform calculations and processing on the massive amounts of data 223 in the memory 22. The operating system 221 can be Windows, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the train timetable optimization method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the electronic device from external devices, as well as data collected by its own input / output interface 25.

[0082] Furthermore, this application also discloses a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, it implements the train timetable optimization method steps disclosed in any of the foregoing embodiments.

[0083] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0084] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0085] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, compact disc read-only memory (CD-ROM), or any other form of storage medium known in the art.

[0086] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0087] The above provides a detailed description of a train timetable optimization method, apparatus, device, and storage medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only intended to help understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for optimizing train timetables, characterized in that, include: Obtain the current operating timetable of the maglev train, and based on the current operating timetable, use a genetic algorithm to generate an initial population including multiple individuals; wherein each individual is a timetable adjustment amount generated within a preset reasonable range; The fitness value of each individual is calculated based on the timetable adjustment amount corresponding to each individual and using an objective function; the fitness value is used to characterize the total energy consumption of the maglev train. Genetic operations are performed on individuals in the current population based on the fitness values ​​to generate a new generation of the population. For the new generation population, the process jumps back to the step of adjusting the timetable based on each individual and calculating the fitness value of each individual using the objective function, until the preset termination condition is met. Then, the current running timetable is optimized based on the individual with the best fitness value in the final population to obtain the optimized running timetable.

2. The train timetable optimization method according to claim 1, characterized in that, The timetable adjustment includes adjustments to departure intervals during peak and off-peak periods; Accordingly, the generation of an initial population comprising multiple individuals using a genetic algorithm includes: Based on the existing departure intervals in the current operating timetable; Multiple gene sequences consisting of peak-hour departure interval adjustment and off-peak departure interval adjustment are randomly generated within a preset reasonable range to serve as multiple individuals in the initial population.

3. The train timetable optimization method according to claim 2, characterized in that, The step of adjusting the timetable for each individual and calculating the fitness value for each individual using the objective function includes: Based on the timetable adjustment amount corresponding to each individual, a corresponding candidate operating timetable is generated, and the train operation process is simulated based on the candidate operating timetable to obtain the operating energy consumption simulation results. Based on the simulation results of the operating energy consumption, the fitness value of each individual is calculated using the objective function; Accordingly, the optimization of the current running timetable based on the individual with the best fitness value in the final population to obtain an optimized running timetable includes: The candidate running timetable corresponding to the individual with the best fitness value in the final population is used as the optimized running timetable.

4. The train timetable optimization method according to claim 3, characterized in that, The process of generating a corresponding candidate running timetable based on the timetable adjustment amount for each individual includes: Obtain the driving pattern data corresponding to the current operating timetable; the driving pattern data includes at least the number of trips, peak period division, and off-peak period division; For each individual, based on the train operation data and according to the peak-hour departure interval adjustment amount and off-peak-hour departure interval adjustment amount corresponding to each individual, the departure time of each maglev train is determined sequentially during the corresponding peak and off-peak periods. Based on the determined departure time and the inter-station travel time, the arrival and departure times of each maglev train at each station are determined, and a candidate timetable for each individual is obtained.

5. The train timetable optimization method according to claim 3, characterized in that, The process of simulating train operation based on the candidate timetable to obtain simulation results of operating energy consumption includes: Input the candidate runtime schedule into the pre-built simulator; The simulator is used to simulate the train operation process based on the candidate timetable to obtain simulation results of operating energy consumption, including operating status, train traction energy consumption, substation energy consumption, regenerative braking energy utilization, and transmission line losses.

6. The train timetable optimization method according to claim 5, characterized in that, The objective function includes a first objective function and a second objective function; the first objective function is constructed based on the total energy consumption of each traction substation, and the second objective function is constructed based on the total energy consumption of each traction substation and a preset penalty coefficient. Accordingly, the step of calculating the fitness value of each individual based on the simulation results of the operating energy consumption and using the objective function includes: For the current individual, obtain the train running time under the corresponding candidate timetable, and determine whether the train running time is within the preset running time constraint range; If the train running time is within the running time constraint range, then the fitness value of the current individual is calculated based on the running energy consumption simulation results and using the first objective function; If the train running time is not within the running time constraint range, the fitness value of the current individual is calculated based on the running energy consumption simulation results and using the second objective function.

7. The train timetable optimization method according to claim 6, characterized in that, The energy consumption of the traction substation is determined based on a preset train operation energy consumption model; wherein, the train operation energy consumption model is constructed based on train traction energy consumption, regenerative braking energy and transmission line loss.

8. The train timetable optimization method according to claim 7, characterized in that, The calculation process for the substation energy consumption of the traction substation includes: The train's traction energy consumption is determined by multiplying the maximum traction force of the maglev train at the current speed by the current speed. The regenerative braking feedback energy is determined based on the product of regenerative braking efficiency, train current, and train voltage. The difference between the train traction energy consumption and the regenerative braking feedback energy is determined, and the substation energy consumption of the traction substation is determined based on the sum of the difference result and the transmission line loss.

9. The train timetable optimization method according to claim 6, characterized in that, The train travel time is determined based on the sum of the inter-station travel time of each maglev train at each station and the train travel interval.

10. The train timetable optimization method according to claim 1, characterized in that, The genetic operations include selection, crossover, and mutation.

11. The train timetable optimization method according to claim 10, characterized in that, The step of performing genetic operations on individuals in the current population based on the fitness value to generate a new generation population includes: Sort the individuals in the current population according to the fitness values; Based on the sorting results, a selection operation is performed on the individuals in the current population, and a crossover operation is performed on the selected individuals according to a preset crossover ratio, and a mutation operation is performed according to a preset mutation ratio, so as to generate a new generation population with the same number of individuals as the current population.

12. The train timetable optimization method according to any one of claims 1 to 11, characterized in that, The preset termination condition includes at least one of the following conditions: The difference in optimal fitness values ​​between two adjacent generations is less than a preset convergence threshold; The optimal fitness value of the population remains stagnant for more than the preset stagnation generation threshold. The total number of iterations in the population reaches the preset maximum number of generations.

13. A train timetable optimization device, characterized in that, include: The population initialization module is used to obtain the current operating timetable of the maglev train and, based on the current operating timetable, use a genetic algorithm to generate an initial population including multiple individuals; wherein, each individual is a timetable adjustment amount generated within a preset reasonable range; The calculation module is used to calculate the fitness value of each individual based on the timetable adjustment amount corresponding to each individual and using the objective function; the fitness value is used to characterize the total energy consumption of the maglev train. The genetic operation module is used to perform genetic operations on individuals in the current population based on the fitness value to generate a new generation of population. The iterative optimization module is used to jump back to the step of adjusting the timetable based on the timetable for each individual and calculating the fitness value of each individual using the objective function for the new generation population, until the preset termination condition is met, and optimize the current running timetable based on the individual with the best fitness value in the final population to obtain the optimized running timetable.

14. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the train timetable optimization method as described in any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that, Used to store a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the train timetable optimization method as described in any one of claims 1 to 12.

Images