Train speed curve energy-saving optimization method and system suitable for complex line
Through genetic algorithms, the train speed curve is optimized, and the problem of excessive energy consumption of trains on complex lines is solved, and the goals of energy conservation, emission reduction and green transportation are achieved. It is suitable for urban rail transit systems and long-distance trunk railways.
Patent Information
- Application Number
- CN202510371155.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-27
- Publication Date
- 2025-08-01
AI Technical Summary
The prior art cannot effectively optimize the energy-saving speed curve of trains under complex line conditions, resulting in excessive traction energy consumption.
Genetic algorithms are used to optimize the train speed curve. By dividing the maximum capacity speed curve into multiple subprocesses, combining idle row control, dynamically solve the optimal idle row starting point and end point position, and an energy-saving speed curve optimization model is constructed to reduce the traction energy consumption of the train on complex lines.
Significantly reduce the energy consumption of trains on complex routes, achieve energy conservation and emission reduction, improve the economy and comfort of train operations, and promote the development of green transportation.
Smart Images

Figure CN120409188A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of energy-saving operation optimization of urban rail transit trains, and particularly to a method and system for optimizing the energy-saving speed curve of trains applicable to complex lines. Background Art
[0002] In recent years, with the growing demand for safe, efficient, and convenient public transportation, the construction of urban rail transit has developed rapidly, and urban rail transit such as subways and light rails in China has taken initial shape. From the perspective of operation energy consumption, traction power supply energy consumption accounts for the largest part of the operation energy consumption of urban rail transit systems, accounting for about 40%. In view of the characteristics of short inter-station distances and simple line conditions of urban rail transit lines, the coasting control method is applied to the problem of optimizing the energy-saving speed curve of trains. Coasting control reduces the traction energy consumption during train operation by keeping the train in the coasting condition and avoiding repeated switching between traction and braking conditions. The key to coasting control lies in determining the starting point of the coasting condition. By appropriately increasing the running time, coasting control can significantly reduce the traction energy consumption during train operation.
[0003] In the prior art, based on the basic train operation model and relevant constraint conditions, the speed curve profile is planned according to the classical four-stage method, and a method for optimizing the train speed curve based on coasting control is proposed, but it cannot effectively optimize the energy consumption during the train operation process when operating on complex lines. In fact, when the line is relatively complex, there may be multiple traction-braking processes during the inter-station operation of the train. Therefore, unified energy consumption optimization for the entire complex line is required. Summary of the Invention
[0004] An embodiment of the present invention provides a method for optimizing the energy-saving speed curve of trains applicable to complex lines, aiming to significantly reduce the traction energy consumption of trains on complex lines and achieve the effect of energy conservation and emission reduction.
[0005] In a first aspect, an embodiment of the present invention provides a method for optimizing the energy-saving speed curve of trains applicable to complex lines, including:
[0006] S1. Obtain the maximum capacity speed curve according to the train parameter data and the line parameter data; divide the maximum capacity speed curve into multiple sub-processes by traction-braking processes;
[0007] S2. Input the maximum capacity speed curve into the energy-saving speed curve optimization model; wherein, the energy-saving speed curve optimization model takes minimizing the inter-station traction energy consumption of the train as the optimization goal and takes the running time constraint, the running speed constraint, and the coasting point position constraint as constraint conditions;
[0008] S3. Solve the energy-saving speed curve optimization model through a genetic algorithm to obtain the target individual represented by the current optimal result and the train speed curve corresponding to the target individual; use the train speed curve corresponding to the target individual as the train speed curve after energy-saving optimization.
[0009] Further, the expression of the optimization objective is:
[0010]
[0011] uf k ·ub k = 0, and uf k , ub k ∈[0, 1]
[0012] where μf k represents the traction force coefficient, μb k represents the braking force coefficient, F max (v k ) represents the traction force, k represents the discrete points during the train operation, when k = 1, it represents the starting position of the train operation, when k = K, it represents the ending position of the train operation, Δx represents the position interval between adjacent discrete points, and η represents the traction drive efficiency coefficient.
[0013] Further, the running time constraint is: during the process of the train running from the starting position to the ending position, the running interval time T of the running section is less than or equal to the set interval running time T set ;
[0014] The running speed constraint is: during the process of the train running from the starting position to the ending position, the running speed v k of the discrete point k is greater than or equal to 0 and less than or equal to the line speed limit V k corresponding to the train at the position discrete point k; and the running speed of the train when it runs to the station K station is 0;
[0015] The coasting point position constraint is: the coasting starting position X i,c0 and the coasting ending position X i,c1 in the i-th coasting condition are both greater than or equal to the traction starting position X i,t of the i-th sub-process and less than or equal to the braking ending position X i,b of the i-th sub-process.
[0016] Further, S3.1. Construct individuals of the initial population, each individual consists of two genes encoded by real numbers, and the genes are respectively set as the coasting starting position and the coasting ending position in the i-th coasting condition;
[0017] S3.2. Initialize the size M of the initial population, the maximum number of iterations gen, the minimum value P of the crossover probability cmin and the maximum value P of the crossover probability; cmax the variance σ of the normal distribution and the mean μ of the normal distribution;
[0018] S3.3. Generate M individuals that satisfy the constraint conditions to complete the establishment of the initial population;
[0019] S3.4. Design a fitness function and calculate the fitness value of each individual in the initial population;
[0020] S3.5. Select individuals using the roulette wheel method according to the fitness value of each individual to obtain a roulette wheel population;
[0021] S3.6. Perform a crossover operation on the individuals in the roulette wheel population using the adaptive crossover method to obtain a crossover population;
[0022] S3.7. Perform a mutation operation on the individuals in the crossover population using the Gaussian mutation method to obtain a mutation population;
[0023] S3.8. Determine whether the maximum number of iterations gen has been reached. If the maximum number of iterations has been reached, execute step S3.9; otherwise, execute step S3.4;
[0024] S3.9. When the maximum number of iterations is reached, screen out the target individuals from the population corresponding at this time and output the train speed curve corresponding to the target individuals.
[0025] Further, S3.3 includes:
[0026] S3.3.1. Obtain the running time constraint and the coasting point position constraint in the constraint conditions;
[0027] S3.3.2. Generate a random solution according to the coasting point position constraint;
[0028] S3.3.3. Calculate the coasting end speed according to the corresponding coasting start position and coasting end position in the random solution;
[0029] S3.3.4. Determine whether the coasting end speed is equal to the speed corresponding to this position in the subprocess. If they are equal, execute S3.3.5; if not, execute S3.3.2;
[0030] S3.3.5. Repeat steps S3.3.3 - S3.3.4 to obtain a train speed curve including multiple coasting conditions;
[0031] S3.3.6. Calculate the interval running time T corresponding to the train speed curve;
[0032] S3.3.7. Determine whether the running time constraint is satisfied. If the running time constraint is satisfied, execute step S3.3.8; otherwise, execute step S3.3.2;
[0033] S3.3.8. Take the random solutions that satisfy the running time constraint and the coasting point position constraint as individuals of the initial population and put them into the initial population;
[0034] S3.3.9. Determine whether the number of individuals in the initial population reaches M. If the number of the initial population reaches M, execute step S3.3.10; otherwise, execute step S3.3.2;
[0035] S3.3.10. Generate the initial population.
[0036] Furthermore, S3.9 includes:
[0037] S3.9.1. Calculate the coasting end speed of any individual in the population according to the coasting start position and the coasting end position of the individual;
[0038] S3.9.2. Determine whether the coasting end speed at the coasting end position is equal to the corresponding speed at this position in the sub-process. If they are equal, execute step S3.9.3; otherwise, discard the individual;
[0039] S3.9.3. Replace a section of the speed curve in the corresponding sub-process with the speed curve of the coasting condition in the individual to obtain the train speed curve corresponding to the individual;
[0040] S3.9.4. Calculate the interval running time T corresponding to the train speed curve of the individual;
[0041] S3.9.5. Determine whether the interval running time T satisfies the running time constraint. If the running time constraint is satisfied, execute step S3.9.6; otherwise, discard the individual;
[0042] S3.9.6. Calculate the train inter-station traction energy consumption E of the train speed curve corresponding to the individual;
[0043] S3.9.7. Record the train inter-station traction energy consumption of each individual, compare the train inter-station traction energy consumption of each individual, select the individual with the minimum train inter-station traction energy consumption as the target individual, and generate the train speed curve corresponding to the target individual.
[0044] Furthermore, S3.9.6 includes:
[0045] The traction energy consumption e of the train at the position interval Δx k is expressed as:
[0046]
[0047] The traction energy consumption between train stations can be expressed as:
[0048]
[0049] Where, μf k represents the traction force action coefficient, F max (v k ) represents the traction force, k represents the discrete points during the train operation. When k = 1, it represents the starting position of the train operation. When k = K, it represents the ending position of the train operation. Δx represents the position interval between adjacent discrete points, and η represents the traction drive efficiency coefficient.
[0050] In a second aspect, an embodiment of the present invention provides a train speed curve energy-saving optimization system applicable to complex lines, including:
[0051] A sub-process division module, configured to obtain the maximum capacity speed curve according to the train parameter data and the line parameter data; divide the maximum capacity speed curve into multiple sub-processes in the traction-braking process;
[0052] An optimization model construction module, configured to input the maximum capacity speed curve into an energy-saving speed curve optimization model; wherein, the energy-saving speed curve optimization model takes minimizing the traction energy consumption between train stations as the optimization objective, and takes the operation time constraint, the operation speed constraint, and the coasting point position constraint as the constraint conditions;
[0053] An optimization model solving module, configured to solve the energy-saving speed curve optimization model through a genetic algorithm to obtain the target individual represented by the current optimal result and the train speed curve corresponding to the target individual; use the train speed curve corresponding to the target individual as the energy-saving optimized train speed curve.
[0054] In a third aspect, an embodiment of the present invention provides an electronic device, and the electronic device includes:
[0055] At least one processor; and
[0056] A memory communicatively connected to the at least one processor; wherein,
[0057] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for optimizing the energy saving of the train speed curve applicable to complex lines according to any embodiment of the present invention.
[0058] Fourthly, an embodiment of the present invention provides a computer-readable storage medium storing computer instructions for causing a processor to implement the train speed curve energy-saving optimization method applicable to complex lines according to any embodiment of the present invention when executed.
[0059] In the embodiment of the present invention, by setting an energy-saving speed curve optimization model, a train speed curve with the lowest traction energy consumption is obtained. The potential energy and operating conditions of the line are fully utilized, and based on the optimization method of the genetic algorithm, the optimal coasting start and end positions of each sub-process are dynamically solved, significantly reducing the traction energy consumption of the train on complex lines. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0061] Figure 1 is a schematic flowchart of a train speed curve energy-saving optimization method applicable to complex lines according to an embodiment of the present invention;
[0062] Figure 2 is a schematic diagram of dividing the maximum capacity speed curve into multiple sub-processes according to an embodiment of the present invention;
[0063] Figure 3 is a schematic diagram of replacing the original speed curve with the coasting condition speed curve according to an embodiment of the present invention;
[0064] Figure 4 is a schematic diagram of the design principle of the coasting condition according to an embodiment of the present invention;
[0065] Figure 5 is a schematic diagram of the optimization result of the coasting condition according to an embodiment of the present invention;
[0066] Figure 6 is a schematic flowchart of generating a target individual through the genetic algorithm according to an embodiment of the present invention;
[0067] Figure 7 is a schematic flowchart of the initial population establishment process according to an embodiment of the present invention;
[0068] Figure 8 is a schematic flowchart of screening the train speed curve with the lowest traction energy consumption according to an embodiment of the present invention;
[0069] Figure 9 It is a schematic structural diagram of a train speed curve energy-saving optimization system applicable to complex lines provided by an embodiment of the present invention;
[0070] Figure 10 It is a schematic structural diagram of an electronic device for implementing a train speed curve energy-saving optimization method applicable to complex lines according to an embodiment of the present invention. Specific embodiments
[0071] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only for explaining the present invention, rather than limiting the present invention. In addition, it should be noted that for the sake of description, only parts related to the present invention rather than all structures are shown in the drawings.
[0072] Embodiment 1
[0073] Figure 1 It is a schematic flow diagram of a train speed curve energy-saving optimization method applicable to complex lines provided by Embodiment 1 of the present invention. This method can be executed by the train speed curve energy-saving optimization system applicable to complex lines in the embodiments of the present invention. The system can be implemented in software and / or hardware and integrated in an electronic device. As Figure 1 shown, the method includes:
[0074] S1. Obtain the maximum capacity speed curve according to the train parameter data and the line parameter data; divide the maximum capacity speed curve into multiple sub-processes in the traction-braking process.
[0075] Among them, the train parameter data includes: vehicle weight, traction drive system efficiency, traction and braking characteristics, basic resistance characteristics, etc.; the line parameter data includes: station kilometer marker, speed limit, gradient, line curve, etc.
[0076] Through the train parameter data and the line parameter data, the maximum capacity speed curve can be calculated. The maximum capacity speed curve is a speed-displacement curve, specifically:
[0077] First, set the limit conditions for the train simulation operation process. For example, the speed limit for the whole line is 100 kilometers per hour, and it is required that the train does not exceed a specific position (such as 1366 meters) during the test. These limits will be used as the basis for calculating the speed curve.
[0078] Then, consider the train parameter data during the train simulation operation. Such as the maximum traction acceleration, maximum braking deceleration, and traction cut-off delay, etc., are important factors for calculating the speed curve. For example, the maximum traction acceleration is 1.7 m / s², the maximum braking deceleration is 1.5 m / s², and the traction cut-off delay is 6 seconds. These parameters will affect the acceleration and braking distances of the train, thus affecting the shape of the speed curve.
[0079] Next, set the safe operating speed during the train simulation operation. The safe operating speed refers to the speed at which the train must take braking measures after exceeding this speed value. The safe operating speed of each point on the line can be calculated through programming, calculating one speed point every centimeter. It involves complex mathematical models and algorithms, including considering the most unfavorable situations, such as when the train is in the acceleration phase when receiving a deceleration instruction.
[0080] Subsequently, consider the line parameter data during the train simulation operation. Such as the curve radius, curve superelevation, and the maximum speed limit of the line in the tunnel, etc., will all affect the maximum speed of the train. For example, the maximum superelevation of the curve should be 120 mm. When the set superelevation value is insufficient, generally an under-superelevation not greater than 61 mm is allowed. The maximum speed value of the line in the tunnel should not exceed 80 km / h.
[0081] Then, when selecting the maximum operating speed of the train, introduce multiple comprehensive conditions. It is necessary to comprehensively consider various factors such as improving the travel speed, reducing the travel time, saving energy consumption, and reducing investment. For example, as the train speed increases, the running resistance and energy consumption of the train will increase with the square value of the speed.
[0082] Finally, professional software can be used for simulation calculations. Such as the simulation program for the geometric curve passing ability of high-speed trains developed using the finite node method and local search technology. These programs can simulate the dynamic change laws of physical parameters such as the coupler swing angle, lateral offset, and inter-vehicle distance with the running distance when the vehicle passes through different types of curves considering the initial offset of the vehicle.
[0083] After obtaining the maximum capacity speed curve, the maximum capacity speed curve can be divided into multiple sub-processes. Figure 2 It is a schematic diagram of dividing the maximum capacity speed curve into multiple sub-processes provided by Embodiment 1 of the present invention. As Figure 2 shown, the process of speed acceleration means being affected by the traction force, while the process of speed deceleration means being affected by the braking force.
[0084] Specifically, the sub - process representing the "traction - braking" process refers to the train operation process that starts with the traction mode and ends with the adjacent braking mode. According to the maximum - capacity speed curve of the train, the maximum - capacity speed curve is divided into multiple sub - processes according to the concept of sub - processes. At the same time, the traction starting position and braking end position of each sub - process can be recorded and used as the position constraints for the coasting starting position and coasting end position in the coasting mode of each sub - process.
[0085] S2. Input the maximum - capacity speed curve into the energy - saving speed - curve optimization model. Among them, the energy - saving speed - curve optimization model takes minimizing the traction energy consumption between stations of the train as the optimization objective and takes the running - time constraint, running - speed constraint, and coasting - point position constraint as the constraint conditions.
[0086] Furthermore, the expression of the optimization objective is:
[0087]
[0088] uf k ·ub k = 0, and uf k , ub k ∈[0, 1]
[0089] Among them, μf k represents the traction - force action coefficient, μb k represents the braking - force action coefficient, F max (v k ) represents the traction force, k represents the discrete points in the train operation process. When k = 1, it represents the starting position of the train operation. When k = K, it represents the ending position of the train operation. Δx represents the position interval between adjacent discrete points, and η represents the traction - drive efficiency coefficient.
[0090] It should be noted that during the train operation, it is subject to the traction force or braking force. What the optimization objective calculates is the energy consumption generated during the traction process. Therefore, when the train is subject to the braking force at the discrete point k, the traction - force action coefficient μf k takes 0.
[0091] When the train runs to the discrete point k and is subject to the traction force or braking force, and reaches the next adjacent discrete point k + 1, the position interval between the two discrete points is Δx. At the discrete point k, the running speed is v k , and it runs to the discrete point k + 1 with an acceleration a k (uf k , ub k ). At the discrete point k + 1, the running speed is vk +1 , then t k+1 = t k +2Δx / (vk +v k+1 )。
[0092] Furthermore, the constraint conditions include: running time constraint, running speed constraint, coasting point position constraint, etc.
[0093] The running time constraint is that during the process of the train running from the starting position to the ending position, the running interval time T of the running section is less than or equal to the set interval running time T set 。
[0094] The running speed constraint is that during the process of the train running from the starting position to the ending position, the running speed v of the discrete point k k is greater than or equal to 0 and less than or equal to the line speed limit V corresponding to the train at the position discrete point k k ; and the running speed of the train when it runs to the station K station is 0.
[0095] The coasting point position constraint is that in the i-th sub-process, the coasting starting position X i,c0 and the coasting ending position X i,c1 in the coasting condition are both greater than or equal to the traction starting position X i,t of the i-th sub-process, and both less than or equal to the braking ending position X i,b of the i-th sub-process.
[0096] · Furthermore, the expression of the energy-saving speed curve optimization model can be expressed as:
[0097]
[0098] S3. Solve the energy-saving speed curve optimization model through the genetic algorithm to obtain the target individual represented by the current optimal result and the train speed curve corresponding to the target individual; use the train speed curve corresponding to the target individual as the train speed curve after energy-saving optimization.
[0099] Among them, solving the energy-saving speed curve optimization model includes: converting a section of the speed curve in each sub-process of the maximum capacity speed curve into a speed curve of a coasting condition to generate a train speed curve; using the same method to generate multiple train speed curves; calculating the energy consumption value of each train speed curve, and using the speed curve with the minimum energy consumption as the train speed curve after energy-saving optimization. In this embodiment, the speed curves are all expressed as speed-displacement curves.
[0100] Figure 3 is a schematic diagram of replacing the original speed curve with the coasting condition speed curve provided by Embodiment 1 of the present invention, as Figure 3As shown, the solid line part can be understood as the speed curve of a sub-process. In this sub-process, there is a section of the speed curve that can be converted into the speed curve of a coasting condition.
[0101] The principle is as follows: There is a section of the speed curve in the sub-process. The speed at the starting point is v1, and the displacement is x1. The speed at the ending point is v2, and the displacement is x2. A coasting condition can be designed. In the speed curve of the coasting condition, the speed at the starting point is v1, the displacement is x1, the speed at the ending point is v2, and the displacement is x2. By replacing a section of the speed curve in the sub-process with the speed curve of the coasting condition, the train can decelerate in advance, which will increase the running time of the train. Since the train is only subject to running resistance and not traction during the operation of the coasting condition, the energy consumption of the train is reduced.
[0102] Figure 4 It is a schematic diagram of the design principle of a coasting condition provided by Embodiment 1 of the present invention. Figure 4 Exemplarily explains how the speed curve of the coasting condition can replace the original speed curve. According to Figure 4 , it is elaborated through the speed-time curve of the coasting condition. For example: There is an original speed-time curve that starts to decelerate at a speed of v1 at time 0 and the speed decreases to 0 at time t1, and its running displacement is x. By designing a speed-time curve of a coasting condition, it starts to decelerate at a speed of v1 at time 0 and changes the acceleration at time t0, so that the speed decreases to 0 at time t2, and its running displacement is also exactly x. That is, two different decelerating running methods have the same starting and ending points, as well as the same starting and ending speeds.
[0103] Figure 5 It is a schematic diagram of the optimization result of a coasting condition provided by Embodiment 1 of the present invention. Combining Figure 3 、 Figure 4 With Figure 5 , the maximum capacity speed curve is divided into multiple sub-processes. In each sub-process, a section of the train running section can be selected. The starting and ending speeds of this section are fixed. By designing the coasting condition, the acting time of the traction force can be reduced, enabling the train to decelerate earlier, and at the same time increasing the deceleration time of the train, so that the train consumes less energy during the driving process of the entire section.
[0104] Figure 6 It is a schematic diagram of the process of generating target individuals through a genetic algorithm provided by Embodiment 1 of the present invention. As Figure 6 shown, its specific process includes:
[0105] S3.1. Construct individuals of the initial population. Each individual consists of two genes encoded by real numbers, which are set as the coasting start position and the coasting end position in the i-th coasting condition, respectively.
[0106] S3.2. Initialize the size M of the initial population, the maximum number of iterations gen, the minimum crossover probability P cmin , the maximum crossover probability P cmax , the variance σ of the normal distribution, and the mean μ of the normal distribution.
[0107] S3.3. Generate M individuals that satisfy the constraint conditions to complete the establishment of the initial population.
[0108] Specifically, according to the coasting start position X i,c0 and the coasting end position X i,c1 , it can be determined whether the speed curve of each coasting condition can replace a section of the speed curve in each sub-process, and then the maximum capacity speed curve is updated. If it can be replaced, the maximum capacity speed curve is updated to obtain the train speed curve including multiple sections of coasting conditions. At the same time, calculate the interval running time corresponding to the updated train speed curve, and judge whether the interval running time at this time meets the running time constraint, avoiding many invalid solutions and further improving the solution efficiency of the algorithm.
[0109] Figure 7 is a schematic flowchart of a process for establishing an initial population provided in Embodiment 1 of the present invention. As Figure 7 shown, its specific process includes:
[0110] S3.3.1. Obtain the running time constraint and the coasting point position constraint in the constraint conditions.
[0111] S3.3.2. Generate random solutions according to the coasting point position constraint.
[0112] It should be noted that the random solution refers to: for each sub-process, design a coasting condition and record the coasting start position X i,c0 and the coasting end position X i,c1 of each section of the coasting condition. Among them, the coasting start speed at the coasting start position is the same as the speed at the position X i,c0 in the sub-process, while the coasting end speed at the coasting end position needs to be calculated to determine whether it is the same as the speed of the sub-process at the position X i,c1 .
[0113] S3.3.3. Calculate the coasting end speed according to the corresponding coasting start position and coasting end position in the random solution.
[0114] In the random solution, the speed at the coasting starting position is the same as the speed at that position in the sub-process. When the train is in the coasting condition, the train is only subject to the running resistance, and the acceleration of the train is obtained by the ratio of the running resistance received by the train to the mass of the train. Furthermore, the coasting end speed of the train can be calculated from the coasting starting position X i,c0 , the coasting starting speed, the coasting end position X i,c1 and the train acceleration.
[0115] S3.3.4. Determine whether the coasting end speed is equal to the speed corresponding to that position in the sub-process. If they are equal, execute S3.3.5; if not, execute S3.3.2.
[0116] S3.3.5. Repeat steps S3.3.3 - S3.3.4 to obtain a train speed curve including multiple coasting conditions.
[0117] S3.3.6. Calculate the interval running time T corresponding to the train speed curve.
[0118] S3.3.7. Determine whether the running time constraint is satisfied. If the running time constraint is satisfied, execute step S3.3.8; otherwise, execute step S3.3.2.
[0119] S3.3.8. Take the random solutions that satisfy the running time constraint and the coasting point position constraint as individuals of the initial population and put them into the initial population.
[0120] S3.3.9. Determine whether the number of individuals in the initial population reaches M. If the number of the initial population reaches M, execute step S3.3.10; otherwise, execute step S3.3.2.
[0121] S3.3.10. Generate the initial population.
[0122] In the embodiment of the present invention, a specific process for generating the initial population is proposed to obtain multiple initial individuals that meet the requirements. Furthermore, mutation operations can be performed on the initial individuals to obtain better target individuals.
[0123] S3.4. Design a fitness function and calculate the fitness value of each individual in the initial population.
[0124] Optionally, calculate the energy consumption value of the train speed curve corresponding to each individual, and choose to use the reciprocal of the individual energy consumption value as the fitness function. The fitness function can be expressed as:
[0125] fit = 1 / f(X i,c0 , X i,c1 )
[0126] where fit represents the fitness value of the individual, and f(X i,c0 , Xi,c1 ) represents the energy consumption value of the current individual.
[0127] S3.5. Select individuals using the roulette wheel method according to the fitness value of each individual to obtain a roulette wheel population.
[0128] Specifically, the sum of all individual fitness values is the total area of the roulette wheel, and the fitness value of the corresponding individual is the area it occupies on the roulette wheel. It can be seen that the larger the fitness value of an individual, the larger the area it occupies on the roulette wheel. Similarly, the greater the probability of being selected in the selection, and the more times an individual is selected, the more it can pass on its genes to the next generation.
[0129] S3.6. Perform crossover operations on the individuals in the roulette wheel population using the adaptive crossover method to obtain a crossover population.
[0130] Optionally, single-point crossover can be used to perform crossover operations on two genes X i,c0 and X i,c1 simultaneously to generate new individuals. The mutation probability P c can be expressed as:
[0131]
[0132] where P c represents the crossover probability, fit represents the fitness value of an individual, represents the average fitness value in the population, fitmax represents the maximum fitness in the population, P cmin represents the minimum crossover probability, and P cmax represents the maximum crossover probability. Through adaptive crossover, the crossover probability can be intelligently adjusted according to the optimization process, which can not only improve the convergence speed, but also avoid premature convergence and local optimum problems, thus greatly improving the solution performance of the genetic algorithm.
[0133] S3.7. Perform mutation operations on the individuals in the crossover population using the Gaussian mutation method to obtain a mutation population.
[0134] Optionally, when performing mutation operations, a random number obeying the Gaussian (normal) distribution can be added to the starting position X i,c0 and the ending position X i,c1 of the idle running point respectively. The mutated gene can be expressed as:
[0135] X i ′ ,c0 = X i,c0 + N(μ, σ 2 )
[0136] X i ′ ,c1 = Xi,c1 +N(μ,σ 2 )
[0137] Among them, X i,c0 represents the starting position of the coasting, and X i,c1 represents the ending position of the coasting. σ represents the variance of the normal distribution, and μ represents the mean of the normal distribution. By introducing the normal distribution perturbation in the Gaussian mutation, flexible and fine search can be achieved, dynamically balancing global exploration and local exploitation during the optimization process, preventing premature convergence, and improving the accuracy and diversity of the solutions.
[0138] S3.8. Determine whether the maximum number of iterations gen is reached. If the maximum number of iterations is reached, execute step S3.9; otherwise, continue to execute step S3.4.
[0139] S3.9. When the maximum number of iterations is reached, select the target individuals from the population corresponding at this time, and output the train speed curve corresponding to the target individuals.
[0140] When facing a large-scale and complex search space, the genetic algorithm can quickly find a solution with better performance in a short time through parallel computing and population evolution mechanisms, meeting the timeliness requirements of actual engineering applications.
[0141] Figure 8 is a schematic flow diagram of a method for screening the train speed curve with the lowest traction energy consumption provided in Embodiment 1 of the present invention. As Figure 8 shown, the specific process includes:
[0142] S3.9.1. Calculate the coasting ending speed of any individual according to the starting position and ending position of the coasting of any individual in the population.
[0143] It should be noted that the calculation method is the same as that in the previous text. From the starting position of the coasting X i,c0 , the starting speed of the coasting, the ending position of the coasting X i,c1 and the train acceleration, calculate the coasting ending speed of the vehicle.
[0144] S3.9.2. Determine whether the coasting ending speed at the coasting ending position is equal to the speed corresponding to this position in the sub-process; if they are equal, execute step S3.9.3; otherwise, discard the said any individual.
[0145] S3.9.3. Replace a section of the speed curve in the corresponding sub-process with the speed curve of the coasting condition in any individual to obtain the train speed curve corresponding to any individual.
[0146] S3.9.4. Calculate the interval running time T corresponding to the train speed curve corresponding to any individual.
[0147] S3.9.5. Determine whether the running time T of the interval meets the running time constraint. If it meets the running time constraint, execute step S3.9.6; otherwise, discard any individual.
[0148] S3.9.6. Calculate the train station - to - station traction energy consumption E of the train speed curve corresponding to the target individual.
[0149] Specifically, the traction energy consumption e of the train at the position interval Δx k can be expressed as:
[0150]
[0151] The total running traction energy consumption during the train's station - to - station operation is the sum of the running traction energy consumptions within each position interval. The train's station - to - station traction energy consumption can be expressed as:
[0152]
[0153] where η represents the traction drive efficiency coefficient, μf k represents the action coefficient of the traction force, F max (v k ) represents the traction force, and Δx represents the position interval.
[0154] S3.9.7. Record the train's station - to - station traction energy consumption of each individual, compare the train's station - to - station traction energy consumption of each individual, select the individual with the minimum train's station - to - station traction energy consumption as the target individual, and generate the train speed curve corresponding to the target individual.
[0155] The embodiment of the present invention proposes a method for optimizing the energy - saving of the train speed curve applicable to complex lines, which makes full use of the potential energy and operating conditions of the line, designs an optimization method based on the genetic algorithm, dynamically solves the optimal coasting start and end positions of each sub - process, can significantly reduce the train's traction energy consumption on complex lines, helps to save energy and reduce emissions, and promotes the development of green transportation.
[0156] The embodiment of the present invention can generate an energy - saving speed curve of the train, thereby reducing the train's running traction energy consumption. At the same time, it has good engineering applicability and can be seamlessly integrated into the train's automatic train operation system (ATO) or the ground control center. It is applicable to complex line scenarios such as urban rail transit systems, suburban express lines, and long - distance main - line railways. By optimizing the train operation strategy, the present invention not only improves the economy and comfort of train operation, but also provides key technical support for promoting the greening and intelligent development of rail transit, and has important practical significance for achieving the goal of low - carbon travel.
[0157] Embodiment 2
[0158] Figure 9It is a schematic structural diagram of a train speed curve energy-saving optimization system applicable to complex lines provided by Embodiment 2 of the present invention. As Figure 9 shown, the system includes:
[0159] A sub-process division module 100, configured to obtain a maximum-capability speed curve according to train parameter data and line parameter data; and divide the maximum-capability speed curve into multiple sub-processes in a traction-braking process.
[0160] An optimization model construction module 200, configured to input the maximum-capability speed curve into an energy-saving speed curve optimization model; wherein, the energy-saving speed curve optimization model takes minimizing the traction energy consumption between train stations as an optimization objective, and takes running time constraints, running speed constraints, and coasting point position constraints as constraint conditions.
[0161] An optimization model solving module 300, configured to solve the energy-saving speed curve optimization model through a genetic algorithm to obtain a target individual represented by a current optimal result and a train speed curve corresponding to the target individual; and use the train speed curve corresponding to the target individual as the energy-saving optimized train speed curve.
[0162] Wherein, the target individual converts a section of speed curve in each sub-process into a speed curve in a coasting working condition.
[0163] The technical solution in the embodiment of the present invention can reduce the traction energy consumption of a train on a complex line and achieve the effect of energy conservation and emission reduction.
[0164] Embodiment 3
[0165] Figure 10 It is a schematic structural diagram of an electronic device for implementing the method for optimizing the energy-saving train speed curve applicable to complex lines according to the embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed herein.
[0166] As Figure 10As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0167] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.
[0168] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the train speed curve energy-saving optimization method applicable to complex lines.
[0169] In some embodiments, the train speed curve energy-saving optimization method applicable to complex lines can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the train speed curve energy-saving optimization method applicable to complex lines described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the train speed curve energy-saving optimization method applicable to complex lines by any other appropriate means (e.g., by means of firmware).
[0170] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.
[0171] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
[0172] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0173] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0174] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.
[0175] A computing system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.
[0176] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.
[0177] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.
Claims
1. A train speed curve energy-saving optimization method applicable to complex lines, characterized in that Including: S1. Obtain the maximum capacity speed curve based on train parameter data and line parameter data; Divide the maximum capacity speed curve into multiple sub-processes in the traction-braking process; S2. Input the maximum capacity speed curve into the energy-saving speed curve optimization model; wherein, the energy-saving speed curve optimization model takes minimizing the traction energy consumption between train stations as the optimization objective, and takes operation time constraint, operation speed constraint, and coasting point position constraint as constraint conditions; S3. Solve the energy-saving speed curve optimization model through a genetic algorithm to obtain the target individual represented by the current optimal result and the train speed curve corresponding to the target individual; use the train speed curve corresponding to the target individual as the energy-saving optimized train speed curve.
2. The method according to claim 1, characterized in that, The expression of the optimization objective is: uf k ·ub k = 0, and uf k , ub k ∈ [0, 1] Among them, μf k represents the traction force coefficient, μb k represents the braking force coefficient, F max (v k ) represents the traction force, k represents the discrete points during the train operation. When k = 1, it represents the starting position of the train operation. When k = K, it represents the ending position of the train operation. Δx represents the position interval between adjacent discrete points, and η represents the traction drive efficiency coefficient.
3. The method according to claim 1, characterized in that, Including: The running time constraint is that during the process of the train running from the starting position to the ending position, the running interval time T is less than or equal to the set interval running time T set ; The running speed constraint is as follows: during the process of the train running from the starting position to the ending position, the running speed v of the discrete point k k is greater than or equal to 0 and less than or equal to the line speed limit V corresponding to the train at the position discrete point k k ; and when the train runs to the station K station the running speed is 0; The coasting point position is constrained as follows: the coasting start position X in the i-th coasting condition i,c0 and the coasting end position X i,c1 are both greater than or equal to the traction start position X of the i-th sub-process i,t , and both are less than or equal to the braking end position X of the i-th sub-process i,b .
4. The method according to claim 1, characterized in that S3 Including: S3.
1. Construct individuals of the initial population, each individual consists of two genes encoded by real numbers, and the genes are respectively set as the coasting start position and the coasting end position in the i-th coasting condition; S3.
2. Initialize the size M of the initial population, the maximum number of iterations gen, the minimum value P of the crossover probability cmin , the maximum value P of the crossover probability cmax , the variance σ of the normal distribution, and the mean μ of the normal distribution; S3.
3. Generate M individuals that meet the constraint conditions to complete the establishment of the initial population; S3.
4. Design a fitness function and calculate the fitness value of each individual in the initial population; S3.
5. Select individuals using the roulette wheel method according to the fitness value of each individual to obtain the roulette wheel population; S3.
6. Perform crossover operations on the individuals in the roulette wheel population using the adaptive crossover method to obtain the crossover population; S3.
7. Perform mutation operations on the individuals in the crossover population using the Gaussian mutation method to obtain the mutation population; S3.
8. Determine whether the maximum iteration number gen is reached. If the maximum iteration number is reached, execute step S3.9; otherwise, execute step S3.4; S3.
9. When the maximum iteration number is reached, screen out the target individual from the population corresponding at this time and output the train speed curve corresponding to the target individual.
5. The method according to claim 4, characterized in that, S3.3 includes: S3.3.
1. Obtain the operation time constraint and the coasting point position constraint in the constraint conditions; S3.3.
2. Generate random solutions according to the coasting point position constraint; S3.3.
3. Calculate the coasting end speed according to the corresponding coasting start position and coasting end position in the random solution; S3.3.
4. Determine whether the coasting end speed is equal to the speed corresponding to this position in the sub-process. If they are equal, execute S3.3.5; if not, execute S3.3.2; S3.3.
5. Repeat steps S3.3.3 - S3.3.4 to obtain a train speed curve including multiple coasting conditions; S3.3.
6. Calculate the interval operation time T corresponding to the train speed curve; S3.3.
7. Determine whether the operation time constraint is satisfied. If the operation time constraint is satisfied, execute step S3.3.8; otherwise, execute step S3.3.2; S3.3.
8. Use the random solutions that meet the operation time constraint and the coasting point position constraint as individuals of the initial population and put them into the initial population; S3.3.
9. Determine whether the number of individuals in the initial population reaches M. If the number of the initial population reaches M, execute step S3.3.10; otherwise, execute step S3.3.
2. S3.3.
10. Generate the initial population.
6. The method according to claim 1, wherein S3.9 includes: S3.9.
1. Calculate the coasting end speed of any individual in the population according to the coasting start position and the coasting end position of the individual. S3.9.
2. Determine whether the coasting end speed at the coasting end position is equal to the speed corresponding to this position in the sub-process. If they are equal, execute step S3.9.3; otherwise, discard the individual. S3.9.
3. Replace a section of the speed curve in the corresponding sub-process with the speed curve of the coasting condition in the individual to obtain the train speed curve corresponding to the individual. S3.9.
4. Calculate the interval running time T corresponding to the train speed curve of the individual. S3.9.
5. Determine whether the interval running time T meets the running time constraint. If it meets the running time constraint, execute step S3.9.6; otherwise, discard the individual. S3.9.
6. Calculate the train inter-station traction energy consumption E of the train speed curve corresponding to the individual. S3.9.
7. Record the train inter-station traction energy consumption of each individual, compare the train inter-station traction energy consumption of each individual, select the individual with the minimum train inter-station traction energy consumption as the target individual, and generate the train speed curve corresponding to the target individual.
7. The method according to claim 6, characterized in that, S3.9.6 includes: The traction energy consumption e of the train at a position interval Δx k is expressed as: The train inter-station traction energy consumption can be expressed as: Among them, μf k represents the traction force coefficient, F max (v k ) represents the traction force, k represents the discrete points during the train operation. When k = 1, it represents the starting position of the train operation. When k = K, it represents the ending position of the train operation. Δx represents the position interval between adjacent discrete points, and η represents the traction drive efficiency coefficient.
8. A train speed curve energy-saving optimization system applicable to complex lines, which implements the steps of the method described in any one of claims 1-7, characterized in that, Includes: A sub-process division module, configured to obtain the maximum capacity speed curve according to the train parameter data and the line parameter data. Divide the maximum capacity speed curve into multiple sub-processes in the traction-braking process. An optimization model construction module, configured to input the maximum capacity speed curve into an energy-saving speed curve optimization model. Wherein, the energy-saving speed curve optimization model takes minimizing the train inter-station traction energy consumption as the optimization goal and takes the running time constraint, the running speed constraint, and the coasting point position constraint as the constraint conditions. An optimization model solving module, configured to solve the energy-saving speed curve optimization model through a genetic algorithm to obtain the target individual represented by the current optimal result and the train speed curve corresponding to the target individual; use the train speed curve corresponding to the target individual as the energy-saving optimized train speed curve.
9. An electronic device, characterized in that, Includes: One or more processors; A memory, configured to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the steps in the method according to any one of claims 1 to 7.
10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps in the method according to any one of claims 1 to 7.
Citation Information
Cited By
Bullet train traction / braking curve dynamic generation and control method and system
CN121578668A