A method for automatically generating a virtual driving speed curve of a high-speed train

Abstract

The present application relates to the technical field of traffic control, and more particularly to a method for automatically generating a virtual driving speed curve of a high-speed train, which is based on the AlphaZero idea, defines a railway scene in a virtual space, simulates a high-speed rail virtual line that has not yet been built, sets constraint conditions of a train driving model in combination with expert experience and dynamics principles, compresses the solution space of the model from infinite to a limited range, and automatically generates a large number of virtual driving speed curves of the high-speed train that conform to the real laws and can break through the existing speed, space and natural condition limitations by using big data technology. Then, performance indicators of the train driving speed curve are defined for statistical analysis, and a certain amount of curves with excellent performance are selected from a large number of virtual curves. The present application provides expandable, exhaustive, accurate and selectable virtual driving speed curves of the high-speed train, and can solve the problem that the train driving data cannot be obtained for the high-speed rail that has not yet been built, and provides high-quality virtual data for the automatic driving research of the high-speed rail.

Description

Technical Field

[0001] This invention relates to the field of traffic control technology, and in particular to a method for automatically generating virtual driving speed curves for high-speed trains. Background Technology

[0002] Automatic driving technology is crucial for the operation and control of high-speed trains. Theoretical research on this technology before the high-speed rail lines are built is of paramount importance. High-speed train driving data is fundamental to automatic driving research, but real-world high-speed train driving data cannot be collected for lines that are not yet under construction.

[0003] Currently, the collection of high-speed train driving data mainly relies on onboard sensors or manual recording. In practice, this presents challenges such as difficulty in data acquisition, long collection cycles, high safety risks, and significant challenges in data protection. Furthermore, the costs associated with collection equipment, manpower, data storage and processing, maintenance, and other risks are high. In addition, the actual amount of train driving data collected is relatively small compared to data from other fields, and it is constrained by natural conditions, making it difficult to obtain driving data under all possible environments, resulting in a relatively limited data type.

[0004] In summary, how to solve the problems of long data acquisition cycles, high costs, and limited data volume in actual high-speed trains, and how to obtain driving data for high-speed train control research, are urgent problems that need to be solved by those skilled in the art. Summary of the Invention

[0005] To address the aforementioned problems, this invention provides an automatic generation method for virtual driving speed curves of high-speed trains. This method does not rely on actual data, but leverages the scalability of virtual space and big data technology. By filtering based on conditions, a certain amount of high-quality virtual data is extracted from a large amount of virtual data, providing a new solution for obtaining train driving data for high-speed rail lines that have not yet been built.

[0006] To achieve the above-mentioned technical objectives, the technical solution adopted by this invention is as follows:

[0007] A method for automatically generating virtual driving speed curves for high-speed trains includes the following steps:

[0008] S1: Construct a virtual high-speed rail line feature model in virtual space;

[0009] S2: Build a high-speed train driving model, set the constraints of the model, determine the boundary state of the virtual driving speed curve of the high-speed train, and obtain a single virtual driving speed curve.

[0010] S3: Utilize big data technology to generate a large number of virtual driving speed curves for high-speed trains;

[0011] S4: Set the evaluation index for the virtual driving speed curve of high-speed trains;

[0012] S5: Perform statistical analysis on all virtual driving speed curves of high-speed trains, and select the virtual driving speed curves with excellent performance based on performance evaluation indicators.

[0013] Furthermore, the characteristic model of the high-speed rail virtual line is as follows:

[0014]

[0015] Where P represents the high-speed train driving intelligent agent; λ i This represents dividing the train line into i segments; E is a multivariate virtual scene integration; ε represents the natural factors affecting train operation, including weather, temperature, and wind; the function integrate() integrates the line segments, virtual scene, and natural factors. These represent the sets of straight road scenes, curved road scenes, ramp scenes, tunnel scenes, and viaduct scenes, respectively, distributed sequentially in the i-th segment of the line; merge() will merge S i C i ,R i ,T i V i To integrate multiple scenarios.

[0016] Furthermore, in S2, the high-speed rail virtual line is divided into several sub-segments, and corresponding speed and acceleration limit intervals are set for each segment. Based on the principle of dynamics, the two boundary states of the virtual driving speed curve are determined, and a single train driving curve is generated.

[0017] Furthermore, the specific method for generating a single train driving curve in S2 includes the following steps:

[0018] S21: The train departs from the initial point p begin Starting from the point, it undergoes uniformly accelerated motion with acceleration a1 in the segment i=1, where... The distance traveled by the train during its uniformly accelerated motion at time j is expressed as:

[0019] S22: After the speed change time The saturation velocity v1 is reached after seconds, where The distance traveled by the train at constant speed at time j is expressed as: At this point, loc1 is the speed change cutoff point of the train's driving curve in the i=1 section;

[0020] S23: The train then travels at a constant speed of v1 to the section boundary point p1. The constant speed travel time during this stage is...

[0021] S24: Repeat S21-S23 in the subsequent i≤n segments;

[0022] When the train arrives at the nearest station p near At that time, the train accelerated at a n It undergoes uniformly accelerated motion, in which The train's final instantaneous speed is 0, meaning it has reached the final destination, station p. end The total travel time of the train is Where T total This represents the total duration of the train's virtual driving curve operation. This indicates the train's speed change time in the i-th section; This represents the travel time of the train at a constant speed in the i-th segment.

[0023] Furthermore, S3 utilizes big data technology to generate a large number of virtual driving speed curves for high-speed trains, as detailed below:

[0024] Each driving section has a corresponding acceleration limit zone. and speed limit range Select the distribution frequency μ respectively a ,μ v Divide the intervals into restricted intervals such that the probabilities of choosing acceleration a and velocity v in each interval are respectively Then a single segment has μ a ×μ v For various curve scenarios, multiplying each segment together will automatically generate the curve. A complete virtual driving curve for high-speed trains.

[0025] Furthermore, the evaluation indicators for the virtual driving speed curve of high-speed trains set in S4 include:

[0026] 1) Train driving energy consumption EC train The expression is as follows:

[0027]

[0028]

[0029] Where: EC train Energy consumption kJ / (t·km); V avg X is the average speed within the i-th running segment; i Let be the distance of the i-th operating segment; K and C represent preset coefficients related to the train; ΔX i t represents the length of the i-th running segment; var t represents the speed change time for the i-th segment; uni Let be the uniform speed time of the i-th segment;

[0030] 2) Passenger comfort δ comfort The expression is as follows:

[0031]

[0032] In the formula: Δ|a| represents the change in acceleration in the i-th segment;

[0033] 3) Curve performance ξ curve

[0034] First, the energy consumption EC train and comfort δ comfort Normalization is performed separately; the normalization expression is as follows:

[0035]

[0036] In the formula: x * is the normalized index value, x is the index value before normalization, is the minimum index value, and is the maximum index value.

[0037] Next, the curve contained in each second of the train's running time is assigned to EC. train and δ comfort The performance of the evaluation curve is weighted by 50% each, and the expression is as follows:

[0038]

[0039] Where, ξ curve This represents a quantified index capable of evaluating driving curve performance; T = t0,...,t n Indicates the range of total train travel time;

[0040] Finally, the optimal train driving curve can be selected at each running time.

[0041] Furthermore, the specific steps for S5 are as follows:

[0042] Statistical analysis was performed on the generated virtual driving speed curves of high-speed trains to determine the range covered by the train's running time. The time span is ΔT number The number of curves contained within each second is counted to obtain ΔT. number The virtual driving speed curve of the train is based on the curve performance index ξ. curve By comprehensively evaluating the performance of each set of curves, the best-performing curve for each second is extracted, and finally, ΔT is selected. number A virtual driving speed curve for a high-speed train.

[0043] Preferably, each high-speed train virtual driving speed curve is tracked in real time with a sampling interval of 0.1 seconds.

[0044] Based on the above, the present invention also provides a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, at least one program, code set, or instruction set is loaded and executed by a processor to implement the above-described method for automatically generating virtual driving speed curves for high-speed trains.

[0045] By adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art:

[0046] 1) Compared with the prior art, the automatic generation method of a large number of virtual driving speed curves of high-speed trains in this invention is based on the AlphaZero concept. It does not rely on real data, but customizes virtual routes, sets section constraints, and uses big data technology to automatically generate a large number of virtual driving speed curves of high-speed trains. This provides a universal, low-cost and high-efficiency way to obtain driving data of high-speed trains on high-speed rail lines that have not yet been built.

[0047] 2) This invention generates a large number of virtual driving speed curves for high-speed trains, and selects a certain number of curves with excellent performance by setting evaluation indicators. This method of selecting the best among the best helps to improve the performance of virtual curves.

[0048] 3) Each high-speed train virtual driving speed curve is tracked in real time with a sampling interval of 0.1 seconds, which helps to improve the accuracy of the curve. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0050] Figure 1 This is a flowchart of the method for generating virtual driving speed curves for high-speed trains according to the present invention.

[0051] Figure 2 It is a schematic diagram of the virtual driving speed curve of a high-speed train constrained by expert experience and dynamic principles.

[0052] Figure 3 This is a histogram of the running time distribution of the virtual driving speed curve of the high-speed train generated by the present invention in Example 1.

[0053] Figure 4 Example 1 uses a certain number of high-speed train virtual driving speed curves selected by the present invention.

[0054] Figure 5 This is the running time distribution histogram of the high-speed train virtual driving speed curve generated by the present invention in Example 2.

[0055] Figure 6Example 2 uses a certain number of high-speed train virtual driving speed curves selected by the present invention. Detailed Implementation

[0056] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be particularly noted that the following embodiments are for illustrative purposes only and do not limit the scope of the invention. Similarly, the following embodiments are only some, not all, embodiments of the present invention, and all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] See attached document Figure 1-2 As shown, this invention provides a method for automatically generating virtual driving speed curves for high-speed trains, comprising the following steps:

[0058] S1: Combine and integrate conventional scenes and natural conditions in virtual space to build a feature model of a virtual high-speed rail line; the feature model of the virtual high-speed rail line is as follows:

[0059]

[0060] Where P represents the high-speed train driving intelligent agent; λ i This represents dividing the train line into i segments; E is a multivariate virtual scene integration; ε represents the natural factors affecting train operation, including weather, temperature, and wind; the function integrate() integrates the line segments, virtual scene, and natural factors. These represent the sets of straight road scenes, curved road scenes, ramp scenes, tunnel scenes, and viaduct scenes, respectively, distributed sequentially in the i-th segment of the line; merge() will merge S i C i ,R i ,T i V i To integrate multiple scenarios.

[0061] S2: Based on expert experience, the high-speed rail virtual line is divided into several sub-segments. Corresponding speed and acceleration limit intervals are set for each segment. The two boundary states of the virtual driving speed curve are determined according to dynamic principles, generating a single train driving curve. The specific method for generating a single train driving curve includes the following steps:

[0062] S21: The train departs from the initial point p begin Starting from the point, it undergoes uniformly accelerated motion with acceleration a1 in the segment i=1, where... The distance traveled by the train during its uniformly accelerated motion at time j is expressed as:

[0063] S22: After the speed change time The saturation velocity v1 is reached after seconds, where The distance traveled by the train at constant speed at time j is expressed as: At this point, loc1 is the speed change cutoff point of the train's driving curve in the i=1 section;

[0064] S23: The train then travels at a constant speed of v1 to the section boundary point p1. The constant speed travel time during this stage is...

[0065] S24: Repeat S21-S23 in the subsequent i≤n segments;

[0066] When the train arrives at the nearest station p near At that time, the train accelerated at a n It undergoes uniformly accelerated motion, in which The train's final instantaneous speed is 0, meaning it has reached the final destination, station p. end The total travel time of the train is Where T total This represents the total duration of the train's virtual driving curve operation. This indicates the train's speed change time in the i-th section; This represents the travel time of the train at a constant speed in the i-th segment.

[0067] S3: Utilize big data technology to generate a large number of virtual driving speed curves for high-speed trains, as detailed below:

[0068] Each driving section has a corresponding acceleration limit zone. and speed limit range Select the distribution frequency μ respectively a ,μ v Divide the intervals into restricted intervals such that the probabilities of choosing acceleration a and velocity v in each interval are respectively Then a single segment has μ a ×μ v For various curve scenarios, multiplying each segment together will automatically generate the curve. A complete virtual driving curve for high-speed trains.

[0069] S4: Evaluation metrics for setting the virtual driving speed curve of high-speed trains; including:

[0070] 1) Train driving energy consumption EC train The expression is as follows:

[0071]

[0072]

[0073] Where: EC train Energy consumption kJ / (t·km); Vavg X is the average speed within the i-th running segment; i ΔX represents the distance of the i-th operating segment; K and C represent preset coefficients related to the train, which are empirical values; ΔX i t represents the length of the i-th running segment; var t represents the speed change time for the i-th segment; uni Let be the uniform speed time of the i-th segment;

[0074] 2) Passenger comfort δ comfort The expression is as follows:

[0075]

[0076] In the formula: Δ|a| represents the change in acceleration in the i-th segment;

[0077] 3) Curve performance ξ curve

[0078] To avoid EC train and δ comfort Due to its own scale, the energy consumption EC will be considered first. train and comfort δ comfort Normalization is performed separately; the normalization expression is as follows:

[0079]

[0080] In the formula: x * is the normalized index value, x is the index value before normalization, is the minimum index value, and is the maximum index value.

[0081] Next, the curve contained in each second of the train's running time is assigned to EC. train and δ comfort The performance of the evaluation curve is weighted by 50% each, and the expression is as follows;

[0082]

[0083] Where, ξ curve This represents a quantified index capable of evaluating driving curve performance; T = t0,...,t n Indicates the range of total train travel time;

[0084] Finally, the optimal train driving curve can be selected at each running time.

[0085] S5: Perform statistical analysis on all virtual driving speed curves of high-speed trains, and select the virtual driving speed curves with excellent performance based on performance evaluation indicators, as detailed below:

[0086] Statistical analysis was performed on the generated virtual driving speed curves of high-speed trains to determine the range covered by the train's running time. The time span is ΔT number The number of curves contained within each second is counted to obtain ΔT. number The virtual driving speed curve of the train is based on the curve performance index ξ. curve By comprehensively evaluating the performance of each set of curves, the best-performing curve for each second is extracted, and finally, ΔT is selected. number A virtual driving speed curve for a high-speed train.

[0087] Each of the aforementioned high-speed train virtual driving speed curves is tracked in real time with a sampling interval of 0.1 seconds, which helps to improve the accuracy of the curves.

[0088] Example 1

[0089] To demonstrate the effectiveness of this method, this embodiment designs a CRH3 train with a maximum operating speed of 300 km / h, considering a long-distance cross-sea railway with a starting point to ending point distance of 150 km. The driving model of the high-speed train, which is not yet built, is defined as follows:

[0090]

[0091] Based on expert experience, the line is divided into 5 sections. The overall design of the line is mainly straight, so straight road scenes are distributed in all five sections. Curved scenes are mainly distributed at the starting station and the terminal station (i.e., sections 1 and 5). The undersea tunnel scene is set in section 3. The undersea tunnel in and out of section 3 is connected by ramp scenes. At the same time, ramp scenes are also distributed in sections 1 and 5, corresponding to the area near the starting station and the area near the terminal station when the train leaves and enters the area near the terminal station, respectively. The viaduct scenes are distributed in sections 1, 2, 4, and 5. As the main way for trains to travel on the sea, the parameters of the high-speed train driving model are shown in Table 1.

[0092] Table 1: Parameter Information of High-Speed ​​Train Driving Model

[0093]

[0094] At this point, the distribution frequency μ of the acceleration is set. a =3, then the acceleration interval is divided into three equal parts for selection, and the velocity distribution frequency μ is set. v =4, then the speed interval is divided into four equal parts for selection, n is set to 5, according to The calculation can generate a total of 746,496 virtual driving speed curves for high-speed trains, such as... Figure 3The running time distribution of all virtual driving speed curves was statistically analyzed. The shortest running time was 2271 seconds (approximately 37.9 minutes), and the longest running time was 2963 seconds (approximately 49.4 minutes).

[0095] Furthermore, the generated virtual driving speed curves were grouped according to running time. Each second contained a large number of curves, and filtering conditions were set to extract the curves with the best performance in each group. Based on expert experience, the train constants K = 0.0247 and C = 15.562 were set. It can calculate the energy consumption of each virtual driving speed curve. According to... The comfort level of each virtual driving speed curve can be calculated, and then the energy consumption and comfort level can be processed separately. Perform normalization processing, using Calculate the combined score of all virtual driving speed curves in the same time group.

[0096] like Figure 4 Table 2 shows the performance analysis results of the virtual driving speed curves of the high-speed train before and after screening. In this example, a total of 746,496 virtual driving speed curves of the high-speed train were generated, with a running time range of 2594 seconds to 3321 seconds, containing 728 time points. Finally, 728 virtual curves with the best performance within their respective groups were selected, representing a selection rate of 0.1%. In the analysis of average energy consumption and average comfort, the overall train energy consumption of the selected curves decreased by 0.9% compared to the unselected curves, and the overall comfort was optimized by 33.3%, indicating that the performance of the selected curves is superior to that of the unselected curves.

[0097] Table 2: Results of Screening Virtual Driving Speed ​​Curves for High-Speed ​​Trains

[0098]

[0099] Example 2

[0100] To demonstrate the effectiveness of this method, this example uses a CRH3 train with a maximum operating speed of 350 km / h and considers a long-distance cross-sea railway with a distance of 150 km from the starting point to the destination. The driving model of the high-speed train, which is not yet built, is defined as follows:

[0101]

[0102] Based on expert experience, the line was divided into five sections, with straight sections distributed throughout. Unlike Example 1, considering the harsh natural conditions at sea, the viaduct was designed with a streamlined shape and a certain radius of curvature to enhance its wind resistance. Therefore, viaduct and curve scenarios are distributed in sections 1, 2, 3, and 5, with deceleration implemented in section 2. The undersea tunnel scenario is located in section 4, serving as the main part of the train's high-speed operation. Ramps connect the undersea tunnel and the beginning and end of stations, and are located in sections 1, 3, and 5. The parameters of the high-speed train driving model are shown in Table 3.

[0103] Table 3: Parameter Information of High-Speed ​​Train Driving Model

[0104]

[0105] At this point, the distribution frequency μ of the acceleration is set. a =4, then the acceleration interval is divided into three equal parts for selection, and the velocity distribution frequency μ is set. v =4, then the speed interval is divided into four equal parts for selection, n is set to 5, according to The calculation can generate a total of 4,194,304 virtual driving speed curves for high-speed trains, such as... Figure 5 The running time distribution of all virtual driving speed curves was statistically analyzed. The shortest running time was 1875 seconds (about 31.3 minutes), and the longest running time was 2553 seconds (about 42.6 minutes).

[0106] Furthermore, the generated virtual driving speed curves were grouped according to running time. Each second contained a large number of curves, and filtering conditions were set to extract the curves with the best performance in each group. Based on expert experience, the train constants K = 0.0247 and C = 15.562 were set. It can calculate the energy consumption of each virtual driving speed curve. According to... The comfort level of each virtual driving speed curve can be calculated, and then the energy consumption and comfort level can be processed separately. Perform normalization processing, using Calculate the combined score of all virtual driving speed curves in the same time group.

[0107] like Figure 6The results of the performance analysis of the virtual driving speed curves of the high-speed train before and after screening are shown in Table 4. In this example, a total of 746,496 virtual driving speed curves of the high-speed train were generated, with a running time range of 1875 seconds to 2553 seconds, containing 679 time points. Finally, 679 virtual curves with the best performance within their respective groups were selected, representing a selection rate of 0.02%. In the analysis of average energy consumption and average comfort, the selected curves showed a 2.2% reduction in overall train energy consumption and a 30.3% improvement in overall comfort compared to the unselected curves, indicating that the performance of the selected curves is superior to that of the unselected curves.

[0108] Table 4: Results of Screening Virtual Driving Speed ​​Curves for High-Speed ​​Trains

[0109]

[0110] This invention, based on the AlphaZero concept, defines a custom railway scenario in virtual space, simulating a virtual high-speed rail line that is not yet built. It combines expert experience and dynamic principles to set constraints for the train driving model, compressing the solution space from infinitely large to a finite range. Utilizing big data technology, it automatically generates a massive amount of virtual high-speed train driving speed curves that conform to real-world laws and can overcome existing speed, space, and natural condition limitations. Performance indicators for these train driving speed curves are then redefined and statistically analyzed, selecting a certain number of high-performance curves from the large number of virtual curves. This invention provides scalable, traversable, accurate, and selectable virtual high-speed train driving speed curves, solving the problem of not being able to obtain train driving data for high-speed rail lines that are not yet built, and providing high-quality virtual data for high-speed rail automatic driving research.

[0111] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0112] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0113] The contents not described in detail in this specification are existing technologies known to those skilled in the art.

[0114] The above description is only a part of the embodiments of the present invention and does not limit the scope of protection of the present invention. Any equivalent device or equivalent process transformation made based on the content of the present invention specification and drawings, or direct or indirect application in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for automatically generating virtual driving speed curves for high-speed trains, characterized in that, Includes the following steps: S1: Construct a virtual high-speed rail line feature model in virtual space; the virtual high-speed rail line feature model is as follows: （1） in, For high-speed train driving intelligent agents; Representatives divided the train lines into Each section; It is a multivariable virtual scene integration body; Represents natural factors affecting train operation, including weather, temperature, and wind; function. Integrate railway line sections, virtual scenes, and natural factors; These represent straight road scenes, curve scenes, slope scenes, tunnel scenes, and viaduct scenes, respectively, distributed sequentially along the line. The set of segments; Will To integrate multiple scenarios; S2: Build a high-speed train driving model and set the constraints of the model. Determine the boundary state of the virtual driving speed curve of the high-speed train and obtain a single virtual driving speed curve. Divide the high-speed rail virtual line into several sub-segments, set corresponding speed and acceleration limit intervals for each segment, determine the two boundary states of the virtual driving speed curve according to the dynamics principle, and generate a single train driving curve. S3: Utilize big data technology to generate a large number of virtual driving speed curves for high-speed trains, as detailed below: Each driving section has a corresponding acceleration limit zone. and speed limit range Select distribution frequencies respectively Divide the restricted intervals so that the acceleration is within each interval. With speed The probabilities of selection are respectively Then a single segment exists For various curve scenarios, multiplying each segment together will automatically generate the curve. A complete virtual driving curve for high-speed trains; S4: Set the evaluation indicators for the virtual driving speed curve of high-speed trains, including: 1) Train driving energy consumption The expression is as follows: （2） （3） In the formula: Energy consumption is expressed in kJ / (t·km); For the first Average speed within each operating segment; For the first The distance between each operating segment; and This indicates the preset coefficients related to the train; Represented as the first Length of each operating segment; For the first The speed change time of each section; For the first The uniform speed time of each segment; 2) Passenger comfort The expression is as follows: （4） In the formula: Indicates the first The change in acceleration of the section; 3) Curve performance First, the energy consumption and comfort Normalization is performed separately; the normalization expression is as follows: （5） In the formula: Here, x represents the normalized index value, and x represents the index value before normalization. min x is the minimum value of the indicator. max This represents the maximum value of the indicator. Next, the curve contained in each second of the train's running time is assigned... and The performance of the evaluation curve is weighted by 50% each, and the expression is as follows; （6） in, This represents a quantified indicator that can evaluate driving curve performance. Indicates the range of total train travel time; Finally, the optimal train driving curve can be selected at each running time. S5: Perform statistical analysis on all virtual driving speed curves of high-speed trains, and select the virtual driving speed curves with excellent performance based on performance evaluation indicators.

2. The method for automatically generating virtual driving speed curves for high-speed trains according to claim 1, characterized in that, The specific method for generating a single train driving curve in S2 includes the following steps: S21: The train departs from the starting point Departure, at Section with acceleration It undergoes uniformly accelerated motion, in which In the The distance traveled by the train in uniformly accelerated motion at any given time is expressed as: ; S22: After the speed change time The saturation speed of the segment will be reached in seconds. ,in ,at this time For the driving curve of this train in The gear shift cutoff point of the section; S23: Then the train... Drive at a constant speed to the section boundary point The constant speed running time during this stage is ; S24: In the following The section repeats from S21 to S23; When the train arrives at the nearest station At that time, the train accelerated. It undergoes uniformly accelerated motion, in which The train eventually reaches a speed of 0, indicating that it has arrived at its final destination. The total travel time of the train is ,in This represents the total duration of the train's virtual driving curve operation. Indicates the first Train speed change operation time within the section; Indicates the first The travel time of a train traveling at a constant speed within a section.

3. The method for automatically generating virtual driving speed curves for high-speed trains according to claim 1, characterized in that, The specific steps for S5 are as follows: Statistical analysis was performed on the generated virtual driving speed curves of high-speed trains to determine the range covered by the train's running time. The time span is The number of curves contained within each second of time is counted, thus obtaining... The virtual driving speed curve of the train is based on the performance indicators of the curve. By comprehensively evaluating the performance of each set of curves, the best-performing curve for each second is extracted, and finally, the best-performing curve is selected. A virtual driving speed curve for a high-speed train.

4. The method for automatically generating virtual driving speed curves for high-speed trains according to claim 1, characterized in that, Each high-speed train virtual driving speed curve is tracked in real time with a sampling interval of 0.1 seconds.

5. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, at least one program, code set, or instruction set is loaded and executed by a processor to implement the automatic generation method for high-speed train virtual driving speed curve as described in any one of claims 1 to 4.

Images