Train working diagram peak-valley smooth conversion method, device and equipment and storage medium

Abstract

The invention provides a peak-valley smooth conversion method and device for a train working diagram, electronic equipment and a storage medium. The method comprises the following steps: acquiring an original train working diagram including a peak period and a flat period; identifying peak and average peak conversion time points in the original train working diagram; taking the peak and flat peak conversion time point as a center, carrying out local fine adjustment on the operation line in a preset time range before and after the center, and dynamically adjusting the initial time difference distance between the turning line and the wiring behind the turning line; initializing a sliding window by taking a conversion time point as a reference, and carrying out iterative homogenization on a turn-back section containing the time point and the running time of a front shift and a rear shift; the original train working diagram is optimized based on the adjusted starting time difference distance, the uniformly adjusted turn-back section and the running time of the front and back shifts, the optimized train working diagram is output, peak and flat peak period interval gradual conversion and smooth transition are achieved, the turn-back time of the working diagram is short, too long turn-back time does not exist, the overall train entering and exiting amount is small, and the train running efficiency is improved. And frequent warehouse-in and warehouse-out can be avoided.

Description

Technical Field

[0001] This invention relates to the field of train control technology, and in particular to a method, apparatus, electronic device, and storage medium for smoothing peak-valley transitions in train timetables. Background Technology

[0002] In the field of rail transit operations, train timetables need to be adjusted according to uneven passenger flow. Currently, the common approach is to use denser timetables (closer train intervals) during peak hours and wider intervals during off-peak hours. However, traditional train timetable creation methods based on Mixed-Integer Linear Programming (MILP) and genetic algorithms often result in excessively long train turnaround times during the transition from peak to off-peak periods due to changes in initial intervals. This turnaround delay leads to train depot delays, severely impacting the capacity allocation of subsequent trains. Furthermore, it easily leads to frequent entry and exit of multiple trains from the depot, and these frequent trackside vehicle switching operations significantly increase scheduling complexity and operating costs. Existing train timetables often exhibit discontinuities during the off-peak transition phase, with abrupt changes in the broken line at the point between peak and off-peak periods, causing sudden shifts in passenger load and affecting passenger experience. Summary of the Invention

[0003] This invention provides a method, apparatus, electronic device, and storage medium for smooth transition between peak and off-peak times in train timetables, which solves the problems of low turnaround efficiency, frequent entry and exit from the depot, and discontinuous transition in traditional train timetable compilation technology, resulting in insufficient actual usability of the timetable.

[0004] This invention provides a method for smoothing peak and valley transitions in train timetables, comprising: Obtain the original train timetable, which includes peak and off-peak hours; Identify the peak and off-peak transition times in the original train timetable; Taking the peak and off-peak transition time point as the center, local fine-tuning is carried out on the operating line within a predetermined time range before and after the center, and the starting time difference distance between the turnaround line and its subsequent connection is dynamically adjusted. The sliding window is initialized based on the aforementioned conversion time point, and the running time of the turnaround segment containing that time point is iteratively adjusted with the running time of the preceding and following shifts. The original train timetable is optimized based on the adjusted starting time difference distance and the evened turnaround section and the running time of the preceding and following trains, and the optimized train timetable is output.

[0005] According to the train timetable peak-valley smoothing transition method provided by the present invention, the step of making local fine adjustments to the train lines within a predetermined time range before and after the peak-valley transition time point as the center, and dynamically adjusting the starting time difference distance between the turnaround line and its subsequent connection, includes: Using the aforementioned conversion time point as a reference point, a fine-tuning interval is formed by extending preset time thresholds forward and backward; Within the fine-tuning interval, calculate the starting time difference distance between the current turnaround line and its subsequent connection line; Based on a preset objective function, the initial time difference distance is iteratively adjusted, wherein the objective function is constructed based on the number of trains running and the turnaround time loss. Record the changes in the output value of the objective function after each adjustment, and select the starting time difference distance that optimizes the output value of the objective function to update the running line within the fine-tuning interval.

[0006] According to the train timetable peak-valley smoothing method provided by the present invention, the objective function is: ; Where z is the output value of the objective function, the smaller z is, the higher the overall efficiency, δ is the adjustment weight, and Tran is the number of trains entering and leaving the depot. The sum of the turnaround times of all trains This represents the difference between the actual turnaround time and the standard time for the i-th train. is the weighting coefficient for turnaround time, and n is the total number of turnaround operations that need to be optimized in the train timetable.

[0007] According to the train timetable peak-valley smoothing method provided by the present invention, the turnaround time weighting coefficient is dynamically adjusted according to the running segment, specifically including: Real-time monitoring of passenger flow load characteristics during the current operating period to determine whether it is a peak or off-peak period; The turnaround time weighting coefficient for peak hours is configured to be greater than that for off-peak hours.

[0008] According to the train timetable peak-valley smoothing transition method provided by the present invention, the step of initializing a sliding window based on the transition time point and iteratively adjusting the turnaround section containing that time point and the running time of the preceding and following trains includes: The transition time point is used as the initial center position of the sliding window; Set a sliding window range that includes at least two consecutive shifts, and perform iterative optimization operations within the sliding window range; Move the sliding window forward or backward along the time axis by a predetermined step, and repeat the iterative optimization operation until the entire transition period is covered, to obtain the running time of the turnaround segment and the preceding and following shifts after the adjustment.

[0009] According to the train timetable peak-valley smoothing method provided by the present invention, the step of performing iterative optimization operations within the sliding window range includes: Calculate the time interval for all shifts within the current sliding window; Assess the degree of change in the interval between adjacent trains, and adjust the departure interval of trains within the sliding window with the goal of minimizing the interval change, while keeping the total running time within the sliding window constant.

[0010] According to the train timetable peak-valley smoothing transition method provided by the present invention, adjusting the departure interval of trains within the sliding window with the goal of minimizing interval changes includes: The two adjacent trains before and after the change in the departure interval within the sliding window are calculated and coordinated for adjustment. The quadratic programming method is used to smooth the transition curve of the interval change, keeping the total running time of the trains within the window unchanged before and after the adjustment. Verify whether the adjusted interval between trains meets the minimum safe interval requirement and whether the passenger load change rate exceeds the preset upper limit; Repeat the above steps until the maximum interval change value is reduced to below the preset threshold or the preset maximum number of iterations is reached.

[0011] The present invention also provides a train timetable peak-valley smoothing conversion device, comprising: The acquisition module is used to obtain the original train timetable, which includes peak and off-peak periods; The identification module is used to identify the peak and off-peak transition time points in the original train timetable; The fine-tuning module is used to make local fine-tuning of the operating line within a predetermined time range before and after the peak and off-peak transition time point as the center, and dynamically adjust the starting time difference distance between the turnaround line and its subsequent connection line. The smoothing module is used to initialize a sliding window based on the conversion time point and iteratively smooth the turnaround segment containing that time point and the running time of the preceding and following shifts. The output module is used to optimize the original train timetable based on the adjusted starting time difference distance and the evened turnaround section and the running time of the preceding and following trains, and output the optimized train timetable.

[0012] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the train timetable peak-valley smoothing conversion method as described in any of the preceding claims.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the train timetable peak-valley smoothing conversion method described in any of the preceding claims.

[0014] The present invention provides a method, apparatus, electronic device, and storage medium for smooth transition between peak and off-peak train schedules. This involves: acquiring an original train schedule containing peak and off-peak periods; identifying the peak-to-off-peak transition time points in the original train schedule; making local fine-tuning of the train lines within a predetermined time range before and after the peak-to-off-peak transition time points as the center, dynamically adjusting the initial time difference distance between the turnaround line and its subsequent connection; initializing a sliding window based on the transition time points, iteratively adjusting the turnaround segment and the running times of the preceding and following trains containing that time point; optimizing the original train schedule based on the adjusted initial time difference distance and the adjusted turnaround segment and the running times of the preceding and following trains; and outputting an optimized train schedule. This achieves a gradual and smooth transition between peak and off-peak periods, with shorter turnaround times, no excessively long turnaround times, and fewer overall train entries and exits from the depot, avoiding frequent entries and exits. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0016] Figure 1 This is one of the flowcharts illustrating the peak-valley smoothing method for train operation diagrams provided in this embodiment of the invention; Figure 2 This is the second flowchart illustrating the peak-valley smoothing method for train operation diagrams provided in this embodiment of the invention. Figure 3 This is a schematic diagram of the functional structure of the train timetable peak-valley smoothing conversion device provided in an embodiment of the present invention; Figure 4 This is a functional structure diagram of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0018] Figure 1 A flowchart of the peak-valley smoothing conversion method for train timetables provided in this embodiment of the invention is shown below. Figure 1 As shown, the train timetable peak-valley smoothing conversion method provided in this embodiment of the invention includes: Step 101: Obtain the original train timetable, which includes peak and off-peak periods; Step 102: Identify the peak and off-peak transition time points in the original train timetable; Step 103: Taking the peak and off-peak transition time point as the center, make local fine adjustments to the operating line within the predetermined time range before and after the center, and dynamically adjust the starting time difference distance between the turnaround line and its subsequent connection line. Step 104: Initialize the sliding window based on the conversion time point, and iteratively adjust the turnaround segment containing that time point and the running time of the preceding and following shifts; Step 105: Optimize the original train timetable based on the adjusted starting time difference distance and the evenly adjusted turnaround section and the running time of the preceding and following trains, and output the optimized train timetable.

[0019] Traditional train timetable creation methods based on global mixed-integer linear programming and genetic algorithms often suffer from excessively long train turnaround times during the transition from peak to off-peak periods due to changes in initial intervals. This turnaround delay leads to train depot congestion, severely impacting the capacity allocation of subsequent trains. Furthermore, it easily results in frequent entry and exit of multiple trains from the depot, and these frequent trackside vehicle switching operations significantly increase scheduling complexity and operating costs. Existing train timetables often exhibit discontinuities during the off-peak transition phase, with abrupt changes in the broken line at the point between peak and off-peak periods, causing sudden shifts in passenger load and affecting passenger experience.

[0020] The train timetable peak-valley smoothing transition method provided in this invention involves: acquiring an original train timetable containing peak and off-peak periods; identifying the peak-off-peak transition time points in the original train timetable; using the peak-off-peak transition time points as the center, making local fine adjustments to the running lines within a predetermined time range before and after the center, dynamically adjusting the initial time difference distance between the turnaround line and its subsequent connection; initializing a sliding window based on the transition time points, iteratively adjusting the turnaround segment containing that time point and the running time of the preceding and following trains; optimizing the original train timetable based on the adjusted initial time difference distance and the adjusted turnaround segment and the running time of the preceding and following trains, and outputting an optimized train timetable. This achieves a gradual transition between peak and off-peak periods with smooth transition, a smaller turnaround time in the timetable, no excessively long turnaround time, and fewer overall train entry and exit times, avoiding frequent entry and exit from the depot.

[0021] Based on any of the above embodiments, the method of making local fine-tuning of the operating line within a predetermined time range before and after the peak and off-peak transition time point as the center, and dynamically adjusting the starting time difference distance between the turnaround line and its subsequent connection, includes: Step 201: Using the conversion time point as a reference point, expand the preset time thresholds forward and backward to form a fine-tuning interval; Step 202: Within the fine-tuning interval, calculate the starting time difference distance between the current turnaround line and its subsequent connection line; Step 203: Based on a preset objective function, iteratively adjust the initial time difference distance, wherein the objective function is constructed based on the number of trains running and the turnaround time loss; Step 204: Record the changes in the output value of the objective function after each adjustment, and select the starting time difference distance that makes the output value of the objective function optimal to update the running line within the fine-tuning interval.

[0022] In this embodiment of the invention, the objective function is: ; Where z is the output value of the objective function, the smaller z is, the higher the overall efficiency, δ is the adjustment weight, and Tran is the number of trains entering and leaving the depot. The sum of the turnaround times of all trains This represents the difference between the actual turnaround time and the standard time for the i-th train. is the weighting coefficient for turnaround time, and n is the total number of turnaround operations that need to be optimized in the train timetable.

[0023] In this embodiment of the invention, by constraining the number of trains entering and leaving the depot, automatic matching of trains entering and leaving the depot can be achieved, thereby improving operational efficiency.

[0024] In this embodiment of the invention, the turnaround time weighting coefficient is dynamically adjusted according to the runtime period, specifically including: Real-time monitoring of passenger flow load characteristics during the current operating period to determine whether it is a peak or off-peak period; The turnaround time weighting coefficient for peak hours is configured to be greater than that for off-peak hours.

[0025] Based on any of the above embodiments, the step of initializing the sliding window based on the conversion time point and iteratively adjusting the turnaround segment containing that time point and the running time of the preceding and following shifts includes: Step 301: Use the aforementioned conversion time point as the initial center position of the sliding window; Step 302: Set a sliding window range that includes at least two consecutive shifts, and perform iterative optimization operations within the sliding window range; In this embodiment of the invention, the sliding window size is configurable, and the parameterized window size adapts to different train schedules.

[0026] Step 303: Move the sliding window forward or backward along the time axis by a predetermined step, and repeat the iterative optimization operation until the entire transition period is covered, and obtain the running time of the turnaround segment and the preceding and following shifts after the adjustment.

[0027] In this embodiment of the invention, performing iterative optimization within the sliding window includes: Step 3021: Calculate the running time interval of all shifts within the current sliding window; Step 3022: Assess the degree of change in the interval between adjacent trains, and adjust the departure interval of trains within the sliding window with the goal of minimizing the interval change, so as to keep the total running time within the sliding window constant.

[0028] In this embodiment of the invention, adjusting the departure interval of the trains within the sliding window with the goal of minimizing interval changes includes: The two adjacent trains before and after the change in the departure interval within the sliding window are calculated and coordinated for adjustment. The quadratic programming method is used to smooth the transition curve of the interval change, keeping the total running time of the trains within the window unchanged before and after the adjustment. Verify whether the adjusted interval between trains meets the minimum safe interval requirement and whether the passenger load change rate exceeds the preset upper limit; Repeat the above steps until the maximum interval change value is reduced to below the preset threshold or the preset maximum number of iterations is reached.

[0029] Based on the above embodiments, such as Figure 2 As shown, the train timetable peak-valley smoothing conversion method provided in this embodiment of the invention specifically includes: (1) Obtain a peak / off-peak operation schedule and ensure that the data includes the departure time, arrival time, turnaround time of each train, as well as the peak / off-peak time interval markings and turnaround station scheduling information; (2) Traverse all running lines; (3) Determine whether it is a peak / off-peak transition. The criteria for determination are that the change rate of the departure interval between the previous and next shifts exceeds the set threshold or the time period switching point marked in the dispatch log. (4) Calculate the objective function, which includes the weight of the number of trains and the penalty term for turnaround time. The weight of the number of trains during peak hours is 0.8, and the weight of the number of trains during off-peak hours is 0.3. (5) Try translating the transformation line and the subsequent running line, and recalculate the objective function; (6) Recalculate the objective function value after each translation, and repeat until the translation amount that minimizes the objective function value is found or the maximum number of attempts (10) is reached; (7) Perform interval smoothing operations at the transition points from peak to off-peak and from off-peak to peak through a sliding window.

[0030] (8) Output the smoothed running graph.

[0031] The peak-valley smoothing transition method for train timetables provided in this invention addresses several issues. Firstly, in terms of operational efficiency, this method effectively solves the problem of delayed turnaround in traditional schemes through dynamic objective function optimization and local fine-tuning techniques. This shortens the turnaround time during the transition from peak to off-peak periods, significantly reduces train detaining, and improves overall capacity allocation efficiency. Secondly, in terms of operational cost control, sliding window optimization reduces vehicle scheduling complexity. Actual application data shows a reduction in the number of depot operations, lowering manual scheduling costs and energy consumption. Thirdly, in terms of passenger flow management, a progressive interval adjustment strategy ensures a smooth transition between peak and off-peak periods, reducing sudden changes in passenger load and improving the passenger experience. Compared to traditional global optimization algorithms, this invention employs a local + window combination strategy, balancing efficiency and accuracy, reducing global computation, and ensuring the practicality of the optimization results. The final output timetable satisfies strict operational safety constraints while maintaining timetable consistency.

[0032] The peak-valley smoothing conversion device for train timetables provided by the present invention is described below. The peak-valley smoothing conversion device for train timetables described below can be referred to in correspondence with the peak-valley smoothing conversion method for train timetables described above.

[0033] Figure 3 This is a functional structure diagram of the train timetable peak-valley smoothing conversion device provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the train timetable peak-valley smoothing conversion device provided in this embodiment of the invention includes: The acquisition module 301 is used to acquire the original train timetable, which includes peak and off-peak periods; The identification module 302 is used to identify the peak and off-peak transition time points in the original train timetable; The fine-tuning module 303 is used to make local fine-tuning of the running line within a predetermined time range before and after the peak and off-peak transition time point as the center, and dynamically adjust the starting time difference distance between the turnaround line and its subsequent connection line. The smoothing module 304 is used to initialize a sliding window based on the conversion time point and iteratively smooth the turnaround segment containing that time point and the running time of the preceding and following shifts. Output module 305 is used to optimize the original train timetable based on the adjusted starting time difference distance and the evenly adjusted turnaround section and the running time of the preceding and following trains, and output the optimized train timetable.

[0034] The train timetable peak-valley smoothing transition device provided in this embodiment of the invention acquires an original train timetable containing peak and off-peak periods; identifies the peak-off-peak transition time points in the original train timetable; uses the peak-off-peak transition time points as the center, performs local fine-tuning on the running lines within a predetermined time range before and after the center, dynamically adjusting the initial time difference distance between the turnaround line and its subsequent connection; initializes a sliding window based on the transition time point, iteratively evens out the turnaround segment and the running time of the preceding and following trains containing that time point; optimizes the original train timetable based on the adjusted initial time difference distance and the evenly adjusted turnaround segment and the running time of the preceding and following trains, and outputs an optimized train timetable, achieving a gradual transition between peak and off-peak period intervals, a smooth transition, a small turnaround time in the timetable, no excessively long turnaround time, and a small overall number of trains entering and leaving the depot, avoiding frequent entry and exit from the depot.

[0035] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The memory 430 includes a computer program, an operating system, and acquired data. The processor 410 can call the logical instructions in the memory 430 to execute a train timetable peak-valley smoothing transition method. This method includes: acquiring an original train timetable containing peak and off-peak periods; identifying the peak-off-peak transition time points in the original train timetable; using the peak-off-peak transition time points as the center, making local fine adjustments to the running lines within a predetermined time range before and after the center, and dynamically adjusting the starting time difference distance between the turnaround line and its subsequent connection; initializing a sliding window based on the transition time point, and iteratively smoothing the running time of the turnaround section and the preceding and following trains containing that time point; optimizing the original train timetable based on the adjusted starting time difference distance and the smoothed running time of the turnaround section and the preceding and following trains, and outputting an optimized train timetable.

[0036] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to related technologies, or a portion 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.) to execute all or part of the steps of the methods described in the various embodiments of the present 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.

[0037] On the other hand, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements a method for smoothing peak-valley transitions in train timetables provided by the methods described above. The method includes: acquiring an original train timetable containing peak and off-peak periods; identifying peak-to-off-peak transition time points in the original train timetable; making local fine-tuning adjustments to the running lines within a predetermined time range before and after the peak-to-off-peak transition time points, dynamically adjusting the initial time difference distance between the turnaround line and its subsequent connection; initializing a sliding window based on the transition time point, iteratively adjusting the running times of the turnaround section and the preceding and following trains containing that time point; optimizing the original train timetable based on the adjusted initial time difference distance and the adjusted running times of the turnaround section and the preceding and following trains, and outputting an optimized train timetable.

[0038] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0039] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of software products. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0040] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for smoothing transition between peak and valley of train working diagram, characterized in that, The method comprises the following steps: obtaining an original train diagram containing peak hours and off-peak hours; identifying peak-to-off-peak transition time points in the original train diagram; centering on the peak-to-off-peak transition time points, locally fine-tuning the running lines within a predetermined time range before and after the center, and dynamically adjusting the start time difference distance of the turnaround line and the line connected thereto; initializing a sliding window based on the transition time points, and iteratively adjusting the turnaround section and the running time of the preceding and following trains containing the time points; optimizing the original train diagram based on the adjusted start time difference distance and the adjusted running time of the turnaround section and the preceding and following trains, and outputting an optimized train diagram.

2. The train graph peak valley smoothing transition method of claim 1, wherein, The step of centering on the peak-to-off-peak transition time points, locally fine-tuning the running lines within a predetermined time range before and after the center, and dynamically adjusting the start time difference distance of the turnaround line and the line connected thereto comprises the following steps: taking the transition time points as reference points, and expanding a preset time threshold forward and backward to form a fine-tuning interval; calculating the start time difference distance of the current turnaround line and the line connected thereto within the fine-tuning interval; iteratively adjusting the start time difference distance based on a preset target function, wherein the target function is constructed based on the number of train runs and turnaround time loss; recording the change of the output value of the target function after each adjustment, and selecting the start time difference distance that optimizes the output value of the target function to update the running lines within the fine-tuning interval.

3. The train graph peak valley smoothing transition method of claim 2, wherein, The target function is: ； Wherein, z is the output value of the objective function, the smaller the overall efficiency is higher, δ is the adjustment weight, Tran is the number of warehouse train, is the sum of all train turnaround time, represents the difference between the actual turnaround time of the ith train and the standard time, is the turnaround time weight coefficient, n is the total number of turnaround operations that need to be optimized in the train working diagram.

4. The train graph peak valley smoothing transition method of claim 3, wherein, The turnaround time weight coefficient is dynamically adjusted according to the running period, and specifically comprises the following steps: real-time monitoring of the passenger flow load characteristics of the current running period to determine whether the current period is a peak period or an off-peak period; configuring the turnaround time weight coefficient of the peak period to be greater than the turnaround time weight coefficient of the off-peak period.

5. The method of claim 1, wherein, The step of initializing a sliding window based on the transition time points, and iteratively adjusting the turnaround section and the running time of the preceding and following trains containing the time points comprises the following steps: taking the transition time points as the initial center position of the sliding window; setting a sliding window range containing at least two consecutive trains, and performing an iterative optimization operation within the sliding window range; moving the sliding window forward or backward by a predetermined step along the time axis, and repeatedly performing the iterative optimization operation until all transition periods are covered, to obtain the adjusted turnaround section and the running time of the preceding and following trains.

6. The train graph peak valley smoothing transition method of claim 4, wherein, The step of performing an iterative optimization operation within the sliding window range comprises the following steps: calculating the running time interval of all trains within the current sliding window; evaluating the degree of change of the interval between adjacent trains, adjusting the departure interval of the trains within the sliding window to minimize the interval change, and keeping the total running time within the sliding window unchanged.

7. The train profile peak valley smoothing transition method of claim 6, wherein, The step of adjusting the departure interval of the trains within the sliding window to minimize the interval change comprises the following steps: calculating the coordinated adjustment of the two trains before and after the adjacent train departure interval changes within the sliding window, smoothing the transition interval change curve using a quadratic programming method, and keeping the total running time of the trains within the window unchanged before and after the adjustment; verifying whether the adjusted train interval meets the minimum safety interval requirement and whether the passenger flow load change rate exceeds a preset upper limit; The above steps are repeatedly performed until the maximum interval change value is reduced to below a preset threshold or a preset maximum iteration number is reached.

8. A train diagram peak valley smoothing transition device, characterized by, Comprise: An acquisition module is configured to acquire an original train operation diagram containing peak hours and flat peak hours; An identification module is configured to identify peak and flat peak conversion time points in the original train operation diagram; A fine-tuning module is configured to center on the peak and flat peak conversion time points, and perform local fine-tuning on the running lines within a predetermined time range before and after the center to dynamically adjust the starting time difference distance of the turn-back line and the line connected thereto; A smoothing module is configured to initialize a sliding window based on the conversion time points, and iteratively smooth the turn-back section and the preceding and following train running times containing the time points; An output module is configured to optimize the original train operation diagram based on the adjusted starting time difference distance and the smoothed turn-back section and preceding and following train running times, and output an optimized train operation diagram.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the train operation diagram peak-valley smooth conversion method of any one of claims 1-7 when executing the program.

10. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that, The computer program implements the train operation diagram peak-valley smooth conversion method of any one of claims 1-7 when executed by the processor.

Images