Large marshalling heavy haul train simulation system, method, device, medium and product

Abstract

The invention relates to the technical field of heavy-load trains, in particular to a simulation system, method, equipment, medium and product for a long marshalling heavy-load train, and the system comprises a traction simulation subsystem which is used for inputting train operation data into a preset traction characteristic curve to obtain a train traction force; the braking simulation subsystem is used for inputting the train operation data into a pre-constructed braking establishment process simulation model to obtain a train braking force; the longitudinal simulation subsystem is used for inputting the marshalling conditions into a pre-constructed buffer simulation model to obtain train coupler force; the decision optimization subsystem is used for obtaining a control command of the train based on the train operation data, the marshalling condition, the train traction force, the train braking force, the train coupler force and an optimization strategy; and the operation of the long and large marshalling heavy haul train can be simulated.

Description

Technical Field

[0001] The present invention relates to the technical field of heavy-haul trains, and particularly to a simulation system, method, device, medium and product for long-formation heavy-haul trains. Background Art

[0002] Heavy-haul trains can significantly improve the efficiency and capacity of freight transportation, reduce logistics costs, reduce dependence on road transportation, thus alleviating road traffic congestion, reducing carbon emissions, and promoting sustainable economic development, playing an important role in transportation. Therefore, it is of great significance to simulate heavy-haul train transportation to improve its safety and efficiency. For the simulation of long-formation heavy-haul trains and their protection strategies under various working conditions, the relevant simulation platforms cannot be completed.

[0003] There is a technical problem in the art of how to simulate the operation of long-formation heavy-haul trains. Summary of the Invention

[0004] The present invention provides a simulation system, method, device, medium and product for long-formation heavy-haul trains, solving the technical problem of how to simulate the operation of long-formation heavy-haul trains.

[0005] In a first aspect, the present invention provides a simulation system for long-formation heavy-haul trains, the system comprising: a traction simulation subsystem for inputting train operation data into a preset traction characteristic curve to obtain train traction force; a braking simulation subsystem for inputting train operation data into a pre-constructed braking establishment process simulation model to obtain train braking force; a longitudinal simulation subsystem for inputting formation conditions into a pre-constructed buffer simulation model to obtain train coupler force; and a decision optimization subsystem for obtaining a control command for the train based on train operation data, formation conditions, train traction force, train braking force, train coupler force, and an optimization strategy.

[0006] In some embodiments, in the traction simulation subsystem, inputting train operation data into a preset traction characteristic curve to obtain train traction force includes: calculating adhesion traction force based on train mass, adhesion coefficient, and gravitational acceleration, and correcting the train traction force based on the adhesion traction force.

[0007] In some embodiments, in the traction simulation subsystem, calculating adhesion traction force based on train mass, adhesion coefficient, and gravitational acceleration includes: taking the product of train mass, adhesion coefficient, and gravitational acceleration as the adhesion traction force.

[0008] In some embodiments, in the braking simulation subsystem, pre-constructing a braking establishment process simulation model includes: substituting expert knowledge and test data into a preset machine learning algorithm to construct an air braking establishment process model.

[0009] In some embodiments, in the braking simulation subsystem, the air braking establishment process model includes a braking valve action condition model, and the braking valve action condition model includes obtaining the acting impedance of the braking valve, including: obtaining the difference between the pressure reduction speed on the train pipe side of the main piston and the pressure reduction speed on the slide valve chamber side of the main piston; taking the product of the action time of the braking valve, the acting area of the main piston, and the difference as the acting impedance of the braking valve.

[0010] In some embodiments, in the longitudinal simulation subsystem, a buffer simulation model is constructed, including: obtaining the product of the elastomer stiffness and the buffer stroke; obtaining the product of the damping coefficient and the stroke change rate; summing the product of the elastomer stiffness and the buffer stroke and the product of the damping coefficient and the stroke change rate to obtain the coupler force.

[0011] In a second aspect, the present invention provides a simulation method for a long and heavy-haul train, the method including: S100, obtaining train operation data, line conditions, and formation conditions; S200, inputting the train operation data, line conditions, and formation conditions into a pre-constructed long and heavy-haul train simulation system to obtain the train state; S300, optimizing the train state based on a preset optimization strategy to obtain the control command of the train.

[0012] In a third aspect, the present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory, and the processor executes the computer program to implement the steps of the above-mentioned simulation method for a long and heavy-haul train.

[0013] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned simulation method for a long and heavy-haul train are implemented.

[0014] In a fifth aspect, the present invention provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned simulation method for a long and heavy-haul train are implemented.

[0015] The present invention provides a simulation system, method, device, medium, and product for a long and heavy-haul train. The system includes: a traction simulation subsystem, configured to input train operation data into a preset traction characteristic curve to obtain the train traction force; a braking simulation subsystem, configured to input train operation data into a pre-constructed braking establishment process simulation model to obtain the train braking force; a longitudinal simulation subsystem, configured to input formation conditions into a pre-constructed buffer simulation model to obtain the train coupler force; a decision-making optimization subsystem, configured to obtain the control command of the train based on train operation data, formation conditions, train traction force, train braking force, train coupler force, and an optimization strategy; and capable of simulating the operation of a long and heavy-haul train. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be described in more detail below based on embodiments with reference to the accompanying drawings:

[0017] Figure 1 A schematic structural diagram of a long-formation heavy-haul train operation simulation platform provided by an embodiment of the present invention;

[0018] Figure 2 A schematic flow diagram of a long-formation heavy-haul train operation simulation method provided by an embodiment of the present invention;

[0019] Figure 3 A schematic diagram of a long-formation heavy-haul train operation simulation provided by an application example of the present invention.

[0020] In the accompanying drawings, the same components are denoted by the same reference numerals, and the drawings are not drawn to actual scale. Detailed implementation manners

[0021] In order to enable those skilled in the art to better understand the solution of the present invention, and to fully understand how the present invention uses technical means to solve technical problems and the implementation process of achieving corresponding technical effects for implementation, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. The embodiments of the present invention and each feature in the embodiments can be combined with each other without conflict, and the formed technical solutions are all within the protection scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned accompanying drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0023] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0024] Heavy-haul trains can significantly improve the efficiency and capacity of freight transportation, reduce logistics costs, reduce dependence on road transportation, thereby alleviating road traffic congestion, reducing carbon emissions, and promoting sustainable economic development, playing an important role in transportation. Therefore, it is of great significance to simulate heavy-haul train transportation to improve its safety and efficiency. For the simulation of long-haul heavy-haul trains and their protection strategies under various working conditions, the relevant simulation platforms cannot complete it. There is a technical problem in the field of how to simulate the operation of long-haul heavy-haul trains.

[0025] To solve the above technical problem of how to simulate the operation of long-haul heavy-haul trains, the present invention proposes a long-haul heavy-haul train simulation system, method, device, medium and product. The following specifically describes the implementation details of the present invention. The following content is only implementation details provided for convenient understanding and is not necessary for implementing this solution.

[0026] Example 1

[0027] Figure 1 The structural schematic diagram of a long-haul heavy-haul train operation simulation platform provided by an embodiment of the present invention is as Figure 1 shown. In the technical solution of this embodiment, a long-haul heavy-haul train simulation system is provided. The system includes: a traction simulation subsystem for inputting train operation data into a preset traction characteristic curve to obtain train traction force; a braking simulation subsystem for inputting train operation data into a pre-constructed braking establishment process simulation model to obtain train braking force; a longitudinal simulation subsystem for inputting formation conditions into a pre-constructed buffer simulation model to obtain train coupler force; a decision-making optimization subsystem for obtaining a control command for the train based on train operation data, formation conditions, train traction force, train braking force, train coupler force, and an optimization strategy.

[0028] During the operation of long-haul heavy-haul trains, there are many defects in the relevant simulation platforms. For example, most of them are oriented towards 10,000-ton heavy-haul trains, and do not fully consider the operating lines and train working conditions, and cannot support the simulation of protection strategies for 30,000-ton heavy-haul trains and under any working conditions. Moreover, the models on which the relevant platforms are based ignore factors such as complex terrain of the line and the actual operating state of the train, and there is a large deviation between the simulation results and the actual data. These problems lead to the inability to accurately simulate the operation of long-haul heavy-haul trains, causing difficulties in related experiments and train operations. There is a technical problem in the field of being difficult to effectively simulate the operation of long-haul heavy-haul trains.

[0029] In the technical solution of this embodiment, the simulation of the operation of a long and heavy-haul train is realized by setting up a traction simulation subsystem, a braking simulation subsystem, a longitudinal simulation subsystem, and a decision-making optimization subsystem. The traction simulation subsystem inputs the train operation data into a preset traction characteristic curve to obtain the train traction force. For example, according to the traction characteristic curve provided by the manufacturer and combined with the real-time train operation speed data, the corresponding traction force value is obtained. The braking simulation subsystem inputs the train operation data into a pre-constructed braking establishment process simulation model to obtain the train braking force, and this model takes into account the influence of braking units such as locomotives, vehicles, and train end devices on braking propagation. The longitudinal simulation subsystem inputs the formation conditions into a pre-constructed buffer simulation model to obtain the train coupler force, which is used to simulate the longitudinal dynamics during train operation. The decision-making optimization subsystem obtains the train control command based on various data such as train operation data and formation conditions, as well as optimization strategies, so as to realize the control simulation of train operation.

[0030] The technical solution of this embodiment provides a comprehensive architecture for the simulation of the operation of a long and heavy-haul train by constructing a simulation system including multiple subsystems. For example, when simulating a 30,000-ton heavy-haul train, the traction simulation subsystem can accurately calculate the traction force according to its operation data, the braking simulation subsystem can accurately simulate the braking process, the longitudinal simulation subsystem can effectively simulate the longitudinal dynamics characteristics of the train, and the decision-making optimization subsystem can generate reasonable control commands. This makes the simulation results closer to the actual train operation situation, provides a reliable simulation platform support for the experiment and operation of the 30,000-ton heavy-haul train. At the same time, this simulation system also helps researchers deeply analyze the operation state of the train under different working conditions, which is of great significance for improving the safety and efficiency of heavy-haul train operation, fills the gap in related technologies in this regard, and promotes the development of heavy-haul train simulation technology.

[0031] Example 2

[0032] On the basis of the above embodiment, in the traction simulation subsystem, inputting the train operation data into a preset traction characteristic curve to obtain the train traction force includes: calculating the adhesion traction force based on the train mass, adhesion coefficient, and gravitational acceleration, and correcting the train traction force based on the adhesion traction force.

[0033] When a long heavy-haul train is in operation, if the train traction force is calculated only based on a preset traction characteristic curve, it is easy for the traction force to exceed the adhesion force between the wheel and the rail, which may lead to wheel spin and affect the normal operation of the train. For example, during the train acceleration phase, if the traction force is inaccurately calculated, wheel spin is likely to occur, reducing the train operation efficiency and easily causing wear to the wheel and rail. Related technologies cannot effectively avoid the problems caused by improper traction force calculation, and there is a technical problem in the field of reasonably correcting the train traction force to prevent wheel spin.

[0034] In the technical solution of this embodiment, in the traction simulation subsystem, the adhesion traction force is calculated based on the train mass, adhesion coefficient, and gravitational acceleration, and then the train traction force is corrected based on the adhesion traction force. For example, given the calculated adhesion mass, adhesion coefficient, and gravitational acceleration of the locomotive, the adhesion traction force is obtained by multiplying the three. When the calculated train traction force is greater than the adhesion traction force, the train traction force is adjusted so that it does not exceed the adhesion traction force, thereby overcoming the phenomenon of wheel spin. At the same time, the obtained basic model is dynamically configured using train driving data, and the parameters of the model are continuously corrected and updated by means of machine learning methods, further reducing the deviation between the traction force calculated by the model and the actual situation, and ensuring the reasonable output of the traction force during the train operation.

[0035] The technical solution of this embodiment effectively avoids the occurrence of wheel spin by calculating the adhesion traction force and correcting the train traction force accordingly, ensures the effective output of the train power, improves the train operation efficiency, and enables the simulated long heavy-haul train to operate stably and efficiently under different operating conditions. At the same time, by combining machine learning methods to continuously optimize the model parameters, the calculation and correction of the traction force are made more accurate, providing more accurate data support for the train operation simulation and enhancing the reliability of the entire simulation system.

[0036] Example 3

[0037] Based on the above embodiment, in the traction simulation subsystem, calculating the adhesion traction force based on the train mass, adhesion coefficient, and gravitational acceleration includes: taking the product of the train mass, adhesion coefficient, and gravitational acceleration as the adhesion traction force.

[0038] When simulating the operation of a long heavy-haul train, the adhesion coefficient will change under different line conditions and train operation states. If the adhesion traction force cannot be accurately calculated, the train traction force cannot be effectively corrected, which is likely to lead to unstable train operation. Related technologies lack an accurate method for calculating the adhesion traction force, and there is a technical problem in the field of how to accurately calculate the adhesion traction force.

[0039] In the technical solution of this embodiment, in the traction simulation subsystem, the product of the train mass, adhesion coefficient, and gravitational acceleration is used as the adhesion traction force. Among them, the train mass reflects the weight characteristics of the train itself, the adhesion coefficient reflects the friction characteristics of the wheel-rail surface, and the gravitational acceleration is a constant. For example, given that the calculated adhesion mass of a locomotive is a certain value, the adhesion coefficient is obtained through actual measurement or experience, and then combined with the standard gravitational acceleration value, and the three are multiplied to obtain the adhesion traction force. This calculation method can quickly and accurately obtain the value of the adhesion traction force, providing basic data for correcting the train traction force based on the adhesion traction force.

[0040] When constructing a traction simulation model, an accurate value of the adhesion traction force can make the model more realistically simulate the mechanical relationship between the wheels and the rails during train operation. Correcting the train traction force based on this value can effectively avoid wheel spin. This helps to improve the accuracy of train operation simulation and make the simulation results more in line with the actual operation situation. At the same time, this simple and clear calculation method is convenient for popularization and use in different simulation scenarios and practical applications, which is beneficial to improving the generality and reliability of the entire heavy-haul train operation simulation technology.

[0041] Example 4

[0042] On the basis of the above embodiment, in the braking simulation subsystem, a simulation model of the braking establishment process is pre-constructed, including: substituting expert knowledge and test data into a preset machine learning algorithm to construct an air braking establishment process model.

[0043] During the braking process of a long and heavy-haul train formation, the traditional aerodynamic numerical simulation model has a large calculation cost and is difficult to accurately simulate the braking process. For example, during an emergency braking of a train, due to the complex formation of the train, there are differences in the braking responses of different carriages, and the traditional model cannot comprehensively consider these factors. Related technologies are difficult to construct a model that can accurately reflect the actual situation of heavy-haul train braking, and there is a technical problem in the field of constructing an accurate simulation model of the braking establishment process.

[0044] In the technical solution of this embodiment, in the braking simulation subsystem, expert knowledge and test data are substituted into a preset machine learning algorithm to construct an air braking establishment process model. Expert knowledge includes in-depth understanding and experience summary of the braking process, and test data is a true reflection of the actual braking situation. For example, a large amount of braking test data collected under different line conditions and different train speeds, as well as the knowledge of braking experts on braking principles, influencing factors, etc., are input into the preset machine learning algorithm. Through learning these data and knowledge, the machine learning algorithm can discover the internal laws in the braking process, thereby constructing an air braking establishment process model that includes links such as air wave propagation, brake valve action, and braking force generation. This model can more comprehensively and accurately simulate the braking establishment process.

[0045] In the technical solution of this embodiment, by using expert knowledge and test data in combination with a machine learning algorithm to construct a braking establishment process simulation model, the accuracy of braking simulation is significantly improved. For example, when simulating the braking process of a train running at high speed, the present invention can accurately simulate the action time of the brake valve, the generation process of the braking force, and the propagation of the air wave according to different initial speeds, train formations, etc. This provides a reliable basis for studying the braking performance of trains, helps optimize the design of train braking systems, and improves the safety and reliability of train braking. At the same time, an accurate braking simulation model can also provide more realistic braking data for train operation simulation, making the simulation of the train operation process by the entire simulation system closer to reality and enhancing the credibility and practicality of the simulation results.

[0046] Example 5

[0047] On the basis of the above embodiment, in the braking simulation subsystem, the air braking establishment process model includes a brake valve action condition model. The brake valve action condition model includes obtaining the action impedance of the brake valve, including: obtaining the difference between the pressure reduction speed on the train pipe side of the main piston and the pressure reduction speed on the slide valve chamber side of the main piston; using the product of the action time of the brake valve, the action area of the main piston, and the difference as the action impedance of the brake valve.

[0048] During train braking, factors such as the action time of the brake valve, the pressure reduction speeds on both sides of the main piston, and the action area of the main piston are interrelated and affect the braking effect. However, it is difficult for related technologies to accurately determine the relationship between these factors, and it is impossible to construct an accurate brake valve action condition model. When simulating the braking process, the working condition of the brake valve cannot be accurately simulated. There is a technical problem in the field of constructing an accurate brake valve action condition model.

[0049] In the technical solution of this embodiment, in the braking simulation subsystem, the action condition model of the brake valve includes obtaining the acting impedance of the brake valve. First, obtain the difference between the pressure reduction speed on the train pipe side of the main piston and the pressure reduction speed on the slide valve chamber side of the main piston. Then, take the product of the action time of the brake valve, the acting area of the main piston, and this difference as the acting impedance of the brake valve. For example, during the actual braking process, collect the pressure reduction speeds on the train pipe side and the slide valve chamber side of the main piston through sensors, calculate the difference between the two, and then combine the pre-determined action time of the brake valve and the acting area of the main piston to obtain the acting impedance of the brake valve. The acting impedance reflects the key characteristics of the brake valve during braking, helps to accurately simulate the action conditions of the brake valve, and further more precisely construct the action condition model of the brake valve.

[0050] The action condition model of the brake valve constructed by the technical solution of this embodiment improves the accuracy of braking simulation. When simulating the train braking under different working conditions, this model can accurately judge the opening and closing states of the brake valve, as well as the generation timing and magnitude of the braking force according to the acting impedance of the brake valve. This makes the simulation of the train braking process more detailed and accurate, providing more accurate data support for studying the train braking performance. At the same time, the accurate action condition model of the brake valve helps to optimize the control strategy of the train braking system, improve the response speed and stability of the braking system, so as to ensure that the long formation heavy-haul train can brake safely and reliably under various conditions, enhancing the reliability and practicability of the entire braking simulation model.

[0051] Example 6

[0052] On the basis of the above embodiment, in the longitudinal simulation subsystem, construct a buffer simulation model, including: obtaining the product of the elastomer stiffness and the buffer stroke; obtaining the product of the damping coefficient and the stroke change rate; summing the product of the elastomer stiffness and the buffer stroke and the product of the damping coefficient and the stroke change rate to obtain the coupler force.

[0053] When a long formation heavy-haul train is running, the buffer plays an important role in mitigating the impact and vibration between vehicles. For example, during the processes of starting, accelerating, decelerating, and passing through curves of the train, longitudinal impact forces will be generated between carriages. If the buffer simulation model is inaccurate, it is impossible to truly simulate the force conditions between carriages during train operation. Related technologies are difficult to construct a simulation model that can accurately reflect the working characteristics of the buffer, and there is a technical problem in the field of constructing an accurate buffer simulation model.

[0054] In the technical solution of this embodiment, in the longitudinal simulation subsystem, when constructing the buffer simulation model, first calculate the product of the elastomer stiffness and the buffer stroke, then calculate the product of the damping coefficient and the stroke change rate, and finally sum these two products to obtain the coupler force. Among them, the elastomer stiffness reflects the ability of the buffer elastomer to resist deformation, the buffer stroke reflects the degree of deformation of the buffer when it is stressed, the damping coefficient represents the ability of the buffer to consume energy, and the stroke change rate reflects the speed of buffer deformation. For example, at the moment when the train starts, the buffer is stretched. By measuring or calculating the elastomer stiffness, buffer stroke, damping coefficient, and stroke change rate at this time, the coupler force is obtained according to the above calculation method, thereby constructing a simulation model that can reflect the working state of the buffer.

[0055] The technical solution of this embodiment effectively improves the accuracy of the longitudinal dynamics simulation of the train by constructing a buffer simulation model. For example, when simulating a train passing through a line with large undulations, the model can accurately calculate the coupler force between carriages at different times and simulate the buffering effect of the buffer on the impact force. This helps researchers deeply understand the longitudinal dynamics characteristics of the train, optimize the train formation and buffer design, provide more realistic longitudinal force data for the train operation simulation, enable the entire simulation system to more accurately simulate the train operation state under various working conditions, improve the reliability and credibility of the simulation results, and is of great significance for ensuring the safe and stable operation of long-formation heavy-haul trains.

[0056] Example 7

[0057] Figure 2 is a schematic flow chart of a simulation method for a long-formation heavy-haul train provided by an embodiment of the present application. As Figure 2 shown, in the technical solution of this embodiment, a simulation method for a long-formation heavy-haul train is provided. The method includes: S100, obtaining train operation data, line conditions, and formation conditions; S200, inputting the train operation data, line conditions, and formation conditions into a pre-constructed long-formation heavy-haul train simulation system to obtain the train state; S300, optimizing the train state based on a preset optimization strategy to obtain the control command of the train.

[0058] The technical problem to be solved in this embodiment is how to comprehensively simulate the operation of a long and heavy-haul train using a simulation system and obtain optimized control commands. During the simulation of the operation of a long and heavy-haul train, various factors such as train operation data, line conditions, and formation conditions need to be comprehensively considered to achieve accurate simulation and obtain reasonable control commands. For example, different line gradients, curve radii, as well as the number and type of train formations will affect the train operation state. It is difficult for related technologies to effectively integrate these factors for simulation and obtain optimized control strategies. There is a technical problem in the field of comprehensively simulating the operation of a long and heavy-haul train and optimizing the control.

[0059] In the technical solution of this embodiment, first, train operation data, line conditions, and formation conditions are obtained. These data include train operation data such as train speed, position, acceleration, line conditions such as line gradient, slope section direction, vertical curve radius, and formation conditions such as the number of train formations and car body types. Then, these data are input into a pre-constructed simulation system for long and heavy-haul trains. The traction simulation subsystem, braking simulation subsystem, longitudinal simulation subsystem, and decision optimization subsystem in this system work together to obtain the train state. For example, the traction simulation subsystem calculates the traction force based on the train operation data, the braking simulation subsystem simulates the braking process to obtain the braking force, the longitudinal simulation subsystem calculates the coupler force, and the decision optimization subsystem comprehensively uses these data to obtain the train state. Finally, based on a preset optimization strategy, the train state is optimized to obtain the control command of the train, realizing the simulation control of the train operation.

[0060] The technical solution of this embodiment realizes the comprehensive simulation and optimized control of the operation of a long and heavy-haul train by obtaining various data and processing them using a simulation system. For example, when simulating a train passing through a complex line with both a steep slope and a curve, the system can accurately calculate the train operation state at different positions based on the obtained line conditions and train operation data. The decision optimization subsystem generates reasonable control commands based on these states, such as adjusting the traction force and braking force, enabling the train to pass through this section safely and efficiently. This not only improves the accuracy and reliability of train operation simulation, provides strong support for train operation experiments and operation, but also helps to optimize train operation strategies, improve train operation efficiency, and reduce energy consumption and equipment wear.

[0061] During the operation of long-haul heavy-haul trains, there are many deficiencies in relevant simulation platforms. For example, most of them are oriented towards 10,000-ton heavy-haul trains, with insufficient consideration of the operating lines and train conditions, and are unable to support the simulation of protection strategies for 30,000-ton heavy-haul trains and under any operating conditions. Moreover, the models on which the relevant platforms are based ignore factors such as the complex terrain of the line and the actual operating status of the train, and there are significant deviations between the simulation results and the actual data. These problems lead to the inability to accurately simulate the operation of long-haul heavy-haul trains, causing difficulties in related experiments and train operations. There is a technical problem in this field that it is difficult to effectively simulate the operation of long-haul heavy-haul trains.

[0062] In the technical solution of this embodiment, the simulation of the operation of long-haul heavy-haul trains is achieved by setting up a traction simulation subsystem, a braking simulation subsystem, a longitudinal simulation subsystem, and a decision-making optimization subsystem. The traction simulation subsystem inputs the train operation data into a preset traction characteristic curve to obtain the train traction force. For example, according to the traction characteristic curve provided by the manufacturer and combined with the real-time train operation speed data, the corresponding traction force value is obtained. The braking simulation subsystem inputs the train operation data into a pre-constructed braking establishment process simulation model to obtain the train braking force, and this model considers the influence of braking units such as locomotives, vehicles, and train end devices on braking propagation. The longitudinal simulation subsystem inputs the formation conditions into a pre-constructed buffer simulation model to obtain the train coupler force, which is used to simulate the longitudinal dynamics during train operation. The decision-making optimization subsystem obtains the control command of the train based on various data such as train operation data and formation conditions, as well as optimization strategies, so as to realize the control simulation of train operation.

[0063] The technical solution of this embodiment provides a comprehensive architecture for the simulation of the operation of long-haul heavy-haul trains by constructing a simulation system including multiple subsystems. For example, when simulating a 30,000-ton heavy-haul train, the traction simulation subsystem can accurately calculate the traction force according to its operation data, the braking simulation subsystem can accurately simulate the braking process, the longitudinal simulation subsystem can effectively simulate the longitudinal dynamics characteristics of the train, and the decision-making optimization subsystem can generate reasonable control commands. This makes the simulation results closer to the actual operation of the train, providing reliable simulation platform support for the experiments and operations of 30,000-ton heavy-haul trains. At the same time, this simulation system also helps researchers deeply analyze the operation status of the train under different conditions, which is of great significance for improving the safety and efficiency of heavy-haul train operation, filling the gap in this aspect of related technologies, and promoting the development of heavy-haul train simulation technology.

[0064] On the basis of the above embodiment, in the traction simulation step, inputting the train operation data into a preset traction characteristic curve to obtain the train traction force includes: calculating the adhesion traction force based on the train mass, adhesion coefficient, and gravitational acceleration, and correcting the train traction force based on the adhesion traction force.

[0065] When a long and heavy-haul train is in operation, if the train traction force is calculated only based on a preset traction characteristic curve, it is easy to have a situation where the traction force exceeds the adhesion force between the wheels and the rails, which may lead to wheel spin and affect the normal operation of the train. For example, during the train acceleration phase, if the traction force is inaccurately calculated, it is easy to cause wheel spin, reduce the train operation efficiency, and also easily cause wear on the wheels and rails. The related technologies cannot effectively avoid the problems caused by improper traction force calculation, and there is a technical problem in the field of reasonably correcting the train traction force to prevent wheel spin.

[0066] In the technical solution of this embodiment, in the traction simulation step, the adhesion traction force is calculated based on the train mass, adhesion coefficient, and gravitational acceleration, and then the train traction force is corrected based on the adhesion traction force. For example, given the calculated adhesion mass, adhesion coefficient, and gravitational acceleration of the locomotive, the adhesion traction force is obtained by multiplying the three. When the calculated train traction force is greater than the adhesion traction force, the train traction force is adjusted so that it does not exceed the adhesion traction force, thereby overcoming the phenomenon of wheel spin. At the same time, the obtained basic model is dynamically configured using the train driving data, and the parameters of the model are continuously corrected and updated by means of machine learning methods to further reduce the deviation between the traction force calculated by the model and the actual situation, ensuring the reasonable output of the traction force during the train operation.

[0067] The technical solution of this embodiment effectively avoids the occurrence of wheel spin by calculating the adhesion traction force and correcting the train traction force based on it, ensures the effective output of the train power, improves the train operation efficiency, and enables the long and heavy-haul train obtained by simulation to operate stably and efficiently under different operation conditions. At the same time, by combining machine learning methods to continuously optimize the model parameters, the calculation and correction of the traction force are made more accurate, providing more accurate data support for the train operation simulation and enhancing the reliability of the entire simulation method.

[0068] Based on the above embodiment, in the traction simulation step, calculating the adhesion traction force based on the train mass, adhesion coefficient, and gravitational acceleration includes: taking the product of the train mass, adhesion coefficient, and gravitational acceleration as the adhesion traction force.

[0069] When simulating the operation of a long and heavy-haul train, the adhesion coefficient will change under different line conditions and train operation states. If the adhesion traction force cannot be accurately calculated, the train traction force cannot be effectively corrected, which may easily lead to unstable train operation. The related technologies lack accurate methods for calculating the adhesion traction force, and there is a technical problem in the field of how to accurately calculate the adhesion traction force.

[0070] In the technical solution of this embodiment, in the traction simulation step, the product of the train mass, adhesion coefficient, and gravitational acceleration is used as the adhesion traction force. Among them, the train mass reflects the weight characteristics of the train itself, the adhesion coefficient reflects the friction characteristics of the wheel-rail surface, and the gravitational acceleration is a constant. For example, given that the calculated adhesion mass of a locomotive is a certain value, the adhesion coefficient is obtained through actual measurement or experience, and then combined with the standard gravitational acceleration value, and the three are multiplied to obtain the adhesion traction force. This calculation method can quickly and accurately obtain the value of the adhesion traction force, providing basic data for correcting the train traction force based on the adhesion traction force.

[0071] When constructing a traction simulation model, an accurate value of the adhesion traction force can make the model more realistically simulate the mechanical relationship between the wheels and the rails during train operation. Correcting the train traction force based on this value can effectively avoid wheel spin. This helps to improve the accuracy of train operation simulation and make the simulation results more in line with the actual operation situation. At the same time, this simple and clear calculation method is convenient for popularization and use in different simulation scenarios and practical applications, which is conducive to improving the generality and reliability of the entire heavy-haul train operation simulation technology.

[0072] Based on the above embodiment, in the braking simulation step, a simulation model of the braking establishment process is pre-constructed, including: substituting expert knowledge and test data into a preset machine learning algorithm to construct an air braking establishment process model.

[0073] During the braking process of a long and heavy-haul train formation, the traditional aerodynamic numerical simulation model has a large calculation cost and is difficult to accurately simulate the braking process. For example, during an emergency braking of a train, due to the complex formation of the train, there are differences in the braking responses of different carriages, and the traditional model cannot comprehensively consider these factors. Related technologies are difficult to construct a model that can accurately reflect the actual situation of heavy-haul train braking, and there is a technical problem in the field of constructing an accurate simulation model of the braking establishment process.

[0074] In the technical solution of this embodiment, in the braking simulation step, expert knowledge and test data are substituted into a preset machine learning algorithm to construct an air braking establishment process model. Expert knowledge contains in-depth understanding and experience summary of the braking process, and test data is a true reflection of the actual braking situation. For example, a large amount of braking test data collected under different line conditions and different train speeds, as well as the knowledge of braking experts on braking principles, influencing factors, etc., are input into the preset machine learning algorithm. Through learning these data and knowledge, the machine learning algorithm can discover the internal laws in the braking process, thereby constructing an air braking establishment process model including links such as air wave propagation, brake valve action, and braking force generation. This model can more comprehensively and accurately simulate the braking establishment process.

[0075] The technical solution of this embodiment significantly improves the accuracy of braking simulation by constructing a braking establishment process simulation model using expert knowledge and experimental data in combination with machine learning algorithms. For example, when simulating the braking process of a train running at high speed, the present invention can accurately simulate the action time of the brake valve, the generation process of braking force, and the propagation of air waves according to different initial speeds, train formations, and other conditions. This provides a reliable basis for studying the braking performance of trains, helps optimize the design of train braking methods, and improves the safety and reliability of train braking. At the same time, an accurate braking simulation model can also provide more realistic braking data for train operation simulation, making the entire simulation method more closely approximate the actual train operation process, and enhancing the credibility and practicality of the simulation results.

[0076] Based on the above embodiment, in the braking simulation step, the air braking establishment process model includes a brake valve action condition model, and the brake valve action condition model includes obtaining the action impedance of the brake valve, including: obtaining the difference between the pressure reduction speed on the train pipe side of the main piston and the pressure reduction speed on the slide valve chamber side of the main piston; taking the product of the action time of the brake valve, the action area of the main piston, and the difference as the action impedance of the brake valve.

[0077] During train braking, factors such as the action time of the brake valve, the pressure reduction speeds on both sides of the main piston, and the action area of the main piston are interrelated and affect the braking effect. However, it is difficult for related technologies to accurately determine the relationships between these factors, unable to construct an accurate brake valve action condition model, and unable to accurately simulate the working conditions of the brake valve during the braking simulation process. There is a technical problem in the field of constructing an accurate brake valve action condition model.

[0078] In the technical solution of this embodiment, in the braking simulation step, the brake valve action condition model includes obtaining the action impedance of the brake valve. First, obtain the difference between the pressure reduction speed on the train pipe side of the main piston and the pressure reduction speed on the slide valve chamber side of the main piston, and then take the product of the action time of the brake valve, the action area of the main piston, and this difference as the action impedance of the brake valve. For example, during the actual braking process, the pressure reduction speeds on the train pipe side and the slide valve chamber side of the main piston are collected by sensors, the difference between the two is calculated, and then combined with the pre-determined action time of the brake valve and the action area of the main piston to obtain the action impedance of the brake valve. The action impedance reflects the key characteristics of the brake valve during the braking process, helps accurately simulate the action conditions of the brake valve, and further more precisely constructs the brake valve action condition model.

[0079] The brake valve action condition model constructed by the technical solution of this embodiment improves the accuracy of braking simulation. When simulating train braking under different working conditions, the model can accurately judge the open and closed state of the brake valve, as well as the timing and magnitude of the generation of braking force based on the action impedance of the brake valve. This makes the simulation of the train braking process more detailed and accurate, and provides more accurate data support for studying the braking performance of the train. At the same time, the accurate brake valve action condition model helps to optimize the control strategy of the train braking method, improve the response speed and stability of the braking method, thereby ensuring that long and large-scale heavy-load trains can brake safely and reliably under various conditions, and enhancing the reliability and practicality of the entire braking simulation model.

[0080] On the basis of the above embodiment, in the longitudinal simulation step, a buffer simulation model is constructed, including: calculating the product of the elastic body stiffness and the buffer stroke; calculating the product of the damping coefficient and the stroke change rate; summing the product of the elastic body stiffness and the buffer stroke and the product of the damping coefficient and the stroke change rate to obtain the coupler force.

[0081] When a long and large train is running, the buffer plays an important role in alleviating the impact and vibration between vehicles. For example, when the train is starting, accelerating, decelerating, and passing through a curve, a longitudinal impact force will be generated between the carriages. If the buffer simulation model is inaccurate, it will not be possible to truly simulate the force between the carriages when the train is running. It is difficult for related technologies to construct a simulation model that can accurately reflect the working characteristics of the buffer. There are technical problems in this field in constructing an accurate buffer simulation model.

[0082] In the technical solution of this embodiment, in the longitudinal simulation step, when constructing the buffer simulation model, first calculate the product of the elastic body stiffness and the buffer stroke, then calculate the product of the damping coefficient and the stroke change rate, and finally sum these two products to obtain the coupler force. Among them, the elastic body stiffness reflects the ability of the buffer elastic body to resist deformation, the buffer stroke reflects the degree of deformation of the buffer when subjected to force, the damping coefficient indicates the ability of the buffer to consume energy, and the stroke change rate reflects the speed of the buffer deformation. For example, at the moment the train starts, the buffer is stretched, and the elastic body stiffness, buffer stroke, damping coefficient and stroke change rate at this time are obtained by measurement or calculation, and the coupler force is obtained according to the above calculation method, thereby constructing a simulation model that can reflect the working state of the buffer.

[0083] The technical solution of this embodiment effectively improves the accuracy of train longitudinal dynamics simulation by constructing a buffer simulation model. For example, when simulating a train passing through a line with large undulations, the model can accurately calculate the coupler forces between carriages at different times and simulate the buffering effect of the buffer on impact forces. This helps researchers deeply understand the longitudinal dynamics characteristics of trains, optimize train formation and buffer design, provide more realistic longitudinal force data for train operation simulation, enable the entire simulation method to more accurately simulate the train operation state under various working conditions, improve the reliability and credibility of the simulation results, and is of great significance for ensuring the safe and stable operation of long-formation heavy-haul trains.

[0084] Example 8

[0085] In the technical solution of this embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the steps of the long-formation heavy-haul train simulation method of claim 7.

[0086] In the technical solution of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the long-formation heavy-haul train simulation method of claim 7 are implemented.

[0087] In the technical solution of this embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps of the long-formation heavy-haul train simulation method of claim 7 are implemented.

[0088] The processor may include, but is not limited to, for example, one or more processors or microprocessors, etc. Each processor may be implemented by an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, and is used to execute the methods in the above embodiments. The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof. The computer-readable storage medium may include, but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (such as hard disks, floppy disks, solid state drives, removable disks, CD-ROMs, DVD-ROMs, Blu-ray discs, etc.).

[0089] The computer-readable storage medium may also store at least one computer-executable program / instructions, and the computer-executable program / instructions are, for example, computer-readable instructions. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may, for example, include random access memory (RAM) and / or cache memory, etc. The computer-readable storage medium may, for example, include read-only memory (ROM), hard disks, flash memory, etc. For example, the non-transitory computer-readable storage medium may be connected to a computing device such as a computer. Then, in the case where the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0090] In addition, the computer device may also include (but is not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (such as a keyboard, a mouse, a speaker, etc.). The processor may communicate with external devices via the I / O bus through a wired or wireless network. In one embodiment, the at least one computer-executable instruction may also be compiled into or constitute a software product / computer program product, and when one or more computer-executable instructions are run by the processor, the steps of the various functions and / or methods in the embodiments described in the present technology are performed.

[0091] Example 9

[0092] Based on the above embodiments, this embodiment provides an application example. This application example provides a long-formation heavy-haul train operation simulation platform.

[0093] Heavy-haul trains can significantly improve the efficiency and capacity of freight transportation, reduce logistics costs, and reduce dependence on road transportation, thereby alleviating road traffic congestion, reducing carbon emissions, and promoting sustainable economic development. They play an important role in transportation. Therefore, it is of great significance to simulate heavy-haul train transportation to improve its safety and efficiency.

[0094] Most of the current heavy-haul train operation simulation platforms are oriented towards 10,000-ton or 20,000-ton heavy-haul trains, and do not fully consider the operating lines and train conditions, and do not support the simulation of protection strategies for 30,000-ton heavy-haul trains and under any conditions. These platforms are mainly based on mechanism models such as traction and braking, ignoring factors such as the complex terrain of the line and the actual operating state of the train. Although they can simulate the basic operation of the train to a certain extent, due to the characteristics of high nonlinearity, uncertainty, time delay, etc. of the heavy-haul train operation mechanism model, there is a certain deviation between the simulation results and the actual train operation data, and it is impossible to accurately reflect the dynamic changes in actual operation. Moreover, for the more complex 30,000-ton heavy-haul trains and the simulation of their protection strategies under various conditions, the existing simulation platforms cannot complete.

[0095] In addition, the existing simulation platforms lack technical application verification of the correctness and authenticity of the simulation results, which limits the credibility and practicality of the simulation results.

[0096] To address the above problems, the proposed long-formation heavy-haul train operation simulation platform adopts a train simulation model that combines train operation mechanism and data-driven, which can achieve accurate modeling and simulation of heavy-haul trains. At the same time, it fills the gap in the current 30,000-ton heavy-haul train simulation experiment platform, provides simulation platform support for the subsequent experiments and operation of 30,000-ton heavy-haul trains, and is of great significance for the operation and control of long-formation heavy-haul trains.

[0097] This method relates to the technical field of rail transit, and specifically proposes a long-formation heavy-haul train operation simulation platform. The core of this simulation platform is to adopt a train simulation model that combines train operation mechanism and data-driven, which can achieve accurate modeling and simulation of heavy-haul trains. The platform includes a traction force simulation subsystem / traction simulation subsystem, a braking simulation subsystem, a longitudinal dynamics simulation subsystem / longitudinal simulation subsystem of the heavy-haul train, and an intelligent decision-making and optimization subsystem / decision-making optimization subsystem of the heavy-haul train. Based on the heavy-haul train operation mechanism and the actual train operation data, the model parameters of the long-formation heavy-haul train are corrected and simulated. Through the train simulation model that combines train operation mechanism and data-driven, the platform can achieve more accurate modeling and simulation of heavy-haul trains.

[0098]

[0099] A running simulation platform for long formation heavy-haul trains in this application example, its subsystems include:

[0100] (1) Traction force simulation subsystem: Around the train status monitoring data and its data link, combined with the known traction characteristic curve, the Lagrangian linear interpolation method is used to obtain the corresponding relationship between speed and traction force magnitude.

[0101] (2) Braking simulation subsystem: Based on the multi-dimensional monitoring data collected on-site, using the function approximation method of machine learning theory, a simulation model for the braking establishment process under the coupling of multiple working conditions such as locomotive working conditions, train end working conditions, and line working conditions is constructed.

[0102] (3) Longitudinal dynamics simulation subsystem / Longitudinal simulation subsystem: First, a buffer simulation model for heavy-haul trains and a multi-particle longitudinal dynamics model of the train are constructed, and the models are corrected in combination with different line vertical profiles and different formation conditions.

[0103] (4) Intelligent decision-making and optimization subsystem / Decision-making optimization subsystem: Combining a large amount of heavy-haul train operation data (such as vehicle data, train working condition data, etc.), based on data mining methods, a simulation scheme for intelligent control decision-making and optimization of heavy-haul trains is formed.

[0104] The architecture of the running simulation platform for long formation heavy-haul trains is as Figure 3 shown.

[0105] Among them, the heavy-haul train dynamics model includes mechanism models such as the above-mentioned simulation model for the braking establishment process under the coupling of multiple working conditions, the buffer simulation model, and the multi-particle longitudinal dynamics model. The running simulation platform for long formation heavy-haul trains in this application, based on the above models and train position data, conducts line simulation of train operation to obtain static line data, and obtains train dynamics parameters based on the above models and train dynamics parameters. The static line data and train dynamics parameters are combined to obtain the train state fusion as the simulation result. The simulation result includes the train state (such as including the train's speed, position, actual acceleration, various parameters, static line data, etc.) and control commands. Among them, the static line data includes gradient, slope section direction, vertical curve radius, etc. The train state is combined with the driving strategy optimization model to obtain the train control command corresponding to the driving strategy of the heavy-haul train, and the control command is transmitted to the heavy-haul train dynamics model to control the heavy-haul train.

[0106] In addition, the train dynamics parameters, static line data, etc. are also fed back to the heavy-haul train dynamics model to enable the heavy-haul train dynamics model to perform real-time closed-loop simulation. Specific function implementation:

[0107] (1) Traction simulation subsystem

[0108] According to the traction characteristic curve obtained from the manufacturer or through traction tests, this subsystem uses Lagrangian linear interpolation to obtain the corresponding relationship between speed and traction force magnitude, that is, at the current speed, given the traction handle position, the corresponding traction force at any speed point is obtained through multiple Lagrangian interpolation methods.

[0109] To overcome the phenomenon of wheel spin when the traction force exceeds the adhesion force between the wheel and the rail, the calculation of adhesion traction force will be considered when establishing the model. Given the calculated adhesion mass P u , adhesion coefficient μ j and gravitational acceleration g, the adhesion traction force F can be calculated using the following expression u .

[0110] F u = P u · g · μ j

[0111] The obtained basic model is dynamically configured using train driving data, and the parameters of the model are continuously corrected and updated with the help of machine learning methods to reduce the deviation between the model and the actual situation.

[0112] (2) Brake simulation subsystem

[0113] Aiming at the characteristics of non-linearity and uncertainty during the braking process of heavy-haul trains, this brake simulation subsystem uses machine learning intelligent algorithms to overcome the problem of high computational cost of the aerodynamic numerical simulation model. With the help of discrete operation samples containing expert knowledge and real test data, an air brake establishment process model composed of air wave propagation, brake valve action, and braking force generation is constructed, and the influence of various braking units such as locomotives, vehicles, and train tails on brake propagation is considered. At the same time, the brake model is simplified into an air wave propagation model, a train brake valve action condition model, and a braking force generation model. For the brake valve action condition model, given the action time t D of the brake valve, the pressure reduction speed n L on one side of the main piston train pipe, the pressure reduction speed n H on one side of the main piston slide valve chamber, and the acting area F Z of the main piston, the acting impedance W of the valve can be calculated using the following formula D .

[0114] (n L - n H ) · t D · F Z = W D

[0115] For the mechanism model, the real train braking data under different initial velocity conditions are compared with the model calculation results, and the model is corrected online in real time.

[0116] (3) Longitudinal dynamics simulation subsystem

[0117] During the operation of a heavy-haul train, the buffer will undergo elastic deformation within a certain range under the impact of longitudinal forces. During the deformation process, due to the existence of damping, the impact and vibration generated between vehicles can be dissipated, thereby alleviating the longitudinal impact. This longitudinal dynamics simulation subsystem first establishes a buffer simulation model using the following coupler force calculation model paradigm. Given the stiffness k of the elastic body, the damping coefficient d, and the buffer stroke x i and the stroke change rate the coupler force F can be calculated coupler .

[0118]

[0119] Secondly, a multi-particle longitudinal dynamics model of the train is established. Each vehicle of the train is regarded as a particle to construct a multi-particle longitudinal dynamics simulation model of the heavy-haul train. Based on the non-linear impedance characteristics of the buffer and the non-linear working characteristics of traction and braking, combined with actual data such as the locomotive traction and braking states, speed, and line conditions, a mutual coupling relationship model between different particles is established.

[0120] For the above model, the direct integration Newmark-β implicit method is used to transform the homogeneous second-order ordinary differential dynamics equation into a set of first-order ordinary differential equations, and a high-precision equilibrium iteration numerical solution is carried out for it.

[0121] (4) Intelligent decision-making and optimization subsystem

[0122] This subsystem first conducts environmental data simulation for ordinary trains, 10,000-ton trains, and 20,000-ton trains, including bridges, tunnels, speed limits, track parameters, and slope curvature, and realizes the interaction between line parameters and control instructions through the simulation data. Based on the data obtained from the line environment simulation, the optimization of the driving strategy of the heavy-haul train is decomposed into a model, constraints (impact force, speed limit), and objectives (safety, efficiency) for optimization and solution. By introducing data to train a neural network, a heavy-haul train controller is constructed, and speed-displacement and control force curves are generated in real time. Finally, the dynamic optimization of the driving strategy is realized through the solution space of the optimization problem.

[0123] Based on the optimized train operation strategy, the platform combines the train's own performance parameters and planned curve data to obtain the train's control instruction data, and uses the interface with the vehicle system to input the instructions to the vehicle to realize the simulation of vehicle operation, achieving the purpose of train operation control simulation and efficient operation.

[0124] Due to factors such as the complex formation pattern and the variable conditions of the operating line of the long and heavy-haul train, its train dynamics model exhibits highly nonlinear characteristics, making it difficult to simulate the complex mechanisms such as multi-operating conditions, parameter time-variation, and vehicle-to-vehicle coupling in the existing technology.

[0125] The train dynamics model constructed by the running simulation platform of the long and heavy-haul train is more refined, and the simulation results are close to the actual running data of the train, which can provide data support for the analysis of special dangerous scenarios in train operation such as derailment and uncoupling.

[0126] In view of the highly nonlinear characteristics of the traction model, combined with the wheel-rail creep mechanism, an adjustment method for the traction model based on the line conditions and train driving data is adopted; for the air braking characteristics of the heavy-haul train, an air braking mechanism model of the locomotive is established, and the key parameters of the model are adjusted by machine learning to reveal the braking laws under different driving conditions; the vehicle operation is simulated based on the refined dynamics model and the optimized train operation strategy to improve the accuracy and credibility of the heavy-haul train operation simulation.

[0127] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are only illustrative. For example, the flowcharts and block diagrams in the drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0128] It should be noted that in the present invention, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, the element limited by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0129] Although the embodiments disclosed in the present invention are as above, the above content is only an embodiment adopted for the convenience of understanding the present invention and is not intended to limit the present invention. Any person skilled in the art within the technical field to which the present invention pertains may make any modifications and changes in the form of implementation and details without departing from the spirit and scope disclosed in the present invention. However, the scope of patent protection of the present invention shall still be subject to the scope defined by the appended claims.

Claims

1. A simulation system for long formation heavy-haul trains, characterized in that, The system includes: A traction simulation subsystem for inputting train operation data into a preset traction characteristic curve to obtain the train traction force; A braking simulation subsystem for inputting train operation data into a pre-constructed braking establishment process simulation model to obtain the train braking force; A longitudinal simulation subsystem for inputting the formation conditions into a pre-constructed buffer simulation model to obtain the train coupler force; A decision-making optimization subsystem for obtaining the train control command based on the train operation data, formation conditions, train traction force, train braking force, train coupler force, and optimization strategy.

2. The simulation system for long-formation heavy-haul trains according to claim 1, characterized in that In the traction simulation subsystem, the step of inputting train operation data into a preset traction characteristic curve to obtain the train traction force includes: Calculating the adhesion traction force based on the train mass, adhesion coefficient, and gravitational acceleration, and correcting the train traction force based on the adhesion traction force.

3. The heavy-haul train simulation system for long formation according to claim 2, wherein In the traction simulation subsystem, the step of calculating the adhesion traction force based on the train mass, adhesion coefficient, and gravitational acceleration includes: Taking the product of the train mass, adhesion coefficient, and gravitational acceleration as the adhesion traction force.

4. The heavy-haul train simulation system for long formation according to claim 1, characterized in that In the braking simulation subsystem, the step of pre-constructing the braking establishment process simulation model includes: Substituting expert knowledge and test data into a preset machine learning algorithm to construct an air braking establishment process model.

5. The heavy-haul train simulation system for long formation according to claim 4, wherein In the braking simulation subsystem, the air braking establishment process model includes a brake valve action condition model, and the brake valve action condition model includes obtaining the action impedance of the brake valve, which includes: Obtaining the difference between the pressure reduction speed on the train pipe side of the main piston and the pressure reduction speed on the slide valve chamber side of the main piston; Taking the product of the action time of the brake valve, the action area of the main piston, and the difference as the action impedance of the brake valve.

6. The heavy-haul train simulation system for long formation according to claim 1, characterized in that In the longitudinal simulation subsystem, the step of constructing the buffer simulation model includes: Obtaining the product of the elastomer stiffness and the buffer stroke; Obtaining the product of the damping coefficient and the stroke change rate; Summing the product of the elastomer stiffness and the buffer stroke and the product of the damping coefficient and the stroke change rate to obtain the coupler force.

7. A simulation method for long formation heavy-haul trains, characterized in that, The method includes: S100. Obtain train operation data, line conditions, and formation conditions; S200. Input the train operation data, line conditions, and formation conditions into a pre-constructed long formation heavy-haul train simulation system to obtain the train state; S300. Optimize the train state based on a preset optimization strategy to obtain the train control command.

8. A computer device, comprising a memory, a processor, and a computer program stored on the memory, characterized in that, The processor executes the computer program to implement the steps of the long formation heavy-haul train simulation method according to claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the long formation heavy-haul train simulation method according to claim 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the long formation heavy-haul train simulation method according to claim 7.

Images