Capacity configuration method, device and equipment of hybrid power train and storage medium
By obtaining operation simulation data and constraints, using particle swarm optimization algorithm and Pontriajin energy management algorithm, the capacity configuration of hybrid train power sources is optimized, which solves the problem of unreasonable configuration in traditional methods and achieves the minimum total cost and improve economic benefits.
Patent Information
- Application Number
- CN202411074719.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-06
- Publication Date
- 2024-11-29
AI Technical Summary
The traditional hybrid train capacity configuration method lacks comprehensive consideration of the total cost of the actual operating line, resulting in unreasonable configuration and the advantages of the hybrid system cannot be fully utilized.
By obtaining the running simulation data and constraints, the capacity configuration constraint domain of the hybrid power source is determined, and the capacity configuration of the power source is optimized by using the particle swarm optimization algorithm and the Pontriajin energy management algorithm to minimize the total cost.
It is realized that the hybrid train can minimize the total cost of capacity configuration while meeting the operation simulation data, reduce costs and improve economic benefits.
Smart Images

Figure CN119047750A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of energy management technology, and in particular to a capacity configuration method, device, equipment and storage medium for a hybrid power train. Background Art
[0002] Due to the green and efficient characteristics of new energy and the transformation of energy layout, the transportation industry is actively developing internal combustion + power battery hybrid trains to reduce pollution emissions.
[0003] The internal combustion + power battery hybrid system combines the advantages of both internal combustion engines and batteries. The internal combustion engine provides continuous power output, while the battery can provide additional power support at high loads or when starting, thereby achieving higher energy efficiency and lower emissions. However, the key to achieving safe and stable operation of this hybrid system lies in reasonable capacity configuration.
[0004] However, traditional capacity configuration methods often only focus on a single performance indicator, such as power performance or economy, and lack comprehensive consideration of the total cost of the actual operating line. This method may lead to unreasonable configuration in actual application and fail to give full play to the advantages of hybrid power systems. Summary of the invention
[0005] The embodiments of the present application provide a capacity configuration method, device, equipment and storage medium for a hybrid power train, which realize capacity configuration with the goal of minimizing the actual total line cost, thereby reducing costs.
[0006] In a first aspect, an embodiment of the present application provides a capacity configuration method for a hybrid train, comprising: acquiring operation simulation data based on train information of a target train, wherein the operation simulation data is used to indicate time data and total power requirements of each operating state of the target train during operation.
[0007] A constraint domain for the capacity configuration of each power source in the hybrid power source providing power for the target train is determined based on the operation simulation data and the constraint conditions, wherein the constraint conditions include vehicle performance constraints and a configurable range of the capacity of each power source, and each feasible capacity configuration point in the constraint domain includes a maximum power that each power source needs to provide.
[0008] A target capacity configuration point is determined in the constraint domain, wherein the target capacity configuration point can minimize the total cost of the capacity configuration for the target train while satisfying the operation simulation data.
[0009] The capacity of each of the power sources is configured according to the target capacity configuration point.
[0010] In a possible implementation manner, the determining, according to the operation simulation data and the constraint conditions, the constraint domain of the capacity configuration of each power source in the hybrid power source providing power to the target train includes:
[0011] A maximum operating speed power constraint is determined according to the operation simulation data and the constraint condition, wherein the maximum operating speed power constraint is used to constrain the sum of powers provided by various power sources of the target train to be greater than the power required when the target train runs at the maximum operating speed.
[0012] An acceleration power constraint is determined according to the operation simulation data and the constraint condition, wherein the acceleration power constraint is used to constrain the sum of powers provided by various power sources of the target train to be greater than the maximum power required for acceleration.
[0013] A constraint domain of capacity configuration is determined according to the maximum operating speed power constraint and the acceleration power constraint.
[0014] In a possible implementation, determining the target capacity configuration point in the constraint domain includes: randomly generating a preset number of particles in the constraint domain as a particle swarm, each of the particles representing a capacity configuration solution.
[0015] For each particle in the particle swarm, the total cost of the capacity configuration corresponding to the particle is calculated, and the individual extreme value of each particle and the global extreme value of the particle swarm are determined according to the total cost, wherein the individual extreme value is the capacity configuration point with the minimum total cost of the particle, and the global extreme value is the capacity configuration point with the minimum total cost in the particle swarm.
[0016] The position and velocity of each particle are updated according to the individual extreme value of the particle, the total cost is recalculated according to the updated particle, and the individual extreme value and the global extreme value are updated, and the iterative process is repeated until a preset stop condition is met.
[0017] The global extreme value is used as the target capacity configuration point.
[0018] In one possible implementation, the hybrid power source includes an internal combustion generator set and a power battery pack, the constraint domain also includes a DC bus voltage constraint domain, the number of battery cells connected in series in the power battery pack is less than the DC bus voltage of the target train; each feasible capacity configuration point in the constraint domain also includes the number of battery cells connected in series.
[0019] In a possible implementation, the total cost of the capacity configuration corresponding to the calculating particle includes: calculating the purchase cost of the power battery pack according to the number of battery cells connected in series and the maximum power provided by the power battery pack; calculating the purchase cost of the internal combustion generator according to the maximum power provided by the internal combustion generator set; calculating the minimum operating cost using the Pontryagin energy management algorithm; and calculating the total cost according to the purchase cost of the power battery pack, the purchase cost of the internal combustion generator and the operating cost.
[0020] In a possible implementation, the calculation of the minimum operating cost using the Pontryagin energy management algorithm includes: taking the charge state of the power battery pack as a state variable, taking the charge state at the initial moment of the operation of the target train and the charge state at the end moment of the operation task as a restriction that is less than a preset threshold, establishing boundary conditions, and determining an operating cost function with the minimum total cost as the goal; and constructing a Hamiltonian function based on the operating cost function; solving the optimal solution of the Hamiltonian function that satisfies the boundary conditions to obtain the minimum operating cost.
[0021] In a possible implementation, the operating cost function is the following formula:
[0022]
[0023] Wherein, the SOC0 is the charge state of the target train at the initial time of operation, and the SOC f is the charge state at the termination time of the target train operation task, and the Q ICE (t) is the instantaneous diesel consumption mass of the target train at time t, and f is the termination time of the target train operation mission.
[0024] The Hamiltonian function is as follows:
[0025]
[0026] Among them, the represents the derivative of the cost function J(t) with respect to time, and SOC(t) represents the charge state of the power battery pack at time t.
[0027] In a possible implementation, solving the optimal solution of the Hamiltonian function that satisfies the boundary conditions to obtain the minimum operating cost includes: initializing the costate variables and obtaining a power sequence, wherein the power sequence is used to indicate the power of the power battery pack and the power of the internal combustion generator set at each moment during the operation of the target train when the function value of the Hamiltonian function reaches a minimum value.
[0028] Determine whether the power sequence satisfies the boundary condition; if so, calculate the minimum operating cost according to the power sequence; if not, update the co-state variable and reacquire the power sequence until the updated power sequence satisfies the boundary condition.
[0029] In a second aspect, an embodiment of the present application provides a capacity configuration device for a hybrid train, comprising:
[0030] The acquisition module is used to acquire operation simulation data according to the train information of the target train, wherein the operation simulation data is used to indicate the time data and total power demand of each operation state of the target train during operation.
[0031] A constraint module is used to determine a constraint domain for the capacity configuration of each power source in the hybrid power source providing power for the target train based on the operation simulation data and the constraint conditions, wherein the constraint conditions include vehicle performance constraints and a configurable range of the capacity of each power source, and each feasible capacity configuration point in the constraint domain includes a maximum power that each power source needs to provide.
[0032] A determination module is used to determine a target capacity configuration point in the constraint domain, wherein the target capacity configuration point can minimize the total cost of the capacity configuration of the target train under the premise of satisfying the operation simulation data.
[0033] A configuration module is used to configure the capacity of each of the power sources according to the target capacity configuration point.
[0034] In one possible implementation, the constraint module is specifically used to determine a maximum operating speed power constraint based on the operation simulation data and the constraint conditions, wherein the maximum operating speed power constraint is used to constrain the sum of the powers provided by each power source of the target train to be greater than the power required when the target train runs at the maximum operating speed.
[0035] An acceleration power constraint is determined according to the operation simulation data and the constraint condition, wherein the acceleration power constraint is used to constrain the sum of powers provided by various power sources of the target train to be greater than the maximum power required for acceleration.
[0036] A constraint domain of capacity configuration is determined according to the maximum operating speed power constraint and the acceleration power constraint.
[0037] In a possible implementation, the determination module is specifically configured to: randomly generate a preset number of particles in the constraint domain as a particle swarm, each of the particles representing a capacity configuration solution.
[0038] For each particle in the particle swarm, the total cost of the capacity configuration corresponding to the particle is calculated, and the individual extreme value of each particle and the global extreme value of the particle swarm are determined according to the total cost, wherein the individual extreme value is the capacity configuration point with the minimum total cost of the particle, and the global extreme value is the capacity configuration point with the minimum total cost in the particle swarm.
[0039] The position and velocity of each particle are updated according to the individual extreme value of the particle, the total cost is recalculated according to the updated particle, and the individual extreme value and the global extreme value are updated, and the iterative process is repeated until a preset stop condition is met.
[0040] The global extreme value is used as the target capacity configuration point.
[0041] In one possible implementation, the hybrid power source includes an internal combustion generator set and a power battery pack, the constraint domain also includes a DC bus voltage constraint domain, the number of battery cells connected in series in the power battery pack is less than the DC bus voltage of the target train; each feasible capacity configuration point in the constraint domain also includes the number of battery cells connected in series.
[0042] In a possible implementation, the determination module is specifically used to: calculate the purchase cost of the power battery pack based on the number of battery cells connected in series and the maximum power provided by the power battery pack; calculate the purchase cost of the internal combustion generator based on the maximum power provided by the internal combustion generator set; calculate the minimum operating cost using the Pontryagin energy management algorithm; calculate the total cost based on the purchase cost of the power battery pack, the purchase cost of the internal combustion generator and the operating cost.
[0043] In a possible implementation, the determination module is specifically used to: take the charge state of the power battery pack as a state variable, establish boundary conditions with the charge state at the initial moment of the target train running and the charge state at the end moment of the running task being less than a preset threshold as a restriction, and determine the operating cost function with the minimum total cost as the goal; construct a Hamiltonian function based on the operating cost function; solve the optimal solution of the Hamiltonian function that meets the boundary conditions to obtain the minimum operating cost.
[0044] In a possible implementation, the operating cost function is the following formula:
[0045]
[0046] Wherein, the SOC0 is the charge state of the target train at the initial time of operation, and the SOC f is the charge state at the termination time of the target train operation task, and the Q ICE(t) is the instantaneous diesel consumption mass of the target train at time t, and f is the termination time of the target train operation task; the Hamiltonian function is the following formula:
[0047]
[0048] Among them, the represents the derivative of the cost function J(t) with respect to time, and SOC(t) represents the charge state of the power battery pack at time t.
[0049] In a possible implementation, the determination module is specifically used to: initialize the costate variables and obtain a power sequence, wherein the power sequence is used to indicate the power of the power battery pack and the power of the internal combustion generator set at each moment during the operation of the target train when the function value of the Hamiltonian function reaches a minimum.
[0050] Determine whether the power sequence satisfies the boundary condition; if so, calculate the minimum operating cost according to the power sequence; if not, update the co-state variable and reacquire the power sequence until the updated power sequence satisfies the boundary condition.
[0051] In a third aspect, an embodiment of the present application provides a capacity configuration device for a hybrid train, including: a memory, a processor;
[0052] The memory stores computer-executable instructions;
[0053] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.
[0054] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.
[0055] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.
[0056] The capacity configuration method, device, equipment and storage medium of a hybrid power train provided in an embodiment of the present application obtain operation simulation data according to train information of a target train, wherein the operation simulation data is used to indicate the time data and total power demand of each operation state of the target train during operation; determine the constraint domain of the capacity configuration of each power source in the hybrid power source providing power for the target train according to the operation simulation data and constraint conditions, wherein the constraint conditions include vehicle performance constraints and the configurable range of the capacity of each power source, and each feasible capacity configuration point in the constraint domain includes the maximum power that each power source needs to provide; determine the target capacity configuration point in the constraint domain, wherein the target capacity configuration point can minimize the total cost of capacity configuration of the target train under the premise of satisfying the operation simulation data; and configure the capacity of each power source according to the target capacity configuration point, thereby realizing capacity configuration with the actual line total cost as the goal, reducing costs and improving the economic benefits of hybrid power trains. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0058] Figure 1 A schematic diagram of the power system structure of a hybrid train provided in an embodiment of the present application;
[0059] Figure 2 A flow chart of the capacity configuration method of a hybrid train provided in this application Figure 1 ;
[0060] Figure 3 A flow chart of the capacity configuration method of a hybrid train provided in this application Figure 2 ;
[0061] Figure 4 A flow chart of the capacity configuration method of a hybrid train provided in this application Figure 3 ;
[0062] Figure 5 A flow chart of the capacity configuration method of a hybrid train provided in this application Figure 4 ;
[0063] Figure 6 A schematic diagram of the structure of a capacity configuration device for a hybrid train provided in this application;
[0064] Figure 7 A schematic diagram of the structure of the capacity configuration device of the hybrid train provided in this application.
[0065] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0066] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0067] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.
[0068] As described in the background technology, traditional diesel engine-driven trains mainly use a diesel engine plus a main generator integrated method to provide traction electricity for the EMU. The diesel engine drives the main generator to generate electricity, which is directly output to the traction motor through the converter to provide a power source for the EMU. The fuel of this configuration comes from fuel oil. The configuration of the diesel engine needs to determine the selection of the diesel engine based on the traction calculation. The diesel engine selection is often large, and the emission will produce a large amount of carbon dioxide and sulfide, and the noise generated is large, which affects the comfort of the EMU passengers and has poor economy. Correspondingly, if the solution relies solely on power batteries, the overall economy is poor due to the high cost of power batteries and the fact that their life and performance are affected by many factors.
[0069] In order to address the above problems, the internal combustion + power battery hybrid system came into being. Figure 1 A schematic diagram of the power system structure of a hybrid train provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the power system includes a diesel generator set, a rectifier connected to the diesel generator set, a power battery pack and its DCDC converter, a traction system, an auxiliary system and a DC bus. It combines the advantages of both internal combustion engines and batteries as power sources, and transmits DC power from the diesel generator set and the power battery to the traction system and the auxiliary system through the DC bus for power supply, so as to meet the power supply needs of the train's drive and other electrical equipment, thereby achieving higher energy efficiency and lower emissions.
[0070] However, the key to achieving safe and stable operation of hybrid power systems lies in reasonable capacity configuration, which is not only related to the power performance of the train, but also directly affects key indicators such as the system's mass, volume and economy.
[0071] Based on this, the present invention provides a capacity configuration method for a hybrid power train, which obtains operation simulation data according to the train information of the train, determines the constraint domain of the capacity configuration of each power source in the hybrid power source that provides power for the target train according to the operation simulation data and constraint conditions, and then determines the target capacity configuration point in the constraint domain with the goal of minimizing the total cost of capacity configuration, and configures the capacity of each power source according to the target capacity configuration point, thereby ultimately achieving the hybrid power train minimizing the total cost of capacity configuration while satisfying the operation simulation data, thereby improving economic benefits.
[0072] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0073] Figure 2 A flow chart of the capacity configuration method of a hybrid train provided in this application Figure 1 ,like Figure 2 As shown, the method includes:
[0074] S201. Acquire operation simulation data according to train information of a target train, wherein the operation simulation data is used to indicate time data and total power demand of each operation state of the target train during operation.
[0075] In this embodiment, the target train is a hybrid train, including at least two power sources. Figure 1 The hybrid power train in the embodiment includes two power sources: a diesel generator set and a power battery set.
[0076] Train information includes train parameters, operating indicators and line conditions. For example, train parameters may include train weight, load under different conditions, resistance characteristics, traction characteristics and braking characteristics, etc.; operating indicators may include the maximum operating speed and acceleration indicators of the train, etc., and line conditions include line mileage, station settings, ramp conditions, curve conditions, speed limit information, etc.
[0077] During the specific implementation process, the train parameters and operating indicators of the train can be input into the simulation software to establish a train model of the target train, and then the line conditions of the train can be input into the simulation software to establish a line model to obtain operation simulation data. The operation simulation data is used to indicate the time data and total power demand of each operating state of the target train during operation.
[0078] In some embodiments, the operation simulation data can be acquired in a minimum time-division operation mode to minimize the train operation process time.
[0079] In some embodiments, the running state of the train includes traction state, uniform speed state and braking state, and the running simulation data can be the time data and total power demand of the train model when it is in traction state, uniform speed state or braking state during the line model operation process, wherein the total power demand can be the total power required by the train at the corresponding time data. Optionally, the minimum time-division operation mode is used, and the forward and reverse calculation combination method is used to obtain the time and power data required for the train to run in the three-stage mode of traction-uniform speed-braking between each station.
[0080] For example, in the traction phase, the time and distance required for the train to accelerate from rest to the maximum operating speed are forward calculated based on the acceleration index and maximum operating speed of the target train, and the power demand required by the train in the traction phase is calculated based on the train parameters of the target train, such as the train weight. Similarly, the time and distance of the uniform speed phase and the braking phase are forward calculated, and then the results of the forward calculation are verified by reverse calculation to ensure that the total distance and time match, and the power demand of each phase is recorded.
[0081] In some embodiments, the operation simulation data may also be the correspondence between the time and the total power demand of the train model during the operation of the line model. For example, the total power demand required by the train model at time t is 700 kW.
[0082] S202. Determine a constraint domain for the capacity configuration of each power source in the hybrid power source providing power for the target train based on the operation simulation data and the constraint conditions, wherein the constraint conditions include vehicle performance constraints and a configurable range of the capacity of each power source, and each feasible capacity configuration point in the constraint domain includes a maximum power that each power source needs to provide.
[0083] In this embodiment, the capacity configuration of the hybrid train is used to allocate the maximum power that each power source needs to provide. That is, the capacity configuration needs to be determined based on the maximum power that each power source needs to provide. For example, if one power source is a diesel generator, the capacity of the diesel generator is obtained based on the rated power of the diesel generator being greater than the maximum power it needs to provide.
[0084] Optionally, the vehicle performance constraints include the maximum power of the drive motor and the energy transfer efficiency of each power source, and the configurable range of the capacity is the actual configurable capacity of each power source. The total power demand of the target train in each operation stage can be obtained based on the operation simulation data, then the constraint domain of the capacity configuration of each power source in the hybrid power source providing power for the target train can be determined based on the operation simulation data and the constraint conditions.
[0085] In some embodiments, the constraint domain includes a maximum operating speed power constraint and an acceleration power constraint. The maximum operating speed power constraint is used to constrain the sum of the powers provided by each power source of the target train to be greater than the power required when the target train runs at the maximum operating speed, and the acceleration power constraint is used to constrain the sum of the powers provided by each power source of the target train to be greater than the maximum power required during acceleration.
[0086] In the specific implementation process, the total power demand of the target train at the maximum operating speed can be obtained based on the operation simulation data, and the maximum operating speed power constraint can be determined by combining the constraint conditions. For example, if the constraint conditions include the energy transfer efficiency of each power source, then the maximum power of each power source needs to be multiplied by the corresponding energy transfer efficiency to obtain the actual maximum power that can be provided before the power constraint is performed.
[0087] For example, if the total power requirement of the target train at the maximum operating speed is 740 kW according to the operation simulation data, the following constraints can be obtained:
[0088] P1η1+P2η2≥740kw,
[0089] Among them, P1 is the maximum power of power source one, η1 is the transmission efficiency of power source one, P2 is the maximum power of power source two, and η2 is the transmission efficiency of power source two.
[0090] Similarly, when calculating the acceleration power constraint, it is necessary to combine the constraint conditions with the total power demand required for the target train to accelerate to obtain the acceleration power constraint.
[0091] Then, the constraint domain of each power source capacity configuration is constructed based on the maximum operating speed power constraint and the acceleration power constraint.
[0092] S203. Determine a target capacity configuration point in the constraint domain, wherein the target capacity configuration point can minimize the total cost of capacity configuration for the target train while satisfying the operation simulation data.
[0093] In this embodiment, each point in the constraint domain represents a capacity configuration scheme. In the constraint domain, the total cost can be minimized as the goal, and the target capacity configuration point can be determined in the constraint domain through an optimization algorithm. For example, a search algorithm can be used to traverse each point in the constraint domain, and after calculating the corresponding total cost, the point with the minimum total cost is selected as the target capacity configuration point; or a particle swarm optimization algorithm can be used to construct an objective function with the minimum total cost to obtain a global optimal solution, and the optimal solution is used as the target capacity configuration point.
[0094] S204: configure the capacity of each power source according to the target capacity configuration point.
[0095] It is understandable that the target capacity configuration point indicates the maximum power allocated to each power source. The capacity of each power source can be configured according to the allocated power.
[0096] For example, if the hybrid power includes a power battery pack and a diesel generator set, the capacity of the diesel generator set is obtained based on the fact that the rated power of the diesel generator set is greater than the maximum power it needs to provide, and the number of parallel and series power batteries is determined based on the maximum power that the power battery pack needs to provide and the model and parameters of the selected power battery.
[0097] The capacity configuration method of a hybrid power train provided in an embodiment of the present application obtains operation simulation data according to train information of a target train, wherein the operation simulation data is used to indicate time data and total power requirements of each operation state of the target train during operation; a constraint domain for the capacity configuration of each power source in a hybrid power source providing power to the target train is determined according to the operation simulation data and constraint conditions, wherein the constraint conditions include vehicle performance constraints and a configurable range of the capacity of each power source, and each feasible capacity configuration point in the constraint domain includes the maximum power that each power source needs to provide; a target capacity configuration point is determined in the constraint domain, wherein the target capacity configuration point can minimize the total cost of capacity configuration of the target train while satisfying the operation simulation data; and the capacity of each power source is configured according to the target capacity configuration point, thereby realizing capacity configuration with the actual line total cost minimized as the goal, reducing costs, and improving the economic benefits of hybrid power trains.
[0098] Figure 3 A flow chart of the capacity configuration method of a hybrid train provided in this application Figure 2 ,like Figure 3 As shown, in this embodiment Figure 2 Based on the embodiment, the process of determining the target capacity configuration point is described in detail. The method includes:
[0099] S301. Randomly generate a preset number of particles in a constraint domain as a particle swarm, where each particle represents a capacity configuration solution.
[0100] S302: For each particle in the particle swarm, calculate the total cost of the capacity configuration corresponding to the particle.
[0101] Specifically, before generating particles, it is necessary to set initial parameters, including the number of particles, the number of iterations, etc., and then assign an initial position and velocity to each particle to obtain an initial particle swarm. It can be understood that the position of a particle represents a potential solution to the problem, that is, a capacity configuration scheme, and the velocity of the particle represents the direction and distance of movement of the particle in the constraint domain.
[0102] Furthermore, for each particle in the particle swarm, the total cost of the capacity configuration corresponding to the particle is calculated.
[0103] Optionally, the total cost may include equipment cost, operation cost, and maintenance cost, and a calculation formula for the total cost is determined based on the equipment cost, operation cost, and maintenance cost. Then, the particle capacity configuration scheme is introduced into the calculation formula to obtain the corresponding total cost.
[0104] S303. Determine the individual extreme value of each particle and the global extreme value of the particle group according to the total cost. The individual extreme value is the capacity configuration point with the minimum total cost of the particle, and the global extreme value is the capacity configuration point with the minimum total cost in the particle group.
[0105] Specifically, the individual extreme value is the capacity configuration point with the minimum total cost of the particle, and the global extreme value is the capacity configuration point with the minimum total cost in the particle group. In this embodiment, in the first iteration, the initial position of each particle can be used as the individual extreme value, and its corresponding total cost can be recorded, and the initial position of the particle with the minimum total cost can be found among the individual extreme values of all particles as the initial global extreme value.
[0106] S304, updating the position and velocity of each particle according to the individual extremum and the global extremum of the particle, recalculating the total cost according to the updated particle, and updating the individual extremum and the global extremum, repeating the iterative process until the preset stop condition is met.
[0107] Further, the position and velocity of each particle are updated according to the velocity update formula and the position update formula.
[0108] In some embodiments, if x i (t) represents particle p i The position of particle p i The change of the position is achieved by adding the particle's velocity to the current position, so the position update formula can be: i (t) = x i (t-1)+v i (t).
[0109] It is understandable that the speed v i (t) determines the distance and direction of particle movement, which can be obtained based on the individual extreme value and global extreme value of the particle. For example, the velocity update formula can refer to the following formula:
[0110] v i (t) = v i (t-1)+C1r1(x pbest -x i (t))+C2r2(x gbest -x i (t))
[0111] Among them, x pbest represents the location of individual extreme values, x gbest Represents the position of the global extreme value, C1 and C2 are learning factors, and r1 and r2 are random numbers between [0,1].
[0112] Furthermore, after the position and velocity of the particle are updated, the total cost is recalculated based on the updated particle, and it is determined whether to update the individual extreme value based on the new total cost. Then, all the current individual extreme values are compared with the global extreme value, and the global extreme value is updated.
[0113] The iterative process is repeated until a preset stop condition is reached. Optionally, the stop condition may be reaching a preset number of iterations.
[0114] S305: Taking the global extreme value as the target capacity configuration point.
[0115] In this embodiment, when the preset stop condition is reached, the global extreme value is taken as the optimal solution, that is, as the target capacity configuration point, to obtain the maximum power of each power source.
[0116] The capacity configuration method of a hybrid train provided in an embodiment of the present application determines the target capacity configuration point in a constraint domain through a particle swarm optimization algorithm, so that the total cost of the capacity configuration is minimized, the cost of train operation is reduced, and the economic benefit is improved.
[0117] As an optional embodiment, Figure 1 In the embodiment shown, the hybrid power source includes an internal combustion generator set and a power battery set.
[0118] In hybrid trains, since the voltage of the power battery pack is generally lower than the voltage of the DC bus, the constraint domain also includes a DC bus voltage constraint to constrain the number of battery cells in the power battery pack to be less than the DC bus voltage of the target train. The specific constraint conditions can be referred to the following formula:
[0119]
[0120] Among them, Nbat,ser Represents the number of battery cells in series in the power battery pack; U bus Represents the voltage of the train DC bus; U bat Represents the rated voltage of the power battery cell.
[0121] Correspondingly, each feasible capacity configuration point in the constraint domain also includes the number of battery cells connected in series.
[0122] Figure 4 A flow chart of the capacity configuration method of a hybrid train provided in this application Figure 3 ,like Figure 4 As shown, in this embodiment Figure 3 Based on the embodiment, taking a hybrid train as an internal combustion engine + power battery pack hybrid train as an example, the process of determining the target capacity configuration point is described in detail. The method includes:
[0123] S401. Randomly generate a preset number of particles in the constraint domain as a particle swarm, each particle representing a capacity configuration scheme.
[0124] S402 . For each particle of the particle group, the purchase cost of the power battery pack is calculated according to the number of battery cells connected in series and the maximum power provided by the power battery pack.
[0125] It is understandable that the goal of the capacity configuration method provided in the embodiment of the present application is to minimize the total cost of the entire system. The total cost of the power system includes the initial purchase cost, the later maintenance cost and the operating cost generated during operation. The operating cost mainly considers the diesel cost during operation. For example, the total cost can be calculated according to the following formula:
[0126] minC=C battery +C ICE +C run ,
[0127] Among them, C battery Including the purchase cost of the power battery pack and its DCDC, C ICE Including the purchase cost of diesel generator sets, C run It is the operating cost, which mainly considers the cost of diesel consumed during operation.
[0128] Therefore, when calculating the total cost, for each particle of the particle group, the purchase cost of the power battery pack is first calculated based on the number of battery cells connected in series and the maximum power provided by the power battery pack.
[0129] In some embodiments, C battery It can also include the purchase cost and maintenance cost of the power battery pack and its DCDC.
[0130] Optional, if C batteryIncluding the purchase cost and maintenance cost of the power battery pack and its DCDC, the number of power batteries in series N in the particle swarm can be calculated based on bat,ser Information to determine C battery , the process is described below:
[0131] Specifically, according to the number of power batteries connected in series N bat,ser Determine the low voltage input voltage of the bidirectional DC-DC converter. After selecting the battery model, the rated voltage U of the battery cell can be determined. bat , then the nominal voltage at the low voltage end of the bidirectional DC-DC converter is U batDCDC,L , refer to the following formula for details:
[0132] U batDCDC,L =N bat,ser U bat
[0133] According to the actual operation line, in order to ensure that the train is in an emergency traction situation, for example, if the diesel generator set fails, the power battery pack needs to provide energy for the traction and auxiliary load of the EMU alone until the rescue platform can be implemented. Therefore, it is necessary to configure it according to the actual situation and obtain the lower limit of the power battery pack energy E power,s .
[0134] According to the characteristics of the energy storage system, the power battery pack needs to meet the train's maximum power demand P for the power battery pack. power,v and energy requirement E power,S , that is:
[0135] N bat m bat .PM bat ≥P power,v
[0136] N bat m bat EM bat ≥E power,S
[0137] The number of parallel power battery packs must meet the following requirements:
[0138]
[0139] Among them, N bat is the total number of cells in the power battery, m bat is the mass of the power battery cell, PM bat is the specific power of the power battery, EM bat is the specific energy of the power battery, N bat,ser is the number of power batteries connected in series, N bat,par is the number of power batteries connected in parallel.
[0140] Usually, the specific energy and specific power of a power battery are the maximum output capacity of the power battery. In actual use, it is necessary to prevent the overcharge and overdischarge of the power battery. The maximum output energy that a power battery pack can provide is:
[0141] E bat,max =U bat,nom Q bat D bat K b
[0142] Among them, U bat,nom It is the voltage of the power battery pack when it is operating at the maximum continuous discharge current; Q bat is the power battery cell capacity, D bat is the discharge depth of the power battery, K b It is the coefficient to be considered when calculating the power battery capacity redundancy, expressed as:
[0143] K b =K b1 .K b2 .K b3 .K b4
[0144] Among them, K b1 is the charging efficiency coefficient; K b2 is the large current discharge coefficient; K b3 is the temperature coefficient; K b4 is the life curve coefficient.
[0145] Furthermore, when considering the characteristics of power batteries such as overcharge and over discharge,
[0146] C bat,max Q bat,Box U bat,nom ≥P power,v
[0147] U bat,max Q bat,Box D bat K b ≥E power,S
[0148] Among them, C bat,max It is the maximum discharge rate of the power battery.
[0149] In summary, the number of parallel connections of power battery packs must meet the following requirements:
[0150]
[0151] Among them, m bat M is the mass of the power battery cell; bat is the total mass of the power battery.
[0152] C battery Including the purchase and maintenance costs of the power battery pack and its DCDC, which is proportional to the number of power batteries in parallel and the maximum power level. battery It can be calculated according to the following formula:
[0153] C battery =a1P bat_max +a2N bat,ser +a3N bat,par ,a1,a2,a3>0
[0154] It should be noted that the above a1, a2, and a3 can be set according to actual work requirements, and this embodiment does not make any specific restrictions here.
[0155] S403. Calculate the purchase cost of the internal combustion generator according to the maximum power provided by the internal combustion generator set.
[0156] Secondly, calculate the purchase cost of the internal combustion generator based on the maximum power provided by the internal combustion generator set.
[0157] In some embodiments, C ICE It may also include the purchase cost and maintenance cost of the diesel generator set and its rectifier, etc., which are not specifically limited in this embodiment.
[0158] Alternatively, the price of the diesel generator set and its rectifier of the EMU is positively correlated with its power, volume and weight, so the greater the power of the diesel generator set, the higher its purchase cost + maintenance cost. ICE It can be calculated according to the following formula:
[0159] C ICE =b1P ICE_max , b1>0
[0160] S404, using the Pontryagin energy management algorithm to calculate the minimum operating cost.
[0161] The Pontryagin energy management algorithm is an effective method for optimizing energy management strategies. By rationally constructing the Hamiltonian function, solving the minimization problem and considering the constraints, a better energy allocation strategy can be obtained, thereby improving the economy and operation efficiency of the system.
[0162] In some embodiments, the minimum operation cost mainly includes the fuel consumption of the train during operation. The fuel consumption cost of the train during operation can be calculated according to the allocated maximum power of the internal combustion generator corresponding to the particle and the fuel consumption-power curve.
[0163] In this embodiment, in order to obtain the minimum operating cost, the global diesel consumption of the target train during operation needs to be used as the optimization target. Specifically, the train operation line parameters, train parameters, and the maximum charge and discharge power P of the power battery pack are used. bat_max And the corresponding power level power battery pack information, the maximum charge and discharge power P of the diesel generator set ICE_max and the corresponding power level diesel generator information as input, assuming that the train runs with the Pontryagin energy management algorithm, the operation simulation is carried out and the operation cost is calculated.
[0164] S405. Calculate the total cost based on the purchase cost of the power battery pack, the purchase cost of the internal combustion generator, and the operating cost.
[0165] Finally, the total cost is obtained by adding the purchase cost of the power battery pack, the purchase cost of the internal combustion generator, and the operating cost.
[0166] S406. Determine the individual extreme value of each particle and the global extreme value of the particle group according to the total cost. The individual extreme value is the capacity configuration point with the minimum total cost of the particle, and the global extreme value is the capacity configuration point with the minimum total cost in the particle group.
[0167] S407. Update the position and velocity of each particle according to the individual extremum and the global extremum of the particle.
[0168] S408, determine whether the preset stop condition is met, if so, execute S409, if not, execute S402.
[0169] S409: Taking the global extreme value as the target capacity configuration point.
[0170] Figure 5 A flow chart of the capacity configuration method of a hybrid train provided in this application Figure 4 ,like Figure 5 As shown, in this embodiment Figure 4 Based on the embodiment, the process of calculating the minimum operating cost is described in detail, and the method includes:
[0171] S501. Taking the charge state of the power battery pack as a state variable, establishing boundary conditions with the charge state at the initial moment of the target train running and the charge state at the end moment of the running task being less than a preset threshold as a restriction, and determining the running cost function with the minimum total cost as the goal.
[0172] In this embodiment, the charge state of the power battery pack is taken as the state variable SOC(t).
[0173] In some embodiments, in order to maintain the reliable operation of the train hybrid power system, it is necessary to limit the output power of the diesel generator set, the output power of the battery, the state of charge of the battery, and the output current of the battery, so that the hybrid power system operates within a reasonable working range. The limiting conditions are as follows:
[0174]
[0175] Among them, SOC b_min Indicates the lower limit of the battery state of charge; SOC b_max Indicates the upper limit of the battery charge state; I bat Represents the output current of the battery pack; I bat_min with I bat_max Respectively represent the maximum allowable charging current and maximum allowable discharging current of the battery pack; P bat_min With P bat_max Respectively represent the maximum allowable charging power and maximum allowable discharging power of the battery pack; P ICE_min With P ICE_max They respectively represent the lower and upper limits of the allowable output power of the diesel generator set.
[0176] Secondly, during operation, in order to ensure that the total power demand of the train is met and there is no power shortage, the hybrid power system should always meet the following power limits:
[0177]
[0178] It is understandable that since the target train runs on an off-grid line throughout the entire journey and none of the stations are equipped with charging devices, the only source of energy for the on-board power battery is the energy generated by the diesel engine and the energy generated by the train's regenerative braking. In order to keep the battery sufficiently charged and run in the high-efficiency range for as long as possible, so that the power battery SOC is kept within a certain range during the operation of the train, the diesel generator set is used to charge the power battery pack through the battery management system when arriving at the next station to return the power battery to its initial charge. Therefore, it is necessary to establish boundary conditions with the charge state at the initial moment of operation and the charge state at the end of the operation task being less than the preset threshold as the limit.
[0179] In some embodiments, the boundary conditions are set as follows:
[0180]
[0181] Among them, SOC0 represents the battery state of charge value of the battery pack at the initial moment of the train operation mission; SOC end Indicates the state of charge value of the battery pack at the end of the train operation mission.
[0182] In some embodiments, the operating cost function may refer to the following formula:
[0183]
[0184] Among them, SOC0 is the charge state of the target train at the initial time of operation, SOC f is the charge state at the end of the target train operation mission, Q ICE (t) is the instantaneous diesel consumption mass of the target train at time t, and f is the termination time of the target train operation mission.
[0185] S502: Construct a Hamiltonian function according to the running cost function.
[0186] In some embodiments, the Hamiltonian function is as follows:
[0187]
[0188] in, Denote the derivative of the cost function J(t) with respect to time, which is derived from the above running cost:
[0189]
[0190] SOC(t) represents the charge state of the power battery pack at time t. Refer to the following formula:
[0191]
[0192] In this embodiment, SOC(t) is a state variable, λ represents a co-state variable of the control system, and the co-state equation is obtained by taking partial derivatives of the state variable according to the Hamiltonian function as follows:
[0193]
[0194] S503: Initialize co-state variables.
[0195] S504, obtaining a power sequence, where the power sequence is used to indicate the power of the power battery pack and the power of the internal combustion generator set at each moment during the operation of the target train when the function value of the Hamiltonian function reaches a minimum value.
[0196] Specifically, after selecting a Lagrange multiplier λ (initially λ (0) (0)) can be used to find the optimal value of each moment in the task process, and find the Hamiltonian function H(SOC(t), P) at each moment within the power tolerance range. bat (t), P ICE (t),λ(t),t) reaches the minimum battery power P bat(t) and the output power P of the diesel generator set ICE (t), and finally obtain the control trajectory of the diesel-electric hybrid system as u=[P bat , P ICE The process of obtaining the optimal power sequence of the diesel-electric hybrid control system is as follows:
[0197]
[0198]
[0199] in, represents the optimal diesel generator output power value at time t; Represents the optimal battery pack output power value at time t.
[0200] S505: Determine whether the power sequence meets the boundary conditions. If so, execute S506; if not, execute S507.
[0201] S506: If satisfied, calculate the minimum operating cost according to the power sequence.
[0202] S507: If not satisfied, update the co-state variable and continue to execute S504.
[0203] The calculated t f The final state and λ at time (0) (t f ) satisfies the boundary conditions. Specifically, when λ (0) (t f ) is equal to the quadratic penalty function α[SOC(t)-SOC(0)] 2 The partial derivative of When the boundary condition is met, that is, the difference between the charge state at the initial moment and the charge state at the termination moment of the running task is less than the preset threshold.
[0204] In some embodiments, the preset threshold ε is defined as 0.5, and the boundary condition needs to be satisfied as shown in the following equation:
[0205] |λ (0) (t f )-2α[SOC(t f )-SOC(0)]|<ε
[0206] If the above inequality is not satisfied, λ is updated according to Newton's method. Specifically, a step size adjustment factor τ is introduced, which ranges from 0 to 1 and helps prevent divergence; the adjustment factor is set to 0.5.
[0207]
[0208] After λ is updated, the optimal calculation is performed again at each moment in the operation process to obtain the power sequence again until the boundary conditions are met.
[0209] Furthermore, the operating cost is calculated according to the power of the internal combustion generator set at each moment in the power sequence and the operating cost function.
[0210] The method provided in this embodiment reasonably distributes the output power of the hybrid power source by applying the Pontryagin energy management algorithm, reduces unnecessary energy consumption while meeting the train power performance indicators, thereby minimizing the total cost and improving the economic benefits of the train.
[0211] Figure 6 The schematic diagram of the structure of the capacity configuration device of the hybrid train provided in this application is as follows: Figure 6 As shown, the capacity configuration device 60 provided in this embodiment includes:
[0212] The acquisition module 601 is used to acquire operation simulation data according to the train information of the target train, wherein the operation simulation data is used to indicate the time data and total power demand of each operation state of the target train during operation.
[0213] The constraint module 602 is used to determine the constraint domain of the capacity configuration of each power source in the hybrid power source providing power for the target train based on the operation simulation data and the constraint conditions, wherein the constraint conditions include the vehicle performance constraint and the configurable range of the capacity of each power source, and each feasible capacity configuration point in the constraint domain includes the maximum power that each power source needs to provide.
[0214] The determination module 603 is used to determine a target capacity configuration point in the constraint domain, wherein the target capacity configuration point can minimize the total cost of capacity configuration of the target train under the premise of satisfying the operation simulation data.
[0215] The configuration module 604 is used to configure the capacity of each power source according to the target capacity configuration point.
[0216] In one possible implementation, the operating index includes at least a maximum operating speed and an acceleration index, and the constraint module 602 is specifically used to determine a maximum operating speed power constraint based on the operating simulation data and the constraint conditions, wherein the maximum operating speed power constraint is used to constrain the sum of the powers provided by each power source of the target train to be greater than the power required when the target train runs at the maximum operating speed.
[0217] The acceleration power constraint is determined according to the operation simulation data and the constraint conditions, wherein the acceleration power constraint is used to constrain the sum of the powers provided by various power sources of the target train to be greater than the maximum power required for acceleration.
[0218] A constraint domain of capacity configuration is determined according to the maximum operating speed power constraint and the acceleration power constraint.
[0219] In a possible implementation, the determination module 603 is specifically configured to: randomly generate a preset number of particles in the constraint domain as a particle swarm, where each particle represents a capacity configuration solution.
[0220] For each particle in the particle swarm, the total cost of the capacity configuration corresponding to the particle is calculated, and the individual extreme value of each particle and the global extreme value of the particle swarm are determined based on the total cost. The individual extreme value is the capacity configuration point with the minimum total cost of the particle, and the global extreme value is the capacity configuration point with the minimum total cost in the particle swarm.
[0221] The position and velocity of each particle are updated according to the individual extremum and global extremum of the particle, and the total cost is recalculated according to the updated particle, and the individual extremum and global extremum are updated. The iterative process is repeated until the preset stop condition is met.
[0222] The global extreme value is taken as the target capacity configuration point.
[0223] In one possible implementation, the hybrid power source includes an internal combustion generator set and a power battery pack, the constraint domain also includes a DC bus voltage constraint domain, the number of battery cells connected in series in the power battery pack is less than the DC bus voltage of the target train; each feasible capacity configuration point in the constraint domain also includes the number of battery cells connected in series.
[0224] In one possible implementation, the determination module 603 is specifically used to: calculate the purchase cost of the power battery pack based on the number of battery cells connected in series and the maximum power provided by the power battery pack; calculate the purchase cost of the internal combustion generator based on the maximum power provided by the internal combustion generator set; calculate the minimum operating cost using the Pontryagin energy management algorithm; and calculate the total cost based on the purchase cost of the power battery pack, the purchase cost of the internal combustion generator, and the operating cost.
[0225] In a possible implementation, the determination module 603 is specifically used to: take the charge state of the power battery pack as a state variable, set the charge state at the initial moment of the target train operation and the charge state at the end moment of the operation task as a limit that are less than a preset threshold, establish boundary conditions, and determine the operation cost function with the minimum total cost as the goal; construct a Hamiltonian function according to the operation cost function; solve the optimal solution of the Hamiltonian function that meets the boundary conditions to obtain the minimum operation cost.
[0226] In a possible implementation, the operating cost function is as follows:
[0227]
[0228] Among them, SOC0 is the charge state of the target train at the initial time of operation, SOC f is the charge state at the end of the target train operation mission, Q ICE (t) is the instantaneous diesel consumption mass of the target train at time t, f is the termination time of the target train operation task; the Hamiltonian function is as follows:
[0229]
[0230] in, It represents the derivative of the cost function J(t) with respect to time, and SOC(t) represents the charge state of the power battery pack at time t.
[0231] In a possible implementation, the determination module 603 is specifically used to: initialize the co-state variables and obtain the power sequence, where the power sequence is used to indicate the power of the power battery pack and the power of the internal combustion generator set at each moment during the operation of the target train when the function value of the Hamiltonian function reaches a minimum.
[0232] Determine whether the power sequence meets the boundary conditions; if so, calculate the minimum operating cost based on the power sequence; if not, update the co-state variables and re-acquire the power sequence until the updated power sequence meets the boundary conditions.
[0233] The capacity configuration device for a hybrid train provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be described in detail here.
[0234] Figure 7 This is a schematic diagram of the structure of the capacity configuration device of the hybrid train provided in this application. Figure 7 As shown, the electronic device 70 provided in this embodiment includes: at least one processor 701 and a memory 702. Optionally, the device 70 further includes a communication component 703. The processor 701, the memory 702 and the communication component 703 are connected via a bus 704.
[0235] In a specific implementation process, at least one processor 701 executes the computer-executable instructions stored in the memory 702, so that at least one processor 701 executes the above method.
[0236] The specific implementation process of the processor 701 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.
[0237] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.
[0238] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.
[0239] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.
[0240] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.
[0241] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.
[0242] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.
[0243] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.
[0244] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.
[0245] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0246] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0247] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0248] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.
[0249] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.
Claims
1. A capacity configuration method for a hybrid train, characterized in that: include: Acquiring operation simulation data according to train information of the target train, wherein the operation simulation data is used to indicate time data and total power demand of each operation state of the target train during operation; Determining a constraint domain of capacity configuration of each power source in a hybrid power source providing power for the target train according to the operation simulation data and constraint conditions, wherein the constraint conditions include vehicle performance constraints and a configurable range of capacity of each power source, and each feasible capacity configuration point in the constraint domain includes a maximum power that each power source needs to provide; Determining a target capacity configuration point in the constraint domain, wherein the target capacity configuration point can minimize the total cost of the capacity configuration for the target train while satisfying the operation simulation data; The capacity of each of the power sources is configured according to the target capacity configuration point.
2. The method according to claim 1, characterized in that The constraint domain for determining the capacity configuration of each power source in the hybrid power source providing power for the target train according to the operation simulation data and the constraint conditions includes: Determine a maximum operating speed power constraint according to the operation simulation data and the constraint condition, wherein the maximum operating speed power constraint is used to constrain the sum of the powers provided by the various power sources of the target train to be greater than the power required when the target train runs at the maximum operating speed; Determining an acceleration power constraint according to the operation simulation data and the constraint condition, wherein the acceleration power constraint is used to constrain the sum of the powers provided by each power source of the target train to be greater than the maximum power required for acceleration; A constraint domain of capacity configuration is determined according to the maximum operating speed power constraint and the acceleration power constraint.
3. The method according to claim 2, characterized in that The determining of the target capacity configuration point in the constraint domain includes: Randomly generating a preset number of particles in the constraint domain as a particle group, each of the particles representing a capacity configuration scheme; For each particle of the particle swarm, the total cost of the capacity configuration corresponding to the particle is calculated, and the individual extreme value of each particle and the global extreme value of the particle swarm are determined according to the total cost, wherein the individual extreme value is the capacity configuration point with the minimum total cost of the particle, and the global extreme value is the capacity configuration point with the minimum total cost in the particle swarm; The position and velocity of each particle are updated according to the individual extreme value of the particle, the total cost is recalculated according to the updated particle, and the individual extreme value and the global extreme value are updated, and the iterative process is repeated until a preset stop condition is met; The global extreme value is used as the target capacity configuration point.
4. The method according to claim 3, characterized in that The hybrid power source includes an internal combustion generator set and a power battery pack, the constraint domain also includes a DC bus voltage constraint domain, and the number of battery cells in the power battery pack connected in series is less than the DC bus voltage of the target train; Each feasible capacity configuration point in the constraint domain also includes the number of battery cells connected in series.
5. The method according to claim 4, characterized in that The total cost of the capacity configuration corresponding to the computing particle includes: Calculate the purchase cost of the power battery pack according to the number of battery cells connected in series and the maximum power provided by the power battery pack; Calculating the purchase cost of the internal combustion generator according to the maximum power provided by the internal combustion generator set; Calculate the minimum operating cost using the Pontryagin energy management algorithm; The total cost is calculated based on the purchase cost of the power battery pack, the purchase cost of the internal combustion generator and the operating cost.
6. The method according to claim 5, characterized in that The method of calculating the minimum operating cost using the Pontryagin energy management algorithm includes: The charge state of the power battery pack is used as a state variable, and the charge state at the initial moment of the operation of the target train and the charge state at the end moment of the operation task are limited to be less than a preset threshold, a boundary condition is established, and an operation cost function is determined with the minimum total cost as the goal; Constructing a Hamiltonian function according to the operating cost function; An optimal solution of the Hamiltonian function that satisfies the boundary conditions is solved to obtain the minimum operating cost.
7. The method according to claim 6, characterized in that The operating cost function is as follows: Wherein, the SOC0 is the charge state of the target train at the initial time of operation, and the SOC f is the charge state at the termination time of the target train operation task, and the Q ICE (t) is the instantaneous diesel consumption mass of the target train at time t, and f is the termination time of the target train operation mission; The Hamiltonian function is as follows: Among them, the represents the derivative of the cost function J(t) with respect to time, and SOC(t) represents the charge state of the power battery pack at time t.
8. The method according to claim 7, characterized in that The step of solving the optimal solution of the Hamiltonian function that satisfies the boundary condition to obtain the minimum operating cost includes: Initializing the co-state variable and acquiring a power sequence, wherein the power sequence is used to indicate the power of the power battery group and the power of the internal combustion generator group at each moment during the operation of the target train when the function value of the Hamiltonian function reaches a minimum value; Determining whether the power sequence satisfies the boundary condition; If satisfied, calculating the minimum operating cost according to the power sequence; If not, the co-state variable is updated, and the power sequence is reacquired until the updated power sequence meets the boundary condition.
9. A capacity configuration method for a hybrid train, characterized in that: include: An acquisition module, used for acquiring operation simulation data according to train information of a target train, wherein the operation simulation data is used for indicating time data and total power demand of each operation state of the target train during operation; A constraint module, used to determine a constraint domain of capacity configuration of each power source in a hybrid power source providing power for the target train according to the operation simulation data and constraint conditions, wherein the constraint conditions include vehicle performance constraints and a configurable range of capacity of each power source, and each feasible capacity configuration point in the constraint domain includes a maximum power that each power source needs to provide; A determination module, configured to determine a target capacity configuration point in the constraint domain, wherein the target capacity configuration point can minimize the total cost of the capacity configuration for the target train while satisfying the operation simulation data; A configuration module is used to configure the capacity of each of the power sources according to the target capacity configuration point.
10. A capacity configuration device for a hybrid train, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 8.
11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.
