Railway vehicle operation processing method and device and railway vehicle

Abstract

The invention provides an operation processing method and device of a railway vehicle and the railway vehicle, the method is applied to the railway vehicle, the railway vehicle takes a hydrogen fuel cell and a lithium battery as power sources, and the method comprises the following steps: calling a pre-trained operation processing network model, the operation processing network model is used for determining the running acceleration of the railway vehicle at the next moment and the output power of the hydrogen fuel cell according to the operation parameters of the railway vehicle at the current moment; acquiring operation parameters of the railway vehicle at the current moment, and inputting the operation parameters into an operation processing network model to obtain the running acceleration of the railway vehicle at the next moment and the output power of the hydrogen fuel cell, which are output by the operation processing network model, under the conditions that the rail vehicle runs according to the running acceleration and the hydrogen fuel cell outputs power according to the output power, the running cost of the rail vehicle is minimum. The energy consumption of the hydrogen energy train is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of rail vehicles, and in particular to an operation processing method and device for a rail vehicle and a rail vehicle. Background Art

[0002] As global awareness of environmental protection increases and the concept of sustainable development becomes more popular, reducing energy consumption and pollution in the railway industry and achieving a green, low-carbon transportation model has become an important direction for the development of urban transportation. Among many new energy sources, hydrogen is considered to be an ideal choice to meet the high power requirements of the railway industry due to its high energy efficiency, zero carbon emissions and wide sources. Hydrogen trains with hydrogen fuel cells as the main power source have emerged.

[0003] Therefore, finding a rail vehicle operation processing method that can effectively reduce the energy consumption of hydrogen trains has become a current research hotspot. Summary of the invention

[0004] The present invention provides a rail vehicle operation processing method, device and rail vehicle, which can effectively reduce the energy consumption of hydrogen energy trains and reduce the operation cost of rail vehicles.

[0005] The present invention provides an operation processing method for a rail vehicle, the method is applied to a rail vehicle, the rail vehicle uses a hydrogen fuel cell and a lithium battery as power sources, the method comprises: calling a pre-trained operation processing network model, wherein the operation processing network model is used to determine the running acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell according to the operation parameters of the rail vehicle at the current moment; obtaining the operation parameters of the rail vehicle at the current moment, and inputting the operation parameters into the operation processing network model, and obtaining the running acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell output by the operation processing network model, so that the operation cost of the rail vehicle is minimized when the rail vehicle runs according to the running acceleration and the hydrogen fuel cell outputs power according to the output power.

[0006] According to a rail vehicle operation processing method provided by the present invention, the operation processing network model is trained in the following manner: constructing a training data set, wherein the training data set is determined based on an optimal data set, and the optimal data set is determined based on an operation curve and a power source curve determined based on historical operation parameters of the rail vehicle, wherein the operation curve is used to characterize the corresponding relationship between the driving acceleration of the rail vehicle and time determined under the minimum operation cost of the rail vehicle; the power source curve is used to characterize the corresponding relationship between the output power of the hydrogen fuel cell and time determined under the minimum operation cost of the rail vehicle; based on the training data set, the operation processing network model is trained according to a proximal strategy optimization algorithm to obtain a trained operation processing network model.

[0007] According to a rail vehicle operation processing method provided by the present invention, the operation processing network model includes a critic network model; the operation processing network model is trained according to a proximal strategy optimization algorithm based on the training data set to obtain a trained operation processing network model, specifically including: determining the operation state of the rail vehicle based on the operation curve and the power source curve in the training data set, wherein the operation state includes the operation speed, the charge state of the hydrogen fuel cell and the operation distance; based on the training data set, an actor network model corresponding to the critic network model is trained according to a proximal strategy optimization algorithm; the operation state is input into the actor network model to obtain the next moment execution action corresponding to the operation state output by the actor network model, wherein the next moment execution action includes the predicted driving acceleration of the rail vehicle at the next moment under the operation state and the predicted output power of the hydrogen fuel cell; based on the next moment execution action and the next moment operation state corresponding to the next moment execution action, a network loss function is determined, and the operation processing network model is iteratively trained based on the network loss function until the operation processing network model converges to obtain a trained operation processing network model.

[0008] According to a rail vehicle operation processing method provided by the present invention, the optimal data set is determined in the following manner: constructing an objective function of the rail vehicle during operation, wherein the objective function is a function that characterizes the operation cost of the rail vehicle; obtaining historical operation route information of the rail vehicle, wherein the historical operation route information includes speed limit information and station stay duration information of the historical operation route of the rail vehicle; based on the Hermitian-Simpson collocation technology, processing the historical operation route information and the objective function to obtain the operation curve and the power source curve; and determining the optimal data set based on the operation curve and the power source curve.

[0009] According to a rail vehicle operation processing method provided by the present invention, the historical operation line information and the objective function are processed based on the Hermitian-Simpson collocation technology to obtain the operation curve and the power source curve, which specifically includes: based on the Hermitian-Simpson collocation technology, the objective function is subjected to dimensionality reduction processing to obtain a nonlinear programming corresponding to the objective function; based on the historical operation line information and the nonlinear programming, the operation curve and the power source curve are obtained.

[0010] According to a rail vehicle operation processing method provided by the present invention, the objective function is subjected to dimensionality reduction processing based on the Hermitian-Simpson collocation technology to obtain a nonlinear programming corresponding to the objective function, specifically comprising: dividing the historical operation route of the rail vehicle into a preset number of operation intervals, and transforming the operation intervals in the time domain to obtain transformed operation intervals, wherein the interval range of the transformed operation intervals is within a preset range; based on the transformed operation intervals, Legendre polynomials under the transformed operation intervals are obtained; based on the Legendre polynomials under the transformed operation intervals, the state space in the objective function is discretized to obtain a discretized state space; based on the discretized state space, the derivative of the discretized state space is determined; and the derivative of the discretized state space is integrated to obtain a nonlinear programming corresponding to the objective function, so as to achieve dimensionality reduction processing of the objective function.

[0011] According to a rail vehicle operation processing method provided by the present invention, the preset number of operation intervals are determined in the following manner: determining the allowable error of each operation interval; when the allowable error of the operation interval is greater than the maximum allowable error, redividing the operation interval until the allowable error of the preset number of operation intervals obtained by the redivision is less than the maximum allowable error and greater than the minimum allowable error; when the allowable error of the operation interval is less than the minimum allowable error, merging the operation intervals until the allowable error of the preset number of operation intervals obtained after the merging is less than the maximum allowable error and greater than the minimum allowable error.

[0012] According to a rail vehicle operation processing method provided by the present invention, the objective function is determined in the following manner: determining a first equivalent hydrogen consumption of the hydrogen fuel cell, a second equivalent hydrogen consumption of the lithium battery, and a first value coefficient of hydrogen; determining a first loss of the hydrogen fuel cell, a second loss of the lithium battery, a second value coefficient of the hydrogen fuel cell, and a third value coefficient of the lithium battery; determining the hydrogen consumption cost of the rail vehicle during operation based on the first equivalent hydrogen consumption, the second equivalent hydrogen consumption, and the first value coefficient; determining the life cost of the power source of the rail vehicle during operation based on the first loss, the second loss, the second value coefficient, and the third value coefficient; determining the objective function based on the hydrogen consumption cost and the life cost of the power source.

[0013] The present invention also provides an operation processing device for a rail vehicle, the device is applied to a rail vehicle, the rail vehicle uses a hydrogen fuel cell and a lithium battery as power sources, the device comprises: a calling module, used to call a pre-trained operation processing network model, wherein the operation processing network model is used to determine the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell according to the operation parameters of the rail vehicle at the current moment; a processing module, used to obtain the operation parameters of the rail vehicle at the current moment, and input the operation parameters into the operation processing network model to obtain the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell output by the operation processing network model, so that the operation cost of the rail vehicle is minimized when the rail vehicle runs according to the driving acceleration and the hydrogen fuel cell outputs power according to the output power.

[0014] The present invention also provides a rail vehicle, comprising: a rail vehicle body, and a processor, wherein the processor is used to execute the operation processing method of the rail vehicle.

[0015] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the operation processing method of the rail vehicle as described above is implemented.

[0016] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the operation processing method of a rail vehicle as described in any one of the above is implemented.

[0017] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned rail vehicle operation processing methods.

[0018] The operation processing method, device and rail vehicle provided by the present invention are applied to rail vehicles, and the rail vehicles are powered by hydrogen fuel cells and lithium batteries. The method includes: calling a pre-trained operation processing network model; obtaining the operation parameters of the rail vehicle at the current moment, and inputting the operation parameters into the operation processing network model, and obtaining the running acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell output by the operation processing network model, so that the rail vehicle runs according to the running acceleration and the hydrogen fuel cell outputs power according to the output power, and the operation cost of the rail vehicle is minimized. Parameter control is achieved from the power source end and the load end to effectively reduce the energy consumption of the hydrogen energy train, thereby reducing the operation cost of the rail vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 It is one of the flow charts of the operation processing method of the rail vehicle provided by the present invention.

[0021] Figure 2 The present invention provides a flow chart of training the operation processing network model based on the training data set according to the proximal strategy optimization algorithm to obtain the trained operation processing network model.

[0022] Figure 3 It is a schematic diagram of a flow chart for determining an optimal data set provided by the present invention.

[0023] Figure 4 The Hermitian-Simpson collocation technology provided by the present invention performs dimension reduction processing on the objective function to obtain a flow chart of nonlinear programming corresponding to the objective function.

[0024] Figure 5 It is a schematic diagram of a flow chart for determining an objective function provided by the present invention.

[0025] Figure 6 It is a structural schematic diagram of the operation processing device of the rail vehicle provided by the present invention.

[0026] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] The rail vehicle operation processing method provided by the present invention deeply explores the "source-load" coupling characteristics of hydrogen-powered high-speed trains, further reducing the operation consumption of fuel cell trains; at the same time, it rationally allocates the outputs between the various systems of the train, thereby significantly improving the operation efficiency and durability of the fuel cell power source system, and effectively reducing the cost of hydrogen trains.

[0029] Figure 1 It is one of the flow charts of the operation processing method of the rail vehicle provided by the present invention.

[0030] The following will be combined Figure 1 The process of the rail vehicle operation processing method provided by the present invention is described.

[0031] In an exemplary embodiment of the present invention, the operation processing method of a rail vehicle can be applied to a rail vehicle. The rail vehicle can be powered by a hydrogen fuel cell and a lithium battery. Figure 1 It can be seen that the operation processing method of the rail vehicle may include step 110 and step 120, and each step will be introduced below.

[0032] In step 110, a pre-trained operation processing network model is called, wherein the operation processing network model is used to determine the running acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell according to the operation parameters of the rail vehicle at the current moment.

[0033] In one embodiment, a pre-trained operation processing network model can be called. In one example, the operation processing network model can be a critic network model. Among them, the operation processing network model can determine the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell according to the operating parameters of the rail vehicle at the current moment. It can be understood that if the rail vehicle runs according to the driving acceleration and the hydrogen fuel cell outputs power according to the output power, the operation cost of the rail vehicle can be minimized. In another example, the operating parameters can be the acceleration of the rail vehicle at the current moment and the output power of the hydrogen fuel cell.

[0034] In step 120, the operating parameters of the rail vehicle at the current moment are obtained, and the operating parameters are input into the operation processing network model to obtain the driving acceleration of the rail vehicle and the output power of the hydrogen fuel cell at the next moment output by the operation processing network model, so that the operating cost of the rail vehicle is minimized when the rail vehicle runs according to the driving acceleration and the hydrogen fuel cell outputs power according to the output power.

[0035] In another embodiment, the operating parameters of the rail vehicle at the current moment can be obtained, such as the acceleration of the rail vehicle at the current moment and the output power of the hydrogen fuel cell at the current moment. Further, the operating parameters are input into the operation processing network model, and the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell output by the operation processing network model can be obtained, so that the rail vehicle runs according to the driving acceleration and the hydrogen fuel cell outputs power according to the output power, and the operating cost of the rail vehicle is minimized. Parameter control is achieved from the power source end and the load end to effectively reduce the energy consumption of the hydrogen train, thereby reducing the operating cost of the rail vehicle.

[0036] The operation processing method of a rail vehicle provided by the present invention is applied to a rail vehicle, and the rail vehicle uses a hydrogen fuel cell and a lithium battery as a power source. The method includes: calling a pre-trained operation processing network model; obtaining the operation parameters of the rail vehicle at the current moment, and inputting the operation parameters into the operation processing network model, and obtaining the running acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell output by the operation processing network model, so that the rail vehicle runs according to the running acceleration and the hydrogen fuel cell outputs power according to the output power, and the operation cost of the rail vehicle is minimized. Parameter control is realized from the power source end and the load end to effectively reduce the energy consumption of the hydrogen energy train, thereby reducing the operation cost of the rail vehicle.

[0037] In another exemplary embodiment of the present invention, the above-mentioned embodiment is continued to be used as an example for description, wherein the operation processing network model can be trained in the following manner: Constructing a training data set, wherein the training data set is determined based on an optimal data set, and the optimal data set is determined based on an operation curve and a power source curve determined based on historical operation parameters of the rail vehicle, wherein the operation curve is used to characterize the corresponding relationship between the travel acceleration of the rail vehicle and time determined under the condition that the operation cost of the rail vehicle is minimized; and the power source curve is used to characterize the corresponding relationship between the output power of the hydrogen fuel cell and time determined under the condition that the operation cost of the rail vehicle is minimized; Based on the training data set, the operation processing network model is trained according to the proximal strategy optimization algorithm to obtain a trained operation processing network model.

[0038] In one embodiment, a training data set may be constructed, wherein the training data set is determined based on an optimal data set. In one example, the optimal data set is determined based on an operation curve and a power source curve determined based on historical operation parameters of the rail vehicle. The operation curve may be used to characterize the corresponding relationship between the travel acceleration of the rail vehicle and time determined when the operation cost of the rail vehicle is minimized; the power source curve may be used to characterize the corresponding relationship between the output power of the hydrogen fuel cell and time determined when the operation cost of the rail vehicle is minimized.

[0039] Furthermore, based on the training data set, the operation processing network model is trained according to the proximal strategy optimization algorithm to obtain a trained operation processing network model. The operation processing network model trained based on the training data set can determine the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell according to the operating parameters of the rail vehicle at the current moment, so that the operation cost of the rail vehicle is minimized when the rail vehicle runs according to the driving acceleration and the hydrogen fuel cell outputs power according to the output power.

[0040] Figure 2 The present invention provides a flow chart of training the operation processing network model based on the training data set according to the proximal strategy optimization algorithm to obtain the trained operation processing network model.

[0041] The following will be combined Figure 2 The process of training the operation processing network model based on the training data set and according to the proximal strategy optimization algorithm to obtain the trained operation processing network model is described.

[0042] In an exemplary embodiment of the present invention, the running process network model may include a critic network model. Figure 2 It can be seen that based on the training data set, the operation processing network model is trained according to the proximal strategy optimization algorithm to obtain the trained operation processing network model, which may include steps 210 to 240. Each step will be introduced below.

[0043] In step 210, the operating state of the rail vehicle is determined based on the operating curve and the power source curve in the training data set, wherein the operating state includes the operating speed, the charge state of the hydrogen fuel cell, and the operating distance.

[0044] In one embodiment, the running state of the rail vehicle can be determined based on the running curve and the power source curve in the training data set, wherein the running state includes the running speed v, the state of charge SoC of the hydrogen fuel cell, and the running distance s.

[0045] In step 220, based on the training data set, an actor network model corresponding to the critic network model is trained according to the proximal strategy optimization algorithm.

[0046] In step 230, the operating state is input into the actor network model, and the next-moment execution action corresponding to the operating state output by the actor network model is obtained, wherein the next-moment execution action includes the predicted driving acceleration of the rail vehicle at the next moment in the operating state and the predicted output power of the hydrogen fuel cell.

[0047] In step 240, based on the action to be executed at the next moment and the running state at the next moment corresponding to the action to be executed at the next moment, the network loss function is determined, and the running processing network model is iteratively trained based on the network loss function until the running processing network model converges to obtain a trained running processing network model.

[0048] In another embodiment, an actor network model corresponding to the critic network model can be obtained by training according to the proximal strategy optimization algorithm based on the training data set. Further, the running state is input into the actor network model to obtain the next moment execution action corresponding to the running state output by the actor network model, wherein the next moment execution action includes the predicted driving acceleration of the rail vehicle at the next moment under the running state and the predicted output power of the hydrogen fuel cell. Further, based on the next moment execution action and the next moment running state corresponding to the next moment execution action, the network loss function is determined, and the operation processing network model is iteratively trained based on the network loss function until the operation processing network model converges, thereby obtaining a trained operation processing network model.

[0049] In another embodiment, the initial state s from the constructed optimal data set (which may correspond to the training data set) can be input into the new actor network, the action probability distribution can be output, the action a with the highest probability can be selected and executed (which may correspond to the action to be executed at the next moment corresponding to the running state), and the reward r of the environmental feedback and the next state s1 (which may correspond to the running state at the next moment) can be obtained. (s, a, r, s1) is stored in the experience pool. Furthermore, the state set S and the action set A can be input into the critic network to output the advantage function Aθ(s, a), and the network loss function can be calculated to update the critic network parameters. That is, based on the action to be executed at the next moment and the running state at the next moment corresponding to the action to be executed at the next moment, the network loss function is determined, and the running processing network model is iteratively trained based on the network loss function until the running processing network model converges, thereby obtaining a trained running processing network model.

[0050] In another embodiment, the current episode cumulative reward can be used to determine whether the current experience is an excellent experience, and put it into the excellent experience pool. When the excellent experience pool is full of m episodes, calculate whether the cumulative reward of the m+1th episode is greater than the average reward value of the previous m episodes. If so, discard the first episode and put the m+1th episode into the experience pool. Furthermore, the state set S and action set in the experience pool can be input into the new actor network and the old actor network respectively to obtain the corresponding probability distributions πθ and πθ old Calculate J PPO (Corresponding to the proximal strategy optimization algorithm) is used to update the new actor network parameters to obtain the actor network model.

[0051] Figure 3 It is a schematic diagram of a flow chart for determining an optimal data set provided by the present invention.

[0052] The following will be combined Figure 3 The process of determining the optimal data set is described.

[0053] In an exemplary embodiment of the present invention, Figure 3 It can be seen that determining the optimal data set may include steps 310 to 340, and each step will be introduced below.

[0054] In step 310, an objective function of the rail vehicle during operation is constructed, wherein the objective function is a function that characterizes the operation cost of the rail vehicle.

[0055] In one embodiment, an objective function of a rail vehicle during operation may be constructed, wherein the objective function may be a function used to characterize the operation cost of the rail vehicle.

[0056] Figure 5 It is a schematic diagram of a flow chart for determining an objective function provided by the present invention.

[0057] In another exemplary embodiment of the present invention, it is possible to combine Figure 5 The process of determining the objective function is explained.

[0058] In an exemplary embodiment of the present invention, Figure 5 It can be seen that determining the objective function may include steps 510 to 550, and each step will be introduced below.

[0059] In step 510, a first equivalent hydrogen consumption of the hydrogen fuel cell, a second equivalent hydrogen consumption of the lithium battery, and a first value coefficient of hydrogen are determined.

[0060] In step 520, a first loss of the hydrogen fuel cell, a second loss of the lithium battery, a second value coefficient of the hydrogen fuel cell, and a third value coefficient of the lithium battery are determined.

[0061] In step 530, the hydrogen consumption cost of the rail vehicle during operation is determined based on the first equivalent hydrogen consumption, the second equivalent hydrogen consumption, and the first value coefficient.

[0062] In step 540, the life cost of the power source of the rail vehicle during operation is determined based on the first loss, the second loss, the second value coefficient, and the third value coefficient.

[0063] In step 550, an objective function is determined based on the hydrogen consumption cost and the power source life cost.

[0064] In one embodiment, the objective function can be expressed by formula (1): (1) Where t represents the running time; t f Represents the running time specified in the timetable; J H2 With J life They represent the hydrogen consumption cost and the life cost of the power source during the train operation. The hydrogen consumption cost and the life cost of the power source can be expressed as formula (2): (2) Among them, C fcs represents the equivalent hydrogen consumption of the fuel cell (corresponding to the first equivalent hydrogen consumption of the hydrogen fuel cell); C bat Represents the equivalent hydrogen consumption of lithium battery (corresponding to the second equivalent hydrogen consumption of lithium battery); α H2 Indicates the value coefficient of hydrogen (corresponding to the first value coefficient of hydrogen); L fcs Indicates the degree of loss of the fuel cell (corresponding to the first loss of the hydrogen fuel cell); L bat Indicates the loss degree of the lithium battery system (corresponding to the second loss of the lithium battery); α fcs Represents the value coefficient of the fuel cell system (corresponding to the second value coefficient of the hydrogen fuel cell); α bat Indicates the value coefficient of the lithium battery system (corresponding to the third value coefficient of the lithium battery).

[0065] In step 320, historical operation route information of the rail vehicle is obtained, wherein the historical operation route information includes speed limit information and station stay duration information of the historical operation route of the rail vehicle.

[0066] In step 330, based on the Hermitian-Simpson collocation technology, the historical operation line information and the objective function are processed to obtain the operation curve and the power source curve.

[0067] In step 340 , an optimal data set is determined based on the operating curve and the power source curve.

[0068] In another embodiment, the historical operation route information of the rail vehicle can be obtained, wherein the historical operation route information can include the speed limit information and the station stay time information of the historical operation route of the rail vehicle. Further, based on the Hermitian-Simpson collocation technology, the historical operation route information and the objective function are processed to obtain the operation curve and the power source curve, and the optimal data set is determined based on the operation curve and the power source curve. In the application process, the Hermitian-Simpson collocation method with adaptive grid update can be used to solve under different initial conditions of the train (such as load, train speed limit, etc.), and the train operation curve, power source output and other data (corresponding to the power source curve) under different conditions are obtained, thereby forming the optimal data set, thereby laying the foundation for effectively training the operation processing network model.

[0069] In another exemplary embodiment of the present invention, the above-mentioned embodiment is continued to be used as an example for explanation, wherein, based on the Hermitian-Simpson collocation technology, the historical operation line information and the objective function are processed to obtain the operation curve and the power source curve, which can be implemented in the following manner: Based on the Hermitian-Simpson collocation technique, the objective function is reduced in dimension to obtain the nonlinear programming corresponding to the objective function. Based on the historical operation line information and nonlinear planning, the operation curve and power source curve are obtained.

[0070] In one embodiment, the objective function obtained in the above text is a complex function, and the dimension of its state space is too high. In order to simplify the calculation, the objective function can be reduced in dimension based on the Hermitian-Simpson collocation technology to obtain a nonlinear programming corresponding to the objective function, that is, the original problem is converted into an NLP problem and solved. Further, based on the historical operation line information and nonlinear programming, the operation curve and the power source curve are obtained. Since the original problem (corresponding to the objective function) is converted into an NLP problem and solved, the operation curve and the power source curve can be obtained quickly and efficiently.

[0071] Figure 4 The Hermitian-Simpson collocation technology provided by the present invention performs dimension reduction processing on the objective function to obtain a flow chart of nonlinear programming corresponding to the objective function.

[0072] The following will be combined Figure 4 The process of performing dimensionality reduction processing on the objective function based on the Hermitian-Simpson collocation technology to obtain a nonlinear programming corresponding to the objective function is described.

[0073] In an exemplary embodiment of the present invention, Figure 4It can be seen that based on the Hermitian-Simpson collocation technology, the objective function is subjected to dimensionality reduction processing to obtain a nonlinear programming corresponding to the objective function, which may include steps 410 to 450, and each step will be introduced below.

[0074] In step 410, the historical operation route of the rail vehicle is divided into a preset number of operation intervals, and the operation intervals are transformed in the time domain to obtain transformed operation intervals, wherein the interval range of the transformed operation interval is within a preset range.

[0075] In one embodiment, the train speed v, position s and lithium battery SOC can be used as state variables, and the train acceleration a and the fuel cell system output power P fcs As the control variable, the state space can be expressed as formula (3): (3) Among them, X can be expressed as a state variable; U can be expressed as a control variable.

[0076] The system transfer equation can be expressed as formula (4): (4) Among them, I bat is the lithium battery current; Q bat is the capacity of lithium battery.

[0077] In addition, the train operation must also meet the following conditions and restrictions, as shown in formula (5): (5) Among them, v max Indicates the maximum speed; s terminal Indicates the distance to the destination; SOC max Indicates the maximum state of charge; SOC min Indicates the minimum state of charge; a max Indicates the maximum acceleration; a min Indicates the minimum acceleration; P max Indicates the maximum output power; P min Indicates the minimum output power.

[0078] In another embodiment, the train operation section can be divided into N sections, and its N+1 segmentation points can be recorded as T0, T1, ..., T N . And each [T n-1 ,T n ] intervals are transformed to [-1, 1), that is, the historical operation routes of the rail vehicle are divided into a preset number of operation intervals, and the operation intervals are transformed in the time domain to obtain the transformed operation intervals. Among them, the interval range of the transformed operation interval can be considered to be on [-1, 1) within the preset range.

[0079] In one example, each [T n-1 ,T n ] interval is transformed to [-1, 1) and can be expressed as formula (6): (6) Among them, τ represents the operating range in the time domain.

[0080] In step 420, based on the transformed operating interval, a Legendre polynomial under the transformed operating interval is obtained.

[0081] In step 430, the state space in the objective function is discretized based on the Legendre polynomials in the transformed operating interval to obtain a discretized state space.

[0082] In another embodiment, the Legendre polynomials in the transformed operating interval can be obtained based on the transformed operating interval. Further, based on the Legendre polynomials in the transformed operating interval, the state space in the objective function is discretized to obtain a discretized state space.

[0083] In yet another embodiment, the polynomial P may be selected N (τ)+P N-1 The zero point of (τ) is τ for point matching, where P N (τ) represents the Nth-order Legendre orthogonal polynomial, where P N (τ) can be expressed as formula (7): (7) Among them, d represents the differential processing; Furthermore, the state space and action space can be discretized using N+1 and N Hermitian interpolation polynomials respectively, and can be expressed as formulas (8)-(9): (8) (9) Among them, L n,i (τ) can be expressed as formula (10): (10) Where P represents the total number of discrete points; i represents the discrete point number; j represents the discrete point number other than i; v(τ n,i ) represents the velocity corresponding to the ith discrete point in the nth interval; s(τ n,i ) represents the displacement corresponding to the ith discrete point in the nth interval; soc(τ n,i ) represents the state of charge of the lithium battery corresponding to the ith discrete point in the nth interval; a(τn,i ) represents the acceleration corresponding to the ith discrete point in the nth interval; P fcs (τ n,i ) represents the fuel cell power corresponding to the ith discrete point in the nth interval.

[0084] In step 440 , based on the discretized state space, a derivative of the discretized state space is determined.

[0085] In step 450, the derivative of the discretized state space is integrated to obtain a nonlinear programming corresponding to the objective function, so as to achieve dimensionality reduction of the objective function.

[0086] In another embodiment, the derivative of the discretized state space can be determined based on the discretized state space, and then the derivative of the discretized state space can be integrated to obtain a nonlinear programming corresponding to the objective function to achieve dimensionality reduction of the objective function.

[0087] In one embodiment, after the state variable function is discretized, its derivative function can be expressed as formula (11): (11) Where, L n,i (τ) can be expressed using the differential matrix D k,i Indicates that D k,i It can be expressed as formula (12): (12) Among them, v(τ n,k ) represents the velocity corresponding to the kth discrete point in the nth interval; s(τ n,k ) represents the displacement corresponding to the kth discrete point in the nth interval; soc(τ n,k ) represents the state of charge of the lithium battery corresponding to the kth discrete point in the nth interval; g(τ n,k ) represents the function value corresponding to the kth discrete point in the nth interval, where the function expression corresponding to the function value is g(τ); g(τ n,i ) represents the function value corresponding to the i-th discrete point in the n-th interval; τ n,i represents the i-th discrete point in the n-th interval; τ n,k Represents the kth discrete point in the nth interval.

[0088] Furthermore, the algebraic constraint can be expressed as formula (13): (13) Among them, D k,i represents the differentiation matrix.

[0089] The original objective function is approximately replaced by Simpson integral, and the original problem is transformed into an NLP problem and solved, so that the nonlinear programming corresponding to the objective function can be obtained to achieve dimensionality reduction of the objective function. The transformed result is formula (14): (14) In another exemplary embodiment of the present invention, continuing with the above Figure 4 The above embodiment is used as an example for explanation, wherein the preset number of operation intervals can be determined in the following manner: Determine the allowable error for each operating range; When the allowable error of the operating interval is greater than the maximum allowable error, the operating interval is redivided until the allowable errors of the preset number of operating intervals obtained by redivision are less than the maximum allowable error and greater than the minimum allowable error; When the allowable error of the operating interval is less than the minimum allowable error, the operating intervals are merged until the allowable errors of a preset number of operating intervals obtained after the merging process are less than the maximum allowable error and greater than the minimum allowable error.

[0090] In one embodiment, a maximum allowable error εmax can be set in each independent interval. When the relative allowable error ε in the interval (corresponding to the allowable error of the operating interval) is greater than εmax, the interval needs to be refined again or the order of the interpolation polynomial needs to be increased. Otherwise, adjacent intervals can be merged or the order of the interpolation polynomial can be reduced. The relative allowable error ε of the interval (corresponding to ε(τ) in the formula) can be expressed as formula (15): (15) Where LN(ζ) is L n,i The Nth-order derivative of (τ), ζ is [t0,t f ] is a number in . X(τ) represents the function value corresponding to the point τ, where X(.) represents the speed, acceleration, SOC, displacement, fuel cell power, etc. mentioned above.

[0091] The maximum allowable error and the minimum allowable error may be adjusted according to actual conditions, and in this embodiment, no specific limitation is made on the maximum allowable error and the minimum allowable error.

[0092] According to the foregoing description, the operation processing method of the rail vehicle provided by the present invention is applied to the rail vehicle, and the rail vehicle is powered by a hydrogen fuel cell and a lithium battery. The method includes: calling a pre-trained operation processing network model; obtaining the operation parameters of the rail vehicle at the current moment, and inputting the operation parameters into the operation processing network model, and obtaining the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell output by the operation processing network model, so that the rail vehicle runs according to the driving acceleration and the hydrogen fuel cell outputs power according to the output power, and the operation cost of the rail vehicle is minimized. Parameter control is achieved from the power source end and the load end to effectively reduce the energy consumption of the hydrogen energy train, thereby reducing the operation cost of the rail vehicle.

[0093] The operation processing device of a rail vehicle provided by the present invention is described below. The operation processing device of a rail vehicle described below and the operation processing method of a rail vehicle described above can be referred to each other.

[0094] Figure 6 It is a structural schematic diagram of the operation processing device of the rail vehicle provided by the present invention.

[0095] The following will be combined Figure 6 The operation processing device for a rail vehicle provided by the present invention is described.

[0096] In an exemplary embodiment of the present invention, the device can be applied to a rail vehicle, which is powered by a hydrogen fuel cell and a lithium battery. Figure 6 It can be seen that the operation processing device of the rail vehicle may include a calling module 610 and a processing module 620, and each module will be introduced below.

[0097] The calling module 610 may be configured to call a pre-trained operation processing network model, wherein the operation processing network model is used to determine the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell according to the operation parameters of the rail vehicle at the current moment; The processing module 620 can be configured to obtain the operating parameters of the rail vehicle at the current moment, and input the operating parameters into the operation processing network model to obtain the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell output by the operation processing network model, so that the operating cost of the rail vehicle is minimized when the rail vehicle runs according to the driving acceleration and the hydrogen fuel cell outputs power according to the output power.

[0098] In an exemplary embodiment of the present invention, the calling module 610 may implement the training to obtain the operation processing network model in the following manner: Constructing a training data set, wherein the training data set is determined based on an optimal data set, and the optimal data set is determined based on an operation curve and a power source curve determined based on historical operation parameters of the rail vehicle, wherein the operation curve is used to characterize the corresponding relationship between the travel acceleration of the rail vehicle and time when the operation cost of the rail vehicle is minimized; and the power source curve is used to characterize the corresponding relationship between the output power of the hydrogen fuel cell and time when the operation cost of the rail vehicle is minimized; Based on the training data set, the operation processing network model is trained according to the proximal strategy optimization algorithm to obtain a trained operation processing network model.

[0099] In an exemplary embodiment of the present invention, the operation processing network model includes a critic network model; the calling module 610 can adopt the following method to train the operation processing network model based on the training data set according to the proximal strategy optimization algorithm to obtain the trained operation processing network model: Determining the operating state of the rail vehicle based on the operating curve and the power source curve in the training data set, wherein the operating state includes an operating speed, a state of charge of the hydrogen fuel cell, and an operating distance; Based on the training data set, an actor network model corresponding to the critic network model is obtained by training according to a proximal strategy optimization algorithm; Input the running state into the actor network model, and obtain the next moment execution action corresponding to the running state output by the actor network model, wherein the next moment execution action includes the predicted driving acceleration of the rail vehicle at the next moment under the running state and the predicted output power of the hydrogen fuel cell; Based on the next-moment execution action and the next-moment operation state corresponding to the next-moment execution action, a network loss function is determined, and based on the network loss function, the operation processing network model is iteratively trained until the operation processing network model converges to obtain a trained operation processing network model.

[0100] In an exemplary embodiment of the present invention, the calling module 610 may determine the optimal data set in the following manner: Constructing an objective function of the rail vehicle during operation, wherein the objective function is a function that characterizes the operating cost of the rail vehicle; Acquire historical operation route information of the rail vehicle, wherein the historical operation route information includes speed limit information and station stay duration information of the historical operation route of the rail vehicle; Based on the Hermitian-Simpson collocation technology, the historical operation route information and the objective function are processed to obtain the operation curve and the power source curve; The optimal data set is determined based on the operation curve and the power source curve.

[0101] In an exemplary embodiment of the present invention, the calling module 610 may process the historical operation route information and the objective function based on the Hermitian-Simpson collocation technology to obtain the operation curve and the power source curve in the following manner: Based on the Hermitian-Simpson collocation technology, the objective function is subjected to dimensionality reduction processing to obtain a nonlinear programming corresponding to the objective function; Based on the historical operation route information and the nonlinear programming, the operation curve and the power source curve are obtained.

[0102] In an exemplary embodiment of the present invention, the calling module 610 may implement the dimension reduction processing of the objective function based on the Hermitian-Simpson collocation technology in the following manner to obtain a nonlinear programming corresponding to the objective function: Dividing the historical running route of the rail vehicle into a preset number of running intervals, and transforming the running intervals in the time domain to obtain transformed running intervals, wherein the interval range of the transformed running intervals is within a preset range; Based on the transformed operation interval, obtaining a Legendre polynomial under the transformed operation interval; Based on the Legendre polynomials in the transformed operating interval, the state space in the objective function is discretized to obtain a discretized state space; Based on the discretized state space, determining a derivative of the discretized state space; The derivative of the discretized state space is integrated to obtain a nonlinear programming corresponding to the objective function, so as to achieve dimensionality reduction of the objective function.

[0103] In an exemplary embodiment of the present invention, the calling module 610 may determine the preset number of operating intervals in the following manner: Determine the allowable error for each operating range; When the allowable error of the operating interval is greater than the maximum allowable error, the operating interval is redivided until the allowable errors of a preset number of operating intervals obtained by redivision are less than the maximum allowable error and greater than the minimum allowable error; When the allowable error of the operating interval is less than the minimum allowable error, the operating intervals are merged until the allowable errors of a preset number of operating intervals obtained after the merging process are less than the maximum allowable error and greater than the minimum allowable error.

[0104] In an exemplary embodiment of the present invention, the calling module 610 may determine the objective function in the following manner: Determining a first equivalent hydrogen consumption of the hydrogen fuel cell, a second equivalent hydrogen consumption of the lithium battery, and a first value coefficient of hydrogen; Determining a first loss of the hydrogen fuel cell, a second loss of the lithium battery, a second value coefficient of the hydrogen fuel cell, and a third value coefficient of the lithium battery; Determining the hydrogen consumption cost of the rail vehicle during operation based on the first equivalent hydrogen consumption, the second equivalent hydrogen consumption, and the first value coefficient; Determining the life cost of the power source of the rail vehicle during operation based on the first loss, the second loss, the second value coefficient, and the third value coefficient; The objective function is determined according to the hydrogen consumption cost and the power source life cost.

[0105] Based on the same inventive concept, the present invention also provides a rail vehicle, which will be described below in conjunction with the following embodiments.

[0106] In an exemplary embodiment of the present invention, a rail vehicle may include: a rail vehicle body, and a processor, wherein the processor is used to execute any of the above-mentioned rail vehicle operation processing methods. Through this embodiment, parameter control is implemented from the power source end and the load end to effectively reduce the energy consumption of the hydrogen train, thereby reducing the operation cost of the rail vehicle.

[0107] Figure 7 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 7As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730 and a communication bus 740, wherein the processor 710, the communication interface 720 and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the operation processing method of the rail vehicle, the method is applied to the rail vehicle, the rail vehicle is powered by a hydrogen fuel cell and a lithium battery, the method includes: calling a pre-trained operation processing network model, wherein the operation processing network model is used to determine the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell according to the operation parameters of the rail vehicle at the current moment; obtaining the operation parameters of the rail vehicle at the current moment, and inputting the operation parameters into the operation processing network model, obtaining the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell output by the operation processing network model, so that the operation cost of the rail vehicle is minimized when the rail vehicle runs according to the driving acceleration and the hydrogen fuel cell outputs power according to the output power.

[0108] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in 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.

[0109] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the operation processing method of the rail vehicle provided by the above-mentioned methods. The method is applied to a rail vehicle, and the rail vehicle is powered by a hydrogen fuel cell and a lithium battery. The method includes: calling a pre-trained operation processing network model, wherein the operation processing network model is used to determine the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell according to the operating parameters of the rail vehicle at the current moment; obtaining the operating parameters of the rail vehicle at the current moment, and inputting the operating parameters into the operation processing network model to obtain the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell output by the operation processing network model, so that when the rail vehicle runs according to the driving acceleration and the hydrogen fuel cell outputs power according to the output power, the operating cost of the rail vehicle is minimized.

[0110] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the operation processing method of a rail vehicle provided by the above-mentioned methods, the method being applied to a rail vehicle, the rail vehicle being powered by a hydrogen fuel cell and a lithium battery, the method comprising: calling a pre-trained operation processing network model, wherein the operation processing network model is used to determine the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell according to the operating parameters of the rail vehicle at the current moment; obtaining the operating parameters of the rail vehicle at the current moment, and inputting the operating parameters into the operation processing network model, to obtain the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell output by the operation processing network model, so that when the rail vehicle runs according to the driving acceleration and the hydrogen fuel cell outputs power according to the output power, the operating cost of the rail vehicle is minimized.

[0111] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0112] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for processing the operation of a rail vehicle, characterized in that: The method is applied to a rail vehicle, wherein the rail vehicle is powered by a hydrogen fuel cell and a lithium battery, and the method comprises: Calling a pre-trained operation processing network model, wherein the operation processing network model is used to determine the running acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell according to the operation parameters of the rail vehicle at the current moment; The operating parameters of the rail vehicle at the current moment are obtained, and the operating parameters are input into the operation processing network model to obtain the driving acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell output by the operation processing network model, so that the operating cost of the rail vehicle is minimized when the rail vehicle runs according to the driving acceleration and the hydrogen fuel cell outputs power according to the output power.

2. The rail vehicle operation processing method according to claim 1, characterized in that: The operation processing network model is trained in the following way: Constructing a training data set, wherein the training data set is determined based on an optimal data set, and the optimal data set is determined based on an operation curve and a power source curve determined based on historical operation parameters of the rail vehicle, wherein the operation curve is used to characterize the corresponding relationship between the travel acceleration of the rail vehicle and time when the operation cost of the rail vehicle is minimized; and the power source curve is used to characterize the corresponding relationship between the output power of the hydrogen fuel cell and time when the operation cost of the rail vehicle is minimized; Based on the training data set, the operation processing network model is trained according to the proximal strategy optimization algorithm to obtain a trained operation processing network model.

3. The rail vehicle operation processing method according to claim 2, characterized in that: The operation processing network model includes a critic network model; the operation processing network model is trained according to the proximal strategy optimization algorithm based on the training data set to obtain a trained operation processing network model, specifically including: Determining the operating state of the rail vehicle based on the operating curve and the power source curve in the training data set, wherein the operating state includes an operating speed, a state of charge of the hydrogen fuel cell, and an operating distance; Based on the training data set, an actor network model corresponding to the critic network model is obtained by training according to a proximal strategy optimization algorithm; Input the running state into the actor network model, and obtain the next moment execution action corresponding to the running state output by the actor network model, wherein the next moment execution action includes the predicted driving acceleration of the rail vehicle at the next moment under the running state and the predicted output power of the hydrogen fuel cell; Based on the next-moment execution action and the next-moment operation state corresponding to the next-moment execution action, a network loss function is determined, and based on the network loss function, the operation processing network model is iteratively trained until the operation processing network model converges to obtain a trained operation processing network model.

4. The rail vehicle operation processing method according to claim 2 or 3, characterized in that: The optimal data set is determined in the following manner: Constructing an objective function of the rail vehicle during operation, wherein the objective function is a function that characterizes the operating cost of the rail vehicle; Acquire historical operation route information of the rail vehicle, wherein the historical operation route information includes speed limit information and station stay duration information of the historical operation route of the rail vehicle; Based on the Hermitian-Simpson collocation technology, the historical operation route information and the objective function are processed to obtain the operation curve and the power source curve; The optimal data set is determined based on the operation curve and the power source curve.

5. The operation processing method of a rail vehicle according to claim 4, characterized in that: The processing of the historical operation route information and the objective function based on the Hermitian-Simpson collocation technology to obtain the operation curve and the power source curve specifically includes: Based on the Hermitian-Simpson collocation technology, the objective function is subjected to dimensionality reduction processing to obtain a nonlinear programming corresponding to the objective function; Based on the historical operation route information and the nonlinear programming, the operation curve and the power source curve are obtained.

6. The rail vehicle operation processing method according to claim 5, characterized in that: The Hermitian-Simpson collocation technique is used to perform dimension reduction processing on the objective function to obtain a nonlinear programming corresponding to the objective function, specifically including: Dividing the historical running route of the rail vehicle into a preset number of running intervals, and transforming the running intervals in the time domain to obtain transformed running intervals, wherein the interval range of the transformed running intervals is within a preset range; Based on the transformed operation interval, obtaining a Legendre polynomial under the transformed operation interval; Based on the Legendre polynomials in the transformed operating interval, the state space in the objective function is discretized to obtain a discretized state space; Based on the discretized state space, determining a derivative of the discretized state space; The derivative of the discretized state space is integrated to obtain a nonlinear programming corresponding to the objective function, so as to achieve dimensionality reduction of the objective function.

7. The rail vehicle operation processing method according to claim 6, characterized in that: The preset number of operating intervals is determined in the following manner: Determine the allowable error for each operating range; When the allowable error of the operating interval is greater than the maximum allowable error, the operating interval is redivided until the allowable errors of a preset number of operating intervals obtained by redivision are less than the maximum allowable error and greater than the minimum allowable error; When the allowable error of the operating interval is less than the minimum allowable error, the operating intervals are merged until the allowable errors of a preset number of operating intervals obtained after the merging process are less than the maximum allowable error and greater than the minimum allowable error.

8. The rail vehicle operation processing method according to claim 5, characterized in that: The objective function is determined in the following way: Determining a first equivalent hydrogen consumption of the hydrogen fuel cell, a second equivalent hydrogen consumption of the lithium battery, and a first value coefficient of hydrogen; Determining a first loss of the hydrogen fuel cell, a second loss of the lithium battery, a second value coefficient of the hydrogen fuel cell, and a third value coefficient of the lithium battery; Determining the hydrogen consumption cost of the rail vehicle during operation based on the first equivalent hydrogen consumption, the second equivalent hydrogen consumption, and the first value coefficient; Determining the life cost of the power source of the rail vehicle during operation based on the first loss, the second loss, the second value coefficient, and the third value coefficient; The objective function is determined according to the hydrogen consumption cost and the power source life cost.

9. A rail vehicle operation processing device, characterized in that: The device is applied to a rail vehicle, the rail vehicle is powered by a hydrogen fuel cell and a lithium battery, and the device comprises: A calling module, used to call a pre-trained operation processing network model, wherein the operation processing network model is used to determine the running acceleration of the rail vehicle at the next moment and the output power of the hydrogen fuel cell according to the operation parameters of the rail vehicle at the current moment; A processing module is used to obtain the operating parameters of the rail vehicle at a current moment, and input the operating parameters into the operation processing network model to obtain the driving acceleration of the rail vehicle at a next moment and the output power of the hydrogen fuel cell output by the operation processing network model, so that the operating cost of the rail vehicle is minimized when the rail vehicle runs according to the driving acceleration and the hydrogen fuel cell outputs power according to the output power.

10. A rail vehicle, characterized in that: The rail vehicle comprises: The rail vehicle body, and A processor, wherein the processor is used to execute the rail vehicle operation processing method described in any one of claims 1 to 8.

Images