A locomotive multi-module fuel cell system coordinated control method and apparatus

Abstract

The application discloses a locomotive multi-module fuel cell system coordination control method and device, belongs to the locomotive multi-module fuel cell system coordination control technical field, and the method is: acquiring line characteristic parameters of a predetermined running line of a locomotive, and generating a global reference running track database based on the line characteristic parameters; at any current time, predicting a locomotive speed sequence within a preset future time window based on the global reference running track database, and acquiring a whole vehicle demand power sequence based on the locomotive speed sequence; acquiring a power battery state of charge at the current time, determining total output power of the multi-module fuel cell system based on the power battery state of charge, the whole vehicle demand power sequence and a preset power distribution rule; distributing the total output power based on a pre-constructed multi-objective optimization function to obtain an optimal power distribution sequence; and performing power output coordination control based on the optimal power distribution sequence, so as to realize prospective power distribution control management.

Description

Technical Field

[0001] This invention relates to the field of coordinated control technology for multi-module fuel cell systems in locomotives, and particularly to a coordinated control method and apparatus for multi-module fuel cell systems in locomotives. Background Technology

[0002] Fuel cells, with their significant advantages of high efficiency, high power density, and zero emissions, are rapidly expanding from highway vehicle applications to high-power, heavy-duty rail transit applications. In rail transit applications, especially for mainline passenger and freight trains, the traction power required for operation typically reaches hundreds of kilowatts or even megawatts. However, limited by the electrochemical active area, bipolar plate size, and current manufacturing processes, the power level of a single fuel cell stack has an insurmountable physical upper limit, making it difficult to independently meet the high-power demands of heavy-duty locomotives. Furthermore, high-power single fuel cell stacks often rely on large-area bipolar plates and a greater number of membrane electrode assemblies (MEAs). This structure easily leads to uneven distribution of the mass-heat-water-electricity fields within the stack, resulting in a series of problems such as localized mass transfer obstruction, hot spot concentration, or accelerated MEA degradation, severely affecting the stack's operational reliability and lifespan.

[0003] To overcome the power limitations and consistency bottlenecks of individual fuel cell stacks, combining multiple low-power fuel cell modules in series and parallel to construct a multi-module fuel cell system, supplemented by a power battery, has become the mainstream technical approach to meet the power requirements of rail transit locomotives. This hydrogen-electric hybrid system architecture not only provides power redundancy and scalability but also significantly enhances the flexibility of system configuration, adapting to the application needs of locomotives with different power levels. However, despite these advantages, the multi-module hydrogen-electric hybrid architecture also introduces new control challenges. How to fully utilize the inherent characteristics of fixed operating routes and predictable operating conditions of rail transit locomotives under dynamically changing traction loads, rationally allocate energy between the multi-module fuel cell system and the power battery, and finely coordinate and control the output power of each fuel cell module to achieve the dual goals of optimal overall system efficiency and longest service life, has become a key technical problem urgently needing to be solved in this field.

[0004] In the prior art, patents CN119764495AA multi-module fuel cell collaborative power generation system and its control method are disclosed. This method calculates the performance degradation rate of each module at each operating point in real time and combines this with the SOC value of the energy storage battery. Based on the current power demand, it determines the number of modules to start / stop and allocates operating points, achieving balanced lifetime control among multiple modules. However, this control strategy relies solely on the current load information, essentially remaining a passive response control. It fails to proactively predict future power demands, resulting in a lag in system response when load power changes abruptly. Furthermore, it cannot plan the start / stop strategies of multiple modules over a future period from a global perspective, making it difficult to achieve system-level efficiency and lifetime synergistic optimization. CN119852466A This invention discloses a multi-stack series controllable fuel cell system, a stack-closure control method, and a vehicle. It achieves precise stack-level isolation by configuring each electrically connected stack with an independent relay switch and a medium supply solenoid valve. Its stack-closure control method determines the number of stacks to be shut down based on the current power demand of the vehicle and selects target stacks for shutdown based on the historical operating time or average individual cell voltage of each stack, aiming to balance the operational lifespan of multiple stacks. However, the decision-making basis of this invention is also limited to the current power demand and historical cumulative data, essentially a reactive control logic. It cannot proactively predict future power demand, making it difficult to coordinate and regulate the gas supply of multiple modules before power surges, and it cannot plan the operating strategies of each stack in the future journey from a global perspective to achieve synergistic optimization of system efficiency and lifespan. In summary, existing technologies generally suffer from a lack of predictability in control strategies and insufficient utilization of the degrees of freedom in multi-module systems, failing to fully leverage the performance advantages of multi-module hydrogen-electric hybrid power systems in rail transit scenarios. Summary of the Invention

[0005] This invention provides a coordinated control method and device for a multi-module fuel cell system in a locomotive, which can solve the technical problems in the prior art of being unable to predict future power demand and lacking predictability in control strategies, and realize forward-looking power distribution control management.

[0006] This invention provides a coordinated control method for a multi-module fuel cell system in a locomotive, comprising: Obtain the line characteristic parameters of the locomotive's predetermined operating route, and generate a global reference operating trajectory database based on the line characteristic parameters; At any given moment, the locomotive speed sequence within a preset future time window is predicted based on the global reference trajectory database, and the vehicle power demand sequence is obtained based on the locomotive speed sequence. Obtain the current state of charge of the power battery, and determine the total output power of the multi-module fuel cell system based on the state of charge of the power battery, the power demand sequence of the vehicle, and the preset power allocation rules; The optimal power allocation sequence is obtained by allocating the total output power based on a pre-constructed multi-objective optimization function; Based on the optimal power allocation sequence, the power output coordination control is performed on the multi-module fuel cell system in the power output preparation state.

[0007] The above scheme generates a global reference operating trajectory database by acquiring the line characteristic parameters of the locomotive's predetermined operating route. At any current moment, it predicts the locomotive speed sequence within a preset future time window based on this database and obtains the vehicle's required power sequence. Then, it combines the state of charge of the power battery and preset power allocation rules to determine the total output power of the multi-module fuel cell system. Finally, after obtaining the optimal power allocation sequence through multi-objective optimization, it performs coordinated control, realizing forward-looking power allocation control management. This solves the technical problems of existing technologies that cannot make forward-looking predictions of future power demand and lack predictability in control strategies.

[0008] Further, the step of predicting the locomotive speed sequence within a preset future time window based on the global reference trajectory database at any current time, and obtaining the vehicle's required power sequence based on the locomotive speed sequence, includes: At any given moment, obtain the locomotive's real-time operating position and historical speed sequence; Based on the locomotive's real-time operating position and the global reference operating trajectory database, a sequence of predicted route feature parameters is obtained; Based on the global reference trajectory database, a locomotive operation mode sequence corresponding to the predicted line feature parameter sequence is obtained; Based on the predicted line characteristic parameter sequence and the historical speed sequence, a locomotive speed sequence within a preset future time window is obtained; The vehicle speed sequence, the locomotive operation mode sequence, and the preset locomotive traction and braking characteristic curve are used to generate the vehicle power demand sequence.

[0009] The above scheme improves the accuracy of train speed prediction and total train power demand prediction by obtaining the real-time operating position and historical speed sequence of the locomotive at any current moment, thereby obtaining the predicted line characteristic parameter sequence and the corresponding locomotive operating mode sequence.

[0010] Furthermore, in the process of obtaining the current state of charge of the power battery and determining the total output power of the multi-module fuel cell system based on the power battery state of charge, the vehicle's power demand sequence, and a preset power allocation rule, the preset power allocation rule includes: When the state of charge of the power battery is less than the preset capacity safety lower limit threshold of the power battery, the first candidate sequence of total output power is obtained by summing the vehicle demand power sequence and the preset maximum charging power of the power battery, and the minimum value between the first candidate sequence and the preset maximum output power of the multi-module fuel cell system is selected as the total output power of the multi-module fuel cell system.

[0011] The above scheme sets the priority to charge the power battery when the state of charge of the power battery is less than the preset capacity safety lower limit threshold, so as to ensure the safety of the power battery and avoid damage to the battery life caused by deep discharge.

[0012] Furthermore, the preset power allocation rule also includes: When the state of charge of the power battery is greater than the preset capacity safety upper limit threshold of the power battery, a second candidate sequence of total output power is obtained by calculating the difference between the vehicle demand power sequence and the preset maximum discharge power of the power battery, and the maximum value between the second candidate sequence and the preset minimum output power of the multi-module fuel cell system is selected as the total output power of the multi-module fuel cell system.

[0013] The above scheme sets that when the state of charge of the power battery is greater than the preset capacity safety upper limit threshold, the power battery's power will be consumed first to avoid overcharging the battery, while reducing the operating time of the fuel cell in the low efficiency range.

[0014] Furthermore, the preset power allocation rule also includes: When the state of charge of the power battery is not less than the preset lower capacity safety threshold and not greater than the preset upper capacity safety threshold: The current output power is obtained, and the current maximum output power is obtained by summing the current output power and the preset maximum discharge power. When it is determined based on the vehicle demand power sequence that there is a peak demand power of the vehicle that is greater than the current maximum output power, a third candidate output power is obtained based on the current output power and the preset charging power increment of the multi-module fuel cell system, and the minimum value between the third candidate output power and the preset maximum output power is selected as the total output power of the multi-module fuel cell system.

[0015] The above scheme is designed to increase the output power of the fuel cell in advance to reserve power for the battery when the state of charge of the power battery is within a safe range and there is a power peak that exceeds the current power supply capacity of the system, so as to avoid the fuel cell from overload operation and ensure the continuity of the locomotive's power output.

[0016] Furthermore, after obtaining the current output power and summing it with the preset maximum discharge power to obtain the current maximum output power, the preset power allocation rule further includes: When it is determined, based on the vehicle demand power sequence, that there is no locomotive vehicle demand power peak greater than the current maximum output power: The power variance is obtained based on the power demand sequence of the whole vehicle, and the fluctuation is judged based on the power variance, the fluctuation coefficient and the rated power of the multi-module fuel cell system to obtain the fluctuation judgment result. When the fluctuation judgment result meets the preset fluctuation conditions, the fuel cell demand power series is obtained by calculating the difference between the vehicle demand power series and the basic discharge power of the power battery. The maximum value between the fuel cell demand power series and the preset minimum output power is selected as the first candidate output power, and the minimum value between the first candidate output power and the preset maximum output power of the multi-module fuel cell system is selected as the total output power of the multi-module fuel cell system.

[0017] The above scheme is designed to utilize the power battery to bear part of the power fluctuations when the state of charge of the power battery is within a safe range and there is no power peak but there are power fluctuations, thereby reducing the number of load changes of the fuel cell and effectively extending the service life of the fuel cell.

[0018] Furthermore, the preset power allocation rule also includes: When the fluctuation judgment result does not meet the preset fluctuation conditions, the preset optimal output efficiency point of the multi-module fuel cell system is taken as the total output power.

[0019] The above scheme is designed so that when the state of charge of the power battery is within a safe range and there are no power peaks or significant fluctuations, the fuel cell operates at the point of optimal output efficiency, thereby reducing the overall hydrogen consumption of the system and improving the economic efficiency of operation.

[0020] Furthermore, the process of allocating the total output power based on a pre-constructed multi-objective optimization function to obtain the optimal power allocation sequence includes: Obtain the cumulative operating time and average segment voltage for each fuel cell module in a multi-module fuel cell system. Obtain several preset lifetime values ​​and several initial average node voltages corresponding to several of the aforementioned fuel cell modules; Based on the cumulative operating time, average cell voltage, preset lifespan value, initial average cell voltage, and preset lifespan decay weighting coefficient, a lifespan decay function is constructed for each of the fuel cell modules. Based on the total output power, construct several instantaneous hydrogen consumption functions corresponding to the fuel cell modules respectively; A multi-objective optimization function is constructed by weighted summation based on preset economic target coefficients, preset durability target coefficients, several instantaneous hydrogen consumption functions, and several lifetime decay functions; The optimal power allocation sequence is obtained by allocating the total output power based on the multi-objective optimization function and preset constraints.

[0021] The above scheme allocates the total output power by constructing a multi-objective optimization function that simultaneously considers instantaneous hydrogen consumption and lifespan decay, thereby balancing the operating load of each fuel cell module and achieving synergistic optimization of system economy and durability.

[0022] Furthermore, it also includes: Based on the vehicle demand power sequence, future power mutation information and power mutation time are obtained, and pre-adjustment instructions are generated based on the future power mutation information. Based on the pre-adjustment command, the air supply to the multi-module fuel cell system is adjusted so that the multi-module fuel cell system is in the power output preparation state at the moment of power change.

[0023] The above solution obtains future power mutation information and time based on the vehicle demand power sequence and generates pre-adjustment commands to adjust the air supply of the multi-module fuel cell system in advance, effectively overcoming the inherent defect of fuel cell air supply lag and significantly improving the dynamic response speed of the system.

[0024] This invention provides a coordinated control device for a multi-module fuel cell system in a locomotive, used to implement the aforementioned coordinated control method for a multi-module fuel cell system in a locomotive, comprising: a vehicle controller, a multi-module fuel cell system controller, a multi-module fuel cell system, and a power battery, wherein: The vehicle controller is used to acquire the line characteristic parameters of the locomotive's predetermined operating route, and generate a global reference operating trajectory database based on the line characteristic parameters; at any current moment, it predicts the locomotive speed sequence within a preset future time window based on the global reference operating trajectory database, and obtains the vehicle's required power sequence based on the locomotive speed sequence; it acquires the power battery state of charge at the current moment, and determines the total output power of the multi-module fuel cell system based on the power battery state of charge, the vehicle's required power sequence, and a preset power allocation rule; The multi-module fuel cell system controller is used to allocate the total output power based on a pre-constructed multi-objective optimization function to obtain an optimal power allocation sequence; and to perform power output coordination control on the multi-module fuel cell system in the power output preparation state based on the optimal power allocation sequence.

[0025] This invention provides a coordinated control method and device for a multi-module fuel cell system in a locomotive, aiming to solve the technical problems of insufficient predictability in control strategies and inadequate utilization of the degrees of freedom of multiple modules in existing technologies. Specifically, this invention utilizes the inherent characteristic of the fixed locomotive operating route to perform operating condition prediction, and adopts a hierarchical coordinated control approach. At the upper level, it achieves reasonable power allocation between the multi-module fuel cell system and the power battery, while at the lower level, it coordinates the output power and balances the lifespan of each fuel cell module. This invention constructs a three-layer prediction framework based on global reference operation, vehicle speed prediction, and overall vehicle power demand prediction. It fully leverages the advantage of the fixed locomotive route, fusing real-time operating position, historical speed sequences, and route characteristic parameter sequences to generate a predicted sequence of overall vehicle power demand, enabling the vehicle controller and fuel cell controller to predict future power demands. Compared to traditional passive response control, this invention can identify power surges in advance and proactively implement energy scheduling, fundamentally overcoming the technical shortcomings of fuel cell gas supply lag and dynamic response delay. Meanwhile, this invention also achieves a dynamic trade-off between economic objectives (minimum hydrogen consumption) and durability objectives (balanced lifespan) during the control process. The optimization strategy prioritizes modules with better health conditions to bear higher power, while modules with weaker health conditions operate in the low decay range. This achieves coordinated control that optimizes the overall efficiency and extends the lifespan of the multi-module system, breaking through the technical bottleneck of traditional control methods that struggle to balance efficiency and lifespan.

[0026] In summary, the coordinated control method and device provided by this invention fully utilize the characteristics of fixed locomotive operating routes and predictable operating conditions to complete forward power prediction. Through line feature extraction, forward power prediction, hierarchical power allocation, and pre-adjustment control, it realizes the pre-allocation and dynamic regulation of power, effectively making up for the shortcomings of passive response in existing technologies, taking into account the system's operating economy, power performance, and the service life of each component, and significantly improving the overall performance and operational reliability of multi-module fuel cell locomotives. Attached Figure Description

[0027] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of a coordinated control method for a multi-module fuel cell system in a locomotive provided in this embodiment; Figure 2 This is a schematic diagram of the power distribution process of an upper-level hydrogen-electric hybrid power system provided in this embodiment; Figure 3 This is a schematic diagram of a lower-level multi-module fuel cell system coordination control process provided in this embodiment; Figure 4 This is a schematic diagram of a coordinated control system for a multi-module fuel cell system in a locomotive, provided in this embodiment. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0031] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0032] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0033] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0034] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0035] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0036] Example 1: This embodiment provides a coordinated control method for a multi-module fuel cell system in a locomotive, such as... Figure 1 As shown, it includes: S1 Obtain the line characteristic parameters of the locomotive's predetermined running route, and generate a global reference running trajectory database based on the line characteristic parameters; S2 At any given moment, the locomotive speed sequence within a preset future time window is predicted based on the global reference trajectory database, and the vehicle power demand sequence is obtained based on the locomotive speed sequence. S3 1. Obtain the current state of charge of the power battery, and determine the total output power of the multi-module fuel cell system based on the state of charge of the power battery, the power demand sequence of the vehicle, and the preset power allocation rules; S4 The optimal power allocation sequence is obtained by allocating the total output power based on a pre-constructed multi-objective optimization function; S5 Based on the optimal power allocation sequence, the power output coordination control is performed on the multi-module fuel cell system in the power output preparation state.

[0037] This embodiment achieves synergistic optimization of efficiency and lifespan through a two-layer power allocation method. Addressing the shortcomings of existing technologies that fail to fully utilize the multi-module degrees of freedom and cannot simultaneously balance efficiency and lifespan, a two-layer power allocation method based on a top and bottom layer is proposed. Based on this method, the locomotive's hydrogen-electric hybrid power system can proactively optimize the power allocation of the power battery and multi-module fuel cell system before actual power demand occurs. Furthermore, it enables refined allocation of the output power of the multi-module fuel cell system, achieving a dynamic trade-off between economic objectives (minimum hydrogen consumption) and durability objectives (balanced lifespan).

[0038] It should be noted that this embodiment is applied to a coordination control device for a multi-module fuel cell system in a locomotive, the coordination control device including: a vehicle controller ( VCU, Vehicle control unit), multi-module fuel cell system controller ( FCU, Fuel cell control unit ), multi-module fuel cell system and power battery ( BMS, Battery management system Among them, the power battery is managed through its internal battery management system (BMS). BMS The system interacts with the vehicle controller to monitor and report the state of charge (SOC) of the power battery to the vehicle controller. The two-layer power allocation method includes: using the vehicle controller as the highest decision-making layer of the hydrogen-electric hybrid power system, responsible for generating the global reference operating trajectory database, predicting the vehicle's power demand, and confirming the total output power of the multi-module fuel cell system; using the multi-module fuel cell system controller as the allocation decision layer, responsible for the coordinated control and fine-grained power allocation among the multi-module fuel cell systems; and the power battery being responsible for monitoring and reporting its SOC. (i is the number of fuel cell modules in the multi-module fuel cell system,) This coordinated control device receives power commands (i.e., the optimal power allocation sequence) from the multi-module fuel cell system controller and reports operating data. Essentially, this coordinated control device achieves power regulation between the multi-module fuel cell system and the power battery in the hydrogen-electric hybrid power system by adjusting the power of each fuel module within the multi-module fuel cell system.

[0039] In the specific implementation process, in the steps S1 In this embodiment, the basic static geographic information of the section involved in the operation of any locomotive is first extracted from the locomotive operation map. Combined with the dispatching instructions and train timetable for that train, the specific operating route, stops, and operating time constraints of the train are determined, ultimately forming the predetermined operating route for that locomotive. Then, through onboard... GPS Alternatively, the BeiDou positioning module interacts with the geographic information system (GIS) database stored inside the locomotive to obtain all route feature parameters corresponding to the locomotive's predetermined operating route. These route feature parameters include at least the percentage gradient, curve curvature, speed limit, and station and signal location information for the locomotive's predetermined operating route. Finally, combined with the predetermined operating route and timetable information contained in the locomotive's route map, a global reference operating trajectory database containing the route feature parameters for the entire operation is generated. This global reference operating trajectory database includes the full-length route feature parameters corresponding to the locomotive's predetermined operating route, including mileage markers, percentage gradient, curve length, curve curvature, speed limit, and station and signal location information.

[0040] Preferably, the locomotive operation mode sequence is obtained based on the global reference operation trajectory database.

[0041] It should be noted that in actual operation, the locomotive's speed trajectory is affected by various real-time factors such as dispatching instructions, temporary speed limits, and the distance between trains, making it impossible to predetermine a unique trajectory. Therefore, the global reference running trajectory database obtained in this embodiment mainly stores the static geographic full-length route characteristic parameters of the locomotive's predetermined running route, and does not directly store multiple complete global reference running trajectories. Based on this, this embodiment also includes: further employing existing traction calculation or energy-saving optimization algorithms (such as dynamic programming, genetic algorithms, or...). Pontryagin Using the minimum principle and train timetable constraints, one or more nominal global reference trajectories (i.e., the desired speed-mileage curve or speed-time curve) are generated offline. This global reference trajectory is not used for forced following, but rather serves as prior input or auxiliary features for the speed prediction model in subsequent steps, helping the model better understand the mapping relationship between track features and train speed. In actual operation, in this embodiment, subsequent speed and power predictions mainly rely on the current track feature parameters extracted from real-time positioning and the track feature parameters ahead, rather than relying on a fixed reference trajectory.

[0042] Optional, steps S2 include: At any given moment, obtain the locomotive's real-time operating position and historical speed sequence; Based on the locomotive's real-time operating position and the global reference operating trajectory database, a sequence of predicted route feature parameters is obtained; Based on the global reference trajectory database, a locomotive operation mode sequence corresponding to the predicted line feature parameter sequence is obtained; Based on the predicted line characteristic parameter sequence and the historical speed sequence, a locomotive speed sequence within a preset future time window is obtained; The vehicle speed sequence, the locomotive operation mode sequence, and the preset locomotive traction and braking characteristic curve are used to generate the vehicle power demand sequence.

[0043] During the actual operation of the locomotive, at any given moment, this embodiment utilizes onboard... GPSAlternatively, a BeiDou positioning module can be used to obtain the locomotive's current longitude and latitude coordinates, thus determining the locomotive's real-time operating position. Starting from this real-time operating position, a sequence of predicted route feature parameters extending forward is extracted from the global reference operating trajectory database. Preferably, starting from the locomotive's real-time operating position, continuous route feature parameters for a predetermined distance (e.g., 1-5 kilometers in the future) are extracted from the global reference operating trajectory database along the operating direction. More preferably, continuous route feature parameters within a predetermined prediction time domain are extracted from the global reference operating trajectory database starting from the locomotive's real-time operating position. Based on the obtained continuous route feature parameters, a sequence of predicted route feature parameters ordered by mileage is formed. This sequence only includes the road segment not yet traversed by the locomotive, excluding previously traversed segments, and the parameters corresponding to each mileage point include at least the route gradient (per mille), curve curvature, curve length, speed limit, and information on station and signal locations. The extraction length of the predicted route feature parameter sequence (i.e., the predetermined distance or predetermined prediction time domain) can be preset according to the requirements of the vehicle speed prediction model.

[0044] Furthermore, this embodiment constructs a long short-term memory neural network (LSM) LSTM This model predicts future train speeds. The core of the model is to integrate the dynamic resistance and static track constraints affecting train operation as prior knowledge with historical speed data, using both as input to the model.

[0045] Specifically, at the current moment The input feature vector of the model It consists of two parts: historical speed sequence and future line characteristic parameter sequence. The historical speed sequence represents the actual operating speed of locomotives within a past time window. , The future route characteristic parameter sequence is from the current time. Start by extracting a preset future time window along the direction of travel. The sequence of predicted line characteristic parameters is used. Each set of parameters in this sequence is used to calculate the resultant force of train operation at the corresponding mileage point. The specific calculation method is as follows: First, calculate the basic resistance: based on the current predicted vehicle speed. Calculate the basic resistance per unit using the Davis formula ,in A , B and C This is the basic drag coefficient; Calculate additional resistance per unit gradient: Based on the gradient *i* (per mille) extracted from the global reference track database, calculate the additional resistance per unit gradient. ; Calculate additional drag on curves: Based on the curve radius R (derived from curve curvature) extracted from the global reference trajectory database, calculate the additional drag per unit curve. Simultaneously, the curve length parameter is used to determine the range of mileage under which this additional resistance continues to act, i.e., to clarify... It takes effect on consecutive mileage points; Calculate additional resistance in the tunnel (if the line data includes this): This can be calculated based on the preset tunnel air resistance coefficient. Finally, the above resistances are summed to obtain the unit total resistance corresponding to the predicted line characteristic parameters (i.e., the unit resultant force of train operation). .

[0046] In addition, other information from the predicted line characteristic parameter sequence is also incorporated into the prediction process in a specific way: Location-based speed limits are the highest priority hard constraint for vehicle speed prediction, and the model outputs a sequence of predicted vehicle speeds. At any mileage point, the speed limit corresponding to that point must not be exceeded. This can be achieved during model training or inference through a penalty term in the loss function or post-processing pruning.

[0047] The locations of stations and traffic lights are used to predict the switching points of operating conditions. For example, when a station is predicted to be ahead, the model tends to output a deceleration sequence within the corresponding mileage range; when the traffic light is red, it needs to predict stopping. This information can be input into the model as categorical features (one-hot encoding) or continuous features (remaining distance to the station).

[0048] Based on the above mechanism LSTM The iterative prediction process of the model can be described as: taking the current time step... Historical speed sequences and features such as total resistance per unit distance over a future distance, speed limits, and distances from stations are input into the trained system. LSTM The network will iteratively output the predicted time intervals for the future. Locomotive speed sequence within (i.e., within the preset future time window) , .

[0049] The locomotive operation modes in this embodiment include traction mode, coasting mode, and braking mode. Based on this global reference trajectory database, the theoretical reference speed corresponding to any mileage position can be obtained. km / h ) and mileage ( kmThe mapping relationship is established, and then the theoretical acceleration is calculated by the change of theoretical reference speed with mileage. Then, combined with the line gradient per thousandth of the corresponding mileage, the mileage point is determined to be in traction mode, coasting mode or braking mode according to the pre-calibrated acceleration and gradient threshold. Finally, the locomotive operation modes of all mileage points are arranged in mileage order to obtain the locomotive operation mode sequence.

[0050] Finally, the predicted locomotive speed sequence is substituted into the preset locomotive traction and braking characteristic curve, and combined with the locomotive operating mode sequence to obtain the predicted locomotive power demand sequence. , The preset locomotive traction and braking characteristic curve can be specifically expressed as shown in the following formula: In the formula, condition one, condition two, and condition three represent the locomotive's operating mode at the current moment as traction mode, coasting mode, and braking mode, respectively. A , B , C These represent the static drag coefficient, linear drag coefficient, and air drag coefficient, respectively, in the basic drag coefficients. The slewing mass coefficient, For transmission efficiency, m The total mass of the locomotive, g It is the acceleration due to gravity. The line gradient per thousand is obtained from the line gradient per thousand that is pre-stored in the global reference running trajectory database. The curve radius is pre-stored in the geographic information system database and can be directly extracted after locating the corresponding mileage marker. The braking force is obtained by real-time acquisition of the brake cylinder pressure by a pressure sensor in the coordination control device, and then converted into a pre-calibrated brake pressure-braking force characteristic curve.

[0051] Obtaining the locomotive's total power demand prediction sequence （ ） Subsequently, this embodiment designs a power allocation strategy based on preset power allocation rules to determine the total output power of the multi-module fuel cell system, thereby realizing power allocation for the hydrogen-electric hybrid power system. The specific steps of this power allocation strategy include: obtaining the state of charge of the power battery. ( (State of charge), combined with the already obtained locomotive power demand prediction sequence. As input to the power allocation strategy, the total output power of the multi-module fuel cell system is determined using a power allocation strategy based on preset power allocation rules. Finally, the total output power of the multi-module fuel cell system will be obtained. Output to the multi-module fuel cell system controller to achieve coordinated control of the power output of the multi-module fuel cell system.

[0052] Optionally, in obtaining the current state of charge of the power battery and determining the total output power of the multi-module fuel cell system based on the power battery state of charge, the vehicle power demand sequence, and a preset power allocation rule, the preset power allocation rule includes rule 1: When the state of charge of the power battery is less than the preset capacity safety lower limit threshold of the power battery, the first candidate sequence of total output power is obtained by summing the vehicle demand power sequence and the preset maximum charging power of the power battery, and the minimum value between the first candidate sequence and the preset maximum output power of the multi-module fuel cell system is selected as the total output power of the multi-module fuel cell system.

[0053] In the specific implementation process, the preset power allocation rules set in this embodiment include rule 1 above, that is, if If the multi-module fuel cell system is activated to charge the power battery, then the total output power of the multi-module fuel cell system is determined. for: .in, This is the preset safety lower limit threshold for the capacity of the power battery. The preset maximum output power for a multi-module fuel cell system, This is the preset maximum charging power for the power battery.

[0054] Optionally, the preset power allocation rule also includes rule 2: When the state of charge of the power battery is greater than the preset capacity safety upper limit threshold of the power battery, a second candidate sequence of total output power is obtained by calculating the difference between the vehicle demand power sequence and the preset maximum discharge power of the power battery, and the maximum value between the second candidate sequence and the preset minimum output power of the multi-module fuel cell system is selected as the total output power of the multi-module fuel cell system.

[0055] In the specific implementation process, the preset power allocation rule set in this embodiment also includes rule 2 above, that is, if In this case, the power of the battery should be consumed first, and the output power of the multi-module fuel cell system should be determined as follows: .in, This refers to the preset safety upper limit threshold for the capacity of the power battery. The preset minimum output power for a multi-module fuel cell system, This is the preset maximum discharge power of the power battery.

[0056] Optionally, the preset power allocation rule also includes rule 3: When the state of charge of the power battery is not less than the preset lower capacity safety threshold and not greater than the preset upper capacity safety threshold: The current output power is obtained, and the current maximum output power is obtained by summing the current output power and the preset maximum discharge power. When it is determined based on the vehicle demand power sequence that there is a peak demand power of the vehicle that is greater than the current maximum output power, a third candidate output power is obtained based on the current output power and the preset charging power increment of the multi-module fuel cell system, and the minimum value between the third candidate output power and the preset maximum output power is selected as the total output power of the multi-module fuel cell system.

[0057] In the specific implementation process, the preset power allocation rules set in this embodiment also include rule 3 above, that is, if And in the future predicted time interval Within, there exists a peak power demand for the entire locomotive. satisfy Therefore, it is necessary to increase the output power of the multi-module fuel cell system in advance to provide the reserve power for the power battery. Thus, the total output power of the multi-module fuel cell system is determined to be... .in, This represents the current output power of the multi-module fuel cell system. The third candidate output power, Preset the charging power increment for the preset multi-module fuel cell system.

[0058] Optionally, after obtaining the current output power and summing it with the preset maximum discharge power to obtain the current maximum output power, the preset power allocation rule further includes rule 4: When it is determined, based on the vehicle demand power sequence, that there is no locomotive vehicle demand power peak greater than the current maximum output power: The power variance is obtained based on the power demand sequence of the whole vehicle, and the fluctuation is judged based on the power variance, the fluctuation coefficient and the rated power of the multi-module fuel cell system to obtain the fluctuation judgment result. When the fluctuation judgment result meets the preset fluctuation conditions, the fuel cell demand power series is obtained by calculating the difference between the vehicle demand power series and the basic discharge power of the power battery. The maximum value between the fuel cell demand power series and the preset minimum output power is selected as the first candidate output power, and the minimum value between the first candidate output power and the preset maximum output power of the multi-module fuel cell system is selected as the total output power of the multi-module fuel cell system.

[0059] In the specific implementation process, the preset power allocation rules set in this embodiment also include rule 4 above, that is, if And in the future predicted time interval Within, there exists a variance in the power demand of the entire locomotive. If a fluctuation judgment result that meets the preset fluctuation conditions is obtained, then the total output power of the multi-module fuel cell system is determined to be... .in, For fluctuation coefficient, This refers to the rated power of a multi-module fuel cell system. This represents the base discharge power of the power battery. It allows the multi-module fuel cell system to follow load changes, but permits the power battery to absorb some of the fluctuations to smooth out the load variation rate of the multi-module fuel cell system.

[0060] Optionally, the preset power allocation rule also includes rule 5: When the fluctuation judgment result does not meet the preset fluctuation conditions, the preset optimal output efficiency point of the multi-module fuel cell system is taken as the total output power.

[0061] In the specific implementation process, the preset power allocation rules set in this embodiment also include rule 5 above, that is, if And in the future predicted time interval Within this range, there exists a variance in the power demand of the entire locomotive. If the fluctuation judgment result does not meet the preset fluctuation condition, then the total output power of the multi-module fuel cell system is determined to be... in, This is the preset optimal output efficiency point for a multi-module fuel cell system.

[0062] Optionally, the step of allocating the total output power based on a pre-constructed multi-objective optimization function to obtain the optimal power allocation sequence includes: Obtain the cumulative operating time and average segment voltage for each fuel cell module in a multi-module fuel cell system. Obtain several preset lifetime values ​​and several initial average node voltages corresponding to several of the aforementioned fuel cell modules; Based on the cumulative operating time, average cell voltage, preset lifespan value, initial average cell voltage, and preset lifespan decay weighting coefficient, a lifespan decay function is constructed for each of the fuel cell modules. Based on the total output power, construct several instantaneous hydrogen consumption functions corresponding to the fuel cell modules respectively; A multi-objective optimization function is constructed by weighted summation based on preset economic target coefficients, preset durability target coefficients, several instantaneous hydrogen consumption functions, and several lifetime decay functions; The optimal power allocation sequence is obtained by allocating the total output power based on the multi-objective optimization function and preset constraints.

[0063] In practical implementation, the underlying multi-module fuel cell system coordinated control achieves fine power allocation among multiple fuel cell modules. This results in obtaining the total output power of the multi-module fuel cell system. Subsequently, this embodiment designs a fine-grained power allocation strategy for multiple fuel cell modules by constructing a multi-objective optimization function to minimize the total hydrogen consumption and total lifetime degradation of the multi-module fuel cell system. Specific steps include: Step 1: First, construct a multi-objective optimization function based on economic and durability objectives. Specifically, it can be expressed as follows: ; In the formula, and These are the preset economic target coefficient (total hydrogen consumption of the system) and the preset durability target coefficient (total lifespan of the system), respectively. ; For the first in a multi-module fuel cell system Each fuel cell system module has an output power The instantaneous hydrogen consumption function under the given conditions characterizes the economic objective; For the first The lifespan degradation function of the fuel cell system module is the... Health status of each fuel cell system module The function represents the durability target.

[0064] In this embodiment, the instantaneous hydrogen consumption function can be expressed as follows: ; In the formula, For the first Each fuel cell system module at its current output power The efficiency of the process; state of charge Hydrogen has a low calorific value; In this embodiment, the lifetime decay function can be expressed as follows: ; In the formula, and This is the lifetime decay weighting coefficient, and ; For the first The cumulative operating time of each fuel cell system module For the first The design life (i.e., the preset life value) of each fuel cell system module. For the first The average node voltage of each fuel cell system module at the current moment. For the first The initial average node voltage of each fuel cell system module.

[0065] Furthermore, the constraints for the multi-objective optimization function are set as follows: ; In the formula, and For the first The minimum and maximum output power of each fuel cell system module, The control cycle for each module of the fuel cell system, For the first The maximum allowable power change rate for each fuel cell system module ensures that the output power of the fuel cell system module changes smoothly.

[0066] Step 2: Optimize the problem and obtain the optimal power allocation sequence for each module of the fuel cell system.

[0067] In each control cycle Within this framework, the particle swarm optimization algorithm is used to solve the multi-objective optimization function, and the optimal power allocation sequence obtained from the optimization solution is as follows: .

[0068] Step 3: Send the optimal power allocation sequence to the multi-module fuel cell system controller. , and by Time interval The operating data of each module of the fuel cell system is uploaded to the multi-module fuel cell system controller. LHV .

[0069] Optional, also includes: Based on the vehicle demand power sequence, future power mutation information and the time of power mutation are obtained, and a pre-adjustment instruction is generated based on the future power mutation information; Based on the pre-adjustment command, the air supply to the multi-module fuel cell system is adjusted so that the multi-module fuel cell system is in the power output preparation state at the moment of power change.

[0070] In the specific implementation process, in view of the inherent characteristics of the multi-module fuel cell system, such as gas supply lag and slow dynamic response, this embodiment designs feedforward control: The multi-module fuel cell system controller first obtains future power mutation information and the corresponding power mutation time based on the power demand sequence of the whole vehicle, and generates a pre-adjustment command accordingly; then, using this forward-looking prediction information, it issues a pre-adjustment command to the air supply system in advance, so that the air compressor speed is pre-adjusted to near the target value before the power mutation occurs, and the hydrogen supply pressure is simultaneously adjusted to ensure that the multi-module fuel cell system is in a power output ready state at the moment of power mutation, effectively overcoming the response delay caused by gas supply lag and improving the dynamic response speed of the system.

[0071] To address the inherent slow dynamic response of each fuel cell system, this embodiment also designs a feedback composite correction control: the multi-module fuel cell system controller monitors the total power tracking deviation and the circulating current state between the multi-module fuel cell systems in real time based on the operating data reported by the multi-module fuel cell systems, and dynamically corrects the power command of the multi-module fuel cell system through PI regulation, and achieves accurate power tracking through dual closed-loop control.

[0072] In summary, this embodiment addresses the inherent characteristics of multi-module fuel cell systems, such as delayed gas supply and slow dynamic response. By combining feedforward and feedback control, and through the synergistic effect of feedforward and feedback, composite correction of power distribution is achieved. This enables the multi-module fuel cell system to respond quickly to predicted changes in operating conditions, eliminate real-time deviations and external disturbances, and significantly improve dynamic response speed and steady-state control accuracy.

[0073] Compared with existing technologies, this embodiment, based on route, speed, and power prediction, leverages the fixed locomotive operating route and predictable operating conditions. Through global trajectory analysis and forward-looking prediction, it achieves coordinated control of the multi-module fuel cell system and power battery, effectively solving the technical challenges of gas supply lag and response delay, and balancing system economy and durability optimization. Furthermore, this embodiment breaks through the limitations of existing passive response control, transforming route geographical information and speed variation patterns into a basis for predicting future power demand. It identifies sudden power surges in advance and pre-adjusts the gas supply status, significantly improving the system's predictability and dynamic response speed, ensuring efficient, stable, and reliable locomotive operation.

[0074] Example 2: Based on the coordinated control method for a multi-module fuel cell system in a locomotive described in Embodiment 1, this embodiment provides a power distribution process for an upper-level hydrogen-electric hybrid power system, such as... FCUAs shown, it includes: step S21 : Obtain the current state of charge of the power battery and the predicted power demand sequence of the locomotive; step S22 Based on the vehicle demand power prediction sequence, analyze the power change characteristics in the future preset prediction time domain, and identify key operating condition nodes such as power peak, fluctuation range, station parking, speed limit change, and curve section; step S23 The total output power of the multi-module fuel cell system is determined based on preset power allocation rules. step S24 The finalized total output power command of the multi-module fuel cell system is sent to the multi-module fuel cell system controller as the target value for fine-grained power allocation at the lower level.

[0075] Example 3: Based on the coordinated control method for a locomotive multi-module fuel cell system described in Embodiment 1, this embodiment provides a lower-level multi-module fuel cell system coordinated control process, such as... Figure 2 As shown, it includes: step S31 The system constructs optimization functions for both economic and durability objectives: The multi-module fuel cell system controller receives the total output power command from the upper layer and simultaneously collects real-time operating data from each fuel cell module, including cumulative operating time, current average node voltage, output power, and efficiency. Based on the dual objectives of economic efficiency and durability, a multi-objective optimization function is constructed: minimizing the total hydrogen consumption of the system is the economic objective, and minimizing the lifespan degradation of each module is the durability objective. Combined with pre-set weighting coefficients, a comprehensive optimization objective function is formed, and upper and lower limits for the output power of each module, power change rate constraints, and total power balance constraints are simultaneously set.

[0076] step S32 The optimization problem is solved to obtain the optimal power allocation sequence for each module of the fuel cell system. The particle swarm optimization algorithm is used to solve the above multi-objective optimization problem. Under the premise of satisfying all constraints, a set of optimal power allocation sequences is obtained, so that each module can achieve coordinated optimization of hydrogen consumption and lifespan decay under the current operating conditions.

[0077] step S33 : Distribute the optimal power allocation sequence and receive operating data: The optimal power allocation sequence obtained by the solution is distributed to the controller of each fuel cell module, and the operating data uploaded by each module within the time interval is received to provide real-time status feedback for the next round of optimization calculation, forming a closed-loop control.

[0078] Example 4: This embodiment provides a coordinated control device for a locomotive multi-module fuel cell system, used to implement the aforementioned coordinated control method for a locomotive multi-module fuel cell system, including: a vehicle controller, a multi-module fuel cell system controller, a multi-module fuel cell system, and a power battery, such as... Figure 3 As shown, where: The vehicle controller is used to acquire the line characteristic parameters of the locomotive's predetermined operating route, and generate a global reference operating trajectory database based on the line characteristic parameters; at any current moment, it predicts the locomotive speed sequence within a preset future time window based on the global reference operating trajectory database, and obtains the vehicle's required power sequence based on the locomotive speed sequence; it acquires the power battery state of charge at the current moment, and determines the total output power of the multi-module fuel cell system based on the power battery state of charge, the vehicle's required power sequence, and a preset power allocation rule; The multi-module fuel cell system controller is used to allocate the total output power based on a pre-built multi-objective optimization function to obtain an optimal power allocation sequence; and to perform power output coordination control on the multi-module fuel cell system in the power output preparation state based on the optimal power allocation sequence.

[0079] The multi-module fuel cell system comprises several fuel cell system modules, each with its own fuel cell module controller. This controller reports operational data and receives power allocation data from the optimal power allocation sequence. The power battery interacts with the vehicle controller through the power battery management system, uploading its state of charge (SOC).

[0080] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can realize the coordinated control method of a locomotive multi-module fuel cell system provided by any of the above-described method embodiments of the present invention.

[0081] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0082] Example 5: Based on the above-described embodiment of a coordinated control method for a multi-module fuel cell system in a locomotive, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a coordinated control method for a multi-module fuel cell system in a locomotive according to any embodiment of the present invention.

[0083] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0084] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0085] The processor referred to may be a central processing unit (CPU). Figure 4 It can also be other general-purpose processors, digital signal processors (DSPs), etc. Central Processing Unit, CPU Application-Specific Integrated Circuits (ASICs) Digital Signal Processor, DSP ), ready-made programmable gate arrays ( Application Specific Integrated Circuit, ASIC Field- This could be a programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, connecting various parts of the terminal device via various interfaces and lines.

[0086] Example 6: Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the coordinated control method for a locomotive multi-module fuel cell system described in any of the above-described method embodiments of the present invention.

[0087] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), etc. Programmable Gate Array, FPGA Random Access Memory (RAM) ROM, Read-Only Memory RAM, Random Access Memory (including) electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0088] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A coordinated control method for a multi-module fuel cell system in a locomotive, characterized in that, include: Obtain the line characteristic parameters of the locomotive's predetermined operating route, and generate a global reference operating trajectory database based on the line characteristic parameters; At any given moment, the locomotive speed sequence within a preset future time window is predicted based on the global reference trajectory database, and the vehicle power demand sequence is obtained based on the locomotive speed sequence. Obtain the current state of charge of the power battery, and determine the total output power of the multi-module fuel cell system based on the state of charge of the power battery, the power demand sequence of the vehicle, and the preset power allocation rules; The optimal power allocation sequence is obtained by allocating the total output power based on a pre-constructed multi-objective optimization function; Based on the optimal power allocation sequence, the power output coordination control is performed on the multi-module fuel cell system in the power output preparation state.

2. The coordinated control method for a multi-module fuel cell system in a locomotive as described in claim 1, characterized in that, The step of predicting the locomotive speed sequence within a preset future time window based on the global reference trajectory database at any current moment, and obtaining the vehicle's required power sequence based on the locomotive speed sequence, includes: At any given moment, obtain the locomotive's real-time operating position and historical speed sequence; Based on the real-time operating position of the locomotive and the global reference operating trajectory database, a sequence of predicted route feature parameters is obtained; Based on the global reference trajectory database, a locomotive operation mode sequence corresponding to the predicted line feature parameter sequence is obtained; Based on the predicted line characteristic parameter sequence and the historical speed sequence, a locomotive speed sequence within a preset future time window is obtained; The vehicle's required power sequence is generated based on the locomotive speed sequence, locomotive operation mode sequence, and preset locomotive traction and braking characteristic curve.

3. The coordinated control method for a multi-module fuel cell system in a locomotive as described in claim 1, characterized in that, In the process of obtaining the current state of charge of the power battery and determining the total output power of the multi-module fuel cell system based on the power battery state of charge, the vehicle power demand sequence, and a preset power allocation rule, the preset power allocation rule includes: When the state of charge of the power battery is less than the preset capacity safety lower limit threshold of the power battery, the first candidate sequence of total output power is obtained by summing the vehicle demand power sequence and the preset maximum charging power of the power battery, and the minimum value between the first candidate sequence and the preset maximum output power of the multi-module fuel cell system is selected as the total output power of the multi-module fuel cell system.

4. The coordinated control method for a multi-module fuel cell system in a locomotive as described in claim 3, characterized in that, The preset power allocation rules also include: When the state of charge of the power battery is greater than the preset capacity safety upper limit threshold of the power battery, a second candidate sequence of total output power is obtained by calculating the difference between the vehicle demand power sequence and the preset maximum discharge power of the power battery, and the maximum value between the second candidate sequence and the preset minimum output power of the multi-module fuel cell system is selected as the total output power of the multi-module fuel cell system.

5. The coordinated control method for a multi-module fuel cell system in a locomotive as described in claim 4, characterized in that, The preset power allocation rules also include: When the state of charge of the power battery is not less than the preset lower limit threshold for safe capacity and not greater than the preset upper limit threshold for safe capacity: The current output power is obtained, and the current maximum output power is obtained by summing the current output power and the preset maximum discharge power. When it is determined based on the vehicle demand power sequence that there is a peak demand power of the vehicle that is greater than the current maximum output power, a third candidate output power is obtained based on the current output power and the preset charging power increment of the multi-module fuel cell system, and the minimum value between the third candidate output power and the preset maximum output power is selected as the total output power of the multi-module fuel cell system.

6. The coordinated control method for a multi-module fuel cell system in a locomotive as described in claim 5, characterized in that, After obtaining the current output power and summing it with the preset maximum discharge power to obtain the current maximum output power, the preset power allocation rule further includes: When it is determined, based on the vehicle demand power sequence, that there is no locomotive vehicle demand power peak greater than the current maximum output power: The power variance is obtained based on the power demand sequence of the whole vehicle, and the fluctuation is judged based on the power variance, the fluctuation coefficient and the rated power of the multi-module fuel cell system to obtain the fluctuation judgment result. When the fluctuation judgment result meets the preset fluctuation conditions, the fuel cell demand power series is obtained by calculating the difference between the vehicle demand power series and the basic discharge power of the power battery. The maximum value between the fuel cell demand power series and the preset minimum output power is selected as the first candidate output power, and the minimum value between the first candidate output power and the preset maximum output power of the multi-module fuel cell system is selected as the total output power of the multi-module fuel cell system.

7. The coordinated control method for a multi-module fuel cell system in a locomotive as described in claim 6, characterized in that, The preset power allocation rules also include: When the fluctuation judgment result does not meet the preset fluctuation conditions, the preset optimal output efficiency point of the multi-module fuel cell system is taken as the total output power.

8. The coordinated control method for a multi-module fuel cell system in a locomotive as described in claim 1, characterized in that, The process of allocating the total output power based on a pre-constructed multi-objective optimization function to obtain the optimal power allocation sequence includes: Obtain the cumulative operating time and average segment voltage for each fuel cell module in a multi-module fuel cell system. Obtain several preset lifetime values ​​and several initial average node voltages corresponding to several of the aforementioned fuel cell modules; Based on the cumulative operating time, average cell voltage, preset lifespan value, initial average cell voltage, and preset lifespan decay weighting coefficient, a lifespan decay function corresponding to each of the fuel cell modules is constructed. Based on the total output power, construct several instantaneous hydrogen consumption functions corresponding to the fuel cell modules respectively; A multi-objective optimization function is constructed by weighted summation based on preset economic target coefficients, preset durability target coefficients, several instantaneous hydrogen consumption functions, and several lifetime decay functions; The optimal power allocation sequence is obtained by allocating the total output power based on the multi-objective optimization function and preset constraints.

9. The coordinated control method for a multi-module fuel cell system in a locomotive as described in claim 1, characterized in that, Also includes: Based on the vehicle demand power sequence, future power mutation information and power mutation time are obtained, and pre-adjustment instructions are generated based on the future power mutation information. Based on the pre-adjustment command, the air supply to the multi-module fuel cell system is adjusted so that the multi-module fuel cell system is in the power output preparation state at the moment of power change.

10. A coordinated control device for a multi-module fuel cell system in a locomotive, characterized in that, A coordinated control method for a locomotive multi-module fuel cell system as described in any one of claims 1 to 9, comprising: a vehicle controller, a multi-module fuel cell system controller, a multi-module fuel cell system, and a power battery, wherein: The vehicle controller is used to acquire the line characteristic parameters of the locomotive's predetermined operating route, and generate a global reference operating trajectory database based on the line characteristic parameters; at any current moment, it predicts the locomotive speed sequence within a preset future time window based on the global reference operating trajectory database, and obtains the vehicle's required power sequence based on the locomotive speed sequence; it acquires the power battery state of charge at the current moment, and determines the total output power of the multi-module fuel cell system based on the power battery state of charge, the vehicle's required power sequence, and a preset power allocation rule; The multi-module fuel cell system controller is used to allocate the total output power based on a pre-built multi-objective optimization function to obtain an optimal power allocation sequence; and to perform power output coordination control on the multi-module fuel cell system in the power output preparation state based on the optimal power allocation sequence.

Images