Fuel cell heavy commercial vehicle energy management method, system, equipment and medium

Abstract

The invention belongs to the field of fuel cell vehicles, and provides a fuel cell heavy commercial vehicle energy management method, system, equipment and medium, a fuel cell heavy commercial vehicle dynamic planning optimization model is established, the purpose of achieving the lowest running cost of a fuel cell heavy commercial vehicle is achieved, and gears of a power cell SOC and an ATM are considered at the same time. Based on the driving condition of the semi-trailer tractor, different initial states of the battery SOC are considered, and the optimal power distribution of the FCECV is determined by using a DP algorithm model. An adaptive fuzzy inference system capable of being applied online is developed based on an ANFIS method, and an ANFIS model is trained in combination with a DP solution set and based on a particle swarm optimization algorithm; finally, the real-time output power of the fuel cell is limited through a power limiting method, the durability of the fuel cell system is ensured, and therefore the energy utilization efficiency of the vehicle is remarkably improved, the endurance mileage is prolonged, and the operation cost is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of fuel cell vehicles, and in particular relates to an energy management method, system, equipment and medium for a fuel cell heavy-duty commercial vehicle. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Energy conservation and new energy technologies are one of the main directions of development of the current automobile industry. Fuel cell vehicles have the advantages of being clean and pollution-free. At the same time, fuel cell commercial vehicles also have broad development space.

[0004] Influenced by fuel cell technology, fuel cell heavy-duty commercial vehicles (FCHEV) often use auxiliary power sources (such as lithium battery packs or supercapacitors) to make up for the shortcomings of fuel cells such as low specific power and slow response. Compared with a single energy source, FCHEV is more complex in terms of power system design and energy management optimization. It is necessary not only to consider the differences in the demand for power systems and energy management in different application scenarios, but also to fully combine the real-time changes of vehicle operation scenarios and their own states. At present, rule-based strategies have low requirements on controller computing power and have the conditions for online application, but they do not fully tap the energy-saving potential of vehicles. Strategies based on global optimization (such as dynamic programming, Pontryagin minimum principle, etc.) can theoretically achieve global optimization, but in the actual operation of the vehicle, the working conditions cannot be fully predicted and the optimization calculation amount is large, so they are only suitable for offline optimization. Strategies based on real-time optimization (such as equivalent fuel consumption minimum strategy and model predictive control-based strategy) obtain the optimal power distribution between multiple energy sources at each moment by solving the minimum value of the cost function in each time step (or short time domain). Real-time optimization does not require the prediction of the global working conditions of the vehicle, has small calculation amount and high real-time performance, but cannot guarantee global optimization. With the rise of machine learning, reinforcement learning has been applied to solve the energy management problem of hybrid power systems, but this method is very likely to cause the "curse of dimensionality" and has certain limitations when dealing with complex problems. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a fuel cell heavy-duty commercial vehicle energy management method, system, equipment and medium. The present invention establishes a DP model for offline optimization of fuel cell vehicle energy management, with the goal of achieving the lowest operating cost of FCECV, and taking into account the power battery state of charge (SOC) and the gear of the automatic transmission (AMT). Based on the China Semi-trailer Tractor Train Driving Condition (CHTC-TT), considering the different initial states of battery SOC, the DP algorithm model is used to determine the optimal power distribution of FCECV. Based on the ANFIS method, an adaptive fuzzy inference system that can be applied online is developed, and the ANFIS model is trained based on the DP solution set and the particle swarm optimization (PSO) algorithm to obtain an adaptive fuzzy inference system that can be applied to FCECV energy management in real time. The real-time output power of the fuel cell is limited by the power limitation method to ensure the durability of the fuel cell system.

[0006] According to some embodiments, a first solution of the present invention provides an energy management method for a fuel cell heavy-duty commercial vehicle, which adopts the following technical solution: A fuel cell heavy-duty commercial vehicle energy management method, comprising: Considering the state of charge of the power battery and the gear position of the automatic transmission, a dynamic programming optimization algorithm model is established with the goal of minimizing the global operating cost of fuel cell heavy-duty commercial vehicles. Using the dynamic programming optimization algorithm model, based on the semi-trailer tractor working conditions and considering the different initial states of the battery state of charge, the optimal power distribution of the fuel cell heavy-duty commercial vehicle is solved to obtain the optimal state of charge change of the power battery and the optimal output power of the fuel cell; Establish an adaptive neural fuzzy inference system with the power battery state of charge and the vehicle power requirement as input and the fuel cell system power as output. Use the dynamic programming optimization algorithm model solution set and the particle swarm optimization algorithm to train the adaptive neural fuzzy inference system to obtain the optimal fuzzy inference system. In the process of real-time energy management using the optimal fuzzy inference system, the output power of the fuel cell system is limited based on power constraints to ensure the durability of the fuel cell.

[0007] According to some embodiments, the second solution of the present invention provides a fuel cell heavy-duty commercial vehicle energy management method system, which adopts the following technical solution: Fuel cell heavy-duty commercial vehicle energy management system, including: The dynamic programming optimization algorithm model building module is configured to consider the state of charge of the power battery and the gear position of the automatic transmission, and to establish a dynamic programming optimization algorithm model with the goal of minimizing the global operating cost of the fuel cell heavy-duty commercial vehicle; The optimal output power determination module is configured to use a dynamic programming optimization algorithm model to solve the optimal power distribution of the fuel cell heavy-duty commercial vehicle based on the semi-trailer tractor operating conditions and take into account different initial states of the battery state of charge to obtain the optimal state of charge change of the power battery and the optimal output power of the fuel cell; The optimal fuzzy inference system determination module is configured to establish an adaptive neural fuzzy inference system with the power battery state of charge and the vehicle required power as input and the fuel cell system power as output, and to train the adaptive neural fuzzy inference system based on the particle swarm optimization algorithm using the dynamic programming optimization algorithm model solution set to obtain the optimal fuzzy inference system; The real-time energy management module is configured to limit the output power of the fuel cell system based on power constraints during the real-time energy management process using the optimal fuzzy inference system to ensure the durability of the fuel cell.

[0008] According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium.

[0009] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the fuel cell heavy-duty commercial vehicle energy management method as described in the first aspect above.

[0010] According to some embodiments, a fourth aspect of the present invention provides a computer device.

[0011] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the energy management method for a fuel cell heavy-duty commercial vehicle as described in the first aspect above are implemented.

[0012] Compared with the prior art, the present invention has the following beneficial effects: The combination of the adaptive neural fuzzy inference system and dynamic programming in the present invention can give full play to the advantages of both and achieve more accurate and optimized energy management. Through the adaptive neural fuzzy inference system to learn the optimal power distribution of the vehicle based on DP, the fuel cell and the power battery can work more efficiently, thereby significantly improving the energy utilization efficiency of the vehicle, extending the cruising range, and reducing operating costs.

[0013] The reasonable energy management of the present invention can reduce the working time and load of fuel cells and power batteries under inappropriate working conditions, reduce their loss and failure risks, and thus enhance the reliability and durability of the entire power system. At the same time, the research and application of energy management methods based on adaptive neural fuzzy reasoning system and dynamic programming will help solve the current technical bottlenecks of fuel cell heavy-duty commercial vehicles, improve their performance and economy, accelerate their promotion and application in the market, and promote the sustainable development of the transportation industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0015] Figure 1 This is a flow chart of a fuel cell heavy-duty commercial vehicle energy management method in an embodiment of the present invention; Figure 2 is a transmission system architecture diagram of the FCECV in an embodiment of the present invention; Figure 3 is a DP solution flow chart based on CHTC-TT working condition in an embodiment of the present invention; Figure 4 Schematic diagram of DP solution results based on CHTC-TT working condition in an embodiment of the present invention, (a) driving condition and AMT gear position; (b) power demand; (c) power distribution; Figure 5 DP verification results of the embodiment of the present invention with initial SOC=0.9, (a) battery SOC; (b) hydrogen consumption; Figure 6 DP verification results of the embodiment of the present invention with initial SOC=0.6, (a) battery SOC; (b) hydrogen consumption; Figure 7 DP verification results of the embodiment of the present invention with initial SOC=0.3, (a) battery SOC; (b) hydrogen consumption; Figure 8 is the training data set of the ANFIS model in the embodiment of the present invention, (a) power demand; (b) battery SOC; (c) FCS power output; Fig. 9 It is an energy management system based on ANFIS in an embodiment of the present invention; Fig.10 is the optimal fitness of the ANFIS model training process in the embodiment of the present invention; Fig.11 is the ANFIS model training result in the embodiment of the present invention, (a) output expected value and estimated value; (b) error; (c) error distribution; Fig.12 The ANFIS model test results in the embodiment of the present invention include: (a) output expected value and estimated value; (b) error; (c) error distribution; Fig.13 are the control results of typical working conditions in the embodiment of the present invention, (a) FCS power; (b) FCS power change rate; (c) battery SOC; (d) hydrogen consumption; Fig.14 is the FCS output power under four random working conditions in the embodiment of the present invention, (a) working condition 1; (b) working condition 2; (c) working condition 3; (d) working condition 4; Fig.15 is the FCS power change rate under four random working conditions in the embodiment of the present invention, (a) working condition 1; (b) working condition 2; (c) working condition 3; (d) working condition 4; Fig.16 1 is the SOC trajectory of the power battery under four random working conditions in the embodiment of the present invention, (a) working condition 1; (b) working condition 2; (c) working condition 3; (d) working condition 4; Fig.17 1 is the distribution of FCS operating points under four random operating conditions in the embodiment of the present invention, (a) operating condition 1; (b) operating condition 2; (c) operating condition 3; (d) operating condition 4; Fig.18 5 is the FCS hydrogen consumption under four random working conditions in the embodiment of the present invention, (a) working condition 1; (b) working condition 2; (c) working condition 3; (d) working condition 4. DETAILED DESCRIPTION

[0016] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0017] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0018] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0019] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0020] Embodiment 1 The present embodiment provides an energy management method for a fuel cell heavy-duty commercial vehicle. The present embodiment uses the method applied to a server as an example for illustration. It is understandable that the method can also be applied to a terminal, and can also be applied to a terminal, a server, and a system, and is implemented through the interaction between the terminal and the server. The server can be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communications, middleware services, domain name services, security services CDN, and big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in this application. In the present embodiment, the method includes the following steps: Considering the state of charge of the power battery and the gear position of the automatic transmission, a dynamic programming optimization algorithm model is established with the goal of minimizing the global operating cost of fuel cell heavy-duty commercial vehicles. Using the dynamic programming optimization algorithm model, based on the semi-trailer tractor working conditions and considering the different initial states of the battery state of charge, the optimal power distribution of the fuel cell heavy-duty commercial vehicle is solved to obtain the optimal state of charge change of the power battery and the optimal output power of the fuel cell; Establish an adaptive neural fuzzy inference system with the power battery state of charge and the vehicle power requirement as input and the fuel cell system power as output. Use the dynamic programming optimization algorithm model solution set and the particle swarm optimization algorithm to train the adaptive neural fuzzy inference system to obtain the optimal fuzzy inference system. In the process of real-time energy management using the optimal fuzzy inference system, the output power of the fuel cell system is limited based on power constraints to ensure the durability of the fuel cell.

[0021] like Figure 1 As shown, this embodiment specifically includes: Dynamic programming: A dynamic programming (DP) algorithm is designed based on FCECV, taking into account the battery SOC and AMT gear position, and calculating the global optimal solution according to the given driving conditions. The power distribution of the power battery and the fuel cell system is optimized to minimize the operating cost of the FCECV while satisfying the given driving conditions and system constraints.

[0022] S1: Considering the battery SOC and AMT gear position, a dynamic programming optimization algorithm model is established.

[0023] The specific operation process of S1 is as follows: S11: Build the powertrain structure of FCECV, the structure of which is as follows Figure 2Based on the studied FCECV, a DP optimization algorithm model is established, with the power battery SOC and AMT gear position as state variables, and FCS power output and AMT shifting as control variables; The state variables are represented as follows: (1); in, is the battery SOC state, This is the AMT gear position.

[0024] At the same time, the decision variables are expressed as follows: (2); in, For FCS The output power of the step, For FCS It should be noted that the output power of the fuel cell system (FCS) is determined by the accelerator pedal opening, while the gear position of the AMT is determined by the current gear position and the gear shifting action. In order to represent downshifting, holding and upshifting, the present invention uses -1, 0 and 1 as the decision variables of the AMT.

[0025] Therefore, based on the previous formula (2), the state equation of the system can be expressed as follows: (3); in, is the battery SOC state, is the open circuit voltage, is the internal resistance of the battery, is the battery level, is the battery capacity, For AMT gear, For FCS The gear shifting action of the step is described in detail, wherein it can be understood that the system here refers to the vehicle power system.

[0026] S12: Taking the minimum global operating cost of FCECV as the DP optimization goal, and adding relevant constraints according to the actual physical characteristics of FCECV to ensure the feasibility of the algorithm, the final dynamic programming (DP) optimization algorithm goal is obtained. .

[0027] The DP solution goal is to optimize the energy consumption and efficiency of the FCECV. The cost function-dynamic programming (DP) optimization algorithm model in the present invention mainly includes three parts: hydrogen consumption cost, battery power consumption cost and shift penalty function, as shown in the following formula: (4); The instantaneous power of the fuel cell system (FCS) and the instantaneous power of the battery are respectively and express, represents the price of hydrogen, For the working efficiency of FCS, Indicates the lower heating value of hydrogen, represents the price of electric energy, is the gear shift penalty coefficient, For FCS Step shifting action.

[0028] In addition, DP problems also need to incorporate specific constraints to ensure compliance with the physical characteristics of the system in order to obtain a feasible solution. The physical constraints of FCECV are implemented in the following ways: (5); The instantaneous power of the battery, fuel cell system (FCS) and motor are respectively , and Their respective constraints are defined as , and The motor is in the Step speed Indicated that restrictions. Indicates steps The battery SOC is limited by In addition, the terminal SOC (i.e. SOC f ) imposes a soft constraint of 0.2 to 0.25 to prevent battery drain.

[0029] S2: Using the established DP model, based on the CHTC-TT operating condition, and considering different initial states of battery SOC, solve the optimal power allocation of FCECV to obtain the optimal SOC change of the power battery and the optimal output power of the fuel cell; The specific operation process of S2 is as follows: Known working conditions, such as Figure 3 As shown, the solution is obtained using the CHTC-TT condition: S21: When the power battery SOC is high (initial value = 0.9), medium (initial value = 0.6) and low (initial value = 0.3), the DP optimization algorithm model is used to solve the FCECV energy management problem based on the CHTC-TT working condition. The solution process includes the following five steps: Step 1: Based on the given driving conditions, with a time step of 1s, the decision-making process is divided into Nphases, calculating the vehicle at each time step k The power demand, k =1,2,3… N .

[0030] Step 2: Take the fuel cell system (FCS) output power and AMT shifting action as decision variables, the battery SOC and AMT gear as state variables, and set the constraints of the battery SOC and AMT gear respectively. At the same time, define a cost function matrix to store the optimal cost. In other words, determine the state variables and constraints based on the dynamic programming algorithm model, and define the cost function matrix to store the optimal cost; Step 3: The battery SOC and the output power of the fuel cell system (FCS) are evenly discretized into Q and M states within their respective ranges. At the same time, the AMT gear position and shifting action are also evenly discretized into the state grid. The shifting actions are downshift, hold and upshift.

[0031] Step 4: Under the condition that the terminal constraint requirements are met, k = N First, solve the cost of the DP optimization algorithm model corresponding to each decision stage in turn to ensure that k All discrete states are traversed until the time step is satisfied. k =1 ends.

[0032] Step 5: Start forward optimization from k=1, obtain the optimal cost of the DP optimization algorithm model in each time step, and store it in the pre-set cost function matrix until the time step is met k = N When it ends.

[0033] The optimal cost and system state equation of the DP optimization algorithm model in each time step are used to obtain the global optimal decision variables, namely the fuel cell system (FCS) output power and the AMT shifting action. At the same time, the optimal decision variables are used to obtain the optimized state variables, including the optimal battery SOC and the optimal AMT gear.

[0034] The final solution result is that each time step will get an optimal solution, and the optimal solution set of all steps is the optimal solution set; the solution result is as follows Figure 4 As shown in the figure, the optimal changes of battery SOC and fuel cell system output power are obtained, and the DP algorithm is verified; the verification results when the power battery SOC is high (initial value = 0.9), medium (initial value = 0.6) and low (initial value = 0.3) are shown in the figure. Figure 5 , Figure 6 and Figure 7 shown.

[0035] The optimal solution set is the optimal SOC change and fuel cell system output power obtained based on different SOC initial values.

[0036] S22: The optimal solution set obtained by DP solving is used as part of the training data set for subsequent model optimization.

[0037] The optimal solution set for FCECV optimal energy management based on different SOC levels is the optimal battery state of charge (SOC) and the optimal fuel cell output power at different time steps. ; Then establish the required power of the whole vehicle , battery SOC and fuel cell output power The training data set is normalized and the results are as follows Figure 8 shown.

[0038] S3: Establish an adaptive neuro-fuzzy inference system (ANFIS) with power battery SOC and vehicle power demand as input and fuel cell system power as output. Use the training data set to train the ANFIS model based on the PSO algorithm to obtain a fuzzy inference system (FIS) that can be applied to FCECV energy management in real time. The specific operation process of S3 is as follows: ANFIS model: S31: The ANFIS model is established with the vehicle power demand and battery SOC as input and the fuel cell system power as output. The energy management system based on ANFIS is as follows: Fig. 9 As shown, the vehicle power requirement , battery SOC as input, fuel cell output power is the output; Optimal FIS: S32: Using the training data set, the ANFIS model is trained based on the PSO algorithm to obtain the optimal fuzzy inference system (FIS). The performance of the ANFIS model is evaluated using statistical indicators, including mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE) and standard deviation error (SDE) distribution. The evaluation indicators are shown in the following formula: (6); in, and Indicates the training process i expected and estimated values, represents the total amount of training data, represents the mean of all expected values.

[0039] During the training process, the maximum number of iterations was 1000 and the population size of the PSO algorithm was 100. The initial inertia weight, inertia weight damping ratio, individual learning coefficient, and global learning coefficient were set to 1, 0.99, 1, and 2, respectively. In addition, the reliability of the training results was evaluated by dividing the training data into two subsets, which contained 80% (i.e., 4320 data points for training) and 20% (1080 data points for testing) of the total data, respectively. The optimal fitness of the training process is shown in Fig.10 As shown in Figure 2, the training and testing results of the ANFIS model are respectively Fig.11 and Fig.12 Given in.

[0040] S4: Real-time optimization: In the real-time energy management process, the output power of the fuel cell system is limited based on the power constraint method to ensure the durability of the fuel cell; The specific operation process of S4 is as follows: Unknown operating conditions, fuzzy control: S41: Apply the trained FIS to FCECV online energy management control, fuzzy control under unknown operating conditions; Energy allocation, durability constraint: S42: Use power constraint to adjust the fuel cell power output by the FIS in real time to ensure that its power variation range does not fluctuate greatly, thereby ensuring the durability of the fuel cell.

[0041] An additional constraint is added to limit the fuel cell power output by the FIS system to ensure the durability of the FCS. The constraint can be expressed as follows: (7); in, represents the rate of change of FCS output power, where and They represent the lower and upper limits of the rate of change of the FCS output power, respectively. When applied online, the adjusted FCS power is used to determine the actual vehicle power allocation. The adjustment can be determined by the following formula: (8); in, is the actual output power of the FCS, which usually varies within 10% of the maximum output power of the FCS.

[0042] In summary, the output power of the fuel cell system is limited based on power constraints, specifically: When the instantaneous power of the fuel cell system is less than the minimum value of the rate of change of the output power of the fuel cell system, the sum of the instantaneous power of the fuel cell system and the minimum value of the rate of change of the output power of the fuel cell system is taken as the actual output power of the fuel cell system; When the instantaneous power of the fuel cell system is greater than the maximum value of the rate of change of the output power of the fuel cell system, the sum of the instantaneous power of the fuel cell system and the maximum value of the rate of change of the output power of the fuel cell system is taken as the actual output power of the fuel cell system; Otherwise, the instantaneous power of the fuel cell system is taken as the actual output power of the fuel cell system.

[0043] The control effect of the implementation of the method described is as follows Fig.13 , Fig.14 , Fig.15 , Fig.16 , Fig.17 and Fig.18 As shown. Among them, Fig.13 These are the results of typical operating conditions. (a), (b), (c), and (d) in the figure respectively represent the power of FCS, the power change rate of FCS, the battery SOC, and the hydrogen consumption. Figure 14~Figure 18 These are the results under four random working conditions. Fig.14 is the FCS output power, Fig.15 is the FCS power change rate, Fig.16 is the power battery SOC trajectory, Fig.17 is the FCS working point distribution, Fig.18 is the hydrogen consumption of FCS.

[0044] Embodiment 2 This embodiment provides a fuel cell heavy-duty commercial vehicle energy management system, including: The dynamic programming optimization algorithm model building module is configured to consider the state of charge of the power battery and the gear position of the automatic transmission, and to establish a dynamic programming optimization algorithm model with the goal of minimizing the global operating cost of the fuel cell heavy-duty commercial vehicle; The optimal output power determination module is configured to use a dynamic programming optimization algorithm model to solve the optimal power distribution of the fuel cell heavy-duty commercial vehicle based on the semi-trailer tractor operating conditions and take into account different initial states of the battery state of charge to obtain the optimal state of charge change of the power battery and the optimal output power of the fuel cell; The optimal fuzzy inference system determination module is configured to establish an adaptive neural fuzzy inference system with the power battery state of charge and the vehicle required power as input and the fuel cell system power as output, and to train the adaptive neural fuzzy inference system based on the particle swarm optimization algorithm using the dynamic programming optimization algorithm model solution set to obtain the optimal fuzzy inference system; The real-time energy management module is configured to limit the output power of the fuel cell system based on power constraints during the real-time energy management process using the optimal fuzzy inference system to ensure the durability of the fuel cell.

[0045] The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment 1. It should be noted that the above modules as part of the system can be executed in a computer system such as a set of computer executable instructions.

[0046] The description of each embodiment in the above embodiments has different emphases. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0047] The proposed system can be implemented in other ways. For example, the system embodiment described above is only illustrative, and the division of the modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0048] Embodiment 3 This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the energy management method for a fuel cell heavy-duty commercial vehicle as described in the first embodiment above are implemented.

[0049] Embodiment 4 This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the fuel cell heavy-duty commercial vehicle energy management method as described in the above-mentioned embodiment 1 are implemented.

[0050] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0051] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0052] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0053] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0054] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0055] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A fuel cell heavy-duty commercial vehicle energy management method, characterized in that: include: Considering the state of charge of the power battery and the gear position of the automatic transmission, a dynamic programming optimization algorithm model is established with the goal of minimizing the global operating cost of fuel cell heavy-duty commercial vehicles. Using the dynamic programming optimization algorithm model, based on the semi-trailer tractor working conditions and considering the different initial states of the battery state of charge, the optimal power distribution of the fuel cell heavy-duty commercial vehicle is solved to obtain the optimal state of charge change of the power battery and the optimal output power of the fuel cell; Establish an adaptive neural fuzzy inference system with the power battery state of charge and the vehicle power requirement as input and the fuel cell system power as output. Use the dynamic programming optimization algorithm model solution set and the particle swarm optimization algorithm to train the adaptive neural fuzzy inference system to obtain the optimal fuzzy inference system. In the process of real-time energy management using the optimal fuzzy inference system, the output power of the fuel cell system is limited based on power constraints to ensure the durability of the fuel cell.

2. The fuel cell heavy-duty commercial vehicle energy management method according to claim 1, characterized in that: The dynamic programming optimization algorithm model is established by considering the power battery charge state and the automatic transmission gear position and taking the global operation cost of the fuel cell heavy-duty commercial vehicle as the minimum, specifically: The state equation of the fuel cell system is constructed by taking the power battery charge state and the automatic transmission gear position as state variables, and the fuel cell system power output and automatic transmission shift as decision variables. A dynamic programming optimization algorithm model is established with the goal of minimizing the global operating cost of fuel cell heavy-duty commercial vehicles and the physical characteristics of fuel cell heavy-duty commercial vehicles as constraints.

3. The fuel cell heavy-duty commercial vehicle energy management method according to claim 2, characterized in that: The global operating cost of the fuel cell heavy-duty commercial vehicle includes hydrogen consumption cost, battery power consumption cost and shift penalty function; The constraints are the instantaneous power limit of the battery, the instantaneous power limit of the fuel cell system, the instantaneous power limit of the motor, the speed limit of a certain step of the motor, the battery state of charge limit of a certain step, and the terminal state of charge limit.

4. The fuel cell heavy-duty commercial vehicle energy management method according to claim 1, characterized in that: The dynamic programming optimization algorithm model is used to solve the optimal power distribution of fuel cell heavy-duty commercial vehicles based on the semi-trailer tractor working conditions and considering different initial states of battery charge state. Specifically, According to the given driving conditions, with 1s as the time step, the decision process is divided into N phases, calculating the vehicle at each time step k The power demand, k =1,2,3… N ; Determine state variables and constraints based on the dynamic programming algorithm model, and define a cost function matrix to store the optimal cost; The battery state of charge and the output power of the fuel cell system are uniformly discretized into their respective ranges. Q and M At the same time, the automatic transmission gear position and shifting action are also evenly discretized into the state grid, and the shifting actions are downshift, hold and upshift; In the case of meeting the terminal constraint requirements, k = N At the beginning, the cost of the dynamic programming optimization algorithm model corresponding to each decision stage is solved in turn to ensure that k All discrete states are traversed until the time step is satisfied. k =1 ends; from k =1 starts forward optimization, obtains the optimal cost of the dynamic programming optimization algorithm model in each time step, and stores it in the pre-set cost function matrix until the time step is met k = N End of time; The optimal cost and system state equation of the dynamic programming optimization algorithm model in each time step are used to obtain the global optimal decision variables, namely the output power of the fuel cell system and the automatic transmission shifting action. At the same time, the optimal decision variables are used to obtain the optimized state variables, including the optimal battery state of charge and the optimal automatic transmission gear.

5. The fuel cell heavy-duty commercial vehicle energy management method according to claim 1, characterized in that: When the adaptive neuro-fuzzy inference system is trained based on the particle swarm optimization algorithm using the dynamic programming optimization algorithm model solution set, statistical indicators are used to evaluate its performance, including mean square error, root mean square error, mean absolute error and standard deviation error distribution.

6. The fuel cell heavy-duty commercial vehicle energy management method according to claim 5, characterized in that: The solution set of the dynamic programming optimization algorithm model is the optimal battery state of charge and the optimal fuel cell output power at different time steps.

7. The fuel cell heavy-duty commercial vehicle energy management method according to claim 1, characterized in that: The limiting of the output power of the fuel cell system based on the power constraint is specifically as follows: When the instantaneous power of the fuel cell system is less than the minimum value of the rate of change of the output power of the fuel cell system, the sum of the instantaneous power of the fuel cell system and the minimum value of the rate of change of the output power of the fuel cell system is taken as the actual output power of the fuel cell system; When the instantaneous power of the fuel cell system is greater than the maximum value of the rate of change of the output power of the fuel cell system, the sum of the instantaneous power of the fuel cell system and the maximum value of the rate of change of the output power of the fuel cell system is taken as the actual output power of the fuel cell system; Otherwise, the instantaneous power of the fuel cell system is taken as the actual output power of the fuel cell system.

8. Fuel cell heavy-duty commercial vehicle energy management system, characterized in that: include: The dynamic programming optimization algorithm model building module is configured to consider the state of charge of the power battery and the gear position of the automatic transmission, and to establish a dynamic programming optimization algorithm model with the goal of minimizing the global operating cost of the fuel cell heavy-duty commercial vehicle; The optimal output power determination module is configured to use a dynamic programming optimization algorithm model to solve the optimal power distribution of the fuel cell heavy-duty commercial vehicle based on the semi-trailer tractor operating conditions and take into account different initial states of the battery state of charge to obtain the optimal state of charge change of the power battery and the optimal output power of the fuel cell; The optimal fuzzy inference system determination module is configured to establish an adaptive neural fuzzy inference system with the power battery state of charge and the vehicle required power as input and the fuel cell system power as output, and to train the adaptive neural fuzzy inference system based on the particle swarm optimization algorithm using the dynamic programming optimization algorithm model solution set to obtain the optimal fuzzy inference system; The real-time energy management module is configured to limit the output power of the fuel cell system based on power constraints during the real-time energy management process using the optimal fuzzy inference system to ensure the durability of the fuel cell.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the fuel cell heavy-duty commercial vehicle energy management method as described in any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the fuel cell heavy-duty commercial vehicle energy management method as described in any one of claims 1 to 7 are implemented.

Images