Energy management method and device for multi-stack fuel cell hybrid power heavy truck and medium

Abstract

The invention discloses an energy management method and device for a multi-stack fuel cell hybrid power heavy truck and a medium, and can be applied to the technical field of automobile energy management. The method comprises the following steps: constructing a performance degradation model of a multi-stack fuel cell and a power cell to obtain the whole vehicle required power of the multi-stack fuel cell hybrid power heavy truck and the residual electric quantity state of the power cell, and predicting to obtain a first health state of the multi-stack fuel cell and a second health state of the power cell; according to the whole vehicle demand power, the first health state, the second health state, the residual electric quantity state, the first performance degradation model and the second performance degradation model, energy management is performed on the multi-stack fuel cell hybrid power heavy truck through a near-end strategy optimization intelligent agent, so that the power among multiple energy sources in the heavy truck can be reasonably distributed; and the performance degradation speed of the fuel cell and the power cell is reduced.

Description

Technical Field

[0001] The present application relates to the field of automobile energy management technology, and in particular to an energy management method, device, and medium for a multi-stack fuel cell hybrid heavy truck. Background Art

[0002] In the related art, the power system of a fuel cell hybrid heavy-duty truck is mostly composed of multiple fuel cell stacks and power batteries. The power distribution between multiple fuel cell stacks and power batteries, as well as between individual fuel cell stacks, has a significant impact on the vehicle's overall fuel economy and the service life of the energy source. A reasonable energy management strategy can greatly help improve the vehicle's fuel economy and extend the service life of the energy source. However, the practical application of energy management strategies still has many limitations. For example, the lifespan of fuel cells and power batteries is one of the bottleneck technologies restricting the development of fuel cell hybrid vehicles. Among learning-based energy management strategies, deep reinforcement learning algorithms can significantly improve vehicle fuel economy compared to traditional rule-based and optimization-based strategies. The proximal policy optimization (PPO) strategy has the advantages of strong robustness and stability. However, existing PPO-based energy management strategies cannot reasonably distribute power among the multiple energy sources in fuel cell hybrid heavy-duty trucks, resulting in rapid performance degradation of the fuel cells and power batteries.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0004] The main purpose of the embodiments of the present application is to propose a multi-stack fuel cell hybrid heavy-duty truck energy management method, device and medium, which can reasonably distribute the power among multiple energy sources in the fuel cell hybrid heavy-duty truck and reduce the performance degradation rate of the fuel cell and power battery.

[0005] To achieve the above objectives, one aspect of an embodiment of the present application provides an energy management method for a multi-stack fuel cell hybrid heavy truck, the method comprising the following steps:

[0006] Obtaining a required vehicle power of the multi-stack fuel cell hybrid heavy-duty truck, wherein the multi-stack fuel cell hybrid heavy-duty truck is provided with multiple stacks of fuel cells and power batteries;

[0007] Constructing a first performance degradation model for multiple fuel cell stacks and a second performance degradation model for power batteries;

[0008] Predicting a first health state of the plurality of fuel cell stacks and a second health state of the power battery using a pre-trained preset neural network model;

[0009] Obtaining the remaining power state of the power batteries in the multi-stack fuel cell hybrid heavy truck;

[0010] According to the required power of the entire vehicle, the first health state, the second health state, the remaining power state, the first performance degradation model and the second performance degradation model, energy management of the multi-stack fuel cell hybrid heavy truck is performed through a proximal strategy optimization intelligent agent.

[0011] In some embodiments, obtaining the vehicle power requirement of the multi-stack fuel cell hybrid heavy truck includes:

[0012] The vehicle dynamics model is used to obtain the required vehicle power of a multi-stack fuel cell hybrid heavy truck, wherein the vehicle dynamics model is as follows:

[0013]

[0014] In the formula, P dem is the required power of the vehicle, V is the vehicle speed, f is the rolling resistance coefficient, C D is the air resistance coefficient, A is the frontal area of the vehicle, a is the vehicle acceleration, α is the road slope, and m is the vehicle mass.

[0015] In some embodiments, constructing a first performance degradation model of a multi-stack fuel cell includes:

[0016] Obtaining a voltage attenuation of each fuel cell stack;

[0017] The first performance degradation model is constructed according to all the voltage attenuations.

[0018] In some embodiments, the voltage attenuation is calculated as follows:

[0019] V fcsd =V s +V i +V f +V h ;

[0020] In the formula, V fcsd is the voltage attenuation of a single fuel cell stack, V s is the fuel cell stack voltage attenuation under start-stop conditions, V i is the fuel cell stack voltage attenuation at idle speed, V f V is the voltage attenuation of the fuel cell stack under frequent load changes. h It is the voltage attenuation of the fuel cell stack under heavy load.

[0021] In some embodiments, the calculation formula of the second performance degradation model is as follows:

[0022]

[0023] In the formula, Q loss is the capacity attenuation of the power battery, α and β are the fitting coefficients of the remaining power state of the power battery, θ is the Celsius temperature, I c is the charge and discharge rate, Ah is the cumulative charge, and z is the power exponential factor.

[0024] In some embodiments, the training process of the pre-trained preset neural network model includes the following steps:

[0025] Acquiring first historical performance degradation data of the plurality of fuel cell stacks and second historical performance degradation data of the power battery;

[0026] Preprocessing the first historical performance degradation data to obtain third historical performance degradation data; and preprocessing the second historical performance degradation data to obtain fourth historical performance degradation data;

[0027] performing feature extraction on the third historical performance degradation data to obtain first feature data;

[0028] performing feature extraction on the fourth historical performance degradation data to obtain second feature data;

[0029] The third historical performance degradation data and the first characteristic data are input into the neural network model to be trained so that the neural network model to be trained learns the performance degradation law information of the multiple fuel cell stacks; and the fourth historical performance degradation data and the second characteristic data are input into the neural network model to be trained so that the neural network model to be trained learns the performance degradation law information of the power battery.

[0030] In some embodiments, the energy management of the multi-stack fuel cell hybrid heavy truck is performed by a proximal strategy optimization agent based on the vehicle's required power, the first health state, the second health state, the remaining power state, the first performance degradation model, and the second performance degradation model, including:

[0031] The state quantity of the proximal strategy optimization agent is formed according to the vehicle required power, the first health state, the second health state, and the remaining power state;

[0032] Calculating a reward for the proximal strategy optimization agent based on the first performance degradation model, the second performance degradation model, the hydrogen consumption of the multiple fuel cell stacks, and a quadratic term corresponding to an offset of the remaining power state of the power battery;

[0033] Using the target power of the multiple fuel cell stacks as an action variable of the proximal strategy optimization agent;

[0034] Adjust the action variable according to the state quantity and the reward to obtain the latest target power corresponding to the multiple fuel cell stacks;

[0035] Energy management is performed on the multi-stack fuel cell hybrid heavy truck according to the latest target power.

[0036] To achieve the above objectives, another aspect of the present invention provides an energy management device for a multi-stack fuel cell hybrid heavy truck, the device comprising:

[0037] The first module is used to obtain the required vehicle power of the multi-stack fuel cell hybrid heavy-duty truck, wherein the multi-stack fuel cell hybrid heavy-duty truck is provided with multiple stacks of fuel cells and power batteries;

[0038] The second module is used to construct a first performance degradation model of multiple fuel cell stacks and a second performance degradation model of power batteries;

[0039] A third module is configured to predict a first health state of the plurality of fuel cell stacks and a second health state of the power battery using a pre-trained preset neural network model;

[0040] A fourth module is used to obtain the remaining power status of the power battery in the multi-stack fuel cell hybrid heavy truck;

[0041] The fifth module is used to perform energy management on the multi-stack fuel cell hybrid heavy truck through a proximal strategy optimization intelligent agent based on the vehicle's required power, the first health state, the second health state, the remaining power state, the first performance degradation model, and the second performance degradation model.

[0042] To achieve the above objectives, another aspect of the present application provides a computer device, including:

[0043] at least one processor;

[0044] at least one memory for storing at least one program;

[0045] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0046] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above-mentioned method when executed by a processor.

[0047] The embodiments of the present application include at least the following beneficial effects: The present application provides a method, device and medium for energy management of a multi-stack fuel cell hybrid heavy-duty truck. The scheme constructs a first performance degradation model of the multi-stack fuel cells and a second performance degradation model of the power battery to obtain the vehicle-wide power requirement of the multi-stack fuel cell hybrid heavy-duty truck, the remaining power status of the power battery, and the first health status of the multi-stack fuel cells and the second health status of the power battery predicted by a pre-trained preset neural network model. Then, according to the vehicle-wide power requirement, the first health status, the second health status, the remaining power status, the first performance degradation model and the second performance degradation model, the multi-stack fuel cell hybrid heavy-duty truck is energy managed by a proximal strategy optimization intelligent agent, thereby reasonably allocating power among multiple energy sources in the fuel cell hybrid heavy-duty truck and reducing the performance degradation rate of the fuel cell and the power battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a flow chart of the energy management method for a multi-stack fuel cell hybrid heavy truck provided in an embodiment of the present application;

[0049] Figure 2 Schematic diagram of energy management based on PPO agent provided in an embodiment of the present application;

[0050] Figure 3 This is a schematic structural diagram of a multi-stack fuel cell hybrid heavy truck energy analysis device provided in an embodiment of the present application;

[0051] Figure 4 Schematic diagram of the hardware structure of the computer device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are merely examples of devices and methods consistent with some aspects of the embodiments of the present application.

[0053] It will be understood that the terms "first", "second", etc. used in this application may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0054] The terms "at least one", "plurality", "each", "any", etc. used in this application include "at least one", "two" or more, "plurality" or "each", "any" or "any one", "each" or "any one" as used herein.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0056] Before describing the embodiments of the present application in detail, some of the nouns and terms involved in the embodiments of the present application are first explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations:

[0057] A heavy truck refers to a truck or semi-trailer tractor with a total mass greater than or equal to 14 tons, which is mainly used in heavy logistics scenarios such as cargo transportation and engineering operations.

[0058] Fuel cells convert chemical energy directly into electrical energy through electrochemical reactions between hydrogen and oxygen in the presence of catalysts. They rely on external fuel supplies (such as hydrogen and natural gas) and require a supporting fuel storage system.

[0059] Power batteries store and release electrical energy through electrochemical reactions between electrodes of lithium ions, nickel-metal hydride and other chemicals. They store chemical energy internally, do not require external fuel replenishment, and can be used through charging cycles.

[0060] Among current learning-based energy management strategies, deep reinforcement learning algorithms can significantly improve vehicle fuel economy compared to traditional rule-based and optimization-based strategies. Proximal Policy Optimization (PPO) strategies offer the advantages of robustness and stability. However, existing PPO-based energy management strategies fail to properly allocate power among multiple energy sources in fuel cell hybrid heavy-duty trucks, resulting in rapid performance degradation of both the fuel cell and power battery.

[0061] In view of this, an embodiment of the present application provides a multi-stack fuel cell hybrid heavy-duty truck energy management method, device and medium, which can reasonably distribute power among multiple energy sources in the fuel cell hybrid heavy-duty truck and reduce the performance degradation rate of the fuel cell and power battery.

[0062] The energy management method for a multi-stack fuel cell hybrid heavy truck provided in the embodiment of the present application relates to the field of automobile energy management technology. The energy management method for a multi-stack fuel cell hybrid heavy truck provided in the embodiment of the present application can be applied to a terminal, can be applied to a server, or can be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a vehicle-mounted terminal, etc., but is not limited thereto; the server side can be configured as an independent physical server, or as a server cluster or distributed system consisting of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements the energy management method for a multi-stack fuel cell hybrid heavy truck, etc., but is not limited to the above forms.

[0063] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0064] The following is a detailed description of the embodiments of the present application with reference to the accompanying drawings:

[0065] Figure 1 This is an optional flow chart of the energy management method for a multi-stack fuel cell hybrid heavy truck provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S110 to S150:

[0066] Step S110: obtaining the required vehicle power of the multi-stack fuel cell hybrid heavy-duty truck, wherein the multi-stack fuel cell hybrid heavy-duty truck is provided with multiple stacks of fuel cells and power batteries;

[0067] Step S120: constructing a first performance degradation model for the multi-stack fuel cells and a second performance degradation model for the power batteries;

[0068] Step S130: predicting a first health state of the plurality of fuel cell stacks and a second health state of the power battery using a pre-trained preset neural network model;

[0069] Step S140: obtaining the remaining power status of the power batteries in the multi-stack fuel cell hybrid heavy truck;

[0070] Step S150: Based on the vehicle's required power, the first health state, the second health state, the remaining power state, the first performance degradation model, and the second performance degradation model, the proximal strategy optimization agent is used to perform energy management on the multi-stack fuel cell hybrid heavy truck.

[0071] It is understandable that in this embodiment, the vehicle power requirement of the multi-stack fuel cell hybrid heavy truck can be obtained through the vehicle dynamics model, wherein the vehicle dynamics model is as follows:

[0072]

[0073] In the formula, P dem is the required power of the vehicle, V is the vehicle speed, f is the rolling resistance coefficient, C D is the air resistance coefficient, A is the frontal area of the vehicle, a is the vehicle acceleration, α is the road slope, m is the vehicle mass, g is the acceleration of gravity, η t and δ are weight coefficients respectively.

[0074] It is understandable that the first performance degradation model of the multi-stack fuel cell in this embodiment can be characterized by the voltage attenuation of the multi-stack fuel cell, and the second performance degradation model of the power battery can be characterized by the capacity attenuation of the power battery. The multi-stack fuel cell in this embodiment includes two fuel cells in parallel, two unidirectional DC / DC converters cascaded with the fuel cells, and the output ends of the multi-stack fuel cells are connected to the load port. Specifically, this embodiment can obtain the voltage attenuation of each fuel cell stack and construct the first performance degradation model shown in the following formula according to the voltage attenuation corresponding to all fuel cell stacks:

[0075] V mfcsd =V fcsd1 +V gcsd2 ;

[0076] In the formula, V mfcsdis the voltage attenuation of multiple fuel cell stacks, V fcsd1 is the voltage attenuation of the first fuel cell stack, V fcsd2 is the voltage attenuation of the second fuel cell stack.

[0077] The voltage attenuation of a single fuel cell stack is as follows:

[0078] V fcsd =V s +V i +V f +V h ;

[0079] In the formula, V fcsd is the voltage attenuation of a single fuel cell stack, V s is the fuel cell stack voltage attenuation under start-stop conditions, V i is the fuel cell stack voltage attenuation at idle speed, V f V is the voltage attenuation of the fuel cell stack under frequent load changes. h It is the voltage attenuation of the fuel cell stack under heavy load.

[0080] The calculation formula of the second performance degradation model corresponding to the power battery is as follows:

[0081]

[0082] In the formula, Q loss is the capacity attenuation of the power battery, α and β are the fitting coefficients of the remaining power state of the power battery, θ is the Celsius temperature, I c is the charge and discharge rate, Ah is the cumulative charge, and z is the power exponential factor.

[0083] It is understood that the preset neural network model of this embodiment is used to predict the future performance degradation data of the fuel cells and power batteries in a multi-stack fuel cell hybrid heavy-duty truck. Specifically, this embodiment first trains the preset neural network model, and the training process includes but is not limited to the following steps:

[0084] Acquire first historical performance degradation data of the plurality of fuel cell stacks and second historical performance degradation data of the power batteries;

[0085] Preprocessing the first historical performance degradation data to obtain third historical performance degradation data; and preprocessing the second historical performance degradation data to obtain fourth historical performance degradation data;

[0086] Performing feature extraction on the third historical performance degradation data to obtain first feature data;

[0087] performing feature extraction on the fourth historical performance degradation data to obtain second feature data;

[0088] The third historical performance degradation data and the first characteristic data are input into the neural network model to be trained so that the neural network model to be trained learns the performance degradation law information of the multiple fuel cell stacks; and the fourth historical performance degradation data and the second characteristic data are input into the neural network model to be trained so that the neural network model to be trained learns the performance degradation law information of the power battery.

[0089] Specifically, the first historical performance degradation data and the second historical performance degradation data of this embodiment may be performance degradation data of certain time periods before the current time point. Among them, the first historical performance degradation data and the corresponding data in the first performance degradation model may have partially overlapping data, but the two are in different forms. The second historical performance degradation data and the corresponding data in the second performance degradation model may have partially overlapping data, but the two are in different forms. The preprocessing process of this embodiment may be to perform denoising and normalization operations on the acquired historical performance degradation data. After completing the training of the preset neural network model, this embodiment uses the trained neural network model to analyze the first health state SOH of multiple fuel cells at the next moment. mfcs And the second health state SOH of the power battery at the next moment bat Since it is difficult to directly measure the SOH value in practical applications, this embodiment uses a neural network to predict the battery health status, which allows PPO to allocate power to energy sources based on more accurate and stable status data, thereby improving economy and the service life of the energy source.

[0090] It can be understood that after obtaining the vehicle's required power, the first health state, the second health state, the remaining power state, the first performance degradation model, and the second performance degradation model, this embodiment uses a proximal policy optimization agent to perform energy management on a multi-stack fuel cell hybrid heavy truck. Specifically, this embodiment first constructs a proximal policy optimization (PPO) agent. The PPO agent includes an Actor neural network and a Critic neural network. Then, after setting the state, action, and reward function of the PPO agent, the set PPO agent is obtained. Figure 2 As shown, this embodiment can be based on the vehicle power requirement P dem , First State of Health SOH mfcs , Second State of Health SOH bat , the remaining power state SOC constitutes the state quantity of the proximal strategy optimization agent. Among them, the set of state quantities is S t ={P dem,t ,SOC t ,SOH mfcs,t ,SOHbat,t}. With the target power P of multiple fuel cell stacks mfcs As the action variable of the PPO agent, the voltage attenuation of the multi-stack fuel cell corresponding to the first performance degradation model V mfcsd , the power battery capacity attenuation Q corresponding to the second performance degradation model loss 、Hydrogen consumption of multiple fuel cell stacks m mfcs The reward r of the proximal policy optimization agent is calculated by the quadratic term corresponding to the remaining power state SOC of the power battery. The reward function r is as follows:

[0091] r=αm mfcs +β(SOC t -SOC init ) 2 +δV mfcsd +εQ loss ;

[0092] In the formula, α, β, δ, and ε are weight coefficients, SOC t is the SOC value of the power battery at time t, SOC init is the initial SOC value of the power battery.

[0093] Specifically, before determining the state, action, and reward function of the PPO agent, this embodiment obtains a relevant training data set, and trains the PPO agent model based on the obtained relevant training data set to obtain a trained PPO agent model, specifically including the following steps:

[0094] Step A: Initialize the set PPO agent model parameters to obtain the initialized PPO agent;

[0095] Step B: Apply the initialized PPO agent to the multi-stack fuel cell hybrid heavy truck model and interact with it in the driving cycle;

[0096] Step C: Continuously update the Actor and Critic network parameters according to the gradient update method until the training requirements of the optimal energy management strategy are met. After convergence, the agent with the latest network parameters is the final trained PPO agent.

[0097] After completing the training of the PPO agent, the embodiment Figure 2 As shown in the figure, after inputting the current state and reward into the PPO agent, the trained PPO agent is used to manage the energy of the multi-stack fuel cell hybrid heavy truck, that is, the PPO agent is used to output the latest target power P corresponding to the multi-stack fuel cell. mfcsIf the multi-stack fuel cell is composed of two single-stack fuel cells, the power allocated to the multi-stack fuel cell is divided equally by the two single-stack fuel cells, that is, the latest target power of each single-stack fuel cell is 1 / 2P mfcs , so that the energy of the multi-stack fuel cell system and the power battery can be redistributed based on the latest target power. Specifically, when the target output power of the multi-stack fuel cell system is determined to be P mfcs , then the target output power of the power battery is the current required power of the vehicle - the target output power P of the multi-stack fuel cell mfcs , so that the output power of the power battery and fuel cell can be effectively managed based on the latest power allocation, reducing the performance degradation rate of the fuel cell and power battery.

[0098] As can be seen from the above, this embodiment can achieve reasonable power distribution among the multiple energy sources of a multi-stack fuel cell hybrid heavy-duty truck. Furthermore, this embodiment can predict the health status of the energy sources before power distribution, taking into account their performance degradation, thereby extending the service life of each energy source and thus improving the economy and durability of the multi-stack fuel cell hybrid heavy-duty truck.

[0099] Reference Figure 3 The embodiment of the present application provides an energy management device for a multi-stack fuel cell hybrid heavy truck, the device comprising:

[0100] The first module 310 is used to obtain the required vehicle power of a multi-stack fuel cell hybrid heavy-duty truck, wherein the multi-stack fuel cell hybrid heavy-duty truck is provided with multiple stacks of fuel cells and power batteries;

[0101] The second module 320 is used to construct a first performance degradation model of the multi-stack fuel cells and a second performance degradation model of the power battery;

[0102] The third module 330 is configured to predict a first health state of the plurality of fuel cell stacks and a second health state of the power battery using a pre-trained preset neural network model;

[0103] The fourth module 340 is used to obtain the remaining power state of the power batteries in the multi-stack fuel cell hybrid heavy truck;

[0104] The fifth module 350 is used to optimize the intelligent agent through the proximal strategy to perform energy management on a multi-stack fuel cell hybrid heavy truck based on the vehicle's required power, the first health state, the second health state, the remaining power state, the first performance degradation model, and the second performance degradation model.

[0105] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0106] The present application also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the above method when executing the computer program. The computer device can be any intelligent terminal including a tablet computer, an in-vehicle computer, or the like.

[0107] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0108] See also Figure 4 , Figure 4 The hardware structure of a computer device according to another embodiment is shown. The computer device includes:

[0109] The processor 410 may be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0110] The memory 420 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 420 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 420 and is called by the processor 410 to execute the above-mentioned methods of the embodiments of this application.

[0111] Input / output interface 430, used to implement information input and output;

[0112] Communication interface 440, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0113] bus 450 , which transmits information between various components of the device (e.g., processor 410 , memory 420 , input / output interface 430 , and communication interface 440 );

[0114] The processor 410 , the memory 420 , the input / output interface 430 and the communication interface 440 are connected to each other in communication within the device via the bus 450 .

[0115] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and the computer program implements the above method when executed by a processor.

[0116] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiment, the functions specifically implemented by the present storage medium embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0117] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0118] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0119] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0120] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0121] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0122] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0123] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0124] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0125] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0126] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0127] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store programs.

[0128] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A multi-stack fuel cell hybrid heavy truck energy management method, characterized in that: The method comprises the following steps: Obtaining a required vehicle power of the multi-stack fuel cell hybrid heavy-duty truck, wherein the multi-stack fuel cell hybrid heavy-duty truck is provided with multiple stacks of fuel cells and power batteries; Constructing a first performance degradation model for multiple fuel cell stacks and a second performance degradation model for power batteries; Predicting a first health state of the plurality of fuel cell stacks and a second health state of the power battery using a pre-trained preset neural network model; Obtaining the remaining power state of the power batteries in the multi-stack fuel cell hybrid heavy truck; According to the required power of the entire vehicle, the first health state, the second health state, the remaining power state, the first performance degradation model and the second performance degradation model, energy management of the multi-stack fuel cell hybrid heavy truck is performed through a proximal strategy optimization intelligent agent.

2. The method according to claim 1, characterized in that The obtaining of the vehicle required power of the multi-stack fuel cell hybrid heavy truck includes: The vehicle dynamics model is used to obtain the required vehicle power of a multi-stack fuel cell hybrid heavy truck, wherein the vehicle dynamics model is as follows: In the formula, P dem is the required power of the vehicle, V is the vehicle speed, f is the rolling resistance coefficient, C D is the air resistance coefficient, A is the frontal area of the vehicle, a is the vehicle acceleration, α is the road slope, and m is the vehicle mass.

3. The method according to claim 1, characterized in that The constructing of a first performance degradation model of a multi-stack fuel cell comprises: Obtaining a voltage attenuation of each fuel cell stack; The first performance degradation model is constructed according to all the voltage attenuation amounts.

4. The method according to claim 3, characterized in that The calculation formula of the voltage attenuation is as follows: V fcsd =V s +V i +V f +V h ; In the formula, V fcsd is the voltage attenuation of a single fuel cell stack, V s is the fuel cell stack voltage attenuation under start-stop conditions, V i is the fuel cell stack voltage attenuation at idle speed, V f V is the voltage attenuation of the fuel cell stack under frequent load changes. h It is the voltage attenuation of the fuel cell stack under heavy load.

5. The method according to claim 1, wherein The calculation formula of the second performance degradation model is as follows: In the formula, Q loss is the capacity attenuation of the power battery, α and β are the fitting coefficients of the remaining power state of the power battery, θ is the Celsius temperature, I c is the charge and discharge rate, Ah is the cumulative charge, and z is the power exponential factor.

6. The method according to claim 1, characterized in that The training process of the pre-trained preset neural network model includes the following steps: Acquiring first historical performance degradation data of the plurality of fuel cell stacks and second historical performance degradation data of the power battery; Preprocessing the first historical performance degradation data to obtain third historical performance degradation data; and preprocessing the second historical performance degradation data to obtain fourth historical performance degradation data; performing feature extraction on the third historical performance degradation data to obtain first feature data; performing feature extraction on the fourth historical performance degradation data to obtain second feature data; The third historical performance degradation data and the first characteristic data are input into the neural network model to be trained so that the neural network model to be trained learns the performance degradation law information of the multiple fuel cell stacks; and the fourth historical performance degradation data and the second characteristic data are input into the neural network model to be trained so that the neural network model to be trained learns the performance degradation law information of the power battery.

7. The method according to claim 1, characterized in that The method of performing energy management on the multi-stack fuel cell hybrid heavy truck by using a proximal strategy optimization agent based on the vehicle's required power, the first health state, the second health state, the remaining power state, the first performance degradation model, and the second performance degradation model includes: The state quantity of the proximal strategy optimization agent is formed according to the vehicle required power, the first health state, the second health state, and the remaining power state; Calculating a reward for the proximal strategy optimization agent based on the first performance degradation model, the second performance degradation model, the hydrogen consumption of the multiple fuel cell stacks, and a quadratic term corresponding to an offset of the remaining power state of the power battery; Using the target power of the multiple fuel cell stacks as an action variable of the proximal strategy optimization agent; Adjust the action variable according to the state quantity and the reward to obtain the latest target power corresponding to the multiple fuel cell stacks; Energy management is performed on the multi-stack fuel cell hybrid heavy truck according to the latest target power.

8. An energy management device for a multi-stack fuel cell hybrid heavy truck, characterized in that: The device comprises: The first module is used to obtain the required vehicle power of the multi-stack fuel cell hybrid heavy-duty truck, wherein the multi-stack fuel cell hybrid heavy-duty truck is provided with multiple stacks of fuel cells and power batteries; The second module is used to construct a first performance degradation model of multiple fuel cell stacks and a second performance degradation model of power batteries; A third module is configured to predict a first health state of the plurality of fuel cell stacks and a second health state of the power battery using a pre-trained preset neural network model; A fourth module is used to obtain the remaining power status of the power battery in the multi-stack fuel cell hybrid heavy truck; The fifth module is used to perform energy management on the multi-stack fuel cell hybrid heavy truck through a proximal strategy optimization intelligent agent based on the vehicle's required power, the first health state, the second health state, the remaining power state, the first performance degradation model, and the second performance degradation model.

9. A computer device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images