Control method and device of power battery system, computer program product and vehicle

Abstract

The invention provides a control method and device of a power battery system, a computer program product and a vehicle, a fuel battery and a storage battery of the power battery system are both used for outputting electric energy to provide power, and the method comprises the following steps: respectively training corresponding fuzzy controllers in various aging states, the fuzzy controller controls the output power of the fuel cell and the storage battery to maximize the service life of the fuel cell and the storage battery, and the aging state is the state under the combination of different aging degrees of the fuel cell and the storage battery; determining the fuzzy controller corresponding to the aging state closest to the aging degree of the power battery system as a target fuzzy controller; and inputting the current system demand power of the power battery system and the current battery electric quantity of the storage battery into the target fuzzy controller to obtain the output power of the fuel battery and the output power of the storage battery so as to control the power distribution of the fuel battery and the storage battery, thereby solving the problem of poor durability of the power battery system in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of power battery control technology, and in particular to a control method, device, computer program product and vehicle for a power battery system. Background Art

[0002] Drive systems powered by hydrogen and using fuel cells to generate electricity are playing a significant role in the decarbonization of the transportation sector. Hydrogen-powered fuel cell vehicles are becoming an important direction for the sustainable development of the future automotive industry. In the transportation sector, led by road vehicles, hydrogen will expand electrification to high-load cycle applications, such as passenger cars, long-distance vehicles, special vehicles, trains and ships, etc. Through re-electrification, the chemical energy in hydrogen is converted into electrical energy, which has the advantages of good environmental performance, high conversion efficiency, short refueling time, and long driving range. Fuel cell vehicles usually use a hybrid electric drive system of "fuel cell / power battery + motor", with fuel cells and power batteries serving as the main and auxiliary power sources to provide power to the motor. Compared with other types of fuel cells, proton exchange membrane fuel cells have good application prospects in the transportation sector due to their high power density, fast start-up speed, and low operating temperature. Although the current fuel cell technology has achieved industrial breakthroughs, the system integration capability has been greatly enhanced. However, due to the strong coupling relationship between gas, water, electricity and other factors in the system and the frequently changing complex working conditions, automotive fuel cell systems usually present the characteristics of being distributed, dynamic, time-varying, multi-physical domains and multi-space-time scales, and have problems such as poor durability and high failure rate. Developing long-life fuel cell systems is one of the important challenges currently facing the field of fuel cell vehicles.

[0003] Fuel cell system control refers to the control strategy at the system supervisory level for power distribution of multi-power source hybrid power systems. It is linked with the low-level controller of the system. The low-level controller obtains the instructions of the energy management strategy, and then acts on the DC / DC converter, DC / AC inverter and motor to achieve the optimal operation of the system. The quality of the control method directly affects the reliability, mobility and economy of fuel cell vehicles. In the control of fuel cell systems, fuel economy is usually the primary goal, supplemented by other goals such as durability and safety, considering the physical parameter constraints of the system, and finally solving the optimal power distribution point between multiple power sources. The existing technology usually improves the durability of the fuel cell and reduces its efficiency decay by establishing a performance decay model of the fuel cell and using it as the rule of the control strategy or the optimization item of the objective function. The existing technology provides a hydrogen fuel cell vehicle energy management method considering thermal safety and durability. Through the reinforcement learning control method established by the deep neural network, the real-time energy optimization management and distribution of the hydrogen fuel cell hybrid electric vehicle are realized, thereby achieving balanced management, reducing the system fuel consumption, and extending the system life cycle and improving the system durability.

[0004] The prior art has the following technical disadvantages:

[0005] 1) Existing automotive fuel cell systems have low efficiency and limited durability optimization:

[0006] Existing automotive fuel cell control methods lack monitoring of the actual operating status of fuel cells. They simply combine the performance decay of fuel cells with control strategies through existing models, or add boundary conditions to the rule design to delay the decay of fuel cells, and focus on the design of real-time optimization algorithms for control methods. However, due to the lack of accurate judgment of fuel cell performance, it is difficult for control methods to achieve their optimality. In addition, the performance decay process of fuel cells is usually considered based on a time scale of hours, while control methods are considered on a smaller time scale. If the fuel cell state monitoring method is directly combined with the optimization-based control method, not only will the computational burden be greatly increased, but the uncertainty of the prediction algorithm will also greatly affect the effectiveness of the control method, making it difficult to achieve the purpose of improving system durability.

[0007] 2) Existing automotive fuel cell control strategies have poor adaptability:

[0008] Existing automotive fuel cell control strategies are not flexible enough, lack accurate state estimation and intelligent decision-making technology, and are difficult to adapt to changing operating conditions and environments, such as temperature changes, humidity changes, load fluctuations, etc. They are unable to effectively predict and prevent potential failures, affecting the performance and life of the fuel cell, thereby affecting the reliability of the fuel cell system and the durability of long-term operation. Summary of the invention

[0009] The main purpose of the present application is to provide a control method, device, computer program product and vehicle for a power battery system, so as to at least solve the problem of poor durability of the power battery system in the prior art.

[0010] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a control method for a power battery system is provided, wherein the fuel cell and the battery of the power battery system are both used to output electrical energy to provide power, and the method comprises: respectively training corresponding fuzzy controllers under multiple aging states, so that the fuzzy controller controls the output power of the fuel cell and the battery to maximize the life of the fuel cell and the battery, and the aging state is the state of the fuel cell and the battery under different aging degree combinations; the fuzzy controller corresponding to the aging state closest to the aging degree of the power battery system is determined as the target fuzzy controller; the current system required power of the power battery system and the current battery power of the battery are input into the target fuzzy controller to obtain the output power of the fuel cell and the output power of the battery, so as to control the power distribution of the fuel cell and the battery.

[0011] Optionally, the current system demand power of the power battery system and the current battery power of the storage battery are input into the target fuzzy controller to obtain the output power of the fuel cell and the output power of the storage battery, including: obtaining the current system demand power and the current battery power; dividing a plurality of first fuzzy sets according to the value range of the current system demand power, dividing a plurality of second fuzzy sets according to the value range of the current battery power, and dividing a plurality of third fuzzy sets according to the value range of the output power of the fuel cell; inputting the current system demand power into the system demand power membership function to obtain a plurality of first memberships, wherein the plurality of first memberships are respectively the memberships of the current system demand power to each of the first fuzzy sets, and inputting the current battery power into the battery power membership function to obtain to multiple second memberships, wherein the multiple second memberships are respectively the memberships of the current battery power to each of the second fuzzy sets, and the required power membership function and the battery power membership function are both trapezoidal membership functions; multiple third memberships are calculated according to fuzzy rules, multiple first memberships and the second memberships, wherein the multiple third memberships are respectively the memberships of the output power of the fuel cell to each of the third fuzzy sets, and the fuzzy rules are the mapping relationships among the first fuzzy sets, the second fuzzy sets and the third fuzzy sets; the output power of the fuel cell is calculated according to the multiple third memberships and the centroid of each of the third fuzzy sets using the centroid method; the difference between the current system required power and the output power of the fuel cell is calculated to obtain the output power of the battery.

[0012] Optionally, multiple third memberships are calculated according to fuzzy rules, multiple first memberships and the second memberships, including: a query step, querying the combination of the first fuzzy set and the second fuzzy set corresponding to any one of the third fuzzy sets according to the fuzzy rules; a first calculation step, calculating the membership components corresponding to each combination of the first fuzzy set and the second fuzzy set, the membership component being the product of the first membership corresponding to the combination of the first fuzzy set and the second fuzzy set and the corresponding second membership; a second calculation step, calculating the sum of the membership components corresponding to all combinations of the first fuzzy set and the second fuzzy set to obtain the third membership corresponding to the third fuzzy set; and repeating the query step, the first calculation step and the second calculation step at least once in sequence until the third memberships corresponding to all the third fuzzy sets are obtained.

[0013] Optionally, use Calculate the output power P of the fuel cell fc * , where P fci is the centroid of the third fuzzy set of the ith Ai (P fc ) is the third membership degree corresponding to the i-th third fuzzy set, and n is the number of the third fuzzy sets.

[0014] Optionally, the corresponding fuzzy controllers are trained respectively under multiple aging states so that the fuzzy controllers control the output powers of the fuel cell and the battery to maximize the lifespan of the fuel cell and the battery, including: an establishment step of establishing an initial fuzzy controller corresponding to a target aging state, wherein the target aging state is any one of the aging states; an input step of inputting the current system demand power and the current battery power into the initial fuzzy controller to obtain a first output power of the fuel cell and a second output power of the battery; an acquisition step of acquiring a current output voltage of the fuel cell and a current battery capacity of the battery while controlling the fuel cell to operate at the first output power and the battery to operate at the second output power for a predetermined period of time; an estimation step of estimating the lifespan of the fuel cell using a state estimation algorithm and the current output voltage, and using the state estimation algorithm to estimate the lifespan of the fuel cell. The state estimation algorithm and the current battery capacity estimate the life of the battery; an adjustment step, adjusting the parameters of the initial fuzzy controller, the current system required power and the current battery capacity, until any one of the current system required power and any one of the current battery capacity is input into the initial fuzzy controller, and the first life difference and the second life difference are both less than a predetermined threshold, and determining that the initial fuzzy controller is the fuzzy controller corresponding to the target aging state, the first life difference is the life difference of the fuel cell before and after the initial fuzzy controller performs fuzzy control, and the second life difference is the life difference of the fuel cell before and after the initial fuzzy controller performs fuzzy control; repeating the establishment step, the input step, the acquisition step, the estimation step and the adjustment step at least once in sequence, until the fuzzy controllers corresponding to all the aging states are obtained.

[0015] Optionally, a state estimation algorithm and the current output voltage are used to estimate the life of the fuel cell, and the state estimation algorithm and the current battery capacity are used to estimate the life of the storage battery, including: a first estimation step, calculating the output voltage at the next moment by the state estimation algorithm according to the current output voltage; a second estimation step, calculating the battery capacity at the next moment by the state estimation algorithm according to the current battery capacity; repeating the first estimation step until the output voltage at the next moment is equal to the end-of-life voltage, and calculating the life of the fuel cell according to the next moment and the current moment, repeating the second estimation step until the battery capacity at the next moment is equal to the end-of-life capacity, and calculating the life of the storage battery according to the next moment and the current moment.

[0016] Optionally, the fuzzy controller corresponding to the aging state that is closest to the aging degree of the power battery system is determined as the target fuzzy controller, including: setting the credibility of each of the fuzzy controllers under multiple reference aging degrees of the fuel cell; determining the fuzzy controller with the largest credibility as the optimal fuzzy controller corresponding to each reference aging degree; when the aging degree of the fuel cell is between two reference aging degrees, using DS theory to combine the credibility of the optimal fuzzy controllers corresponding to the two reference aging degrees to obtain the normalized credibility of the two optimal fuzzy controllers, so that the sum of the two normalized credibility is 1; performing weighted averaging of the corresponding two optimal fuzzy controllers according to the two normalized credibility to obtain the target fuzzy controller, so that the output of the target fuzzy controller is the weighted average of the outputs of the two optimal fuzzy controllers.

[0017] According to another aspect of the present application, a control device for a power battery system is provided, in which the fuel cell and the battery of the power battery system are both used to output electrical energy to provide power, and the device includes: a training unit, used to train the corresponding fuzzy controllers under multiple aging states respectively, so that the fuzzy controllers control the output power of the fuel cell and the battery to maximize the life of the fuel cell and the battery, and the aging state is the state of the fuel cell and the battery under different aging degree combinations; a determination unit, used to determine the fuzzy controller corresponding to the aging state that is closest to the aging degree of the power battery system as a target fuzzy controller; an input unit, used to input the current system required power of the power battery system and the current battery power of the battery into the target fuzzy controller to obtain the output power of the fuel cell and the output power of the battery, so as to control the power distribution of the fuel cell and the battery.

[0018] According to another aspect of the present application, a computer program product is provided, comprising a computer program / instruction, wherein the computer program / instruction implements any one of the methods described above when executed by a processor.

[0019] According to another aspect of the present application, a vehicle is provided, comprising: a power battery system, one or more processors, a memory, and one or more programs, wherein the fuel cell and the battery of the power battery system are both used to output electrical energy to provide power, the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the methods described.

[0020] By applying the technical solution of the present application, in the control method of the above-mentioned power battery system, it is considered that the power control strategies of the fuel cell and the battery in the aging state have different effects on the life of the fuel cell and the battery. Therefore, the corresponding fuzzy controllers are trained respectively under various aging states, and the control strategy is optimized in real time by a suitable fuzzy controller to maximize the life of the fuel cell and the battery, thereby solving the problem of poor durability of the power battery system in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A hardware structure block diagram of a mobile terminal for executing a control method for a power battery system provided in an embodiment of the present application is shown;

[0022] Figure 2 A schematic flow chart of a control method for a power battery system provided according to an embodiment of the present application is shown;

[0023] Figure 3 A curve diagram of a required power membership function and a battery power membership function provided according to an embodiment of the present application is shown;

[0024] Figure 4 A schematic diagram showing a result of real-time optimization control of power distribution of a fuel cell-lithium battery power system provided according to an embodiment of the present application is shown;

[0025] Figure 5 A schematic diagram showing the aging degree of a fuel cell and a lithium battery provided according to an embodiment of the present application is shown;

[0026] Figure 6 A schematic diagram showing a life prediction result of a fuel cell provided according to an embodiment of the present application is shown;

[0027] Figure 7 A schematic diagram showing a life prediction result of a lithium battery provided according to an embodiment of the present application;

[0028] Figure 8 A schematic diagram showing a fuzzy controller fusion result provided according to an embodiment of the present application is shown;

[0029] Fig. 9 A structural block diagram of a control device for a power battery system provided according to an embodiment of the present application is shown.

[0030] The above drawings include the following reference numerals:

[0031] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0032] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0033] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims 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 sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising 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.

[0035] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0036] DS theory (Dempster-Shafer envidence theory): a complete theory for dealing with uncertainty problems.

[0037] As introduced in the background technology, the durability of the power battery system in the prior art is poor. To solve this technical problem, the embodiments of the present application provide a control method, device, computer program product and vehicle for a power battery system.

[0038] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0039] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a control method for a power battery system according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0040] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the display method of device information in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal 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 a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0041] In this embodiment, a control method for a power battery system running on a mobile terminal, a computer terminal or a similar computing device is provided. The fuel cell and the storage battery of the power battery system are both used to output electrical energy to provide power. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0042] Figure 2 : is a flow chart of a control method of a power battery system according to an embodiment of the present application. Figure 2As shown, the method comprises the following steps:

[0043] Step S201, respectively training corresponding fuzzy controllers under various aging conditions, so that the fuzzy controllers control the output power of the fuel cell and the battery to maximize the life of the fuel cell and the battery, wherein the aging conditions are conditions under different combinations of aging degrees of the fuel cell and the battery;

[0044] Specifically, since the power distribution of fuel cells and batteries has different effects on battery life under different aging conditions, the corresponding fuzzy controllers are trained under multiple aging conditions respectively, so as to maximize the life of fuel cells and batteries by controlling the power distribution of fuel cells and batteries through intelligent decision-making of fuzzy controllers.

[0045] Step S202, determining the fuzzy controller corresponding to the aging state that is closest to the aging degree of the power battery system as the target fuzzy controller;

[0046] Specifically, a suitable fuzzy controller is selected according to the aging degree of the power battery system, and the fuzzy controller corresponding to the aging state with the closest aging degree can be determined as the target fuzzy controller.

[0047] Step S203, inputting the current system demand power of the power battery system and the current battery power of the storage battery into the target fuzzy controller to obtain the output power of the fuel cell and the output power of the storage battery to control the power distribution of the fuel cell and the storage battery.

[0048] Specifically, the target fuzzy controller determines the output power of the fuel cell and the battery according to the current system power demand of the power battery system and the current battery power of the battery, and controls the power distribution of the fuel cell and the battery, so as to maximize the life of the fuel cell and the battery while meeting the current system power demand.

[0049] In the control method of the above-mentioned power battery system, it is considered that the power control strategies of the fuel cell and the battery under the aging state have different effects on the life of the fuel cell and the battery. Therefore, the corresponding fuzzy controllers are trained respectively under various aging states, and the control strategy is optimized in real time through a suitable fuzzy controller to maximize the life of the fuel cell and the battery, thereby solving the problem of poor durability of the power battery system in the prior art.

[0050] In order to meet the power requirement, in an optional implementation, the above step S203 includes:

[0051] Step S2031, obtaining the current system required power and the current battery power;

[0052] Step S2032, dividing a plurality of first fuzzy sets according to the value range of the current system required power, dividing a plurality of second fuzzy sets according to the value range of the current battery power, and dividing a plurality of third fuzzy sets according to the value range of the output power of the fuel cell;

[0053] Step S2033, inputting the current system demand power into the system demand power membership function to obtain a plurality of first memberships, wherein the plurality of first memberships are respectively the memberships of the current system demand power to the first fuzzy sets, inputting the current battery power into the battery power membership function to obtain a plurality of second memberships, wherein the plurality of second memberships are respectively the memberships of the current battery power to the second fuzzy sets, wherein both the demand power membership function and the battery power membership function are trapezoidal membership functions;

[0054] Step S2034, calculating a plurality of third memberships according to the fuzzy rule, the plurality of first memberships and the second membership, wherein the plurality of third memberships are memberships of the output power of the fuel cell to each of the third fuzzy sets, and the fuzzy rule is a mapping relationship between the first fuzzy set, the second fuzzy set and the third fuzzy set;

[0055] Step S2035, calculating the output power of the fuel cell by using a centroid method according to the plurality of third membership degrees and the centroids of the third fuzzy sets;

[0056] Step S2036, calculating the difference between the current system required power and the output power of the fuel cell to obtain the output power of the battery.

[0057] In the above implementation, a fuzzy controller is used to implement real-time optimization control of a short-time scale system. First, the fuzzy sets and membership functions of the input and output variables are defined. The input variable is the system demand power P demand and battery charge SOC, which can be divided into several first fuzzy sets and several second fuzzy sets, namely "very low", "low", "medium", "high" and "very high". The output variable is the output power P of the fuel cell fc , the third fuzzy set is divided into “very low”, “low”, “medium”, “high” and “very high”. For SOC, a trapezoidal membership function is used with the following parameters: “very low”: SOC = [0, 0, 10, 20]%, “low”: SOC = [10, 20, 30, 40]%, “medium”: SOC = [30, 40, 60, 70]%, “high”: SOC = [60, 70, 80, 90]%, “very high”: SOC = [80, 90, 100, 100]%, for P demand and Pfc , after normalization, a similar method is used to define the membership function: "very low": P demand =[0,0,10,20]%, "low": P demand =[10,20,30,40]%, "medium": P demand =[30,40,60,70]%, "high": P demand =[60,70,80,90]%, "very high": P demand =[80,90,100,100]%, "very low": P fc =[0,0,10,20]%, "low": P fc =[10,20,30,40]%, "medium": P fc =[30,40,60,70]%, "high": P fc =[60,70,80,90]%, "very high": P fc =[80,90,100,100]%, the curve diagram of the above demand power membership function and the above battery power membership function is as shown in Figure 3 As shown in the figure, a series of fuzzy rules are formulated to calculate different SOC and P demand Next P fc The output value of the fuel cell can be calculated by the centroid method according to the above third membership degrees and the centroids of the above third fuzzy sets; the difference between the current system demand power and the output power of the fuel cell is calculated to obtain the output power of the battery. The real-time optimization control result of the power distribution of the fuel cell-lithium battery power system on a certain driving cycle implemented by the fuzzy controller is as follows: Figure 4 As shown. The system power requirement P is calculated by the fuzzy controller. demand It can be seen from the allocation results that the fuzzy controller can effectively control the output power of the fuel cell, maintain it at a relatively stable level, and effectively maintain the life of the fuel cell. The power of the lithium battery changes with the demand power, and the response performance is good.

[0058] In order to calculate the third membership degree corresponding to each third fuzzy set, in an optional implementation, the above step S2034 includes:

[0059] Step S20341, a query step, querying a combination of the first fuzzy set and the second fuzzy set corresponding to any one of the third fuzzy sets according to the fuzzy rule;

[0060] Step S20342, a first calculation step, calculating the membership component corresponding to each combination of the first fuzzy set and the second fuzzy set, wherein the membership component is the product of the first membership corresponding to the combination of the first fuzzy set and the second fuzzy set and the corresponding second membership;

[0061] Step S20343, a second calculation step, calculating the sum of the membership components corresponding to all combinations of the first fuzzy set and the second fuzzy set to obtain the third membership corresponding to the third fuzzy set;

[0062] Step S20344, repeating the query step, the first calculation step and the second calculation step in sequence at least once, until the third membership degrees corresponding to all the third fuzzy sets are obtained.

[0063] In the above implementation, the fuzzy rules are shown in Table 1. Taking the combination of the above first fuzzy set and the above second fuzzy set, taking the third fuzzy set "very low" as an example, the corresponding combination of the above first fuzzy set and the above second fuzzy set includes the combination of the first fuzzy set "very low" and the second fuzzy set "very low" and the combination of the first fuzzy set "very low" and the second fuzzy set "low", and the system required power P is calculated. demand The product of the first membership of the first fuzzy set "very low" and the second membership of the battery power SOC to the second fuzzy set "very low" is used to obtain a membership component corresponding to the combination, and the system demand power P is calculated. demand The product of the first membership of the first fuzzy set "very low" and the second membership of the battery power SOC to the second fuzzy set "low" obtains another membership component corresponding to the combination. The sum of the two membership components is the output power P of the fuel cell. fc The third membership of “very low” to the third fuzzy set.

[0064] Table 1

[0065]

[0066] In order to obtain a clear output power of the fuel cell, in an optional implementation, the above step S2035 includes:

[0067] Step S20351, using Calculate the output power P of the above fuel cell fc * , where P fci is the centroid of the i-th third fuzzy set, μ Ai (P fc ) is the third membership degree corresponding to the i-th third fuzzy set, and n is the number of the third fuzzy sets.

[0068] In the above implementation, in the actual operation process, the maximum value of the membership function of all activated rules is output as the aggregation result, and the fuzzy output set is converted into a clear output value by defuzzification. The present invention adopts the centroid method: Among them, P fci is the centroid of the i-th third fuzzy set, μ Ai (P fc ) is the third membership degree corresponding to the i-th third fuzzy set, and n is the number of the third fuzzy sets. Based on this, the fuzzy controller can adjust the output power P of the fuel cell under different operating conditions. fc to meet system requirements.

[0069] In order to maximize the battery life, in an optional implementation, the above step S201 includes:

[0070] Step S2011, an establishment step, establishing an initial fuzzy controller corresponding to a target aging state, wherein the target aging state is any one of the above aging states;

[0071] Step S2012, an input step, inputting the current system required power and the current battery power into the initial fuzzy controller to obtain the first output power of the fuel cell and the second output power of the battery;

[0072] Step S2013, an acquisition step, in which the current output voltage of the fuel cell and the current battery capacity of the battery are acquired while controlling the fuel cell to operate at the first output power and the battery to operate at the second output power for a predetermined period of time;

[0073] Step S2014, an estimation step, using a state estimation algorithm and the current output voltage to estimate the life of the fuel cell, and using the state estimation algorithm and the current battery capacity to estimate the life of the storage battery;

[0074] Step S2015, an adjustment step, adjusting the parameters of the initial fuzzy controller, the current system required power and the current battery power, until any one of the current system required power and any one of the current battery power is input into the initial fuzzy controller, and the first life difference and the second life difference are both less than a predetermined threshold, and determining that the initial fuzzy controller is the fuzzy controller corresponding to the target aging state, the first life difference is the life difference of the fuel cell before and after the initial fuzzy controller performs fuzzy control, and the second life difference is the life difference of the fuel cell before and after the initial fuzzy controller performs fuzzy control;

[0075] Step S2016, repeating the establishment step, the input step, the acquisition step, the estimation step and the adjustment step at least once in sequence until the fuzzy controllers corresponding to all the aging states are obtained.

[0076] In the above embodiment, it is assumed that the output voltage of the fuel cell drops to 90% of the initial value as the end-of-life value, and the capacity of the lithium battery drops to 70% of the initial value as the end-of-life value. Figure 5 As shown, five aging state combinations are defined: 1. The fuel cell is not aged and the lithium battery is not aged, 2. The fuel cell has low aging and the lithium battery has not aged, 3. The fuel cell has low aging and the lithium battery has low aging, 4. The fuel cell has high aging and the lithium battery has low aging, 5. The fuel cell has high aging and the lithium battery has high aging. According to the operation modes of the fuel cell system under the above five aging states, five fuzzy controllers are trained. According to the life prediction of multiple power sources, the power allocation results are optimized in real time, so that the control strategy of the trained fuzzy controller can maximize the life and energy efficiency of the overall system while meeting the power demand.

[0077] In order to accurately predict the battery life, in an optional implementation, the above step S2014 includes:

[0078] Step S20141, a first estimation step, calculating the output voltage at the next moment by a state estimation algorithm according to the above current output voltage;

[0079] Step S20142, a second estimation step, calculating the battery capacity at the next moment according to the current battery capacity by using the state estimation algorithm;

[0080] Step S20143, repeat the first estimation step until the output voltage at the next moment is equal to the end-of-life voltage, and calculate the life of the fuel cell based on the next moment and the current moment, repeat the second estimation step until the battery capacity at the next moment is equal to the end-of-life capacity, and calculate the life of the battery based on the next moment and the current moment.

[0081] In the above implementation, the observer-based state estimation method estimates and predicts the aging state of the fuel cell and battery (lithium battery) in the system online. First, a battery state model is constructed, where the fuel cell uses the output voltage as the state quantity and the lithium battery uses the battery capacity as the state quantity: Based on this model, the state equation and measurement equation are constructed in the state space: Among them, X is the state variable, that is, the output voltage of the fuel cell or the capacity of the lithium battery, and ω and θ represent Gaussian white noise. Then, the observer model is used to estimate and predict the variables in the state equation online, which includes three steps: state value prediction, gain calculation and state value update, as shown below: 1) State value prediction: 2) Gain calculation: 3) Status value update: is the estimated value of the state quantity in the kth period, and are the prior state estimate and the error covariance estimate, K k is the feedback gain, R and Q are the noise matrices, y k is the observed value of the state quantity, F is the state transfer matrix, and H is the conversion matrix from the state value to the observed value. Based on historical data, the life prediction results of fuel cells and lithium batteries calculated by the above method are obtained. The uncertainty of the prediction results is obtained by running the program multiple times. The prediction results of different prediction start times are plotted in the figure using a box plot. The life prediction results of fuel cells are shown in the figure. Figure 6 As shown in the figure, and the lithium battery life prediction results are as follows Figure 7 shown.

[0082] In order to select a suitable fuzzy controller, in an optional implementation, the above step S202 includes:

[0083] Step S2021, setting the credibility of each of the fuzzy controllers under multiple reference aging degrees of the fuel cell;

[0084] Step S2022, determining the fuzzy controller with the highest credibility as the optimal fuzzy controller corresponding to each of the reference aging degrees;

[0085] Step S2023, when the aging degree of the fuel cell is between the two reference aging degrees, the credibility of the two optimal fuzzy controllers corresponding to the two reference aging degrees is combined by using the DS theory to obtain the normalized credibility of the two optimal fuzzy controllers, so that the sum of the two normalized credibility is 1;

[0086] Step S2024, performing weighted averaging on the corresponding two optimal fuzzy controllers according to the two normalized credibility degrees to obtain the target fuzzy controller, so that the output of the target fuzzy controller is the weighted average of the outputs of the two optimal fuzzy controllers.

[0087] In the above implementation, for the fuel cell system operation mode under the above five aging conditions, five fuzzy controllers are defined, and control decisions are given according to their inputs and rule bases. The membership function parameter value of the fuel cell output power is represented by , that is, i values ​​are used to describe the membership function of the fuel cell output power, and a fuzzy reasoner based on a Gaussian function is constructed to calculate the basic probability value of the fuel cell aging value (obtained through observer prediction) corresponding to each fuzzy controller in actual situations, reflecting the decision credibility (confidence factor, CF) of each controller. The input of the fuzzy reasoner is three aging conditions (no aging, low aging, high aging), and the output is the credibility of the corresponding five fuzzy controllers. For example, for some random aging conditions during online operation, the credibility of the corresponding five fuzzy controllers is shown in Table 2. Combined with the DS data fusion theory, the credibility of different controllers is combined to form a new credibility function. This method is accomplished by weighted averaging all possible intersections. For example, the following formula represents the calculation method for merging the credibility of the two fuzzy controllers B and C into A: Where K is the normalization constant. Normalization: Normalize the combined results to ensure that the sum of all credibility is 1. The DS theory is used to intelligently fuse the outputs of multiple fuzzy controllers to improve the robustness and accuracy of the overall control system. It is used to deal with the situation where the power distribution optimal points provided by multiple fuzzy controllers under different aging conditions are inconsistent. The results of using an intelligent decision-making method to fuse two fuzzy controllers under a certain aging state of the fuel cell system are as follows: Figure 8 shown.

[0088] Table 2

[0089]

[0090]

[0091] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0092] The embodiment of the present application also provides a control device for a power battery system. It should be noted that the control device for a power battery system in the embodiment of the present application can be used to execute the control method for a power battery system provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred embodiments, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0093] The control device of the power battery system provided in the embodiment of the present application is introduced below. The fuel cell and the storage battery of the power battery system are both used to output electrical energy to provide power.

[0094] Fig. 9 is a structural block diagram of a control device for a power battery system according to an embodiment of the present application. Fig. 9 As shown, the device comprises:

[0095] The training unit 10 is used to train the corresponding fuzzy controllers respectively under various aging conditions, so that the fuzzy controllers control the output power of the fuel cell and the battery to maximize the life of the fuel cell and the battery, wherein the aging conditions are conditions under different aging degree combinations of the fuel cell and the battery;

[0096] Specifically, since the power distribution of fuel cells and batteries has different effects on battery life under different aging conditions, the corresponding fuzzy controllers are trained under multiple aging conditions respectively, so as to maximize the life of fuel cells and batteries by controlling the power distribution of fuel cells and batteries through intelligent decision-making of fuzzy controllers.

[0097] A determination unit 20, configured to determine the fuzzy controller corresponding to the aging state that is closest to the aging degree of the power battery system as a target fuzzy controller;

[0098] Specifically, a suitable fuzzy controller is selected according to the aging degree of the power battery system, and the fuzzy controller corresponding to the aging state with the closest aging degree can be determined as the target fuzzy controller.

[0099] The input unit 30 is used to input the current system demand power of the above-mentioned power battery system and the current battery power of the above-mentioned storage battery into the above-mentioned target fuzzy controller to obtain the output power of the above-mentioned fuel cell and the output power of the above-mentioned storage battery to control the power distribution of the above-mentioned fuel cell and the above-mentioned storage battery.

[0100] Specifically, the target fuzzy controller determines the output power of the fuel cell and the battery according to the current system power demand of the power battery system and the current battery power of the battery, and controls the power distribution of the fuel cell and the battery, so as to maximize the life of the fuel cell and the battery while meeting the current system power demand.

[0101] In the control device of the above-mentioned power battery system, it is considered that the power control strategies of the fuel cell and the battery in the aging state have different effects on the life of the fuel cell and the battery. Therefore, the corresponding fuzzy controllers are trained respectively under various aging states, and the control strategy is optimized in real time through a suitable fuzzy controller to maximize the life of the fuel cell and the battery, thereby solving the problem of poor durability of the power battery system in the prior art.

[0102] In order to meet the power demand, in an optional implementation, the input unit includes:

[0103] A first acquisition module is used to acquire the current system required power and the current battery power;

[0104] A division module, used to divide a plurality of first fuzzy sets according to a value range of the current system required power, divide a plurality of second fuzzy sets according to a value range of the current battery power, and divide a plurality of third fuzzy sets according to a value range of the output power of the fuel cell;

[0105] a first calculation module, configured to input the current system demand power into a system demand power membership function to obtain a plurality of first memberships, wherein the plurality of first memberships are respectively memberships of the current system demand power to the first fuzzy sets, and input the current battery power into a battery power membership function to obtain a plurality of second memberships, wherein the plurality of second memberships are respectively memberships of the current battery power to the second fuzzy sets, wherein both the demand power membership function and the battery power membership function are trapezoidal membership functions;

[0106] A second calculation module is used to calculate a plurality of third memberships according to a fuzzy rule, a plurality of the first memberships and the second membership, wherein the plurality of the third memberships are memberships of the output power of the fuel cell to each of the third fuzzy sets, and the fuzzy rule is a mapping relationship between the first fuzzy set, the second fuzzy set and the third fuzzy set;

[0107] A third calculation module, used for calculating the output power of the fuel cell by using a centroid method according to the plurality of third membership degrees and the centroids of the third fuzzy sets;

[0108] The fourth calculation module is used to calculate the difference between the current system demand power and the output power of the fuel cell to obtain the output power of the battery.

[0109] In the above implementation, a fuzzy controller is used to implement real-time optimization control of a short-time scale system. First, the fuzzy sets and membership functions of the input and output variables are defined. The input variable is the system demand power P demand and battery charge SOC, which can be divided into several first fuzzy sets and several second fuzzy sets, namely "very low", "low", "medium", "high" and "very high". The output variable is the output power P of the fuel cell fc , the third fuzzy set is divided into “very low”, “low”, “medium”, “high” and “very high”. For SOC, a trapezoidal membership function is used with the following parameters: “very low”: SOC = [0, 0, 10, 20]%, “low”: SOC = [10, 20, 30, 40]%, “medium”: SOC = [30, 40, 60, 70]%, “high”: SOC = [60, 70, 80, 90]%, “very high”: SOC = [80, 90, 100, 100]%, for P demand and P fc , after normalization, a similar method is used to define the membership function: "very low": P demand =[0,0,10,20]%, "low": P demand =[10,20,30,40]%, "medium": P demand =[30,40,60,70]%, "high": P demand =[60,70,80,90]%, "very high": P demand =[80,90,100,100]%, "very low": P fc =[0,0,10,20]%, "low": P fc =[10,20,30,40]%, "medium": P fc =[30,40,60,70]%, "high": P fc =[60,70,80,90]%, "very high": P fc =[80,90,100,100]%, the curve diagram of the above demand power membership function and the above battery power membership function is as shown in Figure 3 As shown in the figure, a series of fuzzy rules are formulated to calculate different SOC and P demand Next P fc The output value of the fuel cell can be calculated by the centroid method according to the above third membership degrees and the centroids of the above third fuzzy sets; the difference between the current system demand power and the output power of the fuel cell is calculated to obtain the output power of the battery. The real-time optimization control result of the power distribution of the fuel cell-lithium battery power system on a certain driving cycle implemented by the fuzzy controller is as follows: Figure 4 As shown. The system power requirement P is calculated by the fuzzy controller. demand It can be seen from the allocation results that the fuzzy controller can effectively control the output power of the fuel cell, maintain it at a relatively stable level, and effectively maintain the life of the fuel cell. The power of the lithium battery changes with the demand power, and the response performance is good.

[0110] In order to calculate the third membership degree corresponding to each third fuzzy set, in an optional implementation manner, the second calculation module includes:

[0111] A query submodule, used for executing the query step, querying the combination of the first fuzzy set and the second fuzzy set corresponding to any one of the third fuzzy sets according to the fuzzy rule;

[0112] A first calculation submodule is used to execute a first calculation step to calculate the membership component corresponding to each combination of the first fuzzy set and the second fuzzy set, wherein the membership component is the product of the first membership corresponding to the combination of the first fuzzy set and the second fuzzy set and the corresponding second membership;

[0113] A second calculation submodule, used in a second calculation step, calculates the sum of the membership components corresponding to all combinations of the first fuzzy set and the second fuzzy set to obtain the third membership corresponding to the third fuzzy set;

[0114] The repeating submodule is used to sequentially repeat the query step, the first calculation step and the second calculation step at least once until the third membership degrees corresponding to all the third fuzzy sets are obtained.

[0115] In the above implementation, the fuzzy rules are shown in Table 1. Taking the combination of the above first fuzzy set and the above second fuzzy set, taking the third fuzzy set "very low" as an example, the corresponding combination of the above first fuzzy set and the above second fuzzy set includes the combination of the first fuzzy set "very low" and the second fuzzy set "very low" and the combination of the first fuzzy set "very low" and the second fuzzy set "low", the system required power P is calculated. demand The product of the first membership of the first fuzzy set "very low" and the second membership of the battery power SOC to the second fuzzy set "very low" is used to obtain a membership component corresponding to the combination, and the system demand power P is calculated. demand The product of the first membership of the first fuzzy set "very low" and the second membership of the battery power SOC to the second fuzzy set "low" obtains another membership component corresponding to the combination. The sum of the two membership components is the output power P of the fuel cell. fc The third membership of “very low” to the third fuzzy set.

[0116] In order to obtain a clear output power of the fuel cell, in an optional implementation, the third calculation module includes:

[0117] The third computing submodule is used to adopt Calculate the output power P of the above fuel cell fc * , where P fci is the centroid of the i-th third fuzzy set, μ Ai (P fc ) is the third membership degree corresponding to the i-th third fuzzy set, and n is the number of the third fuzzy sets.

[0118] In the above implementation, in the actual operation process, the maximum value of the membership function of all activated rules is output as the aggregation result, and the fuzzy output set is converted into a clear output value by defuzzification. The present invention adopts the centroid method: Among them, P fci is the centroid of the i-th third fuzzy set, μ Ai (P fc ) is the third membership degree corresponding to the i-th third fuzzy set, and n is the number of the third fuzzy sets. Based on this, the fuzzy controller can adjust the output power P of the fuel cell under different operating conditions. fc to meet system requirements.

[0119] In order to maximize the battery life, in an optional implementation, the training unit includes:

[0120] An establishing module, used for executing an establishing step to establish an initial fuzzy controller corresponding to a target aging state, wherein the target aging state is any one of the above aging states;

[0121] An input module, used to execute an input step, input the current system required power and the current battery power into the initial fuzzy controller, and obtain the first output power of the fuel cell and the second output power of the battery;

[0122] A second acquisition module is used to execute the acquisition step, and acquire the current output voltage of the fuel cell and the current battery capacity of the battery under the condition that the fuel cell is controlled to operate at the first output power and the battery is controlled to operate at the second output power for a predetermined period of time;

[0123] An estimation module, used to execute an estimation step, using a state estimation algorithm and the current output voltage to estimate the life of the fuel cell, and using the state estimation algorithm and the current battery capacity to estimate the life of the storage battery;

[0124] an adjustment module, configured to execute an adjustment step, adjust the parameters of the initial fuzzy controller, the current system required power, and the current battery power, until any one of the current system required power and any one of the current battery power is input into the initial fuzzy controller, and the first life difference and the second life difference are both less than a predetermined threshold, and determine that the initial fuzzy controller is the fuzzy controller corresponding to the target aging state, the first life difference is the life difference of the fuel cell before and after the initial fuzzy controller performs fuzzy control, and the second life difference is the life difference of the fuel cell before and after the initial fuzzy controller performs fuzzy control;

[0125] A repeating module is used to execute the above-mentioned establishment step, the above-mentioned input step, the above-mentioned acquisition step, the above-mentioned estimation step and the above-mentioned adjustment step in sequence at least once until the above-mentioned fuzzy controllers corresponding to all the above-mentioned aging states are obtained.

[0126] In the above embodiment, it is assumed that the output voltage of the fuel cell drops to 90% of the initial value as the end-of-life value, and the capacity of the lithium battery drops to 70% of the initial value as the end-of-life value. Figure 5 As shown, five aging state combinations are defined: 1. The fuel cell is not aged and the lithium battery is not aged, 2. The fuel cell has low aging and the lithium battery has not aged, 3. The fuel cell has low aging and the lithium battery has low aging, 4. The fuel cell has high aging and the lithium battery has low aging, 5. The fuel cell has high aging and the lithium battery has high aging. According to the operation modes of the fuel cell system under the above five aging states, five fuzzy controllers are trained. According to the life prediction of multiple power sources, the power allocation results are optimized in real time, so that the control strategy of the trained fuzzy controller can maximize the life and energy efficiency of the overall system while meeting the power demand.

[0127] In order to accurately predict the battery life, in an optional implementation, the estimation module includes:

[0128] A first estimation submodule, used to perform a first estimation step, and calculate the output voltage at the next moment according to the current output voltage by using a state estimation algorithm;

[0129] A second estimation submodule, used to perform a second estimation step, and calculate the battery capacity at the next moment according to the current battery capacity by using the state estimation algorithm;

[0130] The repeating submodule is used to repeat the first estimation step until the output voltage at the next moment is equal to the end-of-life voltage, and the life of the fuel cell is calculated based on the next moment and the current moment, and repeat the second estimation step until the battery capacity at the next moment is equal to the end-of-life capacity, and the life of the battery is calculated based on the next moment and the current moment.

[0131] In the above implementation, the observer-based state estimation method estimates and predicts the aging state of the fuel cell and battery (lithium battery) in the system online. First, a battery state model is constructed, where the fuel cell uses the output voltage as the state quantity and the lithium battery uses the battery capacity as the state quantity: Based on this model, the state equation and measurement equation are constructed in the state space: Among them, X is the state variable, that is, the output voltage of the fuel cell or the capacity of the lithium battery, and ω and θ represent Gaussian white noise. Then, the observer model is used to estimate and predict the variables in the state equation online, which includes three steps: state value prediction, gain calculation and state value update, as shown below: 1) State value prediction: 2) Gain calculation: 3) Status value update: is the estimated value of the state quantity in the kth period, and are the prior state estimate and the error covariance estimate, K k is the feedback gain, R and Q are the noise matrices, y k is the observed value of the state quantity, F is the state transfer matrix, and H is the conversion matrix from the state value to the observed value. Based on historical data, the life prediction results of fuel cells and lithium batteries calculated by the above method are obtained. The uncertainty of the prediction results is obtained by running the program multiple times. The prediction results of different prediction start times are plotted in the figure using a box plot. The life prediction results of fuel cells are shown in the figure. Figure 6 As shown in the figure, and the lithium battery life prediction results are as follows Figure 7 shown.

[0132] In order to select a suitable fuzzy controller, in an optional implementation manner, the above-mentioned determination unit includes:

[0133] A setting module, used to set the credibility of each of the above fuzzy controllers under multiple reference aging degrees of the above fuel cell;

[0134] A determination module, used for determining the fuzzy controller with the highest credibility as the optimal fuzzy controller corresponding to each of the reference aging degrees;

[0135] a fifth calculation module, configured to combine the credibility of the two optimal fuzzy controllers corresponding to the two reference aging degrees using DS theory when the aging degree of the fuel cell is between the two reference aging degrees, to obtain normalized credibility of the two optimal fuzzy controllers, so that the sum of the two normalized credibility is 1;

[0136] The processing module is used to perform weighted averaging on the corresponding two optimal fuzzy controllers according to the two normalized credibility degrees to obtain the target fuzzy controller, so that the output of the target fuzzy controller is the weighted average of the outputs of the two optimal fuzzy controllers.

[0137] In the above implementation, for the fuel cell system operation mode under the above five aging conditions, five fuzzy controllers are defined, and control decisions are given according to their inputs and rule bases. The membership function parameter value of the fuel cell output power is represented by , that is, i values ​​are used to describe the membership function of the fuel cell output power, and a fuzzy reasoner based on a Gaussian function is constructed to calculate the basic probability value of the fuel cell aging value (obtained through observer prediction) corresponding to each fuzzy controller in actual situations, reflecting the decision credibility (confidence factor, CF) of each controller. The input of the fuzzy reasoner is three aging conditions (no aging, low aging, high aging), and the output is the credibility of the corresponding five fuzzy controllers. For example, for some random aging conditions during online operation, the credibility of the corresponding five fuzzy controllers is shown in Table 2. Combined with the DS data fusion theory, the credibility of different controllers is combined to form a new credibility function. This method is accomplished by weighted averaging all possible intersections. For example, the following formula represents the calculation method for merging the credibility of the two fuzzy controllers B and C into A: Where K is the normalization constant. Normalization: Normalize the combined results to ensure that the sum of all credibility is 1. The DS theory is used to intelligently fuse the outputs of multiple fuzzy controllers to improve the robustness and accuracy of the overall control system. It is used to deal with the situation where the power distribution optimal points provided by multiple fuzzy controllers under different aging conditions are inconsistent. The results of using an intelligent decision-making method to fuse two fuzzy controllers under a certain aging state of the fuel cell system are as follows: Figure 8 shown.

[0138] The control device of the power battery system includes a processor and a memory. The above units are stored in the memory as program units, and the processor executes the above program units stored in the memory to implement corresponding functions. The above modules are all located in the same processor; or, the above modules are located in different processors in any combination.

[0139] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the problem of poor durability of the power battery system in the prior art can be solved by adjusting the kernel parameters.

[0140] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0141] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, a device where the computer-readable storage medium is located is controlled to execute the control method of the power battery system.

[0142] Specifically, the control method of the power battery system includes:

[0143] Step S201, respectively training corresponding fuzzy controllers under various aging conditions, so that the fuzzy controllers control the output power of the fuel cell and the battery to maximize the life of the fuel cell and the battery, wherein the aging conditions are conditions under different combinations of aging degrees of the fuel cell and the battery;

[0144] Specifically, since the power distribution of fuel cells and batteries has different effects on battery life under different aging conditions, the corresponding fuzzy controllers are trained under multiple aging conditions respectively, so as to maximize the life of fuel cells and batteries by controlling the power distribution of fuel cells and batteries through intelligent decision-making of fuzzy controllers.

[0145] Step S202, determining the fuzzy controller corresponding to the aging state that is closest to the aging degree of the power battery system as the target fuzzy controller;

[0146] Specifically, a suitable fuzzy controller is selected according to the aging degree of the power battery system, and the fuzzy controller corresponding to the aging state with the closest aging degree can be determined as the target fuzzy controller.

[0147] Step S203, inputting the current system demand power of the power battery system and the current battery power of the storage battery into the target fuzzy controller to obtain the output power of the fuel cell and the output power of the storage battery to control the power distribution of the fuel cell and the storage battery.

[0148] Specifically, the target fuzzy controller determines the output power of the fuel cell and the battery according to the current system power demand of the power battery system and the current battery power of the battery, and controls the power distribution of the fuel cell and the battery, so as to maximize the life of the fuel cell and the battery while meeting the current system power demand.

[0149] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the control method of the power battery system is executed when the program is run.

[0150] Specifically, the control method of the power battery system includes:

[0151] Step S201, respectively training corresponding fuzzy controllers under various aging conditions, so that the fuzzy controllers control the output power of the fuel cell and the battery to maximize the life of the fuel cell and the battery, wherein the aging conditions are conditions under different combinations of aging degrees of the fuel cell and the battery;

[0152] Specifically, since the power distribution of fuel cells and batteries has different effects on battery life under different aging conditions, the corresponding fuzzy controllers are trained under multiple aging conditions respectively, so as to maximize the life of fuel cells and batteries by controlling the power distribution of fuel cells and batteries through intelligent decision-making of fuzzy controllers.

[0153] Step S202, determining the fuzzy controller corresponding to the aging state that is closest to the aging degree of the power battery system as the target fuzzy controller;

[0154] Specifically, a suitable fuzzy controller is selected according to the aging degree of the power battery system, and the fuzzy controller corresponding to the aging state with the closest aging degree can be determined as the target fuzzy controller.

[0155] Step S203, inputting the current system demand power of the power battery system and the current battery power of the storage battery into the target fuzzy controller to obtain the output power of the fuel cell and the output power of the storage battery to control the power distribution of the fuel cell and the storage battery.

[0156] Specifically, the target fuzzy controller determines the output power of the fuel cell and the battery according to the current system power demand of the power battery system and the current battery power of the battery, and controls the power distribution of the fuel cell and the battery, so as to maximize the life of the fuel cell and the battery while meeting the current system power demand.

[0157] An embodiment of the present invention provides a vehicle, the vehicle comprising a power battery system, a processor, a memory, and a program stored in the memory and executable on the processor, wherein the fuel cell and the storage battery of the power battery system are both used to output electrical energy to provide power, and when the processor executes the program, at least the following steps are implemented:

[0158] Step S201, respectively training corresponding fuzzy controllers under various aging conditions, so that the fuzzy controllers control the output power of the fuel cell and the battery to maximize the life of the fuel cell and the battery, wherein the aging conditions are conditions under different combinations of aging degrees of the fuel cell and the battery;

[0159] Specifically, since the power distribution of fuel cells and batteries has different effects on battery life under different aging conditions, the corresponding fuzzy controllers are trained under multiple aging conditions respectively, so as to maximize the life of fuel cells and batteries by controlling the power distribution of fuel cells and batteries through intelligent decision-making of fuzzy controllers.

[0160] Step S202, determining the fuzzy controller corresponding to the aging state that is closest to the aging degree of the power battery system as the target fuzzy controller;

[0161] Specifically, a suitable fuzzy controller is selected according to the aging degree of the power battery system, and the fuzzy controller corresponding to the aging state with the closest aging degree can be determined as the target fuzzy controller.

[0162] Step S203, inputting the current system demand power of the power battery system and the current battery power of the storage battery into the target fuzzy controller to obtain the output power of the fuel cell and the output power of the storage battery to control the power distribution of the fuel cell and the storage battery.

[0163] Specifically, the target fuzzy controller determines the output power of the fuel cell and the battery according to the current system power demand of the power battery system and the current battery power of the battery, and controls the power distribution of the fuel cell and the battery, so as to maximize the life of the fuel cell and the battery while meeting the current system power demand.

[0164] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps:

[0165] Step S201, respectively training corresponding fuzzy controllers under various aging conditions, so that the fuzzy controllers control the output power of the fuel cell and the battery to maximize the life of the fuel cell and the battery, wherein the aging conditions are conditions under different combinations of aging degrees of the fuel cell and the battery;

[0166] Specifically, since the power distribution of fuel cells and batteries has different effects on battery life under different aging conditions, the corresponding fuzzy controllers are trained under multiple aging conditions respectively, so as to maximize the life of fuel cells and batteries by controlling the power distribution of fuel cells and batteries through intelligent decision-making of fuzzy controllers.

[0167] Step S202, determining the fuzzy controller corresponding to the aging state that is closest to the aging degree of the power battery system as the target fuzzy controller;

[0168] Specifically, a suitable fuzzy controller is selected according to the aging degree of the power battery system, and the fuzzy controller corresponding to the aging state with the closest aging degree can be determined as the target fuzzy controller.

[0169] Step S203, inputting the current system demand power of the power battery system and the current battery power of the storage battery into the target fuzzy controller to obtain the output power of the fuel cell and the output power of the storage battery to control the power distribution of the fuel cell and the storage battery.

[0170] Specifically, the target fuzzy controller determines the output power of the fuel cell and the battery according to the current system power demand of the power battery system and the current battery power of the battery, and controls the power distribution of the fuel cell and the battery, so as to maximize the life of the fuel cell and the battery while meeting the current system power demand.

[0171] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0172] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0173] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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 1 A device that provides the functions specified in a block or multiple blocks.

[0174] 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.

[0175] 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.

[0176] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0177] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0178] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0179] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0180] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0181] 1) In the control method of the power battery system of the present application, it is considered that the power control strategies of the fuel cell and the battery under the aging state have different effects on the life of the fuel cell and the battery. Therefore, the corresponding fuzzy controllers are trained respectively under various aging states, and the control strategy is optimized in real time by a suitable fuzzy controller to maximize the life of the fuel cell and the battery, thereby solving the problem of poor durability of the power battery system in the prior art.

[0182] 2) In the control device of the power battery system of the present application, the power control strategies of the fuel cell and the battery in the aging state have different effects on the life of the fuel cell and the battery. Therefore, the corresponding fuzzy controllers are trained respectively under various aging conditions. The control strategy is optimized in real time through a suitable fuzzy controller to maximize the life of the fuel cell and the battery, thereby solving the problem of poor durability of the power battery system in the prior art.

[0183] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A control method for a power battery system, characterized in that: The fuel cell and the storage battery of the power battery system are both used to output electrical energy to provide power, and the method includes: The corresponding fuzzy controllers are trained respectively under various aging states, so that the fuzzy controllers control the output power of the fuel cell and the battery to maximize the life of the fuel cell and the battery, wherein the aging state is a state of the fuel cell and the battery under different aging degree combinations; Determining the fuzzy controller corresponding to the aging state that is closest to the aging degree of the power battery system as the target fuzzy controller; The current system demand power of the power battery system and the current battery power of the storage battery are input into the target fuzzy controller to obtain the output power of the fuel cell and the output power of the storage battery to control the power distribution of the fuel cell and the storage battery.

2. The method according to claim 1, characterized in that Inputting the current system demand power of the power battery system and the current battery power of the storage battery into the target fuzzy controller to obtain the output power of the fuel cell and the output power of the storage battery, including: Acquire the current system required power and the current battery power; Divide a plurality of first fuzzy sets according to the value range of the current system required power, divide a plurality of second fuzzy sets according to the value range of the current battery power, and divide a plurality of third fuzzy sets according to the value range of the output power of the fuel cell; Inputting the current system demand power into the system demand power membership function to obtain a plurality of first memberships, wherein the plurality of first memberships are respectively the memberships of the current system demand power to each of the first fuzzy sets; inputting the current battery power into the battery power membership function to obtain a plurality of second memberships, wherein the plurality of second memberships are respectively the memberships of the current battery power to each of the second fuzzy sets; and both the demand power membership function and the battery power membership function are trapezoidal membership functions; A plurality of third memberships are calculated according to a fuzzy rule, a plurality of the first memberships and the second memberships, wherein the plurality of the third memberships are respectively memberships of the output power of the fuel cell to each of the third fuzzy sets, and the fuzzy rule is a mapping relationship between the first fuzzy set, the second fuzzy set and the third fuzzy set; Calculating the output power of the fuel cell using a centroid method according to the plurality of third membership degrees and the centroid of each third fuzzy set; The difference between the current system demand power and the output power of the fuel cell is calculated to obtain the output power of the battery.

3. The method according to claim 2, characterized in that A plurality of third memberships are calculated according to the fuzzy rule, the plurality of the first memberships and the second memberships, including: A query step of querying a combination of the first fuzzy set and the second fuzzy set corresponding to any one of the third fuzzy sets according to the fuzzy rule; A first calculation step is to calculate a membership component corresponding to each combination of the first fuzzy set and the second fuzzy set, wherein the membership component is a product of the first membership corresponding to the combination of the first fuzzy set and the second fuzzy set and the corresponding second membership; a second calculation step of calculating the sum of the membership components corresponding to all combinations of the first fuzzy set and the second fuzzy set to obtain the third membership corresponding to the third fuzzy set; The query step, the first calculation step and the second calculation step are sequentially repeated at least once until the third membership degrees corresponding to all the third fuzzy sets are obtained.

4. The method according to claim 2, characterized in that: Calculating the output power of the fuel cell using a centroid method according to the plurality of third membership degrees and the centroid of each third fuzzy set includes: use Calculate the output power P of the fuel cell fc * , where P fci is the centroid of the third fuzzy set of the ith Ai (P fc ) is the third membership degree corresponding to the i-th third fuzzy set, and n is the number of the third fuzzy sets.

5. The method according to any one of claims 1 to 4, characterized in that The corresponding fuzzy controllers are trained respectively under various aging conditions so that the fuzzy controllers control the output power of the fuel cell and the battery to maximize the life of the fuel cell and the battery, including: An establishing step of establishing an initial fuzzy controller corresponding to a target aging state, wherein the target aging state is any one of the aging states; An input step of inputting the current system required power and the current battery power into the initial fuzzy controller to obtain a first output power of the fuel cell and a second output power of the battery; an acquisition step, in which the current output voltage of the fuel cell and the current battery capacity of the battery are acquired while the fuel cell is controlled to operate at the first output power and the battery is controlled to operate at the second output power for a predetermined period of time; An estimation step, using a state estimation algorithm and the current output voltage to estimate the life of the fuel cell, and using the state estimation algorithm and the current battery capacity to estimate the life of the storage battery; an adjustment step, adjusting the parameters of the initial fuzzy controller, the current system required power and the current battery power, until any one of the current system required power and any one of the current battery power is input into the initial fuzzy controller, and the first life difference and the second life difference are both less than a predetermined threshold, and determining that the initial fuzzy controller is the fuzzy controller corresponding to the target aging state, the first life difference is the life difference of the fuel cell before and after the initial fuzzy controller performs fuzzy control, and the second life difference is the life difference of the fuel cell before and after the initial fuzzy controller performs fuzzy control; The establishing step, the inputting step, the acquiring step, the estimating step and the adjusting step are sequentially repeated at least once until the fuzzy controllers corresponding to all the aging states are obtained.

6. The method according to claim 5, characterized in that The method of estimating the life of the fuel cell by using a state estimation algorithm and the current output voltage and estimating the life of the storage battery by using the state estimation algorithm and the current battery capacity comprises: A first estimation step, calculating the output voltage at the next moment by a state estimation algorithm according to the current output voltage; A second estimation step, calculating the battery capacity at the next moment by using the state estimation algorithm according to the current battery capacity; Repeat the first estimation step until the output voltage at the next moment is equal to the end-of-life voltage, and calculate the life of the fuel cell based on the next moment and the current moment. Repeat the second estimation step until the battery capacity at the next moment is equal to the end-of-life capacity, and calculate the life of the battery based on the next moment and the current moment.

7. The method according to claim 1, characterized in that The fuzzy controller corresponding to the aging state that is closest to the aging degree of the power battery system is determined as the target fuzzy controller, including: Setting the credibility of each of the fuzzy controllers at multiple reference aging levels of the fuel cell; Determining the fuzzy controller with the greatest credibility as the optimal fuzzy controller corresponding to each reference aging degree; When the aging degree of the fuel cell is between the two reference aging degrees, the credibility of the optimal fuzzy controllers corresponding to the two reference aging degrees is combined by using the DS theory to obtain the normalized credibility of the two optimal fuzzy controllers, so that the sum of the two normalized credibility is 1; The target fuzzy controller is obtained by performing weighted averaging on the corresponding two optimal fuzzy controllers according to the two normalized credibility degrees, so that the output of the target fuzzy controller is the weighted average of the outputs of the two optimal fuzzy controllers.

8. A control device for a power battery system, characterized in that: The fuel cell and storage battery of the power battery system are both used to output electrical energy to provide power, and the device includes: A training unit, used for respectively training corresponding fuzzy controllers under multiple aging states, so that the fuzzy controllers control the output power of the fuel cell and the battery to maximize the life of the fuel cell and the battery, wherein the aging state is a state of the fuel cell and the battery under different aging degree combinations; A determining unit, configured to determine the fuzzy controller corresponding to the aging state that is closest to the aging degree of the power battery system as a target fuzzy controller; An input unit is used to input the current system demand power of the power battery system and the current battery power of the battery into the target fuzzy controller to obtain the output power of the fuel cell and the output power of the battery to control the power distribution of the fuel cell and the battery.

9. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A vehicle, characterized in that: include: A power battery system, one or more processors, a memory, and one or more programs, wherein the fuel cell and the battery of the power battery system are used to output electrical energy to provide power, the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of claims 1 to 7.

Images