Fuel cell energy management method and device based on fuzzy control

Abstract

The invention provides a fuel cell energy management method and device based on fuzzy control, and the method comprises the steps: carrying out the fuzzy processing of a current data value corresponding to an impact factor, and determining a target fuzzy set discourse domain corresponding to the current data value of the impact factor, and the membership degree of the target fuzzy set discourse domain in the target fuzzy set discourse domain; performing fuzzy reasoning in combination with a target fuzzy set discourse domain corresponding to the influence factor and a preset fuzzy rule table, and determining a fuzzy set discourse domain to which the output power of the fuel cell belongs; and according to the fuzzy set discourse domain to which the output power of the fuel cell belongs and the membership degree of the influence factor on the target fuzzy set discourse domain to which the influence factor belongs, performing sharpening processing on the output power of the fuel cell by using a preset defuzzification method, and determining a predicted value of the output power of the fuel cell. Fuel cell power output management is achieved through the fuzzy control theory, the energy utilization efficiency of the fuel cell hybrid power system is improved, and the driving experience of a driver is improved.

Description

Technical Field

[0001] The present application relates to the technical field of fuel cell energy management, and in particular to a fuel cell energy management method and device based on fuzzy control. Background Art

[0002] At present, in terms of fuel cell energy management, most of them adopt rule-based fuel cell energy management strategies. Specifically, they are further divided into energy management methods based on multi-point control and power following. Both methods are simple in design, highly reliable, do not require complex control algorithms, have low development costs, simple control systems, and low hardware requirements. Therefore, they have obvious advantages in terms of technical maturity, cost, and versatility.

[0003] Due to its simple design, the rule-based energy management strategy cannot adapt to complex and changeable working conditions. Under complex working conditions, the power battery state of charge (SOC) changes unstably, and the user's power demand under complex working conditions cannot be responded to accurately and quickly, that is, the power switching is not flexible enough, which in turn affects the driving experience. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide at least a fuel cell energy management method and device based on fuzzy control, to achieve fuel cell power output management through fuzzy control theory, to improve the energy utilization efficiency of the fuel cell hybrid system, and to improve the driving experience of the driver.

[0005] This application mainly includes the following aspects: In the first aspect, an embodiment of the present application provides a fuel cell energy management method based on fuzzy control, the method comprising: determining a current data value corresponding to an influencing factor of the fuel cell output power; fuzzifying the current data value corresponding to the influencing factor to determine a target fuzzy set domain corresponding to the current data value of the influencing factor and its membership in the target fuzzy set domain; performing fuzzy reasoning based on the target fuzzy set domain corresponding to the influencing factor and a preset fuzzy rule table to determine the fuzzy set domain to which the fuel cell output power belongs, the preset fuzzy rule table describing the mapping relationship between different fuzzy set domains corresponding to the influencing factor and the fuzzy set domain to which the fuel cell output power belongs; based on the fuzzy set domain to which the fuel cell output power belongs and the membership of the influencing factor in the target fuzzy set domain to which it belongs, using a preset defuzzification method to clarify the fuel cell output power to determine a predicted value of the fuel cell output power.

[0006] In a possible implementation, the influencing factors include the required power of the entire vehicle and the state of charge of the power battery.

[0007] In one possible implementation, the current data value corresponding to the influencing factor is determined in the following manner: based on the current pedaling intensity of the accelerator pedal, the current data value of the required power of the entire vehicle is determined; the current power battery voltage and the current power battery current corresponding to the power battery are collected; based on the current power battery voltage and the current power battery current, the current data value of the power battery state of charge is calculated using a given state of charge calculation strategy.

[0008] In one possible implementation, the target fuzzy set corresponding to the current data value of the influencing factor and its membership in the target fuzzy set domain are determined in the following manner: multiple fuzzy set domains corresponding to the influencing factor and the membership function corresponding to each fuzzy set domain are obtained, wherein different fuzzy set domains correspond to different levels of the influencing factor; based on the current data value of the influencing factor, the target fuzzy set domain to which the influencing factor belongs is determined; the current data value of the influencing factor is substituted into the membership function corresponding to the target fuzzy set domain to which it belongs, to obtain the membership of the influencing factor in the target fuzzy set domain to which it belongs.

[0009] In a possible implementation, the preset defuzzification method is any one of a maximum membership method, a center of gravity method, or a weighted average method. In a possible implementation, the method further includes: controlling the fuel cell to output according to the predicted value; monitoring and analyzing the actual operating value of the fuel cell output power, and optimizing the fuzzy processing process according to the analysis result.

[0010] In the second aspect, an embodiment of the present application also provides a fuel cell energy management device based on fuzzy control, the device including: an influencing factor determination module, used to determine the current data value corresponding to the influencing factor of the fuel cell output power; a fuzzification processing module, used to perform fuzzy processing on the current data value corresponding to the influencing factor, and determine the target fuzzy set domain corresponding to the current data value of the influencing factor and its membership in the target fuzzy set domain; a fuzzy reasoning module, used to perform fuzzy reasoning based on the target fuzzy set domain corresponding to the influencing factor and a preset fuzzy rule table to determine the fuzzy set domain to which the fuel cell output power belongs, the preset fuzzy rule table describes the mapping relationship between different fuzzy set domains corresponding to the influencing factor and the fuzzy set domain to which the fuel cell output power belongs; a defuzzification module, used to clarify the fuel cell output power using a preset defuzzification method according to the fuzzy set domain to which the fuel cell output power belongs and the membership of the influencing factor in the target fuzzy set domain to which it belongs, and determine the predicted value of the fuel cell output power.

[0011] In one possible implementation, the fuzzy processing module is further used to: obtain multiple fuzzy set domains corresponding to the influencing factor and the membership function corresponding to each fuzzy set domain, wherein different fuzzy set domains correspond to different levels of the influencing factor; determine the target fuzzy set domain to which the influencing factor belongs based on the current data value of the influencing factor; and bring the current data value of the influencing factor into the membership function corresponding to the target fuzzy set domain to which it belongs, to obtain the membership of the influencing factor in the target fuzzy set domain to which it belongs.

[0012] In a third aspect, an embodiment of the present application further provides an electronic device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the fuel cell energy management method based on fuzzy control in the above-mentioned first aspect or any possible implementation of the first aspect.

[0013] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of fuzzy control-based fuel cell energy management in the above-mentioned first aspect or any possible implementation of the first aspect are executed.

[0014] The embodiments of the present application provide a fuel cell energy management method and device based on fuzzy control, including: fuzzifying the current data value corresponding to the influencing factor to determine the target fuzzy set domain corresponding to the current data value of the influencing factor and its membership in the target fuzzy set domain; performing fuzzy reasoning based on the target fuzzy set domain corresponding to the influencing factor and a preset fuzzy rule table to determine the fuzzy set domain to which the fuel cell output power belongs; and using a preset defuzzification method to clarify the fuel cell output power based on the fuzzy set domain to which the fuel cell output power belongs and the membership of the influencing factor in the target fuzzy set domain to which it belongs, to determine the predicted value of the fuel cell output power. The present application implements fuel cell power output management through fuzzy control theory, improves the energy utilization efficiency of the fuel cell hybrid system, and enhances the driving experience of the driver.

[0015] This application is beneficial in that: (1) Through fuzzy reasoning, the influence of multiple factors on the output power of the fuel cell can be comprehensively considered to improve the SOC stability of the power battery.

[0016] (2) Compared with traditional power allocation methods, fuzzy control methods are more friendly to energy storage batteries and can extend the service life of energy storage batteries.

[0017] (3) The fuzzy reasoning method can be adjusted and optimized according to specific application requirements, and it is easy to incorporate new factors or rules to adapt to different types of fuel cells and energy storage devices.

[0018] (4) Unlike other energy allocation methods based on models and dynamic energy planning, fuzzy reasoning does not require an in-depth understanding of the internal characteristics of fuel cells and is easier to implement and use in practical applications.

[0019] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flowchart of a fuel cell energy management method based on fuzzy control provided in an embodiment of the present application is shown; Figure 2 A distribution diagram of the membership function of vehicle demand power provided by an embodiment of the present application is shown; Figure 3 A distribution diagram of the state of charge membership function of a power battery provided in an embodiment of the present application is shown; Figure 4 A distribution diagram of a membership function of a fuel cell output power provided by an embodiment of the present application is shown; Figure 5 A functional module diagram of a fuel cell energy management device based on fuzzy control provided in an embodiment of the present application is shown; Figure 6 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions 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. It should be understood that the drawings in the present application only serve the purpose of illustration and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can be implemented out of sequence, and steps without logical context can be reversed or implemented simultaneously. In addition, those skilled in the art, under the guidance of the contents of this application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0023] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0024] The fuel cell energy management strategy currently provided refers to a series of control methods and rules for managing the flow and distribution of energy between fuel cells and lithium batteries. A reasonable strategy can effectively improve the efficiency of the fuel cell system and vehicle performance. Currently, most users adopt rule-based fuel cell energy management strategies, which are further divided into energy management methods based on multi-point control and power following. Both methods have the following advantages: It has simple design, high reliability, no need for complex control algorithms, low development cost, simple control system, and low hardware requirements. Therefore, it has obvious advantages in terms of technical maturity, cost, and versatility.

[0025] However, due to its simple design, the rule-based energy management strategy cannot adapt to complex and changeable working conditions. Under complex working conditions, the power output of the fuel cell and its related influencing factors change unstably. Combined with the disadvantage that fuel cells are not as responsive as traditional engines, it will lead to increased hydrogen consumption and reduced cruising range. The user's power requirements under complex working conditions cannot be met, which in turn affects the driving experience.

[0026] Based on this, the embodiments of the present application provide a fuel cell energy management method and device based on fuzzy control, which implements fuel cell power output management through fuzzy control theory, improves the energy utilization efficiency of the fuel cell hybrid system, and enhances the driving experience of the driver. The details are as follows: See also Figure 1 , Figure 1 FIG1 shows a flow chart of a fuel cell energy management method based on fuzzy control provided by an embodiment of the present application. Figure 1 As shown, the method provided in the embodiment of the present application includes the following steps: S100: Determine a current data value corresponding to an influencing factor of fuel cell output power.

[0027] S200 , performing fuzzification processing on the current data value corresponding to the influencing factor, and determining the target fuzzy set domain corresponding to the current data value of the influencing factor and its membership degree on the target fuzzy set domain.

[0028] S300 , performing fuzzy reasoning based on the target fuzzy set domain corresponding to the influencing factor and the preset fuzzy rule table to determine the fuzzy set domain to which the fuel cell output power belongs.

[0029] The preset fuzzy rule table describes the mapping relationship between different fuzzy set domains corresponding to the influencing factors and the fuzzy set domain to which the fuel cell output power belongs.

[0030] S400 , based on the fuzzy set domain to which the fuel cell output power belongs and the degree of membership of the influencing factor in the target fuzzy set domain to which it belongs, a preset defuzzification method is used to clarify the fuel cell output power, and a predicted value of the fuel cell output power is determined.

[0031] Through the analysis of the dynamic characteristics of fuel cells, it is found that the fuel cell system is complex, including complex dynamic processes such as ion transmembrane transport. As a controlled object, it is difficult to establish an accurate mathematical model. Fuzzy reasoning is a reasoning method based on fuzzy logic, which is used to deal with uncertainty and ambiguity problems in the real world. Fuzzy reasoning is based on fuzzy set theory. The elements in the fuzzy set have a certain degree of membership, which indicates the degree to which the element belongs to the set. The value range is between 0 and 1. By defining fuzzy rules, the input fuzzy information is reasoned according to these rules, and finally the fuzzy results are clarified into the final results.

[0032] In steps S100 to S400, the influencing factors corresponding to the fuel cell output power are used as fuzzy input variables, and the fuel cell output power is used as a fuzzy output variable. Fuzzy reasoning is performed on the current data values ​​of the influencing factors corresponding to the fuel cell output power through a pre-selected fuzzy rule table, and the reasoning results are defuzzified to obtain a predicted value of the fuel cell output power. The fuel cell power output is managed through fuzzy control theory, avoiding the creation of complex mathematical models related to the fuel cell system. On the basis of considering and integrating the influence of multiple factors on the fuel cell output power, on the one hand, the calculation rate of the fuel cell output power is improved, and on the other hand, the energy utilization efficiency of the fuel cell hybrid system is improved, thereby improving the driving experience of the driver.

[0033] In a preferred embodiment, the factors affecting the fuel cell output power include at least the vehicle required power P m and power battery state of charge BAT SOC .

[0034] In this application, the above vehicle required power P m and power battery state of charge BAT SOC These are just two examples provided in this application. In actual applications, there is no specific restriction on the factors affecting the output power of the fuel cell, which are predetermined according to the user's own needs.

[0035] In a specific embodiment, the current data value corresponding to the impact factor is determined by: According to the current depression intensity of the accelerator pedal, the current data value of the required power of the whole vehicle is determined, the current power battery voltage and the current power battery current corresponding to the power battery are collected, and based on the current power battery voltage and the current power battery current, the current data value of the power battery state of charge is calculated using a given state of charge calculation strategy. In a specific implementation, based on the predetermined mapping relationship between the accelerator pedal's stepping intensity and the vehicle's required power, the current data value of the vehicle's required power corresponding to the current accelerator pedal's stepping intensity can be determined by collecting the current accelerator pedal's stepping intensity.

[0036] In a preferred embodiment, before executing step S200, different influencing factors and fuel cell output powers are first fuzzified, that is, the value ranges corresponding to the influencing factors and fuel cell output powers are divided into multiple fuzzy set domains according to requirements, and the linguistic variables (indicator levels) and membership functions corresponding to each fuzzy set domain are defined.

[0037] In a specific embodiment, the vehicle required power P m For example, the vehicle's required power P m The maximum value is 150kW, so the vehicle power requirement Pm The corresponding value range is [0, 150], and the vehicle power requirement P m The corresponding value range is normalized to obtain the vehicle required power P m The domain is [0, 1], and the vehicle required power P is calculated according to different levels. m The domain is divided into multiple fuzzy set domains {“very low ZO”, “low S”, “medium to low PS”, “medium to high PM”, “high B”, “very high PB”}, see Figure 2 , Figure 2 A distribution diagram of the membership function of vehicle demand power provided in an embodiment of the present application is shown.

[0038] like Figure 2 As shown, Figure 2 Shows the vehicle's required power P m The domain of discourse is divided into each fuzzy set domain according to the membership function, and the horizontal axis represents the vehicle demand power P m The vertical axis represents the degree of membership.

[0039] In a specific embodiment, if Figure 2 As shown, when the vehicle requires power P m =105KW, the corresponding Figure 2 The horizontal coordinate is 0.7, which belongs to both the fuzzy set domain "medium to high PM" (membership degree is 0.5) and the fuzzy set domain "high B" (membership degree is 0.5).

[0040] In a specific embodiment, the power battery state of charge BAT SOC For example, the power battery state of charge BAT SOC The maximum value is 100%, so the power battery state of charge BAT SOC The corresponding value range is [0%, 100%], which is the state of charge of the power battery BAT SOC The corresponding value range is normalized to obtain the power battery state of charge BAT SOC The domain is [0, 1], and the power battery state of charge BAT is calculated according to different levels. SOC The domain is divided into multiple fuzzy set domains {"very low L", "low LS", "medium to low ME", "medium MD", "medium to high HS", "high H"}, see Figure 3 , Figure 3 A distribution diagram of the state of charge membership function of a power battery provided in an embodiment of the present application is shown.

[0041] like Figure 3 As shown, Figure 3 Shows the power battery charge state BAT SOCThe domain of discourse is divided into each fuzzy set domain according to the membership function, and the horizontal axis represents the power battery state of charge BAT SOC The vertical axis represents the degree of membership.

[0042] In a specific embodiment, if Figure 3 As shown, when the power battery state of charge BAT SOC =90%, the corresponding Figure 3 The horizontal coordinate 0.9 shown belongs to both the fuzzy set domain "medium to high HS" (membership degree is 0.5) and the fuzzy set domain "high H" (membership degree is 0.5).

[0043] In one embodiment, the fuel cell output power P FC For example, the fuel cell output power P FC The maximum value is 60kW, so the fuel cell output power P FC The corresponding value range is [0, 60], and the fuel cell output power P FC The corresponding value range is normalized to obtain the fuel cell output power P FC The domain is [0, 1], and the fuel cell output power P is calculated according to different levels. FC The domain is divided into multiple fuzzy set domains {"0OFF", "small MIN", "medium-small MEM", "medium MED", "medium-large HMM", "maximum MAX"}, see Figure 4 , Figure 4 A distribution diagram of the membership function of a fuel cell output power provided in an embodiment of the present application is shown.

[0044] like Figure 4 As shown, Figure 4 shows the fuel cell output power P FC The domain of discourse is divided into each fuzzy set domain according to the membership function, and the horizontal axis represents the fuel cell output power P FC The vertical axis represents the degree of membership.

[0045] In a specific embodiment, if Figure 4 As shown, when the fuel cell output power P FC =6KW, the corresponding Figure 4 The horizontal coordinate 0.1 shown belongs to both the fuzzy set domain "0OFF" (membership degree is 0.5) and the fuzzy set domain "small MIN" (membership degree is 0.5).

[0046] Furthermore, after mapping different influencing factors and fuel cell output power to corresponding fuzzy set domains, a fuzzy rule table is established, as shown in Table 1. Table 1 shows a fuzzy rule table indicating the relationship between fuel cell output power, vehicle required power, and power battery charge state.

[0047] Table 1

[0048] The fuzzy rules given in Table 1 above can be described using the following logical language: When the vehicle requires power P m It is an extremely low ZO, and the power battery state of charge BAT SOC When L is extremely low, the fuel cell output power P FC is medium MED; When the vehicle requires power P m It is an extremely low ZO, and the power battery state of charge BAT SOC When LS is low, the fuel cell output power P FC It is medium to small MEM; When the vehicle requires power P m It is an extremely low ZO, and the power battery state of charge BAT SOC When the ME is medium to low, the fuel cell output power P FC It is medium to small MEM; And so on, I won’t go into details here.

[0049] In a preferred embodiment, step S200 includes: Obtain multiple fuzzy set domains corresponding to the impact factor and the membership function corresponding to each fuzzy set domain, wherein different fuzzy set domains correspond to different levels of the impact factor. According to the current data value of the impact factor, determine the target fuzzy set domain to which the impact factor belongs. Substitute the current data value of the impact factor into the membership function corresponding to the target fuzzy set domain to which it belongs, and obtain the membership of the impact factor in the target fuzzy set domain to which it belongs. In one example, the vehicle power requirement P is affected by the factors m For example, when the vehicle requires power P m =105KW, the corresponding Figure 2 The horizontal axis is 0.7, which belongs to both the fuzzy set domain "medium to high PM" (membership degree is 0.5) and the fuzzy set domain "high B" (membership degree is 0.5), that is, when the vehicle demand power P m =105KW, the target fuzzy set domain to which it belongs is “medium to high PM” and “high B”.

[0050] In step S300, it is assumed that the vehicle power requirement P m =97.5KW (corresponding Figure 2 The horizontal coordinate is 0.65), the power battery state of charge BAT SOC =85% (corresponding to Figure 2 The horizontal coordinate is 0.85), and the required power P of the vehicle is determinedm The target fuzzy set domain is "medium to high PM" and "high B", and the power battery state of charge BAT SOC The target fuzzy set domain is "medium to high HS" and the fuzzy set domain is "high H". Then, combined with Table 1, the following fuzzy inference results are obtained: The first fuzzy inference result: vehicle required power P m The target fuzzy set domain is "medium to high PM" (membership degree 0.75), and the power battery state of charge BAT SOC When the target fuzzy set domain is “medium to high HS” (membership degree 0.75), the fuel cell output power P FC The fuzzy set domain it belongs to is "small MIN".

[0051] Second fuzzy inference result: vehicle required power P m The target fuzzy set domain is “medium to high PM” (membership degree 0.75), and the power battery state of charge BAT SOC The domain of the target fuzzy set is "high H" (membership degree 0.25), then the fuel cell output power P FC The fuzzy set domain it belongs to is "0OFF".

[0052] The third fuzzy inference result: the vehicle's required power P m The target fuzzy set domain is "High B" (membership degree 0.25), and the power battery state of charge BAT SOC When the target fuzzy set domain is “medium to high HS” (membership degree 0.75), the fuel cell output power P FC The fuzzy set domain it belongs to is "medium to small MEM".

[0053] Fourth fuzzy inference result: vehicle required power P m The target fuzzy set domain is "High B" (membership degree 0.25), and the power battery state of charge BAT SOC When the domain of the target fuzzy set is “high H” (membership degree 0.25), the fuel cell output power P FC The fuzzy set domain it belongs to is "0OFF".

[0054] That is, based on the vehicle's required power P m and power battery state of charge BAT SOC The different combinations of the target fuzzy set domain to which the fuel cell output power belongs determine the fuzzy set domain including "small MIN", "0OFF" and "medium to small MEM".

[0055] In step S400 , the default defuzzification method is any one of the maximum membership method, the centroid method or the weighted average method.

[0056] In a preferred embodiment, taking the above fuzzy result as an example, the steps of using the maximum membership method to defuzzify the fuel cell output power to obtain a predicted value of the fuel cell output power include: Vehicle power requirement P m The target fuzzy set domains are "medium to high PM" (membership degree 0.75) and "high B" (membership degree 0.25). According to the maximum membership method, the fuzzy set domain "medium to high PM" corresponding to the membership degree 0.75 is selected as the defuzzification calculation fuzzy set domain. Similarly, the power battery state of charge BAT SOC The corresponding defuzzification calculation fuzzy set domain is "medium to high HS". Further combined with the fuzzy rule table, the final fuzzy set domain to which the final predicted value of the fuel cell output power belongs is determined to be "small MIN", such as Figure 4 When the “small MIN” membership is 1, the corresponding fuel cell output power is 60KW×20%=12KW, that is, the fuel cell output power prediction value is determined to be 12KW. For the maximum membership method, the final fuel cell output power prediction value can only be the fuel cell output power corresponding to each fuzzy set domain with a membership of 1. Figure 4 For example, the final fuel cell output power can only be selected from 0, 12KW, 24KW, 36KW, 48KW and 60KW.

[0057] In another preferred embodiment, taking the above fuzzy result as an example, the steps of using the centroid method to defuzzify the fuel cell output power to obtain a predicted value of the fuel cell output power include: Determine the credible membership corresponding to each fuzzy inference result respectively. The credible membership represents the product of the corresponding membership of the target fuzzy set domain to which the influencing factor belongs. For example, taking the first fuzzy inference result as an example, the credible membership of the fuzzy set domain to which the fuel cell output power PFC belongs is "small MIN" = the vehicle demand power P m The membership degree of “medium to high PM” is 0.75×power battery state of charge BAT SOC The membership degree of “medium to high HS” is 0.75=0.5625.

[0058] Calculate the credible membership and value between the credible memberships corresponding to each fuzzy inference result.

[0059] Calculate the fuel cell output power P in the fuzzy inference result FCThe product of the fuel cell output power and the corresponding credible membership corresponding to the maximum membership degree (membership degree is 1) under the fuzzy set domain is defined as the calculation process quantity, and the ratio between the sum of the calculation process quantity and the sum of the credible membership degree is determined as the predicted value of the fuel cell output power.

[0060] Taking the above fuzzy results as an example, the credible membership corresponding to the first fuzzy inference result is 0.5625, and the calculation process quantity = 0.5625×12KW=6.75 KW. The credible membership corresponding to the second fuzzy inference result is 0.75×0.25=0.1875, and the calculation process quantity = 0.1875×0=0 KW. The credible membership corresponding to the third fuzzy inference result is 0.25×0.75=0.1875, and the calculation process quantity = 0.1875×24=4.5 KW. The credible membership corresponding to the fourth fuzzy inference result is 0.25×0.25=0.0625, and the calculation process quantity 0.0625×0=0 KW. Further, the credible membership sum value = 0.5625+0.1875+0.1875+0.0625=1, and the calculation process quantity sum value = 6.75 KW+0 KW+4.5 KW+0 KW=11.25 KW, fuel cell output power prediction value = 11.25 KW / 1=11.25 KW.

[0061] In a preferred embodiment, taking the above fuzzy result as an example, the steps of using the weighted average method to defuzzify the fuel cell output power to obtain a predicted value of the fuel cell output power include: The credible membership degree corresponding to the first fuzzy inference result is 0.5625. The second and fourth fuzzy inference results are consistent. The corresponding credible membership degrees are averaged to obtain (0.1875+0.0625) / 2=0.125. Furthermore, among the three fuzzy inference results, the fuzzy inference result with the largest credible membership degree is the first fuzzy inference result, and the predicted value of the fuel cell output power is determined to be 0.5625×12KW=6.75KW.

[0062] In a preferred embodiment, the method provided by the present application further includes: The fuel cell is controlled to output according to the predicted value, the actual operating value of the fuel cell output power is monitored and analyzed, and the fuzzy processing process is optimized according to the analysis result.

[0063] In a specific embodiment, the present application can collect the actual operating values ​​of multiple fuel cell output powers, and further combine them with the predicted values ​​of the fuel cell output power to evaluate the entire fuzzy processing process according to statistical evaluation parameters such as the mean square error. When the evaluation requirements are not met, the fuel cell output power and its corresponding influencing factors are re-fuzzy mapped (the fuzzy set domain is re-divided), and the fuzzy rule table is further readjusted until the final statistical evaluation parameters meet the evaluation requirements.

[0064] Based on the same application concept, the embodiments of the present application also provide a fuel cell energy management device based on fuzzy control corresponding to the fuel cell energy management method based on fuzzy control provided in the above embodiments. Since the principle of solving the problem by the device in the embodiments of the present application is similar to the fuel cell energy management method based on fuzzy control in the above embodiments of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0065] See also Figure 5 , Figure 5 FIG1 shows a functional module diagram of a fuel cell energy management device based on fuzzy control provided by an embodiment of the present application. Figure 5 As shown, the device includes: An influence factor determination module 500 is used to determine a current data value corresponding to an influence factor of the fuel cell output power; The fuzzification processing module 510 is used to perform fuzzification processing on the current data value corresponding to the influencing factor, and determine the target fuzzy set domain corresponding to the current data value of the influencing factor and its membership degree in the target fuzzy set domain; A fuzzy reasoning module 520 is configured to perform fuzzy reasoning based on the target fuzzy set domain corresponding to the influencing factor and a preset fuzzy rule table to determine the fuzzy set domain to which the fuel cell output power belongs. The preset fuzzy rule table describes the mapping relationship between different fuzzy set domains corresponding to the influencing factor and the fuzzy set domain to which the fuel cell output power belongs; The defuzzification module 530 is used to clarify the fuel cell output power using a preset defuzzification method based on the fuzzy set domain to which the fuel cell output power belongs and the membership degree of the influencing factor in the target fuzzy set domain to which it belongs, and determine the predicted value of the fuel cell output power.

[0066] Preferably, the fuzzy processing module is further used for: Obtain multiple fuzzy set domains corresponding to the impact factor and the membership function corresponding to each fuzzy set domain, wherein different fuzzy set domains correspond to different levels of the impact factor; According to the current data value of the impact factor, determine the target fuzzy set domain to which the impact factor belongs; Substitute the current data value of the impact factor into the membership function corresponding to the target fuzzy set domain to which it belongs, and obtain the membership of the impact factor on the target fuzzy set domain to which it belongs.

[0067] Based on the same application idea, please refer to Figure 6 , Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown. The electronic device 600 includes a processor 610, a memory 620, and a bus 630. The memory 620 stores machine-readable instructions executable by the processor 610. When the electronic device 600 is in operation, the processor 610 and the memory 620 communicate via the bus 630. The machine-readable instructions are executed by the processor 610 to execute the steps of the fuzzy control-based fuel cell energy management method provided in any of the above-mentioned embodiments.

[0068] Based on the same application concept, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps of the fuel cell energy management method based on fuzzy control provided in the above embodiment are executed.

[0069] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0070] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0071] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0072] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0073] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A fuel cell energy management method based on fuzzy control, characterized in that: The method comprises: Determine the current data value corresponding to the influencing factor of the fuel cell output power; Performing fuzzification processing on the current data value corresponding to the influencing factor to determine the target fuzzy set domain corresponding to the current data value of the influencing factor and its membership degree on the target fuzzy set domain; Performing fuzzy reasoning based on the target fuzzy set domain corresponding to the influencing factor and a preset fuzzy rule table to determine the fuzzy set domain to which the fuel cell output power belongs, wherein the preset fuzzy rule table describes the mapping relationship between different fuzzy set domains corresponding to the influencing factor and the fuzzy set domain to which the fuel cell output power belongs; According to the fuzzy set domain to which the fuel cell output power belongs and the membership degree of the influencing factors on the target fuzzy set domain to which they belong, the preset defuzzification method is used to clarify the fuel cell output power and determine the predicted value of the fuel cell output power.

2. The method according to claim 1, characterized in that The influencing factors include the required power of the vehicle and the state of charge of the power battery.

3. The method according to claim 2, characterized in that The current data value corresponding to the impact factor is determined by: Determine the current data value of the vehicle's required power based on the current accelerator pedal's depression intensity; Collect the current power battery voltage and current power battery current corresponding to the power battery; Based on the current power battery voltage and the current power battery current, a current data value of the power battery state of charge is calculated using a given state of charge calculation strategy.

4. The method according to claim 1, wherein The target fuzzy set corresponding to the current data value of the influencing factor and its membership on the target fuzzy set domain are determined in the following way: Obtain multiple fuzzy set domains corresponding to the impact factor and the membership function corresponding to each fuzzy set domain, wherein different fuzzy set domains correspond to different levels of the impact factor; According to the current data value of the impact factor, determine the target fuzzy set domain to which the impact factor belongs; Substitute the current data value of the impact factor into the membership function corresponding to the target fuzzy set domain to which it belongs, and obtain the membership of the impact factor on the target fuzzy set domain to which it belongs.

5. The method according to claim 1, wherein The preset defuzzification method is any one of the maximum membership method, the center of gravity method or the weighted average method.

6. The method according to claim 1, characterized in that The method further comprises: controlling the fuel cell to output according to the predicted value; The actual operating value of the fuel cell output power is monitored and analyzed, and the fuzzy processing process is optimized based on the analysis results.

7. A fuel cell energy management device based on fuzzy control, characterized in that: The device comprises: An influence factor determination module, used to determine a current data value corresponding to an influence factor of the fuel cell output power; A fuzzy processing module is used to perform fuzzy processing on the current data value corresponding to the influencing factor, and determine the target fuzzy set domain corresponding to the current data value of the influencing factor and its membership in the target fuzzy set domain; a fuzzy reasoning module, configured to perform fuzzy reasoning based on the target fuzzy set domain corresponding to the influencing factor and a preset fuzzy rule table to determine the fuzzy set domain to which the fuel cell output power belongs, wherein the preset fuzzy rule table describes the mapping relationship between different fuzzy set domains corresponding to the influencing factor and the fuzzy set domain to which the fuel cell output power belongs; The defuzzification module is used to clarify the fuel cell output power using a preset defuzzification method according to the fuzzy set domain to which the fuel cell output power belongs and the membership degree of the influencing factor in the target fuzzy set domain to which it belongs, and determine the predicted value of the fuel cell output power.

8. The device according to claim 7, characterized in that The fuzzy processing module is also used for: Obtain multiple fuzzy set domains corresponding to the impact factor and the membership function corresponding to each fuzzy set domain, wherein different fuzzy set domains correspond to different levels of the impact factor; According to the current data value of the impact factor, determine the target fuzzy set domain to which the impact factor belongs; Substitute the current data value of the impact factor into the membership function corresponding to the target fuzzy set domain to which it belongs, and obtain the membership of the impact factor on the target fuzzy set domain to which it belongs.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the fuel cell energy management method based on fuzzy control as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the fuel cell energy management method based on fuzzy control are executed.

Images