Blade battery temperature control method and system based on fuzzy neural network

Abstract

The application belongs to the technical field of battery temperature control, and provides a blade battery temperature control method and system based on a fuzzy neural network, which comprises the following steps: real-time monitoring of the temperature of a battery cell and phase change material, and real-time monitoring of the battery charging and discharging current by using a current transformer to obtain current data; preprocessing of the cell temperature data, phase change material temperature data and current data to obtain preprocessed data; inputting the preprocessed data as input variables into a fuzzy neural network for fuzzy processing, and generating a temperature adjustment instruction according to a preset working temperature range of the blade battery; temperature adjustment of the blade battery according to the temperature adjustment instruction, and real-time monitoring of temperature changes; and through the complex mapping capability of the fuzzy neural network, accurate control of the battery temperature is realized, temperature fluctuations are reduced, the consistency of battery performance is improved, and the temperature control performance of the blade battery is improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of battery temperature control, and in particular to a blade battery temperature control method and system based on a fuzzy neural network. BACKGROUND

[0002] With the rapid development and wide application of battery technology, especially the increasing importance of blade batteries in electric vehicles and energy storage systems, battery temperature control technology has become increasingly critical. Temperature has a significant impact on the performance, safety, and service life of batteries;

[0003] However, common blade battery temperature control techniques mainly include traditional PID control, model-based control, and simple threshold control methods. Although traditional PID control performs well in some linear systems, it has obvious limitations for blade batteries with complex nonlinear characteristics. The internal resistance, chemical reaction rate, and other parameters of the battery change significantly with temperature, charge / discharge rate, and battery aging, making it difficult for PID control to accurately establish a control model and accurately describe the complex nonlinear relationship between battery temperature and various influencing factors, resulting in low temperature control accuracy and large battery temperature fluctuations, which seriously affects the consistency of battery performance. For example, during high-rate charging, the battery generates heat rapidly, and traditional PID control may not be able to adjust the heat dissipation power in time, causing the battery temperature to be too high, thereby reducing the charge / discharge efficiency of the battery, and even causing safety hazards;

[0004] And the existing threshold control method is to start the heating or cooling equipment when the battery temperature reaches the preset threshold. This method is too simple and lacks comprehensive consideration of the battery temperature change trend and other related factors. On the one hand, since the threshold is usually fixed, it cannot adapt to the needs of the battery under different working conditions, and frequent starting and stopping of the heating or cooling equipment may occur, which not only increases the energy consumption and wear of the equipment, but also may cause the battery temperature to fluctuate sharply. On the other hand, when the battery temperature hovers around the threshold, simple threshold control cannot provide fine-tuned adjustments, making it difficult to ensure that the battery is always within the optimal operating temperature range, which is not conducive to extending the battery life and optimizing its performance;

[0005] Therefore, the blade battery temperature control method and system based on a fuzzy neural network are proposed by those skilled in the art, aiming to achieve more accurate, stable, and reliable temperature control through complex mapping capabilities and real-time feedback mechanisms, and to improve the temperature control performance of blade batteries. SUMMARY

[0006] To solve the above technical problems, the blade battery temperature control method and system based on a fuzzy neural network are provided to solve the problems raised in the background art.

[0007] According to a first aspect of the present disclosure, a blade battery temperature control method based on a fuzzy neural network is proposed, comprising the following steps:

[0008] S1, a thermistor sensor is used to sense temperature fluctuations through current changes, real-time monitoring of battery cell and phase change material temperature, obtaining cell temperature data and phase change material temperature data; and using a current transformer to monitor the battery charging and discharging current in real time, obtaining current data;

[0009] S2, after the cell temperature data, phase change material temperature data and current data are converted into electrical signals by a conditioning circuit, they are transmitted to an intelligent temperature remote detector for preprocessing, which includes cleaning, denoising and normalization, obtaining preprocessed data;

[0010] S3, the preprocessed data is used as an input variable and input into a fuzzy neural network for fuzzy processing, and a temperature adjustment instruction is generated according to the preset working temperature range of the blade battery;

[0011] S4, according to the temperature adjustment instruction, the temperature of the blade battery is adjusted, and the temperature change is monitored in real time, and the new temperature data is fed back to the fuzzy neural network to form a closed loop control.

[0012] Preferably, the preprocessed data is used as an input variable and input into a fuzzy neural network for fuzzy processing, and a temperature adjustment instruction is generated according to the preset working temperature range of the blade battery, comprising:

[0013] The cell temperature data before and after the time is calculated to obtain the temperature change rate ΔT;

[0014] The preprocessed cell temperature data, phase change material temperature data and current data are combined with the temperature change rate ΔT to form an input variable set X = [T a ,T b ,ΔT,I], wherein T a is the preprocessed cell temperature data, T b is the preprocessed phase change material temperature data, and I is the preprocessed current data;

[0015] The input variable set is input into a fuzzy neural network for fuzzy processing to obtain heating instruction intensity and heat dissipation instruction intensity; the fuzzy processing includes: obtaining a fuzzy result through a fuzzy process; obtaining a fuzzy membership function value of heating instruction intensity and heat dissipation instruction intensity through a fuzzy reasoning process; obtaining accurate heating instruction intensity and accurate heat dissipation instruction intensity through a defuzzification process;

[0016] According to the preset working temperature range (T min,T max The final temperature regulation command is generated by combining the intensity of the heating command and the intensity of the heat dissipation command.

[0017] Preferably, obtaining the fuzzification result through the fuzzification process includes:

[0018] The pre-processed cell temperature data T is calculated using the following formula. a Phase change material temperature data T b Membership functions of current data I and temperature change rate ΔT for their respective fuzzy subsets:

[0019]

[0020] Where, x i Let a be the i-th variable in the set of input variables X. i1 Let a be the lower bound of the range of the i-th variable. i2 Let a be the upper limit of the range of the i-th variable, and a i1 <a i2 ,μ(x i ) represents the membership degree;

[0021] Each element in the input variable set X is mapped to its corresponding fuzzy subset membership value to obtain the fuzzy vector μ = [μ1, μ2, ..., μ]. n ], where n is the total number of fuzzy subsets, and each μ i The degree to which an input variable belongs to a corresponding fuzzy subset is represented by the fuzzy vector μ = [μ1, μ2, ..., μ...]. n As a result of blurring.

[0022] Preferably, obtaining the fuzzy membership function values ​​of the heating command intensity and the heat dissipation command intensity through the fuzzy inference process includes:

[0023] Based on the fuzzification result μ=[μ1,μ2,...,μ n Based on the k-th rule in the established fuzzy rule base, the degree of satisfaction of the antecedent, α, is obtained. k =min(μ(x1),μ(x2),...,μ(x) n ));

[0024] Based on the degree of satisfaction of the antecedents, and combined with the k-th rule in the fuzzy rule base, the fuzzy membership function value of the heating command intensity is obtained as follows: Where H f For the fuzzy subset of heating command intensity in the rule consequent, The membership function for the fuzzy subset of heating command intensity;

[0025] Based on the degree of satisfaction of the antecedents, and combined with the k-th rule in the fuzzy rule base, the fuzzy membership function value of the heat dissipation command intensity is obtained as follows: Where C f For the fuzzy subset of heat dissipation command intensity in the rule consequent, The membership function for the fuzzy subset of the heat dissipation command intensity;

[0026] Based on the fuzzy subset membership function of the heating command intensity, the fuzzy membership function value of the heating command intensity is obtained. Based on the fuzzy subset membership function of the heat dissipation command intensity, the fuzzy membership function value of the heat dissipation command intensity is obtained.

[0027] Preferably, obtaining the precise heating command intensity and the precise heat dissipation command intensity through the defuzzification process includes:

[0028] Based on the fuzzy membership function value of the heating command intensity, it is converted into an accurate value using the centroid method, resulting in the accurate heating command intensity.

[0029] Based on the fuzzy membership function value of the heat dissipation command intensity, it is converted into an accurate value using the centroid method, resulting in the accurate heat dissipation command intensity.

[0030] Among them, H i C i μ represents the discrete values ​​in the universe of discourse of the heating command intensity and the cooling command intensity, respectively. H (H i ), μ C (C i ) represent the membership values ​​of the corresponding discrete values, and N and M represent the number of discrete values ​​in the universes of discourse for heating command intensity and heat dissipation command intensity, respectively.

[0031] Based on the precise heating command intensity H0 and the precise heat dissipation command intensity C0, and the preset operating temperature range (T) of the blade battery min ,T max This generates the final temperature adjustment command.

[0032] According to a second aspect of this disclosure, a blade battery temperature control system based on a fuzzy neural network is also proposed, comprising:

[0033] The data acquisition module is used to monitor the temperature of the battery cells and phase change materials in real time, and obtain cell temperature data and phase change material temperature data; and to use a current transformer to monitor the battery charging and discharging current in real time, and obtain current data.

[0034] A data preprocessing module is configured to transmit the data of the cell temperature, the phase change material temperature and the current to an intelligent temperature remote detector for preprocessing after converting the data into electrical signals through a conditioning circuit, and obtain preprocessed data

[0035] A fuzzy neural network control module is configured to input the preprocessed data as input variables into a fuzzy neural network for fuzzy processing, and generate a temperature adjustment instruction according to a preset working temperature range of the blade battery.

[0036] An execution module is configured to adjust the temperature of the blade battery according to the temperature adjustment instruction, start a heating or cooling device, and adjust the temperature.

[0037] A feedback module is configured to monitor the temperature change in real time, feed back new temperature data to the fuzzy neural network for re-fuzzy processing, generate a new temperature adjustment instruction, and form a closed-loop control through continuous circulation.

[0038] Compared with the prior art, the present application has the following beneficial effects:

[0039] 1. The present application combines fuzzy logic and neural network, utilizes fuzzy logic to process uncertain information, and utilizes the self-learning and self-adaptive characteristics of neural network, overcomes the problem of inaccurate description of complex nonlinear characteristics of the battery by traditional control methods, and through the complex mapping capability of the fuzzy neural network, can more accurately process the nonlinear relationship between the battery temperature and various influencing factors, realize accurate control of the battery temperature, reduce temperature fluctuation, and improve the consistency of battery performance.

[0040] 2. The present application has strong tolerance to data noise and uncertainty through fuzzy processing and rule-based reasoning, can maintain good control effect under different environmental conditions and battery aging states, and improves the stability and reliability of the system.

[0041] 3. The present application forms a closed-loop control through real-time monitoring and feedback, can timely adjust the control strategy according to the dynamic change of the battery temperature, has higher control precision and dynamic response capability, and better meets the strict requirements of the blade battery on temperature control under different use scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 The present application is a flow chart of a blade battery temperature control method based on a fuzzy neural network.

[0043] Figure 2 The present application is a block diagram of a blade battery temperature control system based on a fuzzy neural network. DETAILED DESCRIPTION

[0044] The embodiments of the present application will be further described in conjunction with the drawings and examples. The following examples are used to illustrate the present application, but cannot be used to limit the scope of the present application.

[0045] As shown in the accompanying Figure 1 :

[0046] Embodiment one: the present application provides a blade battery temperature control method based on fuzzy neural network, including the following steps:

[0047] S1, using a thermistor sensor, sensing temperature fluctuations through current changes, real-time monitoring the temperature of battery cells and phase change materials, obtaining cell temperature data and phase change material temperature data; and using a current transformer to monitor the battery charging and discharging current in real time, obtaining current data; wherein redundant sensors or multiple types of sensors are added on the basis of the thermistor sensor to cross-verify the data, thereby avoiding the risk of single-point failure.

[0048] S2, after the cell temperature data, phase change material temperature data and current data are converted into electrical signals by the conditioning circuit, they are transmitted to the intelligent temperature remote detector for preprocessing, obtaining the preprocessed data;

[0049] S3, the preprocessed data is used as an input variable and input into the fuzzy neural network for fuzzy processing, and a temperature adjustment instruction is generated according to the preset working temperature range of the blade battery; by inputting the preprocessed data as an input variable into the fuzzy neural network for fuzzy processing, and generating a temperature adjustment instruction according to the preset working temperature range of the blade battery, including:

[0050] The cell temperature data before and after the calculation is obtained, and the temperature change rate ΔT is obtained;

[0051] The preprocessed cell temperature data, phase change material temperature data and current data are combined with the temperature change rate ΔT to form an input variable set X=[T a ,T b ,ΔT,I], wherein T a is the preprocessed cell temperature data, T b is the preprocessed phase change material temperature data, and I is the preprocessed current data;

[0052] The input variable set is input into the fuzzy neural network for fuzzy processing to obtain the heating instruction intensity and the heat dissipation instruction intensity; the fuzzy processing includes fuzzy process, fuzzy reasoning process and de-fuzzy process;

[0053] The heating instruction intensity and the heat dissipation instruction intensity generate the final temperature adjustment instruction according to the preset working temperature range (T min ,T max ) of the blade battery.

[0054] The fuzzification process includes:

[0055] The pre-treated cell temperature data T is calculated using the following formula. a Phase change material temperature data T b Membership functions of current data I and temperature change rate ΔT for their respective fuzzy subsets:

[0056]

[0057] Where, x i Let a be the i-th variable in the set of input variables X. i1 Let a be the lower bound of the range of the i-th variable. i2 Let a be the upper limit of the range of the i-th variable, and a i1 <a i2 ,μ(x i ) represents the membership degree;

[0058] Map each element in the input variable set X to its corresponding fuzzy subset membership value to obtain the fuzzy vector μ = [μ1, μ2, ..., μ n ], where n is the total number of fuzzy subsets, and each μ i This indicates the degree to which the input variable belongs to the corresponding fuzzy subset. The fuzzy vector is μ = [μ1, μ2, ..., μ...]. n As a result of blurring.

[0059] The collected precise data is converted into fuzzy sets, and the numerical values ​​are mapped to the corresponding fuzzy linguistic variables by defining membership functions. This enables the handling of uncertain and imprecise information, which is more in line with the complex situation in actual battery operation, enhances the adaptability to different operating conditions, and avoids overly strict threshold judgments that may occur in precise control.

[0060] The fuzzy reasoning process includes:

[0061] Based on the fuzzification result μ=[μ1,μ2,...,μ n Based on the k-th rule in the established fuzzy rule base, the degree of satisfaction of the antecedent, α, is obtained. k =min(μ(x1),μ(x2),...,μ(x) n ));

[0062] The fuzzy membership function value of the heating command intensity corresponding to the k-th rule in the fuzzy rule base is: Where H f For the fuzzy subset of heating command intensity in the rule consequent, The membership function for the fuzzy subset of heating command intensity;

[0063] The fuzzy membership function value of the heat dissipation instruction intensity corresponding to the kth rule in the fuzzy rule base is: Where C f is the fuzzy subset of the heat dissipation instruction intensity in the rule consequent, is the membership function of the heat dissipation instruction intensity fuzzy subset;

[0064] The fuzzy membership function value of the heating instruction intensity is The fuzzy membership function value of the heat dissipation instruction intensity is

[0065] According to the expert knowledge and experience in the field of batteries, a series of fuzzy rules are formulated to describe the relationship between the input variables and the output variables (such as heating or heat dissipation instructions), which provides the basis for fuzzy reasoning and enables reasonable temperature regulation decisions to be made according to different battery states. Based on the fuzzified input and the fuzzy rule base, fuzzy reasoning algorithms are used to obtain fuzzy output results, i.e., fuzzy decisions for battery temperature regulation. Through the fuzzy reasoning process, the influence of multiple input variables is considered comprehensively, enabling more accurate temperature regulation decisions to be made under complex battery operating conditions, avoiding the limitations of single variable control, and improving the accuracy and rationality of temperature control.

[0066] Wherein, the defuzzification process includes:

[0067] The fuzzy membership function values of the heating instruction intensity and the heat dissipation instruction intensity are converted into precise values using the barycentric method;

[0068] The precise heating instruction intensity obtained is

[0069] The precise heat dissipation instruction intensity obtained is

[0070] Wherein, H i , C i are discrete values in the heating instruction intensity and heat dissipation instruction intensity domains, respectively, μ H (H i ), μ C (C i ) are membership values corresponding to the discrete values, and N and M are the number of discrete values in the heating instruction intensity and heat dissipation instruction intensity domains, respectively.

[0071] According to the precise heating instruction intensity H0 and the precise heat dissipation instruction intensity C0, as well as the preset operating temperature range (T min , T max), and generate final temperature regulation instructions. The fuzzy output result is converted into an accurate control amount, such as a specific heating power or a cooling fan speed, so that the actual execution mechanism can regulate the temperature of the battery according to the control amount, that is, by converting the fuzzy decision into an accurate control signal that can be actually executed, the conversion from fuzzy logic to actual physical control is realized, and the temperature regulation has operability.

[0072] S4, according to the temperature regulation instructions, regulating the temperature of the blade battery, and monitoring the temperature change in real time, feeding the new temperature data into the fuzzy neural network to form a closed loop control;

[0073] When the heating instruction intensity H0 generated by the fuzzy neural network is greater than the set threshold and the current battery temperature T current is lower than the lower limit T min of the preset working temperature range, start the heating device; during the heating process, the battery temperature change Δt heat is monitored in real time, and after a time Δt, the battery temperature change Δt current is estimated by the heat transfer equation, the actual measured battery temperature T new is continuously updated to obtain new temperature data, and the new temperature data T current is collected by the thermistor sensor and transmitted to the fuzzy neural network;

[0074] When the cooling instruction intensity C0 is greater than the set threshold and the current battery temperature T max is higher than the upper limit T new of the preset working temperature range, start the cooling device; during the cooling process, the battery temperature change is monitored in real time to obtain new temperature data, and the new temperature data T new is collected by the thermistor sensor and transmitted to the fuzzy neural network;

[0075] The fuzzy neural network re-performs the processes of fuzzification, fuzzy reasoning and defuzzification according to the newly fed back temperature data T new in combination with the current data I, generates new temperature regulation instructions, and the whole process is continuously cycled to form a closed loop control, so that the battery temperature is always maintained within the preset working temperature range.

[0076] According to the control amount obtained by defuzzification, the heating or cooling device is driven to regulate the temperature of the blade battery, and the temperature change is monitored in real time, the new temperature data is fed back to the fuzzy neural network to form a closed loop control, so that the battery temperature can be quickly and accurately stabilized within the preset working temperature range, the safety and service life of the battery are improved, and through the closed loop control, the battery state can be responded in time, the temperature is dynamically adjusted, and the stability and reliability of the temperature control are ensured.

[0077] Through real-time monitoring and feedback to form a closed-loop control, the control strategy can be adjusted in time according to the dynamic changes of the battery temperature, and compared with some open-loop control or simple feedback control methods, it has higher control accuracy and dynamic response ability, and better meets the strict requirements of the blade battery on temperature control in different use scenarios.

[0078] As shown in the accompanying Figure 2 :

[0079] Embodiment two: the application provides a blade battery temperature control system based on a fuzzy neural network, comprising:

[0080] A data acquisition module is configured to monitor the temperatures of the battery cells and the phase change material in real time, obtain cell temperature data and phase change material temperature data, and use a current transformer to monitor the battery charging and discharging current in real time to obtain current data;

[0081] A data preprocessing module is configured to convert the cell temperature data, phase change material temperature data and current data into electrical signals through a conditioning circuit, and then transmit the electrical signals to an intelligent temperature remote detector for preprocessing to obtain preprocessed data

[0082] A fuzzy neural network control module is configured to input the preprocessed data as input variables into the fuzzy neural network for fuzzy processing, and generate a temperature adjustment instruction according to a preset working temperature range of the blade battery;

[0083] An execution module is configured to adjust the temperature of the blade battery according to the temperature adjustment instruction, start a heating or cooling device, and adjust the temperature;

[0084] A feedback module is configured to monitor the temperature changes in real time, feed back the new temperature data to the fuzzy neural network, re-perform fuzzy processing, generate a new temperature adjustment instruction, and continuously cycle to form a closed-loop control.

[0085] As can be seen from the above, through the complex mapping capability of the fuzzy neural network, the nonlinear relationship between the battery temperature and various influencing factors can be more accurately processed, the battery temperature can be accurately controlled, the temperature fluctuation can be reduced, and the consistency of the battery performance can be improved; the fuzzy processing and the rule-based reasoning method make the system have strong tolerance to data noise and uncertainty, can maintain good control effect under different environmental conditions and battery aging states, and improve the stability and reliability of the system; accurate temperature control helps to keep the battery within a suitable working temperature range, reduces the unevenness of the chemical reaction inside the battery, reduces the battery aging speed, prolongs the service life of the battery, improves the charging and discharging efficiency of the battery, and optimizes the overall performance of the battery.

[0086] Example three: based on the blade battery temperature control method provided in example one, by introducing an online learning mechanism, combining real-time data to dynamically adjust neural network weights and fuzzy rules, thereby improving the long-term adaptability of the system; that is, using historical data to train the model, thereby realizing adaptive temperature control in the full temperature range.

[0087] And in the case of input variables: battery temperature data, phase change material temperature data, current data and temperature change rate, increase environmental humidity, battery state of charge and other potential influencing factors as supplementary multi-source data for input, thereby increasing the model's ability to analyze complex working conditions.

[0088] Experimental example: in extremely cold weather, innovative PTC double-cycle preheating technology, relying on three-channel heating module and symmetrical pipeline to achieve 40% efficiency fast heating of the battery at-30°C. Through the intelligent switching of the two-way valve, the cooling liquid flow direction is guided to the heat dissipation module for forced cooling at high temperature, and the PTC is connected for precise heating at low temperature, forming a full-range temperature control closed loop covering-30°C to 60°C, and finally controlling the battery temperature fluctuation within ±2°C, with a comprehensive energy efficiency improvement of 25%. At the same time, with the help of fuzzy control algorithm and mature neural network, the optimal power of PTC is searched when heating, and the optimal flow of cooling liquid is determined when dissipating heat, greatly improving the temperature control efficiency, reducing energy consumption, and prolonging the service life of the battery.

[0089] Importantly, it should be noted that the constructions and arrangements of the present application shown in the various different example embodiments are merely illustrative. Although only a few embodiments have been described in detail in this disclosure, those skilled in the art will appreciate that many modifications are possible without materially departing from the novel teachings and advantages of the subject matter described in this application. Other substitutions, modifications, changes and omissions can be made in the design, operation and arrangement of the example embodiments without departing from the scope of the present invention. Accordingly, the present invention is not restricted to particular embodiments described, but extends to various modifications that still fall within the scope of the appended claims.

[0090] Furthermore, in order to provide a brief description of the example embodiments, not all features of the actual embodiments can be described (i.e., those features that are not relevant to the best mode of carrying out the invention currently under consideration, or those features that are not relevant to the implementation of the invention).

[0091] It should be understood that in the development of any actual implementation, numerous implementation-specific decisions can be made. Such development efforts might be complex and time-consuming, but would nevertheless be a routine undertaking for those of ordinary skill in the art having the benefit of this disclosure.

[0092] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, without departing from the spirit and scope of the technical solutions of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. A method for controlling the temperature of a blade battery based on a fuzzy neural network, characterized by, The method comprises the following steps: S1, using a thermistor sensor to sense temperature fluctuations through current changes, real-time monitoring of the temperature of the battery cell and the phase change material, obtaining cell temperature data and phase change material temperature data; and using a current transformer to monitor the battery charging and discharging current in real time, obtaining current data; S2, after the cell temperature data, phase change material temperature data and current data are converted into electrical signals by a conditioning circuit, they are transmitted to an intelligent temperature remote detector for preprocessing, which includes cleaning, denoising and normalization, obtaining preprocessed data; S3, the preprocessed data is input into a fuzzy neural network for fuzzy processing, and a temperature adjustment instruction is generated according to the preset working temperature range of the blade battery; S4, according to the temperature adjustment instruction, the temperature of the blade battery is adjusted, and the temperature change is monitored in real time, and the new temperature data is fed back to the fuzzy neural network to form a closed loop control; The S3 further comprises: The temperature change rate is obtained by calculating the temperature data of the battery cell at the before and after time points ; The preprocessed cell temperature data, phase change material temperature data and current data are combined with the temperature change rate to form an input variable set wherein is the preprocessed cell temperature data, is the preprocessed phase change material temperature data, is the preprocessed current data; The input variable set is input into the fuzzy neural network for fuzzy processing to obtain the heating instruction intensity and the heat dissipation instruction intensity; the fuzzy processing comprises: obtaining a fuzzy result through a fuzzy process; obtaining the fuzzy membership function value of the heating instruction intensity and the heat dissipation instruction intensity through a fuzzy reasoning process; obtaining the accurate heating instruction intensity and the accurate heat dissipation instruction intensity through a defuzzification process; According to preset working temperature range of blade battery generate final temperature adjustment instructions in combination with the heating instruction intensity and the heat dissipation instruction intensity.

2. The blade battery temperature control method based on a fuzzy neural network according to claim 1, wherein, The fuzzy result obtained through the fuzzy process comprises: The pre-processed cell temperature data is calculated by the following equation , phase change material temperature data , current data and temperature change rate For the membership function of each fuzzy subset: ； in, For the set of input variables The Middle One variable, For the first The lower bound of the range of a variable For the first The upper limit of the range of each variable, and , Membership degree; each element of the input variable set is mapped into a corresponding fuzzy subset membership value, respectively, to obtain a fuzzy vector where is the total number of fuzzy subsets, each represents the degree to which the input variable belongs to the corresponding fuzzy subset, and the fuzzy vector is the result of the fuzzification.

3. The blade battery temperature control method based on a fuzzy neural network according to claim 2, wherein, The fuzzy reasoning process comprises: According to the fuzzification result , in combination with the first rule in the set fuzzy rule base , the degree of satisfaction of the antecedent is obtained. Based on the degree of satisfaction of the antecedent, combined with the first rule in the fuzzy rule base, the fuzzy membership function value of the heating instruction intensity is obtained as: Wherein is the fuzzy subset of the heating instruction intensity in the rule consequent, is the fuzzy subset membership function of the heating instruction intensity. Based on the degree of satisfaction of the antecedent, combined with the first rule in the fuzzy rule base, the fuzzy membership function value of the heat dissipation instruction intensity is obtained as: , wherein is the fuzzy subset of the heat dissipation instruction intensity in the rule consequent, is the fuzzy subset membership function of the heat dissipation instruction intensity. According to the heating instruction intensity fuzzy subset membership function, the fuzzy membership function value of the heating instruction intensity is obtained as ; and according to the heat dissipation instruction intensity fuzzy subset membership function, the fuzzy membership function value of the heat dissipation instruction intensity is obtained as .

4. The blade battery temperature control method based on a fuzzy neural network according to claim 3, wherein, The defuzzification process comprises: According to the fuzzy membership function value of the heating instruction intensity, the precise value is converted by the barycentric method, and the precise heating instruction intensity obtained is ; According to the fuzzy membership function value of the heat dissipation instruction intensity, the accurate value is converted through the barycentric method, and the accurate heat dissipation instruction intensity is ; wherein, are discrete values in the heating command intensity and heat sink command intensity universe of discourse, respectively, , are membership values corresponding to the discrete values, respectively, are the number of discrete values in the heating command intensity and heat sink command intensity universe of discourse, respectively. According to the precise heating instruction intensity and the precise heat dissipation instruction intensity , and the preset working temperature range of the blade battery , generate the final temperature adjustment instruction.

5. The blade battery temperature control system based on fuzzy neural network, characterized in that, The data acquisition module is used to monitor the temperature of the battery cell and the phase change material in real time, and obtain the cell temperature data and the phase change material temperature data; The current transformer is used to monitor the battery charging and discharging current in real time, and obtain the current data; The data preprocessing module is used to convert the cell temperature data, phase change material temperature data and current data into electrical signals through a conditioning circuit, and then transmit them to an intelligent temperature remote detector for preprocessing, obtaining preprocessed data; The fuzzy neural network control module is used to input the preprocessed data as input variables into a fuzzy neural network for fuzzy processing, and generate a temperature adjustment instruction according to the preset working temperature range of the blade battery; The input variable set is obtained by combining the preprocessed data and the temperature change rate, and the input variable set is input into the fuzzy neural network for fuzzy processing to obtain the heating instruction intensity and the heat dissipation instruction intensity; the final temperature adjustment instruction is generated according to the preset working temperature range of the blade battery combined with the heating instruction intensity and the heat dissipation instruction intensity; The execution module is used to adjust the temperature of the blade battery according to the temperature adjustment instruction, start the heating or heat dissipation equipment, and adjust the temperature. ​ A feedback module is configured to monitor the temperature change in real time, feed new temperature data to the fuzzy neural network, re-perform the fuzzification, generate new temperature regulation instructions, and continuously cycle to form a closed-loop control.

Images