Battery pulse heating method and system

Abstract

The invention relates to the technical field of battery pulse heating, and provides a battery pulse heating method and system, and the method comprises the following steps: collecting battery temperature data and environment temperature data in real time; based on the battery temperature data and the environment temperature data, identifying current working state data of the battery, and calculating pulse parameters of the battery according to the current working state data, the battery temperature data and the environment temperature data; performing pulse heating on the battery through the pulse parameter, recording a heating parameter of the battery under the current working condition, and optimizing the heating parameter of the battery based on the heating effect of the battery; monitoring health state data of the battery in real time, and performing fault diagnosis on the battery based on the health state data to obtain a fault diagnosis result; and performing protection control on the battery according to the fault diagnosis result. Accurate recognition, fault diagnosis and protection control of the working state of the battery are achieved, and the heating efficiency and safety of the battery are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery pulse heating, and in particular to a battery pulse heating method and system. Background Art

[0002] In fields such as electric vehicles and energy storage systems, the low-temperature performance and safety of batteries are key issues. When the ambient temperature is low, the battery's charge and discharge performance will drop significantly, which not only affects the service life but also may pose a safety hazard. Although existing technologies have developed a variety of battery heating methods, such as heating films, liquid heating and other traditional heating methods, these methods still have obvious shortcomings. In actual applications, the operating environment and status of the battery are dynamically changing, and existing technologies lack an adaptive adjustment mechanism and cannot flexibly adjust the heating parameters according to the real-time status of the battery.

[0003] Traditional heating methods often use constant power heating, lack the ability to perceive the real-time status of the battery and intelligently adjust, which can easily cause local overheating or uneven heating, affecting battery performance and life. The existing heating control strategy is relatively simple and fails to fully consider multi-dimensional factors such as the battery's working status and ambient temperature, making it difficult to achieve the optimal heating effect. The existing protection control scheme often uses fixed thresholds, which are difficult to adapt to the protection needs under different working conditions. There are problems of untimely protection or excessive protection, resulting in low battery heating efficiency, affecting battery performance, and increasing safety risks. Summary of the Invention

[0004] In view of this, the present invention proposes a battery pulse heating method and system, which solves the problem in the prior art that the battery heating efficiency is low, which affects the battery performance and increases the safety risk.

[0005] The technical solution of the present invention is implemented as follows: In a first aspect, the present invention provides a battery pulse heating method, comprising the following steps:

[0006] Real-time collection of battery temperature data and ambient temperature data;

[0007] identifying current operating state data of the battery based on the battery temperature data and the ambient temperature data, and calculating pulse parameters of the battery based on the current operating state data, the battery temperature data, and the ambient temperature data, the pulse parameters including an optimal pulse frequency and a duty cycle;

[0008] Pulse heating the battery using the pulse parameters, recording the heating parameters of the battery under the current operating condition, and optimizing the heating parameters of the battery based on the heating effect of the battery;

[0009] Real-time monitoring of battery health status data, including current, voltage, and temperature parameters, and battery fault diagnosis based on the health status data to obtain a fault diagnosis result;

[0010] The battery is protected and controlled according to the fault diagnosis result, and the protection control includes overcurrent protection, overvoltage protection and temperature abnormality protection.

[0011] Based on the above technical solution, preferably, the real-time collection of battery temperature data and ambient temperature data includes:

[0012] A temperature sensor is installed on the battery surface and continuously collects raw battery temperature data based on a preset temperature sampling frequency. The raw battery temperature data is subjected to noise filtering and signal amplification by a signal processing unit to obtain processed battery temperature data.

[0013] An ambient temperature sensor is placed around the battery, and raw ambient temperature data of the battery is collected based on the ambient temperature sensor. The raw ambient temperature data is integrated through a data fusion algorithm to obtain ambient temperature data.

[0014] On the basis of the above technical solution, preferably, identifying the current working status data of the battery based on the battery temperature data and the ambient temperature data includes:

[0015] Based on the battery temperature data and the ambient temperature data, using a data analysis algorithm to identify current operating status data of the battery;

[0016] Building a battery operating state prediction model based on a machine learning model, and training and analyzing the battery temperature data and the ambient temperature data to accurately identify the current operating state data of the battery;

[0017] The calculation formula of the battery working state prediction model is:

[0018]

[0019] Among them, S state is the current working status data score of the battery, σ(·) is the sigmoid activation function, I is the number of hidden layers of the neural network, and W i is the weight matrix of the i-th hidden layer, b i is the bias vector of the i-th hidden layer, x is the battery temperature data and ambient temperature data input to the prediction model, f(·) is the nonlinear activation function, W i-1 and b i-1 are the weight matrix and bias vector of the i-1th hidden layer, λ is the regularization parameter, ||W i || 2 Wi The squared norm of .

[0020] On the basis of the above technical solution, preferably, the pulse parameters of the battery are calculated according to the current working state data, the battery temperature data and the ambient temperature data, and the pulse parameters include the optimal pulse frequency and duty cycle, including:

[0021] Calculating pulse parameters of the battery based on the current working state data, the battery temperature data, and the ambient temperature data, the pulse parameters including an optimal pulse frequency and a duty cycle;

[0022] The calculation formula for the optimal pulse frequency is:

[0023]

[0024] Among them, K1, K2, K3 and K4 are respectively the battery temperature influence coefficient, the ambient temperature influence coefficient, the status score sensitivity influence coefficient and the status score threshold, f optimal is the optimal pulse frequency, T battery is the battery temperature, T environment is the ambient temperature, S state Score the battery's current working status data;

[0025] The duty cycle is calculated as:

[0026]

[0027] Among them, D optimal is the optimal duty cycle, K5 and K6 are the duty cycle reference coefficient and state influence coefficient respectively, T battery is the battery temperature, T reference is the reference temperature value, S state Score the battery's current working status data.

[0028] Based on the above technical solution, preferably, performing pulse heating on the battery using the pulse parameters, recording the heating parameters of the battery under the current working condition, and optimizing the heating parameters of the battery based on the heating effect of the battery includes:

[0029] Pulse heating the battery using the pulse parameters, including adjusting the output of the pulse signal according to the optimal pulse frequency and duty cycle, and dynamically adjusting the output frequency and duty cycle of the pulse signal based on real-time temperature feedback of the battery;

[0030] Record the heating parameters of the battery under the current operating conditions, perform data analysis on the heating parameters, identify abnormal conditions during the heating process, and adjust the heating strategy based on the results of the data analysis.

[0031] Based on the above technical solution, preferably, the health status data of the battery is monitored in real time, and the health status data includes current, voltage and temperature parameters. The battery fault diagnosis is performed based on the health status data, and the fault diagnosis results obtained include:

[0032] The sensor collects current data, voltage data, and temperature data in real time at a sampling frequency of no less than 100 times per second, and uses a low-pass filtering algorithm to pre-process the collected current data, voltage data, and temperature data to obtain the battery health status data;

[0033] The sampling calculation formula for current data is:

[0034]

[0035] Among them, I filtered (t) is the current data of time step t after preprocessing, I raw (t) is I filtered (t) The corresponding raw current data, γ is the filter coefficient, and τ is the integral variable;

[0036] Building a fault diagnosis model based on the support vector machine algorithm, classifying and analyzing the health status data through the fault diagnosis model, obtaining the battery fault type, and outputting the corresponding fault diagnosis results;

[0037] The calculation formula of the fault diagnosis model is:

[0038]

[0039] Among them, f0(·) is the classification function, α j is the weight coefficient of the jth support vector, J is the number of support vectors, K(y,y j ) is the kernel function, and b is the fault diagnosis bias.

[0040] On the basis of the above technical solution, preferably, protection control of the battery is performed according to the fault diagnosis result, and the protection control includes overcurrent protection, overvoltage protection and temperature abnormality protection, including:

[0041] Establishing a battery protection control strategy based on the fault diagnosis results, the battery protection control strategy includes an overcurrent protection threshold, an overvoltage protection threshold, and a temperature anomaly protection threshold. An adaptive threshold adjustment algorithm is used to dynamically adjust the overcurrent protection threshold, overvoltage protection threshold, and temperature anomaly protection threshold according to the operating status of the battery. The overcurrent protection threshold, the overvoltage protection threshold, and the temperature anomaly protection threshold are mapped to the remaining capacity, charge and discharge status, and ambient temperature of the battery, respectively.

[0042] Real-time monitoring of battery parameters and implementation of corresponding protection control measures, including: when the current exceeds the overcurrent protection threshold, current limiting or cutting off measures are implemented; when the voltage exceeds the overvoltage protection threshold, voltage reduction or charging disconnection measures are implemented; when the temperature exceeds the temperature abnormality protection threshold, power reduction or cooling measures are implemented.

[0043] In a second aspect, the present invention further provides a battery pulse heating system, the system comprising:

[0044] Data acquisition module, used to collect battery temperature data and ambient temperature data in real time;

[0045] a state identification module, configured to identify current operating state data of the battery based on the battery temperature data and the ambient temperature data, and calculate pulse parameters of the battery based on the current operating state data, the battery temperature data, and the ambient temperature data, the pulse parameters including an optimal pulse frequency and a duty cycle;

[0046] a heating optimization module, configured to pulse heat the battery using the pulse parameters, record the heating parameters of the battery under the current operating condition, and optimize the heating parameters of the battery based on the heating effect of the battery;

[0047] A fault diagnosis module is used to monitor the health status data of the battery in real time, wherein the health status data includes current, voltage and temperature parameters, and perform fault diagnosis on the battery based on the health status data to obtain a fault diagnosis result;

[0048] The protection control module is used to perform protection control on the battery according to the fault diagnosis result. The protection control includes overcurrent protection, overvoltage protection and temperature abnormality protection.

[0049] In a third aspect, the present invention further provides an electronic device comprising: at least one processor, at least one memory, a communication interface, and a bus;

[0050] The processor, memory, and communication interface communicate with each other via the bus. The memory stores program instructions that can be executed by the processor. The processor calls the program instructions to implement steps such as a battery pulse heating method.

[0051] In a fourth aspect, the present invention further provides a computer-readable storage medium storing computer instructions, wherein the computer instructions enable a computer to implement steps of a battery pulse heating method.

[0052] The battery pulse heating method and system of the present invention have the following beneficial effects compared with the prior art:

[0053] (1) By collecting battery temperature, ambient temperature and battery health status data in real time, and calculating the optimal pulse parameters based on the battery health status data for adaptive heating control, the support vector machine algorithm is used to build a fault diagnosis model. Combined with the adaptive threshold adjustment algorithm, the heating strategy is optimized by continuously recording and analyzing heating parameters, improving the heating effect, and realizing accurate identification of the battery working status, fault diagnosis and protection control. It can respond to protection needs under different working conditions in a timely manner, thereby improving the heating efficiency and safety of the battery;

[0054] (2) Through the machine learning model built based on battery temperature data and ambient temperature data, the current working state of the battery is identified and the optimal pulse parameters, including pulse frequency and duty cycle, are calculated, thereby improving the accuracy and efficiency of battery pulse heating and ensuring that the battery is heated in the best state, thereby optimizing the heating effect, extending the battery life, and improving the reliability of battery pulse heating;

[0055] (3) By applying high-frequency data acquisition and low-pass filtering algorithms, the battery health status data, including current, voltage and temperature parameters, can be monitored in real time and accurately. A fault diagnosis model is constructed through the support vector machine algorithm to accurately identify the battery fault type, thereby improving the accuracy of fault diagnosis and providing important guarantees for the safe operation of the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 This is a flow chart of a battery pulse heating method of the present invention;

[0058] Figure 2 This is a structural diagram of a battery pulse heating system of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0060] See also Figure 1The present invention provides a battery pulse heating method, comprising the following steps:

[0061] Real-time collection of battery temperature data and ambient temperature data;

[0062] identifying current operating state data of the battery based on the battery temperature data and the ambient temperature data, and calculating pulse parameters of the battery based on the current operating state data, the battery temperature data, and the ambient temperature data, the pulse parameters including an optimal pulse frequency and a duty cycle;

[0063] Pulse heating the battery using the pulse parameters, recording the heating parameters of the battery under the current operating condition, and optimizing the heating parameters of the battery based on the heating effect of the battery;

[0064] Real-time monitoring of battery health status data, including current, voltage, and temperature parameters, and battery fault diagnosis based on the health status data to obtain a fault diagnosis result;

[0065] The battery is protected and controlled according to the fault diagnosis result, and the protection control includes overcurrent protection, overvoltage protection and temperature abnormality protection.

[0066] Specifically, this embodiment collects battery temperature, ambient temperature and battery health status data in real time, calculates the optimal pulse parameters based on the battery health status data for adaptive heating control, adopts the support vector machine algorithm to build a fault diagnosis model, and combines it with the adaptive threshold adjustment algorithm to continuously record and analyze heating parameters, optimize the heating strategy, improve the heating effect, and achieve accurate identification of the battery working status, fault diagnosis and protection control, which can respond to the protection needs under different working conditions in a timely manner, thereby improving the heating efficiency and safety of the battery.

[0067] The real-time collection of battery temperature data and ambient temperature data includes:

[0068] A temperature sensor is installed on the battery surface and continuously collects raw battery temperature data based on a preset temperature sampling frequency. The raw battery temperature data is subjected to noise filtering and signal amplification by a signal processing unit to obtain processed battery temperature data.

[0069] An ambient temperature sensor is placed around the battery, and raw ambient temperature data of the battery is collected based on the ambient temperature sensor. The raw ambient temperature data is integrated through a data fusion algorithm to obtain ambient temperature data to compensate for the ambient temperature monitoring error caused by a single sensor.

[0070] Specifically, this embodiment can obtain more accurate battery temperature data by installing a temperature sensor on the battery surface, continuously collecting data based on a preset temperature sampling frequency, and performing noise filtering and signal amplification in combination with a signal processing unit.

[0071] By placing ambient temperature sensors around the battery, collecting raw ambient temperature data, and integrating it through a data fusion algorithm, the ambient temperature monitoring error caused by a single sensor can be compensated, thereby improving the reliability and accuracy of the ambient temperature data.

[0072] The identifying the current working state data of the battery based on the battery temperature data and the ambient temperature data includes:

[0073] Based on the battery temperature data and the ambient temperature data, using a data analysis algorithm to identify current operating status data of the battery;

[0074] Building a battery operating state prediction model based on a machine learning model, training and analyzing the battery temperature data and the ambient temperature data to accurately identify the current operating state data of the battery, the current operating state data including the charge and discharge state, load condition, and remaining life prediction;

[0075] The calculation formula of the battery working state prediction model is:

[0076]

[0077] Among them, S state is the current working status data score of the battery, σ(·) is the sigmoid activation function, I is the number of hidden layers of the neural network, and W i is the weight matrix of the i-th hidden layer, b i is the bias vector of the i-th hidden layer, x is the battery temperature data and ambient temperature data input to the prediction model, f(·) is the nonlinear activation function, W i-1 and b i-1 are the weight matrix and bias vector of the i-1th hidden layer, λ is the regularization parameter, ||W i || 2 W i The squared norm of .

[0078] Calculating the pulse parameters of the battery according to the current working state data, the battery temperature data, and the ambient temperature data, wherein the pulse parameters include an optimal pulse frequency and a duty cycle.

[0079] Calculating pulse parameters of the battery based on the current working state data, the battery temperature data, and the ambient temperature data, the pulse parameters including an optimal pulse frequency and a duty cycle;

[0080] The calculation formula for the optimal pulse frequency is:

[0081]

[0082] Among them, K1, K2, K3 and K4 are respectively the battery temperature influence coefficient, the ambient temperature influence coefficient, the status score sensitivity influence coefficient and the status score threshold, f optimal is the optimal pulse frequency, T battery is the battery temperature, T environment is the ambient temperature, S state Score the battery's current working status data;

[0083] The duty cycle is calculated as:

[0084]

[0085] Among them, D optimal is the optimal duty cycle, K5 and K6 are the duty cycle reference coefficient and state influence coefficient respectively, T battery is the battery temperature, T reference is the reference temperature value, S state Score the battery's current working status data.

[0086] Specifically, this embodiment uses data analysis algorithms and machine learning models based on battery temperature data and ambient temperature data to accurately identify the current working status data of the battery, including key information such as the battery's charge and discharge status, load conditions, and remaining life prediction.

[0087] By utilizing a machine learning model, particularly the multi-layer structure and nonlinear activation function of the neural network in this embodiment, in-depth training and analysis of battery temperature data and ambient temperature data are performed, thereby improving the accuracy of battery operating state prediction. Accurate operating state identification provides a reliable data basis for the calculation of battery pulse heating parameters, thereby optimizing the battery heating effect and extending battery life. By introducing regularization parameters to control model complexity and using mathematical models such as sigmoid activation functions and weight matrices, the robustness and stability of the battery operating state prediction model are enhanced.

[0088] This embodiment performs pulse heating of the battery by calculating the optimal pulse frequency and duty cycle, and ensures that the battery remains in the best working state during the heating process through optimized pulse parameters, thereby improving the heating efficiency and effect.

[0089] By accurately calculating the pulse parameters, overheating or other adverse conditions can be avoided, ensuring that the battery operates within a safe temperature range and reducing the risk of battery damage due to excessively high or low temperatures. Reasonable pulse heating parameters can reduce the thermal and chemical stress of the battery, thereby extending the battery life.

[0090] By considering battery temperature, ambient temperature and current operating status data, the calculated pulse parameters can dynamically adapt to different operating conditions and environmental changes, improving adaptability.

[0091] The pulse heating of the battery using the pulse parameters, recording the heating parameters of the battery under the current operating condition, and optimizing the heating parameters of the battery based on the heating effect of the battery includes:

[0092] Pulse heating the battery using the pulse parameters, including adjusting the output of the pulse signal according to the optimal pulse frequency and duty cycle, and dynamically adjusting the output frequency and duty cycle of the pulse signal based on real-time temperature feedback of the battery to ensure that the battery temperature is within a safe range and improve heating efficiency;

[0093] Record the battery's heating parameters under current operating conditions, including battery temperature changes, pulse frequency, duty cycle, and heating time. Perform data analysis on the heating parameters to identify abnormalities during the heating process. Based on the results of the data analysis, adjust the heating strategy to optimize the battery heating effect and extend the battery life.

[0094] Specifically, this embodiment adjusts the output of the pulse signal according to the optimal pulse frequency and duty cycle, and dynamically adjusts the output frequency and duty cycle of the pulse signal based on the real-time temperature feedback of the battery to ensure that the battery temperature is within a safe range, thereby improving the flexibility and response speed of the heating process. By optimizing the pulse parameters, the heating efficiency of the battery can be effectively improved, so that the battery can reach the required temperature level in a shorter time, thereby improving the energy efficiency of the overall system.

[0095] This embodiment records the heating parameters of the battery under the current operating conditions (such as battery temperature changes, pulse frequency, duty cycle, and heating time), performs data analysis on these parameters, identifies abnormal conditions during the heating process, and adjusts the heating strategy based on the analysis results, which helps to reduce the thermal and chemical stress of the battery, thereby extending the battery life.

[0096] By real-time monitoring and optimization of heating parameters, abnormal situations during the heating process can be identified and responded to in a timely manner, ensuring that the battery operates within a safe temperature range and reducing safety hazards caused by overheating or other adverse conditions.

[0097] The real-time monitoring of the health status data of the battery, wherein the health status data includes current, voltage and temperature parameters, and the battery fault diagnosis is performed based on the health status data to obtain the fault diagnosis result including:

[0098] The sensor collects current data, voltage data, and temperature data in real time at a sampling frequency of no less than 100 times per second. The collected current data, voltage data, and temperature data are pre-processed using a low-pass filtering algorithm to obtain battery health status data to remove high-frequency noise and improve data accuracy and stability.

[0099] The sampling calculation formula for current data is:

[0100]

[0101] Among them, I filtered (t) is the current data of time step t after preprocessing, I raw (t) is I filtered (t) The corresponding raw current data, γ is the filter coefficient, and τ is the integral variable;

[0102] Building a fault diagnosis model based on the support vector machine algorithm, classifying and analyzing the health status data through the fault diagnosis model, obtaining the battery fault type, and outputting the corresponding fault diagnosis results;

[0103] The calculation formula of the fault diagnosis model is:

[0104]

[0105] Among them, f0(·) is the classification function, α j is the weight coefficient of the jth support vector, J is the number of support vectors, K(y,y j ) is the kernel function, and b is the fault diagnosis bias.

[0106] Specifically, this embodiment uses sensors to collect current, voltage and temperature data in real time at a sampling frequency of not less than 100 times per second, and uses a low-pass filtering algorithm to preprocess these data to remove high-frequency noise, thereby improving the accuracy of the health status data. A fault diagnosis model is constructed based on the support vector machine algorithm, and the preprocessed health status data is classified and analyzed. It can accurately identify the fault type of the battery and output the corresponding fault diagnosis results, thereby improving the reliability of fault diagnosis. By monitoring the health status data of the battery in real time, it can timely detect abnormal conditions of the battery and quickly make a diagnosis through the fault diagnosis model. According to the fault diagnosis results, corresponding protection measures (such as overcurrent protection, overvoltage protection and temperature anomaly protection) can be taken in time, thereby effectively preventing damage to the battery under abnormal conditions and enhancing the safety of the battery.

[0107] The battery protection control is performed according to the fault diagnosis result, wherein the protection control includes overcurrent protection, overvoltage protection and temperature abnormality protection.

[0108] Establishing a battery protection control strategy based on the fault diagnosis results. The battery protection control strategy includes an overcurrent protection threshold, an overvoltage protection threshold, and a temperature anomaly protection threshold. An adaptive threshold adjustment algorithm is used to dynamically adjust the overcurrent protection threshold, overvoltage protection threshold, and temperature anomaly protection threshold according to the operating status of the battery. The overcurrent protection threshold, the overvoltage protection threshold, and the temperature anomaly protection threshold are mapped to the remaining capacity, charge and discharge status, and ambient temperature of the battery, respectively, to achieve intelligent adjustment of the protection thresholds.

[0109] Real-time monitoring of battery parameters and implementation of corresponding protection control measures, including: when the current exceeds the overcurrent protection threshold, current limiting or cutting off measures are implemented; when the voltage exceeds the overvoltage protection threshold, voltage reduction or charging disconnection measures are implemented; when the temperature exceeds the temperature abnormality protection threshold, power reduction or cooling measures are implemented.

[0110] Specifically, this embodiment uses an adaptive threshold adjustment algorithm to dynamically adjust the overcurrent protection threshold, overvoltage protection threshold, and temperature anomaly protection threshold based on the battery's operating status. This algorithm maps the protection thresholds based on the battery's remaining capacity, charge / discharge status, and ambient temperature to ensure the rationality of the protection thresholds. It monitors battery parameters in real time and executes corresponding protection control measures, effectively preventing battery damage under abnormal conditions. For example, when the current exceeds the overcurrent protection threshold, current limiting or disconnection measures are implemented; when the voltage exceeds the overvoltage protection threshold, voltage reduction or charging disconnection measures are implemented; and when the temperature exceeds the temperature anomaly protection threshold, power reduction or cooling measures are initiated, effectively preventing dangerous situations such as battery overheating, overcurrent, or overvoltage. By dynamically adjusting the protection thresholds and promptly executing protection measures, the stability and reliability of the battery system can be maintained under various operating conditions, reducing system downtime or damage caused by battery failure.

[0111] See also Figure 2 The present invention also provides a battery pulse heating system, the system comprising:

[0112] Data acquisition module, used to collect battery temperature data and ambient temperature data in real time;

[0113] a state identification module, configured to identify current operating state data of the battery based on the battery temperature data and the ambient temperature data, and calculate pulse parameters of the battery based on the current operating state data, the battery temperature data, and the ambient temperature data, the pulse parameters including an optimal pulse frequency and a duty cycle;

[0114] a heating optimization module, configured to pulse heat the battery using the pulse parameters, record the heating parameters of the battery under the current operating condition, and optimize the heating parameters of the battery based on the heating effect of the battery;

[0115] A fault diagnosis module is used to monitor the health status data of the battery in real time, wherein the health status data includes current, voltage and temperature parameters, and perform fault diagnosis on the battery based on the health status data to obtain a fault diagnosis result;

[0116] The protection control module is used to perform protection control on the battery according to the fault diagnosis result. The protection control includes overcurrent protection, overvoltage protection and temperature abnormality protection.

[0117] Specifically, a battery pulse heating system of this embodiment collects battery temperature data and ambient temperature data in real time through a data acquisition module; the state recognition module can identify the current working state of the battery based on the collected temperature data, and calculate the optimal pulse parameters (including pulse frequency and duty cycle), thereby ensuring that the battery is pulse heated in the best state; the heating optimization module can dynamically adjust the heating strategy by recording and analyzing the heating parameters of the battery under the current working conditions, improve the heating efficiency, ensure that the battery temperature is within a safe range, and extend the battery life; the fault diagnosis module monitors the battery health status data (including current, voltage and temperature parameters) in real time, performs fault diagnosis, and promptly identifies the battery fault type; the protection control module executes corresponding protection measures (such as overcurrent protection, overvoltage protection and temperature anomaly protection) according to the diagnosis results to improve the safety of the system.

[0118] A battery pulse heating system in this embodiment realizes intelligent management and adaptive regulation of the battery heating process through the coordinated work of various modules. It can dynamically adjust the strategy according to the real-time status of the battery and environmental changes to ensure safe and efficient operation of the battery.

[0119] The present invention also discloses an electronic device, comprising: at least one processor, at least one memory communication interface and a bus: wherein the processor, memory and communication interface communicate with each other through the bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement a battery pulse heating method.

[0120] The present invention also discloses a computer-readable storage medium storing computer instructions that cause the computer to implement all or part of the steps of a battery pulse heating method described in an embodiment of the present invention. The storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0121] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A battery pulse heating method, characterized in that: The following steps are involved: Real-time collection of battery temperature data and ambient temperature data; identifying current operating state data of the battery based on the battery temperature data and the ambient temperature data, and calculating pulse parameters of the battery based on the current operating state data, the battery temperature data, and the ambient temperature data, the pulse parameters including an optimal pulse frequency and a duty cycle; Pulse heating the battery using the pulse parameters, recording the heating parameters of the battery under the current operating condition, and optimizing the heating parameters of the battery based on the heating effect of the battery; Real-time monitoring of battery health status data, including current, voltage, and temperature parameters, and battery fault diagnosis based on the health status data to obtain a fault diagnosis result; The battery is protected and controlled according to the fault diagnosis result, and the protection control includes overcurrent protection, overvoltage protection and temperature abnormality protection.

2. A battery pulse heating method according to claim 1, characterized in that: The real-time collection of battery temperature data and ambient temperature data includes: A temperature sensor is installed on the battery surface and continuously collects raw battery temperature data based on a preset temperature sampling frequency. The raw battery temperature data is subjected to noise filtering and signal amplification by a signal processing unit to obtain processed battery temperature data. An ambient temperature sensor is placed around the battery, and raw ambient temperature data of the battery is collected based on the ambient temperature sensor. The raw ambient temperature data is integrated through a data fusion algorithm to obtain ambient temperature data.

3. A battery pulse heating method according to claim 2, characterized in that: Identifying the current operating state data of the battery based on the battery temperature data and the ambient temperature data includes: Based on the battery temperature data and the ambient temperature data, using a data analysis algorithm to identify current operating status data of the battery; Building a battery operating state prediction model based on a machine learning model, and training and analyzing the battery temperature data and the ambient temperature data to accurately identify the current operating state data of the battery; The calculation formula of the battery working state prediction model is: Among them, S state is the current working status data score of the battery, σ(·) is the sigmoid activation function, I is the number of hidden layers of the neural network, and W i is the weight matrix of the i-th hidden layer, b i is the bias vector of the i-th hidden layer, x is the battery temperature data and ambient temperature data input to the prediction model, f(·) is the nonlinear activation function, W i-1 and b i-1 are the weight matrix and bias vector of the i-1th hidden layer, λ is the regularization parameter, ||W i || 2 W i The squared norm of .

4. A battery pulse heating method according to claim 3, characterized in that: Calculating the pulse parameters of the battery according to the current working state data, the battery temperature data, and the ambient temperature data, wherein the pulse parameters include an optimal pulse frequency and a duty cycle. Calculating pulse parameters of the battery based on the current working state data, the battery temperature data, and the ambient temperature data, the pulse parameters including an optimal pulse frequency and a duty cycle; The calculation formula for the optimal pulse frequency is: Among them, K1, K2, K3 and K4 are respectively the battery temperature influence coefficient, the ambient temperature influence coefficient, the status score sensitivity influence coefficient and the status score threshold, f optimal is the optimal pulse frequency, T battery is the battery temperature, T environment is the ambient temperature, S state Score the battery's current working status data; The duty cycle is calculated as: Among them, D optimal is the optimal duty cycle, K5 and K6 are the duty cycle reference coefficient and state influence coefficient respectively, T battery is the battery temperature, T reference is the reference temperature value, S state Score the battery's current operating status data.

5. A battery pulse heating method according to claim 1, characterized in that: Pulse heating the battery using the pulse parameters, recording the heating parameters of the battery under the current operating condition, and optimizing the heating parameters of the battery based on the heating effect of the battery includes: Pulse heating the battery using the pulse parameters, including adjusting the output of the pulse signal according to the optimal pulse frequency and duty cycle, and dynamically adjusting the output frequency and duty cycle of the pulse signal based on real-time temperature feedback of the battery; Record the heating parameters of the battery under the current operating conditions, perform data analysis on the heating parameters, identify abnormal conditions during the heating process, and adjust the heating strategy based on the results of the data analysis.

6. A battery pulse heating method according to claim 1, characterized in that: Real-time monitoring of battery health status data, including current, voltage, and temperature parameters, and battery fault diagnosis based on the health status data. The fault diagnosis results include: The sensor collects current data, voltage data, and temperature data in real time at a sampling frequency of no less than 100 times per second, and uses a low-pass filtering algorithm to pre-process the collected current data, voltage data, and temperature data to obtain the battery health status data; The sampling calculation formula for current data is: Among them, I filtered (t) is the current data of time step t after preprocessing, I raw (t) is I filtered (t) The corresponding raw current data, γ is the filter coefficient, and τ is the integral variable; Building a fault diagnosis model based on the support vector machine algorithm, classifying and analyzing the health status data through the fault diagnosis model, obtaining the battery fault type, and outputting the corresponding fault diagnosis results; The calculation formula of the fault diagnosis model is: Among them, f0(·) is the classification function, α j is the weight coefficient of the jth support vector, J is the number of support vectors, K(y,y j ) is the kernel function, and b is the fault diagnosis bias.

7. A battery pulse heating method according to claim 6, characterized in that: The battery is protected and controlled according to the fault diagnosis results. The protection control includes overcurrent protection, overvoltage protection, and temperature abnormality protection. Establishing a battery protection control strategy based on the fault diagnosis results, the battery protection control strategy includes an overcurrent protection threshold, an overvoltage protection threshold, and a temperature anomaly protection threshold. An adaptive threshold adjustment algorithm is used to dynamically adjust the overcurrent protection threshold, overvoltage protection threshold, and temperature anomaly protection threshold according to the operating status of the battery. The overcurrent protection threshold, the overvoltage protection threshold, and the temperature anomaly protection threshold are mapped to the remaining capacity, charge and discharge status, and ambient temperature of the battery, respectively. Real-time monitoring of battery parameters and implementation of corresponding protection control measures, including: when the current exceeds the overcurrent protection threshold, current limiting or cutting off measures are implemented; when the voltage exceeds the overvoltage protection threshold, voltage reduction or charging disconnection measures are implemented; when the temperature exceeds the temperature abnormality protection threshold, power reduction or cooling measures are implemented.

8. A battery pulse heating system, characterized in that: The system comprises: Data acquisition module, used to collect battery temperature data and ambient temperature data in real time; a state identification module, configured to identify current operating state data of the battery based on the battery temperature data and the ambient temperature data, and calculate pulse parameters of the battery based on the current operating state data, the battery temperature data, and the ambient temperature data, the pulse parameters including an optimal pulse frequency and a duty cycle; a heating optimization module, configured to pulse heat the battery using the pulse parameters, record the heating parameters of the battery under the current operating condition, and optimize the heating parameters of the battery based on the heating effect of the battery; A fault diagnosis module is used to monitor the health status data of the battery in real time, wherein the health status data includes current, voltage and temperature parameters, and perform fault diagnosis on the battery based on the health status data to obtain a fault diagnosis result; The protection control module is used to perform protection control on the battery according to the fault diagnosis result. The protection control includes overcurrent protection, overvoltage protection and temperature abnormality protection.

9. An electronic device, characterized in that: include: at least one processor, at least one memory, a communication interface, and a bus; The processor, memory, and communication interface communicate with each other via the bus, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions enable a computer to implement the method according to any one of claims 1 to 7.

Images