Temperature adjusting method and system based on battery simulator simulation battery

Abstract

The invention discloses a temperature adjustment method and system based on battery simulator simulation, and belongs to the technical field of battery simulators, the system comprises an environment simulation module, a battery simulation module, a data acquisition module, a temperature adjustment module, an equivalent conversion prediction module and a compensation verification module, and regulating and controlling the environment temperature of the simulated battery, and recording environment temperature data. According to the temperature adjustment method and system based on the battery simulator simulation battery, environment temperature simulation, battery work simulation, temperature adjustment control, data acquisition, file recording, equivalent conversion and prediction, and verification and correction can be realized, work simulation is carried out on different batteries in different temperature environments, heat increasing and heat dissipation data is obtained, and the temperature of the battery simulator simulation battery is adjusted. And in combination with related use equipment, equivalent conversion is carried out, and a correction prediction model is obtained, so that heat dissipation and heating equipment in the actual use process of the battery can be conveniently distributed, and data support is provided for engineers.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery simulators, and in particular is a temperature adjustment method and a system thereof based on a battery simulator to simulate a battery. Background Art

[0002] A battery simulator is a device used to simulate the performance and behavior of a battery under actual use conditions. It simulates the voltage, current and capacity changes of a battery under specific loads, environmental conditions and usage patterns to predict important parameters such as battery life, charge and discharge characteristics and temperature response. Existing battery simulators mostly use real-time monitoring when performing battery simulation work, monitor the temperature of the battery during the simulation process, and control related heat dissipation or heating equipment to cool or heat up to ensure that the battery temperature is within the normal use temperature range, but cannot perform equivalent conversion based on the related heat dissipation or heating equipment used in the battery during the simulation process, and cannot provide data support to facilitate users to adjust the battery temperature according to the existing heat dissipation or heating equipment around them during actual use of the battery, which has the problem of low practicality and applicability; In view of the above, this case proposes a temperature adjustment method and system based on a battery simulator to simulate a battery, so as to solve the above technical problems. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a temperature adjustment method and system for simulating a battery based on a battery simulator, which solves the above technical problems by improving the detection method and the processing method.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions: A temperature adjustment system for simulating a battery based on a battery simulator, comprising an environment simulation module, a battery simulation module, a data acquisition module, a temperature adjustment module, an equivalent conversion prediction module, and a compensation verification module; The environmental simulation module controls the environmental temperature of the simulated battery, records the environmental temperature data, and transmits the environmental temperature data to the battery simulation module; The battery simulation module simulates the working process of the battery and establishes a simulated battery file in combination with the ambient temperature data of the environmental simulation module; The data acquisition module collects relevant data of the battery during the simulation process, including voltage, current, and real-time temperature, and associates the simulated battery file to transmit the relevant data to the temperature regulation module; The temperature adjustment module includes a heat dissipation device and a heat increasing device, which calculates and determines the optimal temperature range of the relevant battery in the simulated battery file and the real-time temperature, and controls the relevant equipment to adjust the temperature of the battery during the simulation process; The equivalent conversion prediction module obtains an equivalent conversion formula based on the adjustment result of the temperature adjustment module and the relevant parameters of different devices based on the algorithm formula, performs equivalent conversion on the heat dissipation or heat gain, generates the relevant battery equivalent heat dissipation curve or equivalent heat gain curve under different ambient temperatures and different working conditions, and obtains the usage prediction model; The compensation verification module performs control simulation on the temperature regulation module, the battery simulation module, and the environment simulation module based on the usage prediction model predicted by the equivalent conversion prediction module, verifies the usage prediction model, generates correction parameters, and corrects the usage prediction model.

[0005] Furthermore, the environmental simulation module includes a temperature control box, which sets the ambient temperature of the simulated battery based on the temperature control box according to the actual use environment of the battery, records the ambient temperature data, and transmits the ambient temperature data to the battery simulation module; The battery simulation module includes a battery simulator, which simulates the working process of the battery based on the actual use of different batteries, including charge and discharge simulation and dynamic load simulation, and combines the ambient temperature data of the environmental simulation module to establish a simulated battery file, including battery type, simulation type, duration, ambient temperature, number of series cells, number of parallel cells, and optimal battery temperature range; The data acquisition module includes a voltage sensor, a current sensor, and a temperature sensor, which collects relevant data of the battery during the simulation process, including voltage, current, and real-time temperature, and associates the simulated battery files to transmit the relevant data to the temperature regulation module.

[0006] Furthermore, the temperature adjustment module includes a heat dissipation device and a heat increasing device, which combines the optimal temperature range of the relevant battery in the simulated battery file with the real-time temperature calculation and determination, and controls the relevant equipment to adjust the temperature of the battery during the simulation process, and the steps are as follows: Obtain the optimal temperature range of the relevant battery through the battery simulation module , combined with the relevant battery real-time temperature T obtained by the data acquisition module, data judgment is performed. The specific steps and algorithm formula are as follows: The best temperature range for the relevant batteries , A represents the minimum optimal temperature of the relevant battery, B represents the maximum optimal temperature of the relevant battery, and the determination is made in combination with the real-time temperature T of the relevant battery: when When t is reached, it means that the temperature of the relevant battery is too low, and the adjustment instruction is transmitted to the heating device to perform the battery heating operation, and after t time, the battery temperature is adjusted based on the newly obtained real-time temperature. Make a second judgment, when When the heating equipment is heated, the relevant parameters are recorded and maintained, and the heating is continued. or When the temperature is t, the transmission adjustment signal enters the heat increasing device, adjusts the relevant parameters, and makes a judgment based on the real-time temperature obtained again after t time, repeating the above adjustment operation until the real-time temperature is within the interval; when When , it means the temperature of the relevant battery is normal and no adjustment is performed; when When t is reached, it means that the temperature of the relevant battery is too high, and the adjustment instruction is transmitted to the heat dissipation device to perform battery heat dissipation operations, and after t time, the battery temperature is adjusted based on the newly obtained real-time temperature. Make a second judgment, when When the heat dissipation device is in operation, record and maintain the relevant parameters of the heat dissipation device, and continue to dissipate heat. or When the temperature is t, the transmission adjustment signal enters the heat dissipation device, adjusts the relevant parameters, and makes a judgment based on the real-time temperature obtained again after t time, repeating the above adjustment operation until the real-time temperature is Within the range.

[0007] Furthermore, the equivalent conversion prediction module obtains an equivalent conversion formula based on the adjustment result of the temperature adjustment module and the relevant parameters of different devices based on the algorithm formula, performs equivalent conversion on the heat dissipation or heat gain, generates the relevant battery equivalent heat dissipation curve or equivalent heat gain curve under different ambient temperatures and different working conditions, and obtains the use prediction model. The specific steps are as follows: Based on the adjustment results of the temperature adjustment module, under the same ambient temperature and based on different working conditions, the relevant parameters of the heat dissipation device or heat increase device are obtained, including wattage, output efficiency, output duration, and time nodes. Based on the equivalent conversion formula, the heat dissipation or heat increase at different nodes during the total working time is obtained; Based on the heat dissipation or heat gain of different nodes during the total working time under the same ambient temperature, an equivalent heat dissipation curve or an equivalent heat gain curve of the relevant battery is obtained; Combined with the heat dissipation or heat gain of different nodes during the total working time at different ambient temperatures, a usage prediction model is obtained through a machine learning method, including a heat dissipation prediction model and a heat gain prediction model.

[0008] Furthermore, based on the adjustment result of the temperature adjustment module, at the same ambient temperature, the relevant parameters of the heat dissipation device or the heat increase device are obtained, including wattage, output efficiency, output duration, and time nodes, and based on the equivalent conversion formula, the heat dissipation or heat increase of different nodes during the total working time is obtained. The specific steps and algorithm formula are as follows: For heat dissipation, based on different ambient temperatures , respectively collect the relevant heat dissipation equipment parameters at the corresponding ambient temperature, including wattage , output efficiency , Output duration , calculate the heat dissipation , the specific algorithm formula is: ; in, Represents the total working time, Respectively represent the output duration after each parameter change during the total working time, Represents the same ambient temperature The relevant battery output duration under Based on the above formula, the heat dissipation of different wattages and output efficiencies within the total working time and at different output durations is obtained. ; For heat increase, based on different ambient temperatures , respectively collect the relevant heat-increasing equipment parameters at the corresponding ambient temperature, including wattage , output efficiency , Output duration , calculate the heat gain , the specific algorithm formula is: ; in, Represents the total working time, Respectively represent the output duration after each parameter change during the total working time, Represents the same ambient temperature The relevant battery output duration under Based on the above formula, the heat gain of different wattages and output efficiencies under different output durations during the total working time is obtained. .

[0009] Furthermore, the heat dissipation or heat gain of different nodes during the total working time under different ambient temperatures is combined, and a prediction model is obtained through a machine learning method, including a heat dissipation prediction model and a heat gain prediction model. The specific steps are: Collect the time nodes corresponding to different ambient temperatures as well as , based on the neural network model, the steps for training using the prediction model are: Collect relevant data as training data set, including heat dissipation data for heat dissipation prediction model As well as the corresponding ambient temperature and time nodes, the heat gain prediction model related data includes heat dissipation data And the corresponding ambient temperature and time node; Based on different battery models, select the neural network structure, the number of hidden layers and the number of neurons in each layer, and use ReLU Function as activation function; Divide the training data set into a training set and a validation set, train the neural network model with the training set, validate the neural network model based on the validation set, and adjust the hyperparameters of the neural network model according to the performance of the validation set; The mean square error is selected as the loss function to measure the difference between the predicted value of heat dissipation, the predicted value of heat gain and the actual value of heat dissipation and heat gain in the validation set, and the heat dissipation prediction model and heat gain prediction model are obtained. The specific algorithm formula is: ; in, represents the predicted value of heat dissipation, Represents the weight matrix from the input layer to the hidden layer, The weights from the hidden layer to the output layer, represents the nonlinear activation function, is the bias vector of the hidden layer, is the bias term of the output layer, represents the transpose of the input feature vector, is the time node; ; in, represents the predicted value of heat gain, Represents the weight matrix from the input layer to the hidden layer, The weights from the hidden layer to the output layer, represents the nonlinear activation function, is the bias vector of the hidden layer, is the bias term of the output layer, represents the transpose of the input feature vector, For the time node.

[0010] Furthermore, the compensation verification module performs control simulation on the temperature adjustment module, the battery simulation module, and the environment simulation module based on the usage prediction model predicted by the equivalent conversion prediction module, verifies the usage prediction model, generates correction parameters, and corrects the usage prediction model. The specific steps are as follows: Based on the heat gain prediction model and heat dissipation prediction model obtained in the relevant simulation battery equivalent conversion prediction module, the transmission signal controls the temperature adjustment module, the battery simulation module, and the environmental simulation module to perform control simulation to obtain the predicted values ​​and actual values ​​at different time nodes under the same ambient temperature. Based on the obtained predicted values ​​and actual values, the prediction model is verified, correction parameters are generated, and the predicted values ​​obtained using the prediction model are corrected.

[0011] Furthermore, the heat increase prediction model and the heat dissipation prediction model obtained in the relevant simulation battery equivalent conversion prediction module are used to transmit signals to control the temperature adjustment module, the battery simulation module, and the environment simulation module to perform control simulation, and obtain the predicted values ​​and actual values ​​of different time nodes at the same ambient temperature. The specific steps are: Based on the normal and extreme ambient temperatures of the simulated battery, N groups of ambient temperature data are extracted through simple non-repetitive random sampling. The transmission control signal enters the environment simulation module, the battery simulation module, and the temperature adjustment module. Based on the extracted N groups of environment temperature data, the environment simulation module environment temperature value is set, the battery simulation module is used to perform work simulation, and the temperature adjustment module is used to obtain the heat dissipation value or heat gain value at n time nodes; Based on N groups of ambient temperature data and n time nodes, the heat dissipation prediction model and the heat gain prediction model are used to obtain the heat dissipation prediction value or the heat gain prediction value, and the heat dissipation value or the heat gain value of the temperature control module are corresponding.

[0012] Furthermore, based on the obtained predicted values ​​and actual values, the prediction model is verified, correction parameters are generated, and the predicted values ​​obtained using the prediction model are corrected. The specific steps are: The predicted value is corrected by the residual method, and the algorithm formula is: ; in, represents the residual of the ith data point, Represents the actual value obtained based on the temperature regulation module, Represents the predicted value obtained using the prediction model, based on Calculate the correction value, the specific algorithm formula is: ; Where E represents the correction value, n is the number of data points, and the correction prediction value is obtained , the specific algorithm formula is: .

[0013] A method for adjusting the temperature of a battery based on a battery simulator, comprising the following steps: S1. Based on the battery simulator, different working conditions of the battery are simulated, and the external ambient temperature of the battery in the simulation is controlled by the temperature control box to adapt to different simulated battery usage conditions; S2. Collect relevant data of the battery during the simulation process, including voltage, current, and real-time temperature, through voltage sensors, current sensors, and temperature sensors. According to the optimal temperature range of the simulated battery and the collected real-time temperature, adjust the temperature through heating or cooling equipment; S3. Based on the temperature adjustment data and the relevant parameters of different devices, an equivalent conversion formula is obtained based on the algorithm formula to perform equivalent conversion on the heat dissipation or heat gain, and generate the relevant battery equivalent heat dissipation curve or equivalent heat gain curve under different ambient temperatures and different working conditions; S4. Based on the heat dissipation or heat gain of different nodes during the total working time under different ambient temperatures, a usage prediction model is obtained through a machine learning method, including a heat dissipation prediction model and a heat gain prediction model; S5. Based on the heat dissipation prediction model and the heat gain prediction model, N groups of ambient temperature data are extracted through simple non-repetitive random sampling, and working simulation is performed through a battery simulator and a temperature control box to obtain actual temperature adjustment data. Based on the actual temperature adjustment data and the predicted data, a correction value is obtained to correct the predicted data.

[0014] Compared with the prior art, the present invention has the following beneficial effects: In the present invention, by setting an equivalent conversion prediction module, the temperature adjustment data in the working process of the simulated battery is equivalently converted, the heat dissipation or heat gain is obtained based on the relevant equipment used in the simulation process, and the equivalent heat dissipation curve or equivalent heat gain curve of the relevant battery under different ambient temperatures and different working conditions is generated. The engineer provides data support for the heat dissipation design of the relevant battery, thereby enhancing the applicability of the obtained data; In the present invention, different ambient temperatures are adjusted through an environmental simulation module, and adjustment data is obtained through a temperature adjustment module. Based on the relevant data, a neural network simulation is performed to obtain a heat dissipation prediction model and a heat increase prediction model of the relevant battery. By learning a large amount of data, the heat dissipation and heat increase of the battery at different ambient temperatures are predicted, the actual use strategy of the battery is optimized, and the configuration of the heat dissipation device is adjusted according to the simulation results to ensure that the battery can maintain an appropriate operating temperature under various environmental conditions. In the present invention, by setting a compensation verification module in cooperation with an equivalent conversion prediction module, based on the obtained heat increase prediction model and heat dissipation prediction model, a command signal is transmitted through the compensation verification module, and based on the ambient temperature value extracted by simple random non-repetitive sampling, relevant parameters are regulated, and actual values ​​are obtained through the temperature adjustment module. Based on the comparison between the predicted value and the actual value using the prediction model, a correction value is generated, the predicted value is further corrected, and the output of the prediction model is further corrected to ensure that the simulation result is closer to the actual situation; In the present invention, the compensation verification module adjusts the simulation conditions in real time based on the ambient temperature values ​​extracted by simple random non-repetitive sampling, and records the actual temperature adjustment effect. These data can not only be used to verify the accuracy of the prediction model, but also provide experimental data support for subsequent model optimization and product design; The entire temperature adjustment method based on battery simulator to simulate batteries and its system can realize ambient temperature simulation, battery operation simulation, temperature regulation control, data collection, file recording, equivalent conversion and prediction, verification and correction. By simulating the operation of different batteries in different temperature environments, heat gain and heat dissipation data are obtained, and combined with related equipment for equivalent conversion and a corrected prediction model is obtained, which is convenient for the allocation of heat dissipation and heat gain equipment during the actual use of the battery, and provides data support for engineers. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The present invention provides a temperature adjustment method for simulating a battery based on a battery simulator and a system block diagram thereof. DETAILED DESCRIPTION

[0016] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] like Figure 1 As shown, a temperature adjustment system based on a battery simulator to simulate a battery includes an environment simulation module, a battery simulation module, a data acquisition module, a temperature adjustment module, an equivalent conversion prediction module, and a compensation verification module; The environmental simulation module controls the ambient temperature of the simulated battery, records the ambient temperature data, and transmits the ambient temperature data to the battery simulation module; The environmental simulation module includes a temperature control box. According to the actual use environment of the battery, based on the temperature control box, the ambient temperature of the simulated battery is set, and the ambient temperature data is recorded and transmitted to the battery simulation module.

[0018] It should be noted that the temperature control box can ensure that the battery simulator accurately reflects the environmental conditions of the battery during the simulation process, obtain more reliable and realistic simulation results, and be more in line with the ambient temperature conditions that may occur during actual use. It provides engineers and researchers with more useful analysis and decision-making basis, which helps to optimize battery management strategies and improve product performance.

[0019] The battery simulation module, including the battery simulator, simulates the working process of the battery based on the actual use of different batteries, including charge and discharge simulation, dynamic load simulation, and combines the ambient temperature data of the environmental simulation module to establish a simulated battery file, including battery type, simulation type, duration, ambient temperature, number of series cells, number of parallel cells, and optimal battery temperature range; The data acquisition module, including voltage sensor, current sensor and temperature sensor, collects relevant data of the battery during the simulation process, including voltage, current and real-time temperature, and associates the simulated battery files to transmit the relevant data to the temperature regulation module. It should be noted that based on the battery simulator, the parameters of the relevant batteries are set to simulate the battery's charge and discharge and dynamic load. Combined with the ambient temperature set by the temperature control box, it is used to truly simulate the battery's usage. Relevant data is collected through voltage sensors, current sensors, and temperature sensors to provide data support for subsequent module operations.

[0020] The temperature regulation module, including heat dissipation equipment and heat increasing equipment, combines the optimal temperature range of the relevant battery in the simulated battery file with the real-time temperature calculation and judgment, and controls the relevant equipment to adjust the temperature of the battery during the simulation process. The specific steps are: Obtain the optimal temperature range of the relevant battery through the battery simulation module , combined with the relevant battery real-time temperature T obtained by the data acquisition module, data judgment is performed. The specific steps and algorithm formula are as follows: The best temperature range for the relevant batteries , A represents the minimum optimal temperature of the relevant battery, B represents the maximum optimal temperature of the relevant battery, and the determination is made in combination with the real-time temperature T of the relevant battery: when When t is reached, it means that the temperature of the relevant battery is too low, and the adjustment instruction is transmitted to the heating device to perform the battery heating operation, and after t time, the battery temperature is adjusted based on the newly obtained real-time temperature. Make a second judgment, when When the heating equipment is heated, the relevant parameters are recorded and maintained, and the heating is continued. or When the temperature is t, the transmission adjustment signal enters the heat increasing device, adjusts the relevant parameters, and makes a judgment based on the real-time temperature obtained again after t time, repeating the above adjustment operation until the real-time temperature is within the interval; when When , it means the temperature of the relevant battery is normal and no adjustment is performed; when When t is reached, it means that the temperature of the relevant battery is too high, and the adjustment instruction is transmitted to the heat dissipation device to perform battery heat dissipation operations, and after t time, the battery temperature is adjusted based on the newly obtained real-time temperature. Make a second judgment, when When the heat dissipation device is in operation, record and maintain the relevant parameters of the heat dissipation device, and continue to dissipate heat. or When the temperature is t, the transmission adjustment signal enters the heat dissipation device, adjusts the relevant parameters, and makes a judgment based on the real-time temperature obtained again after t time, repeating the above adjustment operation until the real-time temperature is Within the range.

[0021] It should be noted that the heat-increasing equipment includes heating wires, heating plates, etc., which are used to perform heat-increasing operations on batteries whose temperatures are lower than the normal working range during the simulation process. The heat-dissipating equipment includes cooling fans, semiconductor cooling sheets, etc., which are used to perform heat dissipating operations on batteries whose temperatures are higher than the normal working range during the simulation process. The time interval t can be flexibly set according to different types of batteries and working modes, so as to obtain the required data and provide data support for subsequent modules.

[0022] The equivalent conversion prediction module, based on the adjustment result of the temperature adjustment module and the relevant parameters of different devices, obtains the equivalent conversion formula based on the algorithm formula, performs equivalent conversion on the heat dissipation or heat gain, generates the relevant battery equivalent heat dissipation curve or equivalent heat gain curve under different ambient temperatures and different working conditions, and obtains the usage prediction model. The specific steps are as follows: Based on the adjustment results of the temperature adjustment module, under the same ambient temperature, based on different working conditions, the relevant parameters of the heat dissipation device or heat increase device are obtained, including wattage, output efficiency, output duration, and time nodes. Based on the equivalent conversion formula, the heat dissipation or heat increase at different nodes during the total working time is obtained. The specific steps and algorithm formula are as follows: For heat dissipation, based on different ambient temperatures , respectively collect the relevant heat dissipation equipment parameters at the corresponding ambient temperature, including wattage , output efficiency , Output duration , calculate the heat dissipation , the specific algorithm formula is: ; in, Represents the total working time, Respectively represent the output duration after each parameter change during the total working time, Represents the same ambient temperature The relevant battery output duration under Based on the above formula, the heat dissipation of different wattages and output efficiencies within the total working time and at different output durations is obtained. ; For heat increase, based on different ambient temperatures , respectively collect the relevant heat-increasing equipment parameters at the corresponding ambient temperature, including wattage , output efficiency , Output duration , calculate the heat gain , the specific algorithm formula is: ; in, Represents the total working time, Respectively represent the output duration after each parameter change during the total working time, Represents the same ambient temperature The relevant battery output duration under Based on the above formula, the heat gain of different wattages and output efficiencies under different output durations during the total working time is obtained. .

[0023] Based on the heat dissipation or heat gain of different nodes during the total working time under the same ambient temperature, the relevant battery equivalent heat dissipation curve or equivalent heat gain curve is obtained.

[0024] It should be noted that according to the obtained , according to different nodes as well as ,based on MATLAB By using the curve fitting toolbox, you can draw an equivalent heat dissipation curve or an equivalent heat increase curve based on existing data points.

[0025] Combined with the heat dissipation or heat gain of different nodes during the total working time under different ambient temperatures, a usage prediction model is obtained through a machine learning method, including a heat dissipation prediction model and a heat gain prediction model. The specific steps are as follows: Collect the time nodes corresponding to different ambient temperatures as well as , based on the neural network model, the steps for training using the prediction model are: Collect relevant data as training data set, including heat dissipation data for heat dissipation prediction model As well as the corresponding ambient temperature and time nodes, the heat gain prediction model related data includes heat dissipation data And the corresponding ambient temperature and time node; Based on different battery models, select the neural network structure, the number of hidden layers and the number of neurons in each layer, and use ReLU Function as activation function; Divide the training data set into a training set and a validation set, train the neural network model with the training set, validate the neural network model based on the validation set, and adjust the hyperparameters of the neural network model according to the performance of the validation set; It should be noted that the ratio of validation set to training set is usually 2:8, that is, 80% of the data set is the training set and 20% is the validation set. The training set is used to train the neural network model and adjust the parameters of the model, including weights and biases, by optimizing the loss function. The validation set is used to adjust the hyperparameters and structure of the model to optimize the performance and generalization ability of the model.

[0026] The mean square error is selected as the loss function to measure the difference between the predicted value of heat dissipation, the predicted value of heat gain and the actual value of heat dissipation and heat gain in the validation set, and the heat dissipation prediction model and heat gain prediction model are obtained. The specific algorithm formula is: ; in, represents the predicted value of heat dissipation, Represents the weight matrix from the input layer to the hidden layer, The weights from the hidden layer to the output layer, represents the nonlinear activation function, is the bias vector of the hidden layer, is the bias term of the output layer, represents the transpose of the input feature vector, is the time node; ; in, represents the predicted value of heat gain, Represents the weight matrix from the input layer to the hidden layer, The weights from the hidden layer to the output layer, represents the nonlinear activation function, is the bias vector of the hidden layer, is the bias term of the output layer, represents the transpose of the input feature vector, For the time node.

[0027] It should be noted that the predicted value of heat gain and the predicted value of heat dissipation are the outputs of the model prediction. The weight matrix from the input layer to the hidden layer contains the connection weights between the hidden layer neurons and the input features. Each hidden layer neuron has a bias term, which is used to adjust the activation threshold of the neuron. By adjusting the weights and biases and selecting a suitable activation function, the neural network can learn and predict the heat dissipation or heat gain under a given input ambient temperature and time node.

[0028] The compensation verification module performs control simulation on the temperature adjustment module, the battery simulation module, and the environment simulation module based on the usage prediction model predicted by the equivalent conversion prediction module, verifies the usage prediction model, generates correction parameters, and corrects the usage prediction model. The specific steps are as follows: Based on the heat increase prediction model and heat dissipation prediction model obtained in the relevant simulation battery equivalent conversion prediction module, the transmission signal controls the temperature adjustment module, the battery simulation module, and the environment simulation module to perform control simulation to obtain the predicted values ​​and actual values ​​at different time nodes under the same ambient temperature. The specific steps are as follows: Based on the normal and extreme ambient temperatures of the simulated battery, N groups of ambient temperature data are extracted through simple non-repetitive random sampling. The transmission control signal enters the environment simulation module, the battery simulation module, and the temperature adjustment module. Based on the extracted N groups of environment temperature data, the environment simulation module environment temperature value is set, the battery simulation module is used to perform work simulation, and the temperature adjustment module is used to obtain the heat dissipation value or heat gain value at n time nodes; Based on N groups of ambient temperature data and n time nodes, the heat dissipation prediction model and the heat gain prediction model are used to obtain the heat dissipation prediction value or the heat gain prediction value, and the heat dissipation value or the heat gain value of the temperature control module are corresponding.

[0029] It should be noted that, according to the method of simple random non-repetitive sampling, data points are randomly selected from the normal ambient temperature and the extreme ambient temperature, which are used as the ambient temperature input in the subsequent simulation process, and the collaborative work of the environmental simulation module, battery simulation module and temperature regulation module are utilized to obtain the actual values, which are combined with the predicted values ​​obtained by the prediction model to provide data support for the acquisition of the correction values.

[0030] Based on the obtained predicted values ​​and actual values, the prediction model is verified, correction parameters are generated, and the predicted values ​​obtained using the prediction model are corrected. The specific steps are: The predicted value is corrected by the residual method, and the algorithm formula is: ; in, represents the residual of the ith data point, Represents the actual value obtained based on the temperature regulation module, Represents the predicted value obtained using the prediction model, based on Calculate the correction value, the specific algorithm formula is: ; Where E represents the correction value, n is the number of data points, and the correction prediction value is obtained , the specific algorithm formula is: .

[0031] It should be noted that by comparing the residuals between the predicted values ​​and the actual values ​​to estimate the deviation of using the prediction equation, and applying this deviation to future predictions for correction, the accuracy of the predicted values ​​can be further improved, thereby providing theoretical data support for the actual use of batteries.

[0032] A method for adjusting the temperature of a battery based on a battery simulator, comprising the following steps: S1. Based on the battery simulator, different working conditions of the battery are simulated, and the external ambient temperature of the battery in the simulation is controlled by the temperature control box to adapt to different simulated battery usage conditions; S2. Collect relevant data of the battery during the simulation process, including voltage, current, and real-time temperature, through voltage sensors, current sensors, and temperature sensors. According to the optimal temperature range of the simulated battery and the collected real-time temperature, adjust the temperature through heating or cooling equipment; S3. Based on the temperature adjustment data and the relevant parameters of different devices, an equivalent conversion formula is obtained based on the algorithm formula to perform equivalent conversion on the heat dissipation or heat gain, and generate the relevant battery equivalent heat dissipation curve or equivalent heat gain curve under different ambient temperatures and different working conditions; S4. Based on the heat dissipation or heat gain of different nodes during the total working time under different ambient temperatures, a usage prediction model is obtained through a machine learning method, including a heat dissipation prediction model and a heat gain prediction model; S5. Based on the heat dissipation prediction model and the heat gain prediction model, N groups of ambient temperature data are extracted through simple non-repetitive random sampling, and working simulation is performed through a battery simulator and a temperature control box to obtain actual temperature adjustment data. Based on the actual temperature adjustment data and the predicted data, a correction value is obtained to correct the predicted data.

[0033] In the embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation; the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the method of this embodiment.

[0034] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A temperature adjustment system for simulating a battery based on a battery simulator, characterized in that: It includes environment simulation module, battery simulation module, data acquisition module, temperature regulation module, equivalent conversion prediction module and compensation verification module; The environmental simulation module controls the environmental temperature of the simulated battery, records the environmental temperature data, and transmits the environmental temperature data to the battery simulation module; The battery simulation module simulates the working process of the battery and establishes a simulated battery file in combination with the ambient temperature data of the environmental simulation module; The data acquisition module collects relevant data of the battery during the simulation process, including voltage, current, and real-time temperature, and associates the simulated battery file to transmit the relevant data to the temperature regulation module; The temperature adjustment module includes a heat dissipation device and a heat increasing device, which calculates and determines the optimal temperature range of the relevant battery in the simulated battery file and the real-time temperature, and controls the relevant equipment to adjust the temperature of the battery during the simulation process; The equivalent conversion prediction module obtains an equivalent conversion formula based on the adjustment result of the temperature adjustment module and the relevant parameters of different devices based on the algorithm formula, performs equivalent conversion on the heat dissipation or heat gain, generates the relevant battery equivalent heat dissipation curve or equivalent heat gain curve under different ambient temperatures and different working conditions, and obtains the usage prediction model; The compensation verification module performs control simulation on the temperature regulation module, the battery simulation module, and the environment simulation module based on the usage prediction model predicted by the equivalent conversion prediction module, verifies the usage prediction model, generates correction parameters, and corrects the usage prediction model.

2. A temperature adjustment system for simulating a battery based on a battery simulator according to claim 1, characterized in that: The environmental simulation module includes a temperature control box, which sets the ambient temperature of the simulated battery based on the temperature control box according to the actual use environment of the battery, records the ambient temperature data, and transmits the ambient temperature data to the battery simulation module; The battery simulation module includes a battery simulator, which simulates the working process of the battery based on the actual use of different batteries, including charge and discharge simulation and dynamic load simulation, and combines the ambient temperature data of the environmental simulation module to establish a simulated battery file, including battery type, simulation type, duration, ambient temperature, number of series cells, number of parallel cells, and optimal battery temperature range; The data acquisition module includes a voltage sensor, a current sensor, and a temperature sensor, which collects relevant data of the battery during the simulation process, including voltage, current, and real-time temperature, and associates the simulated battery files to transmit the relevant data to the temperature regulation module.

3. A temperature adjustment system for simulating a battery based on a battery simulator according to claim 1, characterized in that: The temperature adjustment module includes a heat dissipation device and a heat increasing device. It combines the optimal temperature range of the relevant battery in the simulated battery file with the real-time temperature calculation and determination, and controls the relevant equipment to adjust the temperature of the battery during the simulation process. The specific steps are as follows: Obtain the optimal temperature range of the relevant battery through the battery simulation module , combined with the relevant battery real-time temperature T obtained by the data acquisition module, data judgment is performed. The specific steps and algorithm formula are as follows: The best temperature range for the relevant batteries , A represents the minimum optimal temperature of the relevant battery, B represents the maximum optimal temperature of the relevant battery, and the determination is made in combination with the real-time temperature T of the relevant battery: when When t is reached, it means that the temperature of the relevant battery is too low, and the adjustment instruction is transmitted to the heating device to perform the battery heating operation, and after t time, the battery temperature is adjusted based on the newly obtained real-time temperature. Make a second judgment, when When the heating equipment is heated, the relevant parameters are recorded and maintained, and the heating is continued. or When the temperature is t, the transmission adjustment signal enters the heat increasing device, adjusts the relevant parameters, and makes a judgment based on the real-time temperature obtained again after t time, repeating the above adjustment operation until the real-time temperature is within the interval; when When , it means the temperature of the relevant battery is normal and no adjustment is performed; when When t is reached, it means that the temperature of the relevant battery is too high, and the adjustment instruction is transmitted to the heat dissipation device to perform battery heat dissipation operations, and after t time, the battery temperature is adjusted based on the newly obtained real-time temperature. Make a second judgment, when When the heat dissipation device is in operation, record and maintain the relevant parameters of the heat dissipation device, and continue to dissipate heat. or When the temperature is t, the transmission adjustment signal enters the heat dissipation device, adjusts the relevant parameters, and makes a judgment based on the real-time temperature obtained again after t time, repeating the above adjustment operation until the real-time temperature is Within the range.

4. A temperature adjustment system for simulating a battery based on a battery simulator according to claim 1, characterized in that: The equivalent conversion prediction module obtains an equivalent conversion formula based on the adjustment result of the temperature adjustment module and the relevant parameters of different devices based on the algorithm formula, performs equivalent conversion on the heat dissipation or heat gain, generates the relevant battery equivalent heat dissipation curve or equivalent heat gain curve under different ambient temperatures and different working conditions, and obtains the use prediction model. The specific steps are as follows: Based on the adjustment results of the temperature adjustment module, under the same ambient temperature and based on different working conditions, the relevant parameters of the heat dissipation device or heat increase device are obtained, including wattage, output efficiency, output duration, and time nodes. Based on the equivalent conversion formula, the heat dissipation or heat increase at different nodes during the total working time is obtained; Based on the heat dissipation or heat gain of different nodes during the total working time under the same ambient temperature, an equivalent heat dissipation curve or an equivalent heat gain curve of the relevant battery is obtained; Combined with the heat dissipation or heat gain of different nodes during the total working time at different ambient temperatures, a usage prediction model is obtained through a machine learning method, including a heat dissipation prediction model and a heat gain prediction model.

5. A temperature adjustment system for simulating a battery based on a battery simulator according to claim 4, characterized in that: Based on the adjustment result of the temperature adjustment module, under the same ambient temperature, the relevant parameters of the heat dissipation device or the heat increase device are obtained, including wattage, output efficiency, output duration, and time nodes. Based on the equivalent conversion formula, the heat dissipation or heat increase at different nodes during the total working time is obtained. The specific steps and algorithm formula are as follows: For heat dissipation, based on different ambient temperatures , respectively collect the relevant heat dissipation equipment parameters at the corresponding ambient temperature, including wattage , output efficiency , Output duration , calculate the heat dissipation , the specific algorithm formula is: ； in, Represents the total working time, Respectively represent the output duration after each parameter change during the total working time, Represents the same ambient temperature The relevant battery output duration under Based on the above formula, the heat dissipation of different wattages and output efficiencies within the total working time and at different output durations is obtained. ; For heat increase, based on different ambient temperatures , respectively collect the relevant heat-increasing equipment parameters at the corresponding ambient temperature, including wattage , output efficiency , Output duration , calculate the heat gain , the specific algorithm formula is: ； in, Represents the total working time, Respectively represent the output duration after each parameter change during the total working time, Represents the same ambient temperature The relevant battery output duration under Based on the above formula, the heat gain of different wattages and output efficiencies under different output durations during the total working time is obtained. .

6. A temperature adjustment system for simulating a battery based on a battery simulator according to claim 5, characterized in that: The heat dissipation or heat gain of different nodes during the total working time under different ambient temperatures is combined, and a use prediction model is obtained through a machine learning method, including a heat dissipation prediction model and a heat gain prediction model. The specific steps are: Collect the time nodes corresponding to different ambient temperatures as well as , based on the neural network model, the steps for training using the prediction model are: Collect relevant data as training data set, including heat dissipation data for heat dissipation prediction model As well as the corresponding ambient temperature and time nodes, the heat gain prediction model related data includes heat dissipation data And the corresponding ambient temperature and time node; Based on different battery models, select the neural network structure, the number of hidden layers and the number of neurons in each layer, and use ReLU Function as activation function; Divide the training data set into a training set and a validation set, train the neural network model with the training set, validate the neural network model based on the validation set, and adjust the hyperparameters of the neural network model according to the performance of the validation set; The mean square error is selected as the loss function to measure the difference between the predicted value of heat dissipation, the predicted value of heat gain and the actual value of heat dissipation and heat gain in the validation set, and the heat dissipation prediction model and heat gain prediction model are obtained. The specific algorithm formula is: ； in, represents the predicted value of heat dissipation, Represents the weight matrix from the input layer to the hidden layer, The weights from the hidden layer to the output layer, represents the nonlinear activation function, is the bias vector of the hidden layer, is the bias term of the output layer, represents the transpose of the input feature vector, is the time node; ； in, represents the predicted value of heat gain, Represents the weight matrix from the input layer to the hidden layer, The weights from the hidden layer to the output layer, represents the nonlinear activation function, is the bias vector of the hidden layer, is the bias term of the output layer, represents the transpose of the input feature vector, For the time node.

7. The temperature adjustment system based on battery simulator for simulating battery according to claim 1, characterized in that: The compensation verification module performs control simulation on the temperature adjustment module, the battery simulation module, and the environment simulation module based on the usage prediction model predicted by the equivalent conversion prediction module, verifies the usage prediction model, generates correction parameters, and corrects the usage prediction model. The specific steps are as follows: Based on the heat gain prediction model and heat dissipation prediction model obtained in the relevant simulation battery equivalent conversion prediction module, the transmission signal controls the temperature adjustment module, the battery simulation module, and the environment simulation module to perform control simulation to obtain the predicted values ​​and actual values ​​at different time nodes under the same ambient temperature; Based on the obtained predicted values ​​and actual values, the prediction model is verified, correction parameters are generated, and the predicted values ​​obtained using the prediction model are corrected.

8. The temperature adjustment system based on battery simulator for simulating a battery according to claim 7, characterized in that: The heat increase prediction model and the heat dissipation prediction model obtained in the relevant simulation battery equivalent conversion prediction module are used to transmit signals to control the temperature adjustment module, the battery simulation module, and the environment simulation module to perform control simulation, and obtain the predicted values ​​and actual values ​​of different time nodes at the same ambient temperature. The specific steps are: Based on the normal and extreme ambient temperatures of the simulated battery, N groups of ambient temperature data are extracted through simple non-repetitive random sampling. The transmission control signal enters the environment simulation module, the battery simulation module, and the temperature adjustment module. Based on the extracted N groups of environment temperature data, the environment simulation module environment temperature value is set, the battery simulation module is used to perform work simulation, and the temperature adjustment module is used to obtain the heat dissipation value or heat gain value at n time nodes; Based on N groups of ambient temperature data and n time nodes, the heat dissipation prediction model and the heat gain prediction model are used to obtain the heat dissipation prediction value or the heat gain prediction value, and the heat dissipation value or the heat gain value of the temperature control module are corresponding.

9. A temperature adjustment system for simulating a battery based on a battery simulator according to claim 8, characterized in that: Based on the obtained predicted value and actual value, the prediction model is used for verification, correction parameters are generated, and the predicted value obtained by using the prediction model is corrected. The specific steps are: The predicted value is corrected by the residual method, and the algorithm formula is: ； in, represents the residual of the ith data point, Represents the actual value obtained based on the temperature regulation module, Represents the predicted value obtained using the prediction model, based on Calculate the correction value, the specific algorithm formula is: ； Where E represents the correction value, n is the number of data points, and the correction prediction value is obtained , the specific algorithm formula is: 。 10. A method for adjusting the temperature of a battery based on a battery simulator, characterized in that: The method adopts the temperature adjustment system based on the battery simulator simulating the battery as described in any one of claims 1 to 9, comprising the following steps: S1. Based on the battery simulator, different working conditions of the battery are simulated, and the external ambient temperature of the battery in the simulation is controlled by the temperature control box to adapt to different simulated battery usage conditions; S2. Collect relevant data of the battery during the simulation process, including voltage, current, and real-time temperature, through voltage sensors, current sensors, and temperature sensors. According to the optimal temperature range of the simulated battery and the collected real-time temperature, adjust the temperature through heating or cooling equipment; S3. Based on the temperature adjustment data and the relevant parameters of different devices, an equivalent conversion formula is obtained based on the algorithm formula to perform equivalent conversion on the heat dissipation or heat gain, and generate the relevant battery equivalent heat dissipation curve or equivalent heat gain curve under different ambient temperatures and different working conditions; S4. Based on the heat dissipation or heat gain of different nodes during the total working time under different ambient temperatures, a usage prediction model is obtained through a machine learning method, including a heat dissipation prediction model and a heat gain prediction model; S5. Based on the heat dissipation prediction model and the heat gain prediction model, N groups of ambient temperature data are extracted through simple non-repetitive random sampling, and working simulation is performed through a battery simulator and a temperature control box to obtain actual temperature adjustment data. Based on the actual temperature adjustment data and the predicted data, a correction value is obtained to correct the predicted data.

Images