Battery temperature detection methods, devices, equipment and storage media

Abstract

This invention belongs to the field of battery temperature detection technology and discloses a battery temperature detection method, apparatus, device, and storage medium. The invention acquires the measured temperature, real-time voltage value, and remaining charge of the battery under test, as well as the ambient temperature at the current location of the battery. Based on the real-time voltage value and remaining charge, a temperature compensation model is determined. The ambient temperature, real-time voltage value, and remaining charge are input into the temperature compensation model to obtain a temperature compensation value. The measured temperature is then compensated based on this compensation value to obtain the true temperature. If the true temperature exceeds the abnormal temperature, a temperature anomaly warning is issued. By confirming the battery's operating mode and the ambient temperature at the battery's location, a corresponding temperature compensation model is determined, and a corresponding temperature compensation value is obtained. The true battery temperature is obtained by compensating the measured temperature with this compensation value, thus avoiding the influence of ambient temperature and the battery's operating mode, resulting in more accurate battery temperature detection results.

Description

Technical Field

[0001] This invention relates to the field of battery temperature detection technology, and in particular to a battery temperature detection method, apparatus, device, and storage medium. Background Technology

[0002] With the increasing popularity of clean energy, batteries are playing an increasingly important role in our lives. During battery use, it is necessary to pay attention to the battery temperature. When the battery temperature exceeds a certain limit, it may cause the battery to explode and pose a fire hazard. This is especially true when the battery is in a closed operating environment, where the probability of danger increases significantly, increasing the safety risks associated with battery use. When testing the battery temperature, the measured temperature can be affected by the battery's own condition and the current environment, causing the measured result to deviate from the actual battery temperature. This may affect the normal operation of the battery and even cause safety problems.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a battery temperature detection method, apparatus, device, and storage medium, aiming to solve the technical problem of inaccurate battery temperature detection in the prior art.

[0005] To achieve the above objectives, the present invention provides a battery temperature detection method, the method comprising the following steps:

[0006] The measured temperature of the battery under test, the ambient temperature at the current location of the battery under test, the real-time voltage value of the battery under test, and the remaining power of the battery under test are obtained.

[0007] The temperature compensation model is determined based on the real-time voltage value of the battery under test and the remaining charge of the battery under test.

[0008] The ambient temperature, the real-time voltage value, and the remaining power are input into the temperature compensation model to obtain the temperature compensation value.

[0009] The measured temperature is compensated according to the temperature compensation value to obtain the true temperature of the battery under test.

[0010] When the actual temperature is greater than the abnormal temperature, a temperature abnormality warning will be issued.

[0011] Optionally, determining the temperature compensation model based on the real-time voltage value of the battery under test and the remaining charge of the battery under test includes:

[0012] The voltage change rate and the remaining charge change rate are obtained based on the real-time voltage value and the remaining charge of the battery under test;

[0013] The operating mode of the battery under test is determined based on the voltage change rate and the remaining charge change rate.

[0014] According to the operating mode, a temperature compensation model corresponding to the operating mode is matched in the temperature compensation model library, which includes at least one temperature compensation model.

[0015] Optionally, a temperature compensation model is determined based on the real-time voltage value of the battery under test and the remaining charge of the battery under test, including:

[0016] The voltage change rate and the remaining charge change rate are obtained based on the real-time voltage value and the remaining charge of the battery under test;

[0017] The operating mode of the battery under test is determined based on the voltage change rate and the remaining charge change rate.

[0018] According to the operating mode, a temperature compensation model corresponding to the operating mode is matched in the temperature compensation model library, which includes at least one temperature compensation model.

[0019] Optionally, before determining the temperature compensation model based on the real-time voltage value of the battery under test and the remaining charge of the battery under test, the method further includes:

[0020] The historical data set of the battery under test is collected according to a preset collection frequency. The historical data set includes historical voltage value, historical remaining power, and historical ambient temperature.

[0021] The collected data set is divided into a training dataset and a validation dataset;

[0022] The preset model is trained based on the training dataset to obtain a temperature compensation model, and the temperature compensation model is added to the temperature compensation model library.

[0023] Optionally, training the initial temperature compensation model based on the training dataset to obtain the temperature compensation model includes:

[0024] The real-time voltage values, remaining power, and ambient temperature in the training dataset are normalized to obtain a normalized training dataset.

[0025] The normalized dataset is input into the neurons in the hidden layer, and training values ​​are obtained according to preset weight values ​​and bias values. The training values ​​are then input into the next neuron until the last neuron, to obtain the output value of the hidden layer.

[0026] The hidden layer output value is compared with the expected output. When the training value meets the expected output, the training ends and the temperature compensation model is obtained.

[0027] Optionally, after comparing the hidden layer output value with the expected output, and ending the training when the training value meets the expected output to obtain the temperature compensation model, the method further includes:

[0028] The data in the verification dataset is input into the temperature compensation model to obtain the verification temperature compensation value;

[0029] The error value is obtained by comparing the verified temperature compensation value with the true value in the verified dataset.

[0030] The error value is compared with a preset error. When the error value is greater than the preset error, the weight value and the bias value are corrected according to the error value to obtain the corrected temperature compensation model.

[0031] Optionally, after issuing a temperature anomaly alert when the actual temperature is greater than the abnormal temperature, the method further includes:

[0032] The temperature overflow value is obtained based on the actual temperature and the abnormal temperature value;

[0033] The adjustment voltage is obtained by looking up the temperature adjustment table based on the temperature overflow value. The temperature adjustment table includes the correspondence between the temperature overflow value and the adjustment voltage.

[0034] The real-time voltage of the battery under test is adjusted according to the adjustment voltage to reduce the temperature of the battery under test.

[0035] Furthermore, to achieve the above objectives, the present invention also proposes a battery temperature detection device, the battery temperature detection device comprising:

[0036] The parameter acquisition module is used to acquire the measured temperature of the battery under test, the ambient temperature at the current location of the battery under test, the real-time voltage value of the battery under test, and the remaining power of the battery under test.

[0037] The model verification module is used to determine the temperature compensation model based on the real-time voltage value of the battery under test and the remaining charge of the battery under test.

[0038] The compensation value confirmation module is used to input the ambient temperature, the real-time voltage value and the remaining power into the temperature compensation model to obtain the temperature compensation value.

[0039] A temperature compensation module is used to perform temperature compensation on the measured temperature according to the temperature compensation value to obtain the true temperature of the battery under test.

[0040] The temperature detection module is used to issue a temperature anomaly alert when the actual temperature is greater than the abnormal temperature.

[0041] In addition, to achieve the above objectives, the present invention also proposes a battery temperature detection device, which includes: a memory, a processor, and a battery temperature detection program stored in the memory and executable on the processor, wherein the battery temperature detection program is configured to implement the steps of the battery temperature detection method described above.

[0042] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing a battery temperature detection program, which, when executed by a processor, implements the steps of the battery temperature detection method described above.

[0043] This invention acquires the measured temperature of the battery under test, the ambient temperature at the current location of the battery, the real-time voltage value of the battery, and the remaining charge of the battery. Based on the real-time voltage value and the remaining charge of the battery, a temperature compensation model is determined. The ambient temperature, the real-time voltage value, and the remaining charge are input into the temperature compensation model to obtain a temperature compensation value. The measured temperature is then compensated based on this temperature compensation value to obtain the true temperature of the battery. If the true temperature exceeds the abnormal temperature, a temperature anomaly warning is issued. By confirming the battery's current operating mode and the current ambient temperature, a corresponding temperature compensation model is determined, and a corresponding temperature compensation value is obtained. The measured temperature is then compensated using this temperature compensation value to obtain the true battery temperature. Compared to existing technologies, this method avoids the influence of ambient temperature and the battery's current operating mode, resulting in more accurate battery temperature detection results. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of the structure of a battery temperature detection device for the hardware operating environment involved in the embodiments of the present invention;

[0045] Figure 2 This is a flowchart illustrating the first embodiment of the battery temperature detection method of the present invention;

[0046] Figure 3 This is a flowchart illustrating the second embodiment of the battery temperature detection method of the present invention;

[0047] Figure 4 This is a schematic diagram of the temperature compensation model of an embodiment of the battery temperature detection method of the present invention;

[0048] Figure 5 This is a structural block diagram of the first embodiment of the battery temperature detection device of the present invention.

[0049] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0050] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0051] Reference Figure 1 , Figure 1 This is a schematic diagram of the battery temperature detection device structure in the hardware operating environment involved in the embodiments of the present invention.

[0052] like Figure 1 As shown, the battery temperature detection device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0053] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the battery temperature detection device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0054] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a battery temperature detection program.

[0055] exist Figure 1In the battery temperature detection device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the battery temperature detection device of the present invention can be set in the battery temperature detection device, and the battery temperature detection device calls the battery temperature detection program stored in the memory 1005 through the processor 1001 and executes the battery temperature detection method provided in the embodiment of the present invention.

[0056] This invention provides a battery temperature detection method, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of a battery temperature detection method according to the present invention.

[0057] In this embodiment, the battery temperature detection method includes the following steps:

[0058] Step S10: Obtain the measured temperature of the battery under test, the ambient temperature at the current location of the battery under test, the real-time voltage value of the battery under test, and the remaining power of the battery under test.

[0059] It should be noted that the execution subject of this embodiment is a battery temperature detection device, which has functions such as data processing, data communication and program execution. The battery temperature detection device can be an integrated controller, a control computer or other devices with similar functions. This embodiment does not limit the scope of the invention.

[0060] It is understood that the measured temperature of the battery under test can be a temperature value obtained by a contact temperature measurement method, such as using a thermometer to measure the battery temperature, or it can be a non-contact temperature measurement method, such as using infrared temperature measurement technology to obtain the battery temperature. The ambient temperature refers to the air temperature in the area where the battery under test is located. The real-time voltage value and the remaining charge are corresponding parameters of the battery under test. The real-time voltage value refers to the voltage value of the battery at the current detection time, and the current remaining charge value refers to the charge in the battery.

[0061] In practical implementation, since battery safety and lifespan are easily affected by temperature, battery temperature is usually monitored. Methods for measuring battery temperature can be divided into contact and non-contact methods. For example, installing a temperature detector on the battery is a contact temperature measurement method, while installing an infrared camera at a certain distance from the battery and measuring temperature via infrared is a non-contact method. By measuring the temperature of the battery under test, the measured temperature can be used as the actual temperature and stored. When measuring the temperature of the battery under test, the ambient temperature of the location where the battery is located can also be measured. The measurement method can be the same as or different from the method used to measure the battery temperature; this embodiment does not impose any restrictions. Simultaneously, the current real-time voltage value and remaining charge of the battery under test need to be obtained through the detection device, and the real-time voltage value and remaining charge value are stored.

[0062] Step S20: Determine the temperature compensation model based on the real-time voltage value of the battery under test and the remaining charge of the battery under test.

[0063] It should be noted that the temperature compensation model is used to obtain the temperature compensation value for the battery under test based on the real-time voltage value of the battery under test and the estimated remaining power, etc., and the number of the temperature compensation models is at least one.

[0064] In practice, the temperature compensation model has a certain correspondence with the real-time voltage value and remaining charge value of the battery under test. When determining the specific temperature compensation model, the real-time voltage value and the remaining charge value obtained by the detection device can be compared with the correspondence. The temperature compensation model corresponding to the current real-time voltage value and the remaining charge value of the battery under test can be obtained by looking up a table. For example, under the same real-time voltage value, different remaining charges can also correspond to different temperature compensation models. Similarly, when there is the same remaining charge value, the temperature compensation models corresponding to different real-time voltage values ​​are also different. In different temperature compensation models, the degree of temperature compensation is not exactly the same.

[0065] Further, determining the temperature compensation model based on the real-time voltage value of the battery under test and the remaining charge of the battery under test includes:

[0066] The voltage change rate and the remaining charge change rate are obtained based on the real-time voltage value and the remaining charge of the battery under test;

[0067] The operating mode of the battery under test is determined based on the voltage change rate and the remaining charge change rate.

[0068] According to the operating mode, a temperature compensation model corresponding to the operating mode is matched in the temperature compensation model library, which includes at least one temperature compensation model.

[0069] It should be noted that the voltage change rate and the charge change rate refer to the real-time voltage change and remaining charge change of the battery during the detection period. The current battery operating mode can be determined based on the voltage change rate and the charge change rate. The temperature compensation model library is a collection of various temperature compensation models.

[0070] In specific implementation, the rate of change of voltage and the rate of change of remaining charge of the battery under test can be determined based on the real-time voltage value and the remaining charge value of the battery under test. First, the real-time voltage value and the remaining charge of the battery under test are obtained for several consecutive detection cycles. The rate of change of voltage and the remaining charge of the battery under test during this period are calculated. The rate of change of voltage can be divided into three states: static state, standby state, and working state. The static state indicates that the battery is not currently working, neither discharging nor charging. The standby state refers to the battery operating at a lower voltage. The working state refers to the battery operating at a higher voltage. At the same time, the rate of change of battery charge can also be divided into three states: charge increase state, charge maintenance state, and charge decrease state. Therefore, the working mode of the battery can be divided into charging mode, discharging mode, float charging mode, and static mode. After determining the working mode, the temperature compensation model library is traversed according to the working mode to obtain the temperature compensation model corresponding to the working mode.

[0071] Step S30: Input the ambient temperature, the real-time voltage value, and the remaining power into the temperature compensation model to obtain the temperature compensation value.

[0072] It should be noted that the temperature compensation value refers to the correction of the measured temperature, which is used to correct the current measured temperature value. The temperature compensation value is determined by the ambient temperature, real-time voltage value, and remaining power. Therefore, the corresponding temperature compensation value may be the same or different under different ambient temperatures, real-time voltage values, and remaining power.

[0073] In a specific implementation, the battery temperature detection device can input the ambient temperature of the battery under test, the real-time voltage value of the battery under test, and the remaining power into the corresponding temperature compensation model. The temperature compensation model determines the corresponding temperature compensation value according to the actual situation of the battery under test. When the battery is working, the real-time voltage value inside the battery will affect the heat generation value of the battery per unit time, which will cause the battery temperature to change. The battery temperature can further affect the battery capacity and the relative remaining power of the battery. The amount of power in the battery can also affect the battery's heat generation.

[0074] Further, the step of inputting the ambient temperature, the real-time voltage value, and the remaining power into the temperature compensation model to obtain the temperature compensation value includes:

[0075] Determine the model type of the temperature compensation model;

[0076] Based on the model type and the ambient temperature, the temperature compensation correspondence is found to obtain the temperature compensation coefficient;

[0077] The temperature compensation value is obtained based on the real-time voltage value, the remaining power, and the temperature compensation coefficient.

[0078] In the specific implementation, the type of the currently matched temperature compensation model is first determined. Based on the temperature compensation model and the current ambient temperature, a temperature compensation correspondence is determined, resulting in a temperature compensation coefficient. Since ambient temperature interferes with battery temperature detection, the temperature compensation correspondence needs to be determined based on the ambient temperature of the battery under test. For the same voltage change rate and charge change rate, the corresponding temperature compensation coefficients are not entirely the same under different ambient temperatures. After obtaining the temperature compensation coefficient, the temperature compensation value can be predicted based on the real-time voltage value and the remaining charge value. The temperature compensation correspondence is generated during model training based on historical test data. A curve is fitted based on the temperature compensation correspondence, meaning that a corresponding temperature compensation value can be obtained regardless of the real-time voltage value or the remaining charge value.

[0079] Step S40: Perform temperature compensation on the measured temperature according to the temperature compensation value to obtain the true temperature of the battery under test.

[0080] It should be noted that the actual temperature is the true temperature of the battery. There is a certain difference between the actual temperature and the measured temperature. Due to heat dissipation from the air and the battery casing, the measured battery temperature will be lower than the actual battery temperature.

[0081] In a specific implementation, based on the ambient temperature of the location of the battery under test, the real-time voltage value of the battery, and the remaining power of the battery, the ambient temperature, real-time voltage value, and remaining power are input into the temperature compensation model. The temperature compensation model calculates and obtains a temperature compensation value. Based on the temperature compensation value and the measured temperature of the battery under test, temperature compensation is performed to obtain the true temperature, which reflects the actual temperature of the battery.

[0082] Step S50: When the actual temperature is greater than the abnormal temperature, issue a temperature abnormality warning.

[0083] It should be noted that the abnormal temperature value is the temperature at which the battery would encounter dangerous or other abnormal situations during operation. Since the temperature change is not abrupt, the abnormal temperature can be set slightly lower than the temperature at which danger would occur, thereby ensuring that the battery temperature does not reach the dangerous temperature value.

[0084] In practical implementation, since the temperature change of an object is continuous and has a certain thermal inertia, the abnormal temperature setting needs to be set slightly lower than the temperature that would cause battery malfunction. For example, assuming that a battery temperature of 60°C would pose a danger, the abnormal temperature could be set to 59°C, 59.5°C, 59.7°C, etc., slightly lower than the danger temperature, to prevent the temperature from rising to the battery's danger temperature due to thermal inertia and causing a dangerous situation. After obtaining the battery's true temperature through temperature compensation, the true temperature is compared with the abnormal temperature. If the true temperature is lower than the abnormal temperature, the battery temperature is continuously monitored. If the true temperature is higher than the abnormal temperature, a temperature abnormality warning can be issued. When a temperature abnormality warning is issued, an alarm can be used to send an audible and visual signal to relevant personnel, and the battery abnormality can also be sent to a remote user via remote communication.

[0085] Furthermore, after issuing a temperature anomaly alert when the actual temperature is greater than the abnormal temperature, the system also includes:

[0086] The temperature overflow value is obtained based on the actual temperature and the abnormal temperature value;

[0087] The adjustment voltage is obtained by looking up the temperature adjustment table based on the temperature overflow value. The temperature adjustment table includes the correspondence between the temperature overflow value and the adjustment voltage.

[0088] The real-time voltage of the battery under test is adjusted according to the adjustment voltage to reduce the temperature of the battery under test.

[0089] It should be noted that the temperature overflow value refers to the portion of the actual temperature that is greater than the abnormal value, which can be understood as the temperature value that exceeds the abnormal temperature value. The temperature adjustment table is a table showing the correspondence between the temperature overflow value and the adjustment voltage obtained after testing.

[0090] In practical implementation, after temperature compensation is performed on the measured temperature, the actual temperature needs to be compared with the abnormal temperature. The difference between the actual temperature value and the abnormal temperature value is the temperature overflow value. Based on the temperature overflow value, the temperature adjustment table is traversed to obtain the adjustment voltage that needs to be limited. The correspondence between the temperature overflow value and the adjustment voltage can be a function mapping relationship. After the adjustment voltage is determined, the real-time voltage value can be limited based on the real-time voltage of the battery to reduce the real-time temperature value of the battery, thereby reducing the heat generation of the battery, thus reducing the battery temperature and protecting the battery safety.

[0091] This embodiment acquires the measured temperature of the battery under test, the ambient temperature at the current location of the battery, the real-time voltage value of the battery, and the remaining charge of the battery. Based on the real-time voltage value and the remaining charge of the battery, a temperature compensation model is determined. The ambient temperature, the real-time voltage value, and the remaining charge are input into the temperature compensation model to obtain a temperature compensation value. The measured temperature is then compensated based on this temperature compensation value to obtain the true temperature of the battery. If the true temperature exceeds the abnormal temperature, a temperature anomaly warning is issued. By confirming the battery's current operating mode and the current ambient temperature, a corresponding temperature compensation model is determined, and a corresponding temperature compensation value is obtained. The measured temperature is then compensated using this temperature compensation value to obtain the true battery temperature. Compared to existing technologies, this method avoids the influence of ambient temperature and the battery's current operating mode, resulting in more accurate battery temperature detection results.

[0092] refer to Figure 3 , Figure 3 This is a flowchart illustrating a second embodiment of a battery temperature detection method according to the present invention.

[0093] Based on the first embodiment described above, the battery temperature detection method of this embodiment further includes, before step S20:

[0094] Step S201: Collect the historical data set of the battery under test according to the preset collection frequency. The historical data set includes historical voltage value, historical remaining power and historical ambient temperature.

[0095] Step S202: Divide the collected data set into a training dataset and a validation dataset.

[0096] Step S203: Train the preset model according to the training dataset to obtain the temperature compensation model, and add the temperature compensation model to the temperature compensation model library.

[0097] It should be noted that the preset sampling frequency is a manually set sampling frequency, which is the same as the temperature detection frequency. The sampling frequency is preferably 1 second, but it can be reasonably set according to the actual application scenario. This embodiment does not impose any restrictions on this.

[0098] In the specific implementation, data of the battery under test is collected according to a preset collection frequency. This data includes voltage, remaining charge, and ambient temperature. During data collection, the voltage, remaining charge, and ambient temperature are stored as historical data in a historical data set, which includes historical voltage, historical remaining charge, and historical ambient temperature. The historical data set can then be divided into a training dataset and a validation dataset according to a preset ratio. Preferably, 80% of the data is used as the training dataset and 20% as the validation dataset. The training dataset is used to train a preset model to obtain a temperature compensation model, and the validation dataset is used to validate the trained temperature compensation model. Finally, the obtained temperature compensation model is stored in a temperature compensation model library.

[0099] Further, the step of training the initial temperature compensation model based on the training dataset to obtain the temperature compensation model includes:

[0100] The real-time voltage values, remaining power, and ambient temperature in the training dataset are normalized to obtain a normalized training dataset.

[0101] The normalized dataset is input into the neurons in the hidden layer, and training values ​​are obtained according to preset weight values ​​and bias values. The training values ​​are then input into the next neuron until the last neuron, to obtain the output value of the hidden layer.

[0102] The hidden layer output value is compared with the expected output. When the training value meets the expected output, the training ends and the temperature compensation model is obtained.

[0103] In the specific implementation, the initial temperature compensation model is trained using the training dataset. The real-time voltage values, remaining power, and ambient temperature in the training dataset are normalized to obtain a normalized dataset. The preferred normalization method is Z-score standardization, resulting in a processed dataset with a mean of 0 and a standard deviation of 1. The transformation formula is as follows:

[0104]

[0105] Where x′ is the normalized data, x is the original data, μ is the mean of the original data, and δ is the standard deviation of the original data.

[0106] The normalized data is stored in a normalized dataset, and the normalized data is input into a preset model, which can be a recurrent neural network (RNN). Figure 4 , Figure 4 The diagram illustrates the structure of a temperature compensation model. The normalized real-time voltage value, remaining battery power, and ambient temperature are input into the input layer of the preset model. This input layer comprises at least three input neurons. After passing through the input layer, the normalized data enters the neurons of the hidden layer. Iterative training is performed based on preset weights and biases. After a preset number of iterations, the output value of the hidden layer is obtained. Based on a preset expectation, the output value of the trained model can be determined. When the output value meets the preset expectation, the training of the temperature compensation model ends, and the model is stored in a temperature model library.

[0107] Further, after comparing the hidden layer output value with the expected output, and ending the training when the training value meets the expected output to obtain the temperature compensation model, the process further includes:

[0108] The data in the verification dataset is input into the temperature compensation model to obtain the verification temperature compensation value;

[0109] The error value is obtained by comparing the verified temperature compensation value with the true value in the verified dataset.

[0110] The error value is compared with a preset error. When the error value is greater than the preset error, the weight value and the bias value are corrected according to the error value to obtain the corrected temperature compensation model.

[0111] In specific implementation, after the temperature compensation model is trained, its accuracy needs to be verified. Therefore, data from the verification dataset is input into the temperature compensation model, and a verification temperature compensation value is obtained based on the model. Simultaneously, the verification temperature compensation value is compared with the corresponding true value in the verification dataset to obtain the error value between the true value and the verification temperature compensation value. When the error value is greater than a preset error, the weight values ​​and bias values ​​are corrected based on the error value to obtain a corrected temperature compensation model. When correcting the weight values ​​and bias values, the error value can be used to correct them, ensuring that the error between the verification temperature compensation value obtained by the temperature compensation model and the corresponding true value of the input value in the verification dataset is within a preset error range. If the error value is within the preset error range, the temperature compensation model can be stored as a trained temperature compensation model in the temperature compensation model library.

[0112] This embodiment normalizes historical data to reduce its magnitude and computational complexity. By dividing the historical data into training and validation datasets, a preset model is trained and the trained temperature compensation model is validated. By continuously adjusting the weights and biases in the preset model, the accuracy of the temperature compensation model is continuously improved, ensuring that the error between the output value and the true value is within a preset error range. This improves the accuracy of the temperature compensation model, thereby achieving accurate temperature compensation and ultimately obtaining the true temperature of the battery, thus enabling accurate temperature detection.

[0113] Furthermore, embodiments of the present invention also propose a storage medium storing a battery temperature detection program, wherein the battery temperature detection program, when executed by a processor, implements the steps of the battery temperature detection method described above.

[0114] Reference Figure 5 , Figure 5 This is a structural block diagram of the first embodiment of the battery temperature detection device of the present invention.

[0115] like Figure 5 As shown, the battery temperature detection device proposed in this embodiment of the invention includes:

[0116] The parameter acquisition module 10 is used to acquire the measured temperature of the battery under test, the ambient temperature at the current location of the battery under test, the real-time voltage value of the battery under test, and the remaining power of the battery under test.

[0117] Model verification module 20 is used to determine the temperature compensation model based on the real-time voltage value of the battery under test and the remaining charge of the battery under test.

[0118] The compensation value confirmation module 30 is used to input the ambient temperature, the real-time voltage value and the remaining power into the temperature compensation model to obtain the temperature compensation value.

[0119] Temperature compensation module 40 is used to perform temperature compensation on the measured temperature according to the temperature compensation value to obtain the true temperature of the battery under test.

[0120] The temperature detection module 50 is used to issue a temperature abnormality prompt when the actual temperature is greater than the abnormal temperature.

[0121] This embodiment acquires the measured temperature of the battery under test, the ambient temperature at the current location of the battery, the real-time voltage value of the battery, and the remaining charge of the battery. Based on the real-time voltage value and the remaining charge of the battery, a temperature compensation model is determined. The ambient temperature, the real-time voltage value, and the remaining charge are input into the temperature compensation model to obtain a temperature compensation value. The measured temperature is then compensated based on this temperature compensation value to obtain the true temperature of the battery. If the true temperature exceeds the abnormal temperature, a temperature anomaly warning is issued. By confirming the battery's current operating mode and the current ambient temperature, a corresponding temperature compensation model is determined, and a corresponding temperature compensation value is obtained. The measured temperature is then compensated using this temperature compensation value to obtain the true battery temperature. Compared to existing technologies, this method avoids the influence of ambient temperature and the battery's current operating mode, resulting in more accurate battery temperature detection results.

[0122] In one embodiment, the model verification module 20 is further configured to obtain the voltage change rate and the remaining charge change rate based on the real-time voltage value and the remaining charge of the battery under test; determine the operating mode of the battery under test based on the voltage change rate and the remaining charge change rate; and match a temperature compensation model corresponding to the operating mode in a temperature compensation model library based on the operating mode, wherein the temperature compensation model library includes at least one temperature compensation model.

[0123] In one embodiment, the model confirmation module 20 is further configured to determine the model type of the temperature compensation model; find the temperature compensation correspondence between the model type and the ambient temperature to obtain the temperature compensation coefficient; and obtain the temperature compensation value based on the real-time voltage value, the remaining power, and the temperature compensation coefficient.

[0124] In one embodiment, the model verification module 20 is further configured to collect a set of historical data of the battery under test according to a preset collection frequency, the set of historical data including historical voltage values, historical remaining power and historical ambient temperature; divide the set of data into a training dataset and a validation dataset; train a preset model according to the training dataset to obtain a temperature compensation model, and add the temperature compensation model to a temperature compensation model library.

[0125] In one embodiment, the model verification module 20 is further configured to normalize the real-time voltage value, remaining power, and ambient temperature in the training dataset to obtain a normalized training dataset; input the normalized dataset into neurons in the hidden layer, obtain training values ​​according to preset weight values ​​and bias values, and input the training values ​​into the next neuron until the last neuron to obtain the hidden layer output value; compare the hidden layer output value with the expected output, and when the training value meets the expected output, end the training to obtain the temperature compensation model.

[0126] In one embodiment, the model verification module 20 is further configured to input data from the verification dataset into the temperature compensation model to obtain a verification temperature compensation value; compare the verification temperature compensation value with the true value in the verification dataset to obtain an error value; compare the error value with a preset error; and when the error value is greater than the preset error, correct the weight value and the bias value according to the error value to obtain a corrected temperature compensation model.

[0127] In one embodiment, the temperature detection module 50 is further configured to obtain a temperature overflow value based on the actual temperature and the abnormal temperature value; look up an adjustment voltage in a temperature adjustment table based on the temperature overflow value, the temperature adjustment table including the correspondence between the temperature overflow value and the adjustment voltage; and adjust the real-time voltage of the battery under test based on the adjustment voltage to lower the temperature of the battery under test.

[0128] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0129] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0130] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0131] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0132] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0133] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A battery temperature detection method characterized by, The battery temperature detection method comprises: acquiring a measured temperature of a battery to be measured, an ambient temperature of a current location where the battery to be measured is located, a real-time voltage value of the battery to be measured, and a remaining capacity of the battery to be measured; determining a temperature compensation model according to the real-time voltage value of the battery to be measured and the remaining capacity of the battery to be measured; inputting the ambient temperature, the real-time voltage value, and the remaining capacity into the temperature compensation model to obtain a temperature compensation value; carrying out temperature compensation on the measured temperature according to the temperature compensation value to obtain an actual temperature of the battery to be measured; when the actual temperature is greater than an abnormal temperature, issuing a temperature abnormality prompt; wherein the determining of the temperature compensation model according to the real-time voltage value of the battery to be measured and the remaining capacity of the battery to be measured comprises: obtaining a voltage change rate and a remaining capacity change rate according to the real-time voltage value and the remaining capacity of the battery to be measured; determining a working mode of the battery to be measured according to the voltage change rate and the remaining capacity change rate; matching a temperature compensation model corresponding to the working mode in a temperature compensation model library according to the working mode, the temperature compensation model library comprising at least one temperature compensation model; the inputting of the ambient temperature, the real-time voltage value, and the remaining capacity into the temperature compensation model to obtain the temperature compensation value comprises: determining a model type of the temperature compensation model; finding a temperature compensation corresponding relationship according to the model type and the ambient temperature to obtain a temperature compensation coefficient; obtaining the temperature compensation value according to the real-time voltage value, the remaining capacity, and the temperature compensation coefficient.

2. The method of claim 1, wherein, before the determining of the temperature compensation model according to the real-time voltage value of the battery to be measured and the remaining capacity of the battery to be measured, the method further comprises: collecting a historical collection data set of the battery to be measured according to a preset collection frequency, the historical collection data set comprising a historical voltage value, a historical remaining capacity, and a historical ambient temperature; dividing the collection data set into a training data set and a verification data set; training a preset model according to the training data set to obtain a temperature compensation model, and adding the temperature compensation model to a temperature compensation model library.

3. The method of claim 2, wherein, the training of the initial temperature compensation model according to the training data set to obtain the temperature compensation model comprises: normalizing the real-time voltage value, the remaining capacity, and the ambient temperature in the training data set to obtain a normalized training data set; inputting the normalized training data set into neurons in a hidden layer to obtain training values according to preset weight values and bias values, and inputting the training values into next neurons until a last neuron to obtain a hidden layer output value; comparing the hidden layer output value with an expected output, and ending the training when the training values meet the expected output to obtain the temperature compensation model.

4. The method of claim 3, wherein, after the comparing of the hidden layer output value with the expected output and the ending of the training when the training values meet the expected output to obtain the temperature compensation model, the method further comprises: inputting data in the verification data set into the temperature compensation model to obtain a verification temperature compensation value; The verification temperature compensation value is compared with the true value in the verification data set to obtain an error value; The error value is compared with a preset error, and when the error value is greater than the preset error, the weight value and the bias value are corrected according to the error value to obtain a corrected temperature compensation model.

5. The method of claim 1, wherein, After the temperature anomaly prompt is sent when the true temperature is greater than the abnormal temperature, the method further includes: A temperature overflow value is obtained according to the true temperature and the abnormal temperature value; An adjustment voltage is obtained by searching a temperature adjustment table according to the temperature overflow value, the temperature adjustment table including a corresponding relationship between a temperature overflow value and an adjustment voltage; The real-time voltage of the battery under test is adjusted according to the adjustment voltage, so that the temperature of the battery under test is reduced.

6. A battery temperature detecting device characterized by comprising: The battery temperature detection device includes: A parameter acquisition module is configured to acquire a measured temperature of a battery under test, an ambient temperature of a current location where the battery under test is located, a real-time voltage value of the battery under test, and a remaining capacity of the battery under test; A model confirmation module is configured to determine a temperature compensation model according to the real-time voltage value of the battery under test and the remaining capacity of the battery under test; A compensation value confirmation module is configured to input the ambient temperature, the real-time voltage value, and the remaining capacity into the temperature compensation model to obtain a temperature compensation value; A temperature compensation module is configured to perform temperature compensation on the measured temperature according to the temperature compensation value to obtain a true temperature of the battery under test; A temperature detection module is configured to send a temperature anomaly prompt when the true temperature is greater than an abnormal temperature. The determination of the temperature compensation model according to the real-time voltage value of the battery under test and the remaining capacity of the battery under test includes: A voltage change rate and a remaining capacity change rate are obtained according to the real-time voltage value and the remaining capacity of the battery under test; A working mode of the battery under test is determined according to the voltage change rate and the remaining capacity change rate; A temperature compensation model corresponding to the working mode is matched in a temperature compensation model library according to the working mode, the temperature compensation model library including at least one temperature compensation model. The input of the ambient temperature, the real-time voltage value, and the remaining capacity into the temperature compensation model to obtain a temperature compensation value includes: A model type of the temperature compensation model is determined; A temperature compensation coefficient is obtained by searching a temperature compensation corresponding relationship according to the model type and the ambient temperature; A temperature compensation value is obtained according to the real-time voltage value, the remaining capacity, and the temperature compensation coefficient.

7. A battery temperature detecting apparatus characterized by comprising: The device includes a memory, a processor, and a battery temperature detection program stored on the memory and executable on the processor, the battery temperature detection program being configured to implement the steps of the battery temperature detection method according to any one of claims 1 to 5.

8. A storage medium, characterized by The storage medium stores a battery temperature detection program, and the battery temperature detection program is executed by the processor to implement the steps of the battery temperature detection method according to any one of claims 1 to 5.

Images