Battery temperature prediction and control method and device and storage medium

Abstract

The invention provides a battery temperature prediction and control method and device and a storage medium. The prediction method comprises the steps that values of relevant parameters capable of influencing the battery temperature in the equipment at corresponding moments are obtained, the corresponding moments comprise historical moments, or the corresponding moments comprise the historical moments and the current moment; and predicting the temperature of the battery at the future first moment according to the value of the relevant parameter at the corresponding moment, the temperature of the battery at the corresponding moment and the degree of influence of the relevant parameter on the temperature change of the battery. The control method comprises the step of selecting corresponding processing according to the temperature predicted by the prediction method, and the processing can improve the temperature of the battery at the future moment. According to the scheme provided by the invention, the temperature of the battery at the future moment can be predicted, so that corresponding treatment can be taken in advance when the battery temperature is predicted to be too high or too low, and a battery fault caused by temperature abnormality is expected to be avoided.

Description

Technical Field

[0001] The present application relates to the field of batteries, and in particular to a method, device and storage medium for predicting and controlling battery temperature. Background Art

[0002] In the field of new energy, batteries can provide power for vehicles (such as cars) and drive the motors and control systems of vehicles. The life, capacity and performance of batteries are affected by the battery temperature. If the battery temperature is too high or too low, the capacity or voltage of the battery may drop, affecting the normal operation of the vehicle. In order to ensure the safety of batteries in vehicles, the battery temperature needs to be controlled within an appropriate range.

[0003] Currently, the battery temperature can be monitored by the battery management system (BMS) on the vehicle. When the battery temperature is too high or too low, the temperature controller on the vehicle will send an alarm signal to remind the user to take measures. Alternatively, when the battery temperature is too high or too low, the BMS can control the battery temperature within an appropriate range. However, the above-mentioned BMS monitoring or controlling battery temperature is only used when the battery temperature is already too high or too low, which is relatively lagging and cannot avoid problems caused by the battery temperature being too high or too low. Summary of the invention

[0004] In view of the above problems, the present application provides a battery temperature prediction and control method, device and storage medium, which can predict the temperature of the battery at a future time, so that when it is predicted that the battery temperature is too high or too low, corresponding processing can be taken in advance to avoid battery failure caused by abnormal temperature.

[0005] In a first aspect, a method for predicting battery temperature is provided. The method comprises:

[0006] Obtain the value of a relevant parameter that can affect the temperature of a battery in a device at a corresponding moment, wherein the corresponding moment includes a historical moment, or the corresponding moment includes a historical moment and a current moment; predict the temperature of the battery at a first moment in the future based on the value of the relevant parameter at the corresponding moment, the temperature of the battery at the corresponding moment, and the degree to which the relevant parameter affects the change in the battery temperature.

[0007] In the technical solution of the embodiment of the present application, the temperature of the battery at a future moment can be predicted based on the values ​​of relevant parameters at a corresponding moment, the temperature of the battery at a corresponding moment, and the degree to which the relevant parameters affect the temperature change of the battery. If it is predicted that the temperature of the battery at a future moment will be abnormal, such as the temperature is too high or too low, which can cause battery failure, corresponding processing measures can be taken in advance to avoid battery failure caused by temperature. Compared with taking processing measures after the battery temperature has become abnormal, battery failure can be prevented in advance, damage to the battery can be reduced, and the impact on the normal operation of equipment using the battery can be reduced.

[0008] In some embodiments, the acquiring of the values ​​of the relevant parameters that can affect the temperature of the battery in the device at the corresponding time includes: acquiring the values ​​of the relevant parameters at the corresponding time from a local location.

[0009] In this embodiment, the prediction method can be executed in the cloud. Since the cloud has a large storage space, the values ​​of relevant parameters at the corresponding time can be stored in the cloud. In the process of predicting the temperature, the data used to predict the temperature can be directly obtained locally from the cloud, reducing the delay in obtaining the values ​​of relevant parameters. In addition, the cloud has strong computing power, which can improve the speed of predicting the temperature.

[0010] In some embodiments, when the corresponding moment only includes historical moments, obtaining the value of the relevant parameter that can affect the temperature of the battery in the device at the corresponding moment includes:

[0011] Obtaining the value of the relevant parameter at the historical moment from the cloud; when the corresponding moment includes the current moment and the historical moment, obtaining the value of the relevant parameter that can affect the battery temperature in the device at the corresponding moment includes: obtaining the value of the relevant parameter at the current moment from the local; obtaining the value of the relevant parameter at the historical moment from the cloud.

[0012] In this embodiment, the prediction method can be executed on the device side using the battery, combining the real-time data obtained from the local device and the historical data obtained from the cloud to predict the temperature at a future time. If it is predicted that the temperature of the battery will be abnormal at a future time, corresponding processing measures can be taken in advance to avoid battery failure caused by temperature. In addition, there is no need to store the relevant data corresponding to the historical time locally on the device side, thus saving local storage space on the vehicle side.

[0013] In some embodiments, predicting the temperature of the battery at a first moment in the future according to the value of the relevant parameter at the corresponding moment, the temperature of the battery at the corresponding moment, and the degree to which the relevant parameter affects the change in battery temperature includes:

[0014] Determine a first weight value corresponding to the relevant parameter, the first weight value representing the contribution of the relevant parameter to the result of battery failure; determine a second weight value corresponding to the relevant parameter according to the value of the relevant parameter at the corresponding moment, the second weight value representing the contribution of the value of the relevant parameter at the corresponding moment to the change in battery temperature; predict the temperature of the battery at a first moment in the future according to the first weight value, the second weight value and the temperature of the battery at the corresponding moment.

[0015] In this embodiment, the first weight value is calculated for the battery that has failed. In the specific calculation process, the contribution of different related parameters to the failure of the failed battery can be counted. The second weight value can be calculated according to the degree to which the real-time values ​​of the related parameters affect the battery temperature. Therefore, combining the first weight value and the second weight value to predict the temperature takes into account both the statistical laws of big data and the real-time values ​​of the related parameters, so that the predicted result is consistent with the actual situation of battery use while complying with the statistical laws, and is more accurate.

[0016] In some embodiments, the method further comprises:

[0017] Acquire a first weight value sequence corresponding to the battery that has failed, the first weight value sequence including a third weight value corresponding to each of the relevant parameters, any of the third weight values ​​being determined based on a first weight value and a second weight value corresponding to the corresponding relevant parameter at the moment when the battery that has failed failed;

[0018] Predicting the temperature of the battery at a first moment in the future according to the first weight value, the second weight value, and the temperature of the battery at the corresponding moment includes:

[0019] Determine a plurality of second weight value sequences corresponding to a plurality of corresponding moments, wherein the plurality of corresponding moments correspond to the plurality of second weight value sequences one-to-one, and any of the second weight value sequences includes a fourth weight value corresponding to each of the relevant parameters, and the fourth weight value is determined based on the first weight value and the second weight value corresponding to the corresponding relevant parameter at the corresponding moment; predict the temperature of the battery at the first moment based on the plurality of second weight value sequences, the first weight value sequence, and the temperature of the battery at the plurality of corresponding moments.

[0020] In this embodiment, the first weight value and the second weight value corresponding to each relevant parameter of the failed battery are calculated to obtain a third weight value, and the third weight value corresponding to each relevant parameter forms a first weight value sequence. The first weight value and the second weight value corresponding to each relevant parameter at multiple corresponding moments are further calculated in real time according to the actual use of the battery to obtain a fourth weight value, and the fourth weight value corresponding to each relevant parameter forms a second weight value sequence. One corresponding moment corresponds to one second weight value sequence. Finally, the multiple second weight value sequences calculated in real time are compared with the first weight value sequence as a benchmark. During the comparison process, the third weight value and the fourth weight value corresponding to each relevant parameter can be compared, so as to more accurately predict the temperature of the battery at future moments.

[0021] In some embodiments, predicting the temperature of the battery at the first moment according to the plurality of second weight value sequences, the first weight value sequence, and the temperature of the battery at the plurality of corresponding moments includes:

[0022] A first risk index is obtained by summing the third weight value in the first weight value sequence; a plurality of second risk indices are determined according to the plurality of second weight value sequences, the plurality of second weight value sequences and the plurality of second risk indices correspond one to one, and any second risk index is the sum of the fourth weight values ​​included in the corresponding second weight value sequence; and the temperature of the battery at the first moment is predicted based on the plurality of second risk indices, the first risk index, and the battery temperatures corresponding to the plurality of second risk indices and the first risk index.

[0023] In this embodiment, the third weight value in the first weight value sequence is summed to obtain the first risk index, and the fourth weight value in the second weight value sequence is further summed to obtain the second risk index. One corresponding moment corresponds to one second risk index. Finally, the multiple second risk indices calculated in real time are compared with the benchmark calculated based on the relevant data of the failed battery, that is, the first risk index. The comparison process does not involve comparison of a large amount of data and is relatively simple.

[0024] In some embodiments, predicting the temperature of the battery at the first moment based on the multiple second risk indexes, the first risk index, and the battery temperatures corresponding to the multiple second risk indexes and the first risk index includes:

[0025] In the case where the multiple second risk indices change monotonically over time, the second risk index corresponding to the first moment is determined based on the multiple second risk indices and the multiple corresponding moments; and the temperature of the battery at the first moment is predicted based on the second risk index corresponding to the first moment and the battery temperature, the first risk index, and the battery temperature corresponding to the first risk index.

[0026] In this embodiment, the subsequent prediction calculation is performed only when the calculated multiple second risk indices change monotonically over time, so as to avoid the problem that the temperature predicted based on the multiple second risk indices is inaccurate when the second risk indices corresponding to multiple consecutive moments do not change monotonically over time, that is, when the second risk indices corresponding to consecutive moments do not change stably.

[0027] In some embodiments, the step of obtaining a first weight value sequence corresponding to a battery that has failed includes:

[0028] The first weight value sequence is updated according to a third weight value sequence corresponding to a battery that has failed, wherein a sum of third weight values ​​included in the third weight value sequence is less than a first risk index; and the updated first weight value sequence is obtained.

[0029] In this embodiment, as the number of failed batteries increases, the first weight value sequence serving as a comparison benchmark must also be updated according to the third weight value sequence corresponding to the newly added failed batteries, so that subsequent predictions can be calculated based on the updated benchmark, making the predicted temperature more accurate and more in line with actual conditions.

[0030] In some embodiments, determining a first weight value corresponding to the relevant parameter includes:

[0031] The first weight value is determined according to the values ​​of the relevant parameters at the moment when the faulty battery fails and a hierarchy analysis method.

[0032] In this embodiment, the characteristics of the hierarchical analysis method are combined: the weight setting of each layer will directly or indirectly affect the result of battery failure, and the influence of each relevant parameter in each layer on the result is quantified and very clear, so that the contribution of each relevant parameter to the result of battery failure can be calculated more accurately, thereby being more inclined when predicting temperature.

[0033] In some embodiments, determining the second weight value corresponding to the relevant parameter according to the value of the relevant parameter includes:

[0034] The second weight value is determined according to the value of the relevant parameter at the corresponding moment and the first weight value.

[0035] In this embodiment, for any relevant parameter, the second weight value is not only affected by the specific value of the relevant parameter at the corresponding moment, but also by the first weight value corresponding to the relevant parameter obtained based on statistics. This takes into account both statistical laws and actual battery usage.

[0036] In a second aspect, a method for controlling battery temperature is provided. The method comprises:

[0037] According to the method provided in the first aspect, the temperature of a battery in a device at a first moment in the future is predicted; and a process is selected based on the temperature, the process being used to improve the temperature of the battery at the first moment.

[0038] In the technical solution of the embodiment of the present application, after predicting the battery temperature at a future time, it is necessary to select corresponding processing according to the predicted temperature. For example, in the case of predicting abnormal battery temperature, the corresponding processing is selected in advance to improve the battery temperature at a future time, in order to avoid abnormal battery temperature at a future time, thereby causing battery failure. Compared with taking processing measures after the battery temperature has become abnormal, it is possible to prevent battery failure in advance, reduce damage to the battery, and thus reduce the impact on the normal operation of the equipment using the battery.

[0039] In some embodiments, selecting a process based on the temperature includes:

[0040] A range to which the temperature belongs is determined based on the temperature; and the process is selected based on the range to which the temperature belongs.

[0041] In this embodiment, the temperature range and the processing can be mapped one by one, and the corresponding relationship can be set in advance. After the temperature is predicted, the corresponding processing can be selected directly based on the range of the predicted temperature, reducing the process of deciding the processing method after predicting the temperature, and improving the speed and efficiency of temperature control.

[0042] In some embodiments, the range of the temperature determined based on the temperature is greater than or equal to a first threshold, or less than or equal to a second threshold, wherein the first threshold is greater than the second threshold, and when the temperature of the battery is greater than or equal to the first threshold, or less than or equal to the second threshold, the battery will fail.

[0043] In this embodiment, the battery temperature range is divided based on whether the battery will fail, so that corresponding processing can be set for the temperature range where the battery will fail, so that the battery will not fail after the processing.

[0044] In some embodiments, selecting the process based on the scope includes:

[0045] The battery is stopped from being used before the first time based on the belonging range.

[0046] In this embodiment, the predicted temperature can be executed on the device side. If the predicted battery temperature falls within a range that will cause the battery to fail, the device can directly choose to stop using the battery before the first moment in the future, or can choose to stop using the battery immediately when the temperature is predicted, so as to avoid the battery from failing at the first moment. The control strategy is decided and executed locally, and the control speed is faster.

[0047] In some embodiments, selecting the process based on the scope includes:

[0048] Based on the range, first indication information is sent to the device, where the first indication information instructs the device to stop using the battery before the first moment, or the first indication information indicates the range to which the temperature belongs.

[0049] In this embodiment, the predicted temperature can be executed in the cloud. If the predicted battery temperature falls within a range that will cause the battery to fail, the device can directly choose to instruct the device to stop using the battery before the first moment in the future, or it can indicate the predicted temperature range and let the vehicle side decide on the battery treatment measures to avoid battery failure at the first moment as much as possible.

[0050] In some embodiments, the temperature range determined based on the temperature is less than a first threshold and greater than a third threshold. When the temperature of the battery is greater than or equal to the first threshold, the battery will fail. The third threshold is the upper limit temperature for normal operation of the battery.

[0051] In this embodiment, the battery temperature range is divided based on whether the battery will fail and whether the battery temperature exceeds the normal operating temperature, so that corresponding processing can be set for the battery that will not fail but exceeds the normal operating temperature range, so that the processed battery will not fail and can be within the normal operating temperature range, reducing the hidden danger of battery failure.

[0052] In some embodiments, selecting the process based on the scope includes:

[0053] A cooling system for the battery is selectively activated based on the range.

[0054] In this embodiment, the predicted temperature can be executed on the device side. If the predicted battery temperature belongs to a range that will cause the battery to exceed the normal operating upper limit, the device can directly choose to turn on the battery cooling system to cool the battery, thereby preventing the battery temperature from exceeding the normal operating upper limit at the first moment, which may cause battery failure in the future. The control strategy is decided and executed locally, and the control speed is faster.

[0055] In some embodiments, selecting the process based on the scope includes:

[0056] Based on the range, second indication information is sent to the device, where the second indication information instructs the device to turn on a cooling system of the battery, or the second indication information indicates the range to which the temperature belongs.

[0057] In this embodiment, the predicted temperature can be executed in the cloud. If the predicted battery temperature range is a range that will cause the battery to exceed the normal operating upper limit, the device can directly choose to instruct the device to turn on the battery cooling system to cool the battery, or it can indicate the predicted temperature range to allow the vehicle to decide on the treatment measures for the battery to avoid the battery temperature exceeding the normal operating upper limit at the first moment, which may cause battery failure in the future.

[0058] In some embodiments, the temperature range determined based on the temperature is greater than a second threshold and less than a fourth threshold. When the temperature of the battery is less than or equal to the second threshold, the battery will fail. The fourth threshold is the lower limit temperature for normal operation of the battery.

[0059] In this embodiment, the battery temperature range is divided based on whether the battery will fail and whether the battery temperature exceeds the normal operating temperature, so that corresponding processing can be set for the battery temperature range where the battery will not fail but exceeds the normal operating temperature, so that the processed battery will not fail and can be within the normal operating temperature range, reducing the hidden danger of battery failure.

[0060] In some embodiments, selecting the process based on the scope includes:

[0061] A heating system for the battery is selected to be activated based on the belonging range.

[0062] In this embodiment, the predicted temperature can be executed on the device side. If the predicted battery temperature belongs to a range that will cause the battery to be below the normal operating lower limit, the device can directly choose to turn on the battery heating system to heat the battery, thereby preventing the battery temperature from being below the normal operating lower limit at the first moment, which may cause battery failure in the future. The control strategy is decided and executed locally, and the control speed is faster.

[0063] In some embodiments, selecting the process based on the scope includes:

[0064] Based on the range, third indication information is sent to the device, where the third indication information instructs the device to turn on a heating system of the battery, or the third indication information indicates the range to which the temperature belongs.

[0065] In this embodiment, the predicted temperature can be executed in the cloud. If the predicted battery temperature range is a range that will cause the battery to be below the normal operating lower limit, the device can directly choose to instruct the device to turn on the battery heating system to heat the battery, or it can indicate the predicted temperature range to allow the vehicle to decide on the treatment measures for the battery to avoid the battery temperature being below the normal operating lower limit at the first moment, which may cause the risk of battery failure in the future.

[0066] In some embodiments, the first threshold and / or the second threshold are determined based on test data or statistical data of batteries that have failed.

[0067] In this embodiment, the boundary value of the range to which the battery belongs is determined by test data and statistical data, and is therefore more reasonable and practical. The processing selected based on the range will also be more in line with the actual situation, avoiding excessive processing and causing unnecessary losses.

[0068] In some embodiments, the relevant parameters include at least one of the following: ambient temperature, the voltage of the battery, the current of the battery, the internal resistance of the battery, road conditions, driving behavior, and the life of the battery.

[0069] In this embodiment, the relevant parameters include various factors that may affect the battery temperature, so that the more relevant parameters are combined in the temperature prediction process, the more accurate the predicted temperature is.

[0070] In a third aspect, a device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the first aspect or the steps of any one of the embodiments of the first aspect when executing the computer program, or executes the second aspect or the steps of any one of the embodiments of the second aspect when executing the computer program.

[0071] In a fourth aspect, a storage medium is provided, which stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the first aspect or the steps of processing in any one of the embodiments of the first aspect, or executes the second aspect or the steps of processing in any one of the embodiments of the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] By reading the detailed description of the preferred embodiment below, various other advantages and benefits will become clear to those skilled in the art. The accompanying drawings are only used for the purpose of illustrating the preferred embodiment and are not considered to be limiting of the present application. In the accompanying drawings:

[0073] Figure 1 A schematic diagram of the structure of a vehicle according to some embodiments of the present application;

[0074] Figure 2 A scene diagram applicable to the battery temperature prediction and control method provided in the embodiment of the present application;

[0075] Figures 3 to 6 A flowchart of a method for predicting battery temperature provided in some embodiments of the present application;

[0076] Figure 7 A flow chart of a method for controlling battery temperature provided in some embodiments of the present application;

[0077] Figure 8 An overall flow chart for high temperature scenarios provided for some embodiments of the present application;

[0078] Fig. 9 An overall flow chart for low temperature scenarios provided for some embodiments of the present application;

[0079] Fig.10 A schematic diagram of the structure of a prediction device provided in some embodiments of the present application;

[0080] Fig.11 A schematic diagram of the structure of a control device provided in some embodiments of the present application;

[0081] Fig.12 A schematic diagram of the structure of the device provided for some embodiments of the present application. DETAILED DESCRIPTION

[0082] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0083] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0084] In the description of the embodiments of the present application, technical terms such as "first" and "second" are only used to distinguish different objects and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features.

[0085] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0086] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0087] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0088] The battery in the device can provide power for the device itself or for other devices. For example, when the device is a new energy vehicle, the battery in the new energy vehicle can provide power for the new energy vehicle. For another example, when the device is an energy storage power station, the battery in the energy storage power station can provide power for other devices. Abnormal temperature of the battery in the device will affect the battery life, capacity and performance, so it is necessary to monitor and control the temperature of the battery in the device.

[0089] Among them, new energy vehicles have three key technologies: batteries, motors and electronic controls. For simplicity, the new energy vehicles in the following text take vehicles as an example. The battery provides power for the vehicle and drives the vehicle's motor and control system. When the battery works in a high temperature environment, or charges and discharges the battery with a large current, or drives the vehicle for a long time, it may cause the battery temperature to be abnormal, that is, the battery temperature is not within the operating temperature range, affecting the battery life, capacity and performance. For example, when the battery temperature is too high or too low, the battery capacity and voltage will drop, affecting the normal driving of the vehicle. For another example, when the battery temperature changes gradually, it may cause abnormal conditions such as short circuit, overcharging, and over-discharging in the battery. Therefore, in order to protect the safety of vehicle use, the battery temperature needs to be kept within the operating temperature range. The vehicle is equipped with a BMS, which can control the temperature of the battery on the vehicle. Its temperature control strategy is as follows:

[0090] (1) BMS monitors the battery temperature in real time through the sensing equipment on the vehicle. When the battery temperature is too high, the temperature controller on the vehicle will issue a warning or alarm signal to remind people to take measures. After hearing the alarm, people can take measures such as opening the windows, turning on the air conditioner, stopping the car for ventilation, etc. to discharge the heat around the battery. Or people can reduce the speed of the vehicle to reduce the heat emission during operation, or people can try to avoid driving the vehicle for a long time in a high temperature environment.

[0091] (2) BMS can automatically adjust the battery current and voltage to reduce the battery temperature when it detects that the battery temperature is too high.

[0092] (3) When the battery temperature is too high, the BMS can control the battery cooling system to cool the battery so that the battery temperature remains within an appropriate range; or, when the battery temperature is too low, the BMS can control the battery heating system to heat the battery so that the battery temperature remains within an appropriate range.

[0093] However, the measures adopted by the above temperature control strategy are taken when the temperature is too high or too low, and the temperature control is relatively lagging.

[0094] Based on the above considerations, in order to solve the problem of temperature control lag of the battery in the device, the present application proposes a method for predicting and controlling the battery temperature, which can predict the battery temperature in combination with multiple parameters. When it is predicted that the temperature will be too high or too low at a certain moment, measures can be taken before that moment to control the battery temperature within an appropriate range, in order to avoid battery failure caused by the battery temperature.

[0095] The devices involved in the embodiments of the present application include, but are not limited to: electrical equipment and energy storage equipment, such as mobile phones, tablets, laptops, electric toys, electric tools, vehicles, ships, vessels, spacecraft, aircraft, etc. Among them, electric toys can include fixed or mobile electric toys, such as game consoles, electric car toys, electric ship toys and electric airplane toys, etc., and spacecraft can include airplanes, rockets, space shuttles and spacecrafts, etc. Energy storage equipment such as energy storage cabinets, energy storage boxes or energy storage power stations, etc.

[0096] Figure 1 and Figure 2 The structure of the device and the usage scenario of the prediction method provided in this application are introduced using a vehicle as an example of the device.

[0097] Figure 1A schematic diagram of the structure of a vehicle 1000 provided for some embodiments of the present application. The vehicle 1000 may be a fuel vehicle, a gas vehicle or a new energy vehicle, and the new energy vehicle may be a pure electric vehicle, a hybrid vehicle or an extended-range vehicle, etc. A battery 100 is provided inside the vehicle 1000, and the battery 100 may be provided at the bottom, head or tail of the vehicle 1000. The battery 100 may be used to power the vehicle 1000, for example, the battery 100 may be used as an operating power source for the vehicle 1000. The vehicle 1000 may also include a controller 200 and a motor 300, and the controller 200 is used to control the battery 100 to power the motor 300, for example, the battery 100 is used for the starting, navigation and working power requirements of the vehicle 1000 during driving. It is understandable that the battery 100 can be used not only as an operating power source for the vehicle 1000, but also as a driving power source for the vehicle 1000, replacing or partially replacing fuel or natural gas to provide driving power for the vehicle 1000.

[0098] Figure 2 A scene diagram applicable to the battery temperature prediction method provided in the embodiment of the present application. The vehicle is equipped with a heating system and a cooling system, and the cloud has a temperature control system. The vehicle can collect data such as ambient temperature, battery voltage, current, etc. and upload them to the cloud. The cloud can also obtain data such as battery internal resistance, road conditions, driving behavior habits, and battery life. The cloud and the vehicle can communicate with each other. For example, the vehicle can upload the collected data to the cloud. The cloud can combine the above data to predict the temperature of the battery at a future time. When the cloud predicts that the battery temperature will be too low at a certain moment, a control instruction can be issued to the vehicle end. After the vehicle end receives the control instruction, the heating system can be started to control the battery temperature within a suitable range. Alternatively, when the cloud predicts that the battery temperature will be too high at a certain moment, a control instruction can be issued to the vehicle end. After the vehicle end receives the control instruction, the cooling system can be started to control the battery temperature within a suitable range.

[0099] According to some embodiments of the present application, referring to Figure 3 , the battery temperature prediction method includes the following steps:

[0100] S301, obtaining values ​​of relevant parameters that can affect the temperature of a battery in a device at a corresponding moment, where the corresponding moment includes a historical moment, or the corresponding moment includes a historical moment and a current moment.

[0101] The battery is installed in the device and can power the device or other devices. The battery whose temperature is to be predicted may include one battery pack or multiple battery packs, and the battery pack includes multiple battery cells. The battery whose temperature is to be predicted may also include multiple battery cells, which is not limited in the embodiments of the present application.

[0102] There may be multiple related parameters that affect the battery temperature, such as the battery voltage, current, ambient temperature, etc. As long as a parameter can affect the battery temperature, no matter how big or small the impact is, it is within the range of the above-mentioned related parameters.

[0103] It can be understood that there can be multiple corresponding moments, that is, when obtaining the values ​​of the relevant parameters, the values ​​of multiple historical moments can be obtained, and the time intervals between adjacent historical moments can be set according to the needs, for example, the data of the relevant parameters can be obtained in one or more seconds, minutes, etc. It can also be understood that the historical moment is relative to the moment when the temperature prediction is started.

[0104] There are many ways to obtain the values ​​of relevant parameters. If the prediction process is performed on the device side, the execution subject of the acquisition is on the device side, and the specific data can be obtained on the device side or from other places, such as from the cloud. If the prediction process is performed elsewhere, such as the cloud, the execution subject of the acquisition is on the cloud, the values ​​of the relevant parameters at historical moments can be stored in the cloud, and the values ​​of the relevant parameters at the current moment can be obtained from the device side, or the device can actively report them. The embodiments of the present application do not limit this.

[0105] S302 , predicting the temperature of the battery at a first moment in the future according to the values ​​of the relevant parameters at the corresponding moment, the temperature of the battery at the corresponding moment, and the degree to which the relevant parameters affect the change in the battery temperature.

[0106] The temperature of the battery at a historical moment can be obtained in the cloud, and the temperature of the battery at a current moment can be obtained on the device side. The temperature sensor on the device can obtain the value of the battery temperature.

[0107] The degree to which the relevant parameters affect the battery temperature change can be determined based on big data statistics, and this embodiment does not limit the specific determination method.

[0108] The battery temperature prediction method proposed in this embodiment can predict the temperature of the battery at a future moment according to the values ​​of relevant parameters at a corresponding moment, the temperature of the battery at a corresponding moment, and the degree to which the relevant parameters affect the temperature change of the battery. If it is predicted that the temperature of the battery at a future moment will be abnormal, such as the temperature is too high or too low, which may cause a battery failure, corresponding processing measures can be taken in advance to avoid battery failure caused by temperature. Compared with taking processing measures after the battery temperature has become abnormal, battery failure can be prevented in advance, damage to the battery can be reduced, and the impact on the normal operation of equipment using the battery can be reduced.

[0109] In some embodiments, the relevant parameters include at least one of the following: ambient temperature, battery voltage, battery current, battery internal resistance, road conditions, driving behavior, and battery life.

[0110] Exemplarily, if the device is a vehicle, the values ​​of the relevant parameters such as the ambient temperature, the battery voltage, the battery current, and the internal resistance of the battery can be obtained through the sensors on the vehicle and the corresponding measuring instruments, or the values ​​of some of the relevant parameters can be obtained, and the values ​​of other relevant parameters can be calculated by the obtained values ​​of the relevant parameters. Road conditions can be divided into straight roads, curved roads, slope roads, mud roads, sandy roads, gravel roads, snowy roads, cliff roads, bridge roads, tunnel roads, culvert roads, damaged roads, etc., and the specific road conditions can be determined based on the navigation map or the gyroscope installed in the vehicle. Driving behavior can be determined based on big data statistics. Big data can count the common driving behaviors of the vehicle owner, such as sudden acceleration, sudden braking, speeding up and slowing down, taking an S-shaped route, fatigue driving, speeding, etc. The life of the battery can be determined based on factory data, configuration data, and battery usage time.

[0111] In this embodiment, the relevant parameters include multiple parameters that may affect the battery temperature. The more relevant parameters are combined in the temperature prediction process, the more accurate the predicted temperature is.

[0112] In some embodiments, obtaining the values ​​of relevant parameters that can affect the temperature of a battery in a device at a corresponding time includes: obtaining the values ​​of the relevant parameters at the corresponding time from a local device.

[0113] Exemplarily, the prediction method is executed in the cloud. After the vehicle collects the values ​​of the relevant parameters at the corresponding time, it can transmit the collected data to the cloud. After the cloud receives the data transmitted by the vehicle, it can store the data locally, and read the values ​​of the relevant parameters at the corresponding time from the local in the process of predicting the battery temperature. The vehicle can collect the values ​​of the ambient temperature, the battery voltage, and the battery current in real time at the historical moment, and send the collected values ​​to the cloud. The cloud stores it locally, and the values ​​of different relevant parameters are corresponding to the historical moment when storing. In the subsequent prediction process, the values ​​of the above-mentioned relevant parameters corresponding to the target historical moment can be directly read from the local. In addition, after the cloud receives the values ​​of voltage, current, etc. reported by the vehicle, it can calculate the internal resistance of the battery at the corresponding historical moment according to the values ​​of voltage, current, etc., and store it locally. The cloud can also determine the relevant parameters such as road conditions, driving behavior, battery life, etc. at the historical moment based on the relevant data reported by the vehicle and the relevant data of the cloud big data statistics, and store them locally in the cloud.

[0114] In this embodiment, the prediction method can be executed in the cloud, because the cloud has a large storage space, the values ​​of the relevant parameters at the corresponding time can be stored in the cloud, and in the process of predicting the temperature, the data used to predict the temperature can be directly obtained from the cloud, reducing the delay in obtaining the values ​​of the relevant parameters and improving the speed of predicting the temperature. In addition, the cloud has strong computing power, which can reduce the computing delay, and the cloud has strong computing power, so the speed of predicting the temperature in the cloud is faster and more timely.

[0115] In some embodiments, when the corresponding time only includes historical time, obtaining the value of the relevant parameter that can affect the battery temperature in the device at the corresponding time includes:

[0116] Obtain the values ​​of relevant parameters at historical moments from the cloud;

[0117] When the corresponding moment includes the current moment and the historical moment, the values ​​of the relevant parameters that can affect the battery temperature in the device at the corresponding moment are obtained, including:

[0118] Get the current value of the relevant parameters from the local computer; get the historical value of the relevant parameters from the cloud.

[0119] Exemplarily, the prediction method is executed on the vehicle side, and the cloud stores the correspondence between historical moments and the values ​​of relevant parameters at historical moments. The method for obtaining the values ​​of relevant parameters at historical moments on the cloud side is described above and will not be repeated here. If the prediction method only needs to obtain the values ​​of relevant parameters at historical moments, a data request is sent to the cloud side. The request may include the type of relevant parameters and the target historical moment. After receiving the data request, the cloud side can determine which relevant parameters are requested by the vehicle side, and can also determine the target historical moment of the request, and send the data requested by the vehicle side to the vehicle side. If the prediction method needs to obtain the values ​​of relevant parameters at the current moment in addition to the values ​​of relevant parameters at historical moments, the vehicle side can obtain it by itself, and obtain the values ​​of some relevant data collected in real time by the vehicle side at the current moment. The values ​​of the other part of the relevant data at the current moment can be calculated based on the data collected in real time at the current moment.

[0120] In this embodiment, the prediction method can be executed on the device side using the battery, combining the real-time data obtained from the local device and the historical data obtained from the cloud to predict the temperature at a future time. If it is predicted that the temperature of the battery will be abnormal at a future time, corresponding processing measures can be taken in advance to avoid battery failure caused by temperature. In addition, there is no need to store the relevant data corresponding to the historical time locally on the device side, which can save local storage space on the vehicle side.

[0121] In some embodiments, reference Figure 4S302 predicts the temperature of the battery at the first moment in the future according to the value of the relevant parameter at the corresponding moment, the temperature of the battery at the corresponding moment, and the degree to which the relevant parameter affects the change of the battery temperature, including:

[0122] S401, determining a first weight value corresponding to a relevant parameter, where the first weight value represents a contribution degree of the relevant parameter to a result that a battery failure occurs.

[0123] Exemplarily, the first weight value corresponding to the ambient temperature is W T , the first weight value corresponding to the battery voltage is W U , the first weight value corresponding to the battery current is W I , the first weight value corresponding to the battery internal resistance is W R , the first weight value corresponding to the road condition is W C , the first weight value corresponding to the driving behavior is W B The first weight value corresponding to the battery life is W RUL The first weight values ​​corresponding to the above-mentioned related parameters can be obtained based on big data statistics, for example, statistics on the proportion of each related parameter in the failed batteries that causes the battery failure. The failed battery can be a battery that fails during the battery test process or a battery that fails after being put into use, and the embodiments of the present application do not limit this.

[0124] S402, determining a second weight value corresponding to the relevant parameter according to the value of the relevant parameter at the corresponding moment, the second weight value representing the contribution of the value of the relevant parameter at the corresponding moment to the change of the battery temperature.

[0125] Exemplarily, the second weight value corresponding to the ambient temperature is f1(T), the second weight value corresponding to the battery voltage is f2(U), the second weight value corresponding to the battery current is f3(I), the second weight value corresponding to the battery internal resistance is f4(R), the second weight value corresponding to the road condition is f5(C), the second weight value corresponding to the driving behavior is f6(B), and the second weight value corresponding to the battery life is f7(RUL). The second weight values ​​corresponding to the above-mentioned related parameters can be determined according to the value of the related parameter at the corresponding moment, and the difference between the value and the normal value of the related parameter. For example, if the value of the battery voltage at the corresponding moment is significantly different from the normal value of the battery voltage, then the value of the related parameter battery voltage at the corresponding moment contributes more to the change in battery temperature. The normal value of the related parameter is within the value range of the related parameter when the battery is working normally. For example, when the battery is working normally, the value range of the battery voltage is Then the normal value of the battery voltage can be The same applies to other related parameters, and the embodiments of the present application do not limit this.

[0126] S403 , predicting the temperature of the battery at a first moment in the future according to the first weight value, the second weight value, and the temperature of the battery at a corresponding moment.

[0127] Exemplarily, after calculating the first weight value and the second weight value corresponding to each relevant parameter at the corresponding moment, for a corresponding moment, the total weight value of all relevant parameters at the corresponding moment is calculated according to the first weight value and the second weight value corresponding to each relevant parameter, that is, multiple total weight values ​​can be calculated for multiple corresponding moments, each total weight value corresponds to each corresponding moment one by one, and a total weight value can be obtained by summing the first weight value and the second weight value corresponding to all relevant parameters at the corresponding moment. Then compare the multiple total weight values ​​with the preset threshold to see whether the total weight value is approaching the preset threshold over time. If it is close, it means that the temperature of the battery at the first moment is about to approach the fault temperature. The preset threshold is the total weight value calculated for the battery with a fault according to the first weight value and the second weight value corresponding to all relevant parameters at the moment of the fault.

[0128] In this embodiment, the first weight value is calculated for the battery that has failed. In the specific calculation process, the contribution of different related parameters to the failure of the failed battery can be counted. The second weight value can be calculated according to the degree to which the real-time values ​​of the related parameters at the corresponding moment affect the battery temperature. Therefore, combining the first weight value and the second weight value to predict the temperature takes into account both the statistical laws of big data and the real-time values ​​of the related parameters, so that the predicted result is consistent with the actual situation of battery use while complying with the statistical laws, and is more accurate.

[0129] In some embodiments, the method further comprises:

[0130] S501, obtaining a first weight value sequence corresponding to a battery that has failed, the first weight value sequence including a third weight value corresponding to each relevant parameter in the relevant parameters, any third weight value being determined based on a first weight value and a second weight value corresponding to the corresponding relevant parameter at the moment when the battery that has failed failed;

[0131] It can be understood that there can be multiple batteries that have failed, so there can be multiple first weight value sequences. Each battery that has failed can calculate the corresponding first weight value sequence. For one of the batteries that has failed, its corresponding first weight value sequence includes the third weight value corresponding to each of the above-mentioned related parameters. Taking the battery voltage as an example, the third weight value corresponding to the battery voltage is determined based on the first weight value and the second weight value corresponding to the battery voltage. The calculation method of the first weight value and the second weight value corresponding to the battery voltage at the time when the battery fails can be referred to the above description and will not be repeated here.

[0132] Reference Figure 5 S403 predicts the temperature of the battery at a first moment in the future according to the first weight value, the second weight value and the temperature of the battery at a corresponding moment, including:

[0133] S502, determining a plurality of second weight value sequences corresponding to a plurality of corresponding moments, wherein the plurality of corresponding moments correspond to the plurality of second weight value sequences one-to-one, and any second weight value sequence includes a fourth weight value corresponding to each of the relevant parameters, and the fourth weight value is determined based on the first weight value and the second weight value corresponding to the corresponding relevant parameter at the corresponding moment.

[0134] It can be understood that the second weight value sequence is for the battery whose temperature is currently to be predicted. Multiple second weight value sequences correspond to different corresponding moments of the battery. For one corresponding moment, the corresponding second weight value sequence includes the fourth weight value corresponding to each of the above-mentioned related parameters. Taking the battery voltage as an example, the fourth weight value corresponding to the battery voltage is determined based on the first weight value and the second weight value corresponding to the battery voltage. The calculation method of the first weight value and the second weight value corresponding to the battery voltage at the corresponding moment can be referred to the above description and will not be repeated here.

[0135] S503: predicting the temperature of the battery at a first moment according to the plurality of second weight value sequences, the first weight value sequence, and the temperatures of the battery at a plurality of corresponding moments.

[0136] The temperature of the battery at the first moment is predicted based on multiple second weight value sequences, the first weight value sequence and the temperature of the battery at multiple corresponding moments. For example, a first weight value sequence is selected from the multiple first weight value sequences as a benchmark, and the multiple second weight value sequences can be arranged in time order according to their corresponding corresponding moments, and the changes of the multiple second weight value sequences over time are determined, and the second weight value sequences are compared with the first weight value sequence to see whether, with the passage of time, the fourth weight value in the second weight value sequence will gradually approach the third weight value of the corresponding relevant parameter in the first weight value sequence. If the fourth weight value corresponding to a relevant parameter is close to the third weight value, and the relevant parameter contributes more to the battery failure, it is determined that the temperature of the battery at the first moment in the future may cause the battery failure.

[0137] In this embodiment, the first weight value and the second weight value corresponding to each relevant parameter of the failed battery are calculated to obtain a third weight value, and the third weight value corresponding to each relevant parameter forms a first weight value sequence. The first weight value and the second weight value corresponding to each relevant parameter at multiple corresponding moments are further calculated in real time according to the actual use of the battery to obtain a fourth weight value, and the fourth weight value corresponding to each relevant parameter forms a second weight value sequence. One corresponding moment corresponds to one second weight value sequence. Finally, the multiple second weight value sequences calculated in real time are compared with the first weight value sequence as a benchmark. During the comparison process, the third weight value and the fourth weight value corresponding to each relevant parameter can be compared, so as to more accurately predict the temperature of the battery at future moments.

[0138] In some embodiments, reference Figure 6 S503 predicts the temperature of the battery at a first moment according to the plurality of second weight value sequences, the first weight value sequence and the temperature of the battery at a plurality of corresponding moments, including:

[0139] S601, summing up the third weight values ​​in the first weight value sequence to obtain a first risk index; determining multiple second risk indices based on multiple second weight value sequences, the multiple second weight value sequences and the multiple second risk indices correspond one to one, and any second risk index is the sum of the fourth weight values ​​included in the corresponding second weight value sequence.

[0140] It can be understood that there may be multiple batteries that have failed, so there are multiple first weight value sequences and multiple first risk indexes. One of the first risk indexes can be selected as the risk threshold, and the risk threshold can be the smallest first risk index.

[0141] S602 , predicting a temperature of a battery at a first moment based on a plurality of second risk indices, a first risk index, and battery temperatures corresponding to the plurality of second risk indices and the first risk index.

[0142] Exemplarily, the multiple corresponding moments include moment #1 and moment #2, the second weight value sequence corresponding to moment #1 is weight value sequence #1, and the second weight value sequence corresponding to moment #2 is weight value sequence #2. If the relevant parameters involved in predicting the battery temperature include: ambient temperature, battery voltage, battery current, battery internal resistance, road conditions, driving behavior habits and battery life, then weight value sequence #1 and weight value sequence #1 include the fourth weight values ​​corresponding to the above 7 parameters, and the risk index Risk_t = ∑weight_i, 1≤i≤7, weight_i represents the fourth weight value corresponding to the i-th relevant parameter. The second risk index corresponding to weight value sequence #1 is obtained based on the sum of the fourth weight values ​​of the above 7 relevant parameters corresponding to moment #1, and the second risk index corresponding to weight value sequence #2 is obtained based on the sum of the fourth weight values ​​of the above 7 relevant parameters corresponding to moment #2. For example, if the weight value sequence #1 is [9, 4.3, 5, 2, 2.7, 4, 9.2], then the second risk index corresponding to the weight value sequence #1 = 9 + 4.3 + 5 + 2 + 2.7 + 4 + 9.2 = 36.2.

[0143] For high temperature scenarios, a high temperature experience library can be formed by calculating the first weight value sequence corresponding to the moment when the faulty battery has a high temperature fault, and there is a high temperature fault risk threshold in the high temperature experience library, which is the smallest first risk index in the high temperature experience library. For low temperature scenarios, a low temperature experience library can be formed by calculating the first weight value sequence corresponding to the moment when the faulty battery has a low temperature fault, and there is a low temperature fault risk threshold in the low temperature experience library, which is the smallest first risk index in the low temperature experience library. In the process of predicting the temperature at the first moment, if the battery temperature at the corresponding moment obtained corresponds to a high temperature scenario, the second risk index corresponding to the multiple corresponding moments determined is compared with the high temperature fault risk threshold to predict the temperature of the battery at the first moment. If the battery temperature at the corresponding moment obtained corresponds to a low temperature scenario, the second risk index corresponding to the multiple corresponding moments determined is compared with the low temperature fault risk threshold to predict the temperature of the battery at the first moment.

[0144] Specifically, for example, in a high temperature scenario, multiple second risk indices can be arranged in chronological order according to their corresponding moments, and the changes of the multiple second risk indices over time can be determined. The second risk index can be compared with the high temperature failure risk threshold to see whether the second risk index will gradually approach the high temperature failure risk threshold over time. If it is close, it is determined that the temperature of the battery at the first moment in the future may cause the battery to fail, that is, the temperature of the battery at the first moment is close to the high temperature failure temperature.

[0145] In this embodiment, the third weight value in the first weight value sequence is summed to obtain the first risk index, and the fourth weight value in the second weight value sequence is further summed to obtain the second risk index. One corresponding moment corresponds to one second risk index. Finally, the multiple second risk indices calculated in real time are compared with the benchmark calculated based on the relevant data of the failed battery, that is, the first risk index. The comparison process does not involve comparison of a large amount of data and is relatively simple.

[0146] In some embodiments, predicting the temperature of the battery at a first moment based on the plurality of second risk indexes, the first risk index, and the battery temperatures corresponding to the plurality of second risk indexes and the first risk index includes:

[0147] In the case where multiple second risk indices change monotonically over time, the second risk index corresponding to the first moment is determined based on the multiple second risk indices and the multiple corresponding moments; and the temperature of the battery at the first moment is predicted based on the second risk index corresponding to the first moment and the battery temperature, the first risk index, and the battery temperature corresponding to the first risk index.

[0148] Exemplarily, the temperature of the battery at the corresponding time is obtained, the temperature of the battery at time #1 is recorded as T1, the temperature of the battery at time #1 is recorded as T2, the second risk index corresponding to time #1 is recorded as Risk1, and the second risk index corresponding to time #2 is recorded as Risk2. Then, the temperature T of the battery at the first time can be calculated by the following formula:

[0149]

[0150] Among them, Risk represents the second risk index corresponding to the first moment, and Risk can be calculated by the following formula:

[0151]

[0152] Among them, t represents the time corresponding to the first moment, t1 represents the time corresponding to moment #1, and t2 represents the time corresponding to moment #2.

[0153] The execution end (such as the cloud or vehicle end) of the predicted temperature can also determine at which moment in the future the battery will fail according to the values ​​of the relevant parameters at the corresponding moment and the risk threshold in the experience library. The failure is that the predicted battery temperature is higher than the first threshold, or the predicted battery temperature is lower than the second threshold. The execution end can calculate the second risk index of the vehicle in real time during driving, for example, the second risk index is calculated every 10 seconds (S). After calculating the second risk index 10 times in a row, it is found that the calculated second risk index is monotonically increasing with the time sequence and continuously approaching the high temperature risk threshold. It can be predicted that after how much time interval, the second risk index will be equal to the high temperature risk threshold. At this moment when it is equal to the high temperature risk threshold, a high temperature failure will occur, and this moment can be recorded as the first moment. Alternatively, after calculating the second risk index 10 times in a row, it is found that after the calculation time sequence, the calculated second risk index is monotonically decreasing and continuously approaching the low temperature risk threshold. It can be predicted that after how much time interval, the second risk index will be equal to the low temperature risk threshold. At this moment when it is equal to the low temperature risk threshold, a low temperature failure will occur, and this moment can be recorded as the first moment.

[0154] Similarly, the execution end of the predicted temperature (such as the cloud or the vehicle end) can also determine at which moment in the future the battery will overheat according to the values ​​of the relevant parameters at the corresponding moment and the risk threshold in the experience library. Overheating can be divided into ultra-high temperature or ultra-low temperature. Ultra-high temperature is lower than the first threshold and higher than the upper limit temperature of the normal operation of the battery. The upper limit temperature of the normal operation of the battery is recorded as the third threshold. Ultra-low temperature is higher than the second threshold and lower than the lower limit temperature of the normal operation of the battery. The lower limit temperature of the normal operation of the battery is recorded as the fourth threshold, wherein the first threshold is greater than the third threshold, the third threshold is greater than the fourth threshold, and the fourth threshold is greater than the second threshold. In this embodiment, the risk threshold in the experience library also needs to include an ultra-high temperature risk threshold or an ultra-low temperature risk threshold. The ultra-high temperature risk threshold or the ultra-low temperature risk threshold can be calculated for the first weight value sequence corresponding to the ultra-high temperature or ultra-low temperature moment when the ultra-high temperature or ultra-low temperature occurs for the battery that has already experienced ultra-high temperature or ultra-low temperature, which is similar to the calculation method of the high temperature fault risk threshold and the low temperature fault risk threshold, and will not be repeated.

[0155] It can be understood that the first risk index in the embodiment of the present application is a risk index in the experience library, which is a risk index obtained by the first weight value sequence corresponding to the moment when the battery fails. For example, the cloud can calculate the first risk index corresponding to the battery that has failed in the past based on the data of related parameters obtained in the past, thereby forming a high temperature experience library and a low temperature experience library. The second risk index is the risk index calculated in the real-time prediction process.

[0156] If after calculating the second risk indexes multiple times continuously, it is found that the multiple second risk indexes do not increase or decrease monotonically over time, the above prediction method will not be used until the second risk indexes calculated continuously increase or decrease monotonically over time, and then the above method will be used.

[0157] In this embodiment, the subsequent prediction calculation is performed only when the calculated multiple second risk indices change monotonically over time, so as to avoid the problem that the temperature predicted based on the multiple second risk indices is inaccurate when the second risk indices corresponding to multiple consecutive moments do not change monotonically over time, that is, when the second risk indices corresponding to consecutive moments do not change stably.

[0158] In some embodiments, obtaining a first weight value sequence corresponding to a battery that has failed includes:

[0159] The first weight value sequence is updated according to the third weight value sequence corresponding to the battery having failed, the sum of the third weight values ​​included in the third weight value sequence being less than the first risk index; and the updated first weight value sequence is obtained.

[0160] Exemplarily, if a new faulty battery is found, it can be determined whether the risk thresholds in the high temperature experience library and the low temperature experience library need to be updated. For the new faulty battery, a third weight value sequence is calculated. If the first risk index calculated according to the third weight value included in the third weight value sequence is less than the high temperature fault risk threshold or the low temperature fault risk threshold in the existing experience library, the original high temperature fault risk threshold or the low temperature fault risk threshold is updated to the first risk index calculated according to the third weight value sequence. The first weight value sequence corresponding to the high temperature fault risk threshold or the low temperature fault risk threshold can also be updated to the third weight value sequence. The updated first weight value sequence is the third weight value sequence.

[0161] In this embodiment, as the number of failed batteries increases, the first weight value sequence serving as a comparison benchmark must also be updated according to the third weight value sequence corresponding to the newly added failed batteries, so that subsequent predictions can be calculated based on the updated benchmark, making the predicted temperature more accurate and more in line with actual conditions.

[0162] In some embodiments, determining a first weight value corresponding to the relevant parameter includes:

[0163] The first weight value is determined according to the values ​​of the relevant parameters at the time when the faulty battery fails and an analytic hierarchy process (AHP).

[0164] For example, for batteries that have failed in the past, the values ​​of relevant parameters of the failed battery at the time of the failure are analyzed to determine which relevant parameter has a greater impact on the battery failure. The larger the weight value, the greater the impact. For example, the first weight values ​​corresponding to the ambient temperature, battery voltage, battery current, battery internal resistance, road conditions, driving behavior, and battery life can be determined according to AHP to be [6, 3, 3, 2, 2.5, 2.8, 8] respectively.

[0165] In this embodiment, the characteristics of the hierarchical analysis method are combined: the weight setting of each layer will directly or indirectly affect the result of battery failure, and the influence of each relevant parameter in each layer on the result is quantified and very clear, so that the contribution of each relevant parameter to the result of battery failure can be calculated more accurately, thereby being more inclined when predicting temperature.

[0166] In some embodiments, determining the second weight value corresponding to the relevant parameter according to the value of the relevant parameter includes:

[0167] The second weight value is determined according to the value of the relevant parameter at the corresponding moment and the first weight value.

[0168] The following describes the calculation method of the second weight value corresponding to each relevant parameter at time #1, W T , W U , W I , W R , W C , W B , W RUL They respectively represent the first weight value corresponding to each relevant parameter, and the normal value of each relevant parameter in the process of calculating the second weight value takes the average value of the normal value range as an example, and the embodiment of the present application does not impose any restrictions on this.

[0169]

[0170] Among them, f1(T) represents the second weight value corresponding to the ambient temperature, T is the ambient temperature at time #1 collected by the cloud, T0 represents the average temperature T0, and the working temperature of the lithium-ion battery under charging conditions is For example, the average temperature T0 = (-10 + 45) / 2 = 15°C. The average temperature T0 of batteries of different brands or models may be different.

[0171]

[0172] Among them, f2(U) represents the second weight value corresponding to the battery voltage, U is the battery voltage at time #1 collected by the cloud, and U0 represents the average voltage U0. For example, the average voltage U0 = (3.0 + 5.2) / 2 = 4.1 V. The average voltage U0 of batteries of different brands or models may be different.

[0173]

[0174] Among them, f3(I) represents the second weight value corresponding to the battery current, I represents the battery current at time #1 collected by the cloud, I0 represents the average current, and the working current of the lithium-ion battery is For example, the average current I0=(5+15) / 2=10A, and the average current I0 of batteries of different brands or models may be different.

[0175]

[0176] Among them, f4(R) represents the second weight value corresponding to the battery internal resistance, R represents the battery internal resistance at time #1 obtained by the cloud, and R0 represents the average internal resistance. For example, the average internal resistance R0 = (2 + 15) / 2 = 8.5A, and the average internal resistance R0 of batteries of different brands or models may be different.

[0177]

[0178] Among them, f5(C) represents the second weight value corresponding to the road condition, and C represents the road condition at time #1 obtained from the cloud. Specifically, the value of C can be calibrated for common road conditions, for example, straight road (C=0), curved road (C=1), slope road (C=2), mud road (C=3), sandy road (C=3), gravel road (C=3), snowy road (C=4), cliff road (C=7), bridge road (C=2), tunnel road (C=2), culvert road (C=4), damaged road surface (C=8). If there are multiple road conditions coexisting, C is calibrated as the sum of the values ​​of C corresponding to different road conditions.

[0179]

[0180] Among them, f6(B) represents the second weight value corresponding to the driving behavior, B represents the driving behavior determined by the cloud, and the driving behavior can be the habitual driving behavior counted by the cloud. Specifically, the B value can be calibrated for common driving behaviors, for example, sudden acceleration or sudden braking (B=4), speeding up and slowing down or taking an S-shaped route (B=5), fatigue driving (B=6), speeding (B=7). If the driving behavior coexists in multiple conditions, B is the sum of the values ​​of B corresponding to different driving behaviors.

[0181]

[0182] Among them, f7(RUL) represents the second weight value corresponding to the battery life, RUL represents the remaining service life of the battery at time #1 obtained from the cloud, and RUL0 represents the average service life. Taking lithium-ion batteries as an example, the service life is RUL0 = (3 + 5) / 2 = 4 years. The average service life of batteries of different brands or models may be different.

[0183] In this embodiment, for any relevant parameter, the second weight value is not only affected by the specific value of the relevant parameter at the corresponding moment, but also by the first weight value corresponding to the relevant parameter obtained based on statistics. This takes into account both statistical laws and the actual use of the battery, and the predicted temperature is more accurate.

[0184] The present application also provides a method for controlling battery temperature. According to some embodiments of the present application, Figure 7 , the battery temperature control method comprises the following steps:

[0185] S701, predicting the temperature of a battery in a device at a first moment in the future.

[0186] For details, please refer to the above Figure 3-Figure 6 The description of the exemplary temperature prediction method is not repeated here.

[0187] S702, selecting a process based on the temperature, the process being used to improve the temperature of the battery at the first moment.

[0188] It can be understood that if the predicted temperature is completed on the vehicle side, the processing can be directly targeted at the battery, such as turning off the power, heating or cooling the battery. If the predicted temperature is completed on the cloud, the processing can be an indication of the battery processing sent to the vehicle side, or an indication of the predicted temperature. The specific processing can be decided by the vehicle side based on the temperature indicated by the cloud.

[0189] In the technical solution of this embodiment, after predicting the battery temperature at a future time, it is necessary to select a corresponding process according to the predicted temperature. For example, if it is predicted that the battery temperature is abnormal, a corresponding process is selected in advance to improve the battery temperature at a future time, so as to avoid abnormal battery temperature at a future time, thereby causing battery failure. Compared with taking processing measures after the battery temperature has become abnormal, it is possible to prevent battery failure in advance, reduce damage to the battery, and thus reduce the impact on the normal operation of the equipment using the battery.

[0190] If the temperature prediction is done in the cloud, due to its powerful storage and computing capabilities, even if the battery temperature and related parameter values ​​reported by the vehicle-side sensing device are not available at some times, the cloud can still predict the battery temperature at a future time based on the historical temperature and related parameter values ​​at a historical time. That is, the cloud uses "intelligence" to predict the temperature, and then decides whether the battery temperature needs to be controlled in advance, rather than relying on the real-time historical temperature of the battery to determine whether the temperature needs to be controlled, which can reduce the lag of temperature control.

[0191] In some embodiments, the process is selected based on temperature, including:

[0192] A range to which the temperature belongs is determined based on the temperature; and a process is selected based on the range to which the temperature belongs.

[0193] In this embodiment, the temperature range and the processing can be mapped one by one, and the corresponding relationship can be set in advance. After the temperature is predicted, the corresponding processing can be selected directly based on the range of the predicted temperature, thereby reducing the process of deciding the processing method after predicting the temperature and improving the speed and efficiency of temperature control.

[0194] In some embodiments, the temperature range determined based on the temperature is greater than or equal to a first threshold, or less than or equal to a second threshold, wherein the first threshold is greater than the second threshold, and when the temperature of the battery is greater than or equal to the first threshold, or less than or equal to the second threshold, the battery will fail.

[0195] The first threshold can be understood as the threshold in a high temperature scenario, that is, if the battery temperature exceeds the first threshold in a high temperature scenario, a high temperature fault may occur. The second threshold can be understood as the threshold in a low temperature scenario, that is, if the battery temperature is less than the second threshold in a low temperature scenario, a low temperature fault may occur. For example, the normal operating temperature of the battery is 45℃ is the upper limit temperature for normal operation of the battery, -10℃ is the lower limit temperature for normal operation of the battery, the first threshold is much higher than the upper limit temperature, the second threshold is much lower than the lower limit temperature, the first threshold and the second threshold are usually specified by industry standards. The first and second thresholds of batteries of different brands, different models, or different uses may be different, the first and second thresholds can be determined through testing and set at the factory.

[0196] In this embodiment, the battery temperature range is divided based on whether the battery will fail, so that corresponding processing can be set for the temperature range where the battery will fail, so that the battery will not fail after the processing.

[0197] In some embodiments, the process is selected based on the scope of belonging, including:

[0198] Choose to stop using the battery before the first moment based on the range.

[0199] Deactivating a battery may be understood as disconnecting power, or not using the battery as a power or operating source.

[0200] In this embodiment, the predicted temperature can be executed on the device side. If the predicted battery temperature falls within a range that will cause the battery to fail, the device can directly choose to stop using the battery before the first moment in the future, or can choose to stop using the battery immediately when the temperature is predicted, so as to avoid the battery from failing at the first moment. The control strategy is decided and executed locally, and the control speed is faster.

[0201] In some embodiments, selecting the process based on the scope includes:

[0202] A first indication message is sent to the device based on the range, the first indication message instructs the device to stop using the battery before the first moment, or the first indication message indicates the temperature range, that is, when the temperature range is greater than or equal to the first threshold, the first indication message indicates that the temperature range at the first moment is greater than or equal to the first threshold; when the temperature range is less than or equal to the second threshold, the first indication message indicates that the temperature range at the first moment is less than or equal to the second threshold.

[0203] Alternatively, the content specifically indicated by the first indication information may be other, which is not limited in the embodiment of the present application. However, after the device receives the first indication information, it can be determined that the battery needs to be stopped before the first moment.

[0204] In this embodiment, the predicted temperature can be executed in the cloud. If the predicted battery temperature is in a range that will cause the battery to fail, the device can directly choose to instruct the device to stop using the battery before the first moment in the future, or can indicate the predicted temperature range, so that the vehicle side can decide on the treatment measures for the battery to avoid the battery from failing at the first moment. The solution provided in this embodiment can prevent battery failure in advance through prediction, and can avoid the problem of untimely temperature control caused by rapid increase or decrease of battery temperature in a short period of time.

[0205] In some embodiments, the temperature range determined based on the temperature is less than a first threshold and greater than a third threshold. When the temperature of the battery is greater than or equal to the first threshold, the battery will fail. The third threshold is the upper limit temperature for normal operation of the battery.

[0206] In this embodiment, the battery temperature range is divided based on whether the battery will fail and whether the battery temperature exceeds the normal operating temperature, so that corresponding processing can be set for the battery that will not fail but exceeds the normal operating temperature range, so that the processed battery will not fail and can be within the normal operating temperature range.

[0207] In some embodiments, the process is selected based on the scope of belonging, including:

[0208] Depending on the range, the battery cooling system is switched on.

[0209] In this embodiment, the predicted temperature can be executed on the device side. If the predicted battery temperature belongs to a range that will cause the battery to exceed the normal operating upper limit, the device can directly choose to turn on the battery cooling system to cool the battery, thereby preventing the battery temperature from exceeding the normal operating upper limit at the first moment, which may cause battery failure in the future. The control strategy is decided and executed locally, and the control speed is faster.

[0210] In some embodiments, the process is selected based on the scope of belonging, including:

[0211] Based on the range, a second indication message is sent to the device, the second indication message instructs the device to turn on the battery cooling system, or the second indication message indicates the temperature range, that is, the second indication message indicates that the temperature range is less than the first threshold and greater than the third threshold.

[0212] Alternatively, the specific content indicated by the second indication information may be other, which is not limited in the embodiment of the present application. However, after the device receives the second indication information, it can determine that the battery cooling system needs to be turned on before the first moment.

[0213] In this embodiment, the predicted temperature can be executed in the cloud. If the predicted battery temperature range is a range that will cause the battery to exceed the normal operating upper limit, the device can directly choose to instruct the device to turn on the battery cooling system to cool the battery, or it can indicate the predicted temperature range to allow the vehicle to decide on the treatment measures for the battery to avoid the battery temperature exceeding the normal operating upper limit at the first moment, which may cause battery failure in the future.

[0214] In some embodiments, the temperature range determined based on the temperature is greater than the second threshold and less than the fourth threshold. When the battery temperature is less than or equal to the second threshold, the battery will fail. The fourth threshold is the lower limit temperature for normal operation of the battery.

[0215] In this embodiment, the battery temperature range is divided based on whether the battery will fail and whether the battery temperature exceeds the normal operating temperature, so that corresponding processing can be set for the battery temperature range where the battery will not fail but exceeds the normal operating temperature, so that the processed battery will not fail and can be within the normal operating temperature range.

[0216] In some embodiments, the process is selected based on the scope of belonging, including:

[0217] Depending on the range, the battery heating system is switched on.

[0218] In this embodiment, the predicted temperature can be executed on the device side. If the predicted battery temperature belongs to a range that will cause the battery to be below the normal operating lower limit, the device can directly choose to turn on the battery heating system to heat the battery, thereby preventing the battery temperature from being below the normal operating lower limit at the first moment, which may cause battery failure in the future. The control strategy is decided and executed locally, and the control speed is faster.

[0219] In some embodiments, the process is selected based on the scope of belonging, including:

[0220] A third indication message is sent to the device based on the range, the third indication message instructs the device to turn on the battery heating system, or the third indication message indicates the range of the temperature, that is, the third indication message indicates that the range of the temperature is greater than the second threshold and less than the fourth threshold.

[0221] Alternatively, the specific content indicated by the third indication information may be other, which is not limited in the embodiment of the present application. However, after the device receives the third indication information, it can determine that the battery heating system needs to be turned on before the first moment.

[0222] In this embodiment, the predicted temperature can be executed in the cloud. If the predicted battery temperature range is a range that will cause the battery to be below the normal operating lower limit, the device can directly choose to instruct the device to turn on the battery heating system to heat the battery, or it can indicate the predicted temperature range to allow the vehicle to decide on the treatment measures for the battery to avoid the battery temperature being below the normal operating lower limit at the first moment, which may cause the risk of battery failure in the future.

[0223] In some embodiments, the first threshold and / or the second threshold are determined based on test data or statistical data of batteries that have failed.

[0224] In this embodiment, the boundary value of the range to which the battery belongs is determined by test data and statistical data, and is therefore more reasonable and practical. The processing selected based on the range will also be more in line with the actual situation, avoiding excessive processing and causing unnecessary losses.

[0225] The following uses the cloud as an example to predict the temperature and the vehicle as an example to introduce the overall process of controlling the battery temperature based on the predicted temperature.

[0226] like Figure 8 As shown, the cloud predicts the temperature of the battery at the first moment, determines whether the predicted temperature is greater than a first threshold, and if so, sends a first indication message to the BMS of the vehicle. The vehicle can stop using the battery immediately after receiving the first indication message, or stop using the battery before the first moment. If the predicted temperature is determined to be less than or equal to the first threshold, it further determines whether the predicted temperature is greater than a third threshold. If the predicted temperature is greater than the third threshold, it sends a second indication message to the BMS of the vehicle, so that the BMS of the vehicle starts the cooling system to cool the battery after receiving the second indication message. The cooling system includes liquid cooling or air cooling. After the battery is cooled, the temperature will drop. The cloud continues to predict that the cooling However, the temperature at the first moment predicted by the cloud will be lower than the temperature at the first moment predicted before. The process is repeated until the predicted temperature is less than or equal to the third threshold. When it is judged that the predicted temperature is less than or equal to the third threshold, it is necessary to further judge whether the predicted temperature is less than the fourth threshold. If it is judged that the predicted temperature is less than the fourth threshold, the third indication information is sent to the BMS on the vehicle side, so that the BMS on the vehicle side starts the heating system to heat the battery after receiving the third indication information. After the battery is heated, the temperature will rise, and the cloud continues to predict that after heating, the temperature predicted by the cloud at the first moment will be higher than the temperature predicted at the first moment before. The process is repeated until the predicted temperature is greater than or equal to the fourth threshold.

[0227] Figure 8 The process shown can be used for prediction in high temperature scenarios, that is, the process that can be used when the temperature predicted by the cloud is in the high temperature range. The process for low temperature scenarios can be found in Fig. 9 .

[0228] like Fig. 9As shown, the cloud predicts the temperature of the battery at the first moment, and determines whether the predicted temperature is less than the second threshold. If it is less than the second threshold, a first indication message is sent to the BMS of the vehicle. After receiving the first indication message, the vehicle end can immediately stop using the battery, or stop using the battery before the first moment. If it is determined that the predicted temperature is greater than or equal to the second threshold, it is further determined whether the predicted temperature is less than the fourth threshold. If the predicted temperature is less than the fourth threshold, a third indication message is sent to the BMS of the vehicle end, so that the BMS of the vehicle end starts the heating system to heat the battery after receiving the third indication message. After the battery is heated, the temperature will rise, and the cloud continues to predict. After heating, the cloud end predicts the temperature at the first moment. The temperature will be higher than the temperature predicted at the first moment. The process is repeated until the predicted temperature is greater than or equal to the fourth threshold. When it is judged that the predicted temperature is greater than or equal to the fourth threshold, it is necessary to further judge whether the predicted temperature is greater than the third threshold. If it is judged that the predicted temperature is greater than the fourth threshold, a second indication message is sent to the BMS on the vehicle side, so that the BMS on the vehicle side starts the cooling system to cool the battery after receiving the second indication message. The cooling system includes liquid cooling or air cooling. After the battery is cooled, the temperature will drop. The cloud continues to predict that after cooling, the temperature predicted at the first moment by the cloud will be lower than the temperature predicted at the first moment. The process is repeated until the predicted temperature is less than or equal to the third threshold.

[0229] In other words, when the temperature predicted by the cloud is in the high temperature range, Fig. 9 The process can also be used when the temperature predicted by the cloud is in the low temperature range. Figure 8 The process is not limited in this embodiment of the present application.

[0230] According to some embodiments of the present application, the present application also provides a prediction device, which can be in the cloud or on the device side, such as Fig.10 As shown, the prediction device 1000 includes: a transceiver unit 1001 and a prediction unit 1002.

[0231] The transceiver unit 1001 is used to obtain the value of the relevant parameter that can affect the battery temperature in the device at a corresponding moment, where the corresponding moment includes a historical moment, or the corresponding moment includes a historical moment and a current moment.

[0232] The prediction unit 1002 is used to predict the temperature of the battery at a first moment in the future according to the value of the relevant parameter at a corresponding moment, the temperature of the battery at the corresponding moment, and the degree to which the relevant parameter affects the change of the battery temperature.

[0233] According to some embodiments of the present application, the present application also provides a control device, which can be in the cloud or on the device side, such as Fig.11 As shown, the control device 1100 includes: a prediction unit 1002 and a control unit 1101 .

[0234] The prediction unit 1002 is used to predict the temperature of the battery at a first moment in the future; the control unit 1101 is used to select a process based on the predicted temperature, the process being used to improve the temperature of the battery at the first moment.

[0235] According to some embodiments of the present application, the present application also provides a device, which can be installed in a vehicle or in the cloud, or can be a vehicle or in the cloud. The device 1200 includes a processor 1201, and the device 1200 can implement the technical solutions shown in the above-mentioned prediction method and control method.

[0236] Optionally, the device 1200 further includes a transceiver 1202, which is used to accept control of the processor 1201 and to support the device in executing the technical solution shown above.

[0237] Optionally, the device 1200 may further include: a storage medium 1203 .

[0238] It should be noted that the processor can be implemented using the following circuits or devices: one or more field programmable gate arrays (FPGA), programmable logic devices (PLD), controllers, state machines, gate logic, discrete hardware components, any other suitable circuits, or any combination of circuits that can perform the various functions described throughout this application.

[0239] The embodiment of the present application also provides a storage medium, in which computer instructions are stored; when the storage medium is run on a device, the device executes the method shown above. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that can be integrated with one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium, or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0240] The prediction, control devices, equipment, and storage media provided in the above-mentioned embodiments of the present application are all used to execute the method embodiments provided above. Therefore, the beneficial effects that can be achieved can refer to the corresponding beneficial effects of the method embodiments provided above, and will not be repeated here.

[0241] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A method for predicting battery temperature, characterized in that: include: Obtaining a value of a relevant parameter that can affect a battery temperature in a device at a corresponding moment, wherein the corresponding moment includes a historical moment, or the corresponding moment includes a historical moment and a current moment; The temperature of the battery at a first moment in the future is predicted according to the value of the relevant parameter at the corresponding moment, the temperature of the battery at the corresponding moment, and the degree to which the relevant parameter affects the change in battery temperature.

2. The method according to claim 1, characterized in that The obtaining of the values ​​of the relevant parameters that can affect the battery temperature in the device at the corresponding time includes: The values ​​of the relevant parameters at the corresponding time are obtained locally.

3. The method according to claim 1, characterized in that In the case where the corresponding moment only includes historical moments, obtaining the value of the relevant parameter that can affect the temperature of the battery in the device at the corresponding moment includes: Obtaining the value of the relevant parameter at the historical moment from the cloud; In a case where the corresponding moment includes the current moment and the historical moment, the obtaining of the value of the relevant parameter that can affect the temperature of the battery in the device at the corresponding moment includes: Obtaining the value of the relevant parameter at the current moment from the local; The values ​​of the relevant parameters at the historical moment are obtained from the cloud.

4. The method according to any one of claims 1 to 3, characterized in that Predicting the temperature of the battery at a first moment in the future according to the value of the relevant parameter at the corresponding moment, the temperature of the battery at the corresponding moment, and the degree to which the relevant parameter affects the change in battery temperature, includes: Determine a first weight value corresponding to the relevant parameter, where the first weight value represents a contribution degree of the relevant parameter to a result that the battery fails; determining a second weight value corresponding to the relevant parameter according to the value of the relevant parameter at the corresponding moment, wherein the second weight value represents a contribution degree of the value of the relevant parameter at the corresponding moment to a change in battery temperature; Predict the temperature of the battery at a first moment in the future according to the first weight value, the second weight value, and the temperature of the battery at the corresponding moment.

5. The method according to claim 4, characterized in that The method further comprises: Acquire a first weight value sequence corresponding to the battery that has failed, the first weight value sequence including a third weight value corresponding to each of the relevant parameters, any of the third weight values ​​being determined based on a first weight value and a second weight value corresponding to the corresponding relevant parameter at the moment when the battery that has failed failed; Predicting the temperature of the battery at a first moment in the future according to the first weight value, the second weight value, and the temperature of the battery at the corresponding moment includes: Determine a plurality of second weight value sequences corresponding to a plurality of corresponding moments, wherein the plurality of corresponding moments correspond to the plurality of second weight value sequences one-to-one, and any of the second weight value sequences includes a fourth weight value corresponding to each of the relevant parameters, and the fourth weight value is determined based on the first weight value and the second weight value corresponding to the corresponding relevant parameter at the corresponding moment; The temperature of the battery at the first moment is predicted according to the plurality of second weight value sequences, the first weight value sequence, and the temperature of the battery at the plurality of corresponding moments.

6. The method according to claim 5, characterized in that Predicting the temperature of the battery at the first moment according to the plurality of second weight value sequences, the first weight value sequence, and the temperature of the battery at the plurality of corresponding moments comprises: Summing the third weight values ​​in the first weight value sequence to obtain a first risk index; Determine a plurality of second risk indexes according to the plurality of second weight value sequences, wherein the plurality of second weight value sequences correspond to the plurality of second risk indexes one by one, and any second risk index is the sum of the fourth weight values ​​included in the corresponding second weight value sequence; The temperature of the battery at the first moment is predicted based on the multiple second risk indexes, the first risk index, and battery temperatures corresponding to the multiple second risk indexes and the first risk index.

7. The method according to claim 6, characterized in that Predicting the temperature of the battery at the first moment based on the multiple second risk indexes, the first risk index, and battery temperatures corresponding to the multiple second risk indexes and the first risk index includes: In a case where the plurality of second risk indices change monotonically over time, determining the second risk index corresponding to the first moment based on the plurality of second risk indices and the plurality of corresponding moments; The temperature of the battery at the first moment is predicted based on the second risk index and the battery temperature corresponding to the first moment, the first risk index, and the battery temperature corresponding to the first risk index.

8. The method according to any one of claims 5 to 7, characterized in that The step of obtaining a first weight value sequence corresponding to a battery that has failed includes: updating the first weight value sequence according to a third weight value sequence corresponding to the battery having a fault, wherein the sum of the third weight values ​​included in the third weight value sequence is less than the first risk index; Obtain the updated first weight value sequence.

9. The method according to any one of claims 4 to 8, characterized in that Determining a first weight value corresponding to the relevant parameter includes: The first weight value is determined according to the values ​​of the relevant parameters at the moment when the faulty battery fails and a hierarchy analysis method.

10. The method according to any one of claims 4 to 9, characterized in that Determining a second weight value corresponding to the relevant parameter according to the value of the relevant parameter includes: The second weight value is determined according to the value of the relevant parameter at the corresponding moment and the first weight value.

11. A method for controlling battery temperature, characterized in that: include: Predicting the temperature of a battery in a device at a first moment in the future based on the method of any one of claims 1 to 10; A process is selected based on the temperature, the process being used to improve the temperature of the battery at the first time.

12. The method according to claim 11, characterized in that Selecting a process based on the temperature includes: determining, based on the temperature, a range to which the temperature belongs; The process is selected based on the belonging range.

13. The method according to claim 12, characterized in that The range of the temperature determined based on the temperature is greater than or equal to a first threshold, or less than or equal to a second threshold, wherein the first threshold is greater than the second threshold, and when the temperature of the battery is greater than or equal to the first threshold, or less than or equal to the second threshold, the battery will fail.

14. The method according to claim 13, characterized in that Selecting the processing based on the belonging range includes: The battery is stopped from being used before the first time based on the belonging range.

15. The method according to claim 13, characterized in that Selecting the processing based on the belonging range includes: Based on the range, first indication information is sent to the device, where the first indication information instructs the device to stop using the battery before the first moment, or the first indication information indicates the range to which the temperature belongs.

16. The method according to claim 12, characterized in that The temperature range determined based on the temperature is less than a first threshold and greater than a third threshold. When the temperature of the battery is greater than or equal to the first threshold, the battery will fail. The third threshold is the upper limit temperature for normal operation of the battery.

17. The method according to claim 16, characterized in that Selecting the processing based on the belonging range includes: A cooling system for the battery is selectively activated based on the range.

18. The method according to claim 16, characterized in that Selecting the processing based on the belonging range includes: Based on the range, second indication information is sent to the device, where the second indication information instructs the device to turn on a cooling system of the battery, or the second indication information indicates the range to which the temperature belongs.

19. The method according to claim 12, characterized in that The temperature range determined based on the temperature is greater than a second threshold and less than a fourth threshold. When the temperature of the battery is less than or equal to the second threshold, the battery will fail. The fourth threshold is the lower limit temperature for normal operation of the battery.

20. The method according to claim 19, characterized in that Selecting the processing based on the belonging range includes: A heating system for the battery is selected to be activated based on the belonging range.

21. The method according to claim 19, characterized in that Selecting the processing based on the belonging range includes: Based on the range, third indication information is sent to the device, where the third indication information instructs the device to turn on a heating system of the battery, or the third indication information indicates the range to which the temperature belongs.

22. The method according to claim 13, 16 or 19, characterized in that The first threshold value and / or the second threshold value are determined based on test data or statistical data of batteries that have failed.

23. The method according to any one of claims 1 to 22, characterized in that The relevant parameters include at least one of the following: ambient temperature, the voltage of the battery, the current of the battery, the internal resistance of the battery, road conditions, driving behavior, and the life of the battery.

24. A device, characterized in that The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 23 when executing the computer program.

25. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 23.

Images