Vehicle testing methods, vehicle testing equipment, vehicles and storage media

Abstract

This application relates to the field of vehicle battery technology, and in particular to a vehicle detection method, a vehicle detection device, a vehicle, and a storage medium. The vehicle detection method includes: responding to a temperature management system performing thermal control on a battery module, obtaining the duration of the current thermal control as a control duration; predicting the time required for thermal control of the battery module, as a predicted duration; wherein the temperature management system manages the temperature of the battery module, and thermal control includes cooling and / or heating the battery module; comparing the control duration with the predicted duration; and determining that the vehicle's battery thermal control function is abnormal if the control duration exceeds the predicted duration. This method enables thermal management of the battery module from a time perspective, predicting the time required for thermal control of the battery module, and, based on the comparison of the predicted duration and control duration, facilitates timely identification of abnormal situations during thermal control of the battery module.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle battery, in particular to a vehicle detection method, a vehicle detection device, a vehicle and a computer readable storage medium. BACKGROUND

[0002] Battery thermal management is to improve the overall performance of the battery by solving the problem of heat dissipation or thermal runaway caused by the battery working at too high or too low temperature, according to the influence of temperature on the performance of the battery, combining the electrochemical characteristics and heat generation mechanism of the battery, and based on the optimal charging and discharging temperature range of the specific battery.

[0003] However, in the related art, the battery is usually heated or cooled according to the temperature control of the battery module. Further, the battery module can be further managed by combining the temperature difference between the condensate in the battery module and the temperature of the battery module, and the battery module is still managed by temperature dimension, which has the problem of imperfect battery thermal management. SUMMARY

[0004] Therefore, it is necessary to provide a vehicle detection method, a vehicle detection device, a vehicle and a computer readable storage medium which can manage the battery module from the time dimension, predict the time required for thermal control of the battery module, and based on the comparison of the predicted time and the control time, it is beneficial to timely identify the vehicle with abnormal situation of thermal control of the battery module.

[0005] In one aspect, a vehicle detection method is provided, the vehicle detection method comprising: in response to the temperature management system performing thermal control on the battery module, obtaining the time duration of the current thermal control as the control time; predicting the time required for thermal control of the battery module as the predicted time; wherein the temperature management system is used to manage the temperature of the battery module, and the thermal control includes cooling the battery module and / or heating the battery module; comparing the control time with the predicted time; and in response to the control time exceeding the predicted time, determining that the battery thermal control function of the vehicle is abnormal.

[0006] In an embodiment of the present application, the thermal control includes cooling the battery module, and the control time includes the cooling time; the predicted time required for cooling the battery module is the predicted time, which includes: obtaining the battery internal resistance of the battery module; calculating the first heat generated by the battery module in the cooling time based on the battery internal resistance; and predicting the time required for the battery module to generate the first heat in the cooling process under normal circumstances as the predicted time.

[0007] In one embodiment of this application, the first heat generated by the battery module within a cooling time is calculated based on the battery internal resistance: the operating parameters of the battery module and the interval between the previous acquisition of the battery internal resistance are obtained; the second heat generated by the battery module within the interval is calculated using the battery internal resistance, operating parameters and interval; the second heat at the current interval is superimposed with the first heat calculated in the previous adjacent time, and the superposition result is used as the new first heat.

[0008] In one embodiment of this application, thermal control includes cooling the battery module, and the control duration includes a cooling duration. Predicting the time required to cool the battery module includes: identifying the vehicle's configuration information and cooling conditions; obtaining a prediction model that matches both the configuration information and the cooling conditions; wherein multiple prediction models are pre-trained based on both the configuration information and the cooling conditions; and inputting the first heat generated by the battery module during the cooling duration into the prediction model to obtain the predicted duration.

[0009] In one embodiment of this application, pre-training multiple prediction models based on configuration information and cooling conditions includes: acquiring multiple sets of prediction samples; wherein each prediction sample includes a duration sample and a heat sample that has a one-to-one correspondence with it; grouping the prediction samples so that the prediction samples that match the configuration information and cooling conditions are in one group; performing data fitting on the heat sample and duration sample of each group respectively to form a univariate linear function of the heat sample and duration sample of each group, and using the univariate linear function as the prediction model.

[0010] In one embodiment of this application, determining that the vehicle's battery cooling function is abnormal in response to the control duration exceeding the predicted duration includes: obtaining the difference between the control duration and the predicted duration, and comparing the difference with a grade duration; wherein the grade duration includes a first duration, a second duration, and a third duration, and the first duration, the second duration, and the third duration increase sequentially; in response to the difference being between the first duration and the second duration, determining and reporting a first abnormality level; in response to the difference being between the second duration and the third duration, determining and reporting a second abnormality level; in response to the difference exceeding the third duration, determining and reporting a third abnormality level.

[0011] In one embodiment of this application, thermal control includes cooling the battery module, and the control duration includes a cooling duration; predicting the time required to cool the battery module, the predicted duration includes: acquiring the vehicle's cooling conditions; wherein the cooling conditions include single cooling conditions and dual cooling conditions, the single cooling condition is for cooling the battery module, and the dual cooling condition is for cooling both the battery module and the passenger compartment; in response to the vehicle being in dual cooling conditions, acquiring the cooling capacity allocation information of the temperature management system for both the battery module and the passenger compartment; and combining the cooling capacity allocation information and the first heat generated by the battery module during the cooling duration to predict the predicted duration.

[0012] On the other hand, a vehicle detection device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it performs the following steps: in response to a temperature management system cooling the battery module, it obtains the duration of the current cooling cycle; it predicts the time required for the battery module to cool down as the predicted duration; it compares the cooling duration with the predicted duration; and in response to the cooling duration exceeding the predicted duration, it determines that the vehicle's battery cooling function is abnormal.

[0013] On another front, a vehicle is provided, comprising: a battery module, a temperature management system, and a control module; the temperature management system is connected to the battery module and is used to manage the temperature of the battery module, and to perform thermal control on the battery module when the battery module meets the thermal control conditions; the thermal control includes cooling and / or heating the battery module; the control module is connected to the battery module and the temperature management system, and is used to, when the temperature management system performs thermal control on the battery module, obtain the duration of the current thermal control as the control duration; predict the time required for thermal control of the battery module as the predicted duration; compare the control duration with the predicted duration; and, in response to the control duration exceeding the predicted duration, determine that the battery thermal control function of the vehicle is abnormal.

[0014] In another aspect, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the following steps: in response to a temperature management system cooling the battery module, obtaining the duration of the current cooling cycle; predicting the time required for the battery module to cool, as the predicted duration; comparing the cooling duration with the predicted duration; and in response to the cooling duration exceeding the predicted duration, determining that the vehicle's battery cooling function is abnormal.

[0015] The aforementioned vehicle detection method, vehicle detection device, vehicle, and computer-readable storage medium, in response to the temperature management system, perform thermal control on the battery module, compare the control duration with the predicted duration, and combine the time dimension to perform battery thermal management on the battery module. Based on the relative management between the control duration and the predicted duration, the current cooling situation is analyzed. When the control duration exceeds the predicted duration, it is considered that there is a risk of failure in the battery thermal control function of the battery module, and the vehicle's battery thermal control function is judged to be abnormal, which is conducive to timely identification of abnormal battery module cooling. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating an embodiment of the vehicle inspection method of this application;

[0017] Figure 2 This is a flowchart illustrating another embodiment of the vehicle inspection method of this application;

[0018] Figure 3 This is a flowchart illustrating an embodiment of the prediction model training method of this application;

[0019] Figure 4 This is a schematic diagram of the structure of an embodiment of the vehicle detection device of this application;

[0020] Figure 5 This is a structural schematic diagram of an embodiment of the vehicle described in this application. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0022] To address the technical problems arising from deficiencies in battery thermal management methods in related technologies, this application provides a vehicle testing method. This vehicle testing method can inspect the battery module of a vehicle.

[0023] In one embodiment, such as Figure 1 As shown, a vehicle inspection method is provided. Figure 1 This is a flowchart illustrating an embodiment of the vehicle inspection method of this application.

[0024] S101: In response to the temperature management system performing thermal control on the battery module, the duration of the current thermal control is obtained as the control duration; the time required for thermal control of the battery module is predicted as the prediction duration; wherein, the temperature management system is used to manage the temperature of the battery module, and the thermal control includes cooling and / or heating the battery module.

[0025] In this embodiment, as the name suggests, the temperature management system is used to manage the temperature of the battery module. Specifically, temperature management can be achieved through thermal control. In other words, thermal control is a means of regulating the temperature of the battery module, and it can include cooling and / or heating the battery module. When the battery module meets the thermal control conditions, appropriate thermal control can be applied to the battery module.

[0026] For example, thermal control conditions include heating the battery module when its temperature is lower than the heating node temperature, and cooling the battery module when its temperature is higher than the cooling node temperature.

[0027] The control duration is the time recorded from the start of the current thermal control of the battery module by the temperature management system. In other words, the duration of the current thermal control is defined as the control duration.

[0028] The control duration is the actual duration of thermal control of the battery module, while the predicted duration is the estimated duration required for thermal control of the battery module.

[0029] For example, the prediction time could be the initial temperature at which the temperature management system begins thermal control of the battery module; the time required for the battery module to adjust from the initial temperature to the target temperature could be predicted; and the target temperature could be the temperature node at which the temperature management system is allowed to stop thermal control of the battery module. The prediction time could be calculated in real time or a pre-established two-dimensional table of the initial temperature, target temperature, and prediction time could be used; neither is limited here. Examples of methods for obtaining prediction time using temperature changes will be given later and will not be elaborated upon here.

[0030] Alternatively, the management time required for the battery module to generate the first heat within the control period under normal circumstances can be calculated and used as the predicted duration, which is not limited here.

[0031] S102: Compare control duration with prediction duration.

[0032] In this embodiment, the control duration is compared with the predicted duration. During the thermal control of the battery module, the battery thermal management is carried out by combining the time dimension with the temperature dimension, which is beneficial to optimize the battery thermal management.

[0033] S103: If the control duration exceeds the predicted duration, the vehicle's battery thermal control function is determined to be abnormal.

[0034] In this embodiment, when the control duration exceeds the predicted duration, it is considered that the vehicle's control duration has exceeded the time it should take to complete thermal control. This indicates a risk that the current control duration may be unreasonable, and also a risk of battery thermal control function failure. The cause could be a battery module malfunction and / or a performance abnormality in the temperature management system, or even an unknown fault. The cause of the abnormality needs to be investigated to reduce the negative impression of the vehicle's performance. Therefore, the vehicle's battery cooling function is determined to be abnormal.

[0035] This can be achieved by considering the control duration as greater than the predicted duration, thus improving the timeliness of vehicle anomaly detection. Alternatively, it can be considered that the control duration exceeds the predicted duration if the control duration is greater than the predicted duration and the difference between the two is greater than a preset value. This is to account for the fact that the predicted duration is an estimated duration rather than a standard duration, and that the actual performance, operating conditions, and parameters of the vehicle may change dynamically. The information obtained at the sampling node is not stable and continuous, leaving a certain margin of error to adapt to different vehicle states.

[0036] Therefore, this embodiment incorporates battery thermal management into the vehicle detection scope, enabling timely identification of anomalies in battery thermal management. This helps mitigate the risk of severe impacts on vehicle performance and safety caused by battery thermal management malfunctions. In addition to thermal control of the battery module based on its temperature, battery thermal management is also performed in conjunction with a time dimension. By comparing the duration of the current thermal control operation with the predicted duration, and analyzing the current thermal control status, it is beneficial to promptly identify any abnormalities in the battery module's thermal control.

[0037] Furthermore, upon determining that the vehicle's battery thermal control function is malfunctioning, the urgency of the malfunction can be further analyzed, i.e., the malfunction level can be analyzed, and the malfunction level can be reported to the user and / or manufacturer to alert the user and / or manufacturer to the urgency of the vehicle malfunction.

[0038] Specifically, the difference between the control duration and the predicted duration can be obtained, and this difference can be compared with the grade duration. The grade duration includes a first duration, a second duration, and a third duration, with the first, second, and third durations increasing sequentially. If the difference is between the first and second durations, a first anomaly level is determined and reported; if the difference is between the second and third durations, a second anomaly level is determined and reported; if the difference exceeds the third duration, a third anomaly level is determined and reported.

[0039] The severity of the emergency / seriousness of vehicles increases sequentially from the first abnormal level to the second abnormal level and the third abnormal level.

[0040] In one embodiment, such as Figure 2 As shown, another vehicle detection method is provided. Figure 2 This is a flowchart illustrating another embodiment of the vehicle testing method of this application. It should be noted that this embodiment illustrates a vehicle testing method where thermal control involves cooling the battery module; correspondingly, the control duration includes the cooling duration.

[0041] S201: Identify whether the temperature management system is cooling the battery module.

[0042] In this embodiment, if the temperature management system cools the battery module, and it is deemed necessary to incorporate time-based battery thermal management, then step S202 is executed. If the temperature management system does not cool the battery module, then step S201 is repeated.

[0043] Generally, when the temperature of the battery in the battery module rises to a certain threshold, the BMS (Battery Management System) initiates a cooling request, issuing a target temperature for the battery inlet. The water pump typically operates with a fixed, relatively high duty cycle, activating the compressor. The cooling intensity of the temperature management system can be adjusted based on the difference between the actual battery inlet temperature and the target temperature, using control algorithms such as PID control and PI control, to regulate the battery inlet temperature.

[0044] S202: Get the duration of the current cooling cycle.

[0045] In this embodiment, in response to the temperature management system cooling the battery module, the cooling time is managed to determine whether the cooling function is normal.

[0046] In other words, this embodiment assumes that when the temperature management system is functioning normally and the vehicle is in normal working condition, the cooling time should be relatively stable under the same environment.

[0047] The moment the temperature management system begins cooling the battery module is taken as the starting node for cooling duration statistics. The duration of the current cooling cycle is then obtained to perform battery thermal management in conjunction with the time dimension. In other words, the duration of the current cooling cycle on the battery module is defined as the cooling duration.

[0048] S203: Obtain the internal resistance of the battery module.

[0049] In this embodiment, it is assumed that the time from the start of the cooling node to the temperature stabilization of the battery module is highly correlated with the heat generated by the charging and discharging current of the battery module through the battery's internal resistance.

[0050] In this embodiment, the battery internal resistance of the battery module can be acquired by reporting CAN (Controller Area Network) information through the BMS controller. CAN is an internationally standardized serial communication protocol.

[0051] S204: Calculate the first heat generated by the battery module during the cooling period based on the battery's internal resistance.

[0052] In this embodiment, the operating parameters of the battery module can be obtained, such as the output / input current, voltage, and power of the battery module. This is based on the heat calculation formula Q = I... 2 RT or Q=UIT, etc., are used to calculate the first heat generated during the cooling period.

[0053] Since the battery module has two working states, namely charging and discharging, the current value of the battery module can be positive or negative. When calculating the first heat, the absolute value of the current is used for calculation.

[0054] One method is to directly calculate the first heat using the currently obtained battery internal resistance, operating parameters, and cooling time.

[0055] Alternatively, the operating parameters of the battery module and the interval between the previous and next calculated battery internal resistance measurements can be obtained. Using the battery internal resistance, operating parameters, and interval, the second heat generated by the battery module within that interval is calculated. The second heat at the current interval is then added to the first heat calculated in the previous interval, and the result is used as the new first heat. In this case, considering that the battery module's output current / feedback current / input current are updated in real time, and that the battery internal resistance varies with ambient temperature, operating time, and charge / discharge state, the calculated first heat can be made as close as possible to the actual heat generated by the battery module during the cooling period. The formula for calculating the first heat can be as follows:

[0056]

[0057] Where i represents a sampling point within the cooling time, and i is a positive integer; n indicates the number of sampling points within the current cooling time, and n is a positive integer; I represents the absolute value of the battery module current, I i R represents the absolute value of the current collected at the i-th sampling point; R represents the internal resistance of the battery. i ΔT represents the battery internal resistance collected at the i-th sampling point; i This represents the time interval between the i-th sampling point and the (i-1)-th sampling point.

[0058] Optionally, the interval can be the same, that is, the battery internal resistance and operating parameters are acquired periodically.

[0059] S205: Predict the time required for the first heat to be generated during the cooling process under normal conditions, and use this as the prediction duration.

[0060] In this embodiment, the predicted cooling time of the battery module is used as the predicted duration, which can be the predicted time required for the battery module to generate the first heat.

[0061] Specifically, the system can identify the vehicle's configuration information and cooling conditions. A prediction model matching both the configuration information and the cooling conditions is then obtained; multiple prediction models are pre-trained based on both the configuration information and the cooling conditions. The first heat generated by the battery module during the cooling period is input into the prediction model to obtain the predicted duration. The specific methods for training the prediction models will be described in detail below.

[0062] In an alternative embodiment, data analysis can be performed based on heat samples and duration samples to preset multiple heat levels and preset durations for each heat level. The heat corresponding to the first heat level is matched, and the corresponding predicted duration is used as the predicted duration.

[0063] S206: Compare cooling time with predicted time.

[0064] In this embodiment, if the cooling time exceeds the predicted time, it is considered that the temperature management system has been cooling the battery module for too long, and step S207 is executed. If the cooling time does not exceed the predicted time, it is considered that the cooling time of the temperature management system for the battery module is still within the normal range, and step S201 is executed.

[0065] S207: The vehicle's battery cooling function is determined to be abnormal.

[0066] In this embodiment, if the cooling time exceeds the predicted time, the vehicle's battery cooling function is determined to be abnormal. Information regarding the abnormal battery cooling function is provided to the user so that they are aware of the problem and are encouraged to promptly take the vehicle to an authorized service center for troubleshooting of the battery module and temperature management system, thus reducing the risk of serious battery cooling function failure.

[0067] S208: Compare the difference between the cooling time and the predicted time with the level duration.

[0068] In this embodiment, after determining that the vehicle's battery cooling function is abnormal, the level of abnormality can be further evaluated, and the abnormal situation can be classified to help inform the user of the different urgency levels of the vehicle abnormality.

[0069] Specifically, the difference between the actual cooldown duration and the predicted duration can be obtained. This difference is then compared to the tier duration to assess the degree of anomaly based on the gap between the actual and predicted cooldown durations.

[0070] The duration of each level includes the first cooling duration, the second cooling duration, and the third cooling duration, with the first cooling duration, the second cooling duration, and the third cooling duration increasing sequentially.

[0071] S209: Determine and report the vehicle's abnormality level.

[0072] In this embodiment, if the difference between the two values ​​is between the first cooling time and the second cooling time, a first abnormality level is determined and reported; if the difference between the two values ​​is between the second cooling time and the third cooling time, a second abnormality level is determined and reported; if the difference between the two values ​​exceeds the third cooling time, a third abnormality level is determined and reported.

[0073] The severity of the first, second, and third abnormality levels increases sequentially.

[0074] For example, the first duration could be 10 minutes, the second duration could be 15 minutes, and the third duration could be 20 minutes. Let T (cooling) represent the cooling duration and T (prediction) indicate the predicted duration. The specific logic for reporting anomaly levels is as follows:

[0075] If 10min < (T(actual) - T(estimated)) < 15min, then the battery cooling function abnormality should be reported as the first abnormality level.

[0076] If 15min≤(T(actual)-T(estimated))<20min, then the battery cooling function abnormality should be reported as the second abnormality level.

[0077] If 20min ≤ (T(actual) - T(estimated)), then the reported battery cooling function abnormality is classified as the third abnormality level.

[0078] In an alternative embodiment, the anomaly level can be further refined or simplified, which is not limited here.

[0079] Furthermore, in this embodiment, the vehicle's cooling conditions may include a single cooling condition and a dual cooling condition. The single cooling condition cools the battery module, while the dual cooling condition cools both the battery module and the passenger compartment simultaneously.

[0080] The process of predicting the prediction duration described in step S205 can be applied to a single cooling condition.

[0081] Under dual-cooling conditions, the prediction duration can be predicted by combining the cooling capacity allocation information of the temperature management system.

[0082] Specifically, the vehicle's cooling conditions are acquired and identified. In response to the vehicle being in dual-cooling mode, information on the cooling allocation between the battery module and the passenger compartment from the temperature management system is obtained. Combining the cooling allocation information with the initial heat generated by the battery module during the cooling period, the prediction duration is calculated.

[0083] Optionally, the predicted duration can be obtained according to step S205, and the predicted duration obtained in step S205 can be divided by the percentage of cooling amount allocated to the battery module. The obtained value can be used as the predicted duration for comparison in subsequent steps.

[0084] Alternatively, a functional relationship or prediction model could be established between the information on the distribution of primary heat and cooling capacity and the prediction duration, without any limitations here.

[0085] Generally, when the battery temperature reaches a certain threshold, the compressor is turned on to remove heat from the battery circuit through heat exchange between the refrigerant and the battery, thus cooling the battery. The temperature management system includes a water circuit (including an electronic water pump, three-way valve, etc.) and a refrigerant circuit (including an electronic expansion valve, refrigerant piping, etc.).

[0086] Typically, abnormal battery cooling function can be identified through diagnostics of cooling system components or alarms indicating abnormal battery temperature rise. If the cooling system components are functioning correctly, the battery temperature is controlled by the compressor and remains below the over-temperature risk reporting threshold. However, if the cooling time is significantly extended beyond the normal cooling time due to an unknown fault, no fault indication will be given, and technical personnel will not receive any notification. This malfunction in battery cooling function may go undetected and could even further deteriorate the battery cooling effect, negatively impacting battery life and thermal management safety.

[0087] Therefore, in this embodiment, the heat generated by the battery module during cooling (i.e., the first heat) is calculated, and the actual time it takes for the battery to reach a stable cooling state is collected. A relationship between the battery cooling time and the battery heat generated is fitted, i.e., the relationship between cooling time and the first heat mentioned above. A risk assessment for battery cooling system anomalies is then performed based on a threshold difference between the estimated battery cooling time and the actual collected cooling time. Even when no fault codes are reported by relevant components of the battery temperature management system, the risk of an anomaly in the temperature management system can be identified and reported by comparing the estimated cooling time with the actual cooling time. This helps identify unknown risks, thus facilitating the early resolution of potential problems before any adverse effects occur on the vehicle.

[0088] The following examples illustrate methods for training prediction models. Figure 3 As shown, Figure 3 This is a flowchart illustrating an embodiment of the prediction model training method of this application.

[0089] S301: Obtain multiple sets of prediction samples; each prediction sample includes a duration sample and a heat sample that has a one-to-one correspondence with it.

[0090] In this embodiment, multiple historical data points on the cooling of the battery module by the temperature management systems of multiple vehicles are acquired. Each historical data point can represent the data from a single cooling operation of the battery module.

[0091] Historical data can be battery internal resistance, operating parameters, etc. collected by each reporting information node, or it can be pre-calculated duration and heat samples with matching relationships, without any limitation.

[0092] For example, historical data can be the battery internal resistance and operating parameters collected by each reporting node, and heat samples can be calculated using formula (1-1). Furthermore, since historical data contains relatively abundant data on battery internal resistance, operating parameters, and cooling time, a single historical cooling data point can generate multiple duration samples and heat samples, which is beneficial for enriching the prediction samples.

[0093] S302: Group the predicted samples so that the predicted samples whose configuration information matches the cooling conditions are grouped together.

[0094] In this embodiment, the configuration information may include at least one of the following: vehicle temperature management system configuration, vehicle model, and battery module configuration.

[0095] The cooling conditions can be as described above, including single cooling conditions and dual cooling conditions.

[0096] By pulling bus messages from the background big data and combining them with cooling information and cooling conditions, historical data is grouped to facilitate more precise prediction of forecast duration.

[0097] S303: Perform data fitting on the heat samples and duration samples of each group to form a univariate linear function of the heat samples and duration samples of each group, and use the univariate linear function as the prediction model.

[0098] In this embodiment, the relationship between the heat sample and the duration sample is set to a univariate linear function. The univariate linear function of each group is obtained to simplify the relationship function between the heat sample and the duration sample as much as possible, which helps to reduce the training cost and also helps to reduce the computational cost of obtaining the predicted duration.

[0099] Specifically, the following example illustrates the data fitting process for a set of prediction samples, where T represents the duration sample, Q represents the calorie sample, and T... i With Q i This represents duration samples and corresponding heat samples.

[0100] We can assume that the univariate linear function is a typical univariate linear regression function, and the initial univariate linear function is T. i =θ0+θ1Q i Where θ0 and θ1 are the parameters of the function to be determined.

[0101] The parameters of the function to be solved are initially assigned values, and the iteration interval is set. The value of the iteration interval determines the update speed of the parameters of the function to be solved; the larger the iteration interval, the faster the update, and the smaller the iteration interval, the slower the update.

[0102] The squared error function is used as the cost function for iterative training of the parameters of the function to be determined, and the parameters of the function to be determined with the minimum iteration value are selected during the iterative training.

[0103] Gradient descent is applied to the parameters of the function to be determined that minimize the cost function value during iterative training. The processed parameters are then substituted into the initial univariate linear function, and the resulting univariate linear function is used as the prediction model for that group.

[0104] For example, the parameters of the function to be solved can be initialized to θ0 = 1 and θ1 = 1, with an iteration interval of α = 0.001.

[0105] Substitute θ0 and θ1 into the squared error function as shown in Equation 2-1 for iterative training:

[0106]

[0107] Where L is the cost value, M is the number of time-based / calorie-based samples, and T is the total cost. i With Q i This represents duration samples and corresponding heat samples.

[0108] After completing the iterative training, select θ0 and θ1 that minimize L, and substitute them into the following formula for updating:

[0109]

[0110]

[0111] In this context, := indicates assignment.

[0112] The loop iteration count is set to 1000. Based on α, calculations as shown in (Equations 2-1) to (Equations 2-3) are repeated to continuously update θ0 and θ1, and the cost L is calculated after each update. The values ​​of θ0 and θ1 when L is at their minimum are substituted into the initial univariate linear function T. i =θ0+θ1Q i The functional relationship between T and Q is obtained:

[0113] T = f(Q) = θ0 + θ1Q (Equation 3-1)

[0114] Equation 3-1 can be used as the prediction model in the above embodiments, where T is the prediction duration in the above embodiments and Q is the first heat in the above embodiments.

[0115] In an alternative embodiment, the prediction model for the first heat and the prediction duration can be a more complex functional relationship. For example, it may also include weights such as ambient temperature and the temperature of the battery module inlet at the initial stage of thermal control, etc., which are not limited here.

[0116] Alternatively, a neural network model can be used to train the prediction model, which is not limited here.

[0117] It should be noted that this application can also implement a vehicle detection method for heating the battery module by means of thermal control, and the control duration includes the heating duration.

[0118] Specifically, a predictive model for the heating time and battery heat generation during the heating process of the battery module can be pre-trained. The specific training method is similar to that described above. Figure 3 The training method is similar and will not be elaborated here. When the temperature management system actually heats the battery module, it calculates the battery heat generated by the battery module during the heating time, uses a prediction model to predict the predicted time, and compares the heating time with the predicted time to determine whether the vehicle's battery thermal control function is abnormal.

[0119] It should be understood that, although Figures 1-3 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figures 1-3 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0120] In one embodiment, such as Figure 4 As shown, a vehicle detection device is provided. Figure 4 This is a structural schematic diagram of an embodiment of a vehicle detection device.

[0121] The vehicle detection device includes a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor. When the processor 41 executes the computer program, it performs the following steps:

[0122] S101: In response to the temperature management system performing thermal control on the battery module, the duration of the current thermal control is obtained as the control duration; the time required for thermal control of the battery module is predicted as the prediction duration; wherein, the temperature management system is used to manage the temperature of the battery module, and the thermal control includes cooling and / or heating the battery module.

[0123] S102: Compare control duration with prediction duration.

[0124] S103: If the control duration exceeds the predicted duration, the vehicle's battery thermal control function is determined to be abnormal.

[0125] Furthermore, determining that the vehicle's battery cooling function is abnormal in response to the control duration exceeding the predicted duration includes: obtaining the difference between the control duration and the predicted duration, and comparing the difference with the grade duration; wherein the grade duration includes a first duration, a second duration, and a third duration, and the first duration, the second duration, and the third duration increase sequentially; in response to the difference being between the first duration and the second duration, a first abnormality level is determined and reported; in response to the difference being between the second duration and the third duration, a second abnormality level is determined and reported; in response to the difference being exceeding the third duration, a third abnormality level is determined and reported.

[0126] In one embodiment, when the processor 41 executes the computer program, it also implements a vehicle detection method for cooling the battery module, wherein the control duration includes a cooling duration, and specifically includes the following steps:

[0127] S201: Identify whether the temperature management system is cooling the battery module.

[0128] In this embodiment, if the temperature management system cools the battery module, step S202 is executed. If the temperature management system does not cool the battery module, step S201 is repeated.

[0129] S202: Get the duration of the current cooling cycle.

[0130] In this embodiment, in response to the temperature management system cooling the battery module, the cooling time is managed to determine whether the cooling function is normal.

[0131] S203: Obtain the internal resistance of the battery module.

[0132] S204: Calculate the first heat generated by the battery module during the cooling period based on the battery's internal resistance.

[0133] In this embodiment, the operating parameters of the battery module and the interval between the previous acquisition of the battery internal resistance can be obtained. Using the battery internal resistance, operating parameters, and interval, the second heat generated by the battery module within the interval is calculated. The second heat at the current interval is then added to the first heat calculated in the previous interval, and the result is used as the new first heat.

[0134] S205: Predict the time required for the first heat to be generated during the cooling process under normal conditions, and use this as the prediction duration.

[0135] In this embodiment, the predicted cooling time of the battery module is used as the predicted duration, which can be the predicted time required for the battery module to generate the first heat.

[0136] Specifically, the system can identify the vehicle's configuration information and cooling conditions. It then obtains a prediction model that matches both the configuration information and the cooling conditions; multiple prediction models are pre-trained based on both the configuration information and the cooling conditions. The first heat generated by the battery module during the cooling period is input into the prediction model to obtain the predicted duration.

[0137] S206: Compare cooling time with predicted time.

[0138] In this embodiment, if the cooling time exceeds the predicted time, step S207 is executed. If the cooling time does not exceed the predicted time, step S201 is executed.

[0139] S207: The vehicle's battery cooling function is determined to be abnormal.

[0140] In this embodiment, if the cooling time exceeds the predicted time, the vehicle's battery cooling function is determined to be abnormal.

[0141] S208: Compare the difference between the cooling time and the predicted time with the level duration.

[0142] In this embodiment, the difference between the cooling time and the predicted time is obtained. This difference is then compared with the grade duration.

[0143] The duration of each level includes the first cooling duration, the second cooling duration, and the third cooling duration, with the first cooling duration, the second cooling duration, and the third cooling duration increasing sequentially.

[0144] S209: Determine and report the vehicle's abnormality level.

[0145] In this embodiment, if the difference between the two values ​​is between the first cooling time and the second cooling time, a first abnormality level is determined and reported; if the difference between the two values ​​is between the second cooling time and the third cooling time, a second abnormality level is determined and reported; if the difference between the two values ​​exceeds the third cooling time, a third abnormality level is determined and reported.

[0146] Furthermore, the vehicle's cooling conditions can include single cooling and dual cooling. Single cooling involves cooling the battery module, while dual cooling involves cooling both the battery module and the passenger compartment.

[0147] The process of predicting the prediction duration described in step S205 can be applied to a single cooling condition.

[0148] Under dual-cooling conditions, the prediction duration can be predicted by combining the cooling capacity allocation information of the temperature management system.

[0149] Specifically, the vehicle's cooling conditions are acquired and identified. In response to the vehicle being in dual-cooling mode, information on the cooling allocation between the battery module and the passenger compartment from the temperature management system is obtained. Combining the cooling allocation information with the initial heat generated by the battery module during the cooling period, the prediction duration is calculated.

[0150] Optionally, the predicted duration can be obtained according to step S205, and the predicted duration obtained in step S205 can be divided by the percentage of cooling amount allocated to the battery module. The obtained value can be used as the predicted duration for comparison in subsequent steps.

[0151] Alternatively, a functional relationship or prediction model could be established between the information on the distribution of primary heat and cooling capacity and the prediction duration, without any limitations here.

[0152] The following examples illustrate methods for training prediction models:

[0153] S301: Obtain multiple sets of prediction samples; each prediction sample includes a duration sample and a heat sample that has a one-to-one correspondence with it.

[0154] S302: Group the predicted samples so that the predicted samples whose configuration information matches the cooling conditions are grouped together.

[0155] S303: Perform data fitting on the heat samples and duration samples of each group to form a univariate linear function of the heat samples and duration samples of each group, and use the univariate linear function as the prediction model.

[0156] In one embodiment, such as Figure 5 As shown, a vehicle is provided. Figure 5 This is a structural schematic diagram of one embodiment of the vehicle.

[0157] The vehicle includes a battery module 51, a temperature management system 52, and a control module 53.

[0158] The temperature management system 52 is connected to the battery module 51 and is used to manage the temperature of the battery module 51. It performs thermal control on the battery module 51 when the battery module 51 meets the thermal control conditions. This thermal control includes cooling and / or heating the battery module.

[0159] The control module 53 is connected to the battery module 51 and the temperature management system 52. When the temperature management system 52 performs thermal control on the battery module 51, it obtains the duration of the current thermal control; predicts the time required for thermal control of the battery module 51 as the predicted duration; compares the control duration with the predicted duration; and determines that the vehicle's battery cooling function is abnormal if the control duration exceeds the predicted duration.

[0160] Furthermore, the temperature management system 52 may include a heating module and a cooling module. The heating module is used to heat the battery module and may include heating elements such as PTC (Positive Temperature Coefficient) heating devices. The cooling module is used to cool the battery module and may include cooling elements such as compressors and refrigerants.

[0161] As described above, the temperature management system includes a water circuit, such as an electric water pump and a three-way valve. The cooling module includes a refrigerant circuit, such as a temperature sensor, an electronic expansion valve, and refrigerant piping.

[0162] The temperature sensor located in the battery module 51 can be connected to the control module 53 or the battery management system (BMS) to determine whether the thermal control conditions are met. If the thermal control conditions are met, a thermal control cooling signal is sent to the temperature management system 52. Alternatively, the temperature management system 52 may include a temperature sensor located in the battery module 51 or be connected to a temperature sensor located in the battery module 51, and independently determine whether thermal control should be performed.

[0163] Specific limitations regarding vehicle testing devices and vehicles can be found in the limitations of vehicle testing methods described above, and will not be repeated here. The various modules in the aforementioned vehicle testing devices and vehicles can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0164] Those skilled in the art will understand that Figures 4-5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0165] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0166] S101: In response to the temperature management system performing thermal control on the battery module, the duration of the current thermal control is obtained as the control duration; the time required for thermal control of the battery module is predicted as the prediction duration; wherein, the temperature management system is used to manage the temperature of the battery module, and the thermal control includes cooling and / or heating the battery module.

[0167] S102: Compare control duration with prediction duration.

[0168] S103: If the control duration exceeds the predicted duration, the vehicle's battery thermal control function is determined to be abnormal.

[0169] Furthermore, determining that the vehicle's battery cooling function is abnormal in response to the control duration exceeding the predicted duration includes: obtaining the difference between the control duration and the predicted duration, and comparing the difference with the grade duration; wherein the grade duration includes a first duration, a second duration, and a third duration, and the first duration, the second duration, and the third duration increase sequentially; in response to the difference being between the first duration and the second duration, a first abnormality level is determined and reported; in response to the difference being between the second duration and the third duration, a second abnormality level is determined and reported; in response to the difference being exceeding the third duration, a third abnormality level is determined and reported.

[0170] In one embodiment, when the computer program is executed by the processor, it also implements a vehicle detection method for cooling the battery module, wherein the control duration includes a cooling duration, and specifically includes the following steps:

[0171] S201: Identify whether the temperature management system is cooling the battery module.

[0172] In this embodiment, if the temperature management system cools the battery module, step S202 is executed. If the temperature management system does not cool the battery module, step S201 is repeated.

[0173] S202: Get the duration of the current cooling cycle.

[0174] In this embodiment, in response to the temperature management system cooling the battery module, the cooling time is managed to determine whether the cooling function is normal.

[0175] S203: Obtain the internal resistance of the battery module.

[0176] S204: Calculate the first heat generated by the battery module during the cooling period based on the battery's internal resistance.

[0177] In this embodiment, the operating parameters of the battery module and the interval between the previous acquisition of the battery internal resistance can be obtained. Using the battery internal resistance, operating parameters, and interval, the second heat generated by the battery module within the interval is calculated. The second heat at the current interval is then added to the first heat calculated in the previous interval, and the result is used as the new first heat.

[0178] S205: Predict the time required for the first heat to be generated during the cooling process under normal conditions, and use this as the prediction duration.

[0179] In this embodiment, the predicted cooling time of the battery module is used as the predicted duration, which can be the predicted time required for the battery module to generate the first heat.

[0180] Specifically, the system can identify the vehicle's configuration information and cooling conditions. It then obtains a prediction model that matches both the configuration information and the cooling conditions; multiple prediction models are pre-trained based on both the configuration information and the cooling conditions. The first heat generated by the battery module during the cooling period is input into the prediction model to obtain the predicted duration.

[0181] S206: Compare cooling time with predicted time.

[0182] In this embodiment, if the cooling time exceeds the predicted time, step S207 is executed. If the cooling time does not exceed the predicted time, step S201 is executed.

[0183] S207: The vehicle's battery cooling function is determined to be abnormal.

[0184] In this embodiment, if the cooling time exceeds the predicted time, the vehicle's battery cooling function is determined to be abnormal.

[0185] S208: Compare the difference between the cooling time and the predicted time with the level duration.

[0186] In this embodiment, the difference between the cooling time and the predicted time is obtained. This difference is then compared with the grade duration.

[0187] The duration of each level includes the first cooling duration, the second cooling duration, and the third cooling duration, with the first cooling duration, the second cooling duration, and the third cooling duration increasing sequentially.

[0188] S209: Determine and report the vehicle's abnormality level.

[0189] In this embodiment, if the difference between the two values ​​is between the first cooling time and the second cooling time, a first abnormality level is determined and reported; if the difference between the two values ​​is between the second cooling time and the third cooling time, a second abnormality level is determined and reported; if the difference between the two values ​​exceeds the third cooling time, a third abnormality level is determined and reported.

[0190] Furthermore, the vehicle's cooling conditions can include single cooling and dual cooling. Single cooling involves cooling the battery module, while dual cooling involves cooling both the battery module and the passenger compartment.

[0191] The process of predicting the prediction duration described in step S205 can be applied to a single cooling condition.

[0192] Under dual-cooling conditions, the prediction duration can be predicted by combining the cooling capacity allocation information of the temperature management system.

[0193] Specifically, the vehicle's cooling conditions are acquired and identified. In response to the vehicle being in dual-cooling mode, information on the cooling allocation between the battery module and the passenger compartment from the temperature management system is obtained. Combining the cooling allocation information with the initial heat generated by the battery module during the cooling period, the prediction duration is calculated.

[0194] Optionally, the predicted duration can be obtained according to step S205, and the predicted duration obtained in step S205 can be divided by the percentage of cooling amount allocated to the battery module. The obtained value can be used as the predicted duration for comparison in subsequent steps.

[0195] Alternatively, a functional relationship or prediction model could be established between the information on the distribution of primary heat and cooling capacity and the prediction duration, without any limitations here.

[0196] The following examples illustrate methods for training prediction models:

[0197] S301: Obtain multiple sets of prediction samples; each prediction sample includes a duration sample and a heat sample that has a one-to-one correspondence with it.

[0198] S302: Group the predicted samples so that the predicted samples whose configuration information matches the cooling conditions are grouped together.

[0199] S303: Perform data fitting on the heat samples and duration samples of each group to form a univariate linear function of the heat samples and duration samples of each group, and use the univariate linear function as the prediction model.

[0200] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0201] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0202] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A vehicle detection method characterized by, The method comprises: obtaining a current duration of thermal control of the battery module as a control duration in response to the temperature management system performing the thermal control on the battery module; predicting a time required for the thermal control of the battery module as a prediction duration, wherein the temperature management system is configured to manage the temperature of the battery module, and the thermal control comprises cooling the battery module or cooling the battery module and heating the battery module; comparing the control duration with the prediction duration; determining that the battery thermal control function of the vehicle is abnormal in response to the control duration exceeding the prediction duration; the thermal control comprises cooling the battery module, and the control duration comprises a cooling duration; predicting a time required for cooling the battery module as the prediction duration comprises: obtaining a cooling condition of the vehicle, wherein the cooling condition comprises a single cooling condition and a double cooling condition, the single cooling condition is cooling the battery module, and the double cooling condition is cooling the battery module and the passenger compartment; obtaining cooling amount distribution information of the temperature management system for the battery module and the passenger compartment in response to the vehicle being in the double cooling condition; obtaining an operating parameter of the battery module and an interval duration from a previous time when the battery internal resistance is obtained; calculating a second heat generated by the battery module in the interval duration by using the battery internal resistance, the operating parameter, and the interval duration; superimposing the second heat in the current interval duration and a first heat calculated in a previous time to obtain a new first heat; predicting the prediction duration by combining the cooling amount distribution information and the first heat generated by the battery module in the cooling duration.

2. The vehicle detection method according to claim 1, characterized by, the thermal control comprises cooling the battery module, and the control duration comprises a cooling duration; predicting a time required for cooling the battery module as the prediction duration comprises: obtaining a battery internal resistance of the battery module; calculating a first heat generated by the battery module in the cooling duration based on the battery internal resistance; predicting a time required for the battery module to generate the first heat in a cooling process under a normal condition as the prediction duration.

3. The vehicle detection method according to claim 1, characterized by, the thermal control comprises cooling the battery module, and the control duration comprises a cooling duration; predicting a time required for cooling the battery module comprises: identifying configuration information and a cooling condition of the vehicle; obtaining a prediction model matched with the configuration information and the cooling condition, wherein a plurality of prediction models are pre-trained based on the configuration information and the cooling condition; inputting the first heat generated by the battery module in the cooling duration into the prediction model to obtain the prediction duration.

4. The vehicle detection method according to claim 3, characterized by, the plurality of prediction models are pre-trained based on the configuration information and the cooling condition comprises: obtaining a plurality of prediction samples, wherein each prediction sample comprises a duration sample and a heat sample corresponding to the duration sample; grouping the prediction samples, and arranging prediction samples matched with the configuration information and the cooling condition in a group. The heat sample and the time length sample of each group are fitted respectively to form a linear function of the heat sample and the time length sample of each group, and the linear function is taken as the prediction model.

5. The vehicle detection method according to claim 1, characterized by, The response to the control time length exceeding the predicted time length includes determining that the battery cooling function of the vehicle is abnormal. The difference between the control time length and the predicted time length is obtained, and the difference is compared with a level time length; the level time length includes a first time length, a second time length, and a third time length, and the first time length, the second time length, and the third time length increase in turn. In response to the difference being between the first time length and the second time length, a first abnormality level is determined and reported; in response to the difference being between the second time length and the third time length, a second abnormality level is determined and reported; and in response to the difference exceeding the third time length, a third abnormality level is determined and reported.

6. A vehicle detection apparatus characterized by comprising: The vehicle detection device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the steps of the vehicle detection method of any one of claims 1 to 5 are implemented.

7. A vehicle characterized by comprising: The vehicle includes: a battery module; a temperature management system connected to the battery module, configured to manage the temperature of the battery module and perform thermal control on the battery module when the battery module meets a thermal control condition; the thermal control includes cooling the battery module, or cooling the battery module and heating the battery module; a control module connected to the battery module and the temperature management system, configured to obtain the duration of the current thermal control as a control time length when the temperature management system performs thermal control on the battery module, predict the time required for thermal control of the battery module as a predicted time length, compare the control time length with the predicted time length, and determine that the thermal control function of the vehicle is abnormal in response to the control time length exceeding the predicted time length; the thermal control includes cooling the battery module, and the control time length includes a cooling time length; The method comprises: obtaining a cooling condition of the vehicle, wherein the cooling condition comprises a single cooling condition and a double cooling condition, the single cooling condition is cooling the battery module, and the double cooling condition is cooling the battery module and a passenger cabin; in response to the vehicle being in the double cooling condition, obtaining cooling amount distribution information of the temperature management system for the battery module and the passenger cabin; obtaining an operating parameter of the battery module and an interval duration from a previous time point at which a battery internal resistance is obtained; calculating a second heat generated by the battery module in the interval duration based on the battery internal resistance, the operating parameter and the interval duration; superimposing the second heat in the current interval duration and a first heat calculated at the previous time point to obtain a new first heat; and predicting the prediction duration based on the cooling amount distribution information and the first heat generated by the battery module in the cooling duration.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by a processor to implement the steps of the vehicle detection method in any one of claims 1 to 5.

Images