Vehicle battery detection method and device

Abstract

The invention discloses a vehicle battery detection method and device, and the method comprises the steps: obtaining n charge state parameters, n environment temperature parameters, n current parameters and n maximum pressure difference parameters corresponding to n operation moments of a battery of a vehicle in a first time period, so as to determine a maximum pressure difference parameter prediction sequence corresponding to the battery in a second time period, the second time period and the first time period are continuous, and the condition of the battery in the first time period can reflect the possible condition of the battery in the next time domain, so that the obtained maximum voltage difference parameter prediction sequence can reflect the reference change condition of the battery in the second time period. And acquiring a corresponding maximum voltage difference parameter actual sequence of the battery in the second time period, namely the actual condition of the battery, and detecting the battery according to the maximum voltage difference parameter prediction sequence and the maximum voltage difference parameter actual sequence. On the basis, detection can be completed more efficiently and accurately, so that abnormity can be found in time, and influence on vehicle operation and the like is avoided.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle battery detection method and device. Background Art

[0002] New energy vehicles have a profound impact on environmental protection, energy sustainability, and technological innovation, and the global automotive industry has ushered in a wave of new energy transformation. At the same time, users' requirements for the driving range, safety, and intelligence of new energy vehicles are increasing day by day.

[0003] Lithium batteries have become the main power source for new energy vehicles due to their light weight, high energy conversion efficiency, and status monitoring. Lithium battery packs are composed of several cells connected in series and parallel. Inconsistency in the cells will affect the performance of the lithium battery system. In particular, after a vehicle has been used for a long time, there will be differences in the cell temperature, self-discharge rate, and capacity decay rate, making it more likely for the cells to be inconsistent, ultimately affecting the safety or driving range of the entire vehicle.

[0004] In the battery management system, battery consistency is usually judged by the voltage difference of the battery cells. However, each battery cell cannot be completely consistent, and the performance of the battery cells varies under different dynamic conditions. At the same time, the battery cell will also show different performance after failure or aging. Therefore, it is impossible to accurately evaluate battery abnormalities only through discrete voltage differences. In addition, if the battery voltage sensor fails, it may cause false fault alarms or failure to detect battery inconsistencies in time, thereby affecting the performance of the lithium battery system and the operation of the entire vehicle. Therefore, it is urgent to develop a battery fault prediction method and fault diagnosis system to ensure the safe and reliable operation of the lithium battery system. Summary of the invention

[0005] In order to solve the above technical problems, the present application provides a vehicle battery detection method and device, which can predict the theoretical changes in the second time period based on the situation in the first time period, and then realize the battery detection in combination with the actual situation of the battery in the second time period. The battery detection can be completed more efficiently and accurately, so as to detect abnormalities in time and avoid affecting the operation of the vehicle.

[0006] The embodiments of the present application disclose the following technical solutions:

[0007] On the one hand, an embodiment of the present application provides a vehicle battery detection method, the method comprising:

[0008] For the operation process of the vehicle in the first time period, n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum pressure difference parameters corresponding to the n operating moments included in the first time period of the battery of the vehicle are obtained; the i-th maximum pressure difference parameter is used to represent the maximum voltage difference corresponding to the battery cell included in the battery at the i-th operating moment, and n is a positive integer;

[0009] Determine, according to the n state of charge parameters, the n ambient temperature parameters, the n current parameters and the n maximum pressure difference parameters, a maximum pressure difference parameter prediction sequence corresponding to the battery in a second time period; the second time period includes q operating moments, a first operating moment among the q operating moments is an operating moment after the nth operating moment, and q is a positive integer;

[0010] With respect to the operation process of the vehicle in the second time period, obtaining an actual sequence of maximum pressure difference parameters corresponding to the battery in the second time period;

[0011] The battery is detected according to the maximum pressure difference parameter prediction sequence and the maximum pressure difference parameter actual sequence.

[0012] On the other hand, an embodiment of the present application provides a vehicle battery detection device, the device comprising an acquisition unit, a determination unit and a detection unit:

[0013] The acquisition unit is used to acquire, for the operation process of the vehicle in the first time period, n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum pressure difference parameters corresponding to the n operating moments included in the first time period of the battery of the vehicle; the i-th maximum pressure difference parameter is used to represent the maximum voltage difference corresponding to the battery cell included in the battery at the i-th operating moment, and n is a positive integer;

[0014] The determining unit is used to determine a maximum pressure difference parameter prediction sequence corresponding to the battery in a second time period according to the n state of charge parameters, the n ambient temperature parameters, the n current parameters and the n maximum pressure difference parameters; the second time period includes q operating moments, the first operating moment of the q operating moments is an operating moment after the nth operating moment, and q is a positive integer;

[0015] The acquisition unit is further used to acquire an actual sequence of maximum pressure difference parameters corresponding to the battery in the second time period according to the operation process of the vehicle in the second time period;

[0016] The detection unit is used to detect the battery according to the maximum pressure difference parameter prediction sequence and the maximum pressure difference parameter actual sequence.

[0017] It can be seen from the above technical solution that for the operation process of the vehicle in the first time period, the n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum differential pressure parameters corresponding to the n operating moments included in the first time period are obtained, wherein the i-th maximum differential pressure parameter is used to indicate the maximum voltage difference corresponding to the cell included in the battery at the i-th operating moment, and n is a positive integer. Then, the maximum differential pressure parameter prediction sequence corresponding to the battery in the second time period can be determined according to the n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum differential pressure parameters, wherein the second time period includes q operating moments, the first operating moment among the q operating moments is an operating moment after the n-th operating moment, and q is a positive integer. In other words, the second time period and the first time period are continuous, and since the situation of the battery in the first time period can reflect the possible situation of the battery in the next time domain, the situation of the second time period can be predicted based on the situation of the first time period, that is, the obtained maximum differential pressure parameter prediction sequence can reflect the theoretical change of the battery in the second time period. Next, for the operation process of the vehicle in the second time period, the actual sequence of the maximum pressure difference parameters corresponding to the battery in the second time period is obtained, that is, the actual sequence of the maximum pressure difference parameters can refer to the actual situation corresponding to the battery in the actual operation process of the vehicle, and finally the battery can be tested according to the maximum pressure difference parameter prediction sequence and the actual sequence of the maximum pressure difference parameters. Based on this, the theoretical changes in the second time period can be predicted according to the situation in the first time period, and then the battery can be tested in combination with the actual situation of the battery in the second time period, which can complete the battery detection more efficiently and accurately, so as to find abnormalities in time and avoid affecting the operation of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A flow chart of a vehicle battery detection method provided in an embodiment of the present application;

[0020] Figure 2 A schematic diagram of a model training framework of a battery pressure difference prediction model provided in an embodiment of the present application;

[0021] Figure 3 A schematic diagram of a model training process provided in an embodiment of the present application;

[0022] Figure 4A schematic diagram of a vehicle battery detection framework provided in an embodiment of the present application;

[0023] Figure 5 A structural diagram of a vehicle battery detection device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] The vehicle battery detection method provided in the embodiment of the present application can be implemented by a computer device, which can be a terminal device or a server, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. Terminal devices include but are not limited to mobile phones, computers, intelligent voice interaction devices, smart home appliances, vehicle-mounted terminals, etc. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and this application does not impose any restrictions on this.

[0026] The specific examples are as follows:

[0027] Figure 1 This is a flow chart of a vehicle battery detection method provided in an embodiment of the present application, which is described by taking a server as the aforementioned computer device as an example. The method includes S101-S104:

[0028] S101: for the operation process of the vehicle in the first time period, obtain n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum pressure difference parameters corresponding to n operating moments of the battery of the vehicle included in the first time period.

[0029] For the operation process of the vehicle in the first time period, wherein the first time period may include n operating moments, the n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum pressure difference parameters corresponding to the n operating moments included in the first time period may be obtained, wherein the i-th maximum pressure difference parameter is used to indicate the maximum voltage difference corresponding to the cell included in the battery at the i-th operating moment, and n is a positive integer. In practical applications, the vehicle may be, for example, a new energy vehicle, and the battery may be, for example, a low-voltage lithium battery.

[0030] The i-th state of charge parameter can be used to represent the remaining power (State of Charge, SOC) of the battery at the i-th operating moment. Accordingly, the n state of charge parameters can be recorded as a SOC sequence [SOC1, SOC2, ..., SOC n ]. The i-th ambient temperature parameter can be used to represent the working ambient temperature of the battery at the i-th operating moment. Accordingly, the n ambient temperature parameters can be recorded as an ambient temperature sequence [T1, T2, ..., T n ]. The i-th current parameter can be used to represent the charge and discharge current of the battery at the i-th operating moment. Correspondingly, the n current parameters can be recorded as a charge and discharge current sequence [I1, I2, ..., I n ].

[0031] For the maximum pressure difference parameter, the i-th maximum pressure difference parameter is used to indicate the maximum voltage difference corresponding to the battery cells included in the battery at the i-th operating moment. In practical applications, the maximum pressure difference parameter can be used to reflect the voltage difference or capacity difference between the battery cells of the battery, thereby reflecting whether the battery cells are balanced, etc. In practical applications, the battery may include multiple battery cells, and the voltage of each battery cell may be collected to determine the maximum pressure difference parameter. In specific implementation, if the battery includes w battery cells, w is an integer greater than 1, for each of the w battery cells, the voltage corresponding to the battery cell at n operating moments may be collected. Accordingly, the i-th maximum pressure difference parameter may be determined in the following manner: the i-th maximum pressure difference parameter may be determined according to the voltages corresponding to the w battery cells at the i-th operating moment. In practical applications, the maximum pressure difference between the voltages corresponding to the w battery cells at the i-th operating moment may be determined as the i-th maximum pressure difference parameter. It can be understood that in this way, the maximum pressure difference parameters corresponding to the n operating moments may be determined. Accordingly, the n maximum pressure difference parameters may be recorded as the maximum pressure difference sequence [ΔU1, ΔU2, ..., ΔU n ].

[0032] S102: Determine a maximum pressure difference parameter prediction sequence corresponding to the battery in a second time period according to n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum pressure difference parameters.

[0033] Among them, the second time period includes q operating moments, the first operating moment among the q operating moments is an operating moment after the nth operating moment, q is a positive integer, that is, the second time period and the first time period are continuous. Since the condition of the battery in the first time period can reflect the possible condition of the battery in the next time domain, the condition of the second time period can be predicted based on the condition of the first time period. Specifically, the maximum pressure difference parameter prediction sequence corresponding to the battery in the second time period can be determined based on n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum pressure difference parameters. Correspondingly, the obtained maximum pressure difference parameter prediction sequence can reflect the theoretical changes of the battery in the second time period. In practical applications, in order to improve detection accuracy, q can be set to be less than or equal to n.

[0034] It should be noted that the present application does not impose any limitation on how to determine the maximum pressure difference parameter prediction sequence. For ease of understanding, the present application provides the following method as an example:

[0035] In practical applications, in order to improve the detection efficiency, the maximum pressure difference parameter corresponding to the battery in the second time period can be predicted by a pre-trained battery pressure difference prediction model according to n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum pressure difference parameters, to obtain a maximum pressure difference parameter prediction sequence. Among them, the battery pressure difference prediction model can be determined based on machine learning. In this way, the battery pressure difference prediction model can be used to predict any continuous first time period and second time period, which is conducive to improving the detection efficiency.

[0036] Among them, the battery voltage difference prediction model is determined by the following method:

[0037] First, a training sample may be obtained. The training sample may include n state of charge sample parameters, n ambient temperature sample parameters, n current sample parameters, and n maximum differential pressure sample parameters corresponding to the battery in a first sample period including n sample moments, and the sample label of the training sample may be used to identify a maximum differential pressure parameter sample sequence of the battery in a second sample period, and the second sample period may include q sample moments, and the first sample moment among the q sample moments is a sample moment after the nth sample moment, that is, the second sample period and the first sample period are continuous.

[0038] Next, the maximum pressure difference parameter of the battery in the second sample period can be predicted through the initial network model according to the n state of charge sample parameters, n ambient temperature sample parameters, n current sample parameters and n maximum pressure difference sample parameters to obtain a maximum pressure difference parameter pending sequence.

[0039] Then, a training loss function can be constructed based on the maximum pressure difference parameter pending sequence and the maximum pressure difference parameter sample sequence. Finally, the initial network model can be trained based on the training loss function until the initial network model converges, indicating that the initial network model at this time can have good prediction accuracy, so the model training can be ended, and the battery pressure difference prediction model can be obtained accordingly. Based on this, through the model training method, the obtained battery pressure difference prediction model can learn the correlation relationship between the input variables and the output variables (such as a nonlinear mapping relationship), so that it can be used directly in the future to improve the detection efficiency. In practical applications, the initial network model can be a neural network model, and the specific type is not limited in this application. For example, it can be a feedforward neural network deep learning model.

[0040] For better understanding, the present application embodiment also provides a method for obtaining training samples as an example:

[0041] In practical applications, the state of charge parameter sequence, ambient temperature parameter sequence, current parameter sequence and voltage parameter sequence corresponding to the battery in the laboratory simulation environment and the actual vehicle environment corresponding to the battery in the vehicle can be collected to build a battery performance parameter database corresponding to the battery. Based on this, the battery performance parameter database refers to both laboratory data and actual vehicle data, enriching the number of big data training samples and sample application scenarios, which is conducive to improving the effect of model training and obtaining a more generalized battery pressure difference prediction model. In practical applications, the collected voltage parameter sequence can be used to determine the n maximum pressure difference sample parameters and sample labels corresponding to the aforementioned training samples. The implementation method for determining the maximum pressure difference refers to the aforementioned description of the embodiment for determining n maximum pressure difference parameters, which will not be repeated here. Finally, the training samples can be constructed based on the battery performance parameter database.

[0042] For easier understanding, see Figure 2 As shown, Figure 2 A schematic diagram of a model training framework of a battery voltage difference prediction model is shown. For n state of charge sample parameters, n ambient temperature sample parameters, n current sample parameters and n maximum voltage difference sample parameters included in the training samples, an initial network model can be output. The input [SOC1, SOC2, ..., SOC n ], [T1, T2, ..., T n ], [I1, I2, ..., I n ] and [ΔU1, ΔU2,…, ΔU n ] is processed, and after the prediction is completed, the maximum pressure difference parameter sequence to be determined is output, that is, Figure 2 The [ΔU pre n+1 , ΔUpre n+2 , ..., ΔU pre n+q ] After completing the training, the aforementioned battery pressure difference prediction model can be obtained for subsequent use.

[0043] For the model training process, please refer to Figure 3 As shown, Figure 3 A flow chart of model training is shown. First, for the aforementioned initial network model, weights and thresholds can be initialized first. The weights and thresholds can refer to the model parameters of the initial network model. Then, the training samples can be input into the initial network model based on the sample input method. The input training samples are processed based on each layer in the initial network model, and the output of each layer and the error of the output layer are calculated to construct the training loss function. The local gradient can also be calculated to optimize the model training process to avoid problems such as overfitting or underfitting in the model training. Finally, the weights of each layer can be corrected based on the training loss function to adjust the model parameters of the initial network model and achieve the purpose of model training. Based on this, after completing a round of training, it can be judged whether the training is completed, such as whether it has converged. If it has converged, it can be determined that the training is completed and it can be ended. The aforementioned battery voltage difference prediction model can be obtained accordingly. On the contrary, if it has not converged, a new training can be started and the next round of training can be carried out until it converges.

[0044] S103: With respect to the operation process of the vehicle in the second time period, an actual sequence of maximum pressure difference parameters corresponding to the battery in the second time period is obtained.

[0045] Next, for the operation process of the vehicle in the second time period, the actual sequence of the maximum pressure difference parameters corresponding to the battery in the second time period can be obtained. The actual sequence of the maximum pressure difference parameters can refer to the actual situation corresponding to the battery during the actual operation of the vehicle. It should be noted that the method for obtaining the actual sequence of the maximum pressure difference parameters is similar to the method for determining the n maximum pressure difference parameters corresponding to the first time period. For details, please refer to the description of the aforementioned embodiment, which will not be repeated here.

[0046] S104: Detect the battery according to the maximum pressure difference parameter prediction sequence and the maximum pressure difference parameter actual sequence.

[0047] Finally, the battery can be tested based on the maximum pressure difference parameter prediction sequence and the maximum pressure difference parameter actual sequence. Based on this, the theoretical changes in the second period can be predicted based on the situation in the first period, and then the battery can be tested based on the actual situation of the battery in the second period. This can complete the battery test more efficiently and accurately, so as to detect abnormalities in time and avoid affecting the operation of the vehicle.

[0048] It can be understood that the second period includes q operating moments, and accordingly, the aforementioned maximum pressure difference parameter prediction sequence includes q maximum pressure difference parameter prediction values ​​corresponding to the q operating moments, and the aforementioned maximum pressure difference parameter actual sequence includes q maximum pressure difference parameter actual values ​​corresponding to the q operating moments. Correspondingly, in a possible implementation, the battery can be detected based on the q maximum pressure difference parameter actual values ​​and the q maximum pressure difference parameter prediction values. In specific implementation, the deviation result of the maximum pressure difference parameter actual sequence can be determined first according to the q maximum pressure difference parameter actual values ​​and the q maximum pressure difference parameter prediction values, and the deviation result can be used to indicate the deviation of the actual value compared to the predicted value. If the deviation result indicates that the maximum pressure difference parameter actual sequence is abnormal, it indicates that during the actual operation of the vehicle, the maximum pressure difference is significantly different from the predicted maximum pressure difference, for example, the inconsistency of the battery cell may be aggravated due to battery failure or battery aging, so it can be determined that there is inconsistency between the w battery cells included in the battery, resulting in differences in the voltage and capacity of the w battery cells, where w is an integer greater than 1. Based on this, it is determined that there is a difference in the voltage and capacity of the battery cell, so that the car owner can be prompted to repair and inspect the battery in a timely manner.

[0049] In a possible implementation, in order to improve the detection accuracy, the root mean square error corresponding to the actual sequence of the maximum pressure difference parameter can be determined according to the q actual values ​​of the maximum pressure difference parameters and the q predicted values ​​of the maximum pressure difference parameters, and then the deviation percentage corresponding to the actual sequence of the maximum pressure difference parameter can be determined according to the root mean square error and the q predicted values ​​of the maximum pressure difference parameters, and finally, the deviation percentage can be determined as the deviation result. Based on this, the root mean square error and the deviation percentage can be combined to more accurately evaluate the deviation in the actual operation process, which is conducive to improving the detection accuracy.

[0050] In practical applications, the maximum pressure difference parameter prediction sequence can be recorded as ΔU pre =[ΔU pre n+1 , ΔU pre n+2 , ..., ΔU pre n+q ], the actual sequence of the maximum pressure difference parameter can be recorded as ΔU act =[ΔU act n+1 , ΔU act n+2 , ..., ΔU act n+q ], accordingly, the root mean square error can be determined by the following formula:

[0051]

[0052] In the above formula, RMSE(t) may represent a root mean square error, j is greater than or equal to 1 and less than or equal to q, and may represent the jth running moment among q running moments.

[0053] Accordingly, the deviation percentage can be determined by the following formula:

[0054]

[0055] In the above formula, D(t) can be expressed as a percentage of deviation.

[0056] In practical applications, the relevant performance parameters of the battery during the actual operation process (such as the aforementioned n state of charge parameters, n ambient temperature parameters, n current parameters, and the voltages of w cells used to determine the maximum pressure difference parameters, etc.) can be collected by the battery sensor in the vehicle. The collection error of the battery sensor may cause the aforementioned q maximum pressure difference parameters to be abnormal compared to the q maximum pressure difference parameters. The actual value of the predicted value, therefore, in another possible implementation, the battery sensor corresponding to the battery can be detected based on the deviation result. Among them, the battery sensor can be used to collect the voltage corresponding to the cell included in the battery at q operating moments, and the voltage corresponding to the cell at q operating moments is used to determine the actual value of q maximum pressure difference parameters. Taking the aforementioned root mean square error and deviation percentage as an example, the larger the value of the root mean square error and deviation percentage, the larger the collection error of the battery sensor can be considered. In practical applications, a deviation percentage threshold (for example, 10%) can be set. When the deviation percentage is greater than 10%, it can be identified as an abnormal item, and the current deviation result is determined to indicate that the corresponding maximum pressure difference parameter actual sequence is abnormal.

[0057] In practical applications, in order to improve the detection accuracy, the deviation percentage can also be continuously calculated at a fixed time frequency, and the abnormal situation of the battery sensor can be detected using multiple continuous deviation results to improve the detection accuracy. In a possible implementation, the prediction period can be continuously calculated. In the specific implementation, the prediction period can include k consecutive second periods, k is an integer greater than 1. Correspondingly, when the battery sensor corresponding to the battery is detected based on the deviation result, the deviation results corresponding to the k consecutive second periods can be first determined to obtain k deviation results. Then, if the proportion of the deviation results indicating the abnormality of the actual sequence of the maximum pressure difference parameter in the k deviation results is greater than the first threshold, a first-level alarm information indicating that the battery sensor is abnormal can be generated. If the proportion of the deviation results indicating the abnormality of the actual sequence of the maximum pressure difference parameter in the k deviation results is greater than the second threshold, a second-level alarm information indicating that the battery sensor is abnormal can be generated, wherein the second threshold is greater than the first threshold. If the proportion of the deviation results indicating the abnormality of the actual sequence of the maximum pressure difference parameter in the k deviation results is greater than the third threshold, a third-level alarm information indicating that the battery sensor is abnormal can be generated, wherein the third threshold is greater than the second threshold. For example, the first threshold value may be 20%, the second threshold value may be 40%, and the third threshold value may be 60%. Based on this, the deviation results within consecutive k second time periods can be continuously calculated, and the acquisition errors of different battery sensors can be determined based on the proportion of the number of times identified as abnormal, that is, the cumulative failure rate can be used as the basis for fault assessment, avoiding false alarms, missed alarms, and excessive alarms, thereby improving the user experience. Correspondingly, different levels of alarm information can also be generated so that the owner can be prompted to perform subsequent corresponding processing according to different situations. For example, the first-level alarm information can be used to remind the owner to pay attention to the status of the low-voltage lithium battery, the second-level alarm information can be used to remind the owner to go to the car shop in time to maintain the status of the low-voltage lithium battery, and the third-level alarm information can be used to remind the owner to replace the low-voltage lithium battery immediately and issue an alarm sound prompt.

[0058] In practical applications, the vehicle battery detection method provided by the present application can be executed by a cloud server. Accordingly, in order to remind the owner in time, an alarm message can also be sent to the vehicle when it is determined that an alarm message is generated to remind the owner. In specific implementation, if it is determined that an alarm message is generated, the cloud server can send an alarm message to the vehicle, wherein the alarm message can include one of the first-level alarm message, the second-level alarm message and the third-level alarm message. The vehicle is interconnected with the cloud server. Accordingly, the vehicle can be used to display the alarm message through the vehicle display panel so that the owner can understand the desired alarm situation in time to choose to perform corresponding processing.

[0059] It should be noted that this application does not impose any restrictions on the way in which the vehicle and the cloud server are interconnected. For example, the vehicle and the cloud server can be interconnected based on V2I (Vehicle-to-Infrastructure) communication. Based on this, the vehicle can feed back the performance parameters corresponding to each operating moment collected by the battery sensor to the cloud server through V2I communication, so that the cloud server can make predictions and abnormality detection, etc. Finally, when the alarm information corresponding to the abnormality is generated, the cloud server can feed back the alarm information to the vehicle through V2I communication (specifically, it can be the vehicle terminal or the user terminal corresponding to the vehicle). Based on this, a reasonable human-computer interaction solution can be used to remind the owner to handle it in time, so as to perform corresponding maintenance on the low-voltage lithium battery, etc., which is conducive to improving the comprehensive performance and service life of the low-voltage lithium battery.

[0060] It can be seen from the above technical solution that for the operation process of the vehicle in the first time period, the n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum differential pressure parameters corresponding to the n operating moments included in the first time period are obtained, wherein the i-th maximum differential pressure parameter is used to indicate the maximum voltage difference corresponding to the cell included in the battery at the i-th operating moment, and n is a positive integer. Then, the maximum differential pressure parameter prediction sequence corresponding to the battery in the second time period can be determined according to the n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum differential pressure parameters, wherein the second time period includes q operating moments, the first operating moment among the q operating moments is an operating moment after the n-th operating moment, and q is a positive integer. In other words, the second time period and the first time period are continuous, and since the situation of the battery in the first time period can reflect the possible situation of the battery in the next time domain, the situation of the second time period can be predicted based on the situation of the first time period, that is, the obtained maximum differential pressure parameter prediction sequence can reflect the theoretical change of the battery in the second time period. Next, for the operation process of the vehicle in the second time period, the actual sequence of the maximum pressure difference parameters corresponding to the battery in the second time period is obtained, that is, the actual sequence of the maximum pressure difference parameters can refer to the actual situation corresponding to the battery in the actual operation process of the vehicle, and finally the battery can be tested according to the maximum pressure difference parameter prediction sequence and the actual sequence of the maximum pressure difference parameters. Based on this, the theoretical changes in the second time period can be predicted according to the situation in the first time period, and then the battery can be tested in combination with the actual situation of the battery in the second time period, which can complete the battery detection more efficiently and accurately, so as to find abnormalities in time and avoid affecting the operation of the vehicle.

[0061] For better understanding, the present application embodiment provides a schematic diagram of a vehicle battery detection framework, which can be seen in Figure 4As shown, first, for low-voltage lithium batteries, the performance parameters of the battery in the laboratory simulation environment and the performance parameters of the battery in the actual vehicle environment can be collected, so as to construct a battery performance parameter database under different SOCs, different ambient temperatures, different charge and discharge currents and different maximum pressure differences, and then a training sample can be constructed based on the battery performance parameter database to train the initial network model and obtain a battery pressure difference prediction model. In this way, in the subsequent stage, the relevant performance parameters of the vehicle in the first period of actual operation can be collected, such as the collected performance parameters are fed back to the intelligent vehicle terminal through the vehicle's controller area network bus (CAN, Controller Area Network), and then fed back to the cloud server based on V2I communication, so that the cloud server calls the battery pressure difference prediction model to predict the maximum pressure difference parameters of the vehicle in the second period, and obtains the maximum pressure difference parameter prediction sequence, so as to determine the deviation results in the second period. In this way, after obtaining the deviation results of k consecutive second periods, the corresponding alarm level can be determined based on the fault diagnosis model and the proportion of abnormal items identified in the k consecutive deviation results, and the corresponding alarm information can be generated. If it is determined that an alarm message is generated, the corresponding alarm message can be fed back to the intelligent vehicle terminal through V2I communication to prompt the car owner to handle it in time.

[0062] It can be understood that it basically corresponds to the method embodiment, so the relevant parts can refer to the partial description of the method embodiment.

[0063] Figure 5 This is a structural diagram of a vehicle battery detection device provided in an embodiment of the present application, wherein the device includes an acquisition unit 501, a determination unit 502, and a detection unit 503:

[0064] The acquisition unit 501 is used to acquire, for the operation process of the vehicle in the first time period, n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum pressure difference parameters corresponding to the n operating moments included in the first time period of the battery of the vehicle; the i-th maximum pressure difference parameter is used to represent the maximum voltage difference corresponding to the battery cell included in the battery at the i-th operating moment, and n is a positive integer;

[0065] The determining unit 502 is used to determine a maximum pressure difference parameter prediction sequence corresponding to the battery in a second time period according to the n state of charge parameters, the n ambient temperature parameters, the n current parameters and the n maximum pressure difference parameters; the second time period includes q operating moments, the first operating moment of the q operating moments is an operating moment after the nth operating moment, and q is a positive integer;

[0066] The acquisition unit 501 is further configured to acquire an actual sequence of maximum pressure difference parameters corresponding to the battery in the second time period according to the operation process of the vehicle in the second time period;

[0067] The detection unit 503 is used to detect the battery according to the maximum pressure difference parameter prediction sequence and the maximum pressure difference parameter actual sequence.

[0068] In a possible implementation manner, the determining unit is further configured to:

[0069] According to the n state of charge parameters, the n ambient temperature parameters, the n current parameters and the n maximum pressure difference parameters, predicting the maximum pressure difference parameter corresponding to the battery in the second time period by using a pre-trained battery pressure difference prediction model to obtain the maximum pressure difference parameter prediction sequence;

[0070] The battery pressure difference prediction model is determined in the following manner:

[0071] Acquire training samples; the training samples include n state of charge sample parameters, n ambient temperature sample parameters, n current sample parameters, and n maximum pressure difference sample parameters corresponding to the battery in a first sample period including n sample moments, and the sample labels of the training samples are used to identify a maximum pressure difference parameter sample sequence of the battery in a second sample period, the second sample period includes q sample moments, and the first sample moment among the q sample moments is a sample moment after the nth sample moment;

[0072] According to the n state of charge sample parameters, the n ambient temperature sample parameters, the n current sample parameters and the n maximum pressure difference sample parameters, the maximum pressure difference parameter of the battery in the second sample period is predicted by an initial network model to obtain a maximum pressure difference parameter to-be-determined sequence;

[0073] Constructing a training loss function according to the maximum pressure difference parameter to-be-determined sequence and the maximum pressure difference parameter sample sequence;

[0074] The initial network model is trained based on the training loss function until the initial network model converges to obtain the battery voltage difference prediction model.

[0075] In a possible implementation manner, the determining unit is further configured to:

[0076] Collect the state of charge parameter sequence, ambient temperature parameter sequence, current parameter sequence and voltage parameter sequence of the battery in the laboratory simulation environment and the actual vehicle environment corresponding to the battery in the vehicle, and build a battery performance parameter database corresponding to the battery; the voltage parameter sequence is used to determine the n maximum pressure difference sample parameters and the sample label corresponding to the training sample;

[0077] The training samples are constructed based on the battery performance parameter database.

[0078] In a possible implementation, the battery includes w cells, where w is an integer greater than 1, and the device further includes a collection unit:

[0079] The collecting unit is used to collect the voltage corresponding to each of the w battery cells at the n operating moments;

[0080] The i-th maximum pressure difference parameter is determined by:

[0081] The i-th maximum voltage difference parameter is determined according to the voltages respectively corresponding to the w battery cells at the i-th operating moment.

[0082] In a possible implementation, the maximum pressure difference parameter prediction sequence includes q maximum pressure difference parameter prediction values ​​corresponding to the q operating moments, the maximum pressure difference parameter actual sequence includes q maximum pressure difference parameter actual values ​​corresponding to the q operating moments, and the detection unit is further used to:

[0083] Determine a deviation result of the actual sequence of the maximum pressure difference parameters according to the q actual values ​​of the maximum pressure difference parameters and the q predicted values ​​of the maximum pressure difference parameters;

[0084] If the deviation result indicates that the actual sequence of the maximum voltage difference parameter is abnormal, it is determined that there is inconsistency between the w battery cells included in the battery, resulting in differences in voltage and capacity of the w battery cells; w is an integer greater than 1.

[0085] In a possible implementation, the detection unit is further used for:

[0086] Determine a root mean square error corresponding to the actual sequence of the maximum pressure difference parameters according to the q actual values ​​of the maximum pressure difference parameters and the q predicted values ​​of the maximum pressure difference parameters;

[0087] Determine the deviation percentage corresponding to the actual sequence of the maximum pressure difference parameter according to the root mean square error and the q maximum pressure difference parameter prediction values;

[0088] The deviation percentage is determined as the deviation result.

[0089] In a possible implementation, the detection unit is further used for:

[0090] The battery sensor corresponding to the battery is detected based on the deviation result; the battery sensor is used to collect the voltages of the battery cells included in the battery at the q operating moments, and the voltages of the battery cells at the q operating moments are used to determine the actual values ​​of the q maximum pressure difference parameters.

[0091] In a possible implementation, the time period to be predicted includes k consecutive second time periods, k is an integer greater than 1, and the detection unit is further used for:

[0092] Determine the deviation results corresponding to the k consecutive second time periods respectively, to obtain k deviation results;

[0093] If the proportion of the deviation results indicating that the actual sequence of the maximum pressure difference parameter is abnormal among the k deviation results is greater than a first threshold, generating a first-level alarm information indicating that the battery sensor is abnormal;

[0094] If the proportion of the deviation results indicating that the actual sequence of the maximum pressure difference parameter is abnormal among the k deviation results is greater than a second threshold, a secondary alarm message is generated to indicate that the battery sensor is abnormal; the second threshold is greater than the first threshold;

[0095] If the proportion of the deviation results indicating that the actual sequence of the maximum pressure difference parameter is abnormal among the k deviation results is greater than a third threshold, a third-level alarm message is generated to indicate that the battery sensor is abnormal; the third threshold is greater than the second threshold.

[0096] In a possible implementation, the method is executed by a cloud server, and the device further includes a sending unit:

[0097] The sending unit is used for, if it is determined that an alarm message is to be generated, the cloud server sends the alarm message to the vehicle; the alarm message includes one of the first-level alarm message, the second-level alarm message and the third-level alarm message, the vehicle is interconnected with the cloud server, and the vehicle is used to display the alarm message through a vehicle display panel.

[0098] It can be seen from the above technical solution that for the operation process of the vehicle in the first time period, the n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum differential pressure parameters corresponding to the n operating moments included in the first time period are obtained, wherein the i-th maximum differential pressure parameter is used to indicate the maximum voltage difference corresponding to the cell included in the battery at the i-th operating moment, and n is a positive integer. Then, the maximum differential pressure parameter prediction sequence corresponding to the battery in the second time period can be determined according to the n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum differential pressure parameters, wherein the second time period includes q operating moments, the first operating moment among the q operating moments is an operating moment after the n-th operating moment, and q is a positive integer. In other words, the second time period and the first time period are continuous, and since the situation of the battery in the first time period can reflect the possible situation of the battery in the next time domain, the situation of the second time period can be predicted based on the situation of the first time period, that is, the obtained maximum differential pressure parameter prediction sequence can reflect the theoretical change of the battery in the second time period. Next, for the operation process of the vehicle in the second time period, the actual sequence of the maximum pressure difference parameters corresponding to the battery in the second time period is obtained, that is, the actual sequence of the maximum pressure difference parameters can refer to the actual situation corresponding to the battery in the actual operation process of the vehicle, and finally the battery can be tested according to the maximum pressure difference parameter prediction sequence and the actual sequence of the maximum pressure difference parameters. Based on this, the theoretical changes in the second time period can be predicted according to the situation in the first time period, and then the battery can be tested in combination with the actual situation of the battery in the second time period, which can complete the battery detection more efficiently and accurately, so as to find abnormalities in time and avoid affecting the operation of the vehicle.

[0099] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0100] It should be noted that, in this article, relational terms such as "first" and "second", etc. (if any) are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0101] The above is a detailed introduction to a vehicle battery detection method and device provided by the embodiment of the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application. At the same time, for those skilled in the art, according to the method of the present application, there will be changes in the specific implementation method and application scope.

[0102] In summary, the content of this specification should not be understood as limiting the present application, and any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in this application should be included in the protection scope of this application. Moreover, based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations.

Claims

1. A vehicle battery detection method, characterized in that: The method comprises: For the operation process of the vehicle in the first time period, n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum pressure difference parameters corresponding to the n operating moments included in the first time period of the battery of the vehicle are obtained; the i-th maximum pressure difference parameter is used to represent the maximum voltage difference corresponding to the battery cell included in the battery at the i-th operating moment, and n is a positive integer; Determine, according to the n state of charge parameters, the n ambient temperature parameters, the n current parameters and the n maximum pressure difference parameters, a maximum pressure difference parameter prediction sequence corresponding to the battery in a second time period; the second time period includes q operating moments, a first operating moment among the q operating moments is an operating moment after the nth operating moment, and q is a positive integer; With respect to the operation process of the vehicle in the second time period, obtaining an actual sequence of maximum pressure difference parameters corresponding to the battery in the second time period; The battery is detected according to the maximum pressure difference parameter prediction sequence and the maximum pressure difference parameter actual sequence.

2. The method according to claim 1, characterized in that The step of determining a maximum pressure difference parameter prediction sequence corresponding to the battery in the second time period according to the n state of charge parameters, the n ambient temperature parameters, the n current parameters and the n maximum pressure difference parameters includes: According to the n state of charge parameters, the n ambient temperature parameters, the n current parameters and the n maximum pressure difference parameters, predicting the maximum pressure difference parameter corresponding to the battery in the second time period by using a pre-trained battery pressure difference prediction model to obtain the maximum pressure difference parameter prediction sequence; The battery pressure difference prediction model is determined in the following manner: Acquire training samples; the training samples include n state of charge sample parameters, n ambient temperature sample parameters, n current sample parameters, and n maximum pressure difference sample parameters corresponding to the battery in a first sample period including n sample moments, and the sample labels of the training samples are used to identify a maximum pressure difference parameter sample sequence of the battery in a second sample period, the second sample period includes q sample moments, and the first sample moment among the q sample moments is a sample moment after the nth sample moment; According to the n state of charge sample parameters, the n ambient temperature sample parameters, the n current sample parameters and the n maximum pressure difference sample parameters, the maximum pressure difference parameter of the battery in the second sample period is predicted by an initial network model to obtain a maximum pressure difference parameter to-be-determined sequence; Constructing a training loss function according to the maximum pressure difference parameter to-be-determined sequence and the maximum pressure difference parameter sample sequence; The initial network model is trained based on the training loss function until the initial network model converges to obtain the battery voltage difference prediction model.

3. The method according to claim 2, characterized in that The obtaining of training samples comprises: Collect the state of charge parameter sequence, ambient temperature parameter sequence, current parameter sequence and voltage parameter sequence of the battery in the laboratory simulation environment and the actual vehicle environment corresponding to the battery in the vehicle, and build a battery performance parameter database corresponding to the battery; the voltage parameter sequence is used to determine the n maximum pressure difference sample parameters and the sample label corresponding to the training sample; The training samples are constructed based on the battery performance parameter database.

4. The method according to claim 1, characterized in that: The battery includes w cells, where w is an integer greater than 1, and the method further includes: For each of the w battery cells, collecting voltages corresponding to the battery cells at the n operating moments; The i-th maximum pressure difference parameter is determined by: The i-th maximum voltage difference parameter is determined according to the voltages respectively corresponding to the w battery cells at the i-th operating moment.

5. The method according to claim 1, characterized in that The maximum pressure difference parameter prediction sequence includes q maximum pressure difference parameter prediction values ​​corresponding to the q operating moments, the maximum pressure difference parameter actual sequence includes q maximum pressure difference parameter actual values ​​corresponding to the q operating moments, and the battery is tested according to the maximum pressure difference parameter prediction sequence and the maximum pressure difference parameter actual sequence, including: Determine a deviation result of the actual sequence of the maximum pressure difference parameters according to the q actual values ​​of the maximum pressure difference parameters and the q predicted values ​​of the maximum pressure difference parameters; If the deviation result indicates that the actual sequence of the maximum voltage difference parameter is abnormal, it is determined that there is inconsistency between the w battery cells included in the battery, resulting in differences in voltage and capacity of the w battery cells; w is an integer greater than 1.

6. The method according to claim 5, characterized in that The step of determining the deviation result of the actual sequence of the maximum pressure difference parameters according to the q actual values ​​of the maximum pressure difference parameters and the q predicted values ​​of the maximum pressure difference parameters includes: Determine a root mean square error corresponding to the actual sequence of the maximum pressure difference parameters according to the q actual values ​​of the maximum pressure difference parameters and the q predicted values ​​of the maximum pressure difference parameters; Determine the deviation percentage corresponding to the actual sequence of the maximum pressure difference parameter according to the root mean square error and the q maximum pressure difference parameter prediction values; The deviation percentage is determined as the deviation result.

7. The method according to claim 5, characterized in that The method further comprises: The battery sensor corresponding to the battery is detected based on the deviation result; the battery sensor is used to collect the voltages of the battery cells included in the battery at the q operating moments, and the voltages of the battery cells at the q operating moments are used to determine the actual values ​​of the q maximum pressure difference parameters.

8. The method according to claim 7, characterized in that The time period to be predicted includes k consecutive second time periods, where k is an integer greater than 1, and the detecting the battery sensor corresponding to the battery based on the deviation result includes: Determine the deviation results corresponding to the k consecutive second time periods respectively, to obtain k deviation results; If the proportion of the deviation results indicating that the actual sequence of the maximum pressure difference parameter is abnormal among the k deviation results is greater than a first threshold, generating a first-level alarm information indicating that the battery sensor is abnormal; If the proportion of the deviation results indicating that the actual sequence of the maximum pressure difference parameter is abnormal among the k deviation results is greater than a second threshold, a secondary alarm message is generated to indicate that the battery sensor is abnormal; the second threshold is greater than the first threshold; If the proportion of the deviation results indicating that the actual sequence of the maximum pressure difference parameter is abnormal among the k deviation results is greater than a third threshold, a third-level alarm message is generated to indicate that the battery sensor is abnormal; the third threshold is greater than the second threshold.

9. The method according to claim 8, characterized in that: The method is executed by a cloud server, and the method further includes: If it is determined that an alarm message is generated, the cloud server sends the alarm message to the vehicle; the alarm message includes one of the first-level alarm message, the second-level alarm message and the third-level alarm message, the vehicle is interconnected with the cloud server, and the vehicle is used to display the alarm message through a vehicle display panel.

10. A vehicle battery detection device, characterized in that: The device comprises an acquisition unit, a determination unit and a detection unit: The acquisition unit is used to acquire, for the operation process of the vehicle in the first time period, n state of charge parameters, n ambient temperature parameters, n current parameters and n maximum pressure difference parameters corresponding to the n operating moments included in the first time period of the battery of the vehicle; the i-th maximum pressure difference parameter is used to represent the maximum voltage difference corresponding to the battery cell included in the battery at the i-th operating moment, and n is a positive integer; The determining unit is used to determine a maximum pressure difference parameter prediction sequence corresponding to the battery in a second time period according to the n state of charge parameters, the n ambient temperature parameters, the n current parameters and the n maximum pressure difference parameters; the second time period includes q operating moments, the first operating moment of the q operating moments is an operating moment after the nth operating moment, and q is a positive integer; The acquisition unit is further used to acquire an actual sequence of maximum pressure difference parameters corresponding to the battery in the second time period according to the operation process of the vehicle in the second time period; The detection unit is used to detect the battery according to the maximum pressure difference parameter prediction sequence and the maximum pressure difference parameter actual sequence.

Images