Battery state determination method and device, equipment, medium and product

Abstract

The invention relates to a battery state determination method and device, equipment, a medium and a product. The method at least comprises the following steps: collecting a state parameter of a battery and an environment parameter of the battery; determining state characteristics of the battery based on the state parameters and the environmental parameters; performing time dimension anomaly analysis on the state characteristics through a first model to obtain a first result of the battery; the first result is used for representing whether the battery is abnormal in the time dimension; performing abnormal analysis of the spatial dimension on the state characteristics through a second model to obtain a second result of the battery; the second result is used for representing whether the battery is abnormal in the spatial dimension; and determining a target result for representing the state of the battery based on the first result and the second result. According to the scheme, the determined battery state is more accurate, the robustness is higher, and the use safety of the battery is improved.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a method, device, equipment, medium and product for determining a battery status. Background Art

[0002] With the rapid development of electric vehicle technology, batteries, as core components of electric vehicles, directly affect the performance, safety and reliability of vehicles. As the electric vehicle market continues to expand, consumers' requirements for battery performance and safety are also increasing. However, batteries may experience a variety of abnormalities during use, such as overheating, overcharging, overdischarging, increased internal resistance, etc. These abnormalities not only affect the service life of the battery, but may also cause safety accidents, such as fire and explosion.

[0003] Generally, battery monitoring methods mainly rely on simple threshold detection. For example, fixed thresholds of parameters such as voltage, temperature and current can be set. Once the threshold is exceeded, the system will issue an alarm. However, the solution of determining the battery status by threshold cannot identify the relationship between the parameters, resulting in low accuracy. Summary of the invention

[0004] One of the purposes of the present application is to provide a method, device, equipment, medium and product for determining a battery status. The battery status determined by this solution is more accurate and more robust, thereby improving the safety of battery use.

[0005] In order to achieve the above purpose, the technical solution adopted in this application is as follows: In a first aspect, the present application provides a method for determining a battery state, the method comprising: collecting state parameters of the battery and environmental parameters of the battery; determining state characteristics of the battery based on the state parameters and the environmental parameters; performing an abnormality analysis of the state characteristics in a time dimension through a first model to obtain a first result of the battery; the first result is used to characterize whether the battery is abnormal in the time dimension; performing an abnormality analysis of the state characteristics in a spatial dimension through a second model to obtain a second result of the battery; the second result is used to characterize whether the battery is abnormal in the spatial dimension; based on the first result and the second result, determining a target result for characterizing the state of the battery.

[0006] Based on the above technical means, on the one hand, for data, this solution not only considers the influence of battery status parameters based on battery status, but also considers the influence of environmental parameters on battery status, which improves the accuracy of battery status determination; on the other hand, when determining the target result of battery status, the data is processed by means of a model, which improves the robustness of battery status determination; on the other hand, this solution can realize abnormal analysis in the time dimension through the first model, and realize analysis in the space dimension through the second model, and then combine the results of the two to determine the target result, which further improves the accuracy of the target result. Therefore, the battery status determined by this solution is more accurate and more robust, which improves the safety of battery use.

[0007] In one possible implementation, based on the first result and the second result, a target result for characterizing the state of the battery is determined, including: if the first result and the second result are the same, determining the state of the battery to be the first result; if the first result and the second result are different, determining a target score based at least on the first score and the second score; determining the target result based on the target score; wherein the first score is the score output by the first model; and the second score is the score output by the second model.

[0008] Based on the above technical means, when determining the target result, it is determined based on the results of both. Only when the first result and the second result are the same, the target result is directly obtained. When the first result and the second result are different, the target result is not determined directly based on one result. Secondly, the first result and the second result are merged through a more fine-grained scoring method to determine the final target result, thereby improving the accuracy of the target result.

[0009] In a possible implementation, determining the target score based on at least the first score and the second score includes: determining the target score based on the first score and the second score; determining the target score based on the first score, the second score and the feature score.

[0010] Based on the above technical means, the target score is determined based on the first score and the second score. When the two scores are fused, it has the characteristics of simple implementation and good interpretability. The target score is determined based on the first score, the second score and the feature score. Not only the two scores are fused, but also the feature score is fused, which further improves the accuracy of the target score, the accuracy of the target result and the safety of the battery.

[0011] In one possible implementation, a target score is determined based on the first score, the second score, and the feature score, including: determining a score for each state parameter and a score for each environmental parameter; determining a feature score based on the score for each state parameter, the weight for each state parameter, the score for each environmental parameter, and the weight for each environmental parameter; determining a target score based on the feature score, the weight for the feature score, the first score, the weight for the first score, the second score, and the weight for the second score.

[0012] Based on the above technical means, when determining the target score, the score of each state parameter and the score of each environmental parameter are taken into consideration, which improves the accuracy of the target score. In addition, weights are configured for each state parameter and each environmental parameter. The target score can be adjusted by adjusting the weights, which further improves the accuracy and flexibility of the target score.

[0013] In a possible implementation, the method further includes: if the state of the battery in the target result is abnormal, determining a target abnormality type and a target abnormality level of the battery; and outputting the target abnormality type, the target abnormality level, and warning information.

[0014] Based on the above technical means, the target abnormality type, target abnormality level and warning information can also be output, which improves the richness of the output and the user experience.

[0015] In a possible implementation, outputting warning information includes: when the target abnormality level is a first abnormality level, outputting first warning information by means of visual prompts; when the target abnormality level is a second abnormality level, outputting the first warning information by means of visual prompts, and outputting second warning information by means of auditory prompts; when the target abnormality level is a third abnormality level, outputting the first warning information by means of visual prompts, outputting the second warning information by means of auditory prompts, and outputting the third warning information to the client via a network; wherein the degree of abnormality of the first abnormality level, the second abnormality level, and the third abnormality level increases in sequence.

[0016] Based on the above technical means, different output methods are configured for different abnormality levels. For low abnormality levels, output is only performed visually to reduce the impact of output on other processing. For high abnormality levels, multiple output methods are used to determine the accessibility of output, thereby improving security. In short, this multi-level output method improves the output effect.

[0017] In a possible implementation, determining the state characteristics of the battery based on the state parameters and the environmental parameters includes: separately determining the rate of change of each state parameter and the rate of change of each environmental parameter; determining the state characteristics of the battery based on the rate of change of each state parameter and the rate of change of each environmental parameter.

[0018] Based on the above technical means, when determining the state characteristics of the battery, the characteristics are not determined directly based on the parameters, but the change rate of each state parameter and the change rate of each environmental parameter are determined respectively, and the state characteristics of the battery are determined based on the change rate of each state parameter and the change rate of each environmental parameter. Since the change rate can better express the dynamic performance of the battery, the obtained state characteristics are more consistent with the actual situation, which improves the accuracy of the state characteristics, the accuracy of the target results and the safety of the battery.

[0019] In a possible implementation, before determining the state characteristics of the battery based on the rate of change of each state parameter and the rate of change of each environmental parameter, the method further includes: eliminating outliers in the rate of change of each state parameter based on a first method; the first method includes at least one of a moving average algorithm, an autocorrelation function, and a wavelet transform; eliminating outliers in the rate of change of each environmental parameter based on the moving average algorithm.

[0020] Based on the above technical means, different methods of removing outliers are configured according to the characteristics of different parameters, which effectively improves the accuracy of removing outliers.

[0021] In a possible implementation, when the state parameters include battery temperature, voltage, current, internal resistance and state of charge, and the environmental parameters include ambient temperature, the state parameters of the battery and the environmental parameters of the battery are collected, including: collecting the voltage and current of the battery based on a first frequency; and collecting the battery temperature, internal resistance, state of charge and ambient temperature of the battery based on a second frequency.

[0022] Based on the above technical means, different frequencies are used for data collection for different parameter characteristics. On the basis of ensuring the effectiveness of data collection, it can be applied to the characteristics of various parameters. For example, for voltage and current type parameters, the changes are fast, so the collection frequency should be higher. For temperature type parameters, they generally do not change suddenly, so the collection frequency can be slightly lower, which improves the accuracy of parameter collection, the accuracy of target results and the safety of batteries.

[0023] In a possible implementation, collecting the voltage and current of the battery based on the first frequency includes: determining the operating state of the battery; if the operating state of the battery is a first load state, increasing the first frequency; collecting the voltage and current of the battery based on the increased first frequency; if the operating state of the battery is a second load state, reducing the first frequency, and collecting the voltage and current of the battery based on the reduced first frequency; wherein the load of the first load state is higher than the load of the second load state.

[0024] Based on the above technical means, the collection frequency can be adjusted according to the working status of the battery, which further improves the data collection efficiency, the accuracy of the target results and the safety of the battery.

[0025] In a second aspect, the present application provides a device for determining a battery status, the device comprising: A collection unit, used to collect the state parameters of the battery and the environmental parameters of the battery; A first determining unit, configured to determine a state characteristic of the battery based on the state parameter and the environmental parameter; A first analysis unit is used to perform an abnormality analysis on the state feature in a time dimension through a first model to obtain a first result of the battery; the first result is used to characterize whether the battery is abnormal in the time dimension; A second analysis unit is used to perform an abnormality analysis of the state feature in a spatial dimension through a second model to obtain a second result of the battery; the second result is used to characterize whether the battery is abnormal in the spatial dimension; The second determining unit is configured to determine a target result for characterizing a state of the battery based on the first result and the second result.

[0026] In a third aspect, the present application further provides an electronic device, the electronic device comprising a processor and a memory, the memory storing a computer program or instructions, and the computer program or instructions, when executed by the processor, implements the method provided in the first aspect above.

[0027] In a fourth aspect, the present application further provides a storage medium having a computer program or instruction stored thereon, and the computer program or instruction, when executed by a processor, implements the method provided in the first aspect above.

[0028] In a fifth aspect, the present application further provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the method provided in the first aspect is implemented.

[0029] It should be noted that the technical effects of the second to fifth aspects can refer to the detailed description of the first aspect above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A schematic diagram of a first optional flow chart of a method for determining a battery status provided in an embodiment of the present application; Figure 2 A second optional flow chart of the method for determining the battery status provided in the embodiment of the present application; Figure 3 A third optional flow chart of the method for determining the battery status provided in the embodiment of the present application; Figure 4A fourth optional flow chart of the method for determining the battery status provided in the embodiment of the present application; Figure 5 A fifth optional flow chart of the method for determining the battery status provided in the embodiment of the present application; Figure 6 A sixth optional flow chart of the method for determining the battery status provided in the embodiment of the present application; Figure 7 A seventh optional flow chart of the method for determining the battery status provided in the embodiment of the present application; Figure 8 An eighth optional flow chart of the method for determining the battery status provided in the embodiment of the present application; Fig. 9 A ninth optional flow chart of the method for determining the battery status provided in the embodiment of the present application; Fig.10 A schematic diagram of an optional structure of an electric vehicle battery abnormality warning device provided in an embodiment of the present application; Fig.11 An optional flowchart of a feature extraction process provided in an embodiment of the present application; Fig.12 An optional flow chart of the model processing process provided in the embodiment of the present application; Fig.13 An optional flowchart of an anomaly detection process provided in an embodiment of the present application; Fig.14 An optional structural diagram of a device for determining a battery status provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the specific technical solution of the application will be further described in detail below in conjunction with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0032] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0033] In the following description, the terms "first\second\third" are used only as examples to distinguish different objects, and do not represent a specific order for the objects, nor do they have a limitation on the order of precedence. It is understandable that "first\second\third" can be interchanged with a specific order or order of precedence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0035] The embodiments of the present application provide a method, apparatus, device, medium and product for determining the battery status. The method for determining the battery status is performed by a device for determining the battery status, and the device for determining the battery status can be deployed in an electronic device. Below, various embodiments of the method, apparatus, device, medium and product for determining the battery status provided in the embodiments of the present application are described.

[0036] In a first aspect, an embodiment of the present application provides a method for determining a battery status. The method is described below by taking an electronic device as an example.

[0037] refer to Figure 1 As shown in the content, the process may include but is not limited to S101 to S105.

[0038] S101: The electronic device collects battery status parameters and battery environment parameters.

[0039] The embodiment of the present application does not limit the type of battery, which can be determined according to actual conditions. For example, the battery here can include but is not limited to: lithium-ion battery, lead-acid battery, lithium polymer battery, lithium iron phosphate battery and ternary lithium battery, etc.

[0040] The state parameter is used to characterize the current state of the battery. The embodiment of the present application does not limit the type of the state parameter, which can be configured according to actual needs. The state parameter here may include but is not limited to at least one of the following: battery temperature, battery voltage, battery current, battery internal resistance, and battery state of charge.

[0041] Environmental parameters are used to characterize the current environmental state of the battery. The present application does not limit the type of environmental parameters, and can be configured according to actual needs. The environmental parameters here may include but are not limited to at least one of the following: ambient temperature and ambient humidity.

[0042] S101 may be implemented as follows: the electronic device collects the state parameters of the battery and the environmental parameters of the battery through a relevant collection device, and may also store the collected state parameters and environmental parameters.

[0043] The state parameters and environmental parameters collected here include a timestamp of the collection time, so that they can be used for subsequent analysis of parameter changes.

[0044] S102: The electronic device determines a state characteristic of the battery based on the state parameter and the environmental parameter.

[0045] The state feature is used to characterize the state of the battery by means of features.

[0046] S102 may be implemented as follows: the electronic device processes the state parameters and the environmental parameters by using a feature extraction algorithm to obtain the state characteristics of the battery.

[0047] S103: The electronic device performs an abnormality analysis on the state characteristics in a time dimension using a first model to obtain a first result of the battery.

[0048] The first result is used to characterize whether the battery is abnormal in the time dimension.

[0049] The first model is used to perform abnormal analysis on the state characteristics in the time dimension to determine whether the battery is abnormal and obtain a first result. The embodiment of the present application does not limit the type of the first model, and it can be configured according to actual needs.

[0050] Exemplarily, the first model may be: a long short-term memory network model (Long-Short Term Memory, LSTM) or a gated recurrent unit model.

[0051] The first model here is a pre-trained model for obtaining a first result according to state characteristics.

[0052] S103 may be implemented as follows: the electronic device inputs the state characteristics into the first model, and performs an abnormality analysis of the state characteristics in a time dimension through the first model to obtain a first result of the battery.

[0053] The first result here may include: whether it is abnormal or not, and may also include: abnormal type and abnormal level, etc.

[0054] S104. The electronic device performs an abnormality analysis of the state characteristics in a spatial dimension using a second model to obtain a second result of the battery.

[0055] The second result is used to characterize whether the battery is abnormal in the spatial dimension.

[0056] The second model is used to perform abnormal analysis on the state characteristics in the spatial dimension to determine whether the battery is abnormal and obtain a second result. The embodiment of the present application does not limit the type of the second model, and it can be configured according to actual needs.

[0057] Exemplarily, the second model may be a random forest or a decision tree, etc.

[0058] The second model here is a pre-trained model for obtaining a second result according to state characteristics.

[0059] S104 may be implemented as follows: the electronic device inputs the state feature into the second model, and performs an abnormality analysis of the state feature in a spatial dimension through the second model to obtain a second result of the battery.

[0060] The second result here may include: whether it is abnormal or not, and may also include: abnormal type and abnormal level, etc.

[0061] S105: The electronic device determines a target result for representing a battery status based on the first result and the second result.

[0062] The target result is used to characterize the state of the battery determined by this embodiment.

[0063] The target result here may include: whether the result is abnormal or not, and may also include: target abnormality type and target abnormality level, etc.

[0064] S105 may be implemented as follows: the electronic device determines a target result for characterizing the state of the battery based on the first result and the second result. If the first result and the second result are the same, the target result is determined to be the same result; if the first result and the second result are different, the target result here may be one of the two or a fusion of the two results.

[0065] In this embodiment, the method includes: collecting state parameters of the battery and environmental parameters of the battery; determining the state characteristics of the battery based on the state parameters and the environmental parameters; performing an abnormality analysis on the state characteristics in the time dimension through a first model to obtain a first result of the battery; the first result is used to characterize whether the battery is abnormal in the time dimension; performing an abnormality analysis on the state characteristics in the space dimension through a second model to obtain a second result of the battery; the second result is used to characterize whether the battery is abnormal in the space dimension; based on the first result and the second result, determining a target result for characterizing the state of the battery.

[0066] Based on the above technical means, on the one hand, for data, this solution not only considers the influence of battery status parameters based on battery status, but also considers the influence of environmental parameters on battery status, which improves the accuracy of battery status determination; on the other hand, when determining the target result of battery status, the data is processed by means of a model, which improves the robustness of battery status determination; on the other hand, this solution can realize abnormal analysis in the time dimension through the first model, and realize analysis in the space dimension through the second model, and then combine the results of the two to determine the target result, which further improves the accuracy of the target result. Therefore, the battery status determined by this solution is more accurate and more robust, which improves the safety of battery use.

[0067] Next, the process of the electronic device determining the target result for representing the state of the battery based on the first result and the second result in S105 is described.

[0068] refer to Figure 2 As shown in the content, the process may include but is not limited to the following S1051 and S1052.

[0069] S1051: If the first result and the second result are the same, the electronic device determines that the battery status is the first result.

[0070] The battery status may also be considered as the second result, that is, the target result is the first result or the second result.

[0071] S1051 may be implemented as follows: the electronic device compares whether the first result and the second result are the same; if the first result and the second result are the same, determining that the battery status is the first result.

[0072] S1052: If the first result and the second result are different, the electronic device determines a target score based at least on the first score and the second score; and determines a target result based on the target score.

[0073] The first score is the score output by the first model; the second score is the score output by the second model.

[0074] In a possible implementation, the first score may be the abnormal probability output by the first model, and the second score may be the abnormal voting ratio output by the second model.

[0075] In another possible implementation, the first score may be a score converted from the abnormal probability output by the first model, and the second score may be a score converted from the abnormal voting ratio output by the second model.

[0076] The conversion method here may be normalization to convert the two scores to the same score range.

[0077] S1052 may be implemented as follows: if the first result and the second result are different, the electronic device determines a target score based on the first score and the second score; or may also determine the target score in combination with other parameters; and then determines a target result based on the target score.

[0078] Based on the above technical means, when determining the target result, it is determined based on the results of both. Only when the first result and the second result are the same, the target result is directly obtained. When the first result and the second result are different, the target result is not determined directly based on one result. Secondly, the first result and the second result are merged through a more fine-grained scoring method to determine the final target result, thereby improving the accuracy of the target result.

[0079] Next, the process of the electronic device determining the target score based on at least the first score and the second score in S1052 is described.

[0080] refer to Figure 3 As shown in the content, the process may include but is not limited to the following S301 and S302.

[0081] S301: The electronic device determines a target score based on a first score and a second score.

[0082] In a possible implementation, S301 may be implemented as: the electronic device determines an average of the first score and the second score as the target score.

[0083] In another possible implementation, S301 may be implemented as follows: the electronic device may further configure different weights for the first score and the second score, and determine the target score by taking the weighted average of the first score and the second score. The embodiment of the present application does not limit the configuration values ​​of the weight of the first score and the weight of the second score, and may be configured according to actual needs or experience.

[0084] S302: The electronic device determines a target score based on the first score, the second score, and the feature score.

[0085] Feature score refers to the score obtained based on various environmental parameters and state parameters.

[0086] In a possible implementation, a feature score is obtained based on the state feature.

[0087] In another possible implementation, the feature score is determined based on the environmental parameter and the state parameter.

[0088] S302 may be implemented as follows: the electronic device first obtains a feature score based on the state feature; or determines the feature score based on the environment parameter and the state parameter, and then determines the target score based on the first score, the second score and the feature score.

[0089] Based on the above technical means, the target score is determined based on the first score and the second score. When the two scores are fused, it has the characteristics of simple implementation and good interpretability. The target score is determined based on the first score, the second score and the feature score. Not only the two scores are fused, but also the feature score is fused, which further improves the accuracy of the target score, the accuracy of the target result and the safety of the battery.

[0090] Next, the process of the electronic device determining the target score based on the first score, the second score and the feature score in S302 is described.

[0091] refer to Figure 4 As shown in the content, the process may include but is not limited to the following S401 to S403.

[0092] S401. The electronic device determines a score for each state parameter and a score for each environmental parameter.

[0093] The manner of determining the scores of the state parameters may be the same as or different from the manner of determining the scores of the environmental parameters.

[0094] For example, the score of each state parameter and the score of each environment parameter may be determined based on formula (1).

[0095] Formula (1); In formula (1), Characterize the eigenvalues ​​of each parameter x, is the standard value of the parameter; the normal range of parameter x is [ ].

[0096] S402: The electronic device determines a feature score based on the score of each state parameter, the weight of each state parameter, the score of each environmental parameter, and the weight of each environmental parameter.

[0097] The embodiment of the present application does not limit the value of the weight of each state parameter and the weight of each environmental parameter, and can be configured according to actual needs. In a possible implementation, the weight of the state parameter can be greater than the weight of the environmental parameter. For the state parameter, the weight of the internal resistance can be configured as the highest among the state parameter weights. For the environmental parameter, the weight of the ambient temperature can be configured as the highest among the environmental weights.

[0098] S402 may be implemented as follows: the electronic device determines a feature score by taking a weighted average of the score of each state parameter and the score of each environmental parameter.

[0099] S403: The electronic device determines a target score based on the feature score, the weight of the feature score, the first score, the weight of the first score, the second score, and the weight of the second score.

[0100] The electronic device may determine a weighted average of the feature score, the first score, and the second score as the target score.

[0101] The embodiment of the present application does not limit the values ​​of the feature score weight, the first score weight, and the second score weight, and can be configured according to actual needs. For example, the weight value can be configured according to the accuracy of each score in practice.

[0102] S403 may be implemented as follows: the electronic device determines the target score by taking a weighted average based on the feature score, the weight of the feature score, the first score, the weight of the first score, the second score, and the weight of the second score.

[0103] Based on the above technical means, when determining the target score, the score of each state parameter and the score of each environmental parameter are taken into consideration, which improves the accuracy of the target score. In addition, weights are configured for each state parameter and each environmental parameter. The target score can be adjusted by adjusting the weights, which further improves the accuracy and flexibility of the target score.

[0104] The method for determining the battery status provided in the embodiment of the present application may also include but is not limited to the output of the target result.

[0105] refer to Figure 5 As shown in the content, the process may include but is not limited to the following S106 and S107.

[0106] S106: If the battery status in the target result is abnormal, the electronic device determines a target abnormality type and a target abnormality level of the battery.

[0107] The target abnormality type may include, but is not limited to, one or more of the following: current parameter abnormality, voltage parameter abnormality, internal resistance parameter abnormality, etc.

[0108] The abnormality level is used to characterize the abnormality degree of the battery status. The embodiment of the present application does not limit the division method of the abnormality level and the number of division levels, etc., which can be configured according to actual needs.

[0109] The abnormality level can be divided according to the target score. For example, in the score representing that the battery state is abnormal, the abnormal score can be divided into multiple abnormality levels.

[0110] S106 can be implemented as follows: the electronic device first determines whether the battery status in the target result is abnormal or normal. If the battery status in the target result is abnormal, the electronic device determines the target abnormality type and target abnormality level of the battery; if the battery status in the target result is normal, the normal target result is output.

[0111] S107. The electronic device outputs the target abnormality type, target abnormality level and warning information.

[0112] The warning information is used for abnormal reminder. The embodiment of the present application does not limit the output type and content of the warning information, and can be configured according to actual needs.

[0113] Here, the target abnormality type, target abnormality level, and output type of warning information may be the same or different.

[0114] S107 can be implemented as follows: the electronic device outputs the target result, and outputs the target abnormality type, the target abnormality level and the warning information.

[0115] Based on the above technical means, the target abnormality type, target abnormality level and warning information can also be output, which improves the richness of the output and the user experience.

[0116] Next, the process of the electronic device outputting warning information in S107 is described.

[0117] This process may include but is not limited to the following cases 1 to 3.

[0118] Case 1: When the target abnormality level is the first abnormality level, the first warning information is output through a visual prompt.

[0119] Visual prompts include: warning lights, warning information displayed on the display screen, etc.

[0120] For example, the first warning information may include: "Please check the battery status" or "Please stop the car for inspection" and the like.

[0121] Case 2: When the target abnormality level is the secondary abnormality level, the first warning information is output through a visual prompt, and the second warning information is output through an auditory prompt.

[0122] Auditory prompting methods may include: audio output of warning information, output of warning sounds, such as "beep, beep", etc.

[0123] For example, the second warning information may include: "Please check the battery status immediately" or "Please stop the car and check immediately", etc.

[0124] Case 3: When the target abnormality level is level three, the first warning information is output through visual prompts, the second warning information is output through auditory prompts, and the third warning information is output to the client through the network.

[0125] Network methods may include: remote transmission via vehicle network, etc.

[0126] For example, the third warning information may include: "The battery is in a dangerous state, please stay away from it as soon as possible and contact the manufacturer" and the like.

[0127] Among them, the abnormality degrees of the first abnormality level, the second abnormality level, and the third abnormality level increase in sequence.

[0128] Based on the above technical means, different output methods are configured for different abnormality levels. For low abnormality levels, output is only performed visually to reduce the impact of output on other processing. For high abnormality levels, multiple output methods are used to determine the accessibility of output, thereby improving security. In short, this multi-level output method improves the output effect.

[0129] Next, the process of determining the state characteristics of the battery based on the state parameters and the environmental parameters by the electronic device in S102 is described.

[0130] refer to Figure 6 As shown in the content, the process may include but is not limited to the following S601 and S602.

[0131] S601. The electronic device determines a change rate of each state parameter and a change rate of each environmental parameter respectively.

[0132] The method of determining the rate of change may be the same or different for different parameters.

[0133] S601 may be implemented as follows: the electronic device determines, for each state parameter and each environmental parameter, a change rate of each state parameter and a change rate of each environmental parameter, respectively.

[0134] S602: The electronic device determines a state characteristic of the battery based on a change rate of each state parameter and a change rate of each environmental parameter.

[0135] S602 can be implemented as follows: the electronic device processes the change rate of each state parameter through a feature extraction algorithm to obtain the features corresponding to each state parameter, processes the change rate of each environmental parameter to obtain the features corresponding to each environmental parameter, and then combines these features to obtain the state features of the battery.

[0136] Based on the above technical means, when determining the state characteristics of the battery, the characteristics are not determined directly based on the parameters, but the change rate of each state parameter and the change rate of each environmental parameter are determined respectively, and the state characteristics of the battery are determined based on the change rate of each state parameter and the change rate of each environmental parameter. Since the change rate can better express the dynamic performance of the battery, the obtained state characteristics are more consistent with the actual situation, which improves the accuracy of the state characteristics, the accuracy of the target results and the safety of the battery.

[0137] The embodiment of the present application can also eliminate abnormal values ​​after obtaining the change rate of each parameter.

[0138] refer to Figure 7 As shown in the content, the process may include but is not limited to the following S701 and S702.

[0139] S701: The electronic device eliminates abnormal values ​​in the change rate of each state parameter based on the first method.

[0140] The first method includes at least one of a moving average algorithm, an autocorrelation function, and a wavelet transform.

[0141] The moving average algorithm can calculate the mean of data in a continuous time window, observe the overall trend of the data, reduce short-term fluctuations, highlight long-term trends, and improve data stability. By calculating the moving average and comparing it with the current data, abnormal deviations can be identified and outliers can be eliminated.

[0142] The autocorrelation function can measure the similarity of signals under different time lags and help identify the periodicity of data. In battery current analysis, the autocorrelation function is used to detect whether there are specific periodic changes and help identify abnormal data.

[0143] Wavelet transform can decompose the signal into different scales, making it have high resolution in both time and frequency domains. Battery temperature fluctuation analysis Wavelet changes can be used to divide short-term mutations such as local overheating and long-term trends such as battery aging, thereby more accurately identifying abnormal data.

[0144] Wavelet transform can capture the mutation point of the signal, that is, the abnormal point or fault point. Using wavelet transform to detect the mutation in the current signal, wavelet transform can effectively remove high-frequency noise while retaining useful low-frequency information and improving data quality.

[0145] S701 may be implemented as follows: the electronic device removes abnormal values ​​in the change rate of each state parameter based on at least one of the first methods.

[0146] S702: The electronic device removes abnormal values ​​in the change rate of each environmental parameter based on a moving average algorithm.

[0147] S702 may be implemented as follows: the electronic device obtains an average value based on a moving average algorithm, determines the change rate of the environmental parameter with a large deviation from the average value as an abnormal value, and removes it.

[0148] Based on the above technical means, different methods of removing outliers are configured according to the characteristics of different parameters, which effectively improves the accuracy of removing outliers.

[0149] Next, the process of the electronic device collecting the battery status parameters and the battery environment parameters in S101 is described. When the status parameters include battery temperature, voltage, current, internal resistance and state of charge, and the environment parameters include the environment temperature, reference Figure 8 As shown in the content, the process may include but is not limited to the following S801 and S802.

[0150] S801. The electronic device collects voltage and current of a battery based on a first frequency.

[0151] The embodiment of the present application does not limit the value of the first frequency and can be configured according to actual needs.

[0152] S801 may be implemented as follows: the electronic device configures the acquisition frequency in the voltage and current acquisition device to be the first frequency, and then acquires the voltage and current values ​​of the battery within a period of time.

[0153] S802: The electronic device collects battery temperature, internal resistance, state of charge, and ambient temperature of the battery based on the second frequency.

[0154] The embodiment of the present application does not limit the value of the second frequency and can be configured according to actual needs.

[0155] S802 may be implemented as follows: the electronic device configures a collection frequency in a battery temperature, internal resistance, state of charge and ambient temperature collection device of the battery to be a second frequency, and then collects the battery temperature, internal resistance, state of charge and ambient temperature.

[0156] Based on the above technical means, different frequencies are used for data collection for different parameter characteristics. On the basis of ensuring the effectiveness of data collection, it can be applied to the characteristics of various parameters. For example, for voltage and current type parameters, the changes are fast, so the collection frequency should be higher. For temperature type parameters, they generally do not change suddenly, so the collection frequency can be slightly lower, which improves the accuracy of parameter collection, the accuracy of target results and the safety of batteries.

[0157] Next, the process of the electronic device collecting the voltage and current of the battery based on the first frequency in S801 is described.

[0158] In one possible implementation, reference Fig. 9 As shown in the content, the process may include but is not limited to the following S901 to S903.

[0159] S901. The electronic device determines a working status of a battery.

[0160] The working state here may include but is not limited to: a first load state and a second load state.

[0161] The load in the first load state is higher than the load in the second load state.

[0162] Therefore, the first load state may also be referred to as a high load state, and the second load state may also be referred to as a low load state.

[0163] S901 may be implemented as follows: the electronic device detects a load of a certain load, and determines a working state of the battery based on the load of the certain load.

[0164] S902: If the working state of the battery is the first load state, the electronic device increases the first frequency; and collects the voltage and current of the battery based on the increased first frequency.

[0165] The embodiment of the present application does not limit the increase range of the first frequency, and can be configured according to actual needs. For example, it can be determined according to the load of the load.

[0166] S902 can be implemented as follows: if the working state of the battery is the first load state, it indicates that the change of current and voltage is relatively large, so the electronic device increases the first frequency of collecting voltage and current; and collects the voltage and current of the battery based on the increased first frequency.

[0167] S903: If the working state of the battery is the second load state, the electronic device reduces the first frequency, and collects the voltage and current of the battery based on the reduced first frequency.

[0168] S903 may be implemented as follows: if the working state of the battery is the second load state, which indicates that the change in current and voltage is relatively small, the electronic device reduces the first frequency, and collects the voltage and current of the battery based on the reduced first frequency.

[0169] The embodiment of the present application does not limit the amplitude of the first frequency reduction, and can be configured according to actual needs. For example, it can be determined according to the load of the load.

[0170] Based on the above technical means, the collection frequency can be adjusted according to the working status of the battery, which further improves the data collection efficiency, the accuracy of the target results and the safety of the battery.

[0171] Below, taking the battery of an electric vehicle as an example, the process of determining the battery status is described through an embodiment.

[0172] Battery monitoring methods mainly rely on simple threshold detection. For example, fixed thresholds of parameters such as voltage, temperature and current can be set. Once the threshold is exceeded, the system will issue an alarm. However, this static monitoring method may have the following problems: alarm response delays, fixed thresholds may lead to false alarms or missed alarms, lack of in-depth analysis of the battery's comprehensive status, and may not be able to identify potential risks in a timely manner.

[0173] Therefore, a more intelligent, comprehensive and real-time battery monitoring solution is urgently needed to improve the accuracy and timeliness of battery anomaly detection. In recent years, with the development of big data and machine learning technologies, it has become possible to apply these technologies to battery status monitoring. By analyzing historical data and real-time data, abnormal battery patterns can be more effectively identified, thereby providing early warnings.

[0174] In summary, developing an electric vehicle battery abnormality warning method based on an algorithm model can not only improve the safety and reliability of the battery, but also provide users with a better driving experience, which is of great significance to promoting the further development of electric vehicles.

[0175] In order to solve the above technical problems, this embodiment provides an electric vehicle battery abnormality warning method, and the technical solution mainly includes the following steps: Step 1: Data collection: The battery voltage, current, temperature, state of charge (SOC), internal resistance and other data are collected in real time through high-precision sensors. The collected data is transmitted to the processing equipment in real time through the wireless communication module.

[0176] Step 2: Data preprocessing: De-noise and standardize the collected data, and remove external noise through filtering algorithms to ensure the accuracy and reliability of the data.

[0177] Step 3: Feature extraction: Use time series analysis methods to extract characteristic parameters of the battery status. The characteristics of the data include temperature fluctuation rate, charge and discharge rate, internal resistance change, etc., and construct feature vectors to facilitate subsequent model training and anomaly detection.

[0178] Step 4: Algorithm model processing: Apply machine learning algorithms, such as random forest, support vector machine or deep learning model, to train normal and abnormal battery behaviors and establish an anomaly detection model. The model can automatically identify potential abnormal patterns by learning from historical battery data.

[0179] Step 5: Abnormality detection and warning: The newly collected data is input into the algorithm model in real time. The model determines whether the battery status is abnormal based on the feature vector. If an abnormal situation is identified, the system will immediately generate a warning message to prompt the user to take necessary measures, such as stopping the car for inspection, replacing the battery, etc.

[0180] Step 6, Feedback mechanism: Users can provide feedback on the system's warning results. The system will continuously optimize the algorithm model based on user feedback to improve the accuracy and reliability of anomaly detection.

[0181] This embodiment provides an electric vehicle battery abnormality warning device, referring to Fig.10 As shown in the content, the electric vehicle battery abnormality warning device 100 may include: Data acquisition module 1001, real-time acquisition of battery-related real-time data. The data preprocessing module 1002 performs denoising and standardization processing on the collected data.

[0182] The feature extraction module 1003 extracts the feature parameters of the battery status and constructs a feature vector.

[0183] Anomaly detection module 1004, which determines the battery status based on a machine learning algorithm and generates warning information; The user feedback module 1005 optimizes the algorithm model according to the user's early warning feedback.

[0184] This embodiment provides an electric vehicle battery abnormality warning method, including: data is collected through a variety of high-precision sensors installed on the battery pack, including temperature sensors, voltage sensors, current sensors and internal resistance measuring devices; different parameters are set with different collection frequencies according to needs, fast-changing data such as voltage and current can be set to high-frequency collection, and relatively stable data such as temperature can be set to low-frequency collection. The system can dynamically adjust the collection frequency according to the working status of the battery, increase the collection frequency under high load or fast charging / discharging conditions, and reduce the collection frequency under normal and stable working conditions.

[0185] The data is transmitted to the central processing module through the bus, and the data is transmitted to the cloud through the wireless communication module for subsequent analysis and model training. After the data collection is completed, the raw data is preprocessed, which mainly includes the following steps: noise processing, Kalman filtering is used to process time series data such as voltage and current; the sliding average filter method can eliminate the occasional mutation values ​​of relatively stable data such as temperature and state of charge, and the adjacent data is weighted averaged; data integrity check, missing value filling, missing values ​​are filled by interpolation or regression model based on historical data, and abnormal values ​​are eliminated or replaced by setting thresholds; data format standardization, unit standardization; current, voltage and other data are normalized in the range of 0-1; feature dimension processing, for data sets with higher dimensions, principal component analysis or linear discriminant analysis algorithm is used for dimensionality reduction; the preprocessed data set is divided into training set, validation set and test set.

[0186] Next, the feature extraction process is described.

[0187] Input data and extract features from the collected data. Feature extraction mainly includes selecting key features, constructing feature vectors, weighted processing features and applying time series analysis. After determining the key features, the system further optimizes the features through feature engineering to improve the model's discrimination ability. Feature engineering includes constructing composite features, weighted processing and feature derivation.

[0188] refer to Fig.11 As shown in the content, the process may include but is not limited to the following S1101 to S1106.

[0189] S1101. Input preprocessing data.

[0190] S1102. Calculate the temperature fluctuation rate using a sliding window method.

[0191] Temperature fluctuation rate is used to describe the temperature change within a unit time. If the temperature fluctuation rate is within the range of , the temperature fluctuation rate can be determined by the following formula (2).

[0192] Formula (2); In formula (2), N represents the number of sampling points in the time interval, Indicates the interval time, represents the temperature at time i; Indicated in The temperature of the moment; Indicates the temperature fluctuation rate.

[0193] The temperature fluctuation rate can help the system identify abnormal temperature fluctuations, thereby warning of risks such as battery overheating.

[0194] Voltage and current characteristics, by calculating the rate of change of voltage or current per unit time, the charge and discharge rate of the battery is obtained. Abnormal changes in the charge and discharge rate may be a signal that the battery is in an undesirable state such as overcharge or over discharge.

[0195] For example, the current change rate of voltage can be determined by the following formula (3).

[0196] , Formula (3); In formula (3), and They represent the changes in voltage and current per unit time, that is, the rates of change of voltage and current; Indicates unit time; and They represent the rate of change of voltage and current respectively.

[0197] The maximum and minimum values ​​of voltage and current within a time window are collected to analyze their fluctuations. When the peak and valley differences of voltage or current are significant, it may indicate that the battery is unstable.

[0198] S1103. Calculate the internal resistance change rate.

[0199] The internal resistance change rate reflects the health of the battery and is an important feature of the battery degradation process. For example, the internal resistance change rate can be determined by formula (4).

[0200] Formula (4); In formula (4), Indicates the internal resistance change rate, represents the internal resistance at the current moment, represents the internal resistance at the previous moment, A time interval representing a moment in time.

[0201] The internal resistance is smoothed using time-weighted average and the change trend of the internal resistance is calculated to identify the problem of chronic battery degradation. If the rate of change of the internal resistance continues to increase, the system can determine that the battery is in a degraded state.

[0202] S1104. Calculate the SOC change rate.

[0203] Average consumption rate, which estimates the battery power consumption under the current load through the rate of change of SOC within a time window; Instantaneous change rate: At each sampling point, the instantaneous change rate of SOC is calculated to monitor the real-time discharge state of the battery; Among them, outliers can also be eliminated in the following ways.

[0204] Moving average, moving average is used to smooth characteristics such as voltage, current and temperature, and reduce noise fluctuations in a short period of time. The calculation formula of moving average can refer to the following formula (5).

[0205] Formula (5); In formula (5), represents the moving average at time t, k is the window size, is the eigenvalue at the tth moment.

[0206] Among them, the appropriate window size can usually be selected according to the data fluctuation situation.

[0207] The autocorrelation function is used to evaluate the correlation of a feature at different time lags and can identify the periodicity or trend characteristics of battery parameters. For the current feature I, its autocorrelation coefficient can be determined by formula (6).

[0208] = Formula (6); In formula (6), represents the autocorrelation coefficient, is the average current value, k is the number of hysteresis steps, and N is the total number. Represents the current value at time t.

[0209] Wavelet transform,For battery features with multi-scale characteristics, such as battery temperature fluctuation,,wavelet transform is used to decompose the temperature signal to detect abnormal,characteristics of the battery at different time scales.

[0210] Wavelet transform can be implemented by the following formula (7).

[0211] Formula (7); In formula (7), x(t) represents the original signal; represents the wavelet basis function, a and b are scale and translation parameters respectively; represents the signal after transformation.

[0212] The original signal here may be an original temperature signal, an original voltage signal, or the like.

[0213] S1105, feature vector construction.

[0214] The feature vector construction can be achieved by the following formula (8).

[0215] Formula (8); In formula (8), Represents the constructed features, represents the rate of temperature change, It represents the voltage change rate, represents the rate of change of current, represents the internal resistance conversion rate, Indicates the rate of change of SOC.

[0216] For different features in the feature vector, the system performs weighted processing according to their importance to anomaly detection. For example, the battery internal resistance change rate has a greater impact on battery degradation, so it is given a higher weight.

[0217] S1106. Output feature vector.

[0218] The feature extraction system can extract key features reflecting the battery health status from the raw data, provide high-quality data input for anomaly detection, and achieve accurate battery status monitoring and risk warning.

[0219] The model processing process is described below.

[0220] This embodiment adopts a method that combines a long short-term memory network (LSTM) based on deep learning and a random forest (RandomForest) model to process time series data and multi-feature comprehensive analysis respectively. Since battery data has time series characteristics and multiple parameters such as voltage, current, and temperature are interrelated, the above two models are selected.

[0221] refer to Fig.12 As shown in the content, the processing process of the model may include but is not limited to the following S1201 to S1206.

[0222] S1201. Data preparation: data collection, labeling and division.

[0223] Collect various status parameters of the battery and perform manual or automatic labeling to mark abnormal and normal battery states. The labeling method is based on battery laboratory test data, simulation data, and actual operation data. Divide the data set into training set, validation set, and test set. Usually, a ratio of 8:1:1 is used to ensure that the test set is independent enough to effectively verify the generalization ability of the model.

[0224] S1202. Model selection and construction.

[0225] The LSTM model is used for time series data processing. Its basic structure includes an input layer, multiple LSTM hidden layers, and an output layer. The specific structure design is as follows: The input layer accepts the time series data of the battery, such as temperature, current, SOC, etc. Assuming the time window is T, the input data format is (X(tT), ..., Xt), where X is the feature vector; two LSTM hidden layers are set, and the number of layers depends on the data volume and model complexity requirements. Each hidden layer has 128 neurons and uses the ReLU activation function to improve the nonlinear expression ability of the model; the output layer is a single neuron, the activation function is Sigmoid, and the output prediction value is a probability value between 0 and 1, which is used to determine whether there is an anomaly in the time window; the key parameters of the LSTM model include the time window size (such as 10 seconds), the number of hidden layers (such as 2 layers) and the number of neurons (such as 128), and the optimal configuration is found by adjusting the parameters.

[0226] The random forest model is used to process multi-dimensional static features and determine whether the battery is abnormal under a specific state. The structure of the model is designed as follows: The input is a preprocessed feature vector, and each feature is standardized. The random forest model contains 100 decision trees (which can be adjusted according to the data volume and performance requirements). Each tree is trained with a random feature subset to increase the generalization ability of the model. The random forest model outputs the final judgment result through a majority voting mechanism. When the majority of trees judge it to be abnormal, an abnormal alarm is output, otherwise it is judged to be normal.

[0227] S1203, model training: training based on training set data.

[0228] Tune parameters to minimize prediction errors through model training, which includes loss function selection, parameter optimization, and model validation; The LSTM model loss function uses the binary cross entropy loss function to calculate the prediction error. The binary cross entropy loss function can refer to the following formula (9).

[0229] Assume that the loss function is defined as: Formula (9); In formula (9), represents the loss value, N represents the number of training data, y represents the true label, Represents the predicted value of the model output, and i represents the sequence number of the current data.

[0230] By minimizing the loss function, the LSTM model can identify abnormal states more accurately.

[0231] The random forest model is optimized based on classification accuracy to improve the classification accuracy of the model on the validation set. Since the random forest is a non-parametric model, the optimization process mainly improves performance by increasing the number of trees and feature randomness.

[0232] S1204. Hyperparameter optimization.

[0233] LSTM model hyperparameter optimization. The key parameters of the LSTM model include the time window size, the number of hidden layers, and the number of neurons. A combination of grid search and cross-validation is used to train the model under different parameter combinations and select the configuration with the best performance on the validation set.

[0234] Random forest model parameter optimization. The main parameters of random forest include the number of decision trees, maximum depth and number of feature selections. A random search algorithm is used to find the optimal configuration in the parameter space to improve the classification accuracy of the model.

[0235] S1205. Model verification.

[0236] After the model training is completed, the test set is used to verify the model and evaluate the performance of the model. The evaluation indicators used include accuracy, precision, recall and score. In particular, to ensure the effectiveness of the model in anomaly detection, the recall rate is focused on to reduce the probability of missed reports.

[0237] S1206. Model deployment and application.

[0238] After completing the training of the LSTM and random forest models, the two are integrated together to build the final anomaly detection system.

[0239] Integrated logic: The LSTM model is used to detect short-term anomalies in time series data. When the LSTM model outputs an abnormal alarm, an early warning is directly generated. The random forest model is used to further analyze the multi-dimensional static features and comprehensively output the judgment results to ensure that the random forest can supplement the detection when the LSTM misses the detection.

[0240] Real-time optimization: To improve the real-time performance of the system, the reasoning process of the LSTM and random forest models is parallelized; by deploying the model on edge computing devices, it can efficiently process real-time data.

[0241] This embodiment can effectively improve the accuracy and response speed of anomaly detection through the combination of multi-model detection, warning level classification and intelligent prompt mechanism.

[0242] Next, the anomaly detection process is described.

[0243] The anomaly detection process includes several key steps: data input, model analysis, anomaly judgment and result output. Fig.13 As shown in the content, the process may include but is not limited to the following S1301 to S1309.

[0244] S1301: Abnormality detection starts.

[0245] S1302: The feature extraction module inputs a feature vector.

[0246] Various battery parameters, including voltage, current, temperature, internal resistance, SOC, etc., are obtained from the data acquisition module in real time. After preprocessing, these data are input into the LSTM and random forest models for time series detection and multi-dimensional feature detection, respectively.

[0247] S1303, LSTM model analyzes and processes time series data.

[0248] LSTM model detection: The model analyzes the trend of time series data such as temperature and voltage. The model predicts the values ​​of various parameters at the next moment and compares them with the actual collected values. If the error exceeds the preset threshold, it is judged as abnormal.

[0249] S1304. Analyze and process multi-dimensional feature data using a random forest model.

[0250] Random forest model detection, the model will comprehensively analyze the multi-dimensional features of the input to determine whether the current state is abnormal. If most decision trees determine that it is abnormal, the abnormal result will be output.

[0251] S1305. Calculate the comprehensive anomaly score, combining the model output and the feature score.

[0252] Abnormal fusion judgment: When any output of the LSTM model or the random forest model is abnormal, the system will further fuse the results of the two models and give a comprehensive score.

[0253] S1306: Determine the abnormality level.

[0254] Whether to trigger an early warning is determined based on a comprehensive score, which is obtained through weighted calculation according to the confidence level of the model output anomaly.

[0255] In order to improve the practicality of the warning information, this embodiment divides the abnormal detection results into different levels to correspond to different battery states and countermeasures. The warning levels include the following three: Level 1 warning (mild abnormality): a minor abnormality is detected but not enough to pose a direct threat to battery safety. It may be caused by environmental changes or occasional noise. The system will record this status and display a prompt message to the user, such as "Battery status is normal, but please pay attention."

[0256] Level 2 warning (moderate abnormality): obvious abnormality is detected, which may pose a certain safety hazard. At this time, the system will issue a suggestion to the user, such as "Battery status is abnormal, please check or contact the service center as soon as possible."

[0257] Level 3 warning (serious abnormality): a serious abnormality is detected and the battery may have a fault or safety risk. The system will immediately sound an alarm to remind the user that "there is a serious battery fault. Please stop the car and check immediately to ensure safety."

[0258] In order to improve the accuracy of early warning, this embodiment adopts a scoring mechanism to score anomaly detection according to the degree of abnormality of each feature and the confidence of the model. The scoring mechanism includes: Single feature scoring: For each feature (such as temperature, voltage, etc.), a score is given based on its degree of deviation from the normal range. The single feature score can be obtained according to the above formula (1).

[0259] Model confidence score, LSTM and random forest models output anomaly confidence respectively, combined with the results of single feature scoring, to calculate the comprehensive anomaly score. The comprehensive score can be obtained according to the following formula (10).

[0260] Formula (10).

[0261] In formula (10), , and are weighted coefficients to reflect the impact of different models and features on the final judgment. is the score output by LSTM, is the score output by the random forest, The score of the feature corresponding to each parameter.

[0262] S1307: Generate warning information of warning type and operation suggestion.

[0263] When the comprehensive score reaches the warning trigger condition, the system will generate corresponding prompt information according to the warning level. The generated warning information includes the following: Warning type, showing the abnormality type, such as abnormal temperature, abnormal current, etc.

[0264] Abnormality level: level 1, level 2, or level 3 warning is displayed based on the scoring results.

[0265] Operation suggestions: provide corresponding operation suggestions, such as "Please check the battery status" or "Please stop the vehicle and check immediately".

[0266] Warning time: displays the time when the warning occurs, making it easier for users to track abnormal history records.

[0267] S1308. Visual, auditory, and remote prompts to users.

[0268] In order to let users know abnormal situations in time, the system has designed a multi-level early warning mechanism, including visual, auditory and remote notification: Visual prompts display warning information on the vehicle's display screen, including abnormality level, abnormality type and operation suggestions. Visual prompts are non-mandatory reminders and users can view them selectively.

[0269] Auditory reminder: when the warning level reaches level 2 or above, the system will issue an audio alarm to prompt the user to check the battery status in time.

[0270] Remote notification: the system will send abnormal information to the cloud through the vehicle network and push it to the user's mobile phone application, so that the user can know the battery status in time outside the vehicle. In the third-level warning situation, the system will give priority to sending emergency push notifications.

[0271] S1309. Record abnormal events and upload them to the cloud.

[0272] Warning history records: All warning records will be uploaded to the cloud for subsequent model optimization and battery health management analysis.

[0273] After the warning information is generated, the system will record the time, type and processing results of the abnormal detection, and allow users to provide feedback. The user feedback module helps the system collect the following information: abnormal confirmation, users can manually confirm whether it is a real abnormality to optimize the false alarm rate of the model. Abnormal cause, users can select the environment where the abnormality occurs (such as high temperature environment, long driving, etc.) to help the system make adaptive adjustments in similar situations.

[0274] Through the abnormality detection and early warning mechanism provided by this embodiment, the system can accurately identify battery abnormalities of varying degrees and provide graded prompts to users based on the abnormal conditions, thereby ensuring vehicle safety and user experience.

[0275] This embodiment has the following technical effects: 1. Dynamic learning and adaptation are achieved by combining the long short-term memory network (LSTM) and random forest models with machine learning algorithms. The system can self-adjust when the battery status changes, improve the accuracy and robustness of anomaly detection, and make up for the shortcomings of a single model in specific scenarios.

[0276] 2. Use a variety of feature extraction technologies such as volatility calculation and internal resistance change rate to comprehensively analyze the battery status; this comprehensive feature extraction method improves the effectiveness of anomaly detection and ensures the system's adaptability under different working conditions.

[0277] 3. A dynamic scoring mechanism is introduced to quantitatively score the battery status by comprehensively considering the deviation degree of each feature and the confidence of the model. This method not only improves the flexibility of anomaly identification, but also can effectively distinguish different types of anomalies, thereby optimizing the early warning strategy.

[0278] 4. Use the cloud computing platform to analyze and process the collected historical data to realize intelligent battery health management and anomaly detection. Through cloud services, users can remotely monitor the battery status, obtain real-time warning information, and improve the safety of electric vehicles.

[0279] 5. Introduce a warning level classification mechanism and multi-level warning prompts, divide the abnormal detection results into three levels of warning, and provide corresponding operation suggestions and prompts according to different levels of abnormal situations; through multi-level warning prompt mechanisms such as vision, hearing and remote notification, users can be informed of battery status abnormalities in a timely manner in various situations. The invention enhances users' trust in the system and can quickly guide users to take action in high-risk situations.

[0280] The battery abnormality warning system of this embodiment can effectively identify various potential risk situations such as abnormal temperature and increased internal resistance, and issue warning information in advance to avoid safety accidents caused by battery failure; the system can be widely used in various types of electric vehicles, including passenger cars, commercial vehicles and electric buses.

[0281] The electric vehicle battery abnormality warning method provided in this embodiment can intelligently monitor the battery status, identify potential abnormalities in real time, and improve the safety and reliability of the battery by combining advanced machine learning algorithms. As the electric vehicle market continues to expand, the implementation of this embodiment will effectively improve the overall safety level of electric vehicles and provide users with a safer and more reliable driving experience.

[0282] In a second aspect, an embodiment of the present application provides a device for determining a battery status. The device for determining a battery status can be deployed in an electronic device. Fig.14 As shown in the content, the battery status determination device 140 may include but is not limited to: a collection unit 1401 , a first determination unit 1402 , a first analysis unit 1403 , a second analysis unit 1404 and a second determination unit 1405 .

[0283] The collecting unit 1401 is used to collect the state parameters of the battery and the environment parameters of the battery; A first determining unit 1402 is used to determine a state characteristic of the battery based on the state parameter and the environmental parameter; The first analysis unit 1403 is used to perform an abnormality analysis on the state feature in the time dimension through the first model to obtain a first result of the battery; the first result is used to indicate whether the battery is abnormal in the time dimension; The second analysis unit 1404 is used to perform an abnormality analysis of the state feature in the spatial dimension through the second model to obtain a second result of the battery; the second result is used to indicate whether the battery is abnormal in the spatial dimension; The second determining unit 1405 is configured to determine a target result for characterizing the state of the battery based on the first result and the second result.

[0284] In some embodiments, the second determination unit 1405 is also used to: if the first result and the second result are the same, determine the state of the battery as the first result; if the first result and the second result are different, determine the target score based on at least the first score and the second score; determine the target result based on the target score; wherein the first score is the score output by the first model; and the second score is the score output by the second model.

[0285] In some embodiments, the second determining unit 1405 is further used to: determine a target score based on the first score and the second score; determine a target score based on the first score, the second score, and the feature score.

[0286] In some embodiments, a score for each state parameter and a score for each environmental parameter are determined; a feature score is determined based on the score for each state parameter, the weight for each state parameter, the score for each environmental parameter, and the weight for each environmental parameter; a target score is determined based on the feature score, the weight for the feature score, the first score, the weight for the first score, the second score, and the weight for the second score.

[0287] In some embodiments, the battery status determination device 140 may further include an output unit, and the output unit is used to: If the state of the battery in the target result is abnormal, the target abnormality type and target abnormality level of the battery are determined; the target abnormality type, target abnormality level and warning information are output.

[0288] In some embodiments, the output unit is also used for: when the target abnormality level is the first abnormality level, outputting the first warning information by means of visual prompts; when the target abnormality level is the second abnormality level, outputting the first warning information by means of visual prompts, and outputting the second warning information by means of auditory prompts; when the target abnormality level is the third abnormality level, outputting the first warning information by means of visual prompts, outputting the second warning information by means of auditory prompts, and outputting the third warning information to the client via the network; wherein the degree of abnormality of the first abnormality level, the second abnormality level, and the third abnormality level increases in sequence.

[0289] In some embodiments, the first determination unit 1402 is further used to: respectively determine the change rate of each state parameter and the change rate of each environmental parameter; and determine the state characteristics of the battery based on the change rate of each state parameter and the change rate of each environmental parameter.

[0290] In some embodiments, the first determination unit 1402 is also used to: eliminate outliers in the change rate of each state parameter based on a first method; the first method includes at least one of a moving average algorithm, an autocorrelation function, and a wavelet transform; and eliminate outliers in the change rate of each environmental parameter based on a moving average algorithm.

[0291] In some embodiments, the acquisition unit 1401 is also used to perform the following operations when the state parameters include battery temperature, voltage, current, internal resistance and state of charge, and the environmental parameters include ambient temperature: acquiring the voltage and current of the battery based on the first frequency; and acquiring the battery temperature, internal resistance, state of charge and ambient temperature of the battery based on the second frequency.

[0292] In some embodiments, the operating state of the battery is determined; if the operating state of the battery is a first load state, the first frequency is increased; the voltage and current of the battery are collected based on the increased first frequency; if the operating state of the battery is a second load state, the first frequency is reduced, and the voltage and current of the battery are collected based on the reduced first frequency; wherein the load of the first load state is higher than the load of the second load state.

[0293] In a third aspect, the present application further provides an electronic device, the electronic device comprising a processor and a memory, the memory storing a computer program or instructions, and the computer program or instructions, when executed by the processor, implements the method provided in the first aspect above.

[0294] In a fourth aspect, an embodiment of the present application provides a storage medium, that is, a computer-readable storage medium, on which a computer program or instructions are stored. When the computer program or instructions are executed by a processor, the method provided in the first aspect above is implemented.

[0295] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the method provided in the first aspect is implemented.

[0296] It should be noted here that the description of the above storage medium, device, and program product embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium, device, apparatus, and program product embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0297] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in some embodiments" appearing throughout the specification may not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The above-mentioned sequence numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments.

[0298] It should be noted that, in this article, the terms "include", "comprises" or any other variations 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, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0299] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0300] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0301] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be separately configured as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0302] A person skilled in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, read-only memories (ROM), magnetic disks or optical disks.

[0303] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0304] The above description is only an implementation mode of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for determining a battery status, characterized in that: The method comprises: Collecting state parameters of the battery and environmental parameters of the battery; Determining a state characteristic of the battery based on the state parameter and the environmental parameter; Performing an abnormality analysis of the state feature in the time dimension by using a first model to obtain a first result of the battery; the first result is used to characterize whether the battery is abnormal in the time dimension; Performing an abnormality analysis of the state feature in a spatial dimension by using a second model to obtain a second result of the battery; the second result is used to characterize whether the battery is abnormal in a spatial dimension; Based on the first result and the second result, a target result for characterizing a state of the battery is determined.

2. The method according to claim 1, characterized in that The determining, based on the first result and the second result, a target result for characterizing the state of the battery comprises: If the first result and the second result are the same, determining that the state of the battery is the first result; If the first result and the second result are different, determining a target score based on at least the first score and the second score; and determining the target result based on the target score; The first score is the score output by the first model; the second score is the score output by the second model.

3. The method according to claim 2, characterized in that The step of determining the target score based at least on the first score and the second score comprises: determining the target score based on the first score and the second score; The target score is determined based on the first score, the second score, and a feature score.

4. The method according to claim 3, characterized in that: The determining the target score based on the first score, the second score, and the feature score includes: Determining a score for each of the state parameters and a score for each of the environmental parameters; Determining the feature score based on the score of each state parameter, the weight of each state parameter, the score of each environmental parameter, and the weight of each environmental parameter; The target score is determined based on the feature scores, the weights of the feature scores, the first score, the weight of the first score, the second score, and the weight of the second score.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: If the state of the battery in the target result is abnormal, determining a target abnormality type and a target abnormality level of the battery; Output the target abnormality type, the target abnormality level and warning information.

6. The method according to claim 5, characterized in that Output warning information, including: When the target abnormality level is the first abnormality level, outputting the first warning information by means of a visual prompt; When the target abnormality level is a level 2 abnormality level, outputting a first warning message by means of a visual prompt, and outputting a second warning message by means of an auditory prompt; When the target abnormality level is level three, the first warning information is outputted through a visual prompt, the second warning information is outputted through an auditory prompt, and the third warning information is outputted to the client through a network; Among them, the abnormality degrees of the first abnormality level, the second abnormality level and the third abnormality level increase in sequence.

7. The method according to any one of claims 1 to 4, characterized in that: The determining the state characteristic of the battery based on the state parameter and the environmental parameter includes: respectively determining a rate of change of each of the state parameters and a rate of change of each of the environmental parameters; Based on the change rate of each of the state parameters and the change rate of each of the environmental parameters, the state characteristics of the battery are determined.

8. The method according to claim 7, characterized in that Before determining the state characteristic of the battery based on the change rate of each of the state parameters and the change rate of each of the environmental parameters, the method further includes: Eliminate abnormal values ​​in the rate of change of each state parameter based on a first method; the first method includes at least one of a moving average algorithm, an autocorrelation function, and a wavelet transform; Based on the moving average algorithm, outliers in the change rate of each environmental parameter are eliminated.

9. The method according to any one of claims 1 to 4, characterized in that: In the case where the state parameters include battery temperature, voltage, current, internal resistance and state of charge, and the environmental parameters include ambient temperature, the state parameters of the battery and the environmental parameters of the battery are collected, including: collecting the voltage and current of the battery based on a first frequency; The battery temperature, internal resistance, state of charge of the battery and the ambient temperature are collected based on the second frequency.

10. The method according to claim 9, characterized in that The collecting the voltage and current of the battery based on the first frequency includes: determining an operating status of the battery; If the working state of the battery is a first load state, increasing the first frequency; collecting the voltage and current of the battery based on the increased first frequency; If the working state of the battery is the second load state, reducing the first frequency, and collecting the voltage and current of the battery based on the reduced first frequency; Wherein, the load load of the first load state is higher than the load load of the second load state.

11. A device for determining a battery status, characterized in that: The device comprises: A collection unit, used to collect state parameters of the battery and environmental parameters of the battery; A first determining unit, configured to determine a state characteristic of the battery based on the state parameter and the environmental parameter; A first analysis unit, configured to perform an abnormality analysis on the state feature in a time dimension by using a first model to obtain a first result of the battery; the first result is used to characterize whether the battery is abnormal in the time dimension; A second analysis unit is used to perform an abnormality analysis of the state feature in a spatial dimension by using a second model to obtain a second result of the battery; the second result is used to characterize whether the battery is abnormal in the spatial dimension; The second determining unit is configured to determine a target result for characterizing a state of the battery based on the first result and the second result.

12. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory stores a computer program or instructions, and when the computer program or instructions are executed by the processor, the method according to any one of claims 1 to 10 is implemented.

13. A computer-readable storage medium, characterized in that: The storage medium stores a computer program or an instruction, and when the computer program or the instruction is executed by the processor, the method according to any one of claims 1 to 10 is implemented.

14. A computer program product, characterized in that The computer program product comprises a computer program or instructions, and when the computer program or instructions are executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images