A method, apparatus, storage medium, and electronic device for predicting battery life.

Abstract

This application relates to a battery life prediction method, apparatus, storage medium, and electronic device, belonging to the field of battery management technology. The method includes: acquiring at least one actual operating parameter of a battery to be analyzed in a target electric sprinkler truck; determining the initial health state of the battery to be analyzed based on each actual operating parameter using a preset health state prediction model; adjusting and optimizing the initial health state based on the target ambient humidity and the target wet duration to obtain the target health state of the battery to be analyzed; acquiring at least one target operating period within a preset time during which the battery to be analyzed is in a deep discharge state; and adjusting and optimizing the target health state based on each target operating period and each target sprinkler duration to obtain the final health state of the battery to be analyzed. This application improves the accuracy of battery life prediction.

Description

Technical Field

[0001] This application relates to the field of battery management technology, specifically to a battery life prediction method, device, storage medium, and electronic device. Background Technology

[0002] Battery State of Health (SOH) refers to the percentage of a battery's current performance relative to its initial state, and is often used to represent battery life. Therefore, the key to predicting battery life is predicting the battery's state of health. Taking batteries in new energy vehicles as an example, battery life prediction has many important implications. Accurate battery life prediction allows for real-time monitoring of battery performance. Once performance degrades to a certain level, timely intervention can be made to replace or maintain the battery, achieving effective management of the battery's life cycle. In addition, accurate battery life prediction also helps improve the recycling rate of used batteries.

[0003] Currently, the common approach to predicting battery life in new energy vehicles involves establishing a mathematical model of the battery's internal electrochemical reactions to describe the aging process, and then predicting battery life based on this model. However, the usage scenarios of new energy vehicles are complex, resulting in diverse and variable battery operating conditions and environments. Relying solely on established mathematical models for battery life prediction cannot comprehensively assess the battery's health status, leading to poor accuracy in battery life prediction. Summary of the Invention

[0004] To improve the accuracy of battery life prediction, this application provides a battery life prediction method, apparatus, storage medium, and electronic device.

[0005] The first aspect of this application provides a battery life prediction method, specifically including:

[0006] Obtain at least one actual operating parameter of the battery to be analyzed in the target electric sprinkler truck;

[0007] Based on the actual operating parameters, the initial health state of the battery to be analyzed is determined by a preset health state prediction model.

[0008] At least one target watering period corresponding to the target electric sprinkler truck within a preset time is obtained, and the target ambient humidity and target wet duration corresponding to each target watering period are determined. Based on the target ambient humidity and the target wet duration, the initial health state is adjusted and optimized to obtain the target health state corresponding to the battery to be analyzed. The target wet duration is the watering duration when the ambient humidity exceeds the preset humidity, the target watering period is the watering period when the ambient humidity exceeds the preset humidity, and the preset time is the period from the time when the last health state of the battery to be analyzed was determined to the current time.

[0009] The system acquires at least one target operating period during which the battery to be analyzed is in a deep discharge state within the preset time period. Based on each target operating period and each target watering period, the target health status is adjusted and optimized to obtain the final health status corresponding to the battery to be analyzed.

[0010] By employing the above technical solution, at least one actual operating parameter of the battery to be analyzed is obtained. Since the battery's operating parameters reflect its health status and performance, the initial health status of the battery is predicted based on these actual operating parameters using a health status prediction model. Next, based on the target ambient humidity and target wet duration during the target electric sprinkler truck's watering within a preset time period, the impact of high humidity on the battery's health status is taken into account, and the initial health status is adjusted and optimized to obtain the target health status. Finally, based on the target operating period, the impact of deep discharge on the battery's health status is taken into account, and the target health status is adjusted and optimized to obtain the final health status of the battery, thereby improving the accuracy of battery life prediction.

[0011] In one implementation, adjusting and optimizing the initial health state based on the target ambient humidity and the target wet duration to obtain the target health state corresponding to the battery to be analyzed specifically includes:

[0012] The system obtains at least one ambient humidity range that the electric sprinkler truck was in when it was spraying water in the past, and determines a reference humidity range from each of the ambient humidity ranges. The reference humidity range is an ambient humidity range that is easy to accelerate battery degradation. The historical electric sprinkler truck is an electric sprinkler truck whose battery degradation rate exceeds a preset rate due to ambient humidity.

[0013] Based on at least one historical watering duration of the electric sprinkler truck under a single reference humidity range, a corresponding reference duration range is determined, wherein the reference duration range is the range in which the watering duration is likely to accelerate battery degradation.

[0014] A first weight is determined for each of the reference humidity ranges, and a second weight is determined for each of the reference humidity ranges corresponding to the reference duration ranges. The first weight represents the likelihood that the ambient humidity is within the corresponding reference humidity range, which accelerates battery degradation. The second weight represents the likelihood that the watering duration is within the corresponding reference duration range, which accelerates battery degradation.

[0015] Based on the first weight, the second weight, the target ambient humidity, and the target wet duration, the initial health state is adjusted and optimized to obtain the target health state corresponding to the battery to be analyzed.

[0016] In one implementation, adjusting and optimizing the initial health state based on the first weight, the second weight, the target ambient humidity, and the target wet duration to obtain the target health state corresponding to the battery to be analyzed specifically includes:

[0017] The reference humidity range in which the target ambient humidity is located is determined as the important humidity range. If the target humid duration exists in each reference duration range corresponding to the important humidity range, the corresponding reference duration range is determined as the important duration range.

[0018] Calculate the product of the first weight of each important humidity range and the second weight of the corresponding important duration range to obtain the first product of the corresponding target watering period, and sum the first products to obtain the first summation result;

[0019] Based on the first summation result, the corresponding first optimization coefficient is determined, and the first optimization coefficient is multiplied by the initial health state to obtain the target health state corresponding to the battery to be analyzed.

[0020] In one embodiment, the method further includes:

[0021] The range from 0 to the preset humidity is defined as the target humidity range, and the final humidity range is determined from each of the reference humidity ranges, wherein the final humidity range is the reference humidity range included in the target humidity range;

[0022] Calculate the second product of the first weight of each final humidity range and the second weight of the corresponding reference duration range, and sum the second products to obtain the second summation result;

[0023] If the second summation result does not exceed the preset first threshold, then the preset humidity is verified to be correct.

[0024] In one embodiment, the method further includes:

[0025] Obtain the watering area type and at least one dimension of watering parameters corresponding to each target watering time period;

[0026] Summing the first product of each target watering time period corresponding to the same watering area type yields the corresponding third summation result;

[0027] If the third summation result exceeds the preset first threshold, the corresponding watering area type is determined as the alert area type, and each target watering period corresponding to the alert area type is determined as an important watering period.

[0028] Obtain the adjacent watering periods before each of the important watering periods in the same watering process, and calculate the length ratio of each important watering period to the length of the corresponding adjacent watering period;

[0029] If the duration ratio exceeds the preset second threshold, the corresponding important watering period is determined as the reference watering period, and the range of alert parameters for each dimension is determined based on the watering parameters of the reference watering period.

[0030] When the target electric sprinkler truck sprays water on the area of ​​the warning zone type, if the actual spraying parameters of the target electric sprinkler truck are within the corresponding warning parameter range, a spraying parameter adjustment reminder will be issued.

[0031] In one embodiment, the method further includes:

[0032] Summing the first product of each target watering time period corresponding to the same watering parameter yields the corresponding fourth summation result;

[0033] The fourth summation result is compared with the first threshold.

[0034] If the fourth summation result exceeds the first threshold, the corresponding watering parameter is determined as the first parameter, and when the first parameter is within the warning parameter range of the corresponding dimension, the corresponding warning parameter range is verified to be correct.

[0035] If the fourth summation result does not exceed the first threshold, the corresponding watering parameter is determined as the second parameter, and when the second parameter is within the warning parameter range of the corresponding dimension, the corresponding warning parameter range is verified to be incorrect.

[0036] In one implementation, adjusting and optimizing the target health status based on each target operating period and each target watering period to obtain the final health status of the battery to be analyzed specifically includes:

[0037] Perform an intersection operation on the target runtime segment and the target watering period to obtain at least one intersection period;

[0038] Obtain the power range of the battery to be analyzed within the intersection time period, and determine the second optimization coefficient based on the power range and the average ambient humidity corresponding to the intersection time period;

[0039] Based on the total duration corresponding to each target runtime segment, a third optimization coefficient is determined, and the target health state is adjusted and optimized based on the second optimization coefficient and the third optimization coefficient to obtain the final health state corresponding to the battery to be analyzed.

[0040] A second aspect of this application provides a battery life prediction device, specifically comprising:

[0041] The data acquisition module is used to acquire at least one actual operating parameter of the battery to be analyzed in the target electric sprinkler truck;

[0042] The status prediction module is used to determine the initial health status of the battery to be analyzed based on the actual operating parameters and a preset health status prediction model.

[0043] The first optimization module is used to acquire at least one target watering period corresponding to the target electric sprinkler truck within a preset time, and to determine the target ambient humidity and target wet duration corresponding to each target watering period. Based on the target ambient humidity and the target wet duration, the initial health state is adjusted and optimized to obtain the target health state corresponding to the battery to be analyzed. The target wet duration is the watering duration when the ambient humidity exceeds the preset humidity, the target watering period is the watering period when the ambient humidity exceeds the preset humidity, and the preset time is the period from the time when the last health state of the battery to be analyzed was determined to the current time.

[0044] The second optimization module is used to obtain at least one target operating period during which the battery to be analyzed is in a deep discharge state within the preset time period, and to adjust and optimize the target health state according to each target operating period and each target watering period to obtain the final health state corresponding to the battery to be analyzed.

[0045] By adopting the above technical solution, the data acquisition module acquires at least one actual operating parameter of the battery to be analyzed, the state prediction module determines the initial health state of the battery to be analyzed through a preset health state prediction model, then the first optimization module adjusts and optimizes the initial health state according to the target ambient humidity and the target wet duration to obtain the target health state of the battery to be analyzed, and finally, the second optimization module adjusts and optimizes the target health state to obtain the final health state of the battery to be analyzed.

[0046] A third aspect of this application provides a computer-readable storage medium storing a computer program that, when loaded and executed by a processor, performs the steps of the method described in any one of the first aspects.

[0047] A fourth aspect of this application provides an electronic device, specifically comprising:

[0048] A processor, a memory, and a computer program stored in the memory and capable of running on the processor, the processor being configured to load and execute the computer program stored in the memory to cause the electronic device to perform the method as described in any one of the first aspects.

[0049] In summary, this application includes at least one of the following beneficial technical effects: It obtains at least one actual operating parameter of the battery to be analyzed. Since the battery's operating parameters reflect its health status and performance, the initial health status of the battery to be analyzed is predicted using each actual operating parameter as input through a health status prediction model. Next, based on the target ambient humidity and target wet duration during the target electric sprinkler truck's watering within a preset time period, the impact of high humidity on the battery's health status is taken into account, and the initial health status is adjusted and optimized to obtain the target health status. Finally, based on the target operating period, the impact of deep discharge on the battery's health status is taken into account, and the target health status is adjusted and optimized to obtain the final health status of the battery to be analyzed, thereby improving the accuracy of battery life prediction. Attached Figure Description

[0050] Figure 1 This is a schematic flowchart of a battery life prediction method provided in an embodiment of this application;

[0051] Figure 2 This is a schematic diagram of the structure of a battery life prediction device provided in an embodiment of this application;

[0052] Figure 3 This is a schematic diagram of another battery life prediction device provided in the embodiments of this application.

[0053] Explanation of reference numerals in the attached diagram: 11. Data acquisition module; 12. State prediction module; 13. First optimization module; 14. Second optimization module; 15. Threshold verification module; 16. Parameter reminder module; 17. Range verification module. Detailed Implementation

[0054] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0055] In the description of the embodiments of this application, words such as "exemplarily," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily," "for example," or "for instance" is intended to present the relevant concepts in a specific manner.

[0056] In the description of the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, B existing alone, or A and B existing simultaneously. Furthermore, unless otherwise stated, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and their variations all mean "including but not limited to," unless otherwise specifically emphasized.

[0057] See Figure 1 This application discloses a flowchart of a battery life prediction method, which can be implemented using a computer program or run on a battery life prediction device based on the von Neumann architecture. The computer program can be integrated into an application or run as a standalone utility application, specifically including:

[0058] S101: Obtain at least one actual operating parameter of the battery to be analyzed in the target electric sprinkler truck.

[0059] Specifically, in this embodiment, the target electric sprinkler truck is an electric sprinkler truck undergoing battery health management. The battery to be analyzed is the battery for which current battery health status prediction or battery life prediction is required. The battery to be analyzed can be a lithium iron phosphate battery or a ternary lithium battery. Battery state of health (SOH) refers to the percentage of the battery's current performance relative to its initial state, and is usually used to represent the battery's remaining lifespan. Actual operating parameters include, but are not limited to, multi-dimensional parameters such as voltage, current, and internal resistance.

[0060] Furthermore, the battery life prediction method disclosed in this application uses a server as the execution entity. The server is wirelessly connected to a terminal, which can be a smartphone or personal computer. The terminal has a battery health management client installed, and the server is the backend server for this client. Specifically, it can be a standalone physical server or a cluster of multiple physical servers. The server is also wirelessly connected to sensors such as voltage sensors and Hall effect sensors. When battery life prediction is needed for the battery to be analyzed, the operator sends an activation command to the server through the client on the terminal. Based on the activation command, the server obtains the actual operating parameters of the battery to be analyzed, such as voltage and current, through the voltage sensor and Hall effect sensor, respectively. In other embodiments, the actual operating parameters of the battery to be analyzed in multiple dimensions can also be obtained directly through the battery management system (BMS) preset in the target electric sprinkler truck.

[0061] S102: Based on the actual operating parameters, determine the initial health state of the battery to be analyzed through a preset health state prediction model.

[0062] Specifically, after determining the actual operating parameters for each dimension, these parameters are input into a pre-defined health status prediction model to obtain the initial health status of the battery to be analyzed. The health status prediction model can be a trained regression model; in other embodiments, it can be a trained support vector regression model. The training process of the health status prediction model is briefly described as follows: Sample data of operating parameters with dimensions consistent with the actual operating parameters are obtained. Specifically, the relevant operating parameters of batteries with known health status can be determined as the sample data, or sample data can be obtained from the publicly available NASA battery dataset. Next, the sample data is preprocessed. Then, the known health status of the battery is used as the prediction target. The preprocessed results are divided into training and validation sets and input into the model for training. During this process, the hyperparameters of the model are adjusted and optimized based on the prediction target, a pre-defined loss function (cross-entropy loss function), and the backpropagation gradient algorithm until the model converges. This is existing technology and will not be elaborated further.

[0063] S103: Obtain at least one target watering period corresponding to the target electric sprinkler truck within a preset time, and determine the target ambient humidity and target wet duration corresponding to each target watering period. Based on the target ambient humidity and target wet duration, adjust and optimize the initial health state to obtain the target health state corresponding to the battery to be analyzed.

[0064] Specifically, the target humidity duration is the duration during which the ambient humidity exceeds a preset humidity level when the target electric sprinkler truck is spraying water, and the target spraying period is the period during which the ambient humidity exceeds the preset humidity level when the target electric sprinkler truck is spraying water. The preset humidity level is a critical value used to determine whether the ambient humidity is too high. The preset time is the period from the time the battery's last health status was determined to the current time. In this embodiment, a feasible method for obtaining the target spraying period is as follows: The spraying period of the target electric sprinkler truck within the preset time is obtained through the spraying records of the target electric sprinkler truck. Then, the humidity collection records of the preset humidity sensor in the target electric sprinkler truck during the spraying period are used to determine whether a target spraying period exists in each spraying period, thereby determining at least one target spraying period within the preset time. The spraying records include different spraying periods and corresponding spraying parameters, including but not limited to range, flow rate, and spraying width.

[0065] Furthermore, the average of at least one humidity value collected during a single target watering period is calculated to obtain the corresponding target environmental humidity, and the duration of the single target watering period is determined, i.e., the target wet duration. Since electric sprinkler trucks tend to increase the humidity of the environment during watering, this high humidity accelerates battery aging through various mechanisms, reducing battery performance and lifespan. Therefore, based on the target environmental humidity and target wet duration, the initial health state is adjusted and optimized to obtain the target health state. One feasible implementation method is to obtain at least one environmental humidity range that the electric sprinkler truck has historically experienced during watering, based on historical records of the electric sprinkler truck's watering history. These historical records include information such as the environmental humidity range and corresponding watering duration during the battery health monitoring interval before the battery degradation was determined to be abnormal. The frequency of a single ambient humidity range is counted among all ambient humidity ranges. If the frequency of the first occurrence exceeds the corresponding threshold, the corresponding ambient humidity range is determined as the reference humidity range, that is, the ambient humidity range that is likely to accelerate battery degradation. It should be noted that the historical electric sprinkler trucks are those whose battery degradation rate exceeds the preset rate due to ambient humidity.

[0066] Furthermore, based on the aforementioned historical records, the historical spraying duration of the electric sprinkler truck under a single reference humidity range is obtained, and the spraying duration range within each historical spraying duration is determined. This spraying duration range is preset in advance. The second frequency of occurrence of each individual spraying duration range within each historical spraying duration is counted. If the second frequency exceeds the corresponding threshold, then that spraying period range is determined as the reference duration range corresponding to the single reference humidity range; that is, the range where spraying durations that easily accelerate battery degradation are located.

[0067] Further, a first weight is determined for each reference humidity range, and a second weight is determined for the reference duration range corresponding to each reference humidity range. The first weight is the ratio of the first frequency of each reference humidity range to the sum of the first frequencies of all different reference humidity ranges. The second weight is the ratio of the second frequency of a single reference duration range corresponding to a reference humidity range to the sum of the second frequencies of all different reference duration ranges. Finally, based on the first weight, the second weight, the target ambient humidity, and the target humid duration, the initial health state is adjusted and optimized to obtain the target health state. In this embodiment, a feasible method for adjustment and optimization is as follows:

[0068] The reference humidity range within which the target ambient humidity falls is defined as the critical humidity range. If a target humid period exists within any of the reference duration ranges corresponding to the critical humidity range, then that reference duration range is defined as the critical duration range. Next, the product of the first weight of each critical humidity range and the second weight of the corresponding critical duration range is calculated to obtain the first product of the corresponding target watering period. The larger the first product, the greater the likelihood that the watering operation performed by the target electric sprinkler truck within the critical humidity range and its watering duration falls within the corresponding critical duration range, i.e., during the corresponding target watering period, will accelerate battery degradation and aging. The first products are then summed to obtain the first summation result. The larger the first summation result, the greater the overall likelihood that the watering operation performed by the target electric sprinkler truck within the preset time will accelerate battery degradation and aging. Furthermore, based on the first summation result, a corresponding first optimization coefficient is determined. The larger the first summation result, the smaller the first optimization coefficient, which is a positive number not greater than 1. Specifically, the first optimization coefficient can be matched from a preset first matching table based on the first summation result. The first matching table includes different summation result ranges and corresponding optimization coefficients. For example, the first matching table includes a summation result range of 0-0.5, with a corresponding optimization coefficient of 0.8; a summation result range of 0.5-1, with a corresponding optimization coefficient of 0.6, and so on. If the first summation result is in the range of 0.5-1, then the first optimization coefficient is 0.6.

[0069] Finally, the determined first optimization coefficient is multiplied by the initial health state to obtain the target health state. This, combined with the target electric sprinkler truck's past watering performance in high humidity environments, optimizes the health state of the battery to be analyzed, making subsequent predictions of battery life more accurate.

[0070] In other embodiments, the range from 0 to a preset humidity level is defined as the target humidity range, and then each reference humidity range contained within the target humidity range is defined as the final humidity range. Next, the second product of the first weight of each final humidity range and the second weight of the corresponding reference duration range is calculated, and then the second products are summed to obtain a second summation result. The larger the second summation result, the greater the overall probability that the battery degradation and aging will be accelerated when the ambient humidity of the target electric sprinkler truck is within the target humidity range. Finally, the second summation result is compared with a preset first threshold. If the second summation result does not exceed the first threshold, it indicates that the probability of accelerated battery degradation and aging is small when the ambient humidity of the target electric sprinkler truck is within the target humidity range. Therefore, the preset humidity is verified to be correct; that is, sprinkling water when the ambient humidity exceeds the preset humidity will likely accelerate battery degradation.

[0071] In another embodiment, based on the water spraying records of the target electric sprinkler truck within a preset time period, at least one dimension of the spraying parameters corresponding to each target spraying time period is determined. Simultaneously, based on the video monitoring records from the pre-installed cameras in the target electric sprinkler truck, the spraying monitoring video corresponding to each target spraying time period is determined. Therefore, the spraying area type corresponding to each target spraying time period is determined, where the spraying area type refers to the type of area where the target electric sprinkler truck sprays water. In this embodiment, the spraying area type includes, but is not limited to, urban roads, construction sites, and green areas. It should be noted that there may be instances where the spraying area types corresponding to different target spraying time periods are the same.

[0072] Furthermore, the first product of each target spraying time period corresponding to the same spraying area type is summed to obtain the third summation result for that spraying area type. The larger the third summation result, the more likely the target electric sprinkler truck is to accelerate battery degradation due to ambient humidity when spraying the area of ​​that spraying area type. If the third summation result exceeds a preset first threshold, it indicates a higher possibility of accelerated battery degradation and aging. In this case, the corresponding spraying area type is designated as a warning area type, and each target spraying time period corresponding to this warning area type is designated as an important spraying time period. The adjacent spraying time periods before each important spraying time period are obtained, that is, the time period before a single important spraying time period within the same spraying time period. The shorter the duration of adjacent spraying time periods, the higher the ambient humidity appears shortly after spraying within the corresponding spraying time period. Furthermore, the ratio of the duration of each important watering period to the duration of its corresponding adjacent watering period is calculated. A larger ratio indicates that the ambient humidity will be higher shortly after watering within that period. If the ratio exceeds a preset second threshold, the corresponding important watering period is designated as a reference watering period. Based on the watering parameters (parameters that easily trigger high ambient humidity) of different dimensions under each reference watering period, a warning parameter range is determined for each dimension. For example, if the actual watering widths under different reference watering periods are 10m, 13m...20m, then the warning parameter range for the watering width dimension is 10-20m.

[0073] Furthermore, when the target electric sprinkler truck is spraying water on an area of ​​the alert type, if the actual spraying parameters of the target electric sprinkler truck are within the corresponding alert parameter range, it indicates that the ambient humidity is likely to be high during the spraying process, which increases the probability of accelerated battery degradation and aging. In this case, a reminder to adjust the spraying parameters is sent to the sprinkler operator's terminal to adjust the spraying parameters in a timely manner and reduce the risk of accelerated battery degradation and aging.

[0074] In another embodiment, the first product of each target spraying period corresponding to the same spraying parameter is summed to obtain a corresponding fourth summation result. This fourth summation result is compared with a preset first threshold. If the fourth summation result exceeds the first threshold, it indicates that spraying with this parameter is more likely to accelerate battery degradation and aging due to high ambient humidity. Therefore, this spraying parameter is determined as the first parameter. If the first parameter is within the warning parameter range of the corresponding dimension, the warning parameter range for that dimension is verified to be correct. Conversely, if the fourth summation result does not exceed the first threshold, it indicates that spraying with this parameter is less likely to accelerate battery degradation and aging due to high ambient humidity. Therefore, this spraying parameter is determined as the second parameter. If the second parameter is within the warning parameter range of the corresponding dimension, the warning parameter range for that dimension is verified to be incorrect.

[0075] S104: Obtain at least one target operating period within a preset time when the battery to be analyzed is in a deep discharge state, and adjust and optimize the target health status according to each target operating period and each target watering period to obtain the final health status corresponding to the battery to be analyzed.

[0076] Specifically, deep discharge refers to a state where a battery's charge is nearly depleted during discharge. Frequent or severe deep discharges shorten battery life. In this embodiment, deep discharge refers to a state where the charge of the battery under analysis is below 20%. After determining the target health state of the battery under analysis, the battery management system of the target electric sprinkler truck obtains at least one target operating period within a preset time during which the battery under analysis is in a deep discharge state. Since battery life is affected by high humidity, and deep discharge exacerbates this impact, an intersection calculation is performed on the target operating period and the target sprinkling period to obtain at least one intersection period. During this intersection period, the battery under analysis is simultaneously in a high humidity environment and in a deep discharge state. Then, the battery management system of the target electric sprinkler truck obtains the charge range of the battery under analysis within the intersection period. Simultaneously, based on the humidity data collected by the humidity sensor, multiple humidity values ​​within the intersection period are obtained and averaged to obtain the corresponding average ambient humidity. Then, based on the average ambient humidity and the charge range, a second optimization coefficient is determined using a preset coefficient calculation formula. The coefficient calculation formula is as follows:

[0077] ;

[0078] In the formula, D represents the second optimization coefficient, t represents the duration of the intersection period, k represents the duration influence coefficient, which controls the growth rate of the interference of the duration of the intersection period on the health status of the battery to be analyzed, and H represents the average ambient humidity. The humidity influence coefficient is used to adjust the nonlinearity of the effect of average ambient humidity on health status. v and β represent parameters controlling the shape and growth rate of the logarithmic function. Q1 represents the end value of the battery's charge range being analyzed, and Q0 represents the beginning value of the battery's charge range being analyzed. The exp function is used to simulate the nonlinear change in the effect of power loss on the health status of the battery under deep discharge conditions. It maps the overall effect on the health status of the battery under analysis to a range of 0 to 1.

[0079] Furthermore, a third optimization coefficient is determined based on the total duration of all target runtime segments. The longer the total duration, the more severe the deep discharge, and the smaller the third optimization coefficient. The third optimization coefficient is a positive number not greater than 1. Specifically, the corresponding optimization coefficient is matched from a preset second matching table based on the total duration. The second matching table includes different duration ranges and their corresponding optimization coefficients. For example, the second matching table includes a duration range of 0-10, with a corresponding optimization coefficient of 1; a duration range of 10-20, with a corresponding optimization coefficient of 0.8, and so on. When the total duration is 15 minutes, falling within the duration range of 10-20 minutes, then the third optimization coefficient is 0.8. Finally, the second optimization coefficient, the third optimization coefficient, and the target health status are multiplied together to obtain the final health status after adjustment and optimization.

[0080] The implementation principle of a battery life prediction method according to an embodiment of this application is as follows: At least one actual operating parameter of the battery to be analyzed is obtained. Since the battery's operating parameters reflect its health status and performance, each actual operating parameter is used as input. Based on these parameters, a health status prediction model predicts the initial health status of the battery to be analyzed. Next, based on the target ambient humidity and target wet duration during the target electric sprinkler truck's watering within a preset time period, the impact of high humidity on the battery's health status is taken into account, and the initial health status is adjusted and optimized to obtain the target health status. Finally, based on the target operating period, the impact of deep discharge on the battery's health status is taken into account, and the target health status is adjusted and optimized to obtain the final health status of the battery to be analyzed, thereby improving the accuracy of battery life prediction.

[0081] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0082] Please see Figure 2 This is a schematic diagram of the battery life prediction device provided in an embodiment of this application. This battery life prediction device can be implemented as all or part of a device through software, hardware, or a combination of both. The device includes a data acquisition module 11, a state prediction module 12, a first optimization module 13, and a second optimization module 14.

[0083] The data acquisition module 11 is used to acquire at least one actual operating parameter of the battery to be analyzed in the target electric sprinkler truck;

[0084] The state prediction module 12 is used to determine the initial health state of the battery to be analyzed based on each actual operating parameter and a preset health state prediction model.

[0085] The first optimization module 13 is used to obtain at least one target watering period corresponding to the target electric sprinkler truck within a preset time, and to determine the target ambient humidity and target wet duration corresponding to each target watering period. Based on the target ambient humidity and target wet duration, the initial health status is adjusted and optimized to obtain the target health status corresponding to the battery to be analyzed. The target wet duration is the watering duration when the ambient humidity exceeds the preset humidity, the target watering period is the watering period when the ambient humidity exceeds the preset humidity, and the preset time is the period from the time when the last health status of the battery to be analyzed was determined to the current time.

[0086] The second optimization module 14 is used to obtain at least one target operating period in which the battery to be analyzed is in a deep discharge state within a preset time, and to adjust and optimize the target health state according to each target operating period and each target watering period to obtain the final health state corresponding to the battery to be analyzed.

[0087] Optionally, the first optimization module 13 is specifically used for:

[0088] Obtain at least one ambient humidity range that the electric sprinkler truck was in when it was spraying water in the past, and determine a reference humidity range from each ambient humidity range. The reference humidity range is the ambient humidity range that is easy to accelerate battery degradation. The historical electric sprinkler truck is the electric sprinkler truck whose battery degradation rate exceeded the preset speed due to ambient humidity.

[0089] Based on at least one historical watering duration of the electric sprinkler truck under a single reference humidity range, determine the corresponding reference duration range, which is the range of watering durations that are prone to accelerating battery degradation.

[0090] A first weight is determined for each reference humidity range, and a second weight is determined for the reference duration range corresponding to each reference humidity range. The first weight represents the likelihood that the ambient humidity is within the corresponding reference humidity range, which accelerates battery degradation, and the second weight represents the likelihood that the watering duration is within the corresponding reference duration range, which accelerates battery degradation.

[0091] Based on the first weight, the second weight, the target ambient humidity, and the target wet duration, the initial health state is adjusted and optimized to obtain the target health state corresponding to the battery to be analyzed.

[0092] Optionally, the first optimization module 13 is specifically used for:

[0093] The reference humidity range in which the target ambient humidity is located is determined as the important humidity range. If the target wet duration exists in each reference duration range corresponding to the important humidity range, the corresponding reference duration range is determined as the important duration range.

[0094] Calculate the product of the first weight of each important humidity range and the second weight of the corresponding important duration range to obtain the first product of the corresponding target watering period, and sum the first products to obtain the first summation result;

[0095] Based on the first summation result, the corresponding first optimization coefficient is determined, and the first optimization coefficient is multiplied by the initial health state to obtain the target health state corresponding to the battery to be analyzed.

[0096] Optional, such as Figure 3 As shown, the device also includes a threshold verification module 15, specifically used for:

[0097] The range from 0 to the preset humidity is defined as the target humidity range, and the final humidity range is determined from each reference humidity range. The final humidity range is the reference humidity range included in the target humidity range.

[0098] Calculate the second product of the first weight of each final humidity range and the second weight of the corresponding reference duration range, and sum the second products to obtain the second summation result;

[0099] If the second summation result does not exceed the preset first threshold, then the preset humidity is verified to be correct.

[0100] Optionally, the device also includes a parameter notification module 16, specifically used for:

[0101] Obtain the watering area type and at least one dimension of watering parameters corresponding to each target watering time period;

[0102] Summing the first product of each target watering time period corresponding to the same watering area type yields the corresponding third summation result;

[0103] If the third summation result exceeds the preset first threshold, the corresponding watering area type will be determined as the alert area type, and the watering time period corresponding to each target of the alert area type will be determined as the important watering time period.

[0104] Obtain the adjacent watering periods before each important watering period in the same watering operation, and calculate the ratio of the duration of each important watering period to the duration of the corresponding adjacent watering period.

[0105] If the duration ratio exceeds the preset second threshold, the corresponding important watering period is determined as the reference watering period, and the range of warning parameters for each dimension is determined based on the watering parameters of the reference watering period.

[0106] When the target electric sprinkler truck is spraying water on an area of ​​the alert type, if the actual spraying parameters of the target electric sprinkler truck are within the corresponding alert parameter range, a spraying parameter adjustment reminder will be issued.

[0107] Optionally, the device also includes a range verification module 17, specifically used for:

[0108] Summing the first product of each target watering time period corresponding to the same watering parameter yields the corresponding fourth summation result;

[0109] The fourth summation result is compared with the first threshold.

[0110] If the fourth summation result exceeds the first threshold, the corresponding watering parameter is determined as the first parameter, and when the first parameter is within the range of the warning parameter in the corresponding dimension, the corresponding warning parameter range is verified to be correct.

[0111] If the fourth summation result does not exceed the first threshold, the corresponding watering parameter is determined as the second parameter, and when the second parameter is within the warning parameter range of the corresponding dimension, the corresponding warning parameter range is verified to be incorrect.

[0112] Optionally, the second optimization module 14 is specifically used for:

[0113] Perform an intersection operation on the target runtime period and the target watering period to obtain at least one intersection period;

[0114] Obtain the power range of the battery to be analyzed within the intersection period, and determine the second optimization coefficient based on the power range and the average ambient humidity corresponding to the intersection period;

[0115] Based on the total duration of each target runtime segment, a third optimization coefficient is determined. Then, based on the second and third optimization coefficients, the target health status is adjusted and optimized to obtain the final health status of the battery to be analyzed.

[0116] It should be noted that the battery life prediction device provided in the above embodiments is only illustrated by the division of the above functional modules when executing the battery life prediction method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the battery life prediction device and the battery life prediction method embodiment provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiment, which will not be repeated here.

[0117] This application also discloses a computer-readable storage medium, which stores a computer program, wherein when the computer program is executed by a processor, it implements a battery life prediction method according to the above embodiments.

[0118] The computer program can be stored in a computer-readable medium. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or certain middleware. The computer-readable medium includes any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the computer-readable medium includes, but is not limited to, the above-mentioned components.

[0119] The battery life prediction method of the above embodiment is stored in the computer-readable storage medium and loaded and executed on the processor to facilitate the storage and application of the above method.

[0120] This application also discloses an electronic device in which a computer program is stored in a computer-readable storage medium. When the computer program is loaded and executed by a processor, it implements the above-mentioned battery life prediction method.

[0121] The electronic device can be a desktop computer, a laptop computer, or a cloud server, and includes, but is not limited to, a processor and a memory. For example, the electronic device may also include input / output devices, network access devices, and buses.

[0122] The processor can be a central processing unit (CPU). Of course, depending on the actual use, it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc., and this application does not limit it.

[0123] The memory can be an internal storage unit of an electronic device, such as a hard disk or RAM, or an external storage device, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD), or flash memory card (FC) equipped on the electronic device. Furthermore, the memory can be a combination of an internal storage unit and an external storage device. The memory is used to store computer programs and other programs and data required by the electronic device. The memory can also be used to temporarily store data that has been output or will be output. This application does not limit this.

[0124] In this electronic device, the battery life prediction method of the above embodiment is stored in the memory of the electronic device and loaded and executed on the processor of the electronic device for convenient use.

[0125] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for predicting battery life, characterized in that, The method includes: Obtain at least one actual operating parameter of the battery to be analyzed in the target electric sprinkler truck; Based on the actual operating parameters, the initial health state of the battery to be analyzed is determined by a preset health state prediction model. The process involves: acquiring at least one target watering period corresponding to the target electric sprinkler truck within a preset time period; determining the target ambient humidity and target wet duration for each target watering period; adjusting and optimizing the initial health state based on the target ambient humidity and target wet duration to obtain the target health state corresponding to the battery to be analyzed; acquiring at least one ambient humidity range that the electric sprinkler truck has been in during historical watering operations; determining a reference humidity range from each ambient humidity range, wherein the reference humidity range is an ambient humidity range that easily accelerates battery degradation; and the historical electric sprinkler truck being an electric sprinkler truck whose battery degradation rate exceeds a preset rate due to ambient humidity. Based on at least one historical watering duration of the historical electric sprinkler truck within a single reference humidity range, a corresponding reference duration range is determined, wherein the reference duration range is an ambient humidity range that easily accelerates battery degradation. The range of watering duration for battery degradation is determined; a first weight is determined for each reference humidity range, and a second weight is determined for each reference duration range corresponding to each reference humidity range. The first weight represents the probability that the ambient humidity is within the corresponding reference humidity range, which accelerates battery degradation, and the second weight represents the probability that the watering duration is within the corresponding reference duration range, which accelerates battery degradation. Based on the first weight, the second weight, the target ambient humidity, and the target wet duration, the initial health state is adjusted and optimized to obtain the target health state corresponding to the battery to be analyzed. The target wet duration is the watering duration when the ambient humidity exceeds a preset humidity, the target watering period is the watering period when the ambient humidity exceeds a preset humidity, and the preset time is the period from the time when the last health state of the battery to be analyzed was determined to the current time. The system acquires at least one target operating period during which the battery to be analyzed is in a deep discharge state within the preset time period. Based on each target operating period and each target watering period, the target health status is adjusted and optimized to obtain the final health status corresponding to the battery to be analyzed.

2. The battery life prediction method according to claim 1, characterized in that, The step of adjusting and optimizing the initial health state based on the first weight, the second weight, the target ambient humidity, and the target wet duration to obtain the target health state corresponding to the battery to be analyzed specifically includes: The reference humidity range in which the target ambient humidity is located is determined as the important humidity range. If the target humid duration exists in each reference duration range corresponding to the important humidity range, the corresponding reference duration range is determined as the important duration range. Calculate the product of the first weight of each important humidity range and the second weight of the corresponding important duration range to obtain the first product of the corresponding target watering period, and sum the first products to obtain the first summation result; Based on the first summation result, the corresponding first optimization coefficient is determined, and the first optimization coefficient is multiplied by the initial health state to obtain the target health state corresponding to the battery to be analyzed.

3. The battery life prediction method according to claim 1, characterized in that, The method further includes: The range from 0 to the preset humidity is defined as the target humidity range, and the final humidity range is determined from each of the reference humidity ranges, wherein the final humidity range is the reference humidity range included in the target humidity range; Calculate the second product of the first weight of each final humidity range and the second weight of the corresponding reference duration range, and sum the second products to obtain the second summation result; If the second summation result does not exceed the preset first threshold, then the preset humidity is verified to be correct.

4. The battery life prediction method according to claim 1, characterized in that, The method further includes: Obtain the watering area type and at least one dimension of watering parameters corresponding to each target watering time period; Summing the first product of each target watering time period corresponding to the same watering area type yields the corresponding third summation result; If the third summation result exceeds the preset first threshold, the corresponding watering area type is determined as the alert area type, and each target watering period corresponding to the alert area type is determined as an important watering period. Obtain the adjacent watering periods before each of the important watering periods in the same watering process, and calculate the length ratio of each important watering period to the length of the corresponding adjacent watering period; If the duration ratio exceeds the preset second threshold, the corresponding important watering period is determined as the reference watering period, and the range of alert parameters for each dimension is determined based on the watering parameters of the reference watering period. When the target electric sprinkler truck sprays water on the area of ​​the warning zone type, if the actual spraying parameters of the target electric sprinkler truck are within the corresponding warning parameter range, a spraying parameter adjustment reminder will be issued.

5. The battery life prediction method according to claim 4, characterized in that, The method further includes: Summing the first product of each target watering time period corresponding to the same watering parameter yields the corresponding fourth summation result; The fourth summation result is compared with the first threshold. If the fourth summation result exceeds the first threshold, the corresponding watering parameter is determined as the first parameter, and when the first parameter is within the warning parameter range of the corresponding dimension, the corresponding warning parameter range is verified to be correct. If the fourth summation result does not exceed the first threshold, the corresponding watering parameter is determined as the second parameter, and when the second parameter is within the warning parameter range of the corresponding dimension, the corresponding warning parameter range is verified to be incorrect.

6. The battery life prediction method according to claim 1, characterized in that, The step of adjusting and optimizing the target health status based on each target operating period and each target watering period to obtain the final health status of the battery to be analyzed specifically includes: Perform an intersection operation on the target runtime segment and the target watering period to obtain at least one intersection period; Obtain the power range of the battery to be analyzed within the intersection time period, and determine the second optimization coefficient based on the power range and the average ambient humidity corresponding to the intersection time period; Based on the total duration corresponding to each target runtime segment, a third optimization coefficient is determined, and the target health state is adjusted and optimized based on the second optimization coefficient and the third optimization coefficient to obtain the final health state corresponding to the battery to be analyzed.

7. A battery life prediction device, used to implement the battery life prediction method according to any one of claims 1 to 6, characterized in that, include: The data acquisition module (11) is used to acquire at least one actual operating parameter of the battery to be analyzed in the target electric sprinkler truck; The state prediction module (12) is used to determine the initial health state of the battery to be analyzed based on each of the actual operating parameters and a preset health state prediction model. The first optimization module (13) is used to obtain at least one target watering period corresponding to the target electric sprinkler truck within a preset time, and to determine the target ambient humidity and target wet duration corresponding to each target watering period. Based on the target ambient humidity and the target wet duration, the initial health state is adjusted and optimized to obtain the target health state corresponding to the battery to be analyzed. The target wet duration is the watering duration when the ambient humidity exceeds the preset humidity, the target watering period is the watering period when the ambient humidity exceeds the preset humidity, and the preset time is the period from the time when the last health state of the battery to be analyzed was determined to the current time. The second optimization module (14) is used to obtain at least one target running segment in which the battery to be analyzed is in a deep discharge state within the preset time period, and to adjust and optimize the target health state according to each target running segment and each target watering period to obtain the final health state corresponding to the battery to be analyzed.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it implements the method of any one of claims 1-6.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, When the processor loads and executes the computer program, it implements the method of any one of claims 1-6.

Images