A customized state monitoring method and system for new energy vehicle batteries

Abstract

The present invention provides a customized state monitoring method and system for new energy vehicle batteries, the method comprising: obtaining historical operation data of new energy vehicle batteries based on a cloud database, and performing data tagging processing to obtain tagged historical data; performing intelligent analysis on the tagged historical data to determine the influence of ambient temperature and charge / discharge rate on the SOC of new energy vehicle batteries, and obtaining characteristic influence compensation coefficients; extracting battery SOC change characteristics corresponding to driving behavior from the tagged historical data; and modifying the monitoring scheme of new energy vehicle batteries according to the characteristic influence compensation coefficients and battery SOC change characteristics to obtain a customized monitoring scheme. The present invention integrates battery state monitoring with the battery's operating parameter influence characteristics and the battery SOC change characteristics corresponding to driving behavior, and formulates a monitoring scheme that conforms to the battery's current real working state, which is conducive to improving the accuracy of battery state monitoring and the accuracy of SOC monitoring values.

Description

Technical Field

[0001] The present invention relates to the technical field of battery monitoring, and in particular to a customized state monitoring method and system for a new energy vehicle battery. Background Art

[0002] Due to the non-renewable nature of oil resources and the growing global demand for oil, oil prices continue to rise. At the same time, people are also aware that excessive use of oil will make ecological pollution and other problems more serious. Therefore, people are eager to find new energy sources to replace oil resources. As the main consumer of oil resources, people are constantly seeking new sources of automobile power in order to overcome their dependence on traditional oil energy. Among them, new energy electric vehicles with power batteries as power sources stand out. As the heart of new energy electric vehicles, batteries provide energy for the movement of new energy electric vehicles. However, existing batteries mainly rely on chemical reactions generated inside the batteries to complete the conversion of electrical energy. As the battery usage time increases, the battery energy conversion efficiency will change to varying degrees, resulting in changes in battery capacity. In addition, different battery usage methods will also lead to differences in battery life. If new energy vehicles are monitored in a fixed manner according to a fixed battery monitoring strategy, it is easy to have a situation where the monitored battery monitoring status is inconsistent with the actual battery status, resulting in inaccurate battery monitoring status and incorrect battery life estimation. Summary of the invention

[0003] The present invention provides a customized state monitoring method and system for new energy vehicle batteries to solve the above-mentioned problems.

[0004] The present invention provides a customized state monitoring method for a new energy vehicle battery, comprising:

[0005] Based on the cloud database, the historical operation data of new energy vehicle batteries is obtained, and data labeling is performed to obtain labeled historical data;

[0006] Intelligently analyze the marked historical data to determine the impact of ambient temperature and charge / discharge rate on the SOC of new energy vehicle batteries and obtain the characteristic impact compensation coefficient;

[0007] Extract the battery SOC change characteristics corresponding to driving behavior from the marked historical data;

[0008] According to the characteristic impact compensation coefficient and the battery SOC change characteristics, the monitoring plan of the new energy vehicle battery is modified to obtain a customized monitoring plan.

[0009] Preferably, in a customized state monitoring method for a new energy vehicle battery, the historical operation data of the current new energy vehicle battery is obtained based on a cloud database, including:

[0010] Obtain historical operating data of new energy vehicle batteries within a preset effective period from the cloud database;

[0011] The historical operation data is split according to the charge and discharge cycle to obtain the historical operation data corresponding to multiple charging cycles;

[0012] The ambient temperature and the charge and discharge rate in each period of the historical operation data corresponding to each charge and discharge cycle are marked to obtain marked historical data.

[0013] Preferably, in a customized state monitoring method for a new energy vehicle battery, intelligent analysis is performed on the marked historical data to determine the impact of ambient temperature and charge / discharge rate on the SOC of the new energy vehicle battery, and obtain a characteristic impact compensation coefficient, including:

[0014] Based on the temperature tags of the marked historical data, the marked historical data of multiple charge and discharge cycles are aligned to obtain the temperature alignment result, and based on the temperature alignment result and the preset feature extraction model, the first influencing feature of the charge and discharge rate on the SOC transformation of the new energy vehicle battery is extracted;

[0015] Based on the rate labels of the marked historical data, the marked historical data of multiple charge and discharge cycles are aligned to obtain the rate alignment results. Based on the rate alignment results and the preset feature extraction model, the second influence feature of the ambient temperature on the SOC transformation of the new energy vehicle battery is extracted;

[0016] Obtain the normal charge and discharge rate characteristics and standard operating temperature characteristics of the new energy vehicle battery, perform a first influencing characteristic coefficient evaluation on the temperature alignment results corresponding to each ambient temperature based on the normal charge and discharge rate characteristics, and obtain the charge and discharge rate influence coefficient, perform a second influencing characteristic coefficient evaluation on the multiple alignment results corresponding to each charge and discharge multiple based on the standard operating temperature characteristics, and obtain the ambient temperature influence coefficient;

[0017] Based on the first influencing feature and the second influencing feature, determining the combined feature corresponding to each marked historical data, and generating the combined feature impact compensation coefficient corresponding to the marked historical data according to the combined feature, combined with the charge and discharge rate impact coefficient and the ambient temperature impact coefficient;

[0018] Based on the value range of the first influencing feature and the second influencing feature in the combined feature, the marked historical data is classified to obtain multiple feature impact category sets, and the combined feature impact compensation coefficients in each feature impact category set are averaged to obtain feature impact compensation coefficients corresponding to different feature impact category sets.

[0019] Preferably, in a customized state monitoring method for a new energy vehicle battery, battery SOC change characteristics corresponding to driving behavior are extracted from the marked historical data, including:

[0020] Based on the marked historical data, multiple battery SOC transformation curves corresponding to multiple charge and discharge cycles are generated, and the change rates of the multiple battery SOC transformation curves are marked respectively. Based on the change rate marking results, the rate mutation point corresponding to the new energy vehicle battery is determined;

[0021] Obtain the historical vehicle driving data of new energy vehicles corresponding to each charging and discharging cycle, determine the vehicle driving behavior corresponding to each rate mutation point based on the time correspondence between the historical vehicle driving data and the marked historical data, generate a behavior label and add it to the corresponding rate mutation point to obtain the SOC processing curve;

[0022] Compare the rate mutation points of multiple SOC processing curves to determine whether there is a power mutation in the new energy vehicle battery. If so, mark the power mutation position in red, and divide the use of the new energy vehicle battery into stages according to the red marked position to obtain the SOC normal stage and SOC abnormal stage;

[0023] Based on multiple SOC processing curves, the battery monitoring data change characteristics corresponding to different driving behaviors are extracted for the SOC normal stage and the SOC abnormal stage;

[0024] The battery SOC variation characteristics are generated based on the gradient division results of the usage stages of new energy vehicle batteries and the variation characteristics of the battery monitoring data corresponding to each usage stage.

[0025] Preferably, in a customized state monitoring method for a new energy vehicle battery, the monitoring scheme for the new energy vehicle battery is modified according to the characteristic impact compensation coefficient and the battery SOC change characteristics to obtain a customized monitoring scheme, including:

[0026] Obtain the current monitoring scheme of the new energy vehicle battery, re-divide the current use phase gradient of the current monitoring scheme based on the use phase gradient corresponding to the battery SOC change characteristics, and simultaneously obtain the battery monitoring characteristics corresponding to each driving behavior in the current monitoring scheme;

[0027] Comparing the battery monitoring characteristics with the battery monitoring data change characteristics in the battery SOC change characteristics to obtain driving behavior monitoring differences;

[0028] Based on the differences in driving behavior monitoring, the driving behavior monitoring strategies at different use stages are modified to obtain the preliminary modified monitoring strategy for new energy vehicle batteries;

[0029] Obtaining environmental data and a navigation driving route of the new energy vehicle, and predicting the driver's driving strategy on the navigation driving route based on the navigation driving route and the driver's driving behavior preference;

[0030] According to the driving strategy, predict the change of the charge and discharge rate during driving, and determine the compensation coefficient of the real-time characteristic impact of the new energy vehicle based on the environmental data and the change of the charge and discharge rate;

[0031] The battery monitoring characteristics in the preliminary correction monitoring strategy are corrected based on the real-time characteristic impact compensation coefficient to obtain a customized monitoring solution corresponding to the current driving stage of the new energy vehicle battery.

[0032] Preferably, in a customized state monitoring method for a new energy vehicle battery, after obtaining a customized monitoring solution, it also includes:

[0033] Obtain the latest navigation route of new energy vehicles in real time, as well as the actual driving behavior characteristics of the driver corresponding to the different road conditions of the traveled sections corresponding to the latest navigation route;

[0034] According to the actual driving behavior characteristics, the driving strategy in the customized monitoring plan is corrected, and the corresponding customized monitoring plan is updated in real time according to the correction results.

[0035] Preferably, in a customized state monitoring method for a new energy vehicle battery, in the process of monitoring the new energy vehicle battery based on the latest customized monitoring solution, the method includes:

[0036] Obtain the current SOC value of the new energy vehicle, and based on the driving strategy corresponding to the latest navigation route of the new energy vehicle and the battery SOC change characteristics, determine whether the new energy vehicle can complete the full driving task corresponding to the latest navigation route;

[0037] If possible, continue navigation according to the latest driving route;

[0038] Otherwise, an insufficient power warning is generated, and the nearest charging equipment is queried based on the navigation map, and the candidate charging equipment is screened based on the new energy driving direction;

[0039] The positions of the charging devices to be selected are marked on the latest navigation route. Based on the position marking results, the remaining SOC value corresponding to each charging device to be selected is predicted. The charging devices to be selected with remaining SOC values ​​greater than preset values ​​are displayed as alternative devices on the navigation map corresponding to the latest navigation route, and the alternative devices on the latest navigation route are highlighted.

[0040] Preferably, in a customized state monitoring method for a new energy vehicle battery, when the new energy vehicle is determined to be able to complete the full driving task corresponding to the latest navigation route, the method includes:

[0041] Query the charging equipment near the destination of the new energy vehicle, take the charging equipment within the preset range of the destination as the target charging equipment, and predict the arrival time of the new energy vehicle based on the driving strategy corresponding to the latest navigation route;

[0042] Based on the big data analysis results of the target charging equipment, the working status of each target charging equipment within the real-time arrival time is predicted, and the location of the idle charging equipment is determined;

[0043] The location of the idle charging equipment is sent to the display terminal as the recommended destination parking location for the new energy vehicle for display, and a synchronous voice broadcast is performed.

[0044] Preferably, in a customized state monitoring method for a new energy vehicle battery, it also includes:

[0045] Determine the current charge and discharge cycle duration of the new energy vehicle battery based on multiple SOC processing curves, and generate a battery repair warning when the current charge and discharge cycle duration is less than or equal to the average driving time of the driver;

[0046] Otherwise, based on the red marked position, the total usage lengths of the phases corresponding to the normal SOC phase and the abnormal SOC phase are determined respectively, and the normal power supply ratio of the battery is calculated;

[0047] When the normal battery power supply ratio is less than the preset threshold, a battery repair warning is generated.

[0048] The present invention provides a customized state monitoring system for new energy vehicle batteries, comprising:

[0049] An operation data processing module is used to obtain historical operation data of new energy vehicle batteries based on a cloud database, and perform data marking processing to obtain marked historical data;

[0050] The data intelligent analysis module is used to perform intelligent analysis on the marked historical data, determine the impact of ambient temperature and charge and discharge rate on the SOC of new energy vehicle batteries, and obtain the characteristic impact compensation coefficient;

[0051] The battery feature extraction module is used to extract the battery SOC change features corresponding to the driving behavior of the marked historical data;

[0052] The solution optimization and customization module is used to modify the monitoring solution of new energy vehicle batteries according to the characteristic impact compensation coefficient and the battery SOC change characteristics to obtain a customized monitoring solution.

[0053] Compared with the prior art, the present invention has at least the following beneficial effects:

[0054] The present invention is based on a cloud database, obtains historical operating data of new energy vehicle batteries, performs data marking processing, obtains marked historical data, and then performs intelligent analysis on the marked historical data to determine the influence of ambient temperature and charge and discharge rate on the SOC of new energy vehicle batteries, obtains characteristic influence compensation coefficients, and extracts battery SOC change characteristics corresponding to driving behavior from the marked historical data. Finally, according to the characteristic influence compensation coefficients and battery SOC change characteristics, the monitoring scheme of new energy vehicle batteries is corrected to obtain a customized monitoring scheme, and the battery state monitoring is integrated with the influence characteristics of the battery's working parameters (ambient temperature and charge and discharge rate) and the battery SOC change characteristics corresponding to driving behavior. The battery state monitoring strategy of new energy vehicles is adjusted to formulate a monitoring scheme that conforms to the current actual working state of the battery, which is beneficial to improving the accuracy of battery state monitoring and the accuracy of SOC monitoring values, providing accurate endurance reference time for drivers and passengers, and facilitating charging planning in advance for drivers and passengers.

[0055] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in this application document.

[0056] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0058] Figure 1 This is a flow chart of a customized state monitoring method for a new energy vehicle battery according to the present invention;

[0059] Figure 2 This is a flow chart of step 1 of a customized state monitoring method for a new energy vehicle battery of the present invention;

[0060] Figure 3 This is a flow chart of step 2 of a customized state monitoring method for a new energy vehicle battery of the present invention;

[0061] Figure 4 This is a flow chart of step 3 of a customized state monitoring method for a new energy vehicle battery of the present invention;

[0062] Figure 5 This is a flow chart of step 4 of a customized state monitoring method for a new energy vehicle battery of the present invention;

[0063] Figure 6This is a schematic diagram of a customized state monitoring system for new energy vehicle batteries according to the present invention. DETAILED DESCRIPTION

[0064] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0065] Embodiment 1:

[0066] The present invention provides a customized state monitoring method for new energy vehicle batteries, such as Figure 1 As shown, including:

[0067] Step 1: Based on the cloud database, obtain the historical operation data of the new energy vehicle battery, and perform data labeling processing to obtain labeled historical data;

[0068] Step 2: Perform intelligent analysis on the marked historical data to determine the impact of ambient temperature and charge / discharge rate on the SOC of new energy vehicle batteries and obtain the characteristic impact compensation coefficient;

[0069] Step 3: Extract the battery SOC change characteristics corresponding to the driving behavior from the marked historical data;

[0070] Step 4: According to the characteristic impact compensation coefficient and the battery SOC change characteristics, the monitoring plan of the new energy vehicle battery is modified to obtain a customized monitoring plan.

[0071] In this embodiment, SOC refers to the battery state of charge (State Of Charge).

[0072] In this embodiment, the battery SOC variation characteristics refer to the influence of different driving behaviors (such as gentle uphill, gentle downhill, acceleration on uphill roads, acceleration on ordinary roads, deceleration driving, etc.) on the reduction range of the battery SOC value.

[0073] The beneficial effects of the above technical solution are as follows: the present invention obtains the historical operation data of the new energy vehicle battery based on the cloud database, and performs data marking processing to obtain the marked historical data, and then performs intelligent analysis on the marked historical data to determine the influence of ambient temperature and charge and discharge rate on the SOC of the new energy vehicle battery, obtain the characteristic influence compensation coefficient, and extract the battery SOC change characteristics corresponding to the driving behavior of the marked historical data, and finally, according to the characteristic influence compensation coefficient and the battery SOC change characteristics, the monitoring scheme of the new energy vehicle battery is corrected to obtain a customized monitoring scheme, and the battery status monitoring is integrated with the battery working parameters (ambient temperature and charge and discharge rate) influence characteristics and the battery SOC change characteristics corresponding to the driving behavior, and the battery status monitoring strategy of the energy vehicle is adjusted to formulate a monitoring scheme that conforms to the current actual working state of the battery, which is conducive to improving the accuracy of battery status monitoring and the accuracy of SOC monitoring values, providing accurate endurance reference time for drivers and passengers, and facilitating the drivers and passengers to plan charging in advance.

[0074] Embodiment 2:

[0075] On the basis of Example 1, the historical operation data of the current new energy vehicle battery is obtained based on the cloud database, such as Figure 2 As shown, including:

[0076] Step 101: Acquire historical operation data of a new energy vehicle battery within a preset effective period from a cloud database;

[0077] Step 102: splitting the historical operation data according to the charge and discharge cycles to obtain historical operation data corresponding to multiple charging cycles;

[0078] Step 103: marking the ambient temperature and the charge and discharge rate in each time period of the historical operation data corresponding to each charge and discharge cycle to obtain marked historical data.

[0079] In this embodiment, the preset effective period is determined according to the frequency of use of the new energy vehicle, and includes at least historical operation data corresponding to 5 charging and discharging cycles;

[0080] When the frequency of use of new energy vehicles is high, the preset valid period is 3-7 days. When the frequency of use of new energy vehicles is low, the preset valid period is 1-12 months.

[0081] In this embodiment, the marked historical data refers to data of the same period in different charge and discharge cycles, wherein the charge and discharge cycle is the time from the start of current charging to the start of next charging of the new energy vehicle battery.

[0082] The beneficial effects of the above technical solution are as follows: the present invention obtains the historical operation data of the new energy vehicle battery within a preset effective period from the cloud database, and then automatically splits and marks the historical operation data according to the charging and discharging cycle, thereby realizing the automatic organization of the vehicle operation data and providing concise data for subsequent data intelligent analysis, which is conducive to improving the efficiency of intelligent analysis and feature extraction.

[0083] Embodiment 3:

[0084] On the basis of Example 1, the marked historical data is intelligently analyzed to determine the influence of ambient temperature and charge / discharge rate on the SOC of the new energy vehicle battery, and obtain the characteristic influence compensation coefficient, such as Figure 3 As shown, including:

[0085] Step 211: aligning the marked historical data of multiple charge and discharge cycles based on the temperature tags of the marked historical data to obtain a temperature alignment result, and extracting the first influencing feature of the charge and discharge rate on the SOC transformation of the new energy vehicle battery based on the temperature alignment result and a preset feature extraction model;

[0086] Step 212: aligning the marked historical data of multiple charge and discharge cycles based on the rate tags of the marked historical data to obtain a rate alignment result, and extracting a second influence feature of the ambient temperature on the SOC transformation of the new energy vehicle battery based on the rate alignment result and a preset feature extraction model;

[0087] Step 202: obtaining the normal charge and discharge rate characteristics and standard operating temperature characteristics of the new energy vehicle battery, performing a first influencing characteristic coefficient evaluation on the temperature alignment results corresponding to each ambient temperature based on the normal charge and discharge rate characteristics, and obtaining the charge and discharge rate influence coefficient, performing a second influencing characteristic coefficient evaluation on the multiple alignment results corresponding to each charge and discharge multiple based on the standard operating temperature characteristics, and obtaining the ambient temperature influence coefficient;

[0088] Step 203: determining the combination feature corresponding to each marked historical data based on the first influencing feature and the second influencing feature, and generating a combination feature impact compensation coefficient corresponding to the marked historical data according to the combination feature, combined with the charge and discharge rate impact coefficient and the ambient temperature impact coefficient;

[0089] Step 204: Based on the value ranges of the charge and discharge rate influence coefficient and the ambient temperature influence coefficient corresponding to the combined features, the marked historical data is classified to obtain multiple feature influence category sets, and the combined feature influence compensation coefficients in each feature influence category set are averaged to obtain feature influence compensation coefficients corresponding to different feature influence category sets.

[0090] In this embodiment, the temperature label refers to the ambient temperature label of the battery working place on the marked historical data; the rate label refers to the charge and discharge rate label of the battery on the marked historical data.

[0091] In this embodiment, the first influencing feature refers to the influencing feature of the battery SOC value change at different charge and discharge rates, that is, the battery SOC change feature corresponding to different charge and discharge rates at the same ambient temperature.

[0092] In this embodiment, the second influencing feature refers to the influencing feature of the change of the battery SOC value due to different ambient temperatures, that is, the change feature of the battery SOC corresponding to different ambient temperatures at the same charge and discharge rate.

[0093] In this embodiment, the combined feature refers to a combination of a first influencing feature corresponding to the ambient temperature corresponding to each marked historical data and a second influencing feature corresponding to the charge and discharge rate.

[0094] In this embodiment, the first influencing characteristic coefficient refers to a characteristic difference coefficient of the first influencing characteristic corresponding to different charge and discharge rates compared with a standard operating temperature characteristic (referring to a change characteristic of the battery SOC at a standard temperature).

[0095] The second influencing characteristic coefficient refers to the characteristic difference coefficient of the second influencing characteristic corresponding to different ambient temperatures compared with the normal charge and discharge rate characteristics (refers to the change characteristics of the battery SOC at the most commonly used energy supply charge and discharge rate during the driving of new energy vehicles).

[0096] The combined feature impact compensation coefficient refers to the result obtained by processing the charge and discharge rate impact coefficient and the ambient temperature impact coefficient corresponding to the combined feature corresponding to the marked historical data according to preset weights.

[0097] In this embodiment, the value interval refers to the first decimal point of the charge and discharge rate influence coefficient and the ambient temperature influence coefficient, which are rounded off. The feature influence category set refers to the set of combined feature influence compensation coefficients corresponding to the marked historical data whose value intervals of the charge and discharge rate influence coefficient and the ambient temperature influence coefficient corresponding to the combined feature are exactly the same.

[0098] The beneficial effects of the above technical solution are as follows: the present invention aligns the temperature label and the charge and discharge label respectively, and then extracts the SOC change characteristics corresponding to different ambient temperatures or different charge and discharge rates according to the alignment results, and then performs a difference evaluation on multiple change characteristics under the standard state to obtain the charge and discharge rate influence coefficients corresponding to different ambient temperatures and the ambient temperature influence coefficients corresponding to different charge and discharge rates, and then determines the combined features corresponding to each marked historical data, and performs an impact evaluation on each marked historical data according to the combined features to obtain the combined feature influence compensation coefficient, and finally classifies the marked historical data based on the value ranges of the charge and discharge rate influence coefficient and the ambient temperature influence coefficient corresponding to the combined features to obtain multiple feature influence category sets, and performs mean processing on the combined feature influence compensation coefficients in each feature influence category set to obtain the feature influence compensation coefficients corresponding to different feature influence category sets, thereby realizing adaptive compensation for state changes during battery use, combining battery state detection with actual battery use loss, so that the battery state detection is closer to the actual capacity of the battery, which is beneficial to improving the accuracy of battery state monitoring.

[0099] Embodiment 4:

[0100] Based on Example 1, the battery SOC change characteristics corresponding to the driving behavior are extracted from the marked historical data, such as Figure 3 As shown, including:

[0101] Step 301: Based on the marked historical data, multiple battery SOC transformation curves corresponding to multiple charge and discharge cycles are generated, and the change rates of the multiple battery SOC transformation curves are marked respectively, and based on the change rate marking results, the rate mutation point corresponding to the new energy vehicle battery is determined;

[0102] Step 302: Obtain historical vehicle driving data of the new energy vehicle corresponding to each charge and discharge cycle, determine the vehicle driving behavior corresponding to each rate mutation point based on the time correspondence between the historical vehicle driving data and the marked historical data, generate a behavior label and add it to the corresponding rate mutation point, and obtain an SOC processing curve;

[0103] Step 303: compare the rate mutation points of multiple SOC processing curves to determine whether there is a power mutation in the new energy vehicle battery. If so, mark the power mutation position in red, and divide the use of the new energy vehicle battery into stages according to the red marked position to obtain a normal SOC stage and an abnormal SOC stage.

[0104] Step 304: extracting battery monitoring data variation characteristics corresponding to different driving behaviors in the SOC normal stage and the SOC abnormal stage based on multiple SOC processing curves;

[0105] Step 305: Generate battery SOC variation characteristics according to the gradient division results of the use stages of the new energy vehicle battery and the battery monitoring data variation characteristics corresponding to each use stage.

[0106] In this embodiment, the change rate marking refers to marking the curve slope of each curve segment of each SOC change curve.

[0107] In this embodiment, the rate mutation point refers to a node on the SOC change curve where the slope changes.

[0108] In this embodiment, the sudden change in power refers to a substantial reduction in the power of the new energy vehicle during the charging and discharging process that is not affected by driving behavior.

[0109] In this embodiment, the SOC abnormal stage refers to a stage in which the battery is rapidly losing power during power supply; and the SOC normal stage refers to a stage in which the battery is outputting power normally during power supply.

[0110] In this embodiment, the battery detection data variation characteristics refer to the SOC variation characteristics caused by different driving behaviors.

[0111] In this embodiment, the battery SOC change characteristics include battery monitoring data change characteristics corresponding to different SOC stages of the driver's entire driving behavior.

[0112] The beneficial effects of the above technical solution: the present invention combines the SOC change of the new energy vehicle battery with the driver's driving behavior, so that the battery detection status is combined with the current battery usage mode, and compares the rate mutation points of multiple SOC processing curves to determine whether there is a power mutation in the new energy vehicle battery. Based on the power mutation point, the use of the new energy vehicle battery is gradiently divided into stages to obtain the SOC normal stage and the SOC abnormal stage, thereby realizing the division of the normal and abnormal power-off stages of the battery energy supply stage, and according to the division results, the battery monitoring data change characteristics corresponding to different driving behaviors in different usage stages are extracted, which is conducive to improving the accuracy of battery power prediction, thereby improving the accuracy of battery status prediction.

[0113] Embodiment 5:

[0114] On the basis of Example 1, according to the characteristic impact compensation coefficient and the battery SOC change characteristics, the monitoring scheme of the new energy vehicle battery is modified to obtain a customized monitoring scheme, such as Figure 5 As shown, including:

[0115] Step 401: obtaining a current monitoring scheme of a new energy vehicle battery, re-dividing the current use phase gradient of the current monitoring scheme based on the use phase gradient corresponding to the battery SOC change characteristics, and simultaneously obtaining the battery monitoring characteristics corresponding to each driving behavior in the current monitoring scheme;

[0116] Step 402: Compare the battery monitoring characteristics with the battery monitoring data change characteristics in the battery SOC change characteristics to obtain driving behavior monitoring differences;

[0117] Step 403: Based on the driving behavior monitoring differences, the driving behavior monitoring strategies at different use stages are modified to obtain a preliminary modified monitoring strategy for the new energy vehicle battery;

[0118] Step 404: Obtain environmental data and a navigation driving route of the new energy vehicle, and predict the driver's driving strategy on the navigation driving route based on the navigation driving route and the driver's driving behavior preference;

[0119] Step 405: predicting the change of the charge and discharge rate during driving according to the driving strategy, and determining the real-time characteristic impact compensation coefficient of the new energy vehicle based on the environmental data and the change of the charge and discharge rate;

[0120] Step 406: The battery monitoring characteristics in the preliminary correction monitoring strategy are corrected based on the real-time characteristic impact compensation coefficient to obtain a customized monitoring solution corresponding to the current driving stage of the new energy vehicle battery.

[0121] The beneficial effects of the above technical solution: The present invention modifies the monitoring scheme of new energy vehicle batteries based on the characteristic impact compensation coefficient and the battery SOC change characteristics to obtain a customized monitoring scheme, integrates the battery status monitoring with the battery's working parameters (ambient temperature and charge and discharge rate) impact characteristics and the battery SOC change characteristics corresponding to driving behavior, adjusts the battery status monitoring strategy of energy vehicles, and formulates a monitoring scheme that conforms to the current actual working status of the battery, which is beneficial to improving the accuracy of battery status monitoring and the accuracy of SOC monitoring values, providing accurate endurance reference time for drivers and passengers, and facilitating early charging planning for drivers and passengers.

[0122] Embodiment 6:

[0123] On the basis of Example 5, after obtaining a customized monitoring solution, the following is further included:

[0124] Obtain the latest navigation route of new energy vehicles in real time, as well as the actual driving behavior characteristics of the driver corresponding to the different road conditions of the traveled sections corresponding to the latest navigation route;

[0125] According to the actual driving behavior characteristics, the driving strategy in the customized monitoring plan is corrected, and the corresponding customized monitoring plan is updated in real time according to the correction results.

[0126] The beneficial effects of the above technical solution are as follows: when the present invention monitors the battery of a new energy vehicle based on a customized solution, the latest navigation route of the new energy vehicle and the actual driving behavior characteristics of the driver corresponding to the different road conditions of the traveled section corresponding to the latest navigation route are obtained in real time; according to the actual driving behavior characteristics, the driving strategy in the customized monitoring solution is corrected, and the corresponding customized monitoring solution is updated in real time according to the correction result, the predicted driving strategy is automatically calibrated according to the actual driving behavior of the driver in the current driving process, and then the customized monitoring solution is adjusted and updated in real time according to the calibration result, so that the customized monitoring solution is more in line with the actual working condition of the battery, which is beneficial to improve the accuracy of battery status detection of new energy vehicles in the current driving process, thereby improving the accuracy of endurance prediction of new energy vehicles and providing a reliable basis for users' travel charging planning.

[0127] Embodiment 7:

[0128] On the basis of Example 5, in the process of monitoring the new energy vehicle battery based on the latest customized monitoring solution, it includes:

[0129] Obtain the current SOC value of the new energy vehicle, and based on the driving strategy corresponding to the latest navigation route of the new energy vehicle and the battery SOC change characteristics, determine whether the new energy vehicle can complete the full driving task corresponding to the latest navigation route;

[0130] If possible, continue navigation according to the latest driving route;

[0131] Otherwise, an insufficient power warning is generated, and the nearest charging equipment is queried based on the navigation map, and the candidate charging equipment is screened based on the new energy driving direction;

[0132] The positions of the charging devices to be selected are marked on the latest navigation route. Based on the position marking results, the remaining SOC value corresponding to each charging device to be selected is predicted. The charging devices to be selected with remaining SOC values ​​greater than preset values ​​are displayed as alternative devices on the navigation map corresponding to the latest navigation route, and the alternative devices on the latest navigation route are highlighted.

[0133] In this embodiment, when the candidate devices are displayed on the navigation map corresponding to the latest navigation route, the remaining SOC value corresponding to each candidate device will be displayed, so that the driver can make a selection according to the actual situation. The remaining SOC value refers to the SOC value corresponding to the battery of the new energy vehicle when it drives to a charging device.

[0134] The beneficial effects of the above technical solution are as follows: the present invention is based on the current SOC value of the new energy vehicle, according to the driving strategy corresponding to the latest navigation route of the new energy vehicle, combined with the battery SOC change characteristics, to judge whether the new energy vehicle can complete the full driving task corresponding to the latest navigation route, to achieve the prediction of the battery life, and also to provide a basis for the charging judgment during the driving of the new energy vehicle. When it is determined that the full driving task corresponding to the latest navigation route cannot be completed by relying on the power corresponding to the current SOC, the best charging equipment on the way forward is automatically selected for the driver for recommendation, which can replenish the stored energy for the new energy vehicle in time, reduce the probability of the driver deviating during the charging process, and minimize the distance traveled by the new energy vehicle to the destination.

[0135] Embodiment 8:

[0136] On the basis of Example 5, when the new energy vehicle is determined to be able to complete the full driving task corresponding to the latest navigation route, it includes:

[0137] Query the charging equipment near the destination of the new energy vehicle, take the charging equipment within the preset range of the destination as the target charging equipment, and predict the arrival time of the new energy vehicle based on the driving strategy corresponding to the latest navigation route;

[0138] Based on the big data analysis results of the target charging equipment, the working status of each target charging equipment within the real-time arrival time is predicted, and the location of the idle charging equipment is determined;

[0139] The location of the idle charging equipment is sent to the display terminal as the recommended destination parking location for the new energy vehicle for display, and a synchronous voice broadcast is performed.

[0140] In this embodiment, the preset range refers to a radius of several kilometers around the destination. This value can be set by the user or the default value can be used.

[0141] The beneficial effects of the above technical solution are as follows: when the new energy vehicle is judged to be able to complete the full driving task corresponding to the latest navigation route, the present invention queries the charging equipment near the destination of the new energy vehicle, takes the charging equipment within the preset range of the destination as the target charging equipment, and predicts the arrival time of the new energy vehicle based on the driving strategy corresponding to the latest navigation route; based on the big data analysis results of the target charging equipment, predicts the working status of each target charging equipment within the real-time arrival time, and determines the position of the idle charging equipment; sends the position of the idle charging equipment as the recommended destination parking position of the new energy vehicle to the display end for display, and performs synchronous voice broadcast, automatically screens and recommends the location for the driver to charge immediately after the user arrives, provides guarantee for the timely replenishment of the storage energy of the car battery, and is conducive to improving the user experience.

[0142] Embodiment 9:

[0143] Based on Example 4, a customized state monitoring method for a new energy vehicle battery further includes:

[0144] Determine the current charge and discharge cycle duration of the new energy vehicle battery based on multiple SOC processing curves, and generate a battery repair warning when the current charge and discharge cycle duration is less than or equal to the average driving time of the driver;

[0145] Otherwise, based on the red marked position, the total usage lengths of the phases corresponding to the normal SOC phase and the abnormal SOC phase are determined respectively, and the normal power supply ratio of the battery is calculated;

[0146] When the normal battery power supply ratio is less than the preset threshold, a battery repair warning is generated.

[0147] In this embodiment, the average driving time refers to the average value of the driver's daily driving time within a preset effective period.

[0148] In this embodiment, the preset threshold value ranges from [0, 0.5].

[0149] In this embodiment, the normal power supply ratio of the battery refers to the ratio of the total use length of the stage corresponding to the normal SOC stage to the total use length of the stage corresponding to the abnormal SOC stage. The total use length of the stage refers to the total time corresponding to the normal or abnormal change of the battery SOC in the entire battery charge and discharge cycle.

[0150] The beneficial effects of the above technical solution: the present invention determines the current charge and discharge cycle duration of the new energy vehicle battery based on multiple SOC processing curves, and compares the current charge and discharge cycle duration with the average driving time of the driver, so as to judge whether the new energy vehicle battery needs to be replaced, and ensure that the battery life can meet the basic needs of the driver. If it does, the driver is reminded to repair and replace the vehicle battery. While ensuring that the battery life can meet the basic needs of the driver, based on the red mark position, the total usage length of the stages corresponding to the SOC normal stage and the SOC abnormal stage are determined respectively, and the normal power supply ratio of the battery is calculated; when the normal power supply ratio of the battery is less than the preset threshold, a battery repair warning is generated, which is beneficial for the driver to promptly discover the problems of fast battery consumption and severe damage, and reduce the probability of the driver being unable to move due to lack of power halfway during a long journey.

[0151] Embodiment 10:

[0152] The present invention provides a customized state monitoring system for new energy vehicle batteries, such as Figure 6 As shown, including:

[0153] An operation data processing module is used to obtain historical operation data of new energy vehicle batteries based on a cloud database, and perform data marking processing to obtain marked historical data;

[0154] The data intelligent analysis module is used to perform intelligent analysis on the marked historical data, determine the impact of ambient temperature and charge and discharge rate on the SOC of new energy vehicle batteries, and obtain the characteristic impact compensation coefficient;

[0155] The battery feature extraction module is used to extract the battery SOC change features corresponding to the driving behavior of the marked historical data;

[0156] The solution optimization and customization module is used to modify the monitoring solution of new energy vehicle batteries according to the characteristic impact compensation coefficient and the battery SOC change characteristics to obtain a customized monitoring solution.

[0157] The beneficial effects of the above technical solution are as follows: the present invention obtains the historical operation data of the new energy vehicle battery based on the cloud database, and performs data marking processing to obtain the marked historical data, and then performs intelligent analysis on the marked historical data to determine the influence of ambient temperature and charge and discharge rate on the SOC of the new energy vehicle battery, obtain the characteristic influence compensation coefficient, and extract the battery SOC change characteristics corresponding to the driving behavior of the marked historical data, and finally, according to the characteristic influence compensation coefficient and the battery SOC change characteristics, the monitoring scheme of the new energy vehicle battery is corrected to obtain a customized monitoring scheme, and the battery status monitoring is integrated with the battery working parameters (ambient temperature and charge and discharge rate) influence characteristics and the battery SOC change characteristics corresponding to the driving behavior, and the battery status monitoring strategy of the energy vehicle is adjusted to formulate a monitoring scheme that conforms to the current actual working state of the battery, which is conducive to improving the accuracy of battery status monitoring and the accuracy of SOC monitoring values, providing accurate endurance reference time for drivers and passengers, and facilitating the drivers and passengers to plan charging in advance.

[0158] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A customized state monitoring method for new energy vehicle batteries, It is characterized in that include: Based on the cloud database, the historical operation data of new energy vehicle batteries is obtained, and data labeling is performed to obtain labeled historical data; Intelligently analyze the marked historical data to determine the impact of ambient temperature and charge / discharge rate on the SOC of new energy vehicle batteries and obtain the characteristic impact compensation coefficient; Extract the battery SOC change characteristics corresponding to driving behavior from the marked historical data; According to the characteristic impact compensation coefficient and the battery SOC change characteristics, the monitoring plan for new energy vehicle batteries is modified to obtain a customized monitoring plan; Among them, based on the cloud database, the historical operation data of the current new energy vehicle battery is obtained, including: Obtain historical operating data of new energy vehicle batteries within a preset effective period from the cloud database; The historical operation data is split according to the charge and discharge cycle to obtain the historical operation data corresponding to multiple charging cycles; Mark the ambient temperature and charge / discharge rate in each period of the historical operation data corresponding to each charge / discharge cycle to obtain marked historical data; Among them, intelligent analysis is performed on the marked historical data to determine the impact of ambient temperature and charge and discharge rate on the SOC of new energy vehicle batteries, and obtain characteristic impact compensation coefficients, including: Based on the temperature tags of the marked historical data, the marked historical data of multiple charge and discharge cycles are aligned to obtain the temperature alignment result, and based on the temperature alignment result and the preset feature extraction model, the first influencing feature of the charge and discharge rate on the SOC transformation of the new energy vehicle battery is extracted; Based on the rate labels of the marked historical data, the marked historical data of multiple charge and discharge cycles are aligned to obtain the rate alignment results. Based on the rate alignment results and the preset feature extraction model, the second influence feature of the ambient temperature on the SOC transformation of the new energy vehicle battery is extracted; Obtain the normal charge and discharge rate characteristics and standard operating temperature characteristics of the new energy vehicle battery, perform a first influencing characteristic coefficient evaluation on the temperature alignment results corresponding to each ambient temperature based on the normal charge and discharge rate characteristics, and obtain the charge and discharge rate influence coefficient, perform a second influencing characteristic coefficient evaluation on the multiple alignment results corresponding to each charge and discharge multiple based on the standard operating temperature characteristics, and obtain the ambient temperature influence coefficient; Based on the first influencing feature and the second influencing feature, determining the combined feature corresponding to each marked historical data, and generating the combined feature impact compensation coefficient corresponding to the marked historical data according to the combined feature, combined with the charge and discharge rate impact coefficient and the ambient temperature impact coefficient; Based on the value ranges of the first influencing feature and the second influencing feature in the combined feature, the marked historical data is classified to obtain multiple feature influence category sets, and the combined feature influence compensation coefficients in each feature influence category set are averaged to obtain feature influence compensation coefficients corresponding to different feature influence category sets; Among them, the battery SOC change feature extraction corresponding to the driving behavior of the marked historical data includes: Based on the marked historical data, multiple battery SOC transformation curves corresponding to multiple charge and discharge cycles are generated, and the change rates of the multiple battery SOC transformation curves are marked respectively. Based on the change rate marking results, the rate mutation point corresponding to the new energy vehicle battery is determined; Obtain the historical vehicle driving data of new energy vehicles corresponding to each charging and discharging cycle, determine the vehicle driving behavior corresponding to each rate mutation point based on the time correspondence between the historical vehicle driving data and the marked historical data, generate a behavior label and add it to the corresponding rate mutation point to obtain the SOC processing curve; Compare the rate mutation points of multiple SOC processing curves to determine whether there is a power mutation in the new energy vehicle battery. If so, mark the power mutation position in red, and divide the use of the new energy vehicle battery into stages according to the red marked position to obtain the SOC normal stage and SOC abnormal stage; Based on multiple SOC processing curves, the battery monitoring data change characteristics corresponding to different driving behaviors are extracted for the SOC normal stage and the SOC abnormal stage; Generate battery SOC change characteristics based on the gradient division results of the use stages of new energy vehicle batteries and the battery monitoring data change characteristics corresponding to each use stage; Among them, according to the characteristic impact compensation coefficient and the battery SOC change characteristics, the monitoring plan of the new energy vehicle battery is modified to obtain a customized monitoring plan, including: Obtain the current monitoring scheme of the new energy vehicle battery, re-divide the current use phase gradient of the current monitoring scheme based on the use phase gradient corresponding to the battery SOC change characteristics, and simultaneously obtain the battery monitoring characteristics corresponding to each driving behavior in the current monitoring scheme; Comparing the battery monitoring characteristics with the battery monitoring data change characteristics in the battery SOC change characteristics to obtain driving behavior monitoring differences; Based on the differences in driving behavior monitoring, the driving behavior monitoring strategies at different use stages are modified to obtain the preliminary modified monitoring strategy for new energy vehicle batteries; Obtaining environmental data and a navigation driving route of the new energy vehicle, and predicting the driver's driving strategy on the navigation driving route based on the navigation driving route and the driver's driving behavior preference; According to the driving strategy, predict the change of the charge and discharge rate during driving, and determine the compensation coefficient of the real-time characteristic impact of the new energy vehicle based on the environmental data and the change of the charge and discharge rate; The battery monitoring characteristics in the preliminary correction monitoring strategy are corrected based on the real-time characteristic impact compensation coefficient to obtain a customized monitoring solution corresponding to the current driving stage of the new energy vehicle battery.

2. A customized state monitoring method for new energy vehicle batteries according to claim 1, It is characterized in that When you get a customized monitoring solution, it also includes: Obtain the latest navigation route of new energy vehicles in real time, as well as the actual driving behavior characteristics of the driver corresponding to the different road conditions of the traveled sections corresponding to the latest navigation route; According to the actual driving behavior characteristics, the driving strategy in the customized monitoring plan is corrected, and the corresponding customized monitoring plan is updated in real time according to the correction results.

3. A customized state monitoring method for new energy vehicle batteries according to claim 1, It is characterized in that In the process of monitoring new energy vehicle batteries based on the latest customized monitoring solution, it includes: Obtain the current SOC value of the new energy vehicle, and based on the driving strategy corresponding to the latest navigation route of the new energy vehicle and the battery SOC change characteristics, determine whether the new energy vehicle can complete the full driving task corresponding to the latest navigation route; If possible, continue navigation according to the latest driving route; Otherwise, an insufficient power warning is generated, and the nearest charging equipment is queried based on the navigation map, and the candidate charging equipment is screened based on the new energy driving direction; The positions of the charging devices to be selected are marked on the latest navigation route. Based on the position marking results, the remaining SOC value corresponding to each charging device to be selected is predicted. The charging devices to be selected with remaining SOC values ​​greater than preset values ​​are displayed as alternative devices on the navigation map corresponding to the latest navigation route, and the alternative devices on the latest navigation route are highlighted.

4. A customized state monitoring method for new energy vehicle batteries according to claim 1, It is characterized in that When a new energy vehicle is judged to be able to complete the full driving task corresponding to the latest navigation route, it includes: Query the charging equipment near the destination of the new energy vehicle, take the charging equipment within the preset range of the destination as the target charging equipment, and predict the arrival time of the new energy vehicle based on the driving strategy corresponding to the latest navigation route; Based on the big data analysis results of the target charging equipment, the working status of each target charging equipment within the real-time arrival time is predicted, and the location of the idle charging equipment is determined; The location of the idle charging equipment is sent to the display terminal as the recommended destination parking location for the new energy vehicle for display, and a synchronous voice broadcast is performed.

5. A customized state monitoring method for new energy vehicle batteries according to claim 1, It is characterized in that Also includes: Determine the current charge and discharge cycle duration of the new energy vehicle battery based on multiple SOC processing curves, and generate a battery repair warning when the current charge and discharge cycle duration is less than or equal to the average driving time of the driver; Otherwise, based on the red marked position, the total usage lengths of the phases corresponding to the normal SOC phase and the abnormal SOC phase are determined respectively, and the normal power supply ratio of the battery is calculated; When the normal battery power supply ratio is less than the preset threshold, a battery repair warning is generated.

6. A customized state monitoring system for new energy vehicle batteries, It is characterized in that include: An operation data processing module is used to obtain historical operation data of new energy vehicle batteries based on a cloud database, and perform data marking processing to obtain marked historical data; The data intelligent analysis module is used to perform intelligent analysis on the marked historical data, determine the impact of ambient temperature and charge and discharge rate on the SOC of new energy vehicle batteries, and obtain the characteristic impact compensation coefficient; The battery feature extraction module is used to extract the battery SOC change features corresponding to the driving behavior of the marked historical data; The solution optimization and customization module is used to modify the monitoring solution of new energy vehicle batteries according to the characteristic impact compensation coefficient and the battery SOC change characteristics to obtain a customized monitoring solution; Among them, the method for the operation data processing module to obtain the historical operation data of the current new energy vehicle battery based on the cloud database includes: Obtain historical operating data of new energy vehicle batteries within a preset effective period from the cloud database; The historical operation data is split according to the charge and discharge cycle to obtain the historical operation data corresponding to multiple charging cycles; Mark the ambient temperature and charge / discharge rate in each period of the historical operation data corresponding to each charge / discharge cycle to obtain marked historical data; Among them, the data intelligent analysis module performs intelligent analysis on the marked historical data, determines the impact of ambient temperature and charge and discharge rate on the SOC of new energy vehicle batteries, and obtains the method of characteristic impact compensation coefficient, including: Based on the temperature tags of the marked historical data, the marked historical data of multiple charge and discharge cycles are aligned to obtain the temperature alignment result, and based on the temperature alignment result and the preset feature extraction model, the first influencing feature of the charge and discharge rate on the SOC transformation of the new energy vehicle battery is extracted; Based on the rate labels of the marked historical data, the marked historical data of multiple charge and discharge cycles are aligned to obtain the rate alignment results. Based on the rate alignment results and the preset feature extraction model, the second influence feature of the ambient temperature on the SOC transformation of the new energy vehicle battery is extracted; Obtain the normal charge and discharge rate characteristics and standard operating temperature characteristics of the new energy vehicle battery, perform a first influencing characteristic coefficient evaluation on the temperature alignment results corresponding to each ambient temperature based on the normal charge and discharge rate characteristics, and obtain the charge and discharge rate influence coefficient, perform a second influencing characteristic coefficient evaluation on the multiple alignment results corresponding to each charge and discharge multiple based on the standard operating temperature characteristics, and obtain the ambient temperature influence coefficient; Based on the first influencing feature and the second influencing feature, determining the combined feature corresponding to each marked historical data, and generating the combined feature impact compensation coefficient corresponding to the marked historical data according to the combined feature, combined with the charge and discharge rate impact coefficient and the ambient temperature impact coefficient; Based on the value ranges of the first influencing feature and the second influencing feature in the combined feature, the marked historical data is classified to obtain multiple feature influence category sets, and the combined feature influence compensation coefficients in each feature influence category set are averaged to obtain feature influence compensation coefficients corresponding to different feature influence category sets; The method for extracting the battery SOC change characteristics corresponding to the driving behavior from the marked historical data by the battery feature extraction module includes: Based on the marked historical data, multiple battery SOC transformation curves corresponding to multiple charge and discharge cycles are generated, and the change rates of the multiple battery SOC transformation curves are marked respectively. Based on the change rate marking results, the rate mutation point corresponding to the new energy vehicle battery is determined; Obtain the historical vehicle driving data of new energy vehicles corresponding to each charging and discharging cycle, determine the vehicle driving behavior corresponding to each rate mutation point based on the time correspondence between the historical vehicle driving data and the marked historical data, generate a behavior label and add it to the corresponding rate mutation point to obtain the SOC processing curve; Compare the rate mutation points of multiple SOC processing curves to determine whether there is a power mutation in the new energy vehicle battery. If so, mark the power mutation position in red, and divide the use of the new energy vehicle battery into stages according to the red marked position to obtain the SOC normal stage and SOC abnormal stage; Based on multiple SOC processing curves, the battery monitoring data change characteristics corresponding to different driving behaviors are extracted for the SOC normal stage and the SOC abnormal stage; Generate battery SOC change characteristics based on the gradient division results of the use stages of new energy vehicle batteries and the battery monitoring data change characteristics corresponding to each use stage; Among them, the solution optimization and customization module modifies the monitoring solution of the new energy vehicle battery according to the characteristic impact compensation coefficient and the battery SOC change characteristics, and obtains a customized monitoring solution method, including: Obtain the current monitoring scheme of the new energy vehicle battery, re-divide the current use phase gradient of the current monitoring scheme based on the use phase gradient corresponding to the battery SOC change characteristics, and simultaneously obtain the battery monitoring characteristics corresponding to each driving behavior in the current monitoring scheme; Comparing the battery monitoring characteristics with the battery monitoring data change characteristics in the battery SOC change characteristics to obtain driving behavior monitoring differences; Based on the differences in driving behavior monitoring, the driving behavior monitoring strategies at different use stages are modified to obtain the preliminary modified monitoring strategy for new energy vehicle batteries; Obtaining environmental data and a navigation driving route of the new energy vehicle, and predicting the driver's driving strategy on the navigation driving route based on the navigation driving route and the driver's driving behavior preference; According to the driving strategy, predict the change of the charge and discharge rate during driving, and determine the compensation coefficient of the real-time characteristic impact of the new energy vehicle based on the environmental data and the change of the charge and discharge rate; The battery monitoring characteristics in the preliminary correction monitoring strategy are corrected based on the real-time characteristic impact compensation coefficient to obtain a customized monitoring solution corresponding to the current driving stage of the new energy vehicle battery.

Images