Battery management method, management system, medium and program product

Abstract

The invention provides a battery management method, a management system, a medium and a program product, and relates to the technical field of battery management. The method comprises the steps that the traffic congestion condition of a road where a current vehicle is located is obtained in real time through a vehicle-mounted camera, whether the vehicle is located in a congested road section or not is judged according to vehicle speed information, and when it is determined that the vehicle enters a congested state, the outside air temperature, the battery temperature and operation parameters are obtained in real time; inputting into a battery consumption judgment model which is obtained through machine learning training in advance and is used in different congestion environments, calculating a relatively accurate electric quantity consumption predicted value according to various environmental parameters, and judging the duration of the congestion road section by combining with a third party; and finally, according to the congestion duration, the current electric quantity condition of the battery and the electric quantity consumption value predicted by the model, the power utilization strategy of the battery is intelligently and automatically adjusted, and reasonable power utilization in the congestion environment is realized. According to the method, the actual consumption of the battery can be evaluated more accurately, and a more reasonable and reliable battery power utilization strategy is formulated accordingly.

Description

Technical Field

[0001] The present application relates to the field of battery management technology, and in particular to a battery management method, management system, medium and program product. Background Art

[0002] With the widespread popularity of electric vehicles, battery management has become a key factor affecting electric vehicle performance and user experience. During vehicle driving, different road conditions and environmental conditions have a significant impact on battery power consumption. How to accurately manage battery power to increase driving range and ensure normal operation of the vehicle has become an urgent problem to be solved.

[0003] At present, the common battery management method mainly relies on the vehicle's built-in sensors to obtain the basic parameters of the battery, such as voltage, current and other information, and then calculates the power consumption based on the vehicle's driving speed and the preset fixed energy consumption coefficient. According to the calculation results, when the power is lower than a certain threshold, an early warning will be issued and some simple energy-saving measures will be taken, such as reducing the power of the air conditioner.

[0004] However, this management method based on mileage and average power consumption is relatively crude. When the vehicle enters special road conditions such as congested sections, the power consumption will increase significantly and be very different from normal driving due to the frequent start and stop of the vehicle. At the same time, the ambient temperature will also have a significant impact on battery performance and power consumption, and the existing methods are difficult to take these factors into account in a timely and accurate manner. In complex and changeable actual driving scenarios, it is difficult to accurately predict power consumption, resulting in unreasonable power use strategies, which may cause the battery to be exhausted prematurely or fail to fully utilize the battery capacity. Summary of the invention

[0005] The present application provides a battery management method, management system, medium and program product for real-time monitoring of battery status, accurate prediction of power consumption, and intelligent adjustment of battery power usage strategy, thereby improving battery usage efficiency.

[0006] In the first aspect, the present application provides a battery management method, which is applied to a management system, and the method includes: obtaining the traffic conditions of the road where the current vehicle is located in real time through a vehicle-mounted camera; determining whether the current vehicle has entered a congested section in combination with the speed information of the current vehicle; if it is determined that the vehicle has entered the congested section, obtaining the outdoor temperature information, battery temperature and battery operation status in real time in combination with sensors; inputting the outdoor temperature information, the battery temperature and the battery operation status into a preset power consumption judgment model to determine a power consumption prediction value, and the power consumption judgment model is obtained by performing machine learning training on the battery operation status of vehicles under different congestion conditions under multiple environmental parameters in advance; after determining the congestion duration of the congested section through a third-party platform, automatically adjusting the battery power consumption strategy according to the congestion duration, the current battery power status and the power consumption prediction value.

[0007] By adopting the above technical solution, the battery power consumption strategy can be automatically adjusted according to the power consumption in special congestion scenarios to achieve a more reasonable power consumption method. Compared with the traditional simple mileage power consumption calculation method, this technical solution can fully consider the factors affecting the actual battery consumption such as road congestion status and external ambient temperature, and make accurate power consumption predictions, thereby formulating a more reasonable and reliable battery power strategy, improving battery efficiency, and extending the range of electric vehicles.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after the step of inputting the outside temperature information, the battery temperature and the battery operating conditions into a preset power consumption judgment model to determine the power consumption prediction value, it also includes: labeling and classifying the driving data under multiple different weather conditions and different road conditions collected in advance according to weather and road conditions; after obtaining the data of the battery charging and discharging process under each condition, adjusting the power consumption judgment model; when predicting power consumption, inputting the current weather conditions and road conditions into the power consumption judgment model to obtain an optimized power consumption prediction value.

[0009] By adopting the above technical solution, the power consumption model can adapt more accurately to different changes in external conditions. By inputting the current weather and road conditions parameters, a more accurate power consumption forecast value can be obtained, thereby formulating a more reasonable power consumption strategy, maximizing the battery life, and improving the economy and ease of use of electric vehicles.

[0010] In combination with some embodiments of the first aspect, in some embodiments, after the step of inputting the outside temperature information, the battery temperature and the battery operating status into a preset power consumption judgment model to determine the power consumption prediction value, it also includes: continuously collecting the user's travel data, the travel data including the time, route and driving speed changes of each trip; continuously collecting the user's usage parameters of the vehicle-mounted equipment, and using the usage parameters as power consumption habit data; determining the user's personalized battery consumption model based on a machine learning algorithm combined with the power consumption judgment model, the personalized battery consumption model is used to learn the battery consumption pattern corresponding to the user's travel habits and power consumption habits; when predicting the user's power consumption, the personalized battery consumption model is integrated with the general power consumption judgment model to generate a final power consumption judgment model that matches the user.

[0011] By adopting the above technical solution, the battery consumption of different users can be predicted more accurately, and the personalized model can be integrated with the general model to generate the final model. The personalized characteristics of different users can be taken into account to the greatest extent possible, so that the battery power consumption strategy is more in line with user habits, thereby improving battery efficiency and extending driving range.

[0012] In combination with some embodiments of the first aspect, in some embodiments, when predicting the power consumption of a user, the personalized battery consumption model and the general power consumption judgment model are merged to generate a final power consumption judgment model that matches the user. The step also includes: inputting the real-time outdoor temperature information, the battery temperature and the battery operation status into the final power consumption judgment model to obtain a new power consumption strategy; real-time monitoring of various change data of the battery after the new power consumption strategy is adopted, the change data including changes in electrical parameters and changes in battery temperature; comparing and analyzing the monitored data with the data of adopting the new power consumption strategy to evaluate whether there are any abnormalities in the strategy adjustment; if there are any abnormalities, restoring the new power consumption strategy to the state before adjustment, and feeding back the abnormality to the final power consumption judgment model for adjustment.

[0013] By adopting the above technical solution, the rationality of the strategy adjustment can be evaluated. If there is an anomaly in the strategy adjustment that causes battery performance to deteriorate, the strategy adjustment can be rolled back in time to avoid battery damage, and the anomaly can be fed back to the model for self-optimization, which can continuously improve the intelligence level of battery management.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after determining the congestion duration of the congested road section through a third-party platform, after the step of automatically adjusting the battery power usage strategy according to the congestion duration, the current battery power status and the power consumption prediction value, it also includes: monitoring the real-time remaining power of the battery and the current location coordinate information of the vehicle; when the real-time remaining power is lower than the preset minimum power threshold, determining the charging pile information within a preset range according to the location coordinate information; and sending the charging pile information to the vehicle terminal for display.

[0015] By adopting the above technical solution, users can be guided to reach the charging point to charge the battery as quickly as possible, avoiding driving difficulties caused by exhaustion of power, and improving the reliability and safety of electric vehicles.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after determining the congestion duration of the congested road section through a third-party platform, after the step of automatically adjusting the battery power usage strategy according to the congestion duration, the current battery power status and the power consumption prediction value, it also includes: real-time monitoring of battery temperature and current changes, and detecting whether the battery temperature continues to rise and exceeds the temperature threshold; if it exceeds the temperature threshold, it is determined that abnormal heating exists, and a control instruction is sent to the vehicle-mounted equipment, which is used to start the battery cooling system and reduce the power consumption of the vehicle-mounted equipment.

[0017] By adopting the above technical solution, the battery can be effectively prevented from being damaged by overheating, the battery can be ensured to be safe to use, and the battery life and the use cycle of the electric vehicle can be extended.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after determining the congestion duration of the congested road section through a third-party platform, after the step of automatically adjusting the battery power usage strategy according to the congestion duration, the current battery power status and the power consumption prediction value, it also includes: receiving real-time battery data reported by the vehicle terminal, the battery real-time data includes at least voltage, current and temperature parameters; if the battery real-time data exceeds the preset battery performance standard range, it is judged that the battery is abnormal; obtaining the user information of the battery, and querying the maintenance contact information reserved by the user according to the user information; sending a battery abnormality prompt to the user through the maintenance contact information to prompt the user to check and repair the battery.

[0019] By adopting the above technical solution, users can be reminded in time to check and maintain the battery, avoiding safety hazards caused by further expansion of battery failure and extending the battery life; the active battery abnormality prompt maintenance method can also enhance the user experience and make battery management more intelligent and user-friendly.

[0020] In a second aspect, the present application provides a management system, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the management system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0021] In a third aspect, the present application provides a computer-readable storage medium comprising instructions, which, when executed on a management system, causes the management system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, the present application provides a computer program product. When the computer program product is run on a management system, the management system executes the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The technology of judging congestion through cameras and vehicle speed information and predicting power consumption in combination with machine learning models has been adopted to effectively solve the technical problem that the existing technology cannot take into account the congestion status and various influencing factors, thereby achieving the technical effect of accurately predicting power consumption in congestion scenarios and formulating reasonable battery power consumption strategies.

[0024] 2. The technical means of building a user-personalized battery consumption model and integrating it with the general model to generate the final model effectively solves the technical problem that the existing technology cannot take into account the personalized characteristics of different users, thereby achieving the technical effect of making the battery power consumption strategy more in line with user usage habits and improving battery usage efficiency.

[0025] 3. The technical means of detecting the continuous rise in battery temperature and starting the cooling system to reduce power consumption has effectively solved the technical problem that the existing technology cannot prevent battery overheating, thereby achieving the technical effect of preventing battery overheating and damaging and ensuring the safe use of the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flowchart of the battery management method in the embodiment of the present application; Figure 2 is another flowchart of the battery management method in an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device of the management system in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0029] For ease of understanding, the following is a description of the process of the method provided by this implementation. Figure 1 , is a flow chart of the battery management method in an embodiment of the present application.

[0030] S101, obtaining the traffic conditions of the road where the vehicle is currently located in real time through the vehicle-mounted camera; The management system will call the camera equipment installed in the vehicle to capture the road traffic environment in front of and around the vehicle in real time. Specifically, the management system will control the camera to shoot in the driving direction at a set frequency, and use the image recognition algorithm to analyze each image and identify other vehicle targets in the image. Then, the management system will calculate the number of identified vehicle targets and compare it with the number of lanes on the road. If the number of vehicle targets detected in a single lane continues to exceed the preset value, it is determined that there is congestion in the lane. In addition to judging the number of vehicles in the lane, the management system will also analyze two consecutive images, calculate the displacement distance of each vehicle target between the images, and calculate the average displacement speed. If the calculated average displacement speed is lower than the preset speed threshold, it can also be judged as traffic congestion.

[0031] When judging the congestion status of a road, the management system also needs to comprehensively judge the number of lanes in which vehicles are traveling. For multi-lane urban highways, some lanes may be congested while other lanes are still unobstructed. To distinguish this situation, the management system needs to calculate the proportion of congested lanes to the total number of lanes after making a separate judgment on each lane. Only when the proportion of congested lanes exceeds the preset value can the road as a whole be determined to be congested.

[0032] S102, determining whether the current vehicle enters a congested road section based on the speed information of the current vehicle; The management system will collect the vehicle's speed sensor data in real time and obtain the vehicle's real-time speed information at a set frequency. The management system will continue to judge the changing trend of the speed information and the switching point of the congestion state. Specifically, the management system will set speed thresholds A, B and C (A>B>C) to judge the following states: If the speed remains above threshold A, it is judged to be a smooth state; if the speed drops to threshold B and lasts for more than T1, it is pre-judged to be about to enter congestion; if the speed further drops to threshold C and lasts for more than T2, it is officially judged to be in a congested state; if the speed rises to threshold B and lasts for more than T3, it is pre-judged to be about to leave the congestion; if the speed rises to threshold A and lasts for more than T4, it is officially judged to be out of the congestion.

[0033] The above judgment method can filter out the interference of short-term speed fluctuations on the judgment results by setting multi-level vehicle speed thresholds and time thresholds for congestion switching, accurately detect the state switching points where the vehicle enters and leaves congestion, and avoid missed detection or misjudgment. At the same time, when judging the congestion state switch, the management system will also combine the congestion condition of the road ahead judged by the camera in step S101. Only when the speed change trend of the vehicle itself and the congestion judgment result of the road ahead are consistent, will it be officially judged to enter or leave the congestion state. This fusion judgment mechanism can improve the accuracy and reliability of the judgment.

[0034] S103, if it is determined that the vehicle has entered the congested road section, obtain the outside temperature information, battery temperature and battery operation status in real time by using sensors; The management system is connected to a temperature sensor for real-time detection of the ambient temperature outside the vehicle. Considering the wide range of temperature changes outside the vehicle, the management system uses a high-precision temperature sensor with a measurement range of -40°C to 85°C and an accuracy of ±0.5°C. By configuring the sampling frequency of the sensor to collect the temperature data outside the vehicle every 10 seconds, it can fully reflect the temperature changes and reduce data redundancy. The management system is also connected to a battery temperature sensor, which is installed inside the battery pack and directly contacts the battery surface for real-time monitoring of temperature changes during battery operation. The temperature sensor has a measurement range of -20°C to 60°C and an accuracy of ±1°C. Considering that the operating temperature of the battery changes relatively slowly, its temperature sampling frequency is configured to collect data every 30 seconds.

[0035] The operating status of the battery, including real-time voltage, current and other electrical performance parameters, as well as the remaining power percentage and battery charge and discharge status output by the battery management system. The above parameters reflect the current working status and charge change of the battery. The management system collects the battery operating parameters output by the battery management system at a set frequency through the vehicle bus.

[0036] S104, inputting the vehicle external temperature information, the battery temperature and the battery operation status into a preset power consumption judgment model to determine a power consumption prediction value, wherein the power consumption judgment model is obtained by machine learning training of battery operation status of vehicles under various environmental parameters and under different congestion conditions in advance; Before the battery is used for the first time, the management system will use a machine learning algorithm to build a power consumption judgment model. Specifically, the management system connects to the data training server to collect a large amount of battery working data under different ambient temperature conditions, as well as the corresponding vehicle location and speed information, which covers various evenly distributed congestion levels. The server uses a deep learning neural network to train a power consumption judgment model with the collected data. The input features of the model include: outside temperature, battery temperature, altitude, vehicle speed, voltage, current, SOC and other parameters. The output result is the predicted power consumption under this condition. The model contains structures such as convolutional layers and fully connected layers, which can automatically learn the complex mapping relationship between different features and power consumption. As the vehicle is used, the management system will continue to collect new battery data and feed it back to the server for model update and optimization, so that the judgment model can continuously adapt to the performance attenuation changes of the battery. The management system also considers the climate characteristics of different regions and builds a battery consumption sub-model based on regional division to make the prediction results more accurate.

[0037] During the actual use of the battery, the management system inputs various real-time working parameters into the model every set time period, obtains the predicted power consumption value within the set time period under the conditions, and calculates the estimated remaining available time of the battery based on the remaining battery power.

[0038] In some embodiments, driving data under various weather conditions may be collected in advance, such as sunny days, rainy days, snowy days, etc.; and driving data under different road conditions may be collected at the same time, such as highways, urban road conditions, etc. The collected driving data is labeled and classified according to the corresponding weather and road conditions to form a classified data set. For example, the data of driving on a snowy highway is labeled as the "snowy-highway" category. When the driving data after obtaining different classified data sets, the battery charging and discharging process data is extracted. These data can reflect the changes in the battery charging and discharging voltage, current, and capacity under the weather and road conditions. The battery charging and discharging characteristic data in the different classified data sets are input into the power consumption judgment model for training and optimization, so that the model can distinguish the battery consumption mode under different conditions. When predicting the power consumption of a certain trip, the weather conditions and road conditions are detected, and the corresponding conditions are input into the trained power consumption judgment model. In this way, the model can give an optimized power consumption prediction result according to the specific conditions.

[0039] S105: After determining the congestion duration of the congested road section through a third-party platform, automatically adjust the battery power usage strategy according to the congestion duration, the current battery power status and the power consumption prediction value.

[0040] The management system interacts with the third-party map navigation platform based on the Internet in real time. The navigation platform has a big data analysis engine that can predict the duration of a congested section of the road. After the management system determines that it has entered a congested state, it will send the real-time positioning data of the vehicle to the third-party navigation platform. Based on historical statistical data and the real-time traffic situation of the section, the navigation platform uses the congestion time prediction algorithm to calculate the estimated duration of the current congestion of the section, and feeds the result back to the management system. After receiving the congestion duration data, the management system combines the power consumption rate predicted in step S104 to calculate the remaining available time of the battery under the current power state, taking into account the additional consumption caused by congestion. If the remaining available time is lower than the time threshold T, it indicates that the power is seriously insufficient, and the management system will start the energy-saving mode, turn off some power-consuming devices, and reduce the system power to extend the battery life. If the remaining available time is greater than T but lower than the time threshold 2T, it indicates that the power is relatively tight. At this time, the management system will actively negotiate with other on-board systems to reduce their power consumption. For example, limit the output power of the music player and require the navigation system to turn off the auxiliary camera device. If the remaining available time is sufficient, the management system maintains the normal power consumption mode. At the same time, considering that the actual battery power consumption is reduced in congested conditions, the management system will appropriately increase the power consumption of other vehicle systems to improve the user experience.

[0041] In the embodiment of the present application, since the on-board camera and vehicle speed information are used to jointly determine the congested road sections, and the multi-sensor data is combined to input the machine learning model to predict the power consumption, and the congestion duration is determined according to the third-party platform to intelligently adjust the power usage strategy, it is possible to accurately understand the vehicle driving environment and battery operating conditions. The problem that the existing technology is difficult to take into account complex road conditions and environmental factors, resulting in inaccurate power prediction and poor power usage strategy, thereby achieving the technical effect of accurately predicting power in multiple and complex traffic scenarios, scientifically allocating battery power, and significantly improving the endurance stability and energy utilization of electric vehicles.

[0042] In some embodiments, the remaining power of the battery can also be monitored in real time, and the real-time remaining power data of the battery can be obtained through devices such as a power meter. At the same time, the current precise location coordinates of the vehicle can be obtained in real time through GPS or other positioning modules. The real-time remaining power is compared with the preset minimum power threshold to determine whether it is lower than the threshold. The minimum power threshold can be determined based on factors such as battery capacity and driving needs. When it is detected that the remaining power of the battery is lower than the minimum power threshold, the process of finding nearby charging piles is started. According to the precise location coordinates of the vehicle that have been obtained, combined with the charging pile location database, the available charging pile information within a certain range is searched and obtained. The search range can be set according to the vehicle model, driving speed, etc. The detailed information of the nearby charging piles searched, such as the location, distance from the current location, charging type, etc., is sent to the display screen of the vehicle terminal and other interfaces for display to the driver. According to the displayed charging pile information, the driver can choose the nearest charging pile navigation to charge, so as to avoid driving difficulties caused by exhaustion of power.

[0043] In some embodiments, the management system can receive real-time monitoring data of the battery uploaded by the vehicle terminal, which includes key parameters such as voltage, current, and temperature. According to the characteristic parameters of the battery, the standard normal working range of voltage, current, and temperature is preset, and the real-time monitoring value of the battery is compared with the standard working range to determine whether any parameters exceed the normal range. If so, the battery is determined to be abnormal. If the battery is determined to be abnormal, it is necessary to obtain the user information to which the battery belongs. The user data of the battery can be queried from the database to obtain the user's name, contact information, and other information. According to the queried user information, the battery-related maintenance contact information reserved by the user is found. Through the obtained maintenance contact information, such as mobile phone number, email address, etc., the battery abnormality prompt information is actively sent to the user. The prompt information may include a description of the abnormal situation, and a suggestion that the user should perform battery detection and maintenance as soon as possible. The user who receives the prompt information can troubleshoot the battery failure according to the suggestion, and perform maintenance or replacement in time to avoid further deterioration of the problem.

[0044] After combining the above content, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the battery management method in an embodiment of the present application.

[0045] S201, continuously collecting the user's travel data, where the travel data includes the time, route and travel speed change of each trip; Specifically, the management system needs to collect and record detailed data on each user's trip, including: 1) Travel time: record the total driving time from departure to arrival at the destination. 2) Driving route: record the specific route of the trip, including the name of the path passed, road type and other information. Positioning and recording can be performed through the on-board GPS. 3) Driving speed changes: real-time record of changes in vehicle speed during driving, including acceleration, deceleration, parking and other states. The collection frequency of speed information is not less than the set collection frequency. By collecting the above information for each trip, the user's travel habits can be analyzed, such as regular commuting time, fixed travel routes, etc., and the vehicle speed change model under different road conditions can also be obtained. After all travel data is uploaded to the server, it is associated, labeled and classified for storage.

[0046] S202, continuously collecting the user's usage parameters of the vehicle-mounted device and using the usage parameters as power usage habit data; The management system needs to call the vehicle CAN bus to collect the user's usage parameters for vehicle-mounted equipment such as air conditioning, seat massage, and multimedia entertainment. Specifically, the management system needs to collect the set temperature, set air volume, and wind direction mode of the air conditioner; collect the set mode, intensity level, and usage time of the seat massage device; collect the number of times multimedia entertainment devices such as music players are opened and the size of the playback volume; collect parameters such as the usage time of the audio and video system. In order to distinguish the differences in usage habits of different users, the management system needs to call the vehicle user identification module to automatically identify the current vehicle user, and distinguish and classify the device usage parameters of different users to form their respective power usage habit models. In order to achieve a seamless user identification process, this solution uses an infrared camera for face recognition, and combines it with voice recognition technology. When the user enters the car, the user is actively asked to speak to confirm, and the voice features are recorded and checked in real time, so that different users can be seamlessly identified. In addition to the CAN bus parameters, the management system also needs to call the vehicle-mounted sensor to monitor the changes in temperature and humidity in the car and the changes in the vehicle load in real time, and input them into the power usage habit model as parameters. If the temperature inside the car is detected to be continuously lower than the set temperature, or there is a large amount of load in the car, it can be judged that the air conditioning system is underpowered, which is a habit of high power consumption; on the contrary, if the temperature inside the car can quickly reach the set value, it is an energy-saving habit. All kinds of parameters are normalized and then input into the model.

[0047] S203, determining a personalized battery consumption model for the user according to a machine learning algorithm combined with the power consumption judgment model, where the personalized battery consumption model is used to learn the battery consumption pattern corresponding to the user's travel habits and power consumption habits; After the management system collects the detailed travel data and equipment power consumption parameters of the user on the server side, it needs to be input into the power consumption judgment model for training and learning to obtain the user's personalized battery consumption model. In order to achieve a more accurate modeling effect, this solution uses an improved deep learning model, including a convolutional neural network (CNN) to extract features from travel data, and designs a multi-layer LSTM network to learn the temporal correlation of data, and finally establishes a data mapping relationship for personalized user behavior. Compared with the simple multi-layer perceptron structure, this deep network can extract high-dimensional features from travel data, and capture long-term correlations through memory units, more accurately reflecting the user's personalized travel mode and battery consumption change law. In order to achieve incremental training and continuous optimization of the model, the management system needs to design an incremental learning mechanism. After each new travel and power consumption data of the user is collected, the parameters of the model are adjusted to adapt to the changes in the user's behavior pattern to avoid the model from being too dependent on the initial data and becoming invalid. At the same time, when new data of users in extreme weather environments is collected, such as high temperature or severe cold, the model will also adjust the calculation method of battery consumption to adapt to the battery's operating rules in extreme environments. Based on this incremental learning mechanism, the personalized battery consumption model can continuously optimize itself and continuously improve the prediction accuracy.

[0048] S204: when predicting the power consumption of the user, the personalized battery consumption model and the general power consumption judgment model are integrated to generate a final power consumption judgment model that matches the user; The management system takes the personalized battery consumption model and the general battery consumption judgment model as input, and after model fusion operation, outputs a power consumption judgment model that is personalized and optimized for the current user. The management system uses a fusion method based on the attention mechanism, which can dynamically learn the importance weights of the two models. Specifically, the personalized model mainly provides user personalized parameters, which have a higher role in describing the user's power consumption pattern, and therefore will obtain a higher attention weight; while the common parameters such as vehicle platform parameters provided by the general model have a smaller weight. As the amount of data accumulated by the personalized model increases, its attention weight will further increase, thereby generating a final judgment model that tends to be personalized for the user. Compared with simple model superposition, the attention fusion mechanism can realize dynamic and nonlinear model fusion, so that the generated final judgment model not only considers general constraints, but also fully reflects personalized characteristics.

[0049] In addition to model-level fusion, the management system can also perform feature-level fusion. That is, the personalized model and the general model are trained independently first, but when generating the final judgment model, the high-dimensional features extracted from the two models are spliced ​​as new feature inputs, and then the power consumption judgment model with fused features is trained. This method can make full use of the knowledge learned independently by the two models, and fuse a complete feature description with both general constraints and personalized features, which is used as an enhanced input to improve the prediction performance of the final model.

[0050] S205, inputting the real-time acquired outside temperature information, the battery temperature and the battery operation status into the final power consumption judgment model to obtain a new power consumption strategy; The management system can make accurate power predictions in real time based on the user-personalized final power consumption judgment model generated in this step. Specifically, after inputting the external temperature, battery temperature, current, voltage and other data collected by the on-board sensors in real time into the model, the predicted value of battery consumption in the next driving cycle can be obtained. The management system compares the predicted value with the current power status and the expected driving range, and determines whether to implement the enhanced power consumption mode based on the remaining power to allow users to obtain a better experience using the on-board equipment, or to implement the energy-saving power consumption mode to extend the driving range as much as possible. If the remaining power is not sufficient, the power consumption of the on-board equipment will be reduced, and the adjustment range of the power consumption strategy will also be personalized based on the user's personal preferences.

[0051] S206, real-time monitoring of various change data after the battery adopts the new power usage strategy, the change data including changes in electrical parameters and battery temperature; The management system integrates a high-precision battery management system, which can perform high-frequency sampling and monitoring of battery voltage, current, temperature and other parameters. In terms of voltage monitoring, the management system can be configured with a high-precision voltage tester with multi-channel synchronous sampling, with an accuracy of 0.1mV. Through multi-channel sampling, the influence of crosstalk can be eliminated to ensure measurement accuracy. Current monitoring uses a thermistor current sensor, with a response rate of μs level, which can detect fast transient current changes; the temperature monitor can detect the temperature rise of the battery cell, and the battery management system can obtain the battery usage in real time.

[0052] After obtaining a large amount of monitoring data, the management system will immediately perform feature extraction and parameter mapping to obtain the time domain curves and frequency domain spectra of key electrical parameters such as the battery's charge and discharge charge, AC impedance, etc. And compare it with the reference curve before executing the power consumption strategy to determine whether there are abnormal mutations or drastic changes in parameters such as current consumption and AC impedance. At the same time, the management system also needs to conduct a special analysis of the temperature changes of the battery cells. Since the thermal characteristics of the battery cell determine the safety and health of the battery, any overheating risks need to be checked in a timely manner. The system will draw a thermal curve of the temperature of each battery cell over time, and compare it with the thermal curve under normal working conditions. If a battery cell exceeds the safe temperature range, or the temperature rise rate abnormally exceeds the threshold, it will trigger an early warning of battery failure and potential safety risks.

[0053] S207, comparing and analyzing the monitored data with the data of adopting the new power consumption strategy, and evaluating whether there is any abnormality in the strategy adjustment; After obtaining real-time monitoring data, the management system needs to conduct in-depth comparative analysis to determine whether the new strategy causes abnormal battery performance. The main comparative analysis content includes: the management system compares the battery charge and discharge current curve obtained by monitoring with the baseline current curve before the implementation of the new strategy. Through curve fitting and parameter mapping technology, the characteristic parameters of the current curve, such as average current, peak current, high-frequency components, etc., are extracted. Determine whether these parameters have abnormal changes beyond the normal range. For example, if the average current increases steadily by more than 15%, it may indicate that the strategy causes increased battery loss. If abnormal parameter changes are detected, the strategy fault code is recorded. The system also needs to focus on comparing the battery temperature rise curve obtained by monitoring, mainly detecting characteristic parameters such as temperature rise peak value and temperature rise slope. If the temperature rise is too fast but the current is not abnormal, it may indicate that there is a local heating problem inside the battery. Relying on accurate temperature curve analysis, the thermal fault of the battery can be found. The system calculates and compares the absolute power loss and loss rate of the battery before and after the strategy to check whether the strategy causes the system efficiency to decrease and the power is over-consumed. If abnormal power loss is detected, the fault code is recorded.

[0054] If it is determined that there is an abnormality, step S208 is executed; If it is determined that there is no abnormality, step S209 is executed.

[0055] S208, restoring the new power consumption strategy to the state before adjustment, and feeding back the anomaly to the final power consumption judgment model for adjustment; Once the evaluation results determine that the new strategy is abnormal, the management system will immediately execute the strategy rollback program and send an abnormal prompt message to the vehicle terminal to prompt the parameter settings of the vehicle air conditioner and other equipment to be restored to the default state before the strategy adjustment to ensure the safe operation of the battery. At the same time, the management system will automatically generate a strategy abnormality report, which records in detail the hardware environment parameters of the abnormality, the comparison of battery performance data before and after the strategy adjustment, the determined abnormal cause code and other information. The report is fed back to the abnormal case library of the final power consumption judgment model in a standard format. After obtaining a new abnormal case, the model will trigger the online learning process of self-optimization adjustment. The model calls the association analysis algorithm to check the difference between the abnormal case and other normal cases, and find the decisive features that cause the abnormality, such as too high a temperature limit and excessive current slope. Then, the model reduces the weight of these fault-causing features in the model prediction through the gradient penalty method, and enhances the weight of the anti-fault features to complete the iterative optimization adjustment of the model parameters.

[0056] S209. Continue to adopt the new electricity usage strategy.

[0057] If the evaluation results determine that there is no abnormality in the new strategy, the new electricity consumption strategy will continue to be adopted.

[0058] By continuously collecting user travel data and vehicle equipment usage parameters to build a personalized battery consumption model, integrating it with a general model and optimizing real-time monitoring feedback, it is possible to deeply analyze the impact of user behavior habits on battery energy consumption, effectively solving the problem that existing technologies cannot accurately match the actual power needs of different users and are difficult to respond to policy anomalies in a timely manner, thereby achieving the technical effect of dynamically optimizing power strategies based on user personalized characteristics, ensuring safe and efficient battery operation, and continuously improving the accuracy and intelligence of battery management. By accurately capturing the differences in user habits in different travel scenarios, power consumption plans are tailored for users, while improving user experience, maximizing battery life and range, and promoting electric vehicle battery management to be smarter, more reliable, and more in line with user needs.

[0059] The following describes the management system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the structure of a physical device of the management system in an embodiment of the present application.

[0060] It should be noted that Figure 3 The structure of the management system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0061] like Figure 3As shown, the management system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0062] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0063] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0064] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0065] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0066] Specifically, the management system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the battery management method provided in the above embodiment is implemented.

[0067] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the management system described in the above embodiment; or may exist independently without being assembled into the management system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the management system, the management system implements the battery management method provided in the above embodiment.

[0068] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0069] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0070] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A battery management method, applied to a management system, characterized in that: The method comprises: Obtain the traffic conditions of the road where the vehicle is currently located in real time through the on-board camera; Determining whether the current vehicle enters a congested road section in combination with the vehicle speed information of the current vehicle; If it is determined that the vehicle enters the congested road section, the vehicle uses sensors to obtain real-time information on the outside temperature, battery temperature, and battery operating conditions; Inputting the outside air temperature information, the battery temperature and the battery operation status into a preset power consumption judgment model to determine a power consumption prediction value, wherein the power consumption judgment model is obtained by machine learning training of battery operation status of vehicles under various environmental parameters and under different congestion conditions in advance; After the congestion duration of the congested road section is determined through a third-party platform, the battery power usage strategy is automatically adjusted according to the congestion duration, the current battery power status and the power consumption prediction value.

2. The method according to claim 1, characterized in that After the step of inputting the outside air temperature information, the battery temperature and the battery operation status into a preset power consumption judgment model to determine the power consumption prediction value, the method further includes: The driving data collected in advance under multiple different weather conditions and different road conditions are labeled and classified according to the weather and road conditions; After acquiring data of the battery charging and discharging process under each condition, adjusting the power consumption judgment model; When predicting power consumption, current weather conditions and road conditions are input into the power consumption judgment model to obtain an optimized power consumption prediction value.

3. The method according to claim 1, characterized in that After the step of inputting the outside air temperature information, the battery temperature and the battery operation status into a preset power consumption judgment model to determine the power consumption prediction value, the method further includes: Continuously collect the user's travel data, including the time, route and speed changes of each trip; Continuously collect the user's usage parameters of the vehicle-mounted equipment and use the usage parameters as power usage habit data; Determine a personalized battery consumption model for the user according to a machine learning algorithm combined with the power consumption judgment model, wherein the personalized battery consumption model is used to learn the battery consumption pattern corresponding to the user's travel habits and power consumption habits; When predicting the power consumption of a user, the personalized battery consumption model and the general power consumption judgment model are integrated to generate a final power consumption judgment model that matches the user.

4. The method according to claim 3, characterized in that When predicting the power consumption of the user, after the step of fusing the personalized battery consumption model with the general power consumption judgment model to generate a final power consumption judgment model matching the user, the method further includes: After inputting the real-time acquired outside temperature information, the battery temperature and the battery operation status into the final power consumption judgment model, a new power consumption strategy is obtained; Real-time monitoring of various change data of the battery after adopting the new power usage strategy, wherein the change data includes changes in electrical parameters and battery temperature; Compare and analyze the monitored data with the data of adopting the new power consumption strategy to evaluate whether there are any abnormalities in the strategy adjustment; If there is an abnormality, the new power consumption strategy is restored to the state before adjustment, and the abnormality is fed back to the final power consumption judgment model for adjustment.

5. The method according to claim 1, characterized in that After determining the congestion duration of the congested road section through a third-party platform, after the step of automatically adjusting the battery power usage strategy according to the congestion duration, the current battery power status and the power consumption prediction value, the method further includes: Monitor the real-time remaining battery power and the vehicle's current location coordinates; When the real-time remaining power is lower than a preset minimum power threshold, determining the charging pile information within a preset range according to the location coordinate information; The charging pile information is sent to the vehicle terminal for display.

6. The method according to claim 1, characterized in that After determining the congestion duration of the congested road section through a third-party platform, after the step of automatically adjusting the battery power usage strategy according to the congestion duration, the current battery power status and the power consumption prediction value, the method further includes: Monitor battery temperature and current changes in real time to detect whether the battery temperature continues to rise and exceeds a temperature threshold; If the temperature exceeds the threshold value, it is determined that abnormal heating exists, and a control instruction is sent to the vehicle-mounted device, wherein the control instruction is used to start the battery cooling system and reduce the power consumption of the vehicle-mounted device.

7. The method according to claim 1, characterized in that After determining the congestion duration of the congested road section through a third-party platform, after the step of automatically adjusting the battery power usage strategy according to the congestion duration, the current battery power status and the power consumption prediction value, the method further includes: Receiving real-time battery data reported by the vehicle terminal, wherein the real-time battery data includes at least voltage, current and temperature parameters; If the real-time battery data exceeds a preset battery performance standard range, it is determined that the battery is abnormal; Obtaining user information of the battery, and querying the maintenance contact information reserved by the user according to the user information; A battery abnormality prompt is sent to the user through the maintenance contact information to prompt the user to check and repair the battery.

8. A management system, characterized in that: The management system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the management system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a management system, the management system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a management system, the management system is enabled to execute the method according to any one of claims 1 to 7.

Images