Lithium battery electric quantity prediction method and device, computer equipment and storage medium
By obtaining user behavior and lithium battery status information, combining Peukert equation and neural network model, dynamically optimizing lithium battery power prediction, solving the problem of inaccurate power prediction in the existing technology, and achieving more accurate and reliable power management.
Patent Information
- Application Number
- CN202411033315.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing lithium battery power prediction method is not accurate enough under the influence of user operating habits and external factors, and it is difficult to personalize the use scenarios of different users.
By obtaining user behavior information, adjusting the power change file, and combining the real-time status information and operation history information of lithium batteries, use the Peukert equation and neural network model for dynamic optimization and prediction to generate more accurate power prediction results.
It improves the accuracy and reliability of battery power prediction, can reflect users' usage habits and the actual state of the battery in real time, avoids the inconvenience caused by sudden power outage, and extends the battery life.
Smart Images

Figure CN119001448A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of battery management, and in particular to a lithium battery power prediction method, device, computer equipment and storage medium. Background Art
[0002] Electronic products have been deeply integrated into our daily lives and have become an indispensable part. However, the problem of battery life has always troubled the majority of users, especially in mobile devices and portable electronic products.
[0003] In the related technology, with the popularity and diversification of electronic products, people's demand for battery life is also growing. However, the battery life of lithium batteries is affected by many factors, such as temperature, usage frequency, charging habits, etc., making the remaining battery life prediction inaccurate.
[0004] Regarding the above-mentioned related technologies, how to ensure that the prediction results of the remaining battery operating time remain accurate under the influence of user operating habits and external factors is a technical problem that needs to be solved urgently. Summary of the invention
[0005] In order to improve the accuracy of lithium battery power prediction usage time, the present application provides a lithium battery power prediction method, device, computer equipment and storage medium.
[0006] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A lithium battery power prediction method, the lithium battery power prediction method comprising: Obtain user behavior information, adjust and calculate the power change profile according to the user behavior information, and generate a battery power prediction result; optimize the battery power prediction result according to the lithium battery status information to generate a secondary battery power prediction result; obtain the lithium battery operation history information, compare the power prediction time according to the lithium battery operation history information and the secondary battery power prediction result, and generate the battery remaining operation time.
[0007] By adopting the above technical solution, by obtaining user behavior information and adjusting the power change profile accordingly, the actual usage habits of users can be more accurately reflected, thereby improving the accuracy of battery power prediction. The usage patterns of different users may vary greatly, so personalized power change profiles can better adapt to different usage scenarios. By obtaining the real-time status information of the lithium battery and applying the Peukert equation to calculate the discharge rate and capacity, the preliminary prediction results can be dynamically optimized. Make the prediction results more accurate and reliable. By comparing the lithium battery operation history information with the secondary prediction results, a large amount of historical data can be used for verification and correction to ensure the stability and accuracy of the prediction results. It can reflect the actual status and future trends of the battery. By generating information visualization instructions and sending the remaining battery runtime to the mobile terminal, users can understand the remaining battery power in real time. It can help users better manage battery usage and avoid the inconvenience caused by sudden power outages.
[0008] In a preferred example, the present application may be further configured as follows: the obtaining of user behavior information; adjusting and calculating the power change profile according to the user behavior information to generate a battery power prediction result specifically includes: The real-time lithium battery power usage is recorded according to the user behavior information, the power change is updated, an adjusted power change file is obtained, and the battery power prediction result is generated according to the adjusted power change file.
[0009] By adopting the above technical solutions and recording user behavior information, the prediction model can adapt to individual differences and provide more accurate power prediction. Real-time recording of power usage can dynamically reflect battery status and usage, making the prediction results closer to the actual situation. At the same time, the power change archive can be updated at any time to promptly reflect changes in user behavior and usage environment, ensuring that the prediction model always maintains the latest and most accurate data input.
[0010] In a preferred example, the present application can be further configured as follows: recording the real-time lithium battery usage power according to the user behavior information, updating the power change, obtaining an adjusted power change file, and generating the battery power prediction result according to the adjusted power change file, including: The real-time lithium battery usage is recorded according to the user behavior information, by: Where ΔE represents the change in charge, I discharge (t) represents the current consumption of the battery at time t, and the power consumption is updated. charge (t) represents the current added by the battery charging at time t, I self-discharge (t) represents the self-discharge current of the battery at time t, T(t) represents the battery temperature at time t, T refIndicates the reference temperature, T max represents the maximum temperature, H(x) represents a step function. If x is greater than or equal to zero, the function value is 1, otherwise it is 0. health (t) represents the battery health status at time t, t0 represents the start time, and t1 represents the end time. The power change is updated by calculation to adjust the calculation of the power change file; The power change is updated to obtain the adjusted power change file, and the battery power prediction result is generated according to the adjusted power change file.
[0011] According to the power change file, the real-time power change is recorded, and the historical power change information is obtained, and the battery power prediction result is generated through the real-time power change and the historical power change information.
[0012] By adopting the above technical solution, the prediction results are made more accurate and reliable by considering the impact of external conditions on power changes, including charging and discharging conditions, temperature and health status. By recording power changes in real time and constantly updating the archive, it can dynamically respond to changes in battery status, improving the accuracy and stability of the prediction. Accurately predict the remaining power of the battery.
[0013] In a preferred example, the present application may be further configured as follows: the obtaining of the lithium battery operation history information, performing a power prediction time comparison based on the lithium battery operation history information and the secondary battery power prediction result, and generating the remaining battery operation time, includes: Constructing a neural network model, dividing the lithium battery operation history information into a training set and a test set, and using the training set to train the neural network model; Using the test set to evaluate the performance of the neural network model and generate an evaluation result, and tuning the model according to the evaluation result to obtain a trained neural network model; The trained neural network model is used to predict future battery changes, and the real-time power change and the historical power change information are input into the trained neural network model to generate the battery power prediction result.
[0014] By adopting the above technical solution, the neural network model is used to train the historical power changes, and the impact of various external factors on the battery power changes is comprehensively considered, making the prediction results more accurate and reliable. The model is tuned according to the evaluation results of the test set to further improve the accuracy and reliability of the prediction. The real-time recorded power change information can dynamically update the model, making the prediction results more timely and accurate.
[0015] In a preferred example, the present application may be further configured as follows: optimizing the battery power prediction result according to the lithium battery status information to generate a secondary battery power prediction result, specifically including: The battery power prediction result is optimized by the following formula to generate the secondary battery power prediction result: Wherein, Ppredicted refers to the battery power prediction result, Cp refers to the actual battery capacity at a given discharge rate calculated by the Peukert equation, and Cl refers to the rated capacity of the battery under standard conditions. Among them, C p Calculate using the following formula: Among them, T refers to the amount of charge discharged by the battery per unit time, C l It refers to the total amount of electricity that the battery can release under standard conditions, and k is the Peukert coefficient.
[0016] By adopting the above technical solutions, the Peukert equation takes into account multiple factors such as battery performance degradation and discharge rate, and can more comprehensively predict the actual capacity and discharge rate of the battery, thereby improving the accuracy of the prediction. The actual battery capacity obtained by calculation can dynamically adjust the remaining battery power prediction according to different discharge rates, making the prediction results more suitable for actual use. The Peukert coefficient reflects the battery performance degradation. Through the prediction results, changes in battery performance can be discovered in time and corresponding measures can be taken to extend the battery life and maintain performance. According to the actual discharge rate and battery capacity calculation, real-time prediction of battery power can be achieved, and the remaining battery power can be reflected in time, providing users with dynamic power management.
[0017] In a preferred example, the present application may be further configured as follows: the obtaining of lithium battery operation history information, comparing power prediction time according to the lithium battery operation history information with the secondary battery power prediction result, and generating the remaining battery operation time specifically includes: According to the lithium battery operation history information, the discharge time characteristics of the battery at different power levels are obtained, and according to the secondary battery power prediction result, the power of the battery at different time points is obtained; The remaining operating time of the battery is calculated based on the power level of the battery at different time points and the discharge time characteristics of the battery at different power levels.
[0018] By adopting the above technical solution, the lithium battery operation history information and power prediction results are combined to fully understand the actual use and future trends of the battery. This method not only relies on historical data, but also combines real-time power prediction, making the prediction results more timely and accurate. By analyzing the discharge time characteristics of the battery at different power levels, a more refined battery discharge curve can be obtained. This refined analysis helps to accurately predict the operating time of the battery at a specific power level, avoiding relying solely on average or fixed discharge time for prediction, thereby improving accuracy. Real-time prediction of battery power changes at different time points can timely reflect the current state of the battery and changes in the use environment. Combining historical data and real-time prediction, the power prediction results can be dynamically adjusted to improve the accuracy and reliability of the prediction. By comprehensively analyzing historical data and real-time prediction results, different usage scenarios and conditions can be adapted. For example, the discharge characteristics of the battery may be different under different conditions such as temperature and discharge current. Combining historical data can better reflect these differences and improve the accuracy of predictions in various usage scenarios.
[0019] In a preferred example, the present application may be further configured as follows: the calculation of the remaining operating time of the battery by using the power of the battery at different time points and the discharge time characteristics of the battery at different power levels specifically includes: By using an interpolation method, the power of the battery at different time points and the discharge time characteristics of the battery at different power levels are compared to obtain the operating time at each time point; The operating time at each time point is summed up to obtain the remaining operating time of the battery.
[0020] By adopting the above technical solution, the interpolation method can be used to process the power prediction results in more detail. Even if the predicted power value does not completely match the power value in the historical data, the interpolation method can provide an accurate running time estimate. This refinement helps to improve the accuracy of the prediction and avoids the errors caused by simple linear extrapolation. The discharge characteristics of the battery may show different trends and patterns at different power levels. By comparing the power and discharge time characteristics of the battery at different time points through the interpolation method, it can better adapt to the complex situations of the battery in actual use.
[0021] The second object of the invention is achieved by the following technical solutions: A lithium battery power prediction device, the lithium battery power prediction device comprising: A battery power calculation module is used to obtain user behavior information, adjust and calculate the power change profile according to the user behavior information, and generate a battery power prediction result; A battery power prediction module, used to optimize the battery power prediction result according to the lithium battery state information to generate a secondary battery power prediction result; The operating time module is used to obtain the operating history information of the lithium battery, compare the power prediction time according to the operating history information of the lithium battery and the power prediction result of the secondary battery, and generate the remaining operating time of the battery.
[0022] By adopting the above technical solution, by obtaining user behavior information and adjusting the power change profile accordingly, the actual usage habits of users can be more accurately reflected, thereby improving the accuracy of battery power prediction. The usage patterns of different users may vary greatly, so personalized power change profiles can better adapt to different usage scenarios. By obtaining the real-time status information of the lithium battery and applying the Peukert equation to calculate the discharge rate and capacity, the preliminary prediction results can be dynamically optimized. Make the prediction results more accurate and reliable. By comparing the lithium battery operation history information with the secondary prediction results, a large amount of historical data can be used for verification and correction to ensure the stability and accuracy of the prediction results. It can reflect the actual status and future trends of the battery. By generating information visualization instructions and sending the remaining battery runtime to the mobile terminal, users can understand the remaining battery power in real time. It can help users better manage battery usage and avoid the inconvenience caused by sudden power outages.
[0023] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned lithium battery power prediction method when executing the computer program.
[0024] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned lithium battery power prediction method.
[0025] In summary, the present application includes at least one of the following beneficial technical effects: 1. By obtaining user behavior information and adjusting the power change profile accordingly, it can more accurately reflect the user's actual usage habits, thereby improving the accuracy of battery power prediction. The usage patterns of different users may vary greatly, so personalized power change profiles can better adapt to different usage scenarios. Obtaining real-time status information of lithium batteries and applying the Peukert equation to calculate discharge rate and capacity can dynamically optimize the preliminary prediction results. Make the prediction results more accurate and reliable. By comparing the lithium battery operation history information with the secondary prediction results, a large amount of historical data can be used for verification and correction to ensure the stability and accuracy of the prediction results. It can reflect the actual status and future trends of the battery. By generating information visualization instructions and sending the remaining battery runtime to the mobile terminal, users can understand the remaining battery power in real time. It can help users better manage battery usage and avoid the inconvenience caused by sudden power outages; 2. Combining the lithium battery operation history information with the power prediction results can fully understand the actual use of the battery and future trends. This method not only relies on historical data, but also combines real-time power prediction, making the prediction results more timely and accurate. By analyzing the discharge time characteristics of the battery at different power levels, a more refined battery discharge curve can be obtained. This refined analysis helps to accurately predict the battery's operating time at a specific power level, avoiding relying solely on average or fixed discharge time for prediction, thereby improving accuracy. Real-time prediction of battery power changes at different time points can timely reflect the current state of the battery and changes in the use environment. Combining historical data with real-time predictions can dynamically adjust the power prediction results to improve the accuracy and reliability of the prediction. By comprehensively analyzing historical data and real-time prediction results, it can adapt to different usage scenarios and conditions. For example, under different temperature, discharge current and other conditions, the discharge characteristics of the battery may be different. Combining historical data can better reflect these differences and improve the prediction accuracy in various usage scenarios; 3. The interpolation method can be used to process the power prediction results more carefully. Even if the predicted power value does not completely match the power value in the historical data, the interpolation method can provide an accurate running time estimate. This refinement helps improve the accuracy of the prediction and avoids the errors caused by simple linear extrapolation. The discharge characteristics of the battery may show different trends and patterns at different power levels. By comparing the power and discharge time characteristics of the battery at different time points through interpolation methods, it can better adapt to the complex situations of the battery in actual use. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] Figure 1 is a flow chart of a lithium battery power prediction method in one embodiment of the present application; Figure 2 This is a flowchart of the implementation of step S10 of the lithium battery power prediction method in one embodiment of the present application; Figure 3 This is a flowchart of the implementation of step S11 of the lithium battery power prediction method in one embodiment of the present application; Figure 4 This is a flowchart of the implementation of the lithium battery power prediction method after step S112 in one embodiment of the present application; Figure 5 This is a flowchart of the implementation of step S20 of the lithium battery power prediction method in one embodiment of the present application; Figure 6 This is a flowchart of the implementation of step S30 of the lithium battery power prediction method in one embodiment of the present application; Figure 7 This is a flowchart of the implementation of step S32 of the lithium battery power prediction method in one embodiment of the present application; Figure 8 This is a principle block diagram of a lithium battery power prediction method in one embodiment of the present application; Fig. 9 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION
[0027] The present application is further described in detail below in conjunction with the accompanying drawings.
[0028] In one embodiment, if Figure 1 As shown, the present application discloses a lithium battery power prediction method, which specifically includes the following steps: S10: Obtain user behavior information, adjust and calculate the power change profile according to the user behavior information, and generate a battery power prediction result.
[0029] In this embodiment, user behavior information refers to device usage time and frequency, application usage, charging behavior, discharging behavior, device usage environment, and user habits and preferences. The power change file refers to a comprehensive data file that records and analyzes the changes in battery power over time. The battery power prediction result refers to the prediction of the remaining power and usage time in the future.
[0030] Specifically, based on user behavior information, record the applications used by the user and their usage time, record device settings such as screen brightness, volume, network status, record information about the device's environment, such as temperature, signal strength, and record the user's charging time, frequency, and duration. Record real-time changes in battery power, including discharge and charging rates. Combine real-time recorded information with historical information to update the power change archive. Perform preliminary analysis and prediction based on the user's historical power change data. Adjust power consumption expectations based on the current user's usage habits and generate preliminary prediction results. Obtain current battery status information such as current, voltage, and temperature. Generate battery power prediction results based on battery status information.
[0031] S20: Optimizing the battery power prediction result according to the lithium battery status information to generate a secondary battery power prediction result.
[0032] In this embodiment, the lithium battery status information refers to the battery voltage, current, temperature, health status, charging state, discharge rate, self-discharge rate, number of cycles and internal resistance.
[0033] Specifically, by identifying the state of the lithium battery, inputting the lithium battery state information into the Peukert equation, calculating the discharge rate and capacity of the battery, updating the remaining capacity prediction result of the battery, and generating the secondary battery power prediction result.
[0034] S30: Obtaining the lithium battery operation history information, comparing the power prediction time according to the lithium battery operation history information and the secondary battery power prediction result, and generating the battery remaining operation time.
[0035] In this embodiment, the lithium battery operation history information refers to the charging time, discharging time and power change.
[0036] Specifically, the battery charge and discharge mode and power consumption pattern are obtained through the lithium battery operation history information, and the lithium battery operation history information is compared with the current power prediction result to determine the remaining battery operation time.
[0037] In one embodiment, if Figure 2 As shown, in step S10, the user behavior information is obtained; the power change profile is adjusted and calculated according to the user behavior information to generate a battery power prediction result, which specifically includes: S11: Record the real-time lithium battery power usage according to the user behavior information, update the power change, obtain an adjusted power change file, and generate a battery power prediction result according to the adjusted power change file.
[0038] In this embodiment, the adjusted power variation file refers to a comprehensive data file of the adjusted battery power variation over time.
[0039] Specifically, when the user uses the device, the lithium battery power changes in real time, and the lithium battery power is updated in real time, so that the power change file is adjusted. After the adjustment based on the real-time changing power file, the battery power is predicted to generate a battery power prediction result, thereby confirming the remaining battery life.
[0040] In one embodiment, if Figure 3 As shown, in step S11, the real-time lithium battery usage power is recorded according to the user behavior information, the power change is updated, and an adjusted power change file is obtained. According to the adjusted power change file, a battery power prediction result is generated, including: S111: Recording real-time lithium battery power usage based on user behavior information, by: Where ΔE represents the change in charge, I discharge (t) represents the current consumption of the battery at time t, and the power consumption is updated. charge (t) represents the current added by the battery charging at time t, I self-discharge (t) represents the self-discharge current of the battery at time t, T(t) represents the battery temperature at time t, T ref Indicates the reference temperature, T max represents the maximum temperature, H(x) represents a step function. If x is greater than or equal to zero, the function value is 1, otherwise it is 0. health (t) represents the battery health status at time t, t0 represents the start time, and t1 represents the end time. The power change is updated through calculation to adjust the calculated power change file; Specifically, the lithium battery current, temperature and health status data are acquired in real time and stored. The power change is calculated using the integral method, and the real-time power change information is stored and updated in the power change file. The power change file is continuously updated with new power change information. Future power demand is predicted based on user usage habits and historical data. The updated power change file is used to generate the battery power prediction result.
[0041] S112: updating the power change to obtain an adjusted power change file, and generating a battery power prediction result according to the adjusted power change file.
[0042] Specifically, compare the real-time power change data with the historical power change data to analyze the difference between the current usage pattern and the historical pattern. Identify the power change trend and pattern by comparing the historical data with the real-time data. Forecast based on historical data: Use the historical power change data to make trend forecasts and estimate future power changes. Use the real-time data as input to correct the forecast results based on the historical data and generate the battery power forecast results.
[0043] In one embodiment, if Figure 4 As shown, after step S112, that is, obtaining the lithium battery operation history information, comparing the power prediction time according to the lithium battery operation history information and the secondary battery power prediction result, and generating the battery remaining operation time, it includes: S201: Build a neural network model, divide the lithium battery operation history information into a training set and a test set, and use the training set to train the neural network model.
[0044] In this embodiment, the neural network model refers to a computing model that simulates the connection mode of neurons in the human brain.
[0045] Specifically, based on historical power change information, including discharge current, charge current, self-discharge current, temperature and health status. Standardize the historical power change information. Divide the historical power change data into training set and test set in a ratio of 80:20. The number of nodes is equal to the number of input features (such as current, temperature, health status, etc.). A single node outputs the prediction result (remaining battery power or remaining running time). Use TensorFlow to define the structure of the neural network model. Select the mean square error (MSE) to evaluate the error between the predicted value and the true value. Use the training set data to train the model.
[0046] S202: Evaluate the performance of the neural network model using the test set and generate evaluation results. Tune the model according to the evaluation results to obtain a trained neural network model.
[0047] In this embodiment, the evaluation result refers to the evaluation result of the neural network model.
[0048] Specifically, when evaluating the performance of the neural network model, the test set is first used for prediction and performance indicators such as mean square error are calculated. Then, the problems with the model are analyzed based on the evaluation results, and the model structure is adjusted, the algorithm parameters are optimized, or the model is tuned using regularization techniques. Finally, the tuned model is saved and its generalization ability is verified to generate a trained model suitable for battery power prediction.
[0049] S203: Use the trained neural network model to predict future battery changes, input the real-time power change and historical power change information into the trained neural network model, and generate a battery power prediction result.
[0050] Specifically, the real-time power change and historical power change information in the future are integrated to ensure the integrity of the data. The input data is properly preprocessed and normalized to match the format of the model input data. The preprocessed data is input into the trained neural network model for prediction. Finally, the battery power result predicted by the model is obtained.
[0051] In one embodiment, if Figure 5 As shown, in step S20, the battery power prediction result is optimized according to the lithium battery status information to generate a secondary battery power prediction result, which specifically includes: S21: Optimize the battery power prediction result by the following formula to generate a secondary battery power prediction result: Among them, Ppredicted refers to the battery power prediction result, Cp refers to the actual battery capacity at a given discharge rate calculated by the Peukert equation, and Cl refers to the rated capacity of the battery under standard conditions. Among them, Cp is calculated by the following formula: Among them, T refers to the amount of charge released by the battery per unit time, Cl refers to the total amount of electricity that the battery can release under standard conditions, and k is the Peukert coefficient.
[0052] Specifically, according to the status information of the lithium battery, when the battery is in a healthy state, the discharge rate and capacity of the battery can be accurately calculated by applying the Peukert equation. The specific process is as follows: First, collect the current status information of the lithium battery, including health status, discharge current, and temperature. After confirming that the battery is in a healthy state, use the Peukert equation to calculate the amount of charge T released by the battery per unit time. Next, calculate the actual capacity at the current discharge rate. This evaluates the performance of the battery under different discharge conditions and ensures the effectiveness and accuracy of battery management. According to the status information of the lithium battery, first use the Peukert equation to calculate the actual battery capacity C at a specific discharge rate. p Next, the rated capacity C of the battery under standard conditions l With C p For comparison, use the formula P predicted Calculate the battery power prediction result P predicted The result indicates the ratio of the amount of electricity that the battery is expected to release under the current discharge conditions to the rated capacity, thereby accurately predicting the remaining capacity of the battery.
[0053] In one embodiment, if Figure 6 As shown, in step S30, the lithium battery operation history information is obtained, and the power prediction time is compared with the secondary battery power prediction result according to the lithium battery operation history information to generate the battery remaining operation time, which specifically includes: S31: obtaining the discharge time characteristics of the battery at different power levels based on the lithium battery operation history information, and obtaining the power levels of the battery at different time points based on the secondary battery power prediction results.
[0054] In this embodiment, the discharge time characteristics of the battery at different power levels refer to the time that the battery can continue to work at various power percentages (e.g., 100%, 90%, 80%, etc.). The power level of the battery at different time points refers to the power level of the battery at different time points. It refers to the power percentage of the battery at a specific time point (e.g., the battery has a power level of 85% 1 hour after the predicted time point and a power level of 70% 2 hours later).
[0055] Specifically, the experimental data or historical data of the battery is collected, and the discharge time of the battery at different power percentages is recorded. The time series prediction model is used to predict the power percentage of the battery at different time points in the future.
[0056] S32: Calculate the remaining operating time of the battery based on the battery power at different time points and the discharge time characteristics of the battery at different power levels.
[0057] Specifically, the remaining operating time of the battery is obtained by calculating the discharge time corresponding to each time point.
[0058] In one embodiment, if Figure 7 As shown, in step S32, the remaining operating time of the battery is calculated based on the power of the battery at different time points and the discharge time characteristics of the battery at different power levels, which specifically includes: S321: By using an interpolation method, the power of the battery at different time points and the discharge time characteristics of the battery at different power levels are compared to obtain the operating time at each time point.
[0059] In this embodiment, the interpolation method refers to finding the discharge time corresponding to the predicted power between different power and discharge time characteristics of the battery.
[0060] Specifically, collect the discharge time characteristic data of the battery at different power levels and record them in a table. Predict the battery power percentage at different time points in the future. For each predicted power value, determine its interval in the discharge time characteristic data, and apply the linear interpolation formula to calculate the corresponding discharge time. Linear interpolation formula: Among them, x0 and x1 represent two known percentage points of power. For example, the discharge time at 80% and 90% power is known. y1 and y2 represent the discharge time corresponding to x0 and x1. For example, 80% power corresponds to 2 hours, and 90% power corresponds to 1 hour. x represents the predicted power percentage. For example, it is predicted that the battery power will be 85% after 1 hour. y is calculated through linear interpolation to obtain the discharge time corresponding to the predicted power percentage of 85%. T is the discharge time. For example, the power is predicted to be 85% after 1 hour, and the discharge time corresponding to 85% power needs to be calculated. Use the linear interpolation formula: x0=80, x1=90, y0=2, y1=1, x=85, import the formula, Therefore, the discharge time corresponding to 85% of the power is 1.5 hours.
[0061] S322: Sum up the operating time at each time point to obtain the remaining operating time of the battery.
[0062] Specifically, for example, the power forecast after 1 hour is 85%, and 85% power is between 80% and 90%. The known points are (80,2) and (90,1), and the difference is calculated as: The power forecast after 2 hours is 70%. Look up the discharge time characteristic data, 70% power corresponds to 3 hours. The power forecast after 3 hours is 55%, 55% power corresponds to 4.5 hours. Look up the discharge time characteristic data, 40% power corresponds to 6 hours. The power forecast after 5 hours is 25%, 25% corresponds to 7.5 hours. The remaining operating time of the total battery = 1.5 + 3 + 4.5 + 6 + 7.5 = 22.5 hours.
[0063] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0064] In one embodiment, a lithium battery power prediction device is provided, and the lithium battery power prediction device corresponds to the lithium battery power prediction method in the above embodiment. Figure 8 As shown, the lithium battery power prediction device includes a battery power calculation module, a battery power prediction module and a running time module. The detailed description of each functional module is as follows: The battery power calculation module is used to obtain user behavior information, adjust the calculation power change file according to the user behavior information, and generate the battery power prediction result; A battery power prediction module is used to optimize the battery power prediction result according to the lithium battery status information to generate a secondary battery power prediction result; The operating time module is used to obtain the lithium battery operating history information, compare the power prediction time based on the lithium battery operating history information and the secondary battery power prediction result, and generate the battery remaining operating time.
[0065] Optionally, the battery power calculation module includes: The prediction result submodule is used to record the real-time lithium battery usage power according to the user behavior information, update the power change, obtain the adjusted power change file, and generate the battery power prediction result according to the adjusted power change file.
[0066] Optionally, the prediction result submodule includes: The power calculation unit is used to record the real-time lithium battery power usage based on user behavior information, through: Where ΔE represents the change in charge, I discharge (t) represents the current consumption of the battery at time t, and the power consumption is updated. charge (t) represents the current added by the battery charging at time t, Iself-discharge (t) represents the self-discharge current of the battery at time t, T(t) represents the battery temperature at time t, T ref Indicates the reference temperature, T max represents the maximum temperature, H(x) represents a step function. If x is greater than or equal to zero, the function value is 1, otherwise it is 0. health (t) represents the battery health status at time t, t0 represents the start time, and t1 represents the end time. The power change is updated through calculation to adjust the calculated power change file; The power change unit is used to update the power change, obtain an adjusted power change file, and generate a battery power prediction result according to the adjusted power change file.
[0067] Optionally, the electric quantity changing unit includes: A model building subunit is used to build a neural network model, divide the lithium battery operation history information into a training set and a test set, and use the training set to train the neural network model; The training model subunit is used to evaluate the performance of the neural network model using the test set and generate evaluation results, and to tune the model according to the evaluation results to obtain a trained neural network model; The prediction result subunit is used to use the trained neural network model to predict future battery changes, input the real-time power change and historical power change information into the trained neural network model, and generate a battery power prediction result.
[0068] Optionally, the battery power prediction module includes: The actual power unit optimizes the battery power prediction result through the following formula to generate the secondary battery power prediction result: Among them, Ppredicted refers to the battery power prediction result, Cp refers to the actual battery capacity at a given discharge rate calculated by the Peukert equation, and Cl refers to the rated capacity of the battery under standard conditions. Among them, Cp is calculated by the following formula: Among them, T refers to the amount of charge released by the battery per unit time, Cl refers to the total amount of electricity that the battery can release under standard conditions, and k is the Peukert coefficient.
[0069] Optional runtime modules include: The information acquisition submodule is used to obtain the discharge time characteristics of the battery at different power levels based on the lithium battery operation history information, and obtain the power level of the battery at different time points based on the secondary battery power prediction result; The time calculation submodule is used to calculate the remaining operating time of the battery through the battery power at different time points and the discharge time characteristics of the battery at different power levels.
[0070] Optionally, the time calculation submodule includes: An interpolation unit, used to compare the power of the battery at different time points and the discharge time characteristics of the battery at different power levels by an interpolation method to obtain the operating time at each time point; The time calculation unit is used to sum up the operating time at each time point to obtain the remaining operating time of the battery.
[0071] For the specific limitations of the lithium battery power prediction device, please refer to the limitations of the lithium battery power prediction method above, which will not be repeated here. Each module in the above-mentioned lithium battery power prediction device can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0072] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for a lithium battery power prediction database. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a lithium battery power prediction method is implemented.
[0073] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Obtain user behavior information, adjust and calculate the power change profile based on the user behavior information, and generate battery power prediction results; Optimizing the battery power prediction result according to the lithium battery status information to generate a secondary battery power prediction result; Obtain the lithium battery operation history information, compare the power prediction time based on the lithium battery operation history information and the secondary battery power prediction result, and generate the battery remaining operation time.
[0074] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Obtain user behavior information, adjust and calculate the power change profile according to the user behavior information, and generate a battery power prediction result; optimize the battery power prediction result according to the lithium battery status information to generate a secondary battery power prediction result; Obtain the lithium battery operation history information, compare the power prediction time according to the lithium battery operation history information and the secondary battery power prediction result, and generate the battery remaining operation time. Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0075] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.
[0076] The embodiments described above 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, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A lithium battery power prediction method, characterized in that: The lithium battery power prediction method comprises: Obtain user behavior information, adjust and calculate the power change profile according to the user behavior information, and generate a battery power prediction result; optimize the battery power prediction result according to the lithium battery status information to generate a secondary battery power prediction result; obtain the lithium battery operation history information, compare the power prediction time according to the lithium battery operation history information and the secondary battery power prediction result, and generate the battery remaining operation time.
2. The lithium battery power prediction method according to claim 1, characterized in that: The obtaining of user behavior information; and adjusting and calculating the power change profile according to the user behavior information to generate a battery power prediction result specifically include: The real-time lithium battery power usage is recorded according to the user behavior information, the power change is updated, an adjusted power change file is obtained, and the battery power prediction result is generated according to the adjusted power change file.
3. The lithium battery power prediction method according to claim 2, characterized in that: The method of recording the real-time lithium battery power usage according to the user behavior information, updating the power change, obtaining an adjusted power change file, and generating the battery power prediction result according to the adjusted power change file includes: The real-time lithium battery usage is recorded according to the user behavior information, by: Where ΔE represents the change in charge, I discharge (t) represents the current consumption of the battery at time t, and the power consumption is updated. charge (t) represents the current added by the battery charging at time t, I self-discharge (t) represents the self-discharge current of the battery at time t, T(t) represents the battery temperature at time t, T ref Indicates the reference temperature, T max represents the maximum temperature, H(x) represents a step function. If x is greater than or equal to zero, the function value is 1, otherwise it is 0. health (t) represents the battery health status at time t, t0 represents the start time, and t1 represents the end time. The power change is updated by calculation to adjust the calculation of the power change file; The power change is updated to obtain the adjusted power change file, and the battery power prediction result is generated according to the adjusted power change file.
4. The lithium battery power prediction method according to claim 1, characterized in that: The method of obtaining the lithium battery operation history information, comparing the power prediction time with the secondary battery power prediction result according to the lithium battery operation history information, generating the battery remaining operation time to update the power change, obtaining the adjusted power change file, and generating the battery power prediction result according to the adjusted power change file includes: Constructing a neural network model, dividing the lithium battery operation history information into a training set and a test set, and using the training set to train the neural network model; Using the test set to evaluate the performance of the neural network model and generate an evaluation result, and tuning the model according to the evaluation result to obtain a trained neural network model; The trained neural network model is used to predict future battery changes, and the real-time power change and the historical power change information are input into the trained neural network model to generate the battery power prediction result.
5. The lithium battery power prediction method according to claim 1, characterized in that: The optimizing the battery power prediction result according to the lithium battery state information to generate a secondary battery power prediction result specifically includes: The battery power prediction result is optimized by the following formula to generate the secondary battery power prediction result: Wherein, Ppredicted refers to the battery power prediction result, Cp refers to the actual battery capacity at a given discharge rate calculated by the Peukert equation, and Cl refers to the rated capacity of the battery under standard conditions. Among them, C p Calculate using the following formula: Among them, T refers to the amount of charge discharged by the battery per unit time, C l It refers to the total amount of electricity that the battery can release under standard conditions, and k is the Peukert coefficient.
6. The lithium battery power prediction method according to claim 1, characterized in that: The obtaining of the lithium battery operation history information, comparing the power prediction time according to the lithium battery operation history information with the secondary battery power prediction result, and generating the battery remaining operation time specifically includes: According to the lithium battery operation history information, the discharge time characteristics of the battery at different power levels are obtained, and according to the secondary battery power prediction result, the power of the battery at different time points is obtained; The remaining operating time of the battery is calculated based on the power level of the battery at different time points and the discharge time characteristics of the battery at different power levels.
7. The lithium battery power prediction method according to claim 6, characterized in that: The calculating the remaining operating time of the battery by using the power of the battery at different time points and the discharge time characteristics of the battery at different power levels specifically includes: By using an interpolation method, the power of the battery at different time points and the discharge time characteristics of the battery at different power levels are compared to obtain the operating time at each time point; The operating time at each time point is summed up to obtain the remaining operating time of the battery.
8. A lithium battery power prediction device, characterized in that: The lithium battery power prediction device comprises: A battery power calculation module is used to obtain user behavior information, adjust and calculate the power change profile according to the user behavior information, and generate a battery power prediction result; A battery power prediction module, used to optimize the battery power prediction result according to the lithium battery state information to generate a secondary battery power prediction result; The operating time module is used to obtain the operating history information of the lithium battery, compare the power prediction time according to the operating history information of the lithium battery and the power prediction result of the secondary battery, and generate the remaining operating time of the battery.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the lithium battery power prediction method as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the lithium battery power prediction method as claimed in any one of claims 1 to 7 are implemented.
