Battery charging protection method and system for electric screwdrivers

Abstract

The present application relates to the technical field of charging protection, and particularly relates to a battery charging protection method and system for an electric screwdriver. The method comprises the following steps: obtaining a historical operation monitoring log of the electric screwdriver; performing user individualized use demand analysis on the historical operation monitoring log of the electric screwdriver, thereby generating historical use demand evolution data; performing multi-period demand decomposition on the historical use demand evolution data, and performing comprehensive power demand speculation, thereby generating a next battery power demand prediction value; performing maximum safe charging power calculation according to the next battery power demand prediction value, thereby generating a battery maximum safe charging power; performing instant charging control according to the battery maximum safe charging power, and monitoring battery state parameters in real time; and generating a dynamic temperature change trend feature based on the battery state parameters. The present application realizes dynamic calculation of real-time battery charging power, thereby improving the service life and safety of the battery.

Description

Technical Field

[0001] This invention relates to the field of charging protection technology, and in particular to a battery charging protection method and system for an electric screwdriver. Background Technology

[0002] Electric screwdrivers, as a common power tool, are widely used in industrial production, home repair, and other fields. With continuous technological advancements, the performance of electric screwdrivers has been constantly improved, especially in battery selection and battery management system (BMS) optimization, resulting in significant improvements in lifespan and reliability. However, during prolonged use, battery charging issues have gradually become one of the key factors restricting the performance and safety of electric screwdrivers.

[0003] As a core component of electric screwdrivers, the battery has long been responsible for providing energy. Because batteries are affected by various factors during charging and discharging, such as temperature, charging current, and battery aging, the lack of an effective charging protection mechanism can lead to problems like overcharging, over-discharging, and overheating, thus shortening battery life and even causing safety accidents. Traditional battery charging protection methods rely heavily on simple voltage monitoring and temperature control, failing to comprehensively consider the combined effects of battery status, charging rate, and various complex factors. Therefore, given the application requirements of modern electric screwdrivers, traditional charging protection technology is somewhat outdated, and a more intelligent, precise, and comprehensive battery charging protection method is urgently needed. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention proposes a battery charging protection method and system for electric screwdrivers, thereby resolving at least one of the aforementioned technical problems.

[0005] To achieve the above objectives, the present invention provides a battery charging protection method for an electric screwdriver, comprising the following steps:

[0006] Step S1: Obtain the historical operation monitoring log of the electric screwdriver; perform personalized user usage demand analysis on the historical operation monitoring log of the electric screwdriver to generate historical usage demand evolution data;

[0007] Step S2: Decompose the historical usage demand evolution data into multi-period demand and make a comprehensive power demand prediction to generate the next battery power demand forecast.

[0008] Step S3: Calculate the maximum safe charging power based on the next predicted battery power demand, and generate the maximum safe charging power for the battery.

[0009] Step S4: Perform real-time charging control based on the battery's maximum safe charging power and monitor battery status parameters in real time; generate dynamic temperature change characteristics based on the battery status parameters;

[0010] Step S5: Based on the dynamic temperature change characteristics, perform rolling prediction of the time window and intelligently adjust and optimize the maximum safe charging power of the battery to build an intelligent power optimization strategy.

[0011] Step S6: Make overcharge protection decisions based on the battery state parameters, and perform self-learning collaborative control optimization based on the intelligent power optimization strategy to build an intelligent charging control and protection model.

[0012] This invention, through in-depth analysis of historical operation logs, can gain insights into the actual usage patterns and behavioral characteristics of different users, ensuring personalized battery management based on individual needs. By analyzing historical usage data, it can track and predict future user behavior, generating accurate demand evolution data. This provides a reliable foundation for subsequent battery charging demand prediction, ensuring that charging strategies can be tailored to actual usage needs. Utilizing historical data and demand evolution models, battery charging needs can be planned in advance for different usage scenarios, avoiding device usage limitations due to insufficient battery power during high-demand periods. By decomposing and analyzing historical usage demand evolution data by time period, demand prediction can be accurate to specific time periods, greatly improving the accuracy of charging prediction. This segmentation reflects the specific usage frequency of users in different time periods, helping to accurately judge future power needs. Combining multi-time period demand decomposition not only estimates the overall battery power demand but also generates precise power demand predictions for specific time points. This allows for advance scheduling of the charging process, ensuring that the battery is fully charged before the user's next use, avoiding interruptions due to insufficient power during high-frequency use. Based on the next battery power demand forecast, the maximum safe charging power is dynamically calculated to ensure that the charging power matches the battery demand. This avoids overheating caused by excessively rapid charging and ensures that the battery is fully charged when needed, preventing insufficient battery power. Precise calculation of the maximum safe charging power minimizes the risk of damage from excessive current, extending battery life and preventing overcharging or overheating. The system monitors battery voltage, temperature, internal resistance, and other parameters in real time during charging and adjusts the charging strategy accordingly. This real-time dynamic control ensures safety during charging and promptly detects potential battery faults or anomalies. Dynamic temperature change characteristics are generated based on battery state parameters, capturing the amplitude and rate of temperature changes during charging, analyzing temperature fluctuation trends, and dynamically adjusting accordingly. This mechanism avoids battery damage or safety issues caused by overheating and enhances the stability of the charging process. Rolling time window predictions based on dynamic temperature change characteristics allow for more accurate analysis of battery temperature trends, and real-time adjustment of charging power based on the prediction results. The linkage between temperature control and power optimization minimizes battery overheating and provides the optimal charging strategy based on the real-time battery status. Intelligent charging power adjustment can meet users' power needs while avoiding overheating caused by excessive charging power, thereby extending battery life and improving overall charging efficiency. By monitoring battery status parameters (such as battery voltage, temperature, and current) in real time, the system can accurately determine whether there is a risk of overcharging. Once a potential overcharge is detected, the system will immediately adjust the charging strategy, taking measures such as trickle charging or stopping charging to prevent battery damage or safety hazards.Through self-learning collaborative control optimization, the system can automatically adjust and optimize its charging strategy based on historical data and real-time feedback during charging. This adaptive capability ensures that the charging process remains in an optimal state of safety and efficiency under varying environmental and usage conditions. Through its intelligent charging control and protection model, the system can not only accurately determine the safety of the charging process but also adjust its strategy in a timely manner according to user habits, ambient temperature, and other factors, thereby providing a more personalized and intelligent charging protection experience and further enhancing the user experience of the electric screwdriver.

[0013] This specification provides a battery charging protection system for an electric screwdriver, used to perform the battery charging protection method for an electric screwdriver as described above, comprising:

[0014] The usage module is used to obtain historical operation monitoring logs of electric screwdrivers; and to perform personalized user usage demand analysis on the historical operation monitoring logs of electric screwdrivers, thereby generating historical usage demand evolution data.

[0015] The power demand forecasting module is used to decompose historical usage demand evolution data into demand over multiple time periods and make comprehensive power demand predictions to generate the next battery power demand forecast.

[0016] The safe charging power calculation module calculates the maximum safe charging power based on the predicted battery power demand for the next time, and generates the maximum safe charging power for the battery.

[0017] The temperature change status module is used to perform real-time charging control based on the battery's maximum safe charging power and to monitor battery status parameters in real time; and to generate dynamic temperature change status characteristics based on the battery status parameters.

[0018] The charging power adjustment module is used to make rolling predictions of time windows based on dynamic temperature change characteristics, and to intelligently adjust and optimize the maximum safe charging power of the battery, thereby constructing an intelligent power optimization strategy.

[0019] The collaborative control module is used to make overcharge protection decisions based on the battery state parameters, and to perform self-learning collaborative control optimization based on the intelligent power optimization strategy to build an intelligent charging control and protection model.

[0020] This invention, by acquiring and analyzing historical logs, can generate precise, personalized demand data based on different user scenarios, workloads, and usage frequencies. This allows charging strategies to better adapt to actual user needs, avoiding a "standardized" approach. Through the evolution of historical usage data, the module can reveal changes in user usage patterns, helping to predict future battery power needs. This not only improves battery efficiency but also promptly detects potential overuse or abnormal battery behavior. Based on the generated historical usage demand evolution data, the system can identify the battery's actual load and power needs in advance, helping to optimize charging cycles and prevent battery damage from over-discharge or over-charge due to prolonged use. By decomposing historical demand data into time periods, it can accurately identify differences in power demand across different time periods. For example, a screwdriver's power demand differs under high and low load conditions. Precise demand decomposition helps avoid inefficient battery use or overcharging. By integrating multiple factors (such as load, battery health, and usage time), it accurately predicts future battery power needs. Accurately predicting the power demand for the next charge ensures optimized charging time and amount. Power prediction makes charging management more intelligent, ensuring that the battery is always charged on demand, avoiding battery damage caused by overcharging or undercharging. It calculates safe charging power based on battery demand, preventing overheating, swelling, or aging caused by excessive charging power. By intelligently calculating the maximum safe charging power, it ensures the battery receives the fastest possible charging speed within a safe range, while avoiding any risks that could damage the battery. This helps extend battery life. When calculating charging power, it considers not only the battery's current power demand but also its health status, ensuring that each charge is at its optimal state. Real-time monitoring of temperature changes during battery charging allows for timely identification and adjustment of temperature anomalies. This ensures the battery is not damaged by overheating, avoiding battery damage caused by excessive temperature. Generating dynamic temperature change characteristics reflects the temperature change trend during battery charging in real time. Based on these characteristics, the system can predict future temperature fluctuations and make corresponding charging adjustments. Through precise monitoring and dynamic analysis, it avoids the risk of localized overheating of the battery, ensuring balanced battery temperature control during charging. By predicting dynamic temperature changes, the system can dynamically adjust the charging power. When the temperature during charging is about to exceed the safe range, the charging power is automatically reduced to ensure that the battery remains in an optimal temperature control state throughout the charging process. During charging power adjustment, the system optimizes based on real-time temperature data and battery health status, thereby improving charging efficiency and reducing unnecessary energy loss. The intelligent power regulation strategy adjusts the charging power according to the battery's real-time condition, balancing charging speed and battery protection. This avoids overcharging and overheating while efficiently utilizing the battery and reducing energy waste.The collaborative control module continuously optimizes the charging strategy through a self-learning mechanism. With increasing usage, the system intelligently adjusts based on battery health, temperature changes, and charging history. This ensures that each charge adheres to the optimal strategy, improving battery protection. This module integrates all battery state parameters and dynamic changes during charging to construct an intelligent charging protection model. Through real-time collaborative control, it ensures that every decision during charging is adaptively optimized, improving battery lifespan and safety. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the steps of a battery charging protection method for an electric screwdriver according to the present invention;

[0022] Figure 2 This is a detailed flowchart illustrating the implementation steps of step S1.

[0023] Figure 3 This is a detailed flowchart illustrating the implementation steps of step S2;

[0024] Figure 4 This is a flowchart illustrating the detailed implementation steps of step S3. Detailed Implementation

[0025] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0026] This application provides a battery charging protection method and system for an electric screwdriver. The execution entity of the battery charging protection method and system for the electric screwdriver includes, but is not limited to, mechanical equipment, data processing platforms, cloud server nodes, network upload devices, etc., which can be considered as general computing nodes in this application. The data processing platform includes, but is not limited to, at least one of an audio-visual management system, an information management system, and a cloud data management system.

[0027] Please see Figures 1 to 4 This invention provides a battery charging protection method for an electric screwdriver, the method comprising the following steps:

[0028] Step S1: Obtain the historical operation monitoring log of the electric screwdriver; perform personalized user usage demand analysis on the historical operation monitoring log of the electric screwdriver to generate historical usage demand evolution data;

[0029] Step S2: Decompose the historical usage demand evolution data into multi-period demand and make a comprehensive power demand prediction to generate the next battery power demand forecast.

[0030] Step S3: Calculate the maximum safe charging power based on the next predicted battery power demand, and generate the maximum safe charging power for the battery.

[0031] Step S4: Perform real-time charging control based on the battery's maximum safe charging power and monitor battery status parameters in real time; generate dynamic temperature change characteristics based on the battery status parameters;

[0032] Step S5: Based on the dynamic temperature change characteristics, perform rolling prediction of the time window and intelligently adjust and optimize the maximum safe charging power of the battery to build an intelligent power optimization strategy.

[0033] Step S6: Make overcharge protection decisions based on the battery state parameters, and perform self-learning collaborative control optimization based on the intelligent power optimization strategy to build an intelligent charging control and protection model.

[0034] This invention, through in-depth analysis of historical operation logs, can gain insights into the actual usage patterns and behavioral characteristics of different users, ensuring personalized battery management based on individual needs. By analyzing historical usage data, it can track and predict future user behavior, generating accurate demand evolution data. This provides a reliable foundation for subsequent battery charging demand prediction, ensuring that charging strategies can be tailored to actual usage needs. Utilizing historical data and demand evolution models, battery charging needs can be planned in advance for different usage scenarios, avoiding device usage limitations due to insufficient battery power during high-demand periods. By decomposing and analyzing historical usage demand evolution data by time period, demand prediction can be accurate to specific time periods, greatly improving the accuracy of charging prediction. This segmentation reflects the specific usage frequency of users in different time periods, helping to accurately judge future power needs. Combining multi-time period demand decomposition not only estimates the overall battery power demand but also generates precise power demand predictions for specific time points. This allows for advance scheduling of the charging process, ensuring that the battery is fully charged before the user's next use, avoiding interruptions due to insufficient power during high-frequency use. Based on the next battery power demand forecast, the maximum safe charging power is dynamically calculated to ensure that the charging power matches the battery demand. This avoids overheating caused by excessively rapid charging and ensures that the battery is fully charged when needed, preventing insufficient battery power. Precise calculation of the maximum safe charging power minimizes the risk of damage from excessive current, extending battery life and preventing overcharging or overheating. The system monitors battery voltage, temperature, internal resistance, and other parameters in real time during charging and adjusts the charging strategy accordingly. This real-time dynamic control ensures safety during charging and promptly detects potential battery faults or anomalies. Dynamic temperature change characteristics are generated based on battery state parameters, capturing the amplitude and rate of temperature changes during charging, analyzing temperature fluctuation trends, and dynamically adjusting accordingly. This mechanism avoids battery damage or safety issues caused by overheating and enhances the stability of the charging process. Rolling time window predictions based on dynamic temperature change characteristics allow for more accurate analysis of battery temperature trends, and real-time adjustment of charging power based on the prediction results. The linkage between temperature control and power optimization minimizes battery overheating and provides the optimal charging strategy based on the real-time battery status. Intelligent charging power adjustment can meet users' power needs while avoiding overheating caused by excessive charging power, thereby extending battery life and improving overall charging efficiency. By monitoring battery status parameters (such as battery voltage, temperature, and current) in real time, the system can accurately determine whether there is a risk of overcharging. Once a potential overcharge is detected, the system will immediately adjust the charging strategy, taking measures such as trickle charging or stopping charging to prevent battery damage or safety hazards.Through self-learning collaborative control optimization, the system can automatically adjust and optimize its charging strategy based on historical data and real-time feedback during charging. This adaptive capability ensures that the charging process remains in an optimal state of safety and efficiency under varying environmental and usage conditions. Through its intelligent charging control and protection model, the system can not only accurately determine the safety of the charging process but also adjust its strategy in a timely manner according to user habits, ambient temperature, and other factors, thereby providing a more personalized and intelligent charging protection experience and further enhancing the user experience of the electric screwdriver.

[0035] In the embodiments of the present invention, see Figure 1 This is a flowchart illustrating the steps of a battery charging protection method for an electric screwdriver according to the present invention. In this example, the steps of the battery charging protection method for the electric screwdriver include:

[0036] Step S1: Obtain the historical operation monitoring log of the electric screwdriver; perform personalized user usage demand analysis on the historical operation monitoring log of the electric screwdriver to generate historical usage demand evolution data;

[0037] In this embodiment, the data source for storing the historical operation monitoring logs of the electric screwdriver is identified and determined. This data typically includes information such as records from the device's built-in sensors, user operation records, and charging status. After confirming the data source, an extraction strategy is developed to ensure all relevant data is obtained. The data format (e.g., CSV, JSON) and storage location (e.g., local database, cloud storage) need to be clearly defined to ensure smooth access during the extraction process. Appropriate data extraction tools (e.g., ETL tools or database query languages) are used to extract the historical operation monitoring logs from the identified data source. The extracted data should include timestamps, usage duration, usage frequency, charging records, and user operations. During the extraction process, data privacy and security policies must be followed to avoid disclosing sensitive user information. Any anomalies during the extraction process should be recorded for subsequent review. The extracted historical operation monitoring logs are preprocessed to clean and organize the data. This process includes removing duplicate records, filling in missing values, and standardizing the data format. Data cleaning can be achieved using statistical methods and data processing tools (e.g., Pandas). During preprocessing, data consistency and integrity are ensured so that subsequent analysis can provide accurate results. A framework for analyzing personalized user needs is designed to determine the analysis objectives and content. This framework should include analysis of user habits, frequency, usage duration, and different usage scenarios. Identify key performance indicators (KPIs), such as average usage duration, most frequently used functions, and charging cycles, to extract this information from historical data. Select appropriate data analysis methods, such as descriptive statistical analysis, cluster analysis, or association rule analysis. Descriptive statistical analysis helps understand overall user usage patterns, while cluster analysis can classify similar user groups. Set the parameters required for the analysis, such as time periods (e.g., the past three months, six months), and usage frequency thresholds, to facilitate grouping and comparison. Apply the selected data analysis methods to conduct in-depth analysis of the preprocessed historical operation monitoring logs. Extract personalized user usage needs characteristics and generate corresponding statistical data and visualizations. For example, by aggregating usage frequency and duration, identify user usage patterns within specific time periods, such as peak usage times and frequently used functions. Use visualization tools (such as charts or dashboards) to display the analysis results for intuitive understanding of user needs. Based on the results of the personalized user needs analysis, construct historical usage needs evolution data. This data should reflect changes in user usage across different time periods, providing time-series data to observe trends and changes in demand. Data should be aggregated by setting time periods (e.g., days, weeks, months) to calculate metrics such as user frequency, usage duration, and number of charges within each period. Historical usage evolution data should be integrated into a unified data structure to ensure accuracy and consistency. This structure should include information such as time series, usage frequency, and feature usage patterns for subsequent analysis and comparison.

[0038] Step S2: Decompose the historical usage demand evolution data into multi-period demand and make a comprehensive power demand prediction to generate the next battery power demand forecast.

[0039] In this embodiment, the first step is to clarify the objective of demand decomposition. The objective is to identify patterns in users' electricity demand over different time periods by analyzing historical usage demand evolution data. This will help to more accurately predict the next battery power demand. The analysis time periods should be set, such as daily, weekly, and monthly, to capture user usage patterns at different time scales. For example, some weekdays may have higher usage frequency, while weekends may have lower frequency. A suitable demand decomposition method should be selected, typically time series analysis. Specifically, seasonal decomposition (such as STL decomposition) can be used to extract trend, seasonal, and random components. The indicators to be analyzed, such as electricity consumption, usage frequency, and charging frequency, should be determined to comprehensively reflect changes in demand. Historical usage demand evolution data should be organized into a format suitable for time series analysis, ensuring the data is arranged chronologically and filling in any missing values. The data should include timestamps and corresponding electricity consumption data, such as hourly and daily consumption. Statistical tools should be used for data visualization to initially observe data trends and seasonality. For example, a line graph of electricity consumption can be drawn to visually understand changes in electricity demand. The selected decomposition method is applied to perform multi-period demand decomposition on historical usage demand evolution data. Seasonal decomposition extracts trend, seasonal, and random components for different time periods. This helps understand changes in user electricity demand across different time periods. The decomposition results are recorded, including trend components (long-term variations), seasonal components (periodic variations), and random components (irregular fluctuations) for subsequent analysis and comparison. The different components obtained from the decomposition are stored in a database, ensuring that the time-series data for each component is traceable. Each record should include a timestamp and the corresponding demand component for later use. The impact of each component on electricity demand is analyzed to identify the main influencing factors. For example, observing whether electricity consumption on certain workdays is significantly higher than on other days provides a basis for future electricity demand forecasts. A model for comprehensive electricity demand forecasting is determined, typically using a weighted average method or regression analysis. The weighted average method can forecast future electricity demand by assigning weights to each component, while regression analysis can consider the relationships between multiple factors. A forecasting period is set; for example, the next electricity demand forecast can be based on usage patterns on upcoming workdays or weekends. The decomposed trend and seasonal components are integrated for comprehensive electricity demand forecasting. Based on the characteristics of historical data, appropriate weights are assigned to ensure the reasonableness of different components in the forecast. The next battery demand forecast is calculated, reflecting the actual electricity demand of users in the upcoming period. For example, if higher electricity consumption is predicted for next week's workdays, the corresponding battery demand should also increase.

[0040] Step S3: Calculate the maximum safe charging power based on the next predicted battery power demand, and generate the maximum safe charging power for the battery.

[0041] In this embodiment, the objective of calculating the maximum safe charging power of the battery is clearly defined: to ensure that the battery can be charged safely and effectively without the risk of overheating or overcharging during the charging process. The maximum safe charging power should be calculated based on the predicted value of the next battery power demand to ensure that the charging process can meet the user's needs. The unit of charging power is set, usually expressed in watts (W) or milliampere-hours (mAh) for subsequent calculation and comparison. Relevant parameters affecting charging power are collected, including the battery's rated capacity, current charge level, charging efficiency, charging temperature, and battery chemical characteristics. These parameters will directly affect the calculation of the maximum safe charging power. For example, lithium-ion batteries typically have the best charging efficiency at 25°C, so the temperature of the charging environment needs to be considered when calculating the power. The formula for calculating the maximum safe charging power of the battery is designed as P(max) = C(next) / T(charge), where P(max) is the maximum safe charging power, C(next) is the predicted value of the next battery power demand, and T(charge) is the estimated charging time, which is estimated based on historical data and user habits. For example, if a user typically charges for 4 hours on weekdays, then T(charge) can be set to 4 hours. This estimate can be derived by analyzing the user's charging frequency and habits, ensuring the charging time is reasonable. The calculated maximum safe charging power is verified to ensure it is within the battery's safe charging range. According to the battery manufacturer's specifications, confirm whether this charging power meets the battery's maximum charging power standard. If the battery's maximum safe charging power is 60W, then a calculated 50W is safe. The calculated maximum safe charging power and related parameters are recorded in a database, ensuring each record includes a timestamp, predicted power demand, charging time, and calculation results for subsequent analysis and auditing. This record will help analyze future charging needs and strategy improvements, ensuring the effectiveness of the battery management system.

[0042] Step S4: Perform real-time charging control based on the battery's maximum safe charging power and monitor battery status parameters in real time; generate dynamic temperature change characteristics based on the battery status parameters;

[0043] In this embodiment, a charging control strategy is designed, including logic for adjusting the charging power. The charging power should be dynamically adjusted based on the real-time state of the battery and the maximum safe charging power. For example, if the battery temperature rises, the system should automatically reduce the charging power. A charging power adjustment range is set to ensure that the charging power remains within a safe range under all circumstances. This can be achieved using PWM (Pulse Width Modulation) technology for smooth power adjustment. During charging, the monitoring system acquires battery state parameters in real time and compares them with the set maximum safe charging power. If the real-time monitored current or temperature exceeds a safety threshold, the system should immediately adjust the charging power. For example, if the maximum safe charging power is 50W, but the real-time monitored battery temperature reaches an overheating threshold (e.g., 60°C), the charging power should be reduced to 30W to ensure the safety of the charging process. During charging, all relevant data, including battery voltage, current, temperature, and charging power, are recorded in real time. Each record should include a timestamp for subsequent analysis and auditing. This data will be used to evaluate the effectiveness and safety of the charging process and, if necessary, provide a basis for subsequent charging strategies. A framework for dynamic temperature change characteristic analysis is designed, determining the analysis objectives and required parameters. The goal is to generate characteristic data reflecting battery temperature change trends by monitoring battery state parameters in real time. This involves identifying the temperature-related indicators to be analyzed, such as temperature gradient, maximum rate of temperature change, and temperature fluctuation range. Using the real-time monitored battery temperature data, dynamic temperature change characteristics are calculated. For example, the trend of temperature change is observed, and the rate of temperature change, fluctuation amplitude, and average temperature are calculated. Statistical analysis methods (such as moving averages or weighted averages) are used to smooth the temperature data to remove noise and ensure the accuracy and reliability of the generated characteristic data.

[0044] Step S5: Based on the dynamic temperature change characteristics, perform rolling prediction of the time window and intelligently adjust and optimize the maximum safe charging power of the battery to build an intelligent power optimization strategy.

[0045] In this embodiment, based on dynamic temperature change characteristics, a rolling time window prediction is implemented to estimate the battery's temperature change trend over a future period. This provides a basis for adjusting charging power, ensuring the safety and efficiency of the charging process. A prediction time window is set, such as 5 minutes, 10 minutes, or 30 minutes, to adapt to the needs of different charging scenarios. This window should be adjusted according to the user's charging habits and battery usage. A suitable time series prediction method is selected, such as Autoregressive Moving Average (ARIMA), Long Short-Term Memory (LSTM), or simple exponential smoothing. These methods can fully utilize historical temperature data to capture the trend and periodicity of temperature changes. The input features of the model are determined, including past temperature data, charging power, and other relevant parameters, to enable effective prediction. Dynamic temperature change characteristic data is collected and prepared, ensuring the data is arranged chronologically and cleaned. This includes information such as temperature changes, charging power, and timestamps for subsequent analysis. Statistical tools are used to visualize temperature change trends, initially observing the regularity and fluctuations of the data to support model selection. If a machine learning model (such as LSTM) is used, model training is required. Historical temperature data was divided into training and test sets to evaluate the model's generalization ability. During model training, appropriate hyperparameters were used, and model performance was optimized through cross-validation. The model's accuracy was validated to ensure it can effectively predict future temperature changes.

[0046] During charging, a trained model is used for rolling predictions within a time window. Whenever new temperature data is recorded, the input features are updated, and the prediction is repeated to obtain the temperature change trend over a future period. The results of each prediction are recorded, including the predicted temperature value and the corresponding time, for subsequent analysis and feedback. Based on the rolling prediction results within the time window, an intelligent charging power adjustment strategy is designed. The goal is to dynamically adjust the charging power according to predicted temperature changes to prevent battery overheating and extend battery life. The adjustment logic is defined; for example, if the predicted temperature will rise to a critical value within the next 10 minutes, the system should automatically reduce the charging power; conversely, when the temperature drops and remains within a safe range, the charging power can be moderately increased. During charging, temperature changes and prediction results are monitored in real time, and the charging power is adjusted according to the set adjustment strategy. For example, if the predicted temperature will reach 70°C within the next 5 minutes, the system should immediately reduce the charging power from 50W to 30W. The charging power adjustment is recorded, including the power values ​​before and after the adjustment, timestamps, and relevant battery status information, for subsequent analysis.

[0047] Step S6: Make overcharge protection decisions based on the battery state parameters, and perform self-learning collaborative control optimization based on the intelligent power optimization strategy to build an intelligent charging control and protection model.

[0048] In this embodiment, battery status parameters that need to be monitored in real time are defined, including battery voltage, current, temperature, and charging status. The monitoring system is ensured to acquire this data promptly and process information from different sensors. A data acquisition system is configured to ensure a high sampling rate to capture changes in battery status in a timely manner. For example, the system is set to collect battery voltage and temperature data once per second. Overcharge protection decision logic is designed to determine whether protective measures need to be implemented based on real-time monitoring data. The decision logic should include multiple conditions, such as: triggering overcharge protection if the battery voltage exceeds 4.2V; triggering overheat protection if the battery temperature exceeds 65°C. Decision priorities are set to ensure that when multiple protection conditions are triggered simultaneously, the system prioritizes the most important protection measure. During charging, battery status parameters are monitored in real time, and judgments are made according to the set decision logic. For example, when the battery voltage reaches 4.1V and the temperature is 60°C, the system continues charging; but when the battery voltage reaches 4.3V, charging is immediately stopped and an alarm is issued. The results of each protection decision are recorded, including timestamps, parameter values, and decision results, for subsequent analysis and auditing. This data will provide a basis for optimizing protection decisions. A self-learning mechanism will be constructed, enabling the system to continuously optimize the charging control and protection model based on historical charging data and real-time monitoring data. This self-learning mechanism should be based on machine learning algorithms, capable of identifying and learning battery performance and its behavior under different environmental conditions. A dataset required for model training will be set, including current, voltage, and temperature changes during charging and their corresponding overcharge protection decision records, for model training and updates. Self-learning algorithms (such as decision trees and random forests) will be used for model training to optimize the charging control and protection strategy. Analysis of a large amount of historical data will identify key factors affecting the charging process, providing a basis for intelligent charging control. During real-time charging, the trained model will be applied for dynamic decision-making, combined with real-time monitored battery state parameters, to optimize charging power and protection decisions. For example, based on historical data, the system can predict battery behavior under specific conditions, thereby taking protective measures in advance.

[0049] In this embodiment, see Figure 2 The diagram below illustrates the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0050] Step S11: Obtain the historical operation monitoring log of the electric screwdriver;

[0051] Step S12: Detect outlier data in the historical operation monitoring log of the electric screwdriver and mark multiple outlier points;

[0052] Step S13: Perform adaptive filtering on multiple outliers to generate a filtering optimization monitoring log;

[0053] Step S14: Perform user-personalized usage preference mining on the filtering optimization monitoring logs to generate user-personalized usage preference features;

[0054] Step S15: Based on the user's personalized usage preference characteristics, the historical usage demand evolution is carried out to generate historical usage demand evolution data.

[0055] In this embodiment, the required data types for monitoring are determined, including the electric screwdriver's running time, speed, torque, fault codes, temperature, and operating environment. This data will be used for subsequent anomaly detection and user preference analysis. Appropriate data acquisition tools are selected to ensure stable and accurate recording of the equipment's operating status. Built-in sensors and data loggers can be used to periodically upload data to a database or cloud server. The collected monitoring data is stored in a structured format in the database. Each record should include a timestamp, device ID, operating parameters, and status information for subsequent analysis. A periodic backup strategy for data storage is established to ensure the integrity and security of historical data. Appropriate access permissions are provided to ensure that only authorized users can access and analyze this data. Real-time monitoring is implemented during data acquisition to ensure data accuracy. The data acquisition equipment is regularly calibrated and maintained to avoid data loss or errors due to equipment failure. The status of each data acquisition is recorded, including the number of successful acquisitions and any anomalies, to ensure data integrity is considered during subsequent analysis. Appropriate anomaly detection algorithms are selected, such as statistical methods (e.g., Z-score) or machine learning algorithms (e.g., Isolation Forest or Local Outlier Factor (LOF)). These methods effectively identify data points that significantly deviate from normal operating patterns. Detection parameters, such as a Z-score threshold (typically ±3), are set to determine which data points are considered anomalies. Historical operational monitoring logs are preprocessed, including data cleaning, normalization, and noise reduction. The quality of data input into the anomaly detection algorithm is ensured to improve detection accuracy. Missing and outlier values ​​are handled to ensure dataset integrity. Missing data can be imputed using interpolation, or outliers can be replaced with the mean / median. The selected anomaly detection algorithm is run to analyze the historical monitoring logs and identify multiple outliers. The characteristics of each outlier are recorded, including timestamps, specific parameter values, and their degree of anomalousness. An anomaly log containing the identified outliers is generated for subsequent analysis and processing. An adaptive filtering strategy is developed based on the characteristics of the outliers. Different filtering criteria can be set, such as using different processing methods (e.g., removal, replacement, or correction) for different types of anomalies. Filtering parameters, such as thresholds and processing methods for outliers, are determined. For example, setting removal for speed anomalies and correction for temperature anomalies. The identified outliers are processed one by one. Based on the established filtering strategy, these outlier data points are removed, replaced, or corrected, and the results of each processing step are recorded. During processing, the traceability of the original data is ensured, and data records before and after processing are retained for subsequent auditing and analysis. The processed data is reorganized into a filtering optimization monitoring log, ensuring a clear data structure for easy use and analysis. Version control is implemented for the optimized logs to ensure the integrity and traceability of historical data. The definition of personalized user preferences is determined, including the frequency of use of different functions, preference settings, and frequently used modes.User behavior patterns can be extracted by analyzing historical usage data. Define preference mining metrics and parameters, such as usage frequency, recent usage time, and usage duration, to quantify user preferences. Select appropriate data mining techniques, such as cluster analysis, association rule mining, or decision trees, to identify user preference characteristics. Determine the parameters of the mining algorithm, such as the number of clusters and support threshold, to extract clear user preference features. Perform personalized user preference mining on filtering optimization monitoring logs to generate user preference features. Record detailed information for each feature, including feature value and frequency of occurrence. Design an analytical framework for user demand evolution, determining how to derive the evolutionary path of historical usage needs from user preference features. Set the data analysis timeframe, such as the past 6 months or 12 months, to observe trends in user demand changes. Select appropriate data analysis methods, such as time series analysis or trend analysis, to identify patterns in user demand evolution. Determine key analysis metrics, such as demand change rate and evolution of frequently used functions, as evaluation criteria for demand evolution. Combine the mined personalized user preference features with historical data to conduct demand evolution analysis. Identify trends in user needs and record the key milestones and reasons for each evolving need. Generate historical usage need evolution data, including evolution paths and trend charts, for subsequent decision-making and optimization.

[0056] In this embodiment, step S14 specifically involves the following steps:

[0057] Dynamically analyze usage behavior in the filtering and optimization monitoring logs to extract screwdriver usage behavior data;

[0058] Calculate historical usage frequency from screwdriver usage behavior data and extract usage frequency data;

[0059] Extract the timestamp of each use of the screwdriver usage behavior data;

[0060] The usage timestamp is used for each usage timestamp to generate a usage timestamp sequence;

[0061] The usage cycle characteristics of screwdrivers are obtained by analyzing the usage timestamp sequence.

[0062] The duration of each use is calculated based on the timestamp of each use.

[0063] Based on the usage duration, screwdriver usage cycle characteristics, and usage frequency data, we can mine personalized user usage preferences to generate personalized user usage preference features.

[0064] This embodiment defines a framework for dynamic usage behavior analysis, clarifying the analysis objective: extracting screwdriver usage behavior data from the filtering and optimization monitoring logs. Usage behavior data includes the status of each use, usage parameters (such as speed and torque), and potential fault information. A time frame for analysis is set, for example, data from the past six months, to observe changes in user usage patterns and behaviors. Ensuring data completeness and accuracy is crucial for the analysis. Relevant usage behavior data is extracted from the filtering and optimization monitoring logs, ensuring that the extracted data includes timestamps, usage patterns, fault records, and usage parameters. This process is automated using data parsing tools or custom scripts. The extracted data undergoes preliminary cleaning and formatting to ensure consistency. Duplicate records and missing values ​​are removed to improve data quality. Statistical methods (such as mean and standard deviation) are used to detect and handle outliers. The calculation criteria for usage frequency are determined, typically including total usage counts, daily or weekly usage frequency, etc. The calculation period is set to one week, calculating the number of times a user uses the screwdriver each week. Appropriate calculation tools are selected, using database queries or data analysis software (such as Excel or Python) for frequency statistics. By analyzing the extracted usage behavior data, the number of times each user uses the screwdriver within the set period is calculated. Record weekly usage frequency data to generate a usage frequency statistics table. Associate the calculated usage frequency with basic user information (such as user ID, device used, etc.) to form a structured usage frequency dataset for subsequent analysis. Identify the timestamp of each operation in the extracted usage behavior data. Timestamps are crucial for analyzing usage patterns and behaviors, providing a foundation for subsequent serialization processing. Ensure the accuracy of timestamp records, including device startup time, usage end time, and operation duration. Extract the timestamp for each use from the cleaned usage behavior data and record the timestamp format (e.g., YYYY-MM-DDHH:MM:SS). Store the extracted timestamp data in a structured database, ensuring each record includes the user ID and related operation information for subsequent analysis. Select an appropriate time series serialization method to sort and format the extracted timestamp data, forming a continuous time series. Ensure the integrity of the time series for subsequent analysis. Use standard time series analysis methods, such as chronological ordering and removing duplicate timestamps. Sort the extracted timestamp data chronologically to generate a usage timestamp sequence. Record the time interval between each use to analyze usage patterns. The generated timestamp sequences should be stored as arrays or lists for easy periodic analysis and feature extraction. Choose appropriate periodicity analysis methods, such as Fourier transform or autocorrelation function analysis, to identify periodic features in the usage timestamp sequences. Determine the periodic range for analysis, such as daily, weekly, or monthly, to better capture user habits. Perform periodic analysis on the timestamp sequences to identify common usage cycle characteristics.Record the duration and frequency of each cycle. Generate visual charts of the cycle analysis results to help understand user usage patterns. Store cycle feature information in a database for subsequent mining of personalized user characteristics. Set calculation criteria for usage duration, typically including the difference between the start and end times of each use. Ensure the accuracy of the calculations, avoiding inaccurate usage duration calculations due to timestamp errors. Use simple mathematical calculations to derive the duration of each use, ensuring consistent units (e.g., seconds or minutes). Calculate the usage duration for each use based on the extracted usage timestamps, recording the start and end times for each use. Associate the calculation results with the corresponding usage records. Organize the usage duration data into a structured format and store it in a database for subsequent analysis and mining. Design a framework for personalized usage preference mining, integrating usage duration, usage cycle characteristics, and usage frequency data, clarifying the mining objectives and methods. Determine indicators of preference characteristics, such as frequently used time periods, average usage duration, and frequently used functions, to quantify user usage preferences. Utilize data mining techniques such as cluster analysis or decision trees to extract personalized user usage preference characteristics based on the integrated data. Analyze user frequency and duration of usage across different time periods to identify preferred usage patterns. Generate personalized usage preference reports, including individual user preferences, usage habits, and suggested improvements, to optimize product design and user experience in the future.

[0065] In this embodiment, see Figure 3 The diagram below illustrates the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0066] Step S21: Decompose the historical usage demand evolution data into multi-period demand decomposition to generate usage demand data for multiple time periods;

[0067] Step S22: Dynamically perceive demand trends in usage demand data across multiple time periods to generate usage behavior demand trend data;

[0068] Step S23: Perform trend change capture analysis on the usage behavior demand trend data within the period to generate behavioral demand change patterns;

[0069] Step S24: Based on the pattern of behavioral demand changes, predict the recent usage demand to obtain the next usage time and usage duration;

[0070] Step S25: Make a comprehensive prediction of the power demand based on the next usage time and usage duration, thereby generating a predicted value of the battery power demand for the next usage.

[0071] In this embodiment, a framework for multi-period demand decomposition is established to clarify the analysis objectives. The purpose of demand decomposition is to break down historical usage demand evolution data into time periods (e.g., daily, weekly, monthly) for easier subsequent analysis. An analysis time range is set, such as data from the past 12 months, to capture seasonal changes and usage patterns. Relevant usage records, including timestamps, usage duration, and usage frequency, are extracted from the historical usage demand evolution data. Data integrity is ensured for accurate demand decomposition. The extracted data is cleaned and standardized to remove missing values ​​and outliers, improving data quality. Sufficient sample size is ensured for each time period. Based on the defined time periods, data aggregation methods are used to decompose usage demand. For example, daily, weekly, and monthly averages can be used to calculate usage demand for each time period. Multiple time periods of usage demand data are generated, ensuring consistent data format for each period to facilitate subsequent analysis and comparison. This process can be implemented using pivot tables or time series analysis tools. Appropriate dynamic trend analysis methods are selected, such as moving averages, exponential smoothing, or time series analysis. These methods can effectively identify trends and seasonal changes in usage demand data. Determine the analysis parameters, such as the window size for moving averages (e.g., 7 days, 30 days) and the smoothing coefficient for exponential smoothing, to better capture the dynamic trends of demand changes. Perform dynamic trend analysis on usage demand data across multiple time periods to generate usage behavior demand trend data. Process the data for each time period using the selected analysis method to identify ongoing demand changes. Record the analysis results, including whether the trend is rising, falling, or stable, and generate visualizations to visually illustrate changes in usage behavior demand. Identify patterns of change within different periods (e.g., daily, weekly, monthly). Choose an appropriate period length to capture sufficient variation. For example, a week or a month can be selected for analysis. Choose appropriate data analysis methods, such as regression analysis, periodic analysis, or autocorrelation analysis. These methods can effectively identify patterns of demand changes within a period. Determine the analysis parameters, such as the independent and dependent variables in the regression model, and the lag number in the autocorrelation analysis, to ensure the accuracy of the analysis. Perform intra-period trend analysis on the usage behavior demand trend data to record patterns of demand changes. Identify demand peaks and troughs within specific time periods and analyze their possible causes. Generate reports on patterns of behavioral demand changes, recording the characteristics of changes within each period to provide a basis for subsequent demand forecasting. Select an appropriate forecasting model, such as ARIMA (Autoregressive Integral Moving Average) or SARIMA (Seasonal Autoregressive Integral Moving Average), to forecast demand based on historical data. Determine the model parameters, such as the autoregressive order, differencing order, and moving average order, to ensure model accuracy. Based on the captured patterns of behavioral demand changes, input historical data into the forecasting model for analysis.Record the prediction results, including the next usage time and expected usage duration. Validate the prediction results using cross-validation methods (such as hold-out) to evaluate the model's accuracy and reliability. Store the prediction results in a database to ensure traceability. Simultaneously, generate corresponding visualizations to facilitate intuitive user understanding of the prediction results. Develop appropriate usage strategies based on the prediction results to achieve optimal results in the next use. Determine the calculation model for power demand, considering factors such as usage duration, power consumption, and battery capacity. The power of an electric screwdriver typically falls within a certain range (e.g., 20W to 50W), and should be adjusted according to actual usage. Set model parameters, such as the battery's rated voltage, capacity (e.g., 2000mAh), and power consumption, to accurately estimate power demand. Calculate the required power demand based on the predicted usage time and duration. Use the formula: Power (Wh) = Power (W) × Usage Duration (h) to obtain the required power. Considering the battery's health and remaining charge, predict the battery power demand required for the next use. Store the predicted battery power demand in a database for subsequent use and analysis. Simultaneously, a visual report of electricity demand is generated for easy user understanding. A feedback mechanism is established to continuously optimize the electricity demand prediction model based on comparisons between actual usage and forecast results, ensuring its long-term accuracy.

[0072] In this embodiment, see Figure 4 The diagram below illustrates the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0073] Step S31: Identify the current remaining battery power:

[0074] Step S32: Calculate the power demand deviation based on the next battery power demand forecast to obtain the power demand deviation value.

[0075] Step S33: Based on the next usage time, perform current time difference statistics to generate available charging time;

[0076] Step S34: Calculate the maximum safe charging power based on the available charging time and the deviation value of power demand, and generate the maximum safe charging power of the battery.

[0077] In this embodiment, a suitable battery status monitoring device is selected to ensure that it can acquire the battery's remaining power information in real time. Commonly used battery management systems (BMS) can provide key information such as voltage, current, and temperature to accurately calculate the remaining power. The monitoring frequency is determined, for example, once per minute or every five minutes, to promptly acquire information on changes in battery status. The battery management system collects the current battery voltage and current data. The remaining power is calculated using the formula: Remaining power (%) = Current voltage / Rated voltage × 100%. The collected data is processed in real time to ensure accuracy. Filtering algorithms (such as Kalman filtering) can be used to remove noise, ensuring the reliability of the acquired battery status information. The identified current remaining battery power is recorded in a database, ensuring that each data record includes a timestamp and relevant battery parameters for subsequent backtracking and analysis. An alarm mechanism is set up to promptly notify the user to charge when the remaining battery power falls below a certain threshold (e.g., 20%). The formula for calculating the power demand deviation is: Power demand deviation (Wh) = Next battery power demand prediction (Wh) - Current remaining power (Wh). This calculation intuitively reflects whether the battery meets the needs of the next use. To ensure accuracy, the remaining battery capacity needs to be converted to the same unit (e.g., Wh) for effective comparison. Calculations are performed based on the current remaining battery capacity obtained in step S31 and the battery demand prediction value in step S24. The battery demand deviation value is recorded, ensuring it is positive (indicating demand exceeds remaining capacity) or negative (indicating sufficient remaining capacity). A positive deviation value indicates charging is needed; a negative deviation value indicates the current capacity is sufficient for the next use. The battery demand deviation value is recorded in a database, ensuring each calculation has a corresponding timestamp and relevant parameters for subsequent analysis and tracking. A feedback mechanism is set up so that if the deviation value exceeds a certain threshold (e.g., 50Wh), the system should automatically remind the user to charge. The method for obtaining the next usage time point is determined to ensure its accuracy. This time point is usually provided by the prediction result in step S24 and recorded as a timestamp (e.g., YYYY-MM-DD HH:MM:SS). The available charging time is calculated using the difference between the current time and the next usage time point, using the formula: Available charging time (hours) = (next usage time point - current time) / 3600. Calculate the time difference based on the current system time and the next usage time. Record the available charging time, ensuring it is positive (indicating charging time) or zero (indicating no charging time). If the calculation result is negative, it means the next usage time has arrived, and the application should be started immediately. Record the calculated available charging time in the database to ensure data traceability and integrity. Add a timestamp and relevant information to each record for subsequent analysis. Based on the available charging time, the system can suggest the best time for the user to charge, ensuring the battery is fully charged before the next use.The formula for determining the safe charging power is typically: Maximum safe charging power (W) = Energy demand deviation (Wh) / Available charging time (h). This formula ensures that the battery can be safely charged to the required value within the available charging time. Considering battery safety charging standards, such as charging power being less than or equal to 80% of the battery's rated power, prevents overheating and damage. Using the energy demand deviation value from step S32 and the available charging time from step S33, the maximum safe charging power value is calculated according to the established formula. Ensure the calculation result is within the battery's safe charging range. If the calculation result exceeds the safe range, it should be adjusted to a safe charging power (e.g., 80% of the battery's rated power). Record the calculated maximum safe charging power value in a database, ensuring it is associated with a timestamp and relevant parameters for subsequent analysis.

[0078] In this embodiment, step S4 includes the following steps:

[0079] Step S41: Perform real-time charging control on the electric screwdriver according to the battery's maximum safe charging power, and monitor the battery status parameters in real time;

[0080] Step S42: Perform real-time temperature identification based on the battery status parameters and extract the real-time battery temperature parameters;

[0081] Step S43: Calculate the temperature change rate of the real-time battery temperature parameters and generate the temperature change rate value;

[0082] Step S44: Analyze the maximum temperature change range based on the real-time temperature parameters to generate the maximum temperature change range;

[0083] Step S45: Based on the temperature change rate value and the maximum temperature change amplitude, perform time-series temperature change evolution to construct a time-series temperature change curve;

[0084] Step S46: Perform dynamic temperature change trend analysis on the time-series temperature change curve to generate dynamic temperature change trend characteristics.

[0085] In this embodiment, the electric screwdriver's charging is controlled based on the calculated maximum safe charging power value. During charging, battery status parameters, including voltage, current, temperature, and charging time, are monitored in real time. These parameters are key factors in assessing battery health and charging safety. A Battery Management System (BMS) is used to collect battery status data, with a collection frequency set to once per second to ensure data real-time performance and accuracy. Battery status parameters during charging are recorded in a database, ensuring each record includes a timestamp, charging power, and battery status information for subsequent analysis. An alarm mechanism is implemented; when battery status parameters exceed a safety threshold (e.g., battery temperature exceeds 60°C), the system should automatically reduce the charging power or stop charging to prevent battery overheating. A suitable temperature sensor (e.g., thermocouple or NTC thermistor) is selected to ensure accurate measurement of battery temperature in the electric screwdriver's operating environment. The sensor should have fast response and high accuracy. Temperature sensors are installed at critical locations on the battery to accurately acquire real-time temperature data. The Battery Management System (BMS) is used for real-time temperature data acquisition. The data acquisition frequency is set to once per second to ensure the capture of rapid changes in battery temperature. The collected temperature data is processed in real time to ensure accuracy and consistency. Filtering algorithms (such as moving averages) can be used to remove transient noise. The extracted real-time battery temperature parameters are recorded in a database, ensuring each record has a timestamp and relevant battery status information for subsequent analysis and backtracking. An alarm mechanism is implemented; when the battery temperature exceeds a set safety threshold (e.g., 60°C), the system should automatically warn the user and take appropriate measures. The formula for calculating the temperature change rate is determined, typically: Temperature change rate (°C / s) = (Current temperature - Previous temperature) / Time interval. This formula effectively reflects the rate of battery temperature change. A time interval, typically 1 second, is set to ensure the real-time performance and accuracy of the temperature change rate calculation. The temperature change rate is calculated by comparing the temperature at each time point in the acquired temperature data. The calculated temperature change rate value is recorded each time, ensuring it is within a reasonable range. Data records of the temperature change rate are generated, ensuring each record includes a timestamp and the corresponding temperature value for subsequent analysis. The calculated temperature change rate values ​​are stored in a database to ensure traceability and integrity. Add timestamps and relevant parameters to each record for subsequent analysis. Using temperature change rate data, the system can analyze the battery's thermal management performance under different operating conditions, ensuring operation within safe limits. The analysis method for determining the maximum temperature change amplitude is typically: Maximum temperature change amplitude (°C) = Maximum recorded temperature - Minimum recorded temperature. By comparing the maximum and minimum values ​​in the temperature data, the battery's temperature fluctuation range can be identified. Set an analysis time period to statistically analyze the maximum temperature change amplitude within that period, typically using data from the most recent 10 or 30 minutes.Within a selected time period, extract real-time temperature parameter data and calculate the maximum and minimum temperatures within that period. Use statistical methods (such as range) to determine the maximum temperature variation range. Record the analysis results, ensuring that each calculation includes time period information for subsequent tracking. Record the maximum temperature variation range in the database, ensuring it is associated with a timestamp and relevant battery state parameters. Add analysis time period information to each record for subsequent analysis. Using the maximum temperature variation range data, the system can optimize the battery's thermal management strategy to ensure the battery operates within a safe range. Define the analytical framework for time-series temperature evolution, with the clear objective of constructing temperature change curves to visualize how battery temperature changes over time. Set the analysis time period, such as data from the most recent hour, to capture the dynamic process of temperature change. Plot the temperature change curve using real-time temperature parameters and temperature change rate values. Use the temperature value at each time point as the Y-axis and time as the X-axis to record the temperature change at each time point. Use graphics tools (such as Matplotlib or Excel) to generate visualization charts that visually display the shape and trend of the temperature change curve. Store the generated time-series temperature change curve results in the database for subsequent analysis and auditing. Ensure each record includes a timestamp and relevant parameters for easy traceability. Using temperature change curve data, the system can adjust charging strategies in real time to optimize battery thermal management. Define the objective of dynamic temperature change trend analysis: identify key features in the temperature change curve, such as the slope of temperature rise or fall, and fluctuation amplitude. Select appropriate analysis methods, such as regression analysis or Fourier transform, to capture the dynamic characteristics of temperature changes. Perform dynamic analysis on the time-series temperature change curve to extract key features, such as the rate of temperature change, fluctuation frequency, and thermal stability. This can be achieved by calculating the slope of the curve, root mean square (RMS), etc. Record the extracted dynamic temperature change trend features, ensuring they are associated with timestamps and relevant temperature data for subsequent analysis and application. Record the dynamic temperature change trend features in a database to ensure traceability and completeness. Add a timestamp and relevant parameters to each record for subsequent analysis. Using dynamic temperature change trend feature data, the system can optimize battery charging and discharging strategies, ensuring the battery operates efficiently within safe limits.

[0086] In this embodiment, the specific steps of step S5 are as follows:

[0087] Step S51: Obtain the real-time charging voltage based on the battery state parameters;

[0088] Step S52: Perform voltage fluctuation analysis on the real-time charging voltage to generate the real-time charging voltage;

[0089] Step S53: Perform time window rolling prediction on the dynamic temperature change characteristics based on the real-time charging voltage to generate temperature prediction values ​​for multiple time windows;

[0090] Step S54: Perform a battery health status assessment on the predicted temperature values ​​for multiple time windows to obtain a battery health status assessment value;

[0091] Step S55: Based on the battery health status assessment value, intelligent charging power adjustment and optimization is performed on the maximum safe charging power of the battery to construct an intelligent power optimization strategy.

[0092] In this embodiment, a battery charging voltage monitoring system is constructed to ensure real-time acquisition of the battery's charging voltage. This system should be connected to a Battery Management System (BMS) to obtain battery status parameters during charging, such as current and voltage. The monitoring frequency is determined, typically set to once per second, to ensure rapid changes in charging voltage are captured. Charging voltage data is acquired in real-time through the BMS. Data acquisition should include the battery's current voltage, charging current, and other relevant battery parameters for subsequent analysis. The acquired data is processed in real-time to ensure accuracy. Filtering algorithms (such as Kalman filtering) can be used to remove transient noise, ensuring reliable voltage information. Real-time charging voltage is recorded in a database, ensuring each record includes a timestamp, charging voltage, and related battery status information for subsequent analysis and backtracking. An alarm mechanism is set up; when the charging voltage exceeds a set safety threshold (e.g., 4.2V), the system should automatically warn the user and take appropriate measures. Methods for voltage fluctuation analysis are determined, typically employing statistical analysis and spectral analysis. Appropriate indicators, such as standard deviation, root mean square (RMS) value, and fluctuation amplitude, are selected to evaluate voltage stability. Define the analysis time window, such as data from the past 10 seconds or 1 minute, to perform statistical analysis of voltage fluctuations within that time period. Extract voltage values ​​within the specified time window from real-time charging voltage data, calculate the mean and standard deviation within that time window, and thus determine the voltage fluctuation situation. Record the analysis results, including the voltage mean, standard deviation, and fluctuation amplitude, for later use. Record the voltage fluctuation analysis results in a database, ensuring that each record includes a timestamp and relevant battery status information for subsequent analysis and tracking. Generate visual charts to intuitively display voltage fluctuations, helping users understand voltage stability during the charging process. Select a suitable rolling forecasting method, typically employing time series forecasting techniques such as Autoregressive Moving Average (ARIMA) or Long Short-Term Memory (LSTM) networks. Based on real-time charging voltage data, predict temperature changes for multiple future time windows. Determine the prediction time window length, such as 5 minutes, 10 minutes, and 30 minutes, to perform predictions at different time scales. Utilize real-time charging voltage data and dynamic temperature change characteristics to construct a time series model for temperature prediction. Input real-time charging voltage and historical temperature data to generate predicted temperature values ​​for multiple time windows. The prediction results for each time window are recorded and compared with actual temperature data to verify the accuracy of the prediction model. The generated multi-time-window temperature prediction values ​​are recorded in a database, ensuring they are associated with timestamps and relevant battery state parameters for subsequent analysis. Using the temperature prediction results, the system can take proactive measures to optimize battery charging strategies, ensuring safe and efficient charging. A framework for battery health status assessment is established, including assessment metrics such as charge cycle count, temperature variation, internal resistance, and capacity retention. Assessment standards and thresholds are set to accurately assess battery health status.A weighted scoring method is employed, assigning weights to different evaluation indicators to ensure the comprehensiveness and accuracy of the evaluation results. Battery health status is assessed based on generated multi-time-window temperature predictions and other battery state parameters. A score is calculated for each evaluation indicator, and the overall health status assessment value is derived. Evaluation results are recorded, including health status scores and detailed information for each evaluation indicator, for subsequent analysis and optimization. Battery health status assessment values ​​are recorded in a database to ensure traceability and completeness. Timestamps and relevant parameters are added to each record for subsequent analysis. A feedback mechanism is implemented: if the health status assessment value falls below a certain threshold (e.g., 70%), the system should prompt the user to check the battery status and consider replacement. An intelligent charging power adjustment strategy is designed based on the battery health status assessment value. For example, if the health status assessment value is high, the charging power can be increased; if the assessment value is low, the charging power should be reduced to ensure safety. Standards for charging power adjustment are determined, such as setting different charging power ranges based on the range of the health status assessment value (e.g., 0-60%, 60-80%, 80-100%). During charging, the charging power is dynamically adjusted based on the real-time monitored battery health status assessment value. PWM technology is used to achieve smooth adjustment of charging power, ensuring charging within a safe range. The details of each charging power adjustment are recorded, including the power values ​​before and after the adjustment, timestamps, and health status assessment values, for subsequent analysis.

[0093] In this embodiment, step S6 is as follows:

[0094] Step S61: Calculate the latest battery capacity based on the battery state parameters;

[0095] Step S62: Make overcharge protection decisions based on the latest battery capacity to generate an overcharge protection strategy;

[0096] Step S63: Perform self-learning collaborative control optimization on the intelligent power optimization strategy and overcharge protection strategy to build an intelligent charging control and protection model.

[0097] In this embodiment, the formula for calculating battery capacity is typically: Battery capacity (mAh) = (Charging current (A) × Charging time (h)) - Discharging current (A) × Discharging time (h). This formula reflects the actual capacity of the battery within a given time. Necessary battery state parameters are collected, including current voltage, charging current, discharging current, and charging / discharging duration, to ensure calculation accuracy. The battery's charging current, discharging current, and time parameters are collected in real time through the Battery Management System (BMS). The data acquisition frequency is set to once per second to capture changes in battery state. The collected data is processed in real time to ensure accuracy and consistency. A filtering algorithm is used to process transient noise, ensuring data reliability. Based on the collected battery state parameters, the latest battery capacity is calculated using the established formula. The current charging and discharging states are recorded for dynamic battery capacity updates. The calculated latest battery capacity is recorded in a database, ensuring that each record includes a timestamp and relevant battery state information for subsequent analysis and traceability. An overcharge protection strategy framework is designed, clearly defining the protection objectives and standards. Typically, overcharge protection is defined as the battery capacity reaching a certain percentage of its rated capacity (e.g., 90%-100%) to prevent overheating or damage. Methods for determining overcharge status include monitoring whether the battery voltage exceeds a set threshold (e.g., 4.2V), combined with real-time battery capacity data analysis. Based on the latest battery capacity, the system determines in real-time whether overcharge protection needs to be triggered. If the battery capacity exceeds the set threshold, the system should automatically adjust the charging power, reducing or stopping charging. The implementation process of overcharge protection decisions should be recorded, including the decision time, capacity value, and corresponding voltage data, ensuring traceability for each decision. The decision results of the overcharge protection strategy should be recorded in a database to ensure data integrity and traceability. Timestamps and relevant parameters should be added to each record for subsequent analysis. Suitable self-learning algorithms, such as reinforcement learning or adaptive control algorithms, should be selected to achieve coordinated control of intelligent power optimization and overcharge protection strategies. The algorithm should be able to continuously optimize the control strategy based on real-time data. Input parameters for the model should be set, including battery state parameters, charging power, capacity value, and temperature changes, to facilitate effective learning and adjustment. The system utilizes real-time data to learn intelligent power optimization and overcharge protection strategies. Based on historical data and real-time feedback, the system dynamically adjusts charging power and protection strategies to achieve optimal charging performance. Each control optimization process is recorded, including strategy parameters before and after optimization, implementation time, and relevant battery status information for subsequent analysis. The results of control optimization are recorded in a database to ensure data integrity and traceability. Timestamps and relevant parameters are added to each record for further analysis. The intelligent charging control and protection model is regularly evaluated and updated, and model parameters are optimized based on battery usage and performance feedback to ensure safe and efficient operation under different operating conditions.

[0098] In this embodiment, the specific steps of step S62 are as follows:

[0099] Define a charging protection threshold. Based on the predicted battery power demand for the next time, determine whether the latest battery capacity meets the power demand. If the latest battery capacity meets the power demand for the next time, compare the latest battery capacity with the charging protection threshold. If the charging protection threshold is less than or equal to the latest battery capacity, calculate the remaining charging time.

[0100] The minimum full charge power is calculated based on the remaining charging time, thus obtaining the minimum full charge power.

[0101] Trickle charging power control is implemented using the minimum full charge power to generate an overcharge protection strategy.

[0102] In this embodiment, a standard for determining the charging protection threshold is established. Typically, the charging protection threshold should be set between 90% and 95% of the battery's rated capacity. For example, if the battery's rated capacity is 2000mAh, the charging protection threshold can be set between 1800mAh and 1900mAh. The purpose of setting this threshold is to ensure that the battery is not overcharged during charging, avoiding battery damage and safety hazards. The set charging protection threshold is recorded in the Battery Management System (BMS) to ensure real-time monitoring of battery capacity changes during charging. The system should have an alarm mechanism to promptly notify the user and take appropriate protective measures when the battery capacity approaches or exceeds the charging protection threshold. During battery charging, the reasonableness of the set charging protection threshold is periodically verified. The effectiveness of the threshold is evaluated by monitoring the actual charging status and state parameters of the battery. If overcharging is still detected during charging, the charging protection threshold should be adjusted according to the actual situation to ensure its effectiveness and safety. The next predicted battery power demand value is obtained using a previous battery power demand prediction model. This value is usually calculated based on the user's usage habits and historical battery usage data. The accuracy and reliability of the predicted value are ensured for subsequent capacity assessment. The system compares the latest battery capacity with the predicted battery power demand for the next usage session to determine if the latest capacity meets the demand. If the latest battery capacity is greater than or equal to the predicted power demand, the battery can meet the next usage demand; otherwise, the system should remind the user to charge. The judgment results are recorded in the database, ensuring each record includes a timestamp and relevant battery status information for subsequent analysis and traceability. A feedback mechanism is implemented: when the judgment result is "not met," the system should proactively notify the user to charge. The system also compares the latest battery capacity with a set charging protection threshold. If the charging protection threshold is less than or equal to the latest battery capacity, the system should calculate the subsequent rechargeable time. This comparison aims to ensure that the battery does not exceed the set safety range during charging, thus avoiding overcharging. The comparison results are recorded in the database, ensuring data integrity and traceability. The record should include the comparison timestamp, the latest battery capacity, and the charging protection threshold. If the charging protection threshold is found to be greater than the latest battery capacity, the system should promptly issue an alarm to remind the user to pay attention to the battery status to prevent potential safety risks. The formula for calculating the remaining rechargeable time is: Remaining rechargeable time (h) = (Charging protection threshold - Current battery capacity) / Current charging power (W). It's crucial to ensure the unit of charging power matches the unit of battery capacity; typically, battery capacity is converted to Wh (watt-hours) for easier calculation. Calculate the remaining rechargeable time using the current battery capacity, charging protection threshold, and current charging power. Ensure the result is positive, indicating the battery still has the potential to be charged. Record the calculation results, including the battery capacity used, charging protection threshold, and charging power, for subsequent analysis.The calculated remaining charging time is recorded in the database, ensuring each record includes a timestamp and relevant parameters for subsequent analysis. The system can use this remaining charging time information to optimize the charging strategy, ensuring efficient charging within a safe range. The minimum full charge power is calculated using the formula: Minimum Full Charge Power (W) = (Charging Protection Threshold - Current Battery Capacity) / Remaining Charging Time (h). It is crucial that the charging protection threshold and current battery capacity are calculated in the same unit (e.g., Wh). Based on the calculated remaining charging time and current battery capacity, the minimum full charge power is calculated using the established formula. The calculation result must be reasonable and within the battery's safe charging range. The calculation results, including the battery capacity used, the charging protection threshold, and the remaining charging time, are recorded for subsequent analysis. A trickle charging control strategy is designed to ensure that the charging power gradually decreases as the battery approaches full charge, preventing damage from overcharging. The trickle charging power should be lower than the minimum full charge power. Set standards and thresholds for trickle charging. For example, when the battery capacity reaches 95%, the charging power should be reduced to 10%-20% of the minimum charging power. During charging, when the battery capacity approaches the charging protection threshold, the system should automatically adjust the charging power to the set trickle charging power to ensure that the battery is not overcharged when fully charged. Record the power adjustment during the charging process, including the power values ​​before and after adjustment, timestamps, and battery status information for subsequent analysis. Record the implementation results of the trickle charging strategy in a database to ensure data integrity and traceability. Add timestamps and relevant parameters to each record for subsequent analysis and auditing. Implement a feedback mechanism: when the battery capacity reaches the charging protection threshold, the system should notify the user that charging is complete and advise the user to unplug the charger to prevent overcharging.

[0103] In this embodiment, a battery charging protection system for an electric screwdriver is provided, for performing the battery charging protection method for an electric screwdriver as described above, including:

[0104] The usage module is used to obtain historical operation monitoring logs of electric screwdrivers; and to perform personalized user usage demand analysis on the historical operation monitoring logs of electric screwdrivers, thereby generating historical usage demand evolution data.

[0105] The power demand forecasting module is used to decompose historical usage demand evolution data into demand over multiple time periods and make comprehensive power demand predictions to generate the next battery power demand forecast.

[0106] The safe charging power calculation module calculates the maximum safe charging power based on the predicted battery power demand for the next time, and generates the maximum safe charging power for the battery.

[0107] The temperature change status module is used to perform real-time charging control based on the battery's maximum safe charging power and to monitor battery status parameters in real time; and to generate dynamic temperature change status characteristics based on the battery status parameters.

[0108] The charging power adjustment module is used to make rolling predictions of time windows based on dynamic temperature change characteristics, and to intelligently adjust and optimize the maximum safe charging power of the battery, thereby constructing an intelligent power optimization strategy.

[0109] The collaborative control module is used to make overcharge protection decisions based on the battery state parameters, and to perform self-learning collaborative control optimization based on the intelligent power optimization strategy to build an intelligent charging control and protection model.

[0110] This invention, by acquiring and analyzing historical logs, can generate precise, personalized demand data based on different user scenarios, workloads, and usage frequencies. This allows charging strategies to better adapt to actual user needs, avoiding a "standardized" approach. Through the evolution of historical usage data, the module can reveal changes in user usage patterns, helping to predict future battery power needs. This not only improves battery efficiency but also promptly detects potential overuse or abnormal battery behavior. Based on the generated historical usage demand evolution data, the system can identify the battery's actual load and power needs in advance, helping to optimize charging cycles and prevent battery damage from over-discharge or over-charge due to prolonged use. By decomposing historical demand data into time periods, it can accurately identify differences in power demand across different time periods. For example, a screwdriver's power demand differs under high and low load conditions. Precise demand decomposition helps avoid inefficient battery use or overcharging. By integrating multiple factors (such as load, battery health, and usage time), it accurately predicts future battery power needs. Accurately predicting the power demand for the next charge ensures optimized charging time and amount. Power prediction makes charging management more intelligent, ensuring that the battery is always charged on demand, avoiding battery damage caused by overcharging or undercharging. It calculates safe charging power based on battery demand, preventing overheating, swelling, or aging caused by excessive charging power. By intelligently calculating the maximum safe charging power, it ensures the battery receives the fastest possible charging speed within a safe range, while avoiding any risks that could damage the battery. This helps extend battery life. When calculating charging power, it considers not only the battery's current power demand but also its health status, ensuring that each charge is at its optimal state. Real-time monitoring of temperature changes during battery charging allows for timely identification and adjustment of temperature anomalies. This ensures the battery is not damaged by overheating, avoiding battery damage caused by excessive temperature. Generating dynamic temperature change characteristics reflects the temperature change trend during battery charging in real time. Based on these characteristics, the system can predict future temperature fluctuations and make corresponding charging adjustments. Through precise monitoring and dynamic analysis, it avoids the risk of localized overheating of the battery, ensuring balanced battery temperature control during charging. By predicting dynamic temperature changes, the system can dynamically adjust the charging power. When the temperature during charging is about to exceed the safe range, the charging power is automatically reduced to ensure that the battery remains in an optimal temperature control state throughout the charging process. During charging power adjustment, the system optimizes based on real-time temperature data and battery health status, thereby improving charging efficiency and reducing unnecessary energy loss. The intelligent power regulation strategy adjusts the charging power according to the battery's real-time condition, balancing charging speed and battery protection. This avoids overcharging and overheating while efficiently utilizing the battery and reducing energy waste.The collaborative control module continuously optimizes the charging strategy through a self-learning mechanism. With increasing usage, the system intelligently adjusts based on battery health, temperature changes, and charging history. This ensures that each charge adheres to the optimal strategy, improving battery protection. This module integrates all battery state parameters and dynamic changes during charging to construct an intelligent charging protection model. Through real-time collaborative control, it ensures that every decision during charging is adaptively optimized, improving battery lifespan and safety.

[0111] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0112] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A battery charge protection method for a power screwdriver, characterized by, The method comprises the following steps: Step S1: obtaining the historical operation monitoring log of the electric screwdriver; analyzing the user individual use demand of the historical operation monitoring log of the electric screwdriver, thereby generating the historical use demand evolution data; Step S2: decomposing the historical use demand evolution data into multiple time periods, and comprehensively estimating the power demand, thereby generating the next battery power demand prediction value; Step S3: calculating the maximum safe charging power according to the next battery power demand prediction value, and generating the battery maximum safe charging power; Step S4: controlling the instant charging according to the battery maximum safe charging power, and monitoring the battery state parameters in real time; and generating the dynamic temperature change trend characteristics based on the battery state parameters; Step S5: performing time window rolling prediction according to the dynamic temperature change trend characteristics, and intelligently adjusting and optimizing the battery maximum safe charging power, thereby constructing the intelligent power optimization strategy; Step S6: making the overcharge protection decision according to the battery state parameters, and performing self-learning collaborative control optimization according to the intelligent power optimization strategy, thereby constructing the intelligent charging control protection model; The specific steps of step S6 are as follows: Step S61: calculating the latest battery capacity according to the battery state parameters; Step S62: making the overcharge protection decision based on the latest battery capacity, thereby generating the overcharge protection strategy; Step S63: performing self-learning collaborative control optimization on the intelligent power optimization strategy and the overcharge protection strategy, thereby constructing the intelligent charging control protection model; The specific steps of step S62 are as follows: defining the charging protection threshold, judging the power use satisfaction of the latest battery capacity based on the next battery power demand prediction value, comparing the latest battery capacity with the charging protection threshold when the latest battery capacity meets the next power demand, calculating the remaining chargeable duration when the charging protection threshold is less than or equal to the latest battery capacity; calculating the minimum full charging power according to the remaining chargeable duration, thereby obtaining the minimum full charging power; controlling the trickle charging power by using the minimum full charging power, thereby generating the overcharge protection strategy.

2. The battery charge protection method for a power screwdriver according to claim 1, wherein, The specific steps of step S1 are as follows: Step S11: obtaining the historical operation monitoring log of the electric screwdriver; Step S12: detecting the abnormal outlier data of the historical operation monitoring log of the electric screwdriver, and marking multiple abnormal outlier points; Step S13: performing adaptive filtering processing on the multiple abnormal outlier points, thereby generating the filtered and optimized monitoring log; Step S14: mining the user individual use preference from the filtered and optimized monitoring log, thereby generating the user individual use preference characteristics; Step S15: performing historical use demand evolution based on the user individual use preference characteristics, thereby generating the historical use demand evolution data.

3. The battery charge protection method for a power screwdriver according to claim 2, wherein, The specific steps of step S14 are as follows: performing dynamic use behavior analysis on the filtered and optimized monitoring log, and extracting the screwdriver use behavior data; calculating the historical use frequency of the screwdriver use behavior data, and extracting the use frequency data; extracting the use time stamp of the screwdriver use behavior data each time; performing use time sequence processing according to the use time stamp each time, thereby generating the use time stamp sequence; According to the use cycle analysis using the timestamp sequence, the screwdriver use cycle characteristics are obtained; According to the use timestamp of each time, the use duration of each time is calculated; Based on the use duration of each time, the screwdriver use cycle characteristics and the use frequency data, the user personalized use preference mining is performed, so as to generate the user personalized use preference characteristics.

4. The battery charge protection method for a power screwdriver according to claim 1, wherein, The specific steps of step S2 are as follows: Step S21: The historical use demand evolution data is decomposed into multiple time period demand, so as to generate use demand data of multiple time periods; Step S22: The use demand data of multiple time periods is dynamically perceived to generate use behavior demand trend data; Step S23: The use behavior demand trend data is analyzed to capture the trend change in the cycle, and the behavior demand change rule is generated; Step S24: Based on the behavior demand change rule, the recent use demand is predicted, so as to obtain the next use time point and use duration; Step S25: The next use time point and use duration are comprehensively analyzed to speculate the power demand, so as to generate the next battery power demand prediction value.

5. The battery charge protection method for a power screwdriver according to claim 1, wherein, The specific steps of step S3 are as follows: Step S31: Identify the current remaining battery power: Step S32: According to the next battery power demand prediction value, the power demand deviation of the current remaining battery power is calculated to obtain the power demand deviation value; Step S33: Based on the next use time point, the current time gap is counted to generate the available charging time; Step S34: Based on the available charging time and the power demand deviation value, the maximum safe charging power of the battery is calculated to generate the maximum safe charging power of the battery.

6. The battery charge protection method for a power screwdriver according to claim 1, wherein, The specific steps of step S4 are as follows: Step S41: According to the maximum safe charging power of the battery, the electric screwdriver is controlled for instant charging, and the battery state parameters are monitored in real time; Step S42: According to the battery state parameters, the real-time temperature is identified, and the real-time temperature parameters of the battery are extracted; Step S43: The temperature change rate of the battery real-time temperature parameters is calculated to generate the temperature change rate value; Step S44: According to the real-time temperature parameters, the maximum temperature change amplitude is analyzed to generate the maximum temperature change amplitude; Step S45: Based on the temperature change rate value and the maximum temperature change amplitude, the time sequence temperature change evolution is performed, so as to construct the time sequence temperature change curve; Step S46: The dynamic temperature change trend of the time sequence temperature change curve is analyzed, so as to generate the dynamic temperature change trend characteristics.

7. The battery charge protection method for a power screwdriver according to claim 1, wherein, The specific steps of step S5 are as follows: Step S51: According to the battery state parameters, the real-time charging voltage is obtained; Step S52: The real-time charging voltage is analyzed to generate the real-time charging voltage; Step S53: According to the real-time charging voltage, the dynamic temperature change trend characteristics are predicted in a time window, so as to generate temperature prediction values in multiple time windows; Step S54: The battery health state is evaluated according to the temperature prediction values in multiple time windows, so as to obtain the battery health state evaluation value; Step S55: Based on the battery health state evaluation value, the intelligent charging power adjustment optimization of the maximum safe charging power of the battery is performed, and the intelligent power optimization strategy is constructed.

8. A battery charge protection system for a power screwdriver, characterized by, A battery charging protection method for performing an electric screwdriver as claimed in claim 1, comprising: a usage demand module for obtaining a historical operation monitoring log of the electric screwdriver; performing user personalized usage demand analysis on the historical operation monitoring log of the electric screwdriver, thereby generating historical usage demand evolution data; a power demand prediction module for performing multi-period demand decomposition on the historical usage demand evolution data, and performing comprehensive power demand speculation, thereby generating a next battery power demand prediction value; a safe charging power calculation module for performing maximum safe charging power calculation according to the next battery power demand prediction value, thereby generating a battery maximum safe charging power; a temperature change trend module for performing real-time charging control according to the battery maximum safe charging power, and monitoring battery state parameters in real time; generating dynamic temperature change trend characteristics based on the battery state parameters; a charging power adjustment module for performing time window rolling prediction according to the dynamic temperature change trend characteristics, and performing intelligent charging power adjustment optimization on the battery maximum safe charging power, thereby constructing an intelligent power optimization strategy; a cooperative control module for performing overcharging protection decision-making according to the battery state parameters, and performing self-learning cooperative control optimization according to the intelligent power optimization strategy, thereby constructing an intelligent charging control protection model.

Images