Real-time diagnostic method for battery health monitoring in mobile energy storage devices

Abstract

The present application provides a real-time diagnostic method for monitoring the health status of batteries in mobile energy storage devices, which relates to the field of battery monitoring technology. The method includes: obtaining battery data of the battery; analyzing the impact of events on battery health and establishing an impact prediction fitness function; performing continuous monitoring of the battery and establishing an output result; evaluating the impact of abnormal events in the output result through the impact prediction fitness function and establishing an impact cumulative prediction result; synchronizing the impact cumulative prediction result and the number of cycles in the output result to the data processing end; performing real-time evaluation of the battery based on health indicator characteristics and establishing a real-time evaluation result; verifying and evaluating the real-time evaluation result, the impact cumulative prediction result, the number of cycles and the initial health data of the battery to generate a health status diagnosis result. This application can solve the technical problem of low accuracy in evaluating battery performance in the prior art and achieve the technical effect of improving battery performance.

Description

Technical Field

[0001] The present application relates to the field of battery monitoring technology, and in particular to a real-time diagnostic method for monitoring the health status of batteries in mobile energy storage devices. Background Art

[0002] Battery health monitoring for mobile energy storage equipment is the process of checking and evaluating the performance and status of the battery.

[0003] Currently, most existing battery health monitoring processes fail to assess the impact of abnormal events. This can lead to inaccurate detection of abnormal changes in battery health, missing the best opportunity to prevent potential problems. Furthermore, without an evaluation based on health characteristics, battery performance and lifespan cannot be accurately assessed, increasing safety risks during battery use. Therefore, a method is needed to address these issues.

[0004] In summary, the existing technology has technical problems such as the failure to determine the impact of abnormal events on the battery, which leads to reduced battery health and inability to accurately evaluate battery performance and life, further increasing battery safety risks. Summary of the Invention

[0005] The purpose of this application is to provide a real-time diagnostic method for monitoring the health status of batteries in mobile energy storage devices, so as to solve the technical problems in the prior art that most of the impacts of abnormal events on the battery are not judged, resulting in reduced battery health and inability to accurately assess battery performance and life, further increasing battery safety risks.

[0006] In view of the above problems, the present application provides a real-time diagnostic method for monitoring the health status of batteries in mobile energy storage devices.

[0007] The present application provides a real-time diagnostic method for monitoring the health status of batteries in mobile energy storage equipment, wherein the method includes: obtaining battery data of the battery, the battery data including battery parameter data and battery initial health data; analyzing the impact of events on battery health based on the battery parameter data, and establishing an impact prediction fitness function; continuously monitoring the battery with the monitoring communication module, and establishing an output result, the output result including abnormal events, duration and number of cycles; evaluating the impact of abnormal events in the output result through the impact prediction fitness function, and establishing an impact cumulative prediction result; synchronizing the impact cumulative prediction result and the number of cycles in the output result to the data processing end; establishing health indicator characteristics, wherein the health indicator characteristics include capacity characteristics, internal resistance characteristics, and voltage decay rate characteristics, performing real-time evaluation of the battery with the health indicator characteristics, establishing a real-time evaluation result, and synchronizing the real-time evaluation result to the data processing end; verifying and evaluating the real-time evaluation result, the impact cumulative prediction result, the number of cycles and the initial health data of the battery with the data processing end to generate a health status diagnosis result by verifying the evaluation result.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] By acquiring battery data of the battery, the battery data includes battery parameter data and battery initial health data; analyzing the impact of events on battery health based on the battery parameter data, and establishing an impact prediction fitness function; continuously monitoring the battery with the monitoring communication module, and establishing an output result, the output result includes abnormal events, duration and number of cycles; evaluating the impact of abnormal events in the output result with the impact prediction fitness function, and establishing an impact cumulative prediction result; synchronizing the impact cumulative prediction result and the number of cycles in the output result to the data processing end; establishing health indicator characteristics, wherein the health indicator characteristics include capacity characteristics, internal resistance characteristics, and voltage decay rate characteristics, and performing real-time evaluation of the battery with the health indicator characteristics, establishing a real-time evaluation result, and synchronizing the real-time evaluation result to the data processing end; verifying and evaluating the real-time evaluation result, the impact cumulative prediction result, the number of cycles and the battery initial health data with the data processing end, and generating a health status diagnosis result by verifying the evaluation result, thereby achieving the technical goal of preventing potential risks of the battery and achieving the technical effect of improving battery performance.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the description, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically listed below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in this application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and a person of ordinary skill in the art can obtain other drawings based on the provided drawings without creative work.

[0012] Figure 1 This is a flow chart of a real-time diagnostic method for monitoring the health status of batteries in mobile energy storage devices according to the present application;

[0013] Figure 2 A schematic diagram of a flow chart for establishing output results in the real-time diagnostic method for monitoring the health status of batteries in mobile energy storage devices in this application. DETAILED DESCRIPTION

[0014] This application provides a real-time diagnostic method for monitoring the health of batteries in mobile energy storage devices. This method addresses the existing technical issues of failing to assess the impact of abnormal events on the battery, leading to reduced battery health and an inability to accurately assess battery performance and lifespan, further increasing battery safety risks. This method achieves the technical goal of preventing potential battery risks and improving battery performance.

[0015] Below, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited to the example embodiments described herein. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. It should also be noted that, for the convenience of description, only the parts related to this application, rather than all of them, are shown in the accompanying drawings.

[0016] Example

[0017] Please see the attached Figure 1 The present application provides a real-time diagnostic method for monitoring the health status of a battery in a mobile energy storage device, the method specifically comprising the following steps:

[0018] Step 1: Obtain battery data, including battery parameter data and battery initial health data;

[0019] Specifically, battery data for the mobile energy storage device's battery is obtained. Battery data includes battery parameter data and initial battery health data. For example, battery parameter data includes battery type, battery capacity, battery voltage, battery internal resistance, battery charge and discharge cycle count, battery temperature range, and battery weight and size. For example, battery types include lithium-ion batteries and nickel-metal hydride batteries. For another example, initial battery health data includes initial battery capacity, initial battery internal resistance, initial battery charge and discharge efficiency, and initial battery life prediction.

[0020] Step 2: Analyze the impact of the event on battery health based on the battery parameter data and establish an impact prediction fitness function;

[0021] Specifically, identify and control events that affect battery health. For example, events include charging method, discharge rate and depth, battery temperature, battery storage conditions, and mechanical stress. For example, charging methods include fast charging, slow charging, and wireless charging; battery temperatures include high and low temperatures, which affect battery health; battery storage conditions include long-term storage at full or empty charge; and mechanical stress includes vibration and shock. Record changes in battery health data before and after the event. Analyze the degree and trend of the impact of different events on battery health data. Based on the characteristics of battery health data changes and the analysis results, establish an impact prediction fitness function to predict the battery health status. For example, this can be established through a machine learning model. The input and output of the impact prediction fitness function are defined, and supervised learning is performed to complete the establishment of the impact prediction fitness function.

[0022] Step 3: Continuously monitor the battery using the monitoring communication module and generate output results, including abnormal events, duration, and number of cycles;

[0023] Specifically, the battery cycle number and status are monitored by the monitoring communication module. If an abnormal monitoring result is obtained, the current event is determined to be an abnormal event, and the duration of the abnormal event is obtained. The cycle number, abnormal event and its duration are added to the output result.

[0024] Step 4: Evaluate the impact of abnormal events in the output results using the impact prediction fitness function to establish a cumulative impact prediction result;

[0025] Specifically, when an abnormal event is detected, the impact prediction fitness function is used to evaluate the impact of the abnormal event on the battery health status in the output results. Based on the type, severity, and duration of the abnormal event, the impact prediction fitness function calculates an impact value. This impact value is added to the cumulative impact prediction results to form a historical record, which can be used to observe the long-term impact of the abnormal event on the battery health status.

[0026] Step 5: Synchronizing the impact cumulative prediction result and the number of cycles in the output result to the data processing end;

[0027] Specifically, a real-time diagnostic method for monitoring the health status of mobile energy storage devices is applied to an intelligent monitoring system, which includes a data processing end for subsequent analysis and reporting. After each cycle, the current cycle count is recorded. The cycle count and cumulative impact prediction results are synchronized to the data processing end.

[0028] Step 6: Establish health indicator characteristics, wherein the health indicator characteristics include capacity characteristics, internal resistance characteristics, and voltage decay rate characteristics, perform real-time evaluation of the battery based on the health indicator characteristics, establish real-time evaluation results, and synchronize the real-time evaluation results to the data processing end;

[0029] Specifically, the battery health indicator characteristics are defined. The health indicator characteristics are used to comprehensively reflect the health status of the battery. They can include capacity characteristics, internal resistance characteristics, and voltage decay rate characteristics. The capacity characteristics can be evaluated by the battery's charge and discharge capacity, the internal resistance characteristics can be obtained by measuring the battery's internal resistance, and the voltage decay rate characteristics can be calculated by comparing the battery's initial voltage and current voltage. The battery is evaluated in real time using health indicator characteristics, multiple thresholds are set, and the battery's real-time status is used for evaluation to obtain real-time evaluation results, which are then synchronized to the data processing end.

[0030] Step 7: Using the data processing end to verify and evaluate the real-time evaluation results, the cumulative impact prediction results, the number of cycles and the initial health data of the battery, so as to generate a health status diagnosis result based on the verification evaluation results.

[0031] Specifically, check whether the capacity characteristics and voltage decay rate characteristics in the real-time evaluation results are within a reasonable range. Compare with historical data to assess the stability and consistency of the real-time evaluation results. If any abnormal or inconsistent data is found, conduct further investigation and analysis. Analyze the trends and patterns of the impact cumulative prediction results to check whether they are consistent with the battery performance degradation pattern. Compare with historical impact cumulative prediction results to assess their accuracy and reliability. If the predicted results deviate significantly from the actual situation, it may be necessary to adjust the impact prediction fitness function or retrain the adaptive update network. Verify the accuracy and completeness of the cycle count. Check whether the cycle count is consistent with the battery's charge and discharge history. If the cycle count is abnormal or missing, recalculation or supplemental data may be required. Verify the accuracy and reliability of the battery's initial health data by comparing it with manufacturer-provided data or standard data to ensure the accuracy of the initial health data. If any issues are found in the initial health data, reassessment or acquisition of new data may be necessary. A comprehensive evaluation is conducted by combining the real-time evaluation results, impact cumulative prediction results, cycle count, and initial battery health data. Based on the preset health status assessment criteria or model, the battery's health status is determined (e.g., good, fair, poor, etc.) to generate a health status diagnosis result.

[0032] The real-time diagnostic method for monitoring the health status of batteries in mobile energy storage devices can achieve the technical goal of preventing potential risks of batteries and achieve the technical effect of improving battery performance.

[0033] Further, if Figure 2 As shown, this application also includes the following steps:

[0034] The monitoring communication module includes a counting unit, and when the monitoring battery completes any cycle, the count value of the counting unit is increased by 1;

[0035] Configure an abnormality threshold for an event. When the battery is continuously monitored through the monitoring communication module, if any monitoring result meets the abnormality threshold, the current event is determined to be an abnormal event. At this time, the abnormal event is continuously monitored and recorded to obtain the duration;

[0036] Add abnormal events and duration to the output results.

[0037] Specifically, a real-time diagnostic method for monitoring the health status of batteries in mobile energy storage devices is applied to an intelligent monitoring system, which includes a monitoring communication module. The monitoring communication module has a counting unit to record the number of battery cycles and, when an abnormal event is detected, record and report the abnormal event and its duration. When the battery completes a complete charge and discharge process, i.e., a cycle, the count value of the counting unit is incremented by 1. For example, the battery management system or other related equipment can detect the battery's charge and discharge status to determine whether the battery has completed a cycle.

[0038] Then, configure abnormality thresholds based on the battery type, specifications, and usage scenario. These thresholds may include upper and lower limits for voltage, current, temperature, and charge / discharge rates. The monitoring communication module continuously receives battery status data. This data is analyzed in real time to check whether any monitoring results exceed the configured abnormality thresholds. If any monitoring result meets the abnormality threshold, the event is identified as an abnormal event. Once an abnormal event is triggered, it is continuously monitored and recorded, including its duration.

[0039] The detected abnormal events and their duration are then added to the output results to obtain the battery's health status and performance issues.

[0040] By obtaining real-time information on battery health and performance issues, potential failures and safety hazards can be discovered and addressed in a timely manner, thereby improving battery life and safety.

[0041] Furthermore, the present application further comprises the following steps:

[0042] Configuring an adaptive update network, wherein the adaptive update network is a network for performing an optimization process on an impact prediction fitness function;

[0043] Receiving the health status diagnosis result with the adaptive update network, extracting key parameters affecting battery health based on the received result, and generating key values ​​of update parameters;

[0044] The impact prediction fitness function is optimized by updating the parameter key value, and subsequent battery health prediction management is performed using the optimized impact prediction fitness function.

[0045] Specifically, an adaptive update network is configured to optimize the fitness function that affects the prediction. The adaptive update network can use deep learning technology, such as neural networks or recurrent neural networks, to adapt to different battery state change patterns.

[0046] The battery health diagnosis results are then used as input to the adaptive update network, which may include key indicators such as battery capacity, voltage decay rate, and internal resistance change. The adaptive update network extracts key parameters that influence battery health, reflecting performance trends and potential risks. Key parameters closely related to battery health are extracted from the health diagnosis results. Based on these extracted key parameters, update parameter key values ​​are generated and used to adjust parameters affecting the prediction fitness function to optimize its prediction performance.

[0047] Next, the generated updated parameter key values ​​are applied to the impact prediction fitness function to optimize its prediction performance. The parameters or structure of the fitness function are adjusted based on the updated parameter key values ​​to better fit the actual data and improve prediction accuracy. The optimized impact prediction fitness function is then used for subsequent battery health prediction management.

[0048] By adaptively updating the network, the prediction fitness function is optimized, and the battery health status and prediction results are continuously monitored to promptly detect and resolve potential problems.

[0049] Furthermore, the present application further comprises the following steps:

[0050] Performing real-time capacity monitoring on the battery, when the battery capacity is in a preset steady state and the duration of the steady state meets a determination threshold, using the corresponding steady-state value as a real-time evaluation result of the capacity characteristic;

[0051] Configuring a random sampling window, wherein the random sampling window is N evaluation windows of the same length;

[0052] When the battery steady-state value at any time node meets the trigger threshold, a random sampling window is activated using a random number;

[0053] Obtaining sampling results of a random sampling window, and calculating a voltage decay rate mean based on the sampling results, and using the mean as a real-time evaluation result of the voltage decay rate feature;

[0054] The real-time evaluation results are established based on the real-time evaluation results of capacity characteristics and voltage attenuation rate characteristics.

[0055] Specifically, the battery's capacity is monitored in real time, and battery capacity data is continuously collected. A determination is made as to whether the battery capacity is within a preset steady-state range. When the battery capacity is within the preset steady-state range, it indicates that the battery capacity has fluctuated slightly over a period of time, reaching a relatively stable level. If the battery capacity is within the preset steady-state range, and the duration of the steady-state period meets a determination threshold (for example, for a preset duration), the capacity value of the steady-state range is used as the real-time evaluation result of the capacity characteristic.

[0056] Next, define a random sampling window, which consists of N evaluation windows of equal length. This window is used to randomly sample the battery when the battery state meets specific conditions. The length of each evaluation window should be set based on actual conditions and needs to ensure that sufficient data points are captured to assess the battery state.

[0057] Then, when the battery steady-state value at any time node meets the trigger threshold, that is, a certain performance indicator of the battery exceeds the preset trigger threshold, the random number generator is used to activate the random sampling window to randomly select multiple random sampling windows from N evaluation windows for sampling.

[0058] Next, for the activated random sampling window, voltage data is collected at all time points. The voltage decay rate is calculated, for example, by comparing the initial and final voltages of the battery during charging or discharging, and taking time into account.

[0059] Then, the voltage decay rates in all sampling windows are averaged to obtain the voltage decay rate mean value, which serves as a real-time evaluation result of the voltage decay rate feature.

[0060] Next, the real-time evaluation results of the capacity characteristics and the real-time evaluation results of the voltage decay rate characteristics are combined to form a complete real-time evaluation result, which is used to evaluate the current health status of the battery and provide a decision basis for subsequent battery management.

[0061] By monitoring the battery's real-time capacity, when the battery capacity is in a steady state, a sampling window is extracted to evaluate the battery's health status, thereby improving the efficiency of battery monitoring.

[0062] Furthermore, the present application further comprises the following steps:

[0063] Monitor the working environment of the battery through the environmental monitoring module and establish an environmental time series data set;

[0064] Establishing a normal environment time series window based on the environment time series data set, wherein the normal environment time series window is a window not affected by abnormal environment;

[0065] Perform abnormal frequency analysis of battery execution tasks based on the normal environment timing window, and establish a task-frequency additional coefficient;

[0066] The health status diagnosis result is compensated by the task-frequency additional coefficient.

[0067] Specifically, the environmental monitoring module monitors the battery's operating environment in real time, including measurements of environmental factors such as temperature, humidity, air pressure, and light. The monitored environmental data is recorded in chronological order to form an environmental time series dataset.

[0068] Next, the time period without abnormal environmental influence is selected from the environmental time series data set. The environmental data in the time period without abnormal environmental influence has small fluctuations and is within the normal range. It is used as the normal environmental time series window for subsequent analysis and comparison.

[0069] Next, within the normal environment timing window, the battery analyzes task execution, including task type, execution time, and results. Abnormalities during task execution, such as task failures, timeouts, and interruptions, are identified and recorded. Based on the frequency of abnormalities, a task-frequency additive coefficient is established to reflect the frequency of abnormalities for different tasks under different environmental conditions. This coefficient can be used to assess the risk and stability of task execution.

[0070] The task-frequency additional coefficient is then combined with the health status diagnosis results to compensate for the results. If a task has a high frequency of abnormalities within the normal environment time series window, it indicates that the task is more likely to have problems under similar environmental conditions. Therefore, in the health status diagnosis results, the risk rating of the part involving this task can be increased or the health score can be decreased accordingly. The specific compensation method can be set according to the actual situation, for example, by combining the task-frequency additional coefficient with the health status diagnosis results through weighted averaging, linear interpolation, etc.

[0071] The health status diagnosis results are compensated through the normal environment time series window to ensure the accuracy and effectiveness of the compensation results.

[0072] Furthermore, the present application further comprises the following steps:

[0073] Performing an environmental anomaly time series evaluation on the environmental time series data set and establishing an abnormal environmental time series window;

[0074] Performing an impact evaluation based on abnormal values ​​and abnormal duration using the abnormal environment time series window to establish a correlation window;

[0075] The abnormal environment time sequence window and the associated window are excluded to establish a normal environment time sequence window.

[0076] Specifically, environmental time series datasets are evaluated for environmental anomalies. The duration and frequency of outliers are evaluated to help identify long-term or short-term anomalies in environmental conditions. Based on the anomaly detection results, multiple thresholds are set to define the boundaries of the abnormal environmental time series window. These thresholds can be based on the number, duration, or frequency of outliers. Within the abnormal environmental time series dataset, the abnormal environmental time series window is demarcated based on the thresholds. This window contains outliers exceeding the threshold and their associated environmental data.

[0077] Next, the impact of outliers within the abnormal environment time series window on battery performance or health status is analyzed. For example, this can be achieved by comparing battery performance data during the abnormal period with that during normal periods. Based on the impact assessment results of the outliers and the duration of the abnormality, a correlation window related to the abnormal environment time series window is determined. The correlation window may include time periods before and after the abnormal period to more comprehensively assess the impact of the abnormal environment on battery performance.

[0078] Next, the data within the abnormal environmental time series window and the associated window are excluded from the original environmental time series dataset. The remaining data is regarded as the normal environmental time series window. The data within the window represents the environmental conditions that the battery is exposed to under normal circumstances.

[0079] By using the data in the normal environment time series window, the performance of the battery under normal conditions can be more accurately evaluated, thereby appropriately compensating the health status diagnosis results.

[0080] Furthermore, the present application further comprises the following steps:

[0081] Continuously recording the health status diagnosis results and establishing a health status change curve;

[0082] Perform health mutation monitoring based on the health status change curve and call the early warning features corresponding to the health mutation;

[0083] The battery usage warning is performed using the warning feature.

[0084] Specifically, collect battery health status diagnostic results in real time or periodically to ensure data continuity and integrity. Use charting tools to draw health status change curves to show the changing trends of battery health status over time.

[0085] Then, based on the battery type, specifications, and usage, a health status change threshold is set to reflect a significant change in the battery's health status. By comparing the current health status change curve with the threshold, the battery's health status is monitored in real time for sudden changes. A database or knowledge base is established containing different health status change types and corresponding warning features. Warning features may include specific battery performance indicators, abnormal behavior patterns, and so on. When a health status sudden change is detected, a warning feature matching the current mutation type is searched in the warning feature library.

[0086] If a warning feature is matched, the battery usage warning mechanism is triggered. This can be achieved, for example, by sending an alert message, popping up a prompt box, or triggering an audio or light signal. The warning content includes information such as the current health status of the battery, possible risks, and recommended countermeasures.

[0087] By achieving continuous monitoring and early warning of battery health status, potential safety risks can be discovered and addressed in a timely manner, thereby improving battery efficiency and safety.

[0088] Furthermore, the present application further comprises the following steps:

[0089] Determine whether the unit time mutation value of the health status change curve meets the preset mutation threshold;

[0090] If the preset mutation threshold is met, the corresponding position is marked, and the health mutation monitoring is completed based on all the marking results.

[0091] Specifically, determine the unit duration of the health status change curve, for example, the amount of health status change per minute, hour, or day. Calculate the health status change value within the unit duration, that is, the unit duration mutation value. The preset mutation threshold is the benchmark for judging whether the health status has changed significantly. The preset mutation threshold is set based on factors such as the battery's historical data, usage scenarios, and technical specifications. It is used to reflect the normal fluctuation range of the battery's health status and allows for timely early warning when potential problems occur. Compare the calculated unit duration mutation value with the preset mutation threshold. If the unit duration mutation value exceeds the preset threshold, it means that the battery's health status has changed significantly within the unit time, and there may be potential problems.

[0092] Then, each unit duration that meets the preset mutation threshold is marked on the health status change curve. The health mutation monitoring process is completed by traversing the entire health status change curve and marking all unit durations that meet the preset mutation threshold. The marking results are used to assess the battery's health status and take appropriate measures to prevent or resolve potential problems.

[0093] By continuously monitoring and providing early warning of battery health status, potential problems can be discovered and addressed in a timely manner, thereby improving battery efficiency and safety.

[0094] In summary, the real-time diagnostic method for monitoring the health status of batteries in mobile energy storage devices provided by this application has the following technical effects:

[0095] By acquiring battery data of the battery, the battery data includes battery parameter data and battery initial health data; analyzing the impact of events on battery health based on the battery parameter data, and establishing an impact prediction fitness function; continuously monitoring the battery with the monitoring communication module, and establishing an output result, the output result includes abnormal events, duration and number of cycles; evaluating the impact of abnormal events in the output result with the impact prediction fitness function, and establishing an impact cumulative prediction result; synchronizing the impact cumulative prediction result and the number of cycles in the output result to the data processing end; establishing health indicator characteristics, wherein the health indicator characteristics include capacity characteristics, internal resistance characteristics, and voltage decay rate characteristics, and performing real-time evaluation of the battery with the health indicator characteristics, establishing a real-time evaluation result, and synchronizing the real-time evaluation result to the data processing end; verifying and evaluating the real-time evaluation result, the impact cumulative prediction result, the number of cycles and the battery initial health data with the data processing end, and generating a health status diagnosis result by verifying the evaluation result, thereby achieving the technical goal of preventing potential risks of the battery and achieving the technical effect of improving battery performance.

[0096] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one 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 present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

[0097] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A real-time diagnostic method for monitoring the health status of batteries in mobile energy storage devices, the method being applied to an intelligent monitoring system comprising a monitoring communication module and a data processing terminal, characterized in that: The method comprises: Obtain battery data, including battery parameter data and battery initial health data; Analyzing the impact of the event on battery health based on the battery parameter data and establishing an impact prediction fitness function; Continuously monitor the battery using the monitoring communication module and generate output results, including abnormal events, duration, and number of cycles; Evaluate the impact of abnormal events in the output results using the impact prediction fitness function to establish an impact cumulative prediction result; Synchronizing the impact cumulative prediction result and the number of cycles in the output result to the data processing end; Establishing health indicator characteristics, wherein the health indicator characteristics include capacity characteristics, internal resistance characteristics, and voltage decay rate characteristics, performing real-time evaluation of the battery based on the health indicator characteristics, establishing real-time evaluation results, and synchronizing the real-time evaluation results to the data processing end; Verifying and evaluating the real-time evaluation result, the cumulative impact prediction result, the number of cycles, and the initial health data of the battery by the data processing end, so as to generate a health status diagnosis result based on the verification evaluation result; Configuring an adaptive update network, wherein the adaptive update network is a network for performing an optimization process on an impact prediction fitness function; Receiving the health status diagnosis result with the adaptive update network, extracting key parameters affecting battery health based on the received result, and generating key values ​​of update parameters; Optimizing the impact prediction fitness function by updating the parameter key value, and performing subsequent battery health prediction management by using the optimized impact prediction fitness function; Monitor the working environment of the battery through the environmental monitoring module and establish an environmental time series data set; Establishing a normal environment time series window based on the environment time series data set, wherein the normal environment time series window is a window not affected by abnormal environment; Perform abnormal frequency analysis of battery execution tasks based on the normal environment timing window, and establish a task-frequency additional coefficient; The health status diagnosis result is compensated by the task-frequency additional coefficient.

2. The method according to claim 1, wherein The continuous monitoring of the battery by the monitoring communication module and establishing output results further includes: The monitoring communication module includes a counting unit, and when the monitoring battery completes any cycle, the count value of the counting unit is increased by 1; Configure an abnormality threshold for an event. When the battery is continuously monitored through the monitoring communication module, if any monitoring result meets the abnormality threshold, the current event is determined to be an abnormal event. At this time, the abnormal event is continuously monitored and recorded to obtain the duration; Add abnormal events and duration to the output results.

3. The method according to claim 1, wherein The real-time evaluation of the battery based on the health indicator characteristics and establishing the real-time evaluation results also includes: Performing real-time capacity monitoring on the battery, when the battery capacity is in a preset steady state and the duration of the steady state meets a determination threshold, using the corresponding steady-state value as a real-time evaluation result of the capacity characteristic; Configuring a random sampling window, wherein the random sampling window is N evaluation windows of the same length; When the battery steady-state value at any time node meets the trigger threshold, a random sampling window is activated using a random number; Obtaining sampling results of a random sampling window, and calculating a voltage decay rate mean based on the sampling results, and using the mean as a real-time evaluation result of the voltage decay rate feature; The real-time evaluation results are established based on the real-time evaluation results of capacity characteristics and voltage attenuation rate characteristics.

4. The method according to claim 1, wherein The step of establishing a normal environment time series window based on the environment time series data set further includes: Performing an environmental anomaly time series evaluation on the environmental time series data set and establishing an abnormal environmental time series window; Performing an impact evaluation based on abnormal values ​​and abnormal duration using the abnormal environment time series window to establish a correlation window; The abnormal environment time sequence window and the associated window are excluded to establish a normal environment time sequence window.

5. The method according to claim 1, wherein The method further comprises: Continuously recording the health status diagnosis results and establishing a health status change curve; Perform health mutation monitoring based on the health status change curve and call the early warning features corresponding to the health mutation; The battery usage warning is performed using the warning feature.

6. The method according to claim 5, wherein The health mutation monitoring based on the health status change curve further includes: Determine whether the unit time mutation value of the health status change curve meets the preset mutation threshold; If the preset mutation threshold is met, the corresponding position is marked, and healthy mutation monitoring is completed based on all marking results.

Images