Battery RUL Forecasting With Capacity Feedback and Anomaly Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing battery management methods are device-specific, lack self-correction mechanisms, cannot detect anomaly levels, and are computationally intensive, making them inefficient for forecasting remaining useful life (RUL) and health trajectory prediction.
Innovation Solution
A method that measures battery capacity values for each charging and discharging cycle, uses a battery capacity estimation model and data-driven model to forecast RUL, detects anomalies, and continuously corrects forecasts by feeding back capacity values, enabling device-agnostic, efficient health prediction and anomaly detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing battery management methods are used, then health estimation can be performed, but the methods are device-specific and require parameter adjustment for every unseen device
Solution Approach 1:
The patent implements a universal battery management method that can be applied across different device types without requiring device-specific parameter adjustments. The system uses a standardized approach to estimate battery health, detect anomalies, and predict RUL that works for unseen devices, eliminating the need for separate parameter tuning for each device type.
Solution Approach 2:
The system automatically adapts to new devices through self-learning mechanisms. When applied to an unseen device, the method autonomously adjusts to the specific battery characteristics without requiring manual parameter adjustment, enabling the system to serve itself in adapting to different device contexts.
2Reliability
If existing battery prognosis methods are used, then initial health forecast can be provided, but the methods lack self-correction mechanism after abuse or anomaly
Solution Approach 1:
The patent implements a feedback mechanism that continuously monitors battery behavior and compares actual performance against predicted trajectories. When anomalies or abuse conditions are detected, the system automatically corrects the health forecast by incorporating the observed deviations, enabling self-correction without external intervention.
Solution Approach 2:
The prognosis system dynamically adjusts its predictions based on real-time battery behavior. The method transitions from static initial forecasts to dynamic self-correcting predictions that adapt as the battery ages and experiences various operating conditions, allowing the system to respond to changing battery states.
3Difficulty of detecting and measuring
If existing battery management methods are used, then anomaly detection can be performed, but the methods cannot detect level of abuse or anomaly
Solution Approach 1:
The patent applies local quality analysis by examining specific characteristics of battery behavior at different stages and conditions. The method evaluates local deviations in voltage, current, and temperature patterns to not only detect the presence of anomalies but also determine their severity levels, providing granular information about the extent of abuse.
Solution Approach 2:
The system monitors changes in multiple battery parameters simultaneously and analyzes their relationships to determine anomaly levels. By tracking parameter variations over time and comparing them against expected ranges, the method can quantify the severity of abuse conditions rather than merely detecting their presence.
4Ease of operation
If existing battery management methods are used, then separate modules can be implemented for different tasks, but the computation becomes intensive
Solution Approach 1:
The patent merges multiple battery management tasks into a unified computational framework. By integrating health estimation, anomaly detection, and RUL prediction into a single cohesive method that processes data through shared computational pathways, the system reduces overall computation intensity while maintaining the functional separation of tasks.
Data Source
AI summary
A method for forecasting remaining useful life (RUL) of a battery by an electronic device is provided. The method includes forecasting the RUL of the battery based on at least one capacity value of the battery estimated by at least one of a battery capacity estimation model and a data driven model, determining whether the at least one capacity value for the charging cycle and the discharging cycle is lower than the at least one capacity value estimated by at least one of the battery capacity estimation model and the data driven model and correcting the forecasting RUL of the battery by feeding back the at least one capacity value to at least one of the battery capacity estimation model and the data driven model.