Supercapacitor SoH Estimation Using Charge-Discharge Time-Series Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing supercapacitors experience significant non-linear degradation due to repeated charging and discharging, making accurate State of Health (SoH) estimation challenging, which is crucial for determining replacement timing and maintaining stable power operation.
Innovation Solution
A system and method utilizing a multi-graph learning algorithm and a many-to-many recurrent neural network model, including a data detector, vehicle controller, and display device, to construct and estimate SoH based on charge/discharge data, using models like LSTM, GRU, and RNN, with features like self-attention and time-distributed layers for precise estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional estimation methods are used for supercapacitor SoH, then the system complexity remains low, but the estimation accuracy deteriorates due to significant non-linear degradation
Solution Approach 1:
The patent introduces an intermediary processing system that includes a data construction unit and a neural network model. The data construction unit transforms raw charge/discharge data into structured time-series data matrices, which then serve as input to the neural network model for accurate SoH estimation. This intermediary processing layer enables high accuracy while managing system complexity through modular design.
Solution Approach 2:
The patent replaces traditional mechanical or rule-based estimation methods with a neural network model (specifically LSTM or GRU recurrent neural networks). This substitution allows the system to capture complex non-linear degradation patterns that traditional methods cannot handle, significantly improving estimation accuracy for supercapacitor SoH.
2Difficulty of detecting and measuring
If simple monitoring systems are used, then the device complexity remains low, but the ability to detect and measure non-linear degradation patterns deteriorates
Solution Approach 1:
The data construction unit acts as an intermediary that processes raw monitoring data into structured time-series matrices, enabling the neural network to effectively detect and measure non-linear degradation patterns. This intermediary layer transforms complex raw data into a format that reveals degradation trends without requiring overly complex monitoring hardware.
Solution Approach 2:
The system implements feedback mechanisms where the neural network model continuously learns from historical charge/discharge data and adjusts its predictions. The model uses past degradation patterns to inform future SoH estimates, improving detection capability through iterative learning while maintaining a manageable monitoring system structure.
3Measurement precision
If advanced neural network models are deployed, then the SoH estimation accuracy improves, but the computational resources and processing time increase
Solution Approach 1:
The system performs preliminary data construction and preprocessing of charge/discharge data into structured time-series matrices before feeding them to the neural network model. This preliminary action organizes the data in advance, allowing the neural network to process information more efficiently during actual SoH estimation, reducing real-time processing time while maintaining high accuracy.
Solution Approach 2:
The patent segments the neural network processing into distinct components: a data construction unit that prepares input data and a separate neural network model (LSTM or GRU) that performs estimation. This segmentation allows each component to be optimized independently, reducing overall processing time while preserving estimation accuracy.
Data Source
AI summary
A system and a method for supercapacitor state-of-health (SoH) estimation. The system includes: a data detector that monitors charge-discharge data of a supercapacitor mounted in a vehicle; a vehicle controller including a data construction unit that constructs a time series data matrix for each charge/discharge cycle of the supercapacitor based on the charge-discharge data monitored by the data detector, and a neural network model that estimates SoH of the supercapacitor using the time series data matrix for each charge-discharge cycle of the supercapacitor output from the data construction unit; and a display device that displays an estimation result for the SoH of the supercapacitor estimated by the neural network model of the vehicle controller.