Battery SOH Estimation Using Real-Time Discharge Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Accurately predicting and managing the state of health (SOH) of electric vehicle batteries is challenging due to various factors such as driving patterns, environmental conditions, and lack of industry standards, leading to inefficient battery degradation minimization.
Innovation Solution
A system utilizing machine learning techniques, including meta-learning and ensemble learning, combined with blockchain for secure data sharing, to predict battery SOH by integrating real-time data from multiple stakeholders, such as RSUs, OEMs, and charging stations, and providing control information to minimize degradation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional battery SOH prediction methods are used, then the system is simpler to implement, but the prediction accuracy is insufficient
Solution Approach 1:
The system segments the SOH prediction task by creating separate machine learning models for different battery conditions, operating scenarios, and degradation patterns. Each model specializes in specific aspects of battery behavior, allowing high accuracy through divided expertise while managing complexity through modular architecture.
Solution Approach 2:
The system transitions from traditional single-dimension SOH estimation to multi-dimensional prediction by incorporating numerous features including temperature, charge/discharge rates, cycle history, and environmental conditions. This dimensional expansion enables comprehensive accuracy improvement through holistic battery state analysis.
2Loss of information
If real-time data from multiple stakeholders is integrated, then the prediction transparency is improved, but the data processing complexity increases
Solution Approach 1:
The system introduces blockchain technology as an intermediary layer that securely manages data from multiple stakeholders (OEMs, charging stations, RSUs). The blockchain provides transparent, immutable data recording and verification mechanisms, enabling trusted data integration without requiring complex direct peer-to-peer data management systems.
Solution Approach 2:
The system creates a universal data integration platform that handles diverse data types from multiple sources through standardized interfaces. This multi-functional approach consolidates data collection, validation, storage, and processing into a single system architecture, reducing overall complexity despite handling multiple stakeholder data streams.
3Measurement precision
If machine learning models are continuously updated with discharge data, then the prediction accuracy is improved, but the computational resources required increase
Solution Approach 1:
The system implements periodic model updating rather than continuous real-time retraining. Machine learning models are updated at scheduled intervals or triggered by significant data milestones, maintaining high prediction accuracy through regular updates while avoiding the excessive computational energy consumption of continuous real-time retraining operations.
Data Source
AI summary
In some examples, a system may determine route information for a route to be traversed by a vehicle from a start location to a destination location, the vehicle including a battery having a state of health. The system receives discharge data corresponding to traversal of the vehicle along the route, the discharge data indicative of a rate of discharge of the battery at a plurality of locations along the route. Based on the received discharge data, the system at least one of trains or updates a first machine learning model configured for predicting the state of health of the battery. The vehicle may determine an estimated battery state of health based at least on the first machine learning model, and may receive control information while traversing the route based on the estimated battery state of health to at least partially minimize battery degradation during traversal of the route.