Battery State-of-Health Prediction Using Vehicle Route Profiles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing battery management systems in electric and hybrid electric vehicles struggle to accurately predict the state of health (SOH) of batteries, leading to potential premature replacement or failure, resulting in warranty and downtime costs.
Innovation Solution
A system that generates a vehicle-specific route profile based on historical driving data, converts it to a battery demand profile, and predicts the state of health using a battery model, allowing for advanced warnings and optimized scheduling to extend battery life.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If battery replacement is scheduled in advance based on fixed time intervals, then maintenance planning is simplified, but batteries may be replaced prematurely or fail unexpectedly due to varying usage patterns
Solution Approach 1:
The system performs preliminary analysis of historical driving data to generate vehicle-specific route profiles before battery failure occurs. These profiles predict future battery demand and state of health, enabling advance maintenance planning that adapts to actual usage patterns rather than fixed schedules.
Solution Approach 2:
The system continuously monitors actual driving behavior and compares it with historical data to update route profiles and battery predictions. This feedback loop refines the accuracy of state of health predictions over time, allowing maintenance schedules to adapt dynamically to changing usage patterns.
2Measurement precision
If batteries are monitored continuously to predict exact failure time, then replacement can be timed optimally, but system complexity and data processing requirements increase
Solution Approach 1:
The system creates simplified virtual representations (digital twins) of battery behavior based on historical driving data. These route profiles serve as computational models that predict future battery demand without requiring complex real-time simulations, reducing processing requirements while maintaining prediction accuracy.
Solution Approach 2:
The prediction system divides battery monitoring into discrete route-specific profiles rather than continuous monitoring. Each route profile captures battery demand characteristics for specific driving patterns, allowing the system to analyze and predict state of health for individual route types rather than processing all possible driving scenarios simultaneously.
3Reliability
If batteries are replaced sooner than necessary to ensure reliability, then unexpected failures are reduced, but operational costs and resource utilization increase
Solution Approach 1:
The system transitions from static fixed-interval replacement schedules to dynamic prediction-based timing. Route profiles continuously adapt to actual driving patterns, allowing the system to extend battery life when usage is lighter and schedule replacement closer to actual failure points when degradation accelerates, optimizing both reliability and vehicle utilization.
Data Source
AI summary
A system and method used to predict the state of health of a battery in a powertrain of a vehicle including a vehicle route profile generator arranged to generate a vehicle specific rout profile based on historical vehicle driving information, are disclosed. In one example, the system and method also include a powertrain model to convert the vehicle specific route profile to a predicted battery demand profile, and a state of health profile generator to generate a predicted state of health profile of the battery based on the predicted battery demand. In another example, the system further includes a vehicle performance manager arranged to generate a command to modify operation of the powertrain to extend battery life based on the vehicle specific route profile.