Electric Aircraft Battery State Modeling for Remaining Useful Energy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electric aircraft systems lack accurate methods to determine remaining useful energy in batteries, affecting flight range calculations and thermal management.
Innovation Solution
A system and method using a computing device to measure internal battery state data from sensors, train a battery model with correlated energy data, and generate a useful energy remaining datum, enabling accurate energy estimation and thermal runaway prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional battery energy estimation methods are used, then the system is simple to operate, but the measurement precision of remaining useful energy is insufficient
Solution Approach 1:
The system performs preliminary action by training the battery model offline using historical battery data before actual flight operations. This pre-training phase captures battery degradation patterns and establishes the relationship between battery state indicators and remaining useful energy. During actual operation, the pre-trained model is applied directly to new data, enabling accurate predictions without requiring real-time complex processing or retraining, thus resolving the contradiction between measurement precision and operational complexity.
Solution Approach 2:
The battery model serves itself by automatically learning from historical battery data and continuously improving its predictions. The system uses its own operational data to train and refine the model, establishing self-contained capability for accurate energy estimation without requiring external intervention or complex manual calibration processes.
2Measurement precision
If battery model training with comprehensive data is performed, then the remaining useful energy prediction accuracy improves, but the processing time and computational resources increase
Solution Approach 1:
The system performs model training in advance during ground operations or between flights, separating the computationally intensive training phase from the time-critical flight operation phase. This allows comprehensive data processing and model refinement to occur beforehand, ensuring high prediction accuracy during actual flight without consuming valuable flight time or delaying operations.
Solution Approach 2:
The system maintains continuous operation by performing model training during periods when the battery is not in critical use, such as during charging cycles or between flights. This continuous training approach ensures the model remains up-to-date with current battery conditions while maintaining uninterrupted flight readiness, balancing accuracy improvement with operational continuity.
Data Source
AI summary
A system for determining remaining useful energy in an electric aircraft, the system including a computing device where the computing device is configured to measure a internal state datum of a battery as a function of at least a sensor, receive the internal state datum from the at least a sensor, generate a useful energy remaining datum as a function of the internal state datum and a battery model, and display the useful energy remaining datum to a user.