EV Distance-to-Empty Prediction Using Epoch-Based Battery Discharge Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the driving range of electric vehicles are not sufficiently accurate and reliable due to variations in battery discharge rates influenced by factors like temperature, load, and driving patterns.
Innovation Solution
A system and method that utilizes a data interface to collect vehicle data, applies a distance-to-empty predictor with a statistical model and state of charge rate prediction, incorporating temperature measurements and energy consumption data to estimate the remaining battery charge and travel distance, using a combination of statistical models and deep learning techniques to filter outliers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If simple mechanical or electrical sensors are used to determine charge level, then the system complexity is low, but the measurement precision and reliability of driving range prediction is insufficient
Solution Approach 1:
The patent segments the driving range prediction into multiple epochs (time intervals), analyzing energy consumption and speed characteristics for each epoch separately. This allows the system to capture varying driving conditions and battery discharge rates over time, improving prediction accuracy without requiring a single complex monolithic model.
Solution Approach 2:
The system pre-trains statistical models using historical vehicle data before actual prediction. By pre-processing and storing epoch data structures containing energy consumption rates and speed information, the system prepares prediction models in advance, enabling more accurate real-time predictions while keeping the runtime computation relatively simple.
2Reliability
If historical vehicle data is collected and processed through statistical models, then the driving range prediction accuracy improves, but the data processing complexity and computational requirements increase
Solution Approach 1:
The patent divides historical data into discrete epochs with standardized data structures containing energy consumption rates and speed information. This segmentation allows the statistical model to process data in manageable units, improving reliability by capturing temporal variations while controlling processing complexity through structured data organization.
Solution Approach 2:
The system transforms raw vehicle data into derived parameters such as energy consumption rates (dE/dt) and speed (dx/dt) for each epoch. By changing the parameter representation from raw sensor data to processed statistical features, the system improves prediction reliability while the standardized parameter structure helps manage computational complexity.
3Measurement precision
If the system accounts for varying discharge rates based on temperature, load, and driving patterns, then the prediction accuracy improves, but the computational complexity increases
Solution Approach 1:
The patent implements periodic analysis by dividing the prediction into discrete epochs and using iterative prediction loops. The system periodically updates predictions by processing each epoch sequentially, allowing it to account for varying conditions (temperature, load, driving patterns) at different time points without requiring simultaneous complex computation for all factors.
Solution Approach 2:
The system dynamically adjusts predictions by incorporating epoch-specific energy consumption rates and speed variations. Rather than using fixed discharge rates, the model adapts to changing conditions through the statistical relationship between energy consumption, speed, and state of charge, improving accuracy while managing complexity through incremental updates.
Data Source
AI summary
Methods and Systems are provided for predicting a distance until the batter in an electric vehicle is discharged. Vehicle and geophysical data are received and formatted in n epochs over a time period T. For each epoch, an epoch data structure including a total energy consumption rate, a state of charge rate, and a distance rate is generated. The epochs are processed using a vector autoregression model to generate a predicted epoch data structure. A predicted state of charge is calculated using a state of charge model. A predicted distance traveled in the next epoch is calculated. A predicted charge to empty is calculated and checked to determine if the predicted charge to empty has reached an empty level. The process is repeated until the predicted charge to empty reaches an empty level. The distance to empty is then reported to the driver.