Battery SOC Estimation Using Categorized Driving Profiles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for estimating the state of charge (SOC) of electric vehicle batteries rely on limited data collection and fail to accurately predict driving range due to variations in driving behavior and road conditions, leading to inaccurate speed and acceleration predictions.
Innovation Solution
An apparatus that stores and categorizes driving history data based on road frequency, generates a driving profile using speed, acceleration, weather, and road data, and estimates SOC by applying a transition probability matrix to improve predictive accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If driving history data is categorized based on road frequency with multiple parameters (speed, acceleration, weather, road profiles), then the accuracy of driving range estimation is improved, but the device complexity and data processing requirements increase
Solution Approach 1:
The patent segments driving history data into multiple categories based on road frequency and characteristics. The driving history data storage categorizes data by road type, frequency of appearance, and other parameters, creating structured segments that can be processed independently. This segmentation allows the system to handle complex data in manageable portions while maintaining high estimation accuracy.
Solution Approach 2:
The patent introduces multiple dimensions for data categorization beyond simple road type, including frequency of appearance, weather conditions, and road profiles. By adding these dimensional layers to the data structure, the system achieves more precise estimation without fundamentally increasing processing complexity, as each dimension builds upon the previous one in a hierarchical manner.
2Reliability
If driving history data is collected and stored for each category based on frequency of appearance, then the reliability of SOC estimation is improved, but the quantity of data to be processed increases
Solution Approach 1:
The patent extracts only the most relevant features from driving history data for categorization, such as frequency of appearance, road type, and key operational parameters. Instead of processing all raw data, the system extracts essential characteristics that contribute to SOC estimation reliability, reducing the effective data volume while maintaining estimation accuracy.
Solution Approach 2:
The patent transforms raw driving history data into categorized parameters based on frequency of appearance and road characteristics. By changing the parameter representation from raw continuous data to discrete categorized data, the system reduces data volume while preserving the essential information needed for reliable SOC estimation.
3Measurement precision
If a transition probability matrix is applied to generate driving profiles using multiple parameters, then the accuracy of speed and acceleration prediction is improved, but the computational complexity increases
Solution Approach 1:
The patent performs preliminary categorization of driving history data before applying the transition probability matrix. By pre-organizing data into frequency-based categories and extracting relevant parameters in advance, the system reduces the computational burden during the actual prediction phase, allowing complex matrix operations to be performed on already-processed data.
Solution Approach 2:
The driving profile generation process uses the categorized driving history data to automatically populate and update the transition probability matrix without requiring external intervention. The system self-adjusts the matrix based on accumulated categorized data, reducing the need for manual calibration and simplifying the overall computational process while maintaining high prediction accuracy.
Data Source
AI summary
An apparatus for estimating a state of charge (SOC) of a battery in an electric vehicle is provided. The apparatus may include a driving history data storage configured to store driving history data for each category among categories generated based on a frequency of appearance of road data, a driving profile generator configured to categorize road data associated with a driving route for each of the generated categories and generate a driving profile with respect to the driving route based on the driving history data corresponding to the categorized road data, and a battery SOC estimator configured to estimate the SOC of a the battery with respect to the driving route based on the driving profile.