Battery Management Using Location-Based Model Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing battery management systems face challenges in accurately estimating battery state of health (SOH) due to variations in usage environments, such as temperature, humidity, and road conditions, which are not adequately considered in current material parameter-based or statistical training methods.
Innovation Solution
A battery management apparatus and method that utilizes location information from GPS and other sources to dynamically adjust estimation models, incorporating environmental factors like temperature, humidity, weather, and geography through communication with servers via WiFi, Zigbee, NFC, Bluetooth, or RF, using neural networks or deep neural networks to enhance SOH estimation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If material parameter-based estimation technique is used to estimate battery SOH, then the estimation process is simplified, but the estimation error increases due to various approximations
Solution Approach 1:
The patent changes the parameters used in SOH estimation from simple material parameters to a comprehensive set including location information, environmental factors (temperature, humidity, weather), and usage conditions. This allows the system to adapt estimation models to different operating conditions, improving accuracy without requiring overly complex estimation processes.
2Ease of operation
If statistical training method with lookup table is used to estimate battery SOH, then the estimation can be performed using standard sensing data, but the accuracy is insufficient when battery usage environments vary
Solution Approach 1:
The patent implements a dynamic estimation model that adapts to changing environmental conditions. The system dynamically selects or adjusts estimation parameters based on location information and environmental factors, transforming a static lookup table approach into a dynamic, context-aware estimation system that maintains both operational simplicity and environmental adaptability.
Solution Approach 2:
The system changes estimation parameters based on environmental conditions by incorporating location information and environmental factors. Different parameter sets are applied for different locations and conditions, allowing the statistical training method to adapt to varying battery usage environments while maintaining ease of operation through automated parameter selection.
3Device complexity
If fixed estimation model is used for battery SOH estimation, then the model structure is simple, but the model cannot accurately reflect variations in battery performance under different environmental conditions
Solution Approach 1:
The patent applies local quality by tailoring estimation parameters to specific locations and environmental conditions. Instead of using a uniform model everywhere, the system adjusts estimation parameters locally based on GPS location and environmental factors, ensuring that each region's unique characteristics are reflected in the SOH estimation process.
Solution Approach 2:
The estimation model transitions from a fixed structure to a dynamic one that adapts to environmental changes. The system dynamically adjusts model parameters based on location information and environmental conditions, maintaining relatively simple model structures while improving reliability through context-aware parameter adaptation.
4Measurement precision
If location information and environmental factors are incorporated into the estimation model, then the SOH estimation accuracy improves, but the system complexity and data processing requirements increase
Solution Approach 1:
The patent implements a universal estimation framework that handles multiple data types (location information, environmental factors, battery parameters) through a unified parameter adaptation mechanism. This multi-functional approach allows the system to process diverse inputs without requiring separate complex processing paths for each data type, thereby improving accuracy while controlling system complexity.
Data Source
AI summary
The present disclosure is related to a battery management system which includes a location information obtainer configured to obtain location information of a battery, and an estimation model changer configured to change an estimation model to estimate an internal state of the battery according to a change in the location information.