Battery Deterioration Diagnosis Using Selectable AI Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing battery diagnostic methods using single AI models for estimating battery deterioration accuracy are compromised by varying physical quantities due to different connected devices, leading to reduced estimation accuracy.
Innovation Solution
A battery diagnostic device that acquires physical quantities and selects a suitable diagnostic model from multiple AI models based on these quantities to estimate battery deterioration, improving estimation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single diagnostic model is used for battery deterioration estimation, then the device complexity is reduced, but the estimation accuracy deteriorates when different devices are connected to the battery
Solution Approach 1:
The patent changes the parameter of diagnostic model selection based on the connection status of external devices. When a protection circuit is connected, a first diagnostic model is selected; when no protection circuit is connected, a second diagnostic model is selected. This parameter-based selection resolves the contradiction by adapting the diagnostic approach to the specific operational context, maintaining high estimation accuracy without requiring a single overly complex model to handle all scenarios
Solution Approach 2:
The patent segments the diagnostic system into multiple specialized diagnostic models (first diagnostic model for batteries with protection circuits, second diagnostic model for batteries without protection circuits). Each model is optimized for its specific scenario, improving estimation accuracy for each segment while keeping individual model complexity manageable compared to a universal model
2Measurement precision
If multiple diagnostic models are prepared for different connection scenarios, then the estimation accuracy is improved, but the device complexity increases
Solution Approach 1:
The patent performs preliminary detection of the connection status (whether a protection circuit is connected) before selecting the diagnostic model. This preliminary action allows the system to automatically choose the appropriate model in advance, improving estimation accuracy without requiring complex real-time decision-making mechanisms during the diagnostic process
Data Source
AI summary
A battery diagnostic device for diagnosing a state of a battery mounted on a vehicle includes: an acquisition unit that acquires a physical quantity indicating the state of the battery; a setting unit that sets one diagnostic model from two or more diagnostic models based on the physical quantity acquired by the acquisition unit; and an estimation unit that estimates a deterioration state of the battery based on the one diagnostic model set by the setting unit.