AI Battery SOH Control via EV Charging Stations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing battery management systems fail to efficiently monitor and adapt charging/discharging control logic based on the degradation state of electric vehicle batteries, leading to uneven performance degradation due to varying driving habits and environments.
Innovation Solution
A battery performance management system using an AI-driven platform that collects and analyzes big data from multiple charging stations to determine battery degradation levels and update control factors for charging/discharging, optimizing battery performance and extending service life.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Duration of action of stationary object
If battery charging/discharging control logic is not updated based on degradation state, then system complexity is reduced, but battery service life is shortened due to uneven performance degradation
Solution Approach 1:
The system performs preliminary actions by collecting battery performance evaluation information from multiple charging stations in advance, storing it in a database, and training an AI model beforehand. This allows the control logic to be updated proactively based on predicted degradation patterns rather than reactively, extending battery service life while maintaining manageable system complexity through automated preprocessing
Solution Approach 2:
The system implements feedback mechanisms by continuously collecting battery performance data from charging stations, analyzing degradation patterns through AI models, and updating control logic based on the analyzed results. This closed-loop feedback enables adaptive optimization of charging/discharging strategies to extend battery life without requiring complex manual intervention
2Reliability
If centralized monitoring of multiple batteries is implemented, then battery performance management is improved, but device complexity increases
Solution Approach 1:
The system achieves universality by creating a centralized platform that handles multiple batteries through unified processes: collecting performance data from various charging stations, storing in a common database, analyzing with AI models, and distributing updated control logic. This multi-functional approach improves reliability across all batteries while avoiding the complexity of multiple separate monitoring systems
Solution Approach 2:
The server acts as an intermediary between charging stations and battery management systems. It collects data from multiple charging stations, processes information through AI models, and distributes control updates to batteries. This intermediary role simplifies the overall system architecture by centralizing complex functions in a single coordinating component rather than distributing complexity across all nodes
3Measurement precision
If AI model training with big data is implemented, then measurement precision of degradation level is improved, but loss of time for data collection and processing increases
Solution Approach 1:
The system performs preliminary data collection from multiple charging stations and stores performance evaluation information in a database before AI model training. By preparing the data infrastructure in advance and using pre-collected big data from distributed charging stations, the system achieves high measurement precision for degradation levels without requiring time-consuming data collection during critical battery operations
Solution Approach 2:
The system maintains continuity of useful action by continuously collecting battery performance data from multiple charging stations in the background while the AI model processes information. Data collection is an ongoing process that doesn't interrupt critical battery operations, allowing the system to accumulate sufficient big data for accurate degradation assessment without significant time loss
Data Source
Figure 1
Figure 2~3
Figure 4~5
AI summary
Disclosed is a battery performance management system and method using an electric vehicle charging station. The battery performance management server collects battery performance evaluation information including identification information and operation characteristic accumulative information of a battery, identification information and driving characteristic accumulative information of the electric vehicle, and latest charging characteristic information of the battery from a plurality of charging stations through a network. Also, the server determines a current SOH corresponding to the collected battery performance evaluation information by using an artificial intelligence model that is trained in advance to receive the battery performance evaluation information and output a SOH of the battery. Also, the server determines a latest control factor corresponding to the current SOH, and transmits the latest control factor to the charging station through the network so that the charging station may transmit the latest control factor to a control system of the electric vehicle to update the control factor.