一种检测异常车辆电池的方法、装置、设备及介质
By using the unsupervised isolated forest algorithm to perform derivation time-series feature analysis and segmentation processing on electric vehicle battery data, early prediction of battery anomalies is achieved, solving the problems of high battery failure rate and high maintenance cost, and improving the accuracy of battery detection and user experience.
CN116184247BActive Publication Date: 2026-07-17HEFEI GUOXUAN HIGH TECH POWER ENERGY
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HEFEI GUOXUAN HIGH TECH POWER ENERGY
- Filing Date
- 2023-02-28
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies cannot accurately and quickly diagnose abnormalities in electric vehicle batteries, leading to high failure rates and increased maintenance costs.
Method used
An unsupervised isolated forest algorithm is used to perform time-series feature analysis on vehicle battery-related data. By segmenting the data and using a pre-trained unsupervised isolated forest algorithm model, anomaly detection is performed to predict battery failure signs in advance.
Benefits of technology
It improves the accuracy of battery failure prediction, reduces failure rate and maintenance costs, and enhances user experience and brand competitiveness.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116184247B_ABST
Abstract
本发明涉及一种检测异常车辆电池的方法、装置、设备及介质，包括：获取车辆电池相关数据，并对获取的车辆电池相关数据进行衍生得到衍生时序特征数据；基于衍生时序特征数据判断车辆电池充电状态，并获取车辆电池在不同充电周期的车辆特征数据；基于车辆特征数据对所有充电周期的衍生时序特征数据进行分段，得到多个分段数据；将各分段数据均通过基于预先训练的无监督孤立森林算法模型进行异常检测，获得车辆电池异常检测结果。本发明可以提前预判电池故障征兆，降低故障率和运维成本，提升用户体验，保护用户生命财产安全。
Need to check novelty before this filing date? Find Prior Art