关键零部件故障诊断模型数据集

课题充分考虑了新能源汽车电池、电机和电控系统等关键零部件的安全状态感知、故障及信息数据多维等影响因素，建立了关键零部件故障诊断模型。关键零部件故障诊断采用机器学习模型与值率阈值模型相结合的方法，基于新能源汽车防控平台获取的云端实车数据对模型进行训练，主要记录了温度、电压、电流和SOC等观测值及相关报警项，数据量80M。

This study fully considers multiple influencing factors including safety state perception, faults and multi-dimensional information data of key components such as new energy vehicle batteries, motors and electronic control systems, and establishes a fault diagnosis model for these core components. The fault diagnosis of the key components adopts a method combining machine learning models and value-rate threshold models, and the model is trained using real-vehicle cloud data acquired from the new energy vehicle prevention and control platform. The dataset mainly records observed parameters such as temperature, voltage, current and SOC, as well as related alarm items, with a total data size of 80 MB.

搜集汇总

背景与挑战

背景概述

该数据集专注于新能源汽车关键零部件（如电池、电机和电控系统）的故障诊断，通过结合机器学习模型与值率阈值模型，利用云端实车数据训练，包含温度、电压、电流和SOC等观测值及报警项，数据量约为80MB，旨在支持安全状态感知和故障分析。