Scholarlink

<p>Currently, fault detection in vehicles is implemented as self-diagnosis of subsystems in Electronic Control Units (ECUs) using Diagnostic Trouble Codes (DTCs). Recently, with the advancement of technologies such as autonomous driving, automobile companies are increasingly interested in predictive maintenance policies that detect and respond to vehicle failures in advance through real-time online status monitoring of vehicles in operation. Under these circumstances, it is increasingly important to develop technologies that utilize real-time vehicle data to diagnose and predict vehicle conditions. In this study, we have applied machine learning techniques to solve the problem of predicting the occurrence of specific DTC types by analyzing the collected DTC data of commercial vehicles. The results of the case study showed that the proposed methodology could proactively predict the occurrence of certain DTC types.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Case Study on the DTC Prediction of Commercial Vehicles Using Machine Learning Approach

  • 期刊论文

  • 发表日期：

    2025年1月26日

查看全文
  • Hong-Bae Jun,
  • Sewoong Jung,
  • Hansom Kim,
  • Myunghun Jang,
  • Beomkyu Park,
  • Hyounsoo Sung

摘要

Currently, fault detection in vehicles is implemented as self-diagnosis of subsystems in Electronic Control Units (ECUs) using Diagnostic Trouble Codes (DTCs). Recently, with the advancement of technologies such as autonomous driving, automobile companies are increasingly interested in predictive maintenance policies that detect and respond to vehicle failures in advance through real-time online status monitoring of vehicles in operation. Under these circumstances, it is increasingly important to develop technologies that utilize real-time vehicle data to diagnose and predict vehicle conditions. In this study, we have applied machine learning techniques to solve the problem of predicting the occurrence of specific DTC types by analyzing the collected DTC data of commercial vehicles. The results of the case study showed that the proposed methodology could proactively predict the occurrence of certain DTC types.