Scholarlink

Axle counter equipment is a key component in urban rail transit signal systems, and its stability has a great impact on safety and operation efficiency. In this paper, we pay attention to the assessment and prediction methods of the health degree for axle counter equipment in urban rail transit and the corresponding maintenance suggestions. Mainly, two prediction methods, the GM (1, 1) algorithm and the long short-term memory (LSTM) network, are used to compare the prediction effect of health degree for axle counter equipment. Based on enough historical information, the LSTM network can obtain more accurate prediction results with less data input.

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

Study of Health Degree Assessment and Prediction for Axle Counter Equipment in Urban Rail Transit

  • 会议论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年

查看全文
  • Jianjun Yuan,
  • Pengzi Chu,
  • Chunye Huang,
  • Zhe Shen,
  • Yi Yu

摘要

Axle counter equipment is a key component in urban rail transit signal systems, and its stability has a great impact on safety and operation efficiency. In this paper, we pay attention to the assessment and prediction methods of the health degree for axle counter equipment in urban rail transit and the corresponding maintenance suggestions. Mainly, two prediction methods, the GM (1, 1) algorithm and the long short-term memory (LSTM) network, are used to compare the prediction effect of health degree for axle counter equipment. Based on enough historical information, the LSTM network can obtain more accurate prediction results with less data input.