Scholarlink

<p>The stability of the mine ventilation system is crucial for the safety of miners and the production efficiency of mines. Considering the complex and variable mine environment, accurate diagnosis of ventilator bearing faults is of great significance. This paper proposes a fault diagnosis method for mine ventilator bearings based on an improved fuzzy neural network (FNN). By collecting and analyzing the operating data of mine ventilator bearings, fuzzy logic is used to classify the fault characteristics of bearings, and a neural network is employed for learning and training to identify different types of fault patterns. The established fuzzy neural network is trained and tested using a label list, realizing the fault diagnosis of the main mine ventilator. The experimental results show that after self-organizing map classification and confusion matrix verification, the diagnostic accuracy of the test results is 98.87 %.</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

Research on fault characteristics of mine ventilator bearings based on fuzzy neural network

  • 期刊论文

  • 发表日期：

    2025年8月14日

查看全文
  • KunSheng Ma,
  • Sheng Yan,
  • Qili Wang,
  • Ji Liu,
  • Xianzhu Ning,
  • Jiankun Xu

摘要

The stability of the mine ventilation system is crucial for the safety of miners and the production efficiency of mines. Considering the complex and variable mine environment, accurate diagnosis of ventilator bearing faults is of great significance. This paper proposes a fault diagnosis method for mine ventilator bearings based on an improved fuzzy neural network (FNN). By collecting and analyzing the operating data of mine ventilator bearings, fuzzy logic is used to classify the fault characteristics of bearings, and a neural network is employed for learning and training to identify different types of fault patterns. The established fuzzy neural network is trained and tested using a label list, realizing the fault diagnosis of the main mine ventilator. The experimental results show that after self-organizing map classification and confusion matrix verification, the diagnostic accuracy of the test results is 98.87 %.