Intelligent fault diagnosis of belt conveyor rollers using a polar KNN algorithm with audio features

IF 4.4 2区 工程技术 Q1 ENGINEERING, MECHANICAL
Juan Liu , Shiming Fu , Fen Liu , Xuefeng Cheng
{"title":"Intelligent fault diagnosis of belt conveyor rollers using a polar KNN algorithm with audio features","authors":"Juan Liu ,&nbsp;Shiming Fu ,&nbsp;Fen Liu ,&nbsp;Xuefeng Cheng","doi":"10.1016/j.engfailanal.2024.109101","DOIUrl":null,"url":null,"abstract":"<div><div>Belt conveyor rollers are critical components in industrial applications, where early fault detection is essential to maintaining operational efficiency and safety. Existing fault diagnosis methods, such as vibration- and vision-based approaches, often face limitations due to high costs, sensor degradation, and environmental interferences, particularly in complex settings like mines. This study proposes an intelligent fault diagnosis method using a polar K-nearest neighbor (PKNN) algorithm combined with audio signal features. The PKNN algorithm enhances the classic KNN model by integrating both distance and angular similarities, allowing it to capture subtle variations in audio signals indicative of roller faults. The proposed PKNN model was tested on 17 different audio datasets, demonstrating robust performance with 97.34% accuracy, 96.89% precision, 96.72% recall, and 96.70% F1 score. Comparative analyses revealed that PKNN outperformed conventional machine learning models and other audio, vibration, and vision-based diagnostic methods, achieving superior fault classification accuracy and adaptability even in high-noise environments. These findings indicate that the PKNN model offers a reliable, non-invasive, and cost-effective solution for real-time monitoring and fault diagnosis of belt conveyor rollers. Its high adaptability to challenging industrial environments underscores its potential for wide-ranging applications in automated conveyor system maintenance.</div></div>","PeriodicalId":11677,"journal":{"name":"Engineering Failure Analysis","volume":"168 ","pages":"Article 109101"},"PeriodicalIF":4.4000,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Engineering Failure Analysis","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1350630724011476","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
引用次数: 0

Abstract

Belt conveyor rollers are critical components in industrial applications, where early fault detection is essential to maintaining operational efficiency and safety. Existing fault diagnosis methods, such as vibration- and vision-based approaches, often face limitations due to high costs, sensor degradation, and environmental interferences, particularly in complex settings like mines. This study proposes an intelligent fault diagnosis method using a polar K-nearest neighbor (PKNN) algorithm combined with audio signal features. The PKNN algorithm enhances the classic KNN model by integrating both distance and angular similarities, allowing it to capture subtle variations in audio signals indicative of roller faults. The proposed PKNN model was tested on 17 different audio datasets, demonstrating robust performance with 97.34% accuracy, 96.89% precision, 96.72% recall, and 96.70% F1 score. Comparative analyses revealed that PKNN outperformed conventional machine learning models and other audio, vibration, and vision-based diagnostic methods, achieving superior fault classification accuracy and adaptability even in high-noise environments. These findings indicate that the PKNN model offers a reliable, non-invasive, and cost-effective solution for real-time monitoring and fault diagnosis of belt conveyor rollers. Its high adaptability to challenging industrial environments underscores its potential for wide-ranging applications in automated conveyor system maintenance.
基于音频特征的极性KNN算法的带式输送机托辊故障智能诊断
带式输送机托辊是工业应用中的关键部件,早期故障检测对于保持运行效率和安全性至关重要。现有的故障诊断方法,如基于振动和视觉的方法,由于成本高、传感器退化和环境干扰,特别是在矿山等复杂环境中,往往面临局限性。本文提出了一种结合音频信号特征的极k近邻(PKNN)算法的智能故障诊断方法。PKNN算法通过整合距离和角度相似性来增强经典KNN模型,使其能够捕获指示滚轮故障的音频信号的细微变化。本文提出的PKNN模型在17个不同的音频数据集上进行了测试,显示出97.34%的准确率、96.89%的精度、96.72%的召回率和96.70%的F1得分。对比分析表明,PKNN优于传统的机器学习模型和其他基于音频、振动和视觉的诊断方法,即使在高噪声环境下也能实现卓越的故障分类精度和适应性。这些结果表明,PKNN模型为带式输送机托辊的实时监测和故障诊断提供了一种可靠、无创、经济的解决方案。其对具有挑战性的工业环境的高适应性强调了其在自动化输送系统维护中的广泛应用潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Engineering Failure Analysis
Engineering Failure Analysis 工程技术-材料科学:表征与测试
CiteScore
7.70
自引率
20.00%
发文量
956
审稿时长
47 days
期刊介绍: Engineering Failure Analysis publishes research papers describing the analysis of engineering failures and related studies. Papers relating to the structure, properties and behaviour of engineering materials are encouraged, particularly those which also involve the detailed application of materials parameters to problems in engineering structures, components and design. In addition to the area of materials engineering, the interacting fields of mechanical, manufacturing, aeronautical, civil, chemical, corrosion and design engineering are considered relevant. Activity should be directed at analysing engineering failures and carrying out research to help reduce the incidences of failures and to extend the operating horizons of engineering materials. Emphasis is placed on the mechanical properties of materials and their behaviour when influenced by structure, process and environment. Metallic, polymeric, ceramic and natural materials are all included and the application of these materials to real engineering situations should be emphasised. The use of a case-study based approach is also encouraged. Engineering Failure Analysis provides essential reference material and critical feedback into the design process thereby contributing to the prevention of engineering failures in the future. All submissions will be subject to peer review from leading experts in the field.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信