Evaluating Service Life of Metal Processing Machinery: An Intelligent Monitoring Perspective

Author:

Wang Hsiao-Yu1,Hung Ching-Hua1,Chen Cheng-Hui2

Affiliation:

1. National Yang Ming Chiao Tung University

2. National Chin-Yi University of Technology

Abstract

Abstract

This investigation addresses a range of critical challenges within the domain of mechanical engineering and anticipates their potential impacts. The study's goals include developing methods for detecting tool breakage in integrated milling-turning machines, evaluating the service life of punching machine components, and determining the durability of molds in forging equipment, alongside other complex issues. The primary aim is to devise a specialized equipment health diagnostic system, designed for complex industrial environments. Industry consultation has revealed that effective monitoring strategies and threshold values must be tailored to the specific characteristics of each piece of equipment and their respective sectors. Despite the metal processing industry lagging roughly a decade behind the semiconductor sector in adopting intelligent monitoring systems, it encounters similar hurdles. These include shrinking labor demographics necessitating increased reliance on shift-based external labor, higher turnover rates impacting the retention of skilled workers for essential tasks such as tool replacements and machinery maintenance. Furthermore, there is a pressing need to maintain traceability for the usage history of molds and punching heads, especially to meet aerospace industry regulations. In response, the sector aims to accomplish two primary goals for its critical production machinery: firstly, to implement diagnostic tools for evaluating the wear and overall quality of tools and molds; secondly, to shift from time-based to condition-based maintenance protocols, adaptable to the frequent mold changes required for varied product fabrication.

Publisher

Springer Science and Business Media LLC

Reference10 articles.

1. Zhidong Z, Min P, Yuquan C (2004) Instantaneous frequency estimate for non-stationary signal Fifth World Congress on Intelligent Control and Automation, vol. 4, pp. 3641–3643,

2. Hilbert–Huang transform-based vibration signal analysis for machine health monitoring;Ruqiang Y;IEEE Trans Instrum Meas,2006

3. Yuping Z (2006) Hilbert-Huang transform and marginal spectrum for detection of bearing localized defects, The Sixth World Congress on Intelligent Control and Automation, vol. 2, pp. 5457–5461,

4. Sari DY, Wu T-L (2017) Investigation on sound signal emitted bypunching process for punch failure monitoring Conference Paper · March

5. Preliminary study for online monitoring during the punching process;Sari DY;Int J Adv Manuf Technol,2017

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3