Total precision inspection of machine tools with virtual metrology

Haw Ching Yang, Hao Tieng, Fan Tien Cheng

研究成果: Article

9 引文 (Scopus)

摘要

The technology of virtual metrology (VM) has been applied in the semiconductor industry to convert sampling inspection with metrology delay into real time and online total inspection. The purpose of this study is trying to apply VM for inspecting machining precision of machine tools. However, machining processes will cause severe vibrations that make process data collection, data cleaning, and feature extraction difficult to handle. Thus, the tasks of how to accurately segment essential parts of the raw process data from the original numerical-control file, how to effectively handle raw process/sensor data with low signal-to-noise ratios, and how to properly extract significant features from the segmented and clean raw process data are challenging issues for successfully applying VM to machine tools. These issues are judiciously addressed and successfully resolved in this paper. Testing results of machining standard workpieces and cellphone shells of two three-axis CNC machines show that the proposed approach of applying VM to accomplish total precision inspection of machine tools is promising.

指紋

Machine tools
Inspection
Machining
Feature extraction
Cleaning
Signal to noise ratio
Semiconductor materials
Sampling
Sensors
Testing
Industry

All Science Journal Classification (ASJC) codes

  • Engineering(all)

引用此文

@article{f1e187119cb14256b48830bf64e4d0b6,
title = "Total precision inspection of machine tools with virtual metrology",
abstract = "The technology of virtual metrology (VM) has been applied in the semiconductor industry to convert sampling inspection with metrology delay into real time and online total inspection. The purpose of this study is trying to apply VM for inspecting machining precision of machine tools. However, machining processes will cause severe vibrations that make process data collection, data cleaning, and feature extraction difficult to handle. Thus, the tasks of how to accurately segment essential parts of the raw process data from the original numerical-control file, how to effectively handle raw process/sensor data with low signal-to-noise ratios, and how to properly extract significant features from the segmented and clean raw process data are challenging issues for successfully applying VM to machine tools. These issues are judiciously addressed and successfully resolved in this paper. Testing results of machining standard workpieces and cellphone shells of two three-axis CNC machines show that the proposed approach of applying VM to accomplish total precision inspection of machine tools is promising.",
author = "Yang, {Haw Ching} and Hao Tieng and Cheng, {Fan Tien}",
year = "2016",
month = "2",
day = "17",
doi = "10.1080/02533839.2015.1091279",
language = "English",
volume = "39",
pages = "221--235",
journal = "Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers",
issn = "0253-3839",
publisher = "Chinese Institute of Engineers",
number = "2",

}

TY - JOUR

T1 - Total precision inspection of machine tools with virtual metrology

AU - Yang, Haw Ching

AU - Tieng, Hao

AU - Cheng, Fan Tien

PY - 2016/2/17

Y1 - 2016/2/17

N2 - The technology of virtual metrology (VM) has been applied in the semiconductor industry to convert sampling inspection with metrology delay into real time and online total inspection. The purpose of this study is trying to apply VM for inspecting machining precision of machine tools. However, machining processes will cause severe vibrations that make process data collection, data cleaning, and feature extraction difficult to handle. Thus, the tasks of how to accurately segment essential parts of the raw process data from the original numerical-control file, how to effectively handle raw process/sensor data with low signal-to-noise ratios, and how to properly extract significant features from the segmented and clean raw process data are challenging issues for successfully applying VM to machine tools. These issues are judiciously addressed and successfully resolved in this paper. Testing results of machining standard workpieces and cellphone shells of two three-axis CNC machines show that the proposed approach of applying VM to accomplish total precision inspection of machine tools is promising.

AB - The technology of virtual metrology (VM) has been applied in the semiconductor industry to convert sampling inspection with metrology delay into real time and online total inspection. The purpose of this study is trying to apply VM for inspecting machining precision of machine tools. However, machining processes will cause severe vibrations that make process data collection, data cleaning, and feature extraction difficult to handle. Thus, the tasks of how to accurately segment essential parts of the raw process data from the original numerical-control file, how to effectively handle raw process/sensor data with low signal-to-noise ratios, and how to properly extract significant features from the segmented and clean raw process data are challenging issues for successfully applying VM to machine tools. These issues are judiciously addressed and successfully resolved in this paper. Testing results of machining standard workpieces and cellphone shells of two three-axis CNC machines show that the proposed approach of applying VM to accomplish total precision inspection of machine tools is promising.

UR - http://www.scopus.com/inward/record.url?scp=84956907905&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956907905&partnerID=8YFLogxK

U2 - 10.1080/02533839.2015.1091279

DO - 10.1080/02533839.2015.1091279

M3 - Article

AN - SCOPUS:84956907905

VL - 39

SP - 221

EP - 235

JO - Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers

JF - Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers

SN - 0253-3839

IS - 2

ER -