A predictive maintenance system for integral type faults based on support vector machines: An application to ion implantation

Gian Antonio Susto; Andrea Schirru; Simone Pampuri; Daniele Pagano; Sean McLoone; Alessandro Beghi

doi:10.1109/CoASE.2013.6653952

A predictive maintenance system for integral type faults based on support vector machines: An application to ion implantation

Gian Antonio Susto^*, Andrea Schirru, Simone Pampuri, Daniele Pagano, Sean McLoone, Alessandro Beghi

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

13 Citations (Scopus)

Abstract

In semiconductor fabrication processes, effective management of maintenance operations is fundamental to decrease costs associated with failures and downtime. Predictive Maintenance (PdM) approaches, based on statistical methods and historical data, are becoming popular for their predictive capabilities and low (potentially zero) added costs. We present here a PdM module based on Support Vector Machines for prediction of integral type faults, that is, the kind of failures that happen due to machine usage and stress of equipment parts. The proposed module may also be employed as a health factor indicator. The module has been applied to a frequent maintenance problem in semiconductor manufacturing industry, namely the breaking of the filament in the ion-source of ion-implantation tools. The PdM has been tested on a real production dataset.

Original language	English
Title of host publication	IEEE International Conference on Automation Science and Engineering
Pages	195-200
Number of pages	6
DOIs	https://doi.org/10.1109/CoASE.2013.6653952
Publication status	Published - 01 Dec 2013
Event	2013 IEEE International Conference on Automation Science and Engineering, CASE 2013 - WI, Madison, United States Duration: 17 Aug 2013 → 20 Aug 2013

Conference

Conference	2013 IEEE International Conference on Automation Science and Engineering, CASE 2013
Country/Territory	United States
City	Madison
Period	17/08/2013 → 20/08/2013

Keywords

Classification Methods
Ion-Implantation
Predictive Maintenance
Semiconductor Manufacturing
Support Vector Machines

ASJC Scopus subject areas

Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/CoASE.2013.6653952

Cite this

@inproceedings{de46d464ba394d06b5e259587df5f4ce,

title = "A predictive maintenance system for integral type faults based on support vector machines: An application to ion implantation",

abstract = "In semiconductor fabrication processes, effective management of maintenance operations is fundamental to decrease costs associated with failures and downtime. Predictive Maintenance (PdM) approaches, based on statistical methods and historical data, are becoming popular for their predictive capabilities and low (potentially zero) added costs. We present here a PdM module based on Support Vector Machines for prediction of integral type faults, that is, the kind of failures that happen due to machine usage and stress of equipment parts. The proposed module may also be employed as a health factor indicator. The module has been applied to a frequent maintenance problem in semiconductor manufacturing industry, namely the breaking of the filament in the ion-source of ion-implantation tools. The PdM has been tested on a real production dataset.",

keywords = "Classification Methods, Ion-Implantation, Predictive Maintenance, Semiconductor Manufacturing, Support Vector Machines",

author = "Susto, {Gian Antonio} and Andrea Schirru and Simone Pampuri and Daniele Pagano and Sean McLoone and Alessandro Beghi",

year = "2013",

month = dec,

day = "1",

doi = "10.1109/CoASE.2013.6653952",

language = "English",

isbn = "9781479915156",

pages = "195--200",

booktitle = "IEEE International Conference on Automation Science and Engineering",

note = "2013 IEEE International Conference on Automation Science and Engineering, CASE 2013 ; Conference date: 17-08-2013 Through 20-08-2013",

}

Susto, GA, Schirru, A, Pampuri, S, Pagano, D, McLoone, S & Beghi, A 2013, A predictive maintenance system for integral type faults based on support vector machines: An application to ion implantation. in IEEE International Conference on Automation Science and Engineering., 6653952, pp. 195-200, 2013 IEEE International Conference on Automation Science and Engineering, CASE 2013, Madison, United States, 17/08/2013. https://doi.org/10.1109/CoASE.2013.6653952

A predictive maintenance system for integral type faults based on support vector machines : An application to ion implantation. / Susto, Gian Antonio; Schirru, Andrea; Pampuri, Simone; Pagano, Daniele; McLoone, Sean; Beghi, Alessandro.

IEEE International Conference on Automation Science and Engineering. 2013. p. 195-200 6653952.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A predictive maintenance system for integral type faults based on support vector machines

T2 - 2013 IEEE International Conference on Automation Science and Engineering, CASE 2013

AU - Susto, Gian Antonio

AU - Schirru, Andrea

AU - Pampuri, Simone

AU - Pagano, Daniele

AU - McLoone, Sean

AU - Beghi, Alessandro

PY - 2013/12/1

Y1 - 2013/12/1

N2 - In semiconductor fabrication processes, effective management of maintenance operations is fundamental to decrease costs associated with failures and downtime. Predictive Maintenance (PdM) approaches, based on statistical methods and historical data, are becoming popular for their predictive capabilities and low (potentially zero) added costs. We present here a PdM module based on Support Vector Machines for prediction of integral type faults, that is, the kind of failures that happen due to machine usage and stress of equipment parts. The proposed module may also be employed as a health factor indicator. The module has been applied to a frequent maintenance problem in semiconductor manufacturing industry, namely the breaking of the filament in the ion-source of ion-implantation tools. The PdM has been tested on a real production dataset.

AB - In semiconductor fabrication processes, effective management of maintenance operations is fundamental to decrease costs associated with failures and downtime. Predictive Maintenance (PdM) approaches, based on statistical methods and historical data, are becoming popular for their predictive capabilities and low (potentially zero) added costs. We present here a PdM module based on Support Vector Machines for prediction of integral type faults, that is, the kind of failures that happen due to machine usage and stress of equipment parts. The proposed module may also be employed as a health factor indicator. The module has been applied to a frequent maintenance problem in semiconductor manufacturing industry, namely the breaking of the filament in the ion-source of ion-implantation tools. The PdM has been tested on a real production dataset.

KW - Classification Methods

KW - Ion-Implantation

KW - Predictive Maintenance

KW - Semiconductor Manufacturing

KW - Support Vector Machines

UR - http://www.scopus.com/inward/record.url?scp=84891505814&partnerID=8YFLogxK

U2 - 10.1109/CoASE.2013.6653952

DO - 10.1109/CoASE.2013.6653952

M3 - Conference contribution

AN - SCOPUS:84891505814

SN - 9781479915156

SP - 195

EP - 200

BT - IEEE International Conference on Automation Science and Engineering

Y2 - 17 August 2013 through 20 August 2013

ER -

A predictive maintenance system for integral type faults based on support vector machines: An application to ion implantation

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this