Predictive Manufacturing: A Classification Strategy to Predict Product Failures

Abdul Rauf Khan, Henrik Schiøler, Murat Kulahci, Mohamed Zaki, Peter Westermann Rasmussen

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Resumé

Predicting failures can be considered a meaningful insight for the optimal planning of an industrial manufacturing process. In this era of advanced sensor technologies, when the collection of data from each step of the manufacturing process is common practice and advanced analytical skills enable us to efficiently analyze heterogeneous data streams, predicting failure becomes an achievable task. In this article: first, we propose a data mining strategy to deal with heterogeneous streams of data to predict failures in the production process; second, we aim to build a novel predictive manufacturing analytics model that employs a big data approach to predicting product failures; third, we illustrate the issue of high dimensionality, along with statistically redundant information; and, finally, our proposed method will be compared against the well-known classification methods (SVM, K-nearest neighbor, artificial neural networks). The results from real data show that our predictive manufacturing analytics approach, using genetic algorithms and Voronoi tessellations, is capable of predicting product failure with reasonable accuracy. The potential application of this method contributes to accurately predicting product failures, which would enable manufacturers to reduce production costs without compromising product quality.
OriginalsprogEngelsk
TidsskriftExpert Systems with Applications
ISSN0957-4174
StatusAfsendt - 2019

Fingerprint

Data mining
Genetic algorithms
Neural networks
Planning
Sensors
Costs
Big data

Citer dette

Khan, A. R., Schiøler, H., Kulahci, M., Zaki, M., & Rasmussen, P. W. (2019). Predictive Manufacturing: A Classification Strategy to Predict Product Failures. Manuskript afsendt til publicering.
Khan, Abdul Rauf ; Schiøler, Henrik ; Kulahci, Murat ; Zaki, Mohamed ; Rasmussen, Peter Westermann. / Predictive Manufacturing: A Classification Strategy to Predict Product Failures. I: Expert Systems with Applications. 2019.
@article{a202c26331584a628eef5564c077cd62,
title = "Predictive Manufacturing: A Classification Strategy to Predict Product Failures",
abstract = "Predicting failures can be considered a meaningful insight for the optimal planning of an industrial manufacturing process. In this era of advanced sensor technologies, when the collection of data from each step of the manufacturing process is common practice and advanced analytical skills enable us to efficiently analyze heterogeneous data streams, predicting failure becomes an achievable task. In this article: first, we propose a data mining strategy to deal with heterogeneous streams of data to predict failures in the production process; second, we aim to build a novel predictive manufacturing analytics model that employs a big data approach to predicting product failures; third, we illustrate the issue of high dimensionality, along with statistically redundant information; and, finally, our proposed method will be compared against the well-known classification methods (SVM, K-nearest neighbor, artificial neural networks). The results from real data show that our predictive manufacturing analytics approach, using genetic algorithms and Voronoi tessellations, is capable of predicting product failure with reasonable accuracy. The potential application of this method contributes to accurately predicting product failures, which would enable manufacturers to reduce production costs without compromising product quality.",
author = "Khan, {Abdul Rauf} and Henrik Schi{\o}ler and Murat Kulahci and Mohamed Zaki and Rasmussen, {Peter Westermann}",
year = "2019",
language = "English",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Pergamon Press",

}

Predictive Manufacturing: A Classification Strategy to Predict Product Failures. / Khan, Abdul Rauf; Schiøler, Henrik; Kulahci, Murat; Zaki, Mohamed ; Rasmussen, Peter Westermann.

I: Expert Systems with Applications, 2019.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - Predictive Manufacturing: A Classification Strategy to Predict Product Failures

AU - Khan, Abdul Rauf

AU - Schiøler, Henrik

AU - Kulahci, Murat

AU - Zaki, Mohamed

AU - Rasmussen, Peter Westermann

PY - 2019

Y1 - 2019

N2 - Predicting failures can be considered a meaningful insight for the optimal planning of an industrial manufacturing process. In this era of advanced sensor technologies, when the collection of data from each step of the manufacturing process is common practice and advanced analytical skills enable us to efficiently analyze heterogeneous data streams, predicting failure becomes an achievable task. In this article: first, we propose a data mining strategy to deal with heterogeneous streams of data to predict failures in the production process; second, we aim to build a novel predictive manufacturing analytics model that employs a big data approach to predicting product failures; third, we illustrate the issue of high dimensionality, along with statistically redundant information; and, finally, our proposed method will be compared against the well-known classification methods (SVM, K-nearest neighbor, artificial neural networks). The results from real data show that our predictive manufacturing analytics approach, using genetic algorithms and Voronoi tessellations, is capable of predicting product failure with reasonable accuracy. The potential application of this method contributes to accurately predicting product failures, which would enable manufacturers to reduce production costs without compromising product quality.

AB - Predicting failures can be considered a meaningful insight for the optimal planning of an industrial manufacturing process. In this era of advanced sensor technologies, when the collection of data from each step of the manufacturing process is common practice and advanced analytical skills enable us to efficiently analyze heterogeneous data streams, predicting failure becomes an achievable task. In this article: first, we propose a data mining strategy to deal with heterogeneous streams of data to predict failures in the production process; second, we aim to build a novel predictive manufacturing analytics model that employs a big data approach to predicting product failures; third, we illustrate the issue of high dimensionality, along with statistically redundant information; and, finally, our proposed method will be compared against the well-known classification methods (SVM, K-nearest neighbor, artificial neural networks). The results from real data show that our predictive manufacturing analytics approach, using genetic algorithms and Voronoi tessellations, is capable of predicting product failure with reasonable accuracy. The potential application of this method contributes to accurately predicting product failures, which would enable manufacturers to reduce production costs without compromising product quality.

M3 - Journal article

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -