A Prediction Model for Fault Detection in Molding Process Based on Logistic Regression Technique
Küçük Resim Yok
Tarih
2020
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Springer Science and Business Media Deutschland GmbH
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Industry 4.0 is often described as a wave of transformation that enforces the digitalization of processes to create integrated and autonomous systems. In this regard, the collection of process data is a necessity to analyze data with advanced techniques for various purposes. Statistical techniques in machine learning might provide solutions for fault detection and other tasks in manufacturing processes. In our study, a learning model is proposed for a fault prediction task with the use of Logistic Regression. The data used for the analysis involve measurements from sequential processes carried out in a large-scale wheel rim manufacturer. The pre-processing and analysis of process data was introduced along with a case study. Moreover, findings of the model were presented and the potential use of the model will be discussed. © 2020, Springer Nature Switzerland AG.
Açıklama
19th International Symposium for Production Research, ISPR 2019 -- 28 August 2019 through 30 August 2019 -- -- 233539
Anahtar Kelimeler
Binary classification, Fault prediction, Industry 4.0, Logistic regression, Machine learning
Kaynak
Lecture Notes in Mechanical Engineering
WoS Q Değeri
Scopus Q Değeri
Q4
