A Prediction Model for Fault Detection in Molding Process Based On Logistic Regression Technique
Bildiriler > Tam Metin Bildiri · 2019
Yazarlar: İnanç KABASAKAL, Fatma DEMİRCAN KESKİN, Aydın KOÇAK, Haluk SOYUER
2019 International Symposium for Production Research (ISPR 2019), Avusturya, Viyana, Uluslararası, Sözlü Sunum, Tam Metin Bildiri, 2019-2019, Scopus, ss 351-360
DOI: 10.1007/978-3-030-31343-2_31
Özet
<p>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.</p>