Impact of Feature Selection on the Performance of Classification Algorithms in Predicting Industrial Robot Failures

Fatma Günseli Yaşar Çıklaçandır; Serfiraz Abdullah Mumcu

Article Details

Impact of Feature Selection on the Performance of Classification Algorithms in Predicting Industrial Robot Failures

Authors:

Fatma Günseli Yaşar Çıklaçandır | Serfiraz Abdullah Mumcu

Publisher:

Dokuz Eylul University

Main Topics:

Endüstri Mühendisliği

Journal:

Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi Vol.27 Issue 81, pp.393-399

Document Type:

Article

Publication Date:

9/2025

Document Language:

English

Document ID (Org No.):

2001358738

pISSN:

1302-9304

Keywords:

Abstract:

 Industrial robots enhance manufacturing efficiency, productivity, and precision. However, failures can disrupt production lines, leading to losses and significant system impact. In this study, robot failures are predicted using the UR3 CobotOps dataset and the impact of feature selection on the performance of various classification algorithms in predicting two targets protective stops, and grip losses is explored. Initially, the baseline performance of classifiers without feature selection has been evaluated. Then, two different feature selection methods recursive feature elimination and chi-square are applied to select the top 10 features and reassess the classifiers performance. High classification success rates are obtained with Decision Tree and Random Forest after feature selection in this study, which tests five different classifiers Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and k-Nearest Neighbors in the classification stage. This paper provides valuable insights into the different applications of classifiers, contributing to the field of machine learning by identifying different feature selection techniques and their impacts on classification accuracy. According to the experimental tests, an accuracy rate of about 99 has been obtained when Random Forest is used. This success has been also achieved when Chi-Square is used for feature selection. This paper shows that this prediction can be achieved in a shorter time using feature selection.

 Industrial robots enhance manufacturing efficiency, productivity, and precision. However, failures can disrupt production lines, leading to losses and significant system impact. In this study, robot failures are predicted using the UR3 CobotOps dataset and the impact of feature selection on the performance of various classification algorithms in predicting two targets protective stops, and grip losses is explored. Initially, the baseline performance of classifiers without feature selection has been evaluated. Then, two different feature selection methods recursive feature elimination and chi-square are applied to select the top 10 features and reassess the classifiers performance. High classification success rates are obtained with Decision Tree and Random Forest after feature selection in this study, which tests five different classifiers Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and k-Nearest Neighbors in the classification stage. This paper provides valuable insights into the different applications of classifiers, contributing to the field of machine learning by identifying different feature selection techniques and their impacts on classification accuracy. According to the experimental tests, an accuracy rate of about 99 has been obtained when Random Forest is used. This success has been also achieved when Chi-Square is used for feature selection. This paper shows that this prediction can be achieved in a shorter time using feature selection.

 Industrial robots enhance manufacturing efficiency, productivity, and precision. However, failures can disrupt production lines, leading to losses and significant system impact. In this study, robot failures are predicted using the UR3 CobotOps dataset and the impact of feature selection on the performance of various classification algorithms in predicting two targets protective stops, and grip losses is explored. Initially, the baseline performance of classifiers without feature selection has been evaluated. Then, two different feature selection methods recursive feature elimination and chi-square are applied to select the top 10 features and reassess the classifiers performance. High classification success rates are obtained with Decision Tree and Random Forest after feature selection in this study, which tests five different classifiers Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and k-Nearest Neighbors in the classification stage. This paper provides valuable insights into the different applications of classifiers, contributing to the field of machine learning by identifying different feature selection techniques and their impacts on classification accuracy. According to the experimental tests, an accuracy rate of about 99 has been obtained when Random Forest is used. This success has been also achieved when Chi-Square is used for feature selection. This paper shows that this prediction can be achieved in a shorter time using feature selection.

 Endüstriyel robotlar üretim verimliliğini, üretkenliği ve hassasiyeti artırır. Ancak arızalar üretim hatlarını kesintiye uğratarak kayıplara ve önemli sistem etkilerine yol açabilir. Bu çalışmada, UR3 CobotOps veri seti kullanılarak robot arızaları tahmin edilmektedir. Özellik seçiminin, iki hedefi protective stops, and grip losses tahmin etmede çeşitli sınıflandırma algoritmalarının performansı üzerindeki etkisini araştırıyor. Başlangıçta öznitelik seçimi yapılmayan sınıflandırıcıların temel performansı değerlendirilmiştir. Daha sonra ilk 10 özniteliğin seçilmesi ve sınıflandırıcı performansının yeniden değerlendirilmesi için iki farklı öznitelik seçme yöntemi özyinelemeli öznitelik eleme ve Ki-Kare uygulanmıştır. Beş farklı sınıflandırıcının lojistik regresyon, karar ağacı, rastgele orman, destek vektör makinesi, ve k-en yakın komşu test edildiği bu çalışmada öznitelik seçimi sonrasında sınıflandırma aşamasında karar ağacı ve rastgele orman ile yüksek sınıflandırma başarıları elde edilmiştir. Bu makale, farklı öznitelik seçme tekniklerini ve bunların sınıflandırma doğruluğu üzerindeki etkilerini belirleyerek makine öğrenimi alanına katkıda bulunarak sınıflandırıcıların farklı uygulamalarına ilişkin değerli bilgiler sağlar. Yapılan deneyler, rastgele orman algoritmasının endüstriyel robot arızalarını 0,99a varan bir doğrulukla tahmin edebildiğini göstermektedir. Feature selection için Ki-Kare kullanıldığında da bu başarıya erişilmiştir. Bu araştırma sayesinde feature selection kullanılarak daha kısa sürede bu tahminin gerçekleştirilebileceği görülür.

Article Details

Impact of Feature Selection on the Performance of Classification Algorithms in Predicting Industrial Robot Failures

Authors:

Fatma Günseli Yaşar Çıklaçandır | Serfiraz Abdullah Mumcu

Publisher:

Dokuz Eylul University

Main Topics:

Endüstri Mühendisliği

Journal:

Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi Vol.27 Issue 81, pp.393-399

Document Type:

Article

Publication Date:

9/2025

Document Language:

English

Document ID (Org No.):

2001358738

pISSN:

1302-9304

Predictive Maintenance

Operational Efficiency

Feature Selection

Machine LearningKestirimci Bakım

Operasyonel Verimlilik

Öznitelik Seçimi

Makine Öğrenmesi

Issues

Article Details

Authors: Fatma Günseli Yaşar Çıklaçandır | Serfiraz Abdullah Mumcu

Publisher: Dokuz Eylul University

Main Topics: Endüstri Mühendisliği

Journal: Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi Vol.27 Issue 81, pp.393-399

Document Type: Article

Publication Date: 9/2025

Document Language: English

Document ID (Org No.): 2001358738

pISSN: 1302-9304

Issues

Authors:

Fatma Günseli Yaşar Çıklaçandır | Serfiraz Abdullah Mumcu

Publisher:

Dokuz Eylul University

Main Topics:

Endüstri Mühendisliği

Journal:

Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi Vol.27 Issue 81, pp.393-399

Document Type:

Article

Publication Date:

9/2025

Document Language:

English

Document ID (Org No.):

2001358738

pISSN:

1302-9304