Predictive maintenance (PdM) is implemented to efficiently manage maintenance schedules of machinery and equipment in manufacturing by predicting potential faults with advanced technologies such as sensors, data analysis, and machine learning algorithms. This paper introduces a study of different methodologies for automatically classifying the failures in PdM data. We first present the performance evaluation of fault classification performed by shallow machine learning (SML) methods such as Decision Trees, Support Vector Machines, k-Nearest Neighbors, and one-dimensional deep learning (DL) techniques like 1D-LeNet, 1D-AlexNet, and 1D-VGG16. Then, we apply normalization, which is a scaling technique in which features are shifted and rescaled in the dataset. We reapply classification algorithms to the normalized dataset and present the performance tables in comparison with the first results we obtained. Moreover, in contrast to existing studies in the literature, we generate balanced dataset groups by randomly selecting normal data and all faulty data for all fault types from the original dataset. The dataset groups are generated with 100 different repetitions, recording performance scores for each one and presenting the maximum scores. All methods utilized in the study are similarly employed on these groups. From these scores, the use of 1D-LeNet deep learning classifiers and feature normalization resulted in achieving the highest overall accuracy and F1-score performance of 98.50% and 98.32%, respectively. As a result, the goal of this study was to develop an efficient approach for automatic fault classification, leveraging data balance, and additionally, to provide an analysis of one-dimensional deep learning and shallow machine learning-based classification methods. In light of the experimentation and comparative analysis, this study successfully achieves its stated goal by demonstrating that one-dimensional deep learning and data balance collectively emerge as the optimal approach, offering good prediction accuracy.

Using smart sensors and data analytics tools, predictive maintenance (PdM) aims to reduce downtime by forecasting potential faults; however, accurately distinguishing between failure and normal conditions remains a significant challenge. To address this challenge, we propose a fault classification system that transforms 1D PdM sensor signals into 2D images using a novel Predictive Maintenance Image Transformation (PdM-IT) technique, followed by feature extraction with pre-trained convolutional neural networks (CNNs). The extracted features are then combined across all CNN models. We additionally optimize the combined feature set using three nature-inspired optimization algorithms, including Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), and Grey Wolf Optimization (GWO), and then evaluate four different classifier such as Support Vector Machines (SVM), k-Nearest Neighbors (k-NN), Naive Bayes (NB), and Decision Trees (DT) on the obtained data using cross-validation. In our experimental evaluation, the best-performing model, SVM with features selected via ACO, achieved 98.22% accuracy, 98.39% F1-score, 98.51% precision, and 98.26% recall. These results show the effectiveness of the proposed hybrid image-based fault classification approach and its potential to support more reliable fault diagnosis and operational planning in PdM systems.

Makine öğrenimi ve nesnelerin internetindeki gelişmeler, kestirimci bakımı sanayi sistemleri için vazgeçilmez bir bileşen hâline getirmiştir. Ancak bu yaklaşımların başarımı, veri işleme süreçlerinin etkinliğine doğrudan bağlıdır. Özellikle veri dengesizliği, öznitelik seçimi ve normalizasyon teknikleri, model performansını belirleyen temel unsurlar arasındadır. Bu çalışmada, AI4I 2020 veri seti kullanılarak makine arızalarının ve dört farklı arıza modunun sınıflandırılması hedeflenmiştir. Karar Ağaçları (DT), Destek Vektör Makineleri (SVM) ve k-En Yakın Komşu (k-NN) gibi sığ makine öğrenmesi algoritmalarının performansları kapsamlı biçimde analiz edilmiştir. Veri dengesizliğini gidermek amacıyla rastgele seçim ve SMOTE yöntemleri uygulanmış, SMOTE’un daha başarılı sonuçlar sunduğu görülmüştür. Ayrıca min–max ve z-skor normalizasyon teknikleri karşılaştırılmış ve z-skor normalizasyonunun sınıflandırma başarımını artırdığı belirlenmiştir. Arıza modları ikili sınıflara ayrılarak en uygun öznitelik seti oluşturulmuş, ardından geriye doğru eleme yöntemiyle beş öznitelik kademeli olarak çıkarılarak performansa etkileri incelenmiştir. Sonuçlar, önerilen yaklaşımın sınıflandırma performansını anlamlı biçimde iyileştirdiğini göstermektedir. Özellikle k-NN algoritması, SMOTE ile dengelenmiş veri setinde %99,2 doğruluk oranı elde ederek en yüksek başarımı sağlamıştır. Bu çalışma, kestirimci bakım uygulamalarının güvenilirliğini artırmaya yönelik özgün bir katkı sunmaktadır.