The concept of Industry 4.0 aims fully digital and autonomous production. For manufacturing systems to work properly, their maintenance must be done correctly. However, while unnecessary maintenance causes waste of money and time, skipping necessary maintenance can also cause unexpected down times in production. Predictive maintenance (PdM) aims to predict and diagnose faults at an early stage and also the time remaining for future failures of equipment which might provide significant cost savings compared to traditional maintenance approaches. Today's sensor and data collection technologies have become more accessible and reliable which paved the way for manufacturers to continuously monitor their equipment, collect and store large volume of data in their production systems. Using this data with machine learning (ML) algorithms and analyzing the fingerprints of equipment faults can help making more informed decision regarding maintenance in manufacturing which might help increasing production quality and capacity. In our study, induction motors (IM) which are widely used in factories for different purposes and their failure scenarios are targeted. Triaxial vibration data collected from two similar induction motors under different operating conditions are examined. Various features of vibration data are extracted, scaled and labeled with a status information of the operation state. The obtained dataset is analyzed with six different ML algorithms. Performances are examined and compared against each other. In this study, we present our promising experimental results and experimentally show that the abnormal operating conditions of IMs can be successfully detected utilizing ML algorithms for a PdM application.

No abstract