Motor Operational Settings Prediction for Sustainable Manufacturing Facilities

Abstract

Preventive maintenance of rotating machinery, such as motors, is pivotal for cost reduction in manufacturing facilities. Condition-based maintenance is considered the driving force in the health management of industrial machinery, which necessitates the development of efficient, able-to-generalize, and reusable approaches to help manufacturing facilities identify operational conditions. This study proposes an approach for classifying the operational settings of motors based on vibration data. This was accomplished by first creating a merged class of weight distribution and speed percentage ranges to be classified. These two operational settings can be classified to address sustainable manufacturing concerns as they relate to the development of systematic maintenance plans. Ensemble learning was then used as the machine learning algorithm of choice for the classification task. It was found that ensemble learning is capable of producing reasonable classification accuracy results that are superior to those of single-model approaches. In addition, the testing size and window size of the segmented vibration signals have been identified to have a clear effect on classification accuracy that is considered consistent with the logical trend. The proposed approach addresses the need for manufacturing facilities to utilize efficient and accurate algorithms for cost-effective, and sustainable maintenance practices.

Keywords

• Classification
• ensemble learning
• motors
• sustainable manufacturing