Machine Learning Approaches for Analyzing Computerized Maintenance Management System Data Mining

Mohd Shukri Abdul Wahab Abdul Wahab; Syed Tarmizi Syed Shazali; Noor Hisyam Noor Mohamed; Abdul Rani Achmed Abdullah; Muhamad Fadzli Ashari; Mohd Syahmi  Jamaludin

Authors

Mohd Shukri Abdul Wahab Abdul Wahab Faculty of Engineering, Universiti Malaysia Sarawak,Sarawak, Malaysia
Syed Tarmizi Syed Shazali Faculty of Engineering, Universiti Malaysia Sarawak,Sarawak, Malaysia
Noor Hisyam Noor Mohamed Faculty of Engineering, Universiti Malaysia Sarawak,Sarawak, Malaysia
Abdul Rani Achmed Abdullah CWorks Technologies Sdn Bhd, Kinrara Straits One, Bandar Kinrara, Selangor. Malaysia
Muhamad Fadzli Ashari Faculty of Engineering, Universiti Malaysia Sarawak,Sarawak, Malaysia
Mohd Syahmi Jamaludin Faculty of Engineering, Universiti Malaysia Sarawak,Sarawak, Malaysia

Keywords:

Maintenance management, Computerized Maintenance Management System (CMMS), machine learning, data mining, unsupervised learning, K-Means clustering

Abstract

In the realm of maintenance management, the growing complexity and volume of Computerized Maintenance Management System (CMMS) data necessitate innovative approaches. Traditional methods fail to address contemporary CMMS datasets, compelling the adoption of advanced methodologies. This research focuses on leveraging machine learning approaches to comprehensively analyse CMMS data mining, enhancing predictive capabilities and interpretability. The study's objectives encompass addressing limitations in traditional data mining and employing unsupervised learning methods by using clustering techniques through K-Means. The results reveal heightened accuracy in predicting maintenance needs, improved interpretability, and identifying involved relationships within extensive CMMS datasets. This research contributes by demonstrating practical applications, offering insights for organisations enhancing CMMS analytics, and proposing future studies to advance machine learning integration further.