2026_Improving Accuracy of Equipment Reliability Prediction for Preventive Maintenance Activities in Cmms Framework Using Predictive Model
| Format: | General Document |
|---|
| _version_ | 1860798361550979072 |
|---|---|
| building | INTELEK Repository |
| collection | Online Access |
| collectionurl | https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection8802 |
| copyright | Copyright©PWB2026 |
| country | Malaysia |
| date | 2025-01-28 |
| format | General Document |
| id | 17462 |
| institution | UniSZA |
| originalfilename | 17462_b36814bfe700999.pdf |
| person | Zuriana Ibrahim |
| recordtype | oai_dc |
| resourceurl | https://intelek.unisza.edu.my/intelek/pages/view.php?ref=17462 |
| sourcemedia | Server storage Scanned document |
| spelling | 17462 https://intelek.unisza.edu.my/intelek/pages/view.php?ref=17462 https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection8802 General Document Malaysia Library Staff (Top Management) Library Staff (Management) Library Staff (Support) Terengganu Faculty of Informatics & Computing English application/pdf 1.6 152 Public Access Server storage Scanned document Universiti Sultan Zainal Abidin Universiti Sultan Zainal Abidin Machine Learning Dissertations, Academic Adobe PDF Library 11.0 Predictive Modeling Manufacturing Industry Predictive Analytics 2025-01-28 Copyright©PWB2026 Thesis Zuriana Ibrahim Equipment Reliability Preventive Maintenance Computerized Maintenance Management System (CMMS) Predictive Maintenance Reliability Prediction Supervised Learning Maintenance Management Knowledge Discovery in Databases (KDD) Feature Selection Reliability (Engineering) Machine Learning Industrial Engineering Manufacturing Processes Data Mining Decision Support Systems 2026_Improving Accuracy of Equipment Reliability Prediction for Preventive Maintenance Activities in Cmms Framework Using Predictive Model Introduction: In the manufacturing industry, predicting production downtime due to equipment failures is challenging. Using the computerized maintenance management system (CMMS) framework in predictive maintenance (PdM), equipment reliability can be assessed. However, its implementation requires a complex infrastructure, a high level of skill, significant investment, and cultural change. Consequently, preventive maintenance (PM) remains prevalent, but it faces challenges in measuring equipment reliability and collecting accurate data due to manual processes. Thus, there is a need to automate data collection and predict equipment reliability by using a machine learning approach. The objective of this study is to enhance the CMMS framework for PM by incorporating predictive analytics capabilities. It intends to propose a prediction model for equipment reliability during PM using the CMMS database. The study also aims to assess the efficacy of the proposed model by analysing the collected data using supervised learning algorithms. Methodology: This research follows the Knowledge Discovery in Database (KDD) methodology, incorporating problem understanding, data selection, data preprocessing, transformation and reduction, data mining, and evaluation. The dataset was collected from a printed circuit board (PCB) assembly manufacturer in North Malaysia, focusing on the Aquos Hydro Cleaner (AHC) machine. The proposed CMMS framework utilizes equipment information, maintenance activities, and performance indicators such as PlanUptime, PlanDowntime, UnplanDowntime, ActualUptime, ActualDowntime, ActualRunHours, ActualMTBF, EquipmentStatus, and WorkOrderStatus. The predictive model performance was evaluated using metrics that included the correlation coefficient (r) and mean absolute error (MAE) to indicate the accuracy of the model. Results: The evaluation results show that the predictive model training data using the Regression by Discretization, Additive Regression, Linear Regression, Random Forest, and Decision Table algorithms through the WEKA application showed high accuracy, with mean absolute error (MAE) = 0 and r = 1 after selecting relevant features compared to all features. Conclusions: The success highlights the potential benefits of using the CMMS framework to extract reliable data for equipment maintenance activities in the manufacturing industry. Furthermore, the use of machine learning techniques can be effectively applied for the predictive analysis of equipment reliability, despite the adoption of PM strategies in the manufacturing industry. uuid:7ec6cefc-6b0e-4073-bb4f-90805038bcfd 17462_b36814bfe700999.pdf |
| spellingShingle | 2026_Improving Accuracy of Equipment Reliability Prediction for Preventive Maintenance Activities in Cmms Framework Using Predictive Model |
| state | Terengganu |
| subject | Dissertations, Academic Reliability (Engineering) Machine Learning Industrial Engineering Manufacturing Processes Data Mining Decision Support Systems |
| summary | Introduction: In the manufacturing industry, predicting production downtime due to equipment failures is challenging. Using the computerized maintenance management system (CMMS) framework in predictive maintenance (PdM), equipment reliability can be assessed. However, its implementation requires a complex infrastructure, a high level of skill, significant investment, and cultural change. Consequently, preventive maintenance (PM) remains prevalent, but it faces challenges in measuring equipment reliability and collecting accurate data due to manual processes. Thus, there is a need to automate data collection and predict equipment reliability by using a machine learning approach. The objective of this study is to enhance the CMMS framework for PM by incorporating predictive analytics capabilities. It intends to propose a prediction model for equipment reliability during PM using the CMMS database. The study also aims to assess the efficacy of the proposed model by analysing the collected data using supervised learning algorithms. Methodology: This research follows the Knowledge Discovery in Database (KDD) methodology, incorporating problem understanding, data selection, data preprocessing, transformation and reduction, data mining, and evaluation. The dataset was collected from a printed circuit board (PCB) assembly manufacturer in North Malaysia, focusing on the Aquos Hydro Cleaner (AHC) machine. The proposed CMMS framework utilizes equipment information, maintenance activities, and performance indicators such as PlanUptime, PlanDowntime, UnplanDowntime, ActualUptime, ActualDowntime, ActualRunHours, ActualMTBF, EquipmentStatus, and WorkOrderStatus. The predictive model performance was evaluated using metrics that included the correlation coefficient (r) and mean absolute error (MAE) to indicate the accuracy of the model. Results: The evaluation results show that the predictive model training data using the Regression by Discretization, Additive Regression, Linear Regression, Random Forest, and Decision Table algorithms through the WEKA application showed high accuracy, with mean absolute error (MAE) = 0 and r = 1 after selecting relevant features compared to all features. Conclusions: The success highlights the potential benefits of using the CMMS framework to extract reliable data for equipment maintenance activities in the manufacturing industry. Furthermore, the use of machine learning techniques can be effectively applied for the predictive analysis of equipment reliability, despite the adoption of PM strategies in the manufacturing industry. |
| title | 2026_Improving Accuracy of Equipment Reliability Prediction for Preventive Maintenance Activities in Cmms Framework Using Predictive Model |
| title_full | 2026_Improving Accuracy of Equipment Reliability Prediction for Preventive Maintenance Activities in Cmms Framework Using Predictive Model |
| title_fullStr | 2026_Improving Accuracy of Equipment Reliability Prediction for Preventive Maintenance Activities in Cmms Framework Using Predictive Model |
| title_full_unstemmed | 2026_Improving Accuracy of Equipment Reliability Prediction for Preventive Maintenance Activities in Cmms Framework Using Predictive Model |
| title_short | 2026_Improving Accuracy of Equipment Reliability Prediction for Preventive Maintenance Activities in Cmms Framework Using Predictive Model |
| title_sort | 2026_improving accuracy of equipment reliability prediction for preventive maintenance activities in cmms framework using predictive model |