Year: 2025
Type: article
Abstract: For many years, unplanned equipment downtime has wreaked havoc on productivity and is an expensive way to run an operational business; yet when we look at the manufacturing of today, virtually all industries are impacted. However, conventional maintenance approaches, like reactive and preventive, do not provide an effective solution for tackling these issues. Through predictive maintenance, it is possible to anticipate equipment failures as well as optimize maintenance schedules. This study will explore the integration of predictive maintenance capabilities within the QAD Enterprise Resource Planning (ERP) system, using machine learning algorithms to predict equipment failures. Our approach helps reduce unnecessary downtime and maximizes overall equipment effectiveness using real-time data from such Internet of Things (IoT) sensors and advanced predictive analytics. The methodology includes the collection of data from IoTs, data pre-processing, feature engineering, and employing Machine Learning models for predictive maintenance. The result of these key findings is that this predicts a substantial decrease in unplanned downtime and maintenance costs, which validates the ability to include predictive maintenance in QAD ERP. Finally, the study concludes by demonstrating the potential to create more resilient and efficient manufacturing operations by combining machine learning-powered predictive maintenance with enterprise resource planning (ERP) systems.
Authors: Ravi Jaiswal, Manisha Jaiswal
Language: English
Subfield: Safety, Risk, Reliability and Quality
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4409425849