The Impact of Machine Learning-Based Predictive Maintenance on Downtime in Smart Manufacturing Systems in Bangladesh

Abstract

Purpose: The purpose of this article was to evaluate the impact of machine learning-based predictive maintenance on downtime in smart manufacturing systems in Bangladesh.

Methodology: This study adopted a desk methodology. A desk study research design is commonly known as secondary data collection. This is basically collecting data from existing resources preferably because of its low cost advantage as compared to a field research. Our current study looked into already published studies and reports as the data was easily accessed through online journals and libraries.

Findings: ​ The study found that machine learning-based predictive maintenance cut unplanned downtime in Bangladesh smart factories by 30–40%. Predictive models achieved over 85% accuracy in forecasting failures, leading to higher production efficiency and lower maintenance costs. Overall, this approach proved highly effective for improving reliability in manufacturing systems.

Unique Contribution to Theory, Practice and Policy: Theory of constraints (TOC), sociotechnical systems theory & resource-based view (RBV) may be used to anchor future studies on the impact of machine learning-based predictive maintenance on downtime in smart manufacturing systems in Bangladesh. Manufacturing firms should prioritize pilot programs to validate machine learning predictive maintenance on critical assets before scaling across operations. Policymakers should create incentives such as tax credits or grants to encourage small- and medium-sized manufacturers to adopt predictive maintenance technologies, reducing barriers to entry caused by high initial costs.