Desalegn Wogaso Wolla is a mechanical engineer whose research focuses on the development of predictive, maintainable, and scalable digital twin framework leveraging machine learning algorithms for predictive maintenance of manufacturing equipment: a case study of a rotary system. The manufacturing sector has been facing number of challenges such as use of outdated technologies, limited access to skilled labour, and inefficient processes hindering their competitiveness. They have been struggling with poor quality and productivity due to lack of tools and practices to analyse and detect early failure of equipment.
Among the manufacturing equipment, rotary systems, including motors, pumps, and turbines, are ubiquitous in manufacturing. Their reliability directly impacts productivity and operational costs. Imbalance in rotary systems is a significant issue that can lead to various operational problems, including increased wear, vibration, and potential failure of the machinery. Most of manufacturing industries rely on traditional maintenance practices that involve labour-intensive approach, which are prone to human error, and lack precision and reliability required in modern manufacturing. These maintenance practices for addressing imbalance in rotary systems typically involve scheduled inspections and reactive maintenance strategies. These practices aim to ensure the reliability and efficiency of equipment but may not always effectively prevent issues related to imbalance. It often relies on scheduled maintenance routines, where equipment is inspected and serviced at predetermined intervals to ensure operational reliability. Over all, conventional maintenance practices often lead to unexpected downtimes and increased costs. A digital twin framework that incorporates machine learning algorithms is expected to mitigate these issues by predicting failures and scheduling maintenance proactively. Digital twins leveraging ML algorithm allow for real-time monitoring, performance optimization, and predictive maintenance of equipment. In rotary systems, the proposed research aims to significantly enhance predictive capabilities for identifying and mitigating imbalance issues.