The project centered on the exploration and development of an innovative Adaptive Weighted Signal Preprocessing Technique (AWSPT)-based Sparsity Measure (SMs). The principal intention was to refine Machine Health Monitoring (MHM) practices by enhancing the efficiency and effectiveness of early fault detection systems in rotating machinery.

(1)   The first objective was to develop an AWSPT-based SMs resistant to impulse noise, providing a sturdy foundation for fault detection.

(2)   The second aim was to facilitate early detection of faults, thereby preventing extensive machine damage.

(3)   The third objective was to illustrate a monotonic degradation trend, providing a robust and reliable degradation assessment for preventative maintenance.

The project culminated in a successful development of the AWSPT-based SMs, showcasing impressive resistance to impulse noise and capacity for early fault detection. The user-friendly application was also created for practical data visualization and automatic realization of MHM, which significantly aids in maintenance decision-making. This breakthrough not only advances the field of MHM but also sets the stage for potential financial benefits across industries heavily reliant on machine maintenance efficiency.