Edzel Lapira
Papers
2
Total Citations
104
H-Index
2
About
Edzel Lapira is a leading researcher in prognostics and health management (PHM), with a core focus on fault detection, novelty detection, and machinery condition monitoring. His work addresses the critical challenge of identifying equipment degradation before failures occur, a cornerstone of modern industrial reliability. Lapira’s most influential contribution is his 2012 paper on a modified support vector data description (SVDD) approach for novelty detection in machinery components, which has garnered 67 citations for its robust method of identifying anomalous behavior in complex systems. He further advanced the field with his 2012 study on fault detection in networks of similar machines using clustering, cited 37 times, demonstrating how comparative analysis across multiple units can enhance diagnostic accuracy. By developing algorithms that distinguish normal wear from incipient faults, Lapira has provided practical tools for predictive maintenance, reducing downtime and costs. His work is essential reading for engineers and researchers seeking to implement intelligent, data-driven health management in industrial applications, bridging the gap between theoretical machine learning and real-world asset monitoring.
Research Focus
Key Achievements
Top Papers
- 1
- 2Fault detection in a network of similar machines using clustering approach37 citations · 2012