A master's thesis at the University of Basra examines the diagnosis of rotating machinery faults based on vibration signals.

A master's thesis at the University of Basra examines the diagnosis of rotating machinery faults based on vibration signals.

A master's thesis at the University of Basra's College of Engineering investigated the diagnosis of rotating machinery faults based on vibration and sound signals using CNN deep learning technology.

The thesis, submitted by student Hussein Nasser Jaber, aims to develop an effective and reliable diagnostic methodology for the early detection of bearing failures. 

The research focuses on analyzing two types of signals extracted from rotating machines, acoustic emission (AE) and vibration signals.

The thesis consisted of four chapters, during which the student discussed the ability to detect defects in their early stages, which may lead to system-wide failures, causing increased maintenance costs and unplanned downtime.

Department of Media and Government Communication