MSc in Sound and Vibration: Engine Diagnostic

Project Title

Wireless HEV Engine Diagnostics Using Z-Freq Machine Learning-based Signal Analysis


Profesor Madya Ts Dr Azma Putra

Faculty of Mechanical Engineering, Universiti Teknikal Malaysia Melaka


Ts Nor Azazi bin Ngatiman

Faculty of Mechanical and Manufacturing Engineering Technology, Universiti Teknikal Malaysia Melaka



Detecting early symptoms of engine failures, such as spark plug misfire, valve clearance, and valve crack in a Hybrid Electric Vehicle (HEV) is a crucial phase in an engine management system to prevent poor driving performance and experience. The current engine management system is known to be unable to evaluate the performance of each cylinder operation and to predict various faults in internal combustion engine faulty condition monitoring. In consequence, this affects the whole hybrid monitoring system, especially during charging and cruising. Furthermore, vibration signal data transmission through wires provides difficulties for an area with limited space and contribute to safety issue to the observer. 

This research proposes a wireless technique of diagnostics for HEV engine using a state of the art statistical-based method called Z- Freq. The engine faulties will be controlled and vibration or acoustic signals of the engine will be measured using piezo-based sensors and accelerometers (to measure vibration amplitude), micro-fiber composite sensors (to measure dynamic strain) and acoustic microphones (to measure sound pressure level). All these data will then be analysed by utilising the Z-Freq with the aid of a machine learning technique as a validation tool.

A mathematical correlation is expected to be found between all the measured signals and the calculated coefficient value obtained from the Z-Freq, which provides the relation between the data from the engine and these will generate identical patterns depending on the engine faults. This technique can be useful for engineers to conveniently monitor the ‘health’ of the hybrid engine based on the pattern generated by the Z-Freq and the proposed technique can become a prediction tool for the wireless engine fault monitoring.


  1. Malaysian or Non-Malaysian
  2. Bachelor Degree in Mechanical Engineering or related field
  3. CGPA > 3.0
  4. Good writing & speaking in English
  5. Highly motivated and hard working
  6. Must be registered as MSc student in UTeM (once agreed to be involved in the project)


Monthly allowance up to RM1800

If you are interested, please fill in the FORM here.