Ultrasonic sensor based defect detection and characterisation of ceramics

• Identifying defects in ceramic components using ultrasonic sensing, neural network and DWT.
• Neural network approach to defect classification is very effective.
• Results are promising for developing an online quality control system for NDT of ceramic tiles.
• ANN has been chosen over other classifiers as it contributes to a fast and user friendly system.
• This research assists industrial operators by reducing their effort and time spent in classifying the defect signals.

Ceramic tiles, used in body armour systems, are currently inspected visually offline using an X-ray technique that is both time consuming and very expensive. The aim of this research is to develop a methodology to detect, locate and classify various manufacturing defects in Reaction Sintered Silicon Carbide (RSSC) ceramic tiles, using an ultrasonic sensing technique. Defects such as free silicon, un-sintered silicon carbide material and conventional porosity are often difficult to detect using conventional X-radiography. An alternative inspection system was developed to detect defects in ceramic components using an Artificial Neural Network (ANN) based signal processing technique. The inspection methodology proposed focuses on pre-processing of signals, de-noising, wavelet decomposition, feature extraction and post-processing of the signals for classification purposes. This research contributes to developing an on-line inspection system that would be far more cost effective than present methods and, moreover, assist manufacturers in checking the location of high density areas, defects and enable real time quality control, including the implementation of accept/reject criteria.