Use this URL to cite or link to this record in EThOS:
Title: Application of smart classification techniques to non-destructive testing of composites
Author: Iskandarani, M. Z.
ISNI:       0000 0001 3587 294X
Awarding Body: University of Warwick
Current Institution: University of Warwick
Date of Award: 1995
Availability of Full Text:
Access from EThOS:
Access from Institution:
Composites manufactured for applications in the automotive industry were non-destructively tested to determine damage using the following techniques: (1) Low frequency tapping. (2) High frequency (C-Scan). (3) Visual imaging. (4) Low and high temperature pulse video thermography. Various levels of impact energy were applied to the following types of composites (I) RIM: Reaction injection moulded. (II) Woven Glass. (III) GMT: Glass mat thermoplastic. Some interesting results were obtained which could be explained through analytical and numerical modelling. These results were analyzed through developments of the following algorithms: (a) A novel approach to damage detection using wavelength variation and sequence grouping software. (b) Correlation of the various NDT techniques through one mathematical equation and software. (c) The introduction of the uniformity factor concept and software to account for variations among samples quality in relation to experimental results. (d) The development of smart classification system together with standard neural network algorithms for prediction and classification. The objectives of this research were all achieved.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available
Keywords: TA Engineering (General). Civil engineering (General)