Study on ultrasonic flaw identification based on complex wavelet transform and support vector machine;

According to the classic indeterminate problem of flaw detection,a new approach of flaw identification was presented in this paper based on complex wavelet transform and Bayesian classifier.

The defect identification and positioning methods were discussed.

A novel biological optimization algorithm,particle swarm optimization(PSO) algorithm,is applied in defect identification in the paper.

This paper focus on solid propellant of rocket engine defects characteristics automatic extraction and identification technology, which is helpful for propellant automatic ultrasonic NDT and automatic defect identification.

In order to realize the flaw recognition,a special sensor which is composed of a rectangle exciting coil and a foursquare is designed to excite and induce the change of magnetic field,and a method based on the orthogonal LIA is applied to measure the mV-level change of the weak-induced voltage signal.

Study on method for flaw identification based on support vector machine;

Study to the Flaw Identification of Ultrasonic Testing based on Optimal Support Vector Machines;

New material, new method and new theory are the basis of the non-destructive testing(NDT)development, and credible flaw identification, quantitive analysis and non- destructiveevaluation(NDE) are the main research of NDT.

Workpiece defect recognition methods based on industrial CT;

Method of defect recognition in solid motor CT testing

According to the characters and requirements of the nondestructive steel radial tire detection, an X-ray inspection and defect recognition system for all-steel radial tire is designed.