Non-destructive Testing of Fusion Joints of Polyethylene Piping by Neuro-Wavelet Method

In this paper a new combined algorithm is presented considering neural network, digital image processing and mathematical morphology techniques for improving the quality of extracted images from NDT evaluations. The demand of polyethylene (PE) pipeline is increased for gas energy transportation and Electro-fusion (EF) joining is an essential method to build PE pipeline. Usually, EF joints are considered as weak points for leakage. The main goal is to present a practical method on Non-destructive Testing (NDT) testing of fusion joints in polyethylene piping using ultrasonic image processing technique. In theproposed technique all extracted information from digital image processor and wavelet transform is used by ANN for more evaluation. The simulations are done using MATLAB platform. Obtained results show that the algorithms developed and applied to ultrasonic signals are highly reliable and precise for quality of NDT testing and monitoring.

Keywords:

ANN , Digital image processing , Non-Destructive testing , Ultrasonic Technique , Wavelet transform