International Journal of Computer Science and Network Solutions (IJCSNS)
The most important parts of drilling machines are drilling pipes. The emergence of various defects in these pipes during working times due to environmental conditions, heat, ground pressures, abrasion and erosion in adjacent of very hard rock's is inevitable. Therefore defect detection and testing of these pipes before making problems in drilling oil and gas wells is an important matter. By using a combination of machine vision techniques and artificial neural networks Learning Vector Quantization-Neural Network (LVQ-NN) for defect classification, this paper examines variations of drilling pipe failures and with regard to different criteria in terms of processing speed and accuracy, it has proceeded with comparison with other Feed Forward Back Propagation-Neural Networks (FFBP-NN).