Intelligent Small Sample Defect Detection of Water Walls in Power Plants Using Novel Deep Learning Integrating Deep Convolutional GAN

Abstract

Thermal power generation is one of main forms of the electricity generation in the world. However, power plants are often shut down due to boiler accidents caused by the damage of water walls. Therefore, a novel intelligent small sample defect detection method of water walls in power plants based on the deep learning integrating deep convolutional GAN (DCGAN) and seam carving algorithm is proposed. The proposed method uses the seam carving algorithm to solve the overfitting of the DCGAN for generating high-quality images. Then the intelligent small sample defect detection model is built by convolutional neural networks (CNNs). Finally, the proposed method is used in the defect detection of water walls in actual thermal power generation plants. Experimental results demonstrate that the proposed method can achieve the detection accuracy of 98.43%. which is higher than different GANs, different detection networks integrating different processes used and not used data expand methods.