Industrial Laser Welding Defect Detection and Image Defect Recognition Based on Deep Learning Model Developed

Abstract

Aiming at the problem of the poor robustness of existing methods to deal with diverse industrial weld image data, we collected a series of asymmetric laser weld images in the largest laser equipment workshop in Asia, and studied these data based on an industrial image processing algorithm and deep learning algorithm. The median filter was used to remove the noises in weld images. The image enhancement technique was adopted to increase the image contrast in different areas. The deep convolutional neural network (CNN) was employed for feature extraction; the activation function and the adaptive pooling approach were improved. Transfer Learning (TL) was introduced for defect detection and image classification on the dataset. Finally, a deep learning-based model was constructed for weld defect detection and image recognition. Specific instance datasets verified the model’s performance. The results demonstrate that this model can accurately identify weld defects and eliminate the complexity of manually extracting features, reaching a recognition accuracy of 98.75%. Hence, the reliability and automation of detection and recognition are improved significantly. The research results can provide a theoretical and practical reference for the defect detection of sheet metal laser welding and the development of the industrial laser manufacturing industry.

An Implementation of Trust Chain Framework with Hierarchical Content Identifier Mechanism by Using Blockchain Technology

“…In the other words, MS still pays his full efforts to optimize production and product transactions as a broad manufacturing concept toward Industry 4.0 by integrating advanced manufacturing with information engineering [18]. With advancements in information engineering, these cutting-edge models might likely be employed to address the shortcomings of the present production model [19][20][21]. Furthermore, with the emergence of the IIoT concept based on small intelligent sensors, the future production line is supported by heterogeneous sensory modules that functionally collaborate to support the manufacturing process [22].…”

A Weld Surface Defect Recognition Method Based on Improved MobileNetV2 Algorithm

“…Aims to make the best use of unannotated image data, Dong et al [25] proposed a novel unsupervised local deep feature learning method based on image segmentation, built a network that can extract useful features from an image, and demonstrated the approach on two aerospace weld inspection tasks. Aiming at the problem of the poor robustness of existing methods to deal with diverse industrial weld image data, Deng et al [26] collected a series of asymmetric laser weld images for study. The median filter was used to remove the noises, the deep CNN was employed for feature extraction, and the activation function and the adaptive pooling approach were improved.…”

Image Data-Centric Visual Feature Selection on Roll-to-Roll Slot-Die Coating Systems for Edge Wave Coating Defect Detection

“…Studies focusing on vision image-based defect detection methods have primarily focused on the structure of deep neural networks to facilitate efficient learning [ 25 , 26 , 27 , 28 , 29 ]. Many of these studies have proposed modifications to learning algorithms or structural layers within neural networks to achieve high-accuracy detection [ 30 , 31 , 32 , 33 , 34 ].…”