A defect detection system of glass tube yarn based on machine vision

Abstract

Tube yarn is also called glass fiber spun yarn. Due to the excellent properties of glass fiber, various industrial products based on glass fiber are used in a variety of industries. As the most obvious factor affecting the quality of products, quality detection of glass fiber yarns is very important for companies. Due to traditional defect detection relies on the experience and subjective factors of workers, which makes many different views on the same defect. Some traditional methods limit the solution to specific types of defects and do not accurately detect various defects. In this paper, we propose a comprehensive defect detection system of tube yarn via combining machine vision and deep learning methods. In whole system, we inspect the weight through a weight sensor firstly. Then, we propose a multi-scale cross-fusion attention module to improve the MobileNetV2, and combine with machine vision image feature extraction method for hairiness detection. Finally, the modified MobileNetV2 network is used as the backbone of YOLOX network, making the YOLOX is lighter and achieve more efficiently stain detection of tube yarn. Then, the detection results are used to determine whether the glass tube yarn has passed. In addition, we establish an effective and sufficient amount of tube yarn defects dataset. The experimental results show that the proposed hairiness detection algorithm achieve 96% accuracy with 160+ FPS, and the surface stain detection algorithm achieve 0.89 mAP with 71+ FPS on the tube yarn dataset. The system is efficient, precise, and can be applied to actual production.

FLCNet: faster and lighter cross-scale feature aggregation network for lead bar surface defect detection

“…Ling et al [46] proposed an adaptive multi scale feature fusion algorithm to address the problem of significant scale variation in track sleeper crack targets. Bao et al [47] proposed an improved YOLOx algorithm with multi scale feature fusion. It effectively improves the detection accuracy of glass fiber tube sand by parallelly using three different kernels to perform convolution, followed by global average pooling and max pooling on each feature.…”

Light-Trans YOLO: A Lightweight Network Based on Transformer for Defect Detection of Industrial Lace Surface

“…In order to meet the requirements of practical industrial production, researchers have started to focus on more efficient and lightweight network models. Ma et al [16] proposed a lightweight aluminum strip defect detector based on YOLOV4, which could effectively simplify the parameters of the model and achieve accurate detection of aluminum strip defects. Zhao et al [17] utilized embedded Ghost module instead of standard convolution and Transformer module was used to extract multi-head attention features, which realized the detection of digital ray images and further facilitated the industrial implementation of the model.…”

Pixel-level pruning deep supervision UNet++ for detecting fabric defects

“…These objective values well reflect the strand integrity and feature of the belt-forming of yarn, and are consistent with the subjective evaluation. Bao et al 21 proposed a comprehensive defect detection system of tube yarn by combining machine vision and deep learning methods. In the whole system, we inspect the weight through a weight sensor first.…”

“…Bao et al. 21 proposed a comprehensive defect detection system of tube yarn by combining machine vision and deep learning methods. In the whole system, we inspect the weight through a weight sensor first.…”