Convolutional Neural Network Defect Detection Algorithm for Wire Bonding X-ray Images.

To address the challenges of complex backgrounds, small defect sizes, and diverse defect types in defect detection of wire bonding X-ray images, this paper proposes a convolutional-neural-network-based defect detection method called YOLO-CSS. This method designs a novel feature extraction network that effectively captures semantic features from different gradient information. It utilizes a self-adaptive weighted multi-scale feature fusion module called SMA which adaptively weights the contribution of detection results based on different scales of feature maps. Simultaneously, skip connections are employed at the bottleneck of the network to ensure the integrity of feature information. Experimental results demonstrate that on the wire bonding X-ray defect image dataset, the proposed algorithm achieves mAP 0.5 and mAP 0.5-0.95 values of 97.3% and 72.1%, respectively, surpassing the YOLO series algorithms. It also exhibits certain advantages in terms of model size and detection speed, effectively balancing detection accuracy and speed.

A High-Precision Multi-Beam Optical Measurement Method for Cylindrical Surface Profile.

To automatically measure the surface profile of a cylindrical workpiece, a high-precision multi-beam optical method is proposed in this paper. First, some successive images for the cylindrical workpiece's surface are acquired by a multi-beam angle sensor under different light directions. Then, the light directions are estimated based on the feature regions in the images to calculate surface normal vectors. Finally, according to the relationship of the surface normal vector and the vertical section of the workpiece's surface, a depth map is reconstructed to achieve the curvature surface, which can be employed to measure the curvature radius of the cylindrical workpiece's surface. Experimental results indicate that the proposed measurement method can achieve good measurement precision with a mean error of the curvature radius of a workpiece's surface of 0.89% at a reasonable speed of 10.226 s, which is superior to some existing methods.

ATNet: A Defect Detection Framework for X-ray Images of DIP Chip Lead Bonding.

In order to improve the production quality and qualification rate of chips, X-ray nondestructive imaging technology has been widely used in the detection of chip defects, which represents an important part of the quality inspection of products after packaging. However, the current traditional defect detection algorithm cannot meet the demands of high accuracy, fast speed, and real-time chip defect detection in industrial production. Therefore, this paper proposes a new multi-scale feature fusion module (ATSPPF) based on convolutional neural networks, which can more fully extract semantic information at different scales. In addition, based on this module, we design a deep learning model (ATNet) for detecting lead defects in chips. The experimental results show that at 8.2 giga floating point operations (GFLOPs) and 146 frames per second (FPS), mAP0.5 and mAP0.5-0.95 can achieve an average accuracy of 99.4% and 69.3%, respectively, while the detection speed is faster than the baseline yolov5s by nearly 50%.

A Lightweight Method for Detecting IC Wire Bonding Defects in X-ray Images.

Integrated circuit (IC) X-ray wire bonding image inspections are crucial for ensuring the quality of packaged products. However, detecting defects in IC chips can be challenging due to the slow defect detection speed and the high energy consumption of the available models. In this paper, we propose a new convolutional neural network (CNN)-based framework for detecting wire bonding defects in IC chip images. This framework incorporates a Spatial Convolution Attention (SCA) module to integrate multi-scale features and assign adaptive weights to each feature source. We also designed a lightweight network, called the Light and Mobile Network (LMNet), using the SCA module to enhance the framework's practicality in the industry. The experimental results demonstrate that the LMNet achieves a satisfactory balance between performance and consumption. Specifically, the network achieved a mean average precision (mAP50) of 99.2, with 1.5 giga floating-point operations (GFLOPs) and 108.7 frames per second (FPS), in wire bonding defect detection.

Strip Surface Defect Detection Algorithm Based on YOLOv5.

In order to improve the detection accuracy of the surface defect detection of industrial hot rolled strip steel, the advanced technology of deep learning is applied to the surface defect detection of strip steel. In this paper, we propose a framework for strip surface defect detection based on a convolutional neural network (CNN). In particular, we propose a novel multi-scale feature fusion module (ATPF) for integrating multi-scale features and adaptively assigning weights to each feature. This module can extract semantic information at different scales more fully. At the same time, based on this module, we build a deep learning network, CG-Net, that is suitable for strip surface defect detection. The test results showed that it achieved an average accuracy of 75.9 percent (mAP50) in 6.5 giga floating-point operation (GFLOPs) and 105 frames per second (FPS). The detection accuracy improved by 6.3% over the baseline YOLOv5s. Compared with YOLOv5s, the reference quantity and calculation amount were reduced by 67% and 59.5%, respectively. At the same time, we also verify that our model exhibits good generalization performance on the NEU-CLS dataset.

Surface Quality Control Strategy of Aspherical Mold Based on Screw Feed Polishing of Small Polishing Tool.

For small aspherical molds, it is difficult for the existing polishing method to take into account the correction of the surface error and the control of the uniformity of the surface roughness (SR) distribution, because the polishing tool is always larger than the small mold. Therefore, we used viscoelastic polyester fiber cloth to wrap the small steel ball as a polishing tool to adapt to the surface shape change of the aspherical mold, and designed a semi-flexible small polishing disc tool with microstructure, which can better adapt to the curvature change of aspherical surface and obtain better SR Ra. At the same time, a combined polishing method of constant speed and variable speed for screw feed was proposed to improve the uniformity of SR distribution in the paper. Then, a series of theoretical analysis and experimental verification were carried out in this paper to predict the tool influence function (TIF) of the two polishing tools and the effectiveness of the combined polishing method. In the experiment, a TIF bandwidth of about 0.46 mm was obtained with a small spherical polishing tool, which favors the surface shape correction of the small aspherical mold. The experiment of uniform removal with a small polishing disc tool was carried out to quickly reduce the Ra. Finally, the surface quality of the aspherical mold was effectively improved, combined with the constant speed and variable speed polishing modes of screw feed of the small spherical polishing tool and the smoothing effect of the small polishing disc tool. The peak valley (PV) of two small aspherical molds with an optical effective diameter less than 13 mm converged from 0.3572 µm and 0.2075 µm to 0.1282 µm and 0.071 µm, respectively. At the same time, the SR dispersion coefficient was reduced from 27.9% and 41.6% to 14.2% and 12.7%, respectively. The study provides a good solution for the surface quality control of small aspherical molds.