With the development of science and technology, consumers’ requirements for various electronic devices present a trend of more diverse functions and thinner bodies. This makes integrated circuits mounted in electronic products and their packaging more vital to satisfying the above requirements. Ball grid array (BGA) packaging is widely used in the field of microelectronic manufacturing industries due to its multiple I/O volumes and excellent electric characteristics. However, due to environmental loads such as vibration and impact during its production and application, defects inevitably emerge in BGA solder joint defects, which will lead to the failure of electronic products. This article summarizes the state-of-the-art research on the factors, analysis methods, and models for the fatigue failure of BGA chips. After rigorous discussions concerning this research, some theoretical suggestions are provided for BGA packaging in reliability analysis and the establishment of evaluation standards.

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.

At present, the situation of air pollution is still serious, and research on air filtration is still crucial. For the nanofiber air filtration membrane, the diameter, porosity, tensile strength, and hydrophilicity of the nanofiber will affect the filtration performance and stability. In this paper, based on the far-field electrospinning process and the performance effect mechanism of the stacked structure fiber membrane, nanofiber membrane was prepared by selecting the environmental protection, degradable and pollution-free natural polysaccharide biopolymer pullulan, and polyvinylidene fluoride polymer with strong hydrophobicity and high impact strength. By combining two kinds of fiber membranes with different fiber diameter and porosity, a three-layer composite nanofiber membrane with better hydrophobicity, higher tensile strength, smaller fiber diameter, and better filtration performance was prepared. Performance characterization showed that this three-layer composite nanofiber membrane had excellent air permeability and filtration efficiency, and the filtration efficiency of particles above PM 2.5 reached 99.9%. This study also provides important reference values for the preparation of high-efficiency composite nanofiber filtration membrane.

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.

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 ($mA{P}_{50}$) of 99.2, with 1.5 giga floating-point operations (GFLOPs) and 108.7 frames per second (FPS), in wire bonding defect detection.

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), mAP_0.5 and mAP_0.5–0.95 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%.