Solder Joint Defects Research Articles

XSCAN: Explainable solder joint defect probability prediction through solder paste printing status with imbalanced data

This research addresses challenges in Surface Mount Technology (SMT) related to solder joint quality prediction, focusing on the initial solder paste printing stage. Recognizing that over 50% of defects originate at the printing stage, this research delves into establishing a direct correlation between printing quality and joint quality. Traditional approaches have limitations in accurately predicting defects due to isolated treatment of printing quality indicators, scarce explainability of prediction models, and lack of joint defect data. This research introduces a novel framework, XSCAN, aimed at predicting the probabilities of solder joint defects from the states of the printed solder paste. This is accomplished by using a generative adversarial network (GAN) to synthesize additional defect data and segment the feature space of printing indicators using customized decision trees to minimize defect probability prediction error. Specifically, XSCAN optimizes generative model structures using decision tree prediction results focused on defects, generating valuable defect information to help feature space partition. Also, pruning rules are designed to handle imbalanced data and improve defect prediction. They enhance explainability by defining safe and high-risk zones for solder paste quality. XSCAN outperforms all other baselines when tested on real-world datasets of chip resistors. It achieves the lowest prediction error and provides different warning levels for potential joint defects. XSCAN takes a proactive approach to improve manufacturing quality while addressing data imbalance and model explainability challenges. It provides practical insights to enhance SMT processes and reduce waste and rework costs.

PCB plug-in solder joint defect detection method based on coordinated attention-guided information fusion

Printed Circuit Boards (PCBs) are the foundational component of electronic devices, and the detection of PCB defects is essential for ensuring the quality control of electronic products. Aiming at the problem that the existing PCB plug-in solder defect detection algorithms cannot meet the requirements of high precision, low false alarm rate, and high speed at the same time, this paper proposes a method based on spatial convolution pooling and information fusion. Firstly, on the basis of YOLOv3, an attention-guided pyramid structure is used to fuse context information, and multiple convolutions of different size are used to explore richer high-level semantic information; Secondly, a coordinated attention network structure is introduced to calibrate the fused pyramidal feature information, highlighting the important feature channels, and reducing the adverse impact of redundant parameters generated by feature fusion; Finally, the ASPP (Atrous Spatial Pyramid Pooling) structure is implemented in the original Darknet53 backbone feature extraction network to acquire multi-scale feature information of the detection targets. With these improvements, the average detection accuracy of the enhanced network has been elevated from 94.45 to 96.43%. This experiments shows that the improved network is more suitable for PCB plug-in solder defect detection applications.

Analytical solution for forced vibration of multilayer structures composed of plates with different geometric dimensions

Multilayer system composed of parallel plate components with different geometric dimensions is frequently used to describe engineering objects, such as electronic assembly. In this work, an analytical method was proposed for forced vibration of this type of multilayer system. The proposed method overcomes the limitation that the traditional wave method is only applicable to all plate components must have the same in-plane dimensions. The proposed analytical method has an efficiency advantages in parameter analysis than element-based methods such as finite element method (FEM). The connection joints between two adjacent plate components, such as ball grid array (BGA) solder interconnect, are represented by elastic springs. The vibration of each component are described in terms of general and physical analytical waves, respectively, and the dynamic coupling between them are established by an equivalent dynamic flexibility matrix. The forced responses of the multilayer system are analytically calculated by solving the system equation in wave space. In the numerical examples, the effectiveness of the proposed method is validated by comparing the present results with the FEM results. The influence of number of the defective solder joints on vibration response is also investigated.

DBHF: A double fusion backbone and bidirectional feature hybrid fusion detector for high-precision inspection of avionics solder joint defects

The quality of avionics thermistor wire solder joints has a critical impact on the performance of in-orbit spacecraft. However, it is still hard to simultaneously realize a high-precision inspection of the multi-scale internal and external defects of avionics solder joints. Herein, in combination with active infrared thermography technique, an innovative DBHF detector with a double fusion backbone and a learnable weighted multi-scale bidirectional feature hybrid fusion pyramid network (BdFPN) is demonstrated based on RT-DETR framework. Specifically, the double fusion backbone framework comprises with two lightweight convolutional neural network-based backbones. Compared with conventional single backbone, the double-backbone design forms a multi-level Resnet-like structure, helping to enrich the extracted multi-dimension feature information and retain rich detail information of small-scale defects. The complex learnable weighted multi-scale BdFPN is designed for cross fusion of deep features. One or more additional multi-scale inputs are added to each node involved in feature fusion to aggregate more features from multiple scales and strengthen the interaction between low-level details and high-level semantic information, enabling the detector to make full use of multi-level feature information. Meanwhile, a learnable weight coefficient is set on each node involved in feature fusion and the importance of the input to each node is estimated by training, so that the effective information can be deeply aggregated at different levels. Our DBHF detector achieves a 92.7 % mAP@0.5 on a self-made avionics solder joint dataset with a body size of only 27.2 MB and FPS of 149, outperforming all the typical advanced real-time detectors.

The preparation and wettability of the Sn-9Zn-2.5Bi-1.5In solder paste for SMT process and high shear ball performance

Purpose This study aims to focus on the surface mount technology (SMT) mass production process of Sn-9Zn-2.5Bi-1.5In solder. It explores it with some components that will provide theoretical support for the industrial SMT application of Sn-Zn solder. Design/methodology/approach This study evaluates the properties of solder pastes and selects a more appropriate reflow parameter by comparing the microstructure of solder joints with different reflow soldering profile parameters. The aim is to provide an economical and reliable process for SMT production in the industry. Findings Solder paste wettability and solder ball testing in a nitrogen environment with an oxygen content of 3,000 ppm meet the requirements of industrial production. The printing performance of the solder paste is good and can achieve a printing rate of 100–160 mm/s. When soldering with a traditional stepped reflow soldering profile, air bubbles are generated on the surface of the solder joint, and there are many voids and defects in the solder joint. A linear reflow soldering profile reduces the residence time below the melting point of the solder paste (approximately 110 s). This reduces the time the zinc is oxidized, reducing solder joint defects. The joint strength of tin-zinc joints soldered with the optimized reflow parameters is close to that of Sn-58Bi and SAC305, with high joint strength. Originality/value This study attempts to industrialize the application of Sn-Zn solder and solves the problem that Sn-Zn solder paste is prone to be oxidized in the application and obtains the SMT process parameters suitable for Sn-9Zn-2.5Bi-1.5In solder.

YOLO algorithm with hybrid attention feature pyramid network for solder joint defect detection

YOLO algorithm with hybrid attention feature pyramid network for solder joint defect detection

Progress and comparison in nondestructive detection, imaging and recognition technology for defects of wafers, chips and solder joints

ABSTRACT As an essential part of integrated circuit, chip manufacturing has increasingly demanding requirements for quality, cost and others. Some technical limitations and the development direction of miniaturisation and high density have led to defects in the manufacturing process, which affect the performance and life of the chip. Therefore, the detection, identification and classification of defects are very important to improve the chip reliability. Based on the orderly and concise literature research, this paper focuses on a comprehensive review of the main research results in the field of non-contact non-destructive testing imaging methods for chip defects. Firstly, various defects that may occur in the chip design and packaging process are introduced. Then the contact detection methods including manual and probe method are clarified, and the principles, properties and development applications of NDT methods are introduced in detail, also the defect identification methods after imaging are briefly introduced. Moreover, the advantages and limitations of NDT technologies are summarised through comparative studies. Finally, the future development trend of non-destructive testing methods is predicted. This work hopes to provide some reference for the non-destructive testing of chips, which is of great significance for the health testing of chips in the electronics manufacturing industry.

SolderNet: Towards trustworthy visual inspection of solder joints in electronics manufacturing using explainable artificial intelligence

AbstractIn electronics manufacturing, solder joint defects are a common problem affecting a variety of printed circuit board components. To identify and correct solder joint defects, the solder joints on a circuit board are typically inspected manually by trained human inspectors, which is a very time‐consuming and error‐prone process. To improve both inspection efficiency and accuracy, in this work, we describe an explainable deep learning‐based visual quality inspection system tailored for visual inspection of solder joints in electronics manufacturing environments. At the core of this system is an explainable solder joint defect identification system called SolderNet that we design and implement with trust and transparency in mind. While several challenges remain before the full system can be developed and deployed, this study presents important progress towards trustworthy visual inspection of solder joints in electronics manufacturing.

CSSD-YOLO: A Modified YOLOv5 Method for Solder Joint Defect Detection

Surface Mount Technology (SMT) pin solder joint defects are hard to detect since the joints are smaller and denser and have high similarity between defect samples and standard samples in solder joint images. We propose an improved YOLOv5 defect detection algorithm embedding Cascade Shuffle Space to Depth (CSSD), Coordinate Attention (CA) mechanism module, and K-means++ algorithm. The proposed improved Yolov5 significantly impacts the loss and model parameter reduction and higher positioning precision of the defect location on the disk. The optimum anchor box produces better clustering and stability. Compared with the original YOLOv5 under the same test conditions, the method in this paper improves the precision by 12.2%, recall by 9.4%, mAP by 9.0%, and model parameters reduced by 1.3M. In conclusion, the experimental results show that the algorithm proposed in this paper has a better detection effect and a smaller parameter scale. It also can better meet the defect detection and model deployment in the actual industrial production environment.

SolderNet: Towards Trustworthy Visual Inspection of Solder Joints in Electronics Manufacturing Using Explainable Artificial Intelligence

In electronics manufacturing, solder joint defects are a common problem affecting a variety of printed circuit board components. To identify and correct solder joint defects, the solder joints on a circuit board are typically inspected manually by trained human inspectors, which is a very time-consuming and error-prone process. To improve both inspection efficiency and accuracy, in this work we describe an explainable deep learning-based visual quality inspection system tailored for visual inspection of solder joints in electronics manufacturing environments. At the core of this system is an explainable solder joint defect identification system called SolderNet which we design and implement with trust and transparency in mind. While several challenges remain before the full system can be developed and deployed, this study presents important progress towards trustworthy visual inspection of solder joints in electronics manufacturing.

A Novel Contrastive Self-Supervised Learning Framework for Solving Data Imbalance in Solder Joint Defect Detection.

Poor chip solder joints can severely affect the quality of the finished printed circuit boards (PCBs). Due to the diversity of solder joint defects and the scarcity of anomaly data, it is a challenging task to automatically and accurately detect all types of solder joint defects in the production process in real time. To address this issue, we propose a flexible framework based on contrastive self-supervised learning (CSSL). In this framework, we first design several special data augmentation approaches to generate abundant synthetic, not good (sNG) data from the normal solder joint data. Then, we develop a data filter network to distill the highest quality data from sNG data. Based on the proposed CSSL framework, a high-accuracy classifier can be obtained even when the available training data are very limited. Ablation experiments verify that the proposed method can effectively improve the ability of the classifier to learn normal solder joint (OK) features. Through comparative experiments, the classifier trained with the help of the proposed method can achieve an accuracy of 99.14% on the test set, which is better than other competitive methods. In addition, its reasoning time is less than 6 ms per chip image, which is in favor of the real-time defect detection of chip solder joints.

Solder Joint Defect Inspection Method Based on ConvNeXt-YOLOX

ConvNeXt-YOLOX model, an improved deep learning algorithm based on the YOLOX neural network, is proposed for surface mount technology (SMT) production line printed circuit board assembly (PCBA) solder joint defect detection with high accuracy and speed. The improved model employs the classification neural network ConvNeXt to enhance the feature extraction capability of the YOLOX backbone feature extraction network, thus enhancing the target detection accuracy and speed as well as the small target detection capability while maintaining the same number of parameters. A solder joint defect detection dataset containing 759 PCBA solder joint defect images is constructed, on which the improved model ConvNeXt-YOLOX, the original model YOLOX, and the lightweight model YOLOX-s are trained. Subsequently, the training results of the three models are compared. The comparison shows that the mean average precision (mAP) of the improved model ConvNeXt-YOLOX is 97.21%, which is 0.82% and 3.02% higher than that of YOLOX and YOLOX-s, respectively, while the mAP at (0.5:0.95) is increased from 76.3 to 77.5. Moreover, the detection speed is increased from the original 27.06 to 27.88 frames/s. In summary, the improved model ConvNeXt-YOLOX has strong small target feature extraction and detection capabilities, which are consistent with the actual requirements of solder joint defect detection.

Micro solder bump detection of flip chip using improved decision tree model based on SAM image

The increasing packaging density of flip chips brings great challenges for micro defect detection. It is necessary to develop an efficient and automatic inspection system for electronic industrial application. In this paper, the scanning acoustic microscopy (SAM) technology and the optimized classifier were investigated for the automatic detection of solder joint defects of flip chips. Ultrasonic images of 1902 solder bumps from 6 chip samples were obtained using a SAM equipment. The decision tree model was improved by introducing the granularity decision entropy. The feature vectors were extracted from the images of solder bumps, and then used for classification. The results show that the decision tree model correctly detected 1812 solder bumps with the accuracy of 95.3%. It is verified that the ultrasonic defect detection system based on the improve decision tree model has high accuracy for micro defect inspection, which has potential and promising application in the electronic packaging industry.

Vision-based Inspection of PCB Soldering Defects

Vision-based inspection of printed circuit board (PCB) soldering defects was studied for preparing feature data and classifying the overall PCB soldering defects on a PCB prototype into different classes. The image data of overall PCB soldering defects on a PCB prototype was developed using an image sensor camera. Image data augmentation was conducted to enhance the dataset volume. Image pre-processing included image resizing, image colour conversion, and image denoising. Watershed-based image segmentation was performed in the image post-processing to segmented images; then, feature extraction was conducted using curvelet transform to prepare image feature data. The feature data as the statistical data include kurtosis, contrast, energy, homogeneity, and variance. These data were analysed, and the percentage difference of mean values of statistical data between image classes was calculated. Kurtosis had the highest percentage difference among the statistical data. In the comparison of the mean values, kurtosis obtained 4.97% difference for the class of good and medium condition; 17.02% difference for the good and bad condition; and 12.08% difference for the bad and medium condition. Through this analysis, kurtosis is considered more reliable data for the machine-learning based classification in this project. The extracted data can be applied in future studies to classify overall solder joint defects on a PCB prototype by artificial neural network in machine learning classification.

A feasibility study on potential of stress sensors to detect solder joint defects toward prognostics of power modules

The superiority of stress sensors over temperature sensors for detecting defects in solder joints was investigated. The effects of joint defects on device stress and temperature in a single-sided cooling structure were obtained via thermal stress simulation. The peripheral, edge, and central defects were assumed as the defect distributions. The central defects did not result in a remarkable occurrence rate of the stress waveform change. In contrast, the periphery and edge defects caused a large occurrence rate of the stress waveform change compared to that of the temperature. In general, the thermal strain of solder joints in a power module causes its initial degradation from the joint edge or periphery. Thus, the stress waveform provides useful information for detecting initial degradation. The change pattern of the temperature waveform because of the solder joint defects only caused an amplitude increase. In contrast, stress waveform changes exhibited four different patterns: amplitude increase, amplitude decrease, waveform inversion, and waveform disappearance. These results confirm that stress sensors are better than temperature sensors for detecting waveform changes caused by slight joint defects at peripheral or edge, particularly with a small number of sensors. Application of the data acquired via stress sensors to machine learning will allow estimation of the joint defect distribution. Furthermore, time-series stress waveform data can provide prognostics of solder joint degradation.

Improved YOLOv3 detection method for PCB plug-in solder joint defects based on ordered probability density weighting and attention mechanism

Printed Circuit Board (PCB) is the heart component of electronic products, and its defect detection is the basic requirement of PCB quality control in the production process. Traditional visual detection methods need artificial design features, so their detection accuracy is poor, and the rate of missed and false detection is high. To solve the above problems, this paper proposes an improved YOLOv3 (You Only Look Once) detection method for PCB plug-in solder spot defects based on the combination of the ordered probability density weighting and the attention mechanism. First, in order to obtain a higher priority priori box, the ordered probability density weighting (OWA) method is used to optimize the multiple sets of a priori boxes generated by K-means. Then, to get more effective feature information, the Squeeze-and-Excitation mechanism (SE) is added to the backbone network. In the feature detection network, the Convolutional Block Attention Module (CBAM) attention mechanism is joined, at the same time in the inspection network output layer three layer feature are fusions. Finally, in order to accelerate the convergence speed of model and improve the accuracy of the model, the network loss function was improved by using the generalized joint generalized intersection over union (GIoU), and the COCO data model was applied to PCB solder spot defect training by transfer learning method. After testing, the average detection accuracy of improved network is improved from 84.35% to 96.69%, and the improved network has better convergence than the original network. The study shows that the improved method based on YOLOv3 is more suitable for industrial application of PCB plug-in solder spot defect detection.

Automatic compact camera module solder joint inspection method based on machine vision

Because of the contradiction between the production requirements of compact camera modules (CCMs) to achieve high efficiency and quality and the low efficiency and poor accuracy of traditional solder joint inspection methods, an automatic inspection method of CCM solder joint based on machine vision is proposed. After optimizing the imaging parameters according to the CCM inspection process, the region of interest is dynamically identified based on feature matching and image enhancement methods to remove background interference. On this basis, an improved adaptive particle swarm optimization is used to optimize the kernel extreme learning machine to automatically classify the solder joint defects. Experimental results showed that with its low latency, high precision and robustness, the CCM surface solder joint defect detection and classification method based on machine vision can effectively solve the problem of low efficiency and high cost of the current CCM solder joint defect detection technology.

Infrared nondestructive detection of defective visible-reflective solder joints in solenoid coil connectors

Nondestructive infrared detection of solder defects in solenoid coil connectors was investigated. A detailed experimental setup and a meticulous and repeatable experimental procedure were developed. The experimental methods were firmly based on the application of heat transfer science. Time averaged excess temperature ([Formula: see text]) was the sole discrimination parameter, and a difference larger than 2°C between good and defective solders was conservatively considered for good discrimination. Analysis of variance determined the minimum differences in [Formula: see text] between good and defective solder joints. The effects in discriminability of heating time ( th), time integration interval length ( ti), region of interest (ROI) geometry, and solder radiative properties were investigated. A rectangular ROI tightly enclosing the good solder was found as the best discrimination ROI. Matte black paint increasing radiative emission of solder joints significantly reduced discriminability. The defects were discriminated from the good solder for a rectangular ROI, th = 78 s, and ti = 20 s. Moreover, an excellent total inspection time of 34 s per solenoid coil is obtained by considering a well-controlled inspection environment during manufacturing, severe defects detection, and a possible 1°C difference for discrimination. Several aspects of the novel inspection procedure developed can greatly benefit the thermal imaging scientific community.

An efficient solder joint defects method for 3D point clouds with double-flow region attention network

In electronics mass-production, image-based methods are often used to detect the solder joint defects for achieving high-quality assurance with low labor costs. Recently, deep learning in 3D point clouds has shown an effective form of characterization for 3D objects. However, existing work rarely involves defect detection for PCBs based on 3D point clouds. In this paper, we propose a novel neural network named double-flow region attention network (DoubRAN) to detect defects of solder joints with 3D point clouds. On the one hand, a binocular lidar system is designed to efficiently capture 3D point clouds of solder joints. On the other hand, a fine-grained method named region attention network (RAN) is designed to detect defects, which attends on the region of interest directly by backpropagation without bounding box annotation. To evaluate the performance of our proposed network, we conduct extensive experiments on a unique dataset built by ourselves. The experimental results show that the region of interest extracted by RAN is consistent with the basis for human evaluation of solder joint quality. Besides, the defect detection results of DoubRAN meet factory requirements.

Study on Properties of High-Vanadium Full-Locked Cable with Alloy Coating with Defects

The Zn-5%Al-rare earth alloy coating has been used in High-Vanadium Full-Locked Cable (HVFLC) that is made in China. This application has shown excellent protective performance. However, during practical use, the coating may appear to be deteriorated in various degrees, which may further worsen the corrosion resistance and mechanical properties of the cable. This paper focuses on High-Vanadium Full-Locked Cable (HVFLC). Firstly, different types of prefabricated defect treatments have been applied into the wires of the cable, followed by corrosion paste accelerated corrosion test and mechanical tensile properties test. The aim of this act is to figure out the effects on the corrosion resistance and mechanical properties of the wire due to different types of defects in alloy plating. The results show that the corrosion resistance of the wires has been greatly affected because of the solder joint defects. Furthermore, the tensile strength of the wire indicates a drop of about 40%. This research makes up the gap in the related fields in China. In addition, basic data has been provided for the development of the HVFLC in China.