Solder Joint Inspection Research Articles

Enhancing GLCM-Based Feature Extraction for THT Solder Joint Inspection through Log Polar Transformation

Enhancing GLCM-Based Feature Extraction for THT Solder Joint Inspection through Log Polar Transformation

Advancing surface mount technology quality: a computer-assisted approach for enhanced X-ray inspection of solder joints

Advancing surface mount technology quality: a computer-assisted approach for enhanced X-ray inspection of solder joints

Immersion Tin Plating Enabling Reliable Wettable Flanks on QFN Packages

The automotive market increasingly uses bottom-termination IC packages, like Quad-Flat No leads (QFN) packages, for miniaturization, cost reduction and performance. QFN lead frames are electroplated with 8?12 um of tin for PCB soldering, but subsequent singulation exposes the copper-alloy lead frame at the cut edges. On these exposed lead flanks a solder fillet does not form, making Automatic Optical Inspection (AOI) of solder joints on lead-less packages not reliable. A solder fillet on lead flanks also improves the reliability of solder joints. Therefore, the automotive industry strives for a tin plated wettable flank on lead-less packages. Several approaches, e.g. dimpled or step-cut leads, to create a wettable flank are in use or development. Disadvantage of these methods is that only a part of the flank is tin-plated. Immersion tin plating processes are able to fully plate lead flanks. However, the maximum ~1.5um of standard self-limiting displacement immersion tin processes is too thin to comply with the durability requirements of automotive tin solder finishes. This contribution will discuss an immersion tin-plating process, machine concept and test results for a >2 um tin plated wettable flanks. The immersion tin plating process consist of the following process steps: 1. A high-pressure spray rinse prevents incomplete tin coverage by removing copper burrs formed during singulation. 2. A selective descaling process removes the natural copper oxide film on the exposed copper leads. 3. A selective activation process creates a high tin nucleation density to obtain a fine-grained tin layer. 4. The autocatalytic immersion tin process plates a 2 ? 3um tin layer in 45-60 minutes at 70-75oC. 5. An anti-tarnish process protects the tin layer against oxidation. Finally, rinsing and drying remove all traces of the used chemicals from the packages with tin plated flanks. A machine concept for the immersion tin-plating process is currently under development. The lead-less packages are processed directly on Standard singulation tape rings without repacking or manipulation of the packages. This enables a throughput of 20 tape rings per hour with the full package traceability required for the automotive market. Different types of QFN packages mounted on singulation tape were tin plated and subjected to standard (JEDEC J-STD-002E) solderability tests for component lead durability. Fine-grained 2-3 um thick pure tin deposit of good visual quality were obtained on the exposed QFN copper lead sidewalls with the following properties: • 0.5-1.5um residual tin layer after intermetallic formation in 8 h steam aging and 16 h oven bake. • 100% solder wetting after 6h dry bake at 150C • 100% solder wetting after 8h steam aging (93C and 80-90% RH). • 100% solder fillet height after ceramic glass test.

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.

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.

Board-Level Reliability of Lead-Frame Based Substrate and Surface Finishing Technology

Lead-frames have been widely used in the semiconductor package assembly field, and QFN (Quad flat no leads) has the advantages of miniaturization and cost reduction of the semiconductor package. It has had limited use in automotive or defense products because of its board-level reliability. Nevertheless, due to the advantages of QFN packages, there is a trend toward using QFNs in automotive packaging. Automotive use would also require a wettable flank design of the QFN leads and automated optical inspection (AOI) of solder joints. New lead forming and surface finish technologies, including wettable flank design, are expected to improve reliability and enable AOI inspection, but much research is needed. This study investigated the board-level reliability of various QFN lead designs and surface finishes. All lead frames with different structures and surface finish types were assembled under the same conditions and then mounted on a daisy chain printed circuit board to evaluate board-level reliability. Accelerated thermal cycling (TC) tests were performed per IPC-9701A rev 2/2006 over a temperature range of -40°C to 125°C and 6080cycles. Lastly, each package type tested was cross-sectioned, and failure analysis was performed by observing the solder joint crack for all leg samples.

Development of an Accurate and Automated Quality Inspection System for Solder Joints on Aviation Plugs Using Fine-Tuned YOLOv5 Models

The quality inspection of solder joints on aviation plugs is extremely important in modern manufacturing industries. However, this task is still mostly performed by skilled workers after welding operations, posing the problems of subjective judgment and low efficiency. To address these issues, an accurate and automated detection system using fine-tuned YOLOv5 models is developed in this paper. Firstly, we design an intelligent image acquisition system to obtain the high-resolution image of each solder joint automatically. Then, a two-phase approach is proposed for fast and accurate weld quality detection. In the first phase, a fine-tuned YOLOv5 model is applied to extract the region of interest (ROI), i.e., the row of solder joints to be inspected, within the whole image. With the sliding platform, the ROI is automatically moved to the center of the image to enhance its imaging clarity. Subsequently, another fine-tuned YOLOv5 model takes this adjusted ROI as input and realizes quality assessment. Finally, a concise and easy-to-use GUI has been designed and deployed in real production lines. Experimental results in the actual production line show that the proposed method can achieve a detection accuracy of more than 97.5% with a detection speed of about 0.1 s, which meets the needs of actual production

Fine-Grained Classification of Solder Joints With α-Skew Jensen–Shannon Divergence

Solder joint inspection (SJI) is a critical process in the production of printed circuit boards (PCB). Detection of solder errors during SJI is quite challenging as the solder joints have very small sizes and can take various shapes. In this study, we first show that solders have low feature diversity, and that the SJI can be carried out as a fine-grained image classification task which focuses on hard-to-distinguish object classes. To improve the fine-grained classification accuracy, penalizing confident model predictions by maximizing entropy was found useful in the literature. Inline with this information, we propose using the α-skew Jensen-Shannon divergence (α-JS) for penalizing the confidence in model predictions. We compare the α-JS regularization with both existing entropy-regularization based methods and the methods based on attention mechanism, segmentation techniques, transformer models, and specific loss functions for fine-grained image classification tasks. We show that the proposed approach achieves the highest F1-score and competitive accuracy for different models in the fine-grained solder joint classification task. Finally, we visualize the activation maps and show that with entropy-regularization, more precise class-discriminative regions are localized, which are also more resilient to noise. The code is available at https://github.com/furkanulger/SJI-entropy-reg.

Solder Joint Inspection Using SAM Image through Sparse Reconstruction

Solder Joint Inspection Using SAM Image through Sparse Reconstruction

Solder Joint Inspection on Printed Circuit Boards: A Survey and a Dataset

Surface Mount Technology (SMT) is a procedure for mounting electronic components to the surface of the printed circuit boards (PCB). Although the SMT procedure is more reliable than the conventional through-hole mounting, many errors may occur in SMT lines. In this paper, we surveyed methods presented for the optical inspection of solder joints on PCBs. The methods are grouped by problem-solving approach: reference-based, machine learning/computer vision, deep learning, and 3D reconstruction. We compare and discuss these approaches according to their advantages and disadvantages, with a focus on the more recent deep learning and 3D reconstruction techniques, and list the public datasets for solder joints inspection. Since defective samples rarely occur in the SMT manufacturing lines, public datasets have few defective samples that are essential for the inspection task. To fill this gap, we publish a public dataset with both normal and different types of SMT errors. Our dataset can be used as a benchmark to compare different algorithms. The dataset is available at https://github.com/furkanulger/solder-joint-dataset.

IC solder joint inspection via adaptive statistical modeling

Purpose Statistical modeling has been successfully applied to integrated circuit (IC) solder joint inspection. However, there are some inherent problems in previous statistical modeling methods. This paper aims to propose an adaptive statistical modeling method to further improve the inspection performance for IC solder joints. Design/methodology/approach First, different pixels in the IC solder joint image were modeled by different templates, each of which was composed of the hue value of the pixel and a proposed template significance factor. Then, the potential defect image was obtained by adaptive template matching and the potential defect threshold for each pixel. It was noted that the number of templates, matching distance threshold, potential defect threshold and updating rate were adaptively updated during model training. Finally, the trained statistical model was used to inspect the IC solder joints by means of defect degree. Findings Experimental results indicated that the proposed adaptive schemes greatly contributed to the inspection performance of statistical modeling. Also, the proposed inspection method achieved better performance compared with some state-of-the-art inspection methods. Originality/value The proposed method offers a promising approach for IC solder joint inspection, which establishes different numbers of templates constructed by pixel values and template significance factors for different pixels. Also, some important parameters were adaptively updated with the updating of the model, which contributed to the inspection performance of the model.

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.

A reliable solder joint inspection method based on a light-weight point cloud network and modulated loss

High-speed and high-reliability automated quality inspection is widely demanded in the electronics industry. Recently, deep learning theory combined with many non-destructive technologies shows superior performance for inspecting failed soldering. In this paper, a reliable point cloud learning based method is implemented for high-speed solder joint shape defect detection. First, a light-weight neural network named Solder PointNet (SPNet) is proposed. With local group attention mechanisms, SPNet avoids adverse effects of outliers in the scanning point cloud and finds favorable critical point feature adaptively. Then, a modulated loss is designed to ensure reliable low false detection rate. By adjusting the weights of cross-entropy loss, the predictive distribution of defective samples is guided to a smaller range, thereby setting an appropriate threshold to efficiently separate the predictive distribution. Furthermore, the proposed method is further trained and evaluated on the self built solder joint dataset DHU-PAD1000 of point cloud data. Comparison experiments are carried out on the built dataset, and the results show that SPNet achieves higher accuracy with fewer parameters, considerable speed advantage, and more reliable automated detection.

IC Solder Joints Inspection via an Optimized Statistical Modeling Method

IC Solder Joints Inspection via an Optimized Statistical Modeling Method

A novel solder joints inspection method using curvature and geometry features in high-density flexible IC substrates surface mount technology

The automatic optical inspection based defective diagnosis systems in the surface-mounted device is fairly important to the optimization of electronic manufacturing. The gist of this paper is that presents a novel inspection system for the distinction of defective solder joints on the high-density flexible IC substrates. Initially, an ultra-high precision 3D information acquirement system is elaborated. Then, several critical sub-regions are divided and pivotal features are extracted from them, in which the differential geometry based estimation scheme to obtain discrete curvatures directly and the crest line representation based shape characterization method are proposed. Finally, each type of the solder joints is described with different and ordered feature sequences, and the practical classification process is formulated as the pattern recognition and classification problem, which is also implemented by the set of predefined diagnosis rules of thumb and the introduced logical operations. By classifying seven categories of industrial solder joints and exhaustively comparing with other state-of-the-art methods, the performances of the proposed diagnosis system is validated. Experimental results verify the effectiveness and efficiency of the developed system from three aspects, i.e. inspection speed, total correct rate, and detectable types.

Quality inspection of micro solder joints in laser spot welding by laser ultrasonic method

The quality inspection of micro solder joints in laser spot welding (LSW) is a problem of great concern in industrial application. In this paper, a laser ultrasonic technology (LUT) was proposed to inspect the quality of micro solder joints in LSW. Firstly, based on the thermoelastic model of acoustic wave propagation in solid, a theoretical model was built and used to analyze the propagation properties of the Lamb wave in the whole field by finite element method (FEM), the transmitting properties of the excited Lamb wave via solder joint were affected by the effective contacted area of solder joint. Secondly, LUT was used to inspect the 1.2 mm/0.4 mm welding spot of standard/false 304 stainless steel welded components. By comparing the propagating properties of excited ultrasonic wave in different samples with different weld quality, the standard and false welding can be visually distinguished. Finally, a industrial CT was used to check the quality of the samples used in our experiment. Inclusions and pores have been found in the false solder joints, which will reduce the effective contacted area of solder joint, and then affected the propagation of ultrasonic wave. By combining the CT results and the experimental analysis, the experimental results detected by LUT are in good agreement with the simulation results. So, the LUT is a potential method in field of the quality inspection of micro solder joints in LSW.

IC solder joint inspection via generator-adversarial-network based template

IC solder joint inspection via generator-adversarial-network based template

Automatic optical inspection system for IC solder joint based on local-to-global ensemble learning

PurposeAutomatic optical inspection (AOI) systems have been widely used in many fields to evaluate the qualities of products at the end of the production line. The purpose of this paper is to propose a local-to-global ensemble learning method for the AOI system based on to inspect integrated circuit (IC) solder joints defects.Design/methodology/approachIn the proposed method, the locally statistically modeling stage and the globally ensemble learning stage are involved to tackle the inspection problem. At the former stage, the improved visual background extraction–based algorithm is used for locally statistically modeling to grasp tiny appearance differences between the IC solder joints to achieve potential defect images for the subsequent stage. At the latter stage, mean unqualified probability is introduced based on a novel ensemble learning, in which an adaptive weighted strategy is proposed for revealing different contributions of the base classifier to the inspection performance.FindingsExperimental results demonstrate that the proposed method achieves better inspection performance with an acceptable inspection time compared with some state-of-the-art methods.Originality/valueThe approach is a promising method for IC solder joint inspection, which can simultaneously grasp the local characteristics of IC solder joints and reveal inherently global relationships between IC solder joints.

Adversarial autoencoder for detecting anomalies in soldered joints on printed circuit boards

The inspection of solder joints on printed circuit boards is a difficult task because defects inside the joints cannot be observed directly. In addition, because anomalous samples are rarely obtained in a general anomaly detection situation, many methods use only normal samples in the learning phase. However, sometimes a small number of anomalous samples are available for learning. We propose a method to improve performance using a small number of anomalous samples for training in such situations. Specifically, our proposal is an anomaly detection method using an adversarial autoencoder (AAE) and Hotelling’s T-squared distribution. First, the AAE learns features of the solder joint following the standard Gaussian distribution from a large number of normal samples and a small number of anomalous samples. Then, the anomaly score of a solder joint is calculated by Hotelling’s T-squared method from the features learned by the AAE. Finally, anomaly detection is performed by thresholding using this anomaly score. In experiments, we show that our method performs anomaly detection with few false positives in such situations. Moreover, we confirmed that our method outperforms the conventional method using handcrafted features and a one-class support vector machine.

Detection of Micro Solder Balls Using Active Thermography Technology and <italic>K</italic>-Means Algorithm

Solder bump/ball technology has been extensively applied in microelectronic packaging industry. However, the size of solder balls/bumps as well as the pitch are getting smaller and smaller, conventional inspection techniques are insufficient for diagnosis of the defect. It is indispensable to explore new methods for solder joint inspection. In this paper, a nondestructive diagnosis system based on active thermography was proposed. The test vehicles, named as SFA1 and SFA2, were excited by the laser pulse, and the consequent thermal response of the packages was captured by a thermal imager. In order to improve the signal-to-noise ratio, the polynomial fit and differential absolute contrast techniques were utilized to reconstruct the thermal images. Then, the statistical features corresponding to each solder ball were extracted from the reconstructed thermal images, and used for clustering analysis with K -means algorithm. The results show that all the solder balls were recognized accurately, which demonstrates that the intelligent system using active thermography and K -means algorithm is effective for defects inspection in microelectronic packaging industry.