An Implementation of Health Prediction in SMT Solder Joint via Machine Learning

Chang, Yi-Ming; Wei, Chia-Chen; Chen, Jeffrey; Hsieh, Pack

doi:10.1109/bigcomp.2019.8679428

Cited by 15 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The presence of irrelevant pixels included in the GLCM operation diminishes the accuracy of the model. However, this issue has not been resolved in previous studies [9][10][11][12][13][14][15][16][17][18][19], prompting the need for a solution in this research.…”

Section: Introductionmentioning

confidence: 91%

“…Considering these opportunities, several studies [9][10][11][12][13][14][15][16][17][18][19] have aimed to develop algorithms capable of running on lower-capacity CPU-based computers. The approach involves utilizing classical machine learning techniques to ensure that the algorithm can run on simple CPU devices, like microcomputers or single-board computers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

2024

IJIES

View full text Add to dashboard Cite

Quality inspection of solder connections in electronic circuit manufacturing is commonly performed using automatic optical inspection (AOI) technology. The utilization of deep learning in AOI has demonstrated high accuracy and fast computation, yet it requires expensive graphics processing unit (GPU) equipped computers. To enable broader and more cost-effective utilization, there is a need for an AOI model that can be embedded in simple central processing unit (CPU) based computers. To pursue this objective, several research efforts have been undertaken to develop AOI models based on classical machine learning techniques. However, the accuracy and speed achieved by these models have not yet matched deep learning-based AOI models. This study aims to enhance the computational efficiency of classic machine learning by processing only pixels containing textural information. The effectiveness enhancement is achieved through the application of log-polar transformation in the extraction of texture features using the gray level co-occurrence matrix (GLCM) to detect defects in trough hole technology (THT) solder joint connections. By transforming cartesian coordinates into polar coordinates, the textural areas to be detected assume a square shape, facilitating efficient texture feature extraction. To ensure a significant improvement in performance, a comparative performance evaluation is conducted on classic machine learning-based AOI models with and without the log-polar transformation. The texture features extracted from both models are classified using the support vector machine (SVM) method. Model testing and evaluation reveals that the proposed enhancement effort is capable of increasing accuracy levels to 95% and reach computation time by 120 milliseconds.

show abstract

Section: Introductionmentioning

confidence: 91%

Section: Introductionmentioning

confidence: 99%

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

2024

IJIES

View full text Add to dashboard Cite

show abstract

“…Among the meter anomaly, a common means is to short-cut the welding spots of the current input area, as shown in Figure 7. The authors of [17] used traditional machine vision methods to detect welding spot defects but had the disadvantages of difficult threshold selection and poor robustness. The authors of [18] proposed a deep learning welding spot detection method to classify leakage welding, bridging, and normal welding spot images, but it could not meet the requirements of on-site real-time detection.…”

Section: Detection Of An Anomaly In Welding Spotsmentioning

confidence: 99%

Energy Meter Patch Resistance and Welding Spot Anomaly Detection Method Based on Machine Vision

Jiang

Chen

Zhang

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Based on the problems, such as the difficulty of detecting and obtaining evidence of patch resistance replacement and welding spot anomaly in the current field of meter anomaly detection, a patch resistance and welding spot anomaly detection algorithm is proposed based on machine vision. The resistance anomaly detection algorithm combines the K-D tree and Ransac to complete the high-efficiency energy meter registration. It detects the suspected resistance abnormal area through the difference shadow method and then judges the resistance abnormal situation according to the resistance value recognized by the classification network. The welding spot anomaly detection algorithm enhances the feature of the image through saliency detection, then obtains the target information of the welding spot by segmentation, and finally determines the welding spot anomaly condition in combination with the connection domain analysis. Experimental results show that the precision of patch resistance anomaly of this method reaches 95.28%, and the detection time is about 1.52s; the precision of welding spot anomaly reaches 96.74%, and the detection time is about 0.74s. The method can meet the requirements of spot detection accuracy and speed and has good application value.

show abstract

“…The quality of the soldering can be enhanced by optimizing the key factors [21], [22]: squeegee pressure, squeegee speed, and stencil cleaning interval. By analyzing the trend of soldering, the stencil cleaning interval can be automatically optimized [23], [24]. Similarly, the optimization of SPP parameters improves the quality of the end-products [25].…”

Section: B Smt Optimizationmentioning

confidence: 99%

Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste Inspection

Yoo¹,

Kim

2022

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Surface mount technology (SMT) is a process for producing printed circuit boards. Solder paste printer (SPP), package mounter, and solder reflow oven are used for SMT. The board on which the solder paste is deposited from the SPP is monitored by solder paste inspector (SPI). If SPP malfunctions due to the printer defects, the SPP produces defective products, and then abnormal patterns are detected by SPI. In this paper, we propose a convolutional recurrent reconstructive network (CRRN), which decomposes the anomaly patterns generated by the printer defects, from SPI data. CRRN learns only normal data and detects anomaly pattern through reconstruction error. CRRN consists of a spatial encoder (S-Encoder), a spatiotemporal encoder and decoder (ST-Encoder-Decoder), and a spatial decoder (S-Decoder). The ST-Encoder-Decoder consists of multiple convolutional spatiotemporal memories (CSTMs) with ST-Attention mechanism. CSTM is developed to extract spatiotemporal patterns efficiently. Additionally, a spatiotemporal attention (ST-Attention) mechanism is designed to facilitate transmitting information from the ST-Encoder to the ST-Decoder, which can solve the long-term dependency problem. We demonstrate the proposed CRRN outperforms the other conventional models in anomaly detection. Moreover, we show the discriminative power of the anomaly map decomposed by the proposed CRRN through the printer defect classification.

show abstract

An Implementation of Health Prediction in SMT Solder Joint via Machine Learning

Cited by 15 publications

References 10 publications

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

Energy Meter Patch Resistance and Welding Spot Anomaly Detection Method Based on Machine Vision

Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste Inspection

Contact Info

Product

Resources

About