Automated Detection of Printed Circuit Boards (PCB) Defects by Using Machine Learning in Electronic Manufacturing: Current Approaches

Zakaria, Syed Muhammad Mamduh Syed; Amir, Amiza; Yaakob, Naimah; Nazemi, Shamsodin

doi:10.1088/1757-899x/767/1/012064

Cited by 21 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML-based computer vision tasks include image target classification and target proposed another feature-learning-based PCB inspection method via speeded-up Random Forest in [104]. Similarly, for defect detection, Zakaria et al proposed an automated detection of PCB defects by using machine learning in electronic manufacturing [107]. Hu et al proposed a surface defect detection method with faster CNN and feature pyramid network [108].…”

Section: Ml-based Pcb Analysis Of Hardware Vulnerabilitiesmentioning

confidence: 99%

A Survey on Hardware Vulnerability Analysis Using Machine Learning

Pan

Mishra

2022

IEEE Access

View full text Add to dashboard Cite

Electronic systems rely on efficient hardware, popularly known as system-on-chip (SoC), to support its core functionalities. A typical SoC consists of diverse components gathered from third-party vendors to reduce SoC design cost and meet time-to-market constraints. Unfortunately, the participation of third-party companies in global supply chain introduces potential security vulnerabilities. There is a critical need to efficiently detect and mitigate hardware vulnerabilities. Machine learning has been successfully used in hardware security verification as well as development of effective countermeasures. There are recent surveys on hardware Trojan detection using machine learning. To the best of our knowledge, there are no comprehensive surveys on utilization of machine learning techniques for detection and mitigation of a wide variety of hardware vulnerabilities including malicious implants (e.g., hardware Trojans), sidechannel leakage, reverse engineering, and supply-chain vulnerabilities (e.g., counterfeiting, overbuilding and recycling). In this paper, we provide a comprehensive survey of hardware vulnerability analysis using machine learning techniques. Specifically, we discuss how existing approaches effectively utilize machine learning algorithms for hardware security verification using simulation-based validation, formal verification as well as side-channel analysis.

show abstract

Section: Ml-based Pcb Analysis Of Hardware Vulnerabilitiesmentioning

confidence: 99%

A Survey on Hardware Vulnerability Analysis Using Machine Learning

Pan

Mishra

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…They also used the ResNet50 method together with Feature Pyramid Networks as the pillar for feature extraction, aiming for the effective detection of small defects on the PCB. Zakaria et al (2020) examined whether the machine learning approaches can significantly contribute to better PCB fault detection in the assembly line. They presented several different attitudes to PCB defect detection using various machine learning methods.…”

Section: Literature Reviewmentioning

confidence: 99%

A Novel Data Mining Approach for Defect Detection in the Printed Circuit Board Manufacturing Process

Bártová

Bína

2022

Engineering Management in Production and Services

View full text Add to dashboard Cite

This research aims to propose an effective model for the detection of defective Printed Circuit Boards (PCBs) in the output stage of the Surface-Mount Technology (SMT) line. The emphasis is placed on increasing the classification accuracy, reducing the algorithm training time, and a further improvement of the final product quality. This approach combines a feature extraction technique, the Principal Component Analysis (PCA), and a classification algorithm, the Support Vector Machine (SVM), with previously applied Automated Optical Inspection (AOI). Different types of SVM algorithms (linear, kernels and weighted) were tuned to get the best accuracy of the resulting algorithm for separating good-quality and defective products. A novel automated defect detection approach for the PCB manufacturing process is proposed. The data from the real PCB manufacturing process were used for this experimental study. The resulting PCALWSVM model achieved 100 % accuracy in the PCB defect detection task. This article proposes a potentially unique model for accurate defect detection in the PCB industry. A combination of PCA and LWSVM methods with AOI technology is an original and effective solution. The proposed model can be used in various manufacturing companies as a postprocessing step for an SMT line with AOI, either for accurate defect detection or for preventing false calls.

show abstract

“…So after filtering a null field method is performed to manipulate the pixel points in the image with pixel range normalization to adjust the pixel range after image enhancement to within the grayscale value of 0~255. After completing the image pre-processing, Dongjie Li 1 • Liwen Zhang 2 • Weihua Liu 3 • Xinghu Yu Affiliations 4 Improvement of FLIP CHIP detection and localization based on traditional image algorithm region screening is needed to reduce interference and extract the image information of the most valuable part. Defective balls are usually not round but have an elongated or oval shape.…”

Section: Introductionmentioning

confidence: 99%

Improvement of FLIP CHIP detection and localization based on traditional image algorithm

Li¹,

Zhang²,

Liu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Surface mount technology (SMT) in integrated circuits, is one of the pillars of electronic information industry. Its degree of development is also one of the core indicators to measure the level of science and technology of a country, which affects process of social information. In recent years, chip technology has improved, and surface mount technology has also achieved remarkable results. But there are still two problems, one is for high-density integrated chips (such as BGA, FLIP CHIP, etc.), the recognition of pass rate is low by the light, chip quality, and other external factors such as more significant impact. The other is traditional template matching algorithm used for positioning, which takes a long time and leads to low production placement speed. In this paper, we take FLIP CHIP as an example and propose a regional screening algorithm to reduce interference, which includes area screening and roundness screening to extract the most valuable part of image information. The regional connected domain method is proposed to obtain the center of gravity set of weld balls and the circle fitting function in OpenCV is used to calculate weld ball radius. The pre-processed image is taken to improve linear fitting method to calculate the chip body size, the average pitch of solder ball, the rotation angle, and the coordinates of the center point of the chip. The remapping search algorithm is used to calculate the number of empty spaces. Then, the rotation angle under the obtained image coordinate system and the center point coordinates of chip are converted to the physical coordinate system at the time of positioning. Then, the offset is output by subtracting from the size of acquired ROI. It is more advantageous than the method of template matching to improve detection speed while ensuring accuracy.

show abstract

Automated Detection of Printed Circuit Boards (PCB) Defects by Using Machine Learning in Electronic Manufacturing: Current Approaches

Cited by 21 publications

References 9 publications

A Survey on Hardware Vulnerability Analysis Using Machine Learning

A Survey on Hardware Vulnerability Analysis Using Machine Learning

A Novel Data Mining Approach for Defect Detection in the Printed Circuit Board Manufacturing Process

Improvement of FLIP CHIP detection and localization based on traditional image algorithm

Contact Info

Product

Resources

About