Edge finite elements - neural networks modelling for crosstalk in electronic printed circuit boards

A multidisciplinary placement optimization methodology for heat generating electronic components on printed circuit boards (PCBs) is presented. The methodology includes thermal, electrical and placement criteria involving junction temperature, wiring density, line length for high frequency signals, and critical component location which are optimized simultaneously using the genetic algorithm. A board-level thermal performance prediction methodology which is based on a combination of a superposition method and artificial neural networks (ANNs) is developed for this study. Two genetic algorithms with different thermal prediction methods are used in a cascade in the optimization process. The first genetic algorithm is based on simplified thermal network modeling and it is mainly aimed at finding component locations that avoid any overlap. Compact thermal models are used in the second genetic algorithm leading to more accurate thermal prediction which improves the placement optimization obtained using the first algorithm. Using this optimization methodology, large calculation time reduction is achieved without losing accuracy. To demonstrate the capabilities of the present methodology, a test case involving component placement on a PCB is presented.

Download Full-text

Defect Detection in Printed Circuit Boards with Pre-Trained Feature Extraction Methodology with Convolution Neural Networks

Computers Materials & Continua ◽

10.32604/cmc.2022.019527 ◽

2022 ◽

Vol 70 (1) ◽

pp. 637-652

Author(s):

Mohammed A. Alghassab

Keyword(s):

Neural Networks ◽

Feature Extraction ◽

Defect Detection ◽

Printed Circuit Boards ◽

Circuit Boards ◽

Printed Circuit ◽

Convolution Neural Networks

Download Full-text

Defect Detection in Printed Circuit Boards Using You-Only-Look-Once Convolutional Neural Networks

Electronics ◽

10.3390/electronics9091547 ◽

2020 ◽

Vol 9 (9) ◽

pp. 1547

Author(s):

Venkat Anil Adibhatla ◽

Huan-Chuang Chih ◽

Chi-Chang Hsu ◽

Joseph Cheng ◽

Maysam F. Abbod ◽

...

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Defect Detection ◽

Printed Circuit Boards ◽

Learning Algorithms ◽

Detection Accuracy ◽

Quality Inspection ◽

Circuit Boards ◽

Printed Circuit

In this study, a deep learning algorithm based on the you-only-look-once (YOLO) approach is proposed for the quality inspection of printed circuit boards (PCBs). The high accuracy and efficiency of deep learning algorithms has resulted in their increased adoption in every field. Similarly, accurate detection of defects in PCBs by using deep learning algorithms, such as convolutional neural networks (CNNs), has garnered considerable attention. In the proposed method, highly skilled quality inspection engineers first use an interface to record and label defective PCBs. The data are then used to train a YOLO/CNN model to detect defects in PCBs. In this study, 11,000 images and a network of 24 convolutional layers and 2 fully connected layers were used. The proposed model achieved a defect detection accuracy of 98.79% in PCBs with a batch size of 32.

Download Full-text