In Case You Missed It
Additive Manufacturing
“Inkjet-Printed Electronics for Rapid and Low-Cost Prototyping of Digital Microfluidic Devices Using an Off-the-Shelf Printer”
Authors: Babak Kamali Doust Azad, et al.
Abstract: Digital microfluidics (DMF) provides a versatile platform for lab-on-a-chip (LOC) systems to dispense, mix, merge and separate discrete droplets at the nanoliter to microliter scale with high precision and reproducibility. Inkjet printing offers a cleanroom-free alternative for fabricating electrodes, potentially replacing existing methods even for mass production of DMF devices, by reducing design complexity, fabrication time and cost.
Recent research explored inkjet printing of various conductive materials such as copper, gold, silver, graphene and carbon-based inks on multiple substrates. Researchers have found inkjet-printed devices for various applications, including 13-step rubella virus (RV), IgG immunoassay, microfluidic cancer biomarker detection, and electrochemical impedance spectroscopy for detecting picomolar concentration levels of heavy metals. However, many research groups still rely on expensive material printers for inkjet printing of electrodes, with costs reaching $40,000. This price can make such printers inaccessible to many researchers, necessitating the development of fast and cost-effective electrode printing protocols using unmodified desktop inkjet printers. Their work also has the potential to substantially reduce the costs associated with mass production of DMF devices.
The authors present a detailed report on implementing single-plate DMF using an office inkjet printer and accessible electronic modules. This approach enables rapid and cost-effective prototyping outside of a cleanroom environment.
The focus on single-plate devices stems from their simpler fabrication process and ease of operation, making them more suitable for rapid prototyping and experimentation. The authors thoroughly characterize a novel inkjet printer to print electrodes of Ag-ink on polyethylene terephthalate (PET) and glass slide substrates between terms here achieving maximum conductance.
Silver (Ag) offers high electrical conductivity, relative affordability compared to gold and conductive oxides, and excellent chemical stability. Three different dielectric materials – SU8, parafilm, and tape – are evaluated in terms of minimum AC and DC actuation voltages. The authors designed the actuation setup from scratch using common electronic modules and components. They demonstrate the efficacy of their approach by manipulating droplets within a micromixer design based on the fabricated inkjet-printed DMF chips. Mixing is a fundamental function in LOC devices, and this demonstration highlights the potential of the authors’ printed electronics approach for developing various LOC applications.
The authors employ image processing to assess the mixing process, further validating the accessibility and effectiveness of the developed inkjet printing workflow. The presented approach can adapt to similar off-the-shelf printers, broadening the available equipment for inkjet printing. (Scientific Reports, Feb. 7, 2025)
Circularity
“Increasing Opportunities for Component Reuse on Printed Circuit Boards Using Deep Learning”
Authors: N. N. Dinh, et al.
Abstract: The increasing volume of discarded printed circuit boards spurs an urgent need to classify and reuse electronic components efficiently to mitigate environmental risks and recover valuable materials. Current solutions face challenges due to high computational requirements and inefficiencies in detecting reusable components before destruction. This study introduces PCBNet, a lightweight deep learning model based on a modified YOLOv8-tiny architecture, optimized for electronic component classification. PCBNet incorporates novel knowledge distillation strategies, involving three teacher models using a projection head that dynamically updates the teacher model weights to enhance performance without increasing computational complexity.
The optimized version, with α = 0.3 and β = 0.7 during the knowledge distillation process, achieves an mAP@50 of 0.467 and an mAP@95 of 0.368 with 0.5 million parameters and 1.7 billion floating-point operations, achieving an optimal balance between performance and computational efficiency. A prototype system using a Raspberry Pi, an automated conveyor and a monitoring camera has been developed to verify PCBNet’s effectiveness in detecting and classifying electronic components in PCBs. The results demonstrate that PCBNet is not only capable of accurate classification of electronic components but is also deployable on low-configuration devices, making it an effective solution for real-time e-waste recycling and component reuse. (International Journal of Environmental Science and Technology, Dec. 29, 2024)
Quality Control
“AI-Driven Quality Control in PCB Manufacturing: Enhancing Production Efficiency and Precision”
Author: Harshitkumar J. Ghelani
Abstract: This paper investigates how artificial intelligence (AI) enhances quality control within printed circuit board (PCB) manufacturing processes, focusing on improvements in production efficiency and precision. The research addresses traditional quality control methods like manual inspection and automated optical inspection (AOI) and highlights their limitations in addressing the complexities and demand for high-precision PCBs in modern electronics.
The study delves into how AI technologies, particularly machine learning, computer vision and predictive analytics, help to overcome these limitations. By automating defect detection, improving accuracy and enabling real-time analysis, AI systems streamline the quality control process and significantly reduce human error and production costs.
AI-driven quality control systems are shown to increase defect detection rates, reduce inspection times, and enhance overall production throughput. The paper provides a comparative analysis between traditional and AI-based quality control methods, revealing a notable improvement in both detection accuracy and production speed when employing AI systems. It also examines cost efficiency, demonstrating how AI systems reduce waste, minimize rework, and lower operational costs.
The authors discuss the potential challenges of AI implementation, such as high initial costs, data requirements and integration with legacy systems. Despite these challenges, AI offers a transformative solution to the growing demands of the PCB manufacturing industry, with the ability to scale effectively and adapt to future technological advancements. Ultimately, this research underscores the significant role of AI in revolutionizing PCB quality control by providing a more efficient, precise, and cost-effective approach, paving the way for further innovation in the electronics manufacturing sector. (International Journal of Scientific Research and Management, vol. 12, no. 10, October 2024)
“Multidimensional Computed Measurement for Highly Accurate PCBA Defect Detection”
Authors: Zefang Chen, et al.
Abstract: Accurate defect detection in industrial automated optical inspection (AOI) plays a crucial role in ensuring product quality and production efficiency. Although numerous techniques have been developed for industrial defect detection, most rely on single-texture image data. This dependence limits the accuracy and robustness of the defect detection due to inadequate optical source information.
To address the low accuracy resulting from the absence of 3-D topographic information, the authors propose a multidimensional information fusion (MIF) module that fuses texture image and depth image features. The MIF module includes tailored mechanisms to fully extract complementary semantic information from space and channel dimensions. A hierarchical fusion strategy further improves feature integration by enabling higher-layer feature fusion via lower-layer Transformer blocks and efficiently removing redundant features. Afterward, the authors perform the feature extraction on the fused feature map and obtain the output.
To enhance the detection accuracy, the authors introduce the position information mask (PIM) module for post-processing. The PIM module uses surface mount devices (SMDs) position data from Gerber files to create a position information mask. The mask helps filter out defects that are often misidentified owing to missing design information. The results of the comparative experiments demonstrate that the average accuracy of the authors’ method on the printed circuit board assembly (PCBA) defect dataset is 99.93%, which is 5.64% higher than that of conventional YOLOV5. Furthermore, a comprehensive ablation study is conducted to elucidate the contribution of the proposed MIF and PIM modules. The findings indicate that this model serves as a valuable reference for detecting PCBA surface defects. (Optics Express, Feb. 10, 2025)
