Estimating Recycling Return of Integrated Circuits Using Computer Vision on Printed Circuit Boards

Abstract

The technological growth of the last decades has brought many improvements in daily life, but also concerns on how to deal with electronic waste. Electrical and electronic equipment waste is the fastest-growing rate in the industrialized world. One of the elements of electronic equipment is the printed circuit board (PCB) and almost every electronic equipment has a PCB inside it. While waste PCB (WPCB) recycling may result in the recovery of potentially precious materials and the reuse of some components, it is a challenging task because its composition diversity requires a cautious pre-processing stage to achieve optimal recycling outcomes. Our research focused on proposing a method to evaluate the economic feasibility of recycling integrated circuits (ICs) from WPCB. The proposed method can help decide whether to dismantle a separate WPCB before the physical or mechanical recycling process and consists of estimating the IC area from a WPCB, calculating the IC’s weight using surface density, and estimating how much metal can be recovered by recycling those ICs. To estimate the IC area in a WPCB, we used a state-of-the-art object detection deep learning model (YOLO) and the PCB DSLR image dataset to detect the WPCB’s ICs. Regarding IC detection, the best result was obtained with the partitioned analysis of each image through a sliding window, thus creating new images of smaller dimensions, reaching 86.77% mAP. As a final result, we estimate that the Deep PCB Dataset has a total of 1079.18 g of ICs, from which it would be possible to recover at least 909.94 g of metals and silicon elements from all WPCBs’ ICs. Since there is a high variability in the compositions of WPCBs, it is possible to calculate the gross income for each WPCB and use it as a decision criterion for the type of pre-processing.

Enhancing EfficientNet-YOLOv4 for Integrated Circuit Detection on Printed Circuit Board (PCB)

“…YOLOv3 stands out over YOLOv2 primarily due to its Feature Pyramid Network (FPN) architecture, facilitating multi-scale prediction and effective small object detection [12]. Silva et al [13] employed a pretrained YOLOv3 model, fine-tuned using the PCB DSLR dataset [14], to detect ICs in waste PCBs, facilitating their recycling process. Addressing the concern of missing components in PCB assembly, Khare et al [15] proposed a solution involving object detection, image subtraction, and pixel manipulation to mitigate the issue of absent components within PCBs.…”

“…In this study, YOLOv4, by default, uses a set of nine anchor sizes for 416 input size: 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326, which encompasses various scales and aspect ratios and is also termed the anchor size set of YOLOv3. Additionally, the study explores another set of anchor sizes (13,31,21,42,31,15,34,58,51,29,57,98,78,48,150,118,255,323) derived from [2]. This alternative anchor size set is tailored explicitly from a dataset of PCB electronic components.…”

Multi-Layer Ceramic Capacitors in Lighting Equipment: Presence and Characterisation of Rare Earth Elements and Precious Metals

“…Gd, Ho, and Sm showed small to insignificant differences ranging between 0.40 and 2.10% as a function of the acids used. Due to the nature of the sample, the low concentration of Au may be explained as (a) its main use in electrical-electronic equipment focuses on the internal structure of the integrated circuits and the protection of electrical contacts from environmental conditions such as oxidation; and (b) MLCCs in gold-plated terminals are used in specific and high-cost applications, so their potential presence in the sample is minimal, with external LED drivers and LME being the most likely origin [12,19,73]. Increased concentrations of Ag and Pd may be explained as multi-layer ceramic capacitors being one of the main electrotechnical applications of Ag and, simultaneously, the main electrotechnical application of Pd.…”

“…In particular, the presence of significant quantities of precious metals with a high economic value supports the effort to recover them from urban mines and the viability of recycling plants. It is worth noting that, for the year 2019, the stored mass of specific precious metals in e-waste corresponded to Ag 1200 t, Au 200 t, Ir 1 t, Ru 0.3 t, and Pd 100 t [2,[11][12][13][14][15][16][17][18][19][20].…”

Hydrometallurgical Recycling Process for Mobile Phone Printed Circuit Boards Using Ozone

“…In other studies [5,6], hazardous cadmium, arsenic, chromium, and antimony were also identified in PCBs. The total composition of printed circuit boards has been analyzed by many researchers [7][8][9][10][11][12]. PCBs usually contain 40% metals, 30% plastics, and 30% ceramic materials, although their actual composition varies depending on the intended use of the device.…”