Energy Optimized AI Based O-Ring Defect Detection for Sustainable Manufacturing

The integration of Artificial Intelligence (AI) and Machine Learning (ML) presents a paradigm shift for enhancing sustainability within the textile industry. This review examines the transformative potential of these technologies in fostering a circular economy, with a focus on material design, process optimisation, and end-of-life solutions. It surveys applications across textile science, from natural fibre composites to technical and smart textiles, highlighting the role of predictive modelling and ML algorithms—including neural networks, convolutional neural networks (CNNs), and random forests. These techniques are demonstrated to enhance the design of fibre-based materials, predict key properties such as tensile strength and thermal stability, and optimise manufacturing processes like dyeing and weaving. Furthermore, the review explores the significant contribution of computer vision to automated quality control, defect detection, and the assessment of garment condition for resale, thereby supporting circular business models. A central theme is the capacity of AI to drive sustainability by enabling zero-waste pattern design, improving colour prediction accuracy to reduce chemical waste, and advancing automated textile sorting for recycling. Despite this promising progress, the principal challenges identified are not algorithmic but systemic, relating to data scarcity, integration complexities, and the need for cross-sector collaboration. The review concludes by identifying critical future research directions, emphasising the need for robust, physics-informed models, the collaborative development of larger, more diverse datasets, and AI-driven Design for Disassembly (DfD) to fully realise AI's potential in creating a more innovative, efficient, and sustainable textile industry. Keywords: Artificial Intelligence; Circular Economy; Textile Recycling; Predictive Modelling; Computer Vision; Sustainable Manufacturing

Printed Circuit Board (PCB) testing has traditionally relied on manual inspection methods, which are often timeconsuming, error-prone, and costly. These limitations result in longer processing times, increased production costs, and inconsistent quality assurance. To address these challenges, this paper proposes a Generative AI-Based PCB Testing (GABPT) system designed to automate defect detection and classification in PCBs. The system leverages high-resolution image acquisition, advanced AI-powered image processing, and classification algorithms to identify common defects such as scratches, missing holes, broken paths, mouse bites, short circuits, and absent conductors. Utilizing a Quad ARM Cortex-A72 processor, the system processes captured PCB images in realtime and delivers immediate feedback on defects. The GABPT system aims to reduce human error, accelerate the inspection process, and minimize testing costs. It emphasizes efficient image preprocessing, precise image analysis, and hardware-software integration for reliable defect detection. By automating PCB inspection, the proposed system enhances testing accuracy, promotes cost-effective production, and supports sustainable manufacturing practices, ultimately contributing to the delivery of higher-quality electronic products.

Printed Circuit Board (PCB) defect inspection is critical in electronics manufacturing, yet annotating large training sets is labor-intensive and costly. This paper proposes a semi-supervised PCB defect detection framework based on YOLOv5, which leverages a small labeled dataset and a larger pool of unlabeled images through an iterative self-training pipeline. A YOLOv5 detector is first trained on the limited labeled data, then used to generate pseudo-labels on unlabeled images; high-confidence detections are retained as defect annotations, and the model is retrained on the combination of labeled and pseudo-labeled data. This pseudo-labeling and retraining cycle is repeated for multiple iterations to progressively refine the detector. The approach is evaluated on a PCB defect dataset with 100 labeled and 1,000 unlabeled images, and shows significant gains over a fully supervised baseline. The proposed semi-supervised YOLOv5 achieves 91.6% mAP@0.5 with only 100 labeled images, outperforming both the baseline (87.0% mAP) and prior semi-supervised methods, while substantially improving recall and precision. The results demonstrate that the method effectively reduces annotation effort while maintaining high detection accuracy, providing a simple, confidence-thresholded self-training strategy for deploying PCB defect detectors under limited labeling resources. This work directly supports SDG 9 by enabling cost-efficient, high-accuracy AI-based PCB inspection that strengthens intelligent and sustainable manufacturing systems.