Automated Micro-Crack Detection within Photovoltaic Manufacturing Facility via Ground Modelling for a Regularized Convolutional Network

Abstract

The manufacturing of photovoltaic cells is a complex and intensive process involving the exposure of the cell surface to high temperature differentials and external pressure, which can lead to the development of surface defects, such as micro-cracks. Currently, domain experts manually inspect the cell surface to detect micro-cracks, a process that is subject to human bias, high error rates, fatigue, and labor costs. To overcome the need for domain experts, this research proposes modelling cell surfaces via representative augmentations grounded in production floor conditions. The modelled dataset is then used as input for a custom ‘lightweight’ convolutional neural network architecture for training a robust, noninvasive classifier, essentially presenting an automated micro-crack detector. In addition to data modelling, the proposed architecture is further regularized using several regularization strategies to enhance performance, achieving an overall F1-score of 85%.

Lightweight Convolutional Network with Integrated Attention Mechanism for Missing Bolt Detection in Railways

“…Lastly, the principles and methodologies developed in this study have implications beyond railway safety, suggesting broader applicability to other domains where safety and maintenance are concerns, such as in warehouse pallet detection [42], PV crack detection [43], aerospace component detection [44], automotive [45], and micro-cracks in equipment [46]. Investigating these cross-domain applications could not only broaden the impact of the current research but also drive innovation in the field of deep learning and its practical applications.…”