Moez Krichen

The detection of weld defects by using X-rays is an important task in the industry. It requires trained specialists with the expertise to conduct a timely inspection, which is costly and cumbersome. Moreover, the process can be erroneous due to fatigue and lack of concentration. In this context, this study proposes an automated approach to identify multi-class welding defects by processing the X-ray images. It is realized by an intelligent hybridization of the data augmentation techniques and convolutional neural network (CNN). The proposed data augmentation mainly performs random rotation, shearing, zooming, brightness adjustment, and horizontal flips on the intended images. This augmentation is beneficial for the realization of a generalized trained CNN model, which can process the multi-class dataset for the identification of welding defects. The effectiveness of the proposed method is confirmed by testing its performance in processing an industrial dataset. The intended dataset contains 4479 X-ray images and belongs to six groups: cavity, cracks, inclusion slag, lack of fusion, shape defects, and normal defects. The devised technique achieved an average accuracy of 92%. This indicates that the approach is promising and can be used in contemporary solutions for the automated detection and categorization of welding defects.

This work aims to create a web-based real-time monitoring system for electrical energy consumption inside a specific residence. This electrical energy is generated from a micro-CPV system lying on the roof of this residence. The micro-CPV is composed of a Fresnel lens as the main optical element, a spherical lens as the secondary optical element, and a multi-junction solar cell. A tiny photovoltaic concentrator system with a geometric concentration ratio of 100× is analyzed in the first part of this study, while the second part is designed to monitor the electricity generated by the micro-CPV system. An ESP8266 controller chipset is used to build the sensing peripheral node, which controls a relay and a PZEM-004T current sensor. As a result, the optical element used has approximately 83% optical efficiency, with an acceptance angle of 1.5°. Regarding the monitoring system, the architecture demonstrates the ability of the system to monitor current and energy consumption in real time using a computer or smartphone and a web server specially designed to continuously update the power consumption profile in a specific smart home environment. The whole electric power consumption monitoring system generally worked well. The monitoring system is configured to provide excellent accuracy for a 0.6% hit.