ABSTRACT
The quality of welds is critical to the safety of structures in construction, so early detection of irregularities is crucial. Advances in machine vision inspection technologies, such as deep learning models, have improved the detection of weld defects. This paper presents a new CNN model based on ResNet50 to classify four types of weld defects in radiographic images: crack, pore, non-penetration, and no defect. Stratified cross-validation, data augmentation, and regularization were used to improve generalization and avoid over-fitting. The model was tested on three datasets, RIAWELC, GDXray, and a private dataset of low image quality, obtaining an accuracy of 98.75 %, 90.255 %, and 75.83 %, respectively. The model proposed in this paper achieves high accuracies on different datasets and constitutes a valuable tool to improve the efficiency and effectiveness of quality control processes in the welding industry. Moreover, experimental tests show that the proposed approach performs well on even low-resolution images.
ABSTRACT
This research proposes a new index to evaluate the stability of the melting process, in three-phase electric arc furnaces (EAFs), based on the acoustic signals generated during the different stages of the casting. The proposed stability index is obtained by characterizing the time and frequency domain of the acoustic signals. During EAF monitoring, acoustic signals were acquired using a microphone coupled to an NI USB-9234 acquisition system. To validate the results, the voltage and current signals were measured with the aid of a Circutor AR6 power analyzer for three-phase electrical networks. The results showed that the acoustic signal energy in the frequency range of 1 to 12 kHz can be used as an indicator of the process stability in the EAF. Finally, the validity of the proposed stability index is evaluated from the process characterization using the harmonic distortion analysis methods and the dynamic U-I characteristics of the arc voltage and current signals. The results obtained demonstrated the effectiveness of the proposal and constitute a starting point for advances in the automatic control of the process in the EAF, from the acoustic signals.
ABSTRACT
Se efectuó una revisión bibliográfica para determinar el impacto de la mecatrónica en el sector de la salud. Se valoró el desarrollo de esta desde la visión de diferentes investigadores, lo cual ha permitido su inserción en dicho sector. También se comprobó que la robótica y el procesamiento digital de imágenes y señales tienen mayor incidencia en la medicina. Asimismo, se hizo un análisis de la mecatrónica aplicada a esta ciencia, el cual demostró que las áreas quirúrgica y terapéutica son las más favorecidas y se nutren de técnicas innovadoras, que resultan más fiables y menos invasivas para el paciente
A literature review was carried out to determine the impact of mechatronic in the health sector. Its development was evaluated from the point of view of different investigators, which has allowed its insertion in this sector. It was also proven that robotics and digital processing of images and signs have higher incidence in medicine. Also, an analysis of mechatronic applied to this science was carried out, which demonstrated that the surgical and therapeutical areas are the most favored and receive nourishment through innovative techniques that are more reliable and less invasive for the patient
Subject(s)
Humans , Male , Female , Robotics/methods , Electronics, Medical/instrumentation , Electrical Equipment and Supplies , Robotic Surgical Procedures , Health Systems , Electromagnetic Phenomena , Wearable Electronic Devices/statistics & numerical dataABSTRACT
Se efectuó una revisión bibliográfica para determinar el impacto de la mecatrónica en el sector de la salud. Se valoró el desarrollo de esta desde la visión de diferentes investigadores, lo cual ha permitido su inserción en dicho sector. También se comprobó que la robótica y el procesamiento digital de imágenes y señales tienen mayor incidencia en la medicina. Asimismo, se hizo un análisis de la mecatrónica aplicada a esta ciencia, el cual demostró que las áreas quirúrgica y terapéutica son las más favorecidas y se nutren de técnicas innovadoras, que resultan más fiables y menos invasivas para el paciente(AU)
A literature review was carried out to determine the impact of mechatronic in the health sector. Its development was evaluated from the point of view of different investigators, which has allowed its insertion in this sector. It was also proven that robotics and digital processing of images and signs have higher incidence in medicine. Also, an analysis of mechatronic applied to this science was carried out, which demonstrated that the surgical and therapeutical areas are the most favored and receive nourishment through innovative techniques that are more reliable and less invasive for the patient(AU)
