Kazufumi Nomura

In a single bevel GMAW (gas metal arc welding) with gap fluctuation, a deep learning model was constructed using the monitoring image during the welding to predict the welding quality. We utilized Python and the library Keras and created a CNN (Convolutional neural network) model using the top surface image including the molten pool as an input. The classification model was used to predict the burn-through, and the regression model was used to estimate the penetration depth. As a result, the exc

The shape of arc plasma in gas-shielded arc welding is an important factor for the quality and efficiency of the welding. The arc plasma changes its shape by an external magnetic field because the arc is a flow of electricity and is subjected to the electromagnetic force. In this study, we examined the control of arc plasma by a cusp-type magnetic field. The field produces a high and low magnetic area alternatively, and changes the cross-section of the arc plasma from a circular to an elliptical

Understanding the joining process in real time during welding can help improve welding quality, reliability, and manufacturing process efficiency. For this purpose, a laser ultrasonic method that can detect in situ welding quality without contact during welding would be useful. However, the behaviors of ultrasonic propagation as well as melting and joining with increasing temperature remain unclear. Therefore, this study aimed to experimentally investigate the in-process ultrasonic behavior when

Measurements of arc plasma are important for determining the associated physical properties. Such measurements usually involve the use of spectroscopic techniques to measure temperature distribution in free-burning arcs. Most studies have reported the temperature of axially symmetric arc plasma using Abel inversion. This method cannot be used for axially asymmetric arc plasma such as two-electrode TIG arc plasma. It is a complex phenomenon because the arc plasma generated from each electrode is

In manufacturing industry, in-process monitoring for quality assurance during the welding process is emerging. Conventional ultrasonic testing can be conducted only post-process because of the requirement of contact to target material where still hot in case during the welding process. Therefore, we employed a laser ultrasonic technique (LUT), which can be applied to a high temperature field like the welding process. In this study, we investigated the detectability of solidification cracks at si

Blowholes caused by vaporization of the galvanized layer are a problem with galvanized steel sheets, which use lap joint welding. The laser ultrasonic method is the possible solution to realize the desirable 100% inspection instead of the conventional sampling inspection. We have previously proposed a method to detect blowholes by capturing the reduction in ultrasonic intensity when it passes through internal defects through signal processing. However, there was a problem that the detection indi

Measurements of arc plasma are important for determining the associated physical properties. Such measurements usually involve the use of spectroscopic techniques to measure temperature distribution in free-burning arcs. Most of the studies have reported the temperature of axially symmetric arc plasma using Abel inversion. This method cannot be used for axially asymmetric arc plasma such as two-electrode TIG arc plasma. It is complex phenomenon because the arc plasma generated from each electrod

A shape of arc plasma in gas shielded arc welding is an important factor for the quality and efficiency of the welding. The arc plasma changes its shape by an external magnetic field because the arc is a flow of electricity and is subjected to the electro magnetic force. In this study, we examined the control of arc plasma by a cusp type magnetic field. The field produces a high and low magnetic area alternatively, and changes the cross section of the arc plasma from a circular to an elliptical