Search

Various nondestructive testing (NDT) methods have been proposed to detect defects inside products. The hammering test is an NDT technique widely used for this purpose. In this test method, a worker judges whether a part is defective or not by listening to the sound after hitting the product with a hammer. Conventional research has shown that a classifier using machine learning can discriminate the hammering data with high accuracy. However, to use these machine learning methods, a lot of samples are needed for learning. In actual industrial situations, it is difficult to collect a lot of samples of defective products. Regarding the hammering test, a machine learning method that can correctly discriminate defective products without sample data has not been proposed. This study aims to construct a system that can correctly discriminate the hammering test data even when there are no defective samples. We propose a method using 'transfer learning.' We conducted case studies to demonstrate the effectiveness of the proposed method using two variants of a brazed product. First, we verified the effectiveness of normal machine learning in a hammering test. In this study, we succeeded in discriminating brazed products, which were not correctly discriminated by the workers. We then applied the proposed method to brazed products. We succeeded in discriminating a variant of the brazed products by transferring the knowledge learned from another variant of the brazed products. [ABSTRACT FROM AUTHOR]

Sit-to-stand motion is an important daily activity, and disability of motion can significantly reduce quality of life. Therefore, it is important to understand the mechanism of sit-to-stand motion in order to prevent such scenarios. The sit-to-stand motion was found to be generated by four muscle groups, through muscle synergy. However, it is unclear how muscle synergy can be controlled. Human sit-to-stand motion may be planned based on body condition before motion. In this study, we aimed to clarify the relationship between body condition and muscle activity during the sit-to-stand motion. Accordingly, we measured the muscle activity when knee movability was disturbed as a condition of body change. We also measured the muscle activity during normal sit-to-stand motion and sit-to-stand motion with disturbed knee movability using surface electromyography. Subsequently, we extracted the muscle synergy from the measured muscle activity and compared the activity levels of muscle synergy. The results revealed that muscle activity contributing to forward bending increased and that contributing to the rise of the hip and stabilization decreased when knee movability was disturbed. These results suggest that humans compensate for disturbed knee movability with forward momentum and bending motion. Moreover, this implies that humans adjust their motion to various environments or body conditions by adjusting the level of forward bending activity. [ABSTRACT FROM AUTHOR]