Since artificial intelligence (AI) was introduced into engineering fields, it has made many breakthroughs. Machine learning (ML) algorithms have been very commonly used in structural health monitoring (SHM) systems in the last decade. In this study, a vibration-based early stage of bolt loosening detection and identification technique is proposed using ML algorithms, for a motor fastened with four bolts (M8 × 1.5) to a stationary support. First, several cases with fastened and loosened bolts were established, and the motor was operated in three different types of working condition (800 rpm, 1000 rpm, and 1200 rpm), in order to obtain enough vibration data. Second, for feature extraction of the dataset, the short-time Fourier transform (STFT) method was performed. Third, different types of classifier of ML were trained, and a new test dataset was applied to evaluate the performance of the classifiers. Finally, the classifier with the greatest accuracy was identified. The test results showed that the capability of the classifier was satisfactory for detecting bolt loosening and identifying which bolt or bolts started to lose their preload in each working condition. The identified classifier will be implemented for online monitoring of the early stage of bolt loosening of a multi-bolt structure in future works.

Virtual surface characteristics of tactile displays are investigated to characterize the feeling of human touch for a haptic interface application. In order to represent the tactile feeling, a prototype tactile display incorporating Magneto-Rheological (MR) fluid has been developed. Tactile display devices simulate the finger’s skin to feel the sensations of contact such as compliance, friction, and topography of the surface. Thus, the tactile display can provide information on the surface of an organic tissue to the surgeon in virtual reality. In order to investigate the compliance feeling of a human finger’s touch, normal force responses of a tactile display under various magnetic fields have been assessed. Also, shearing friction force responses of the tactile display are investigated to simulate the action of finger dragging on the surface. Moreover, different matrix arrays of magnetic poles are applied to form the virtual surface topography. From the results, different tactile feelings are observed according to the applied magnetic field strength as well as the arrays of magnetic poles combinations. This research presents a smart tactile display technology for virtual surfaces.

Research on the applications of magneto-rheological (MR) elastomers in mechanical engineering has greatly expanded, whereas the performance of MR fluids in tribology has rarely been investigated. In this study, the tribological characteristics of an MR elastomer are identified in order to improve tribological performance with the activation of a magnetic field. Microscopic changes in the surface and in the MR particles are investigated. The friction and wear of an MR elastomer is measured using a pin-on-disc tester under applied and unapplied magnetic fields. In addition, the linear sliding friction of an MR elastomer with respect to different velocities and loads is measured using a linear sliding tester.