Gear transmission is widely used in mechanical equipment. In practice, if the gearbox is damaged, it not only affects the yield rate but also damages other parts of machines; thus, increases the cost and difficulty of maintenance. With the advancement of technology, the concept of unmanned factories has been proposed; an automatic diagnosis system for the health management of gearboxes becomes necessary. In this paper, a compound fault diagnosis system for the gearbox based on convolutional neural network (CNN) is developed. Specifically, three-axis vibration signals measured by accelerometers are used as the input of the one-dimensional CNN; the detection of the existence and type of the fault is directly output. In testing, the model achieved nearly 100% accuracy on the fault samples we captured. Experimental evidence also shows that the frequency-domain data can provide better diagnostic results than the time-domain data due to the stable characteristics in the frequency spectrum. For practical usage, we demonstrated a remote fault diagnosis system through a local area network on an embedded platform. Furthermore, optimization of convolution kernels was also investigated. When moderately reducing the number of convolution kernels, it does not affect the diagnostic accuracy but greatly reduces the training time of the model.

A blood-typing assay is a critical test to ensure the serological compatibility of a donor and an intended recipient prior to a blood transfusion. This article presents a lab-on-disc blood-typing system to conduct a total of eight assays for a patient, including forward-typing tests, reverse-typing tests, and irregular-antibody tests. These assays are carried out in a microfluidic disc simultaneously. A blood-typing apparatus was designed to automatically manipulate the disc. The blood type can be determined by integrating the results of red blood cell (RBC) agglutination in the microchannels. The experimental results of our current 40 blood samples show that the results agree with those examined in the hospital. The accuracy reaches 97.5%.

This study proposes a model-based force estimator with an adaptive tuner for a single active magnetic bearing suspended rotor system to eliminate the vibration associated with imbalance of mass. The adaptive tuner is added to the integral-typed observer to overcome the estimation error caused by the parameter uncertainty and the model uncertainty. Simulation results show that the adaptive estimation system is more accurate than the integral-type estimator, even though the system model has a 20% parameter error, and the feed-forward compensator can ameliorate the rotational accuracy in the operational range.

The article describes the effect of a magnetic field applied to a ferrofluid–lubricated hydrodynamic journal bearing–rotor system. A rotor with a single journal bearing in one end was built to be the test rig. The experimental results showed that 3 to 8 permanent magnets, arranged by different methods, can all increase the instability threshold of the oil bearing. Especially, the magnetic field formed by eight magnets has the optimal effect. The whirl speed and the whip speed can be increased from 3024 rpm to 4480 rpm, and from 3184 rpm to 5268 rpm.

Magnetic gel abrasive finishing is a high-precision polishing method that uses magnetic forces to attract and restrain a gel abrasive, composed of aqueous slime gel, steel grits, and silicon carbon (SiC), for polishing workpieces. However, the magnetic adsorption performance of the gel abrasive will drop quickly when polishing non-ferromagnetic material such as stainless-steel or brass. Moreover, centrifugal force will push out the gel abrasive from the machining surface reducing the stability of polishing. Therefore, this paper developed a rotating cylinder-based magnetic finishing setup to allow the gel abrasive and workpieces to tumble and rotate together during the polishing process. To make the gel abrasive produce irregular and complicated movement paths for improving the polishing performance, this study first analyzed and compared the average surface roughness and removed material weight of workpieces using three kinds of motor operating modes; a unidirectional trapezoidal wave mode, a bidirectional sine wave mode, and a bidirectional trapezoidal wave mode. After identifying the best motor operating mode, the study further compared the polishing characteristics using several SiC particle and steel grit sizes. The experimental results showed that the rotating cylinder driven using a bidirectional trapezoidal wave could obtain better results for average surface roughness and removed material weight than the other two operating modes, while use of the larger steel grit size also obtained improved results. However, different silicon carbide particle sizes did not have a significant impact on the polishing characteristics.