Search

The temperature rise of key internal components and ambient temperature changes during machining processes are the main causes of thermal displacement in machine tool spindle. This wastes materials and reduces working efficiency. A highly accurate and robust thermal spindle displacement estimation scheme is proposed in this paper which is based on the convolutional neural network (CNN) technique. Several key signals of specific dimensions related to spindle thermal displacement were first collected as two-dimensional (2D) signal maps. A multi-level feature expression for these 2D signal maps was extracted using convolution and pooling. A relationship between the extracted features and spindle thermal displacement was then learned using the neural architecture of the full connection layer. Optimized hyperparameter settings were determined by design of experiments (DoE) applied to the proposed CNN model. Experimental results showed that the proposed method had better performance than the multiple regression analysis (MLR) or back propagation neural network (BPNN) methods in terms of estimation accuracy and robustness at different spindle speeds. [ABSTRACT FROM AUTHOR]

Silicon nanowire possesses great potential as the material for renewable energy harvesting and conversion. The significantly reduced spectral reflectivity of silicon nanowire to visible light makes it even more attractive in solar energy applications. However, the benefit of its use for solar thermal energy harvesting remains to be investigated and has so far not been clearly reported. The purpose of this study is to provide practical information and insight into the performance of silicon nanowires in solar thermal energy conversion systems. Spectral hemispherical reflectivity and transmissivity of the black silicon nanowire array on silicon wafer substrate were measured. It was observed that the reflectivity is lower in the visible range but higher in the infrared range compared to the plain silicon wafer. A drying experiment and a theoretical calculation were carried out to directly evaluate the effects of the trade-off between scattering properties at different wavelengths. It is clearly seen that silicon nanowires can improve the solar thermal energy harnessing. The results showed that a 17.8 % increase in the harvest and utilization of solar thermal energy could be achieved using a silicon nanowire array on silicon substrate as compared to that obtained with a plain silicon wafer. [ABSTRACT FROM AUTHOR]