Bulk nanocrystalline Al prepared by cryomilling

Bulk nanocrystalline Al was fabricated by mechanically milling at cryogenic temperature （cryomilling） and then by hot pressing in vacuum. By using X-ray diffraction （XRD）, scanning electron microscopy （SEM）, and transmission electron microscopy （TEM）, the microstructure evolution of the material during cryomilling and consolidation was investigated. With increasing the milling time, the grain size decreased sharply and reduced to 42 nm when cryomilled for 12 h. The grains had grown up, and the columnar grain was formed under the hot pressing and extrusion compared with the cryomilled powders. The grain size of as-extruded specimen was approximately 300-500 nm. The reason of high thermal stability of this bulk was attributed primarily to the Zener pinning from the grain boundary of the AlN arising from cryomilling and the solute drag of the impurity. Tensile tests show that the strength of nanocrystalline Al is enhanced with decreasing grain size. The ultimate tensile strength and tensile elongation were 173 MPa and 17.5%, respectively. It appears that the measured high strength in the cryomilled Al is related to a grain-size effect, dispersion strengthening, and dislocation strengthening.

An adaptive data-driven method for accurate prediction of remaining useful life of rolling bearings

A novel data-driven method based on Gaussian mixture model （GMM） and distance evaluation technique （DET） is proposed to predict the remaining useful life （RUL） of rolling bearings. The data sets are clustered by GMM to divide all data sets into several health states adaptively and reasonably. The number of clusters is determined by the minimum description length principle. Thus, either the health state of the data sets or the number of the states is obtained automatically. Meanwhile, the abnormal data sets can be recognized during the clustering process and removed from the training data sets. After obtaining the health states, appropriate features are selected by DET for increasing the classification and prediction accuracy. In the prediction process, each vibration signal is decomposed into several components by empirical mode decomposition. Some common statis- tical parameters of the components are calculated first and then the features are clustered using GMM to divide the data sets into several health states and remove the abnormal data sets. Thereafter, appropriate statistical parameters of the generated components are selected using DET. Finally, least squares support vector machine is utilized to predict the RUL of rolling bearings.Experimental results indicate that the proposed method reliably predicts the RUL of rolling bearings.