The failures of rolling bearings usually cause the breakdown of rotating machinery. Therefore, bearing fault diagnosis is receiving more and more attentions. In this paper, a new coding-statistic feature is proposed for bearing fault diagnosis. Firstly, a waveform coding matrix (WCM) is drawn from each signal using a coding algorithm then a statistical feature is extracted from the WCM with a pre-defined dictionary. Secondly, all statistical features are processed using two-dimensional principal component analysis (2DPCA) to reduce redundant information and dimensionality. Finally, a nearest neighbor classifier (NNC) is employed to classify the bearing faults. Two bearing fault classification problems are utilized to demonstrate the effectiveness of the proposed scheme. Experimental results show that an excellent performance could be accomplished with the proposed scheme.

No abstract

No abstract

A reverse process design method is established in this paper by reversely applying the Hodgson recrystallization models. The method allows a draft schedule to be designed according to the requirements of the resulting microstructure, and it is made up of the design equations of process parameters and the criteria-selected values of the parameters. First, the microstructural evolution is summarized as ve paths, and the temperature and strain are set to xed ranges according to the authors experience. The mathematical models of the other parameters for each evolution path are established by applying the Hodgson recrystallization models. Secondly, criteria are established to select suitable values as a better draft schedule from uncountable groups of values. Finally, some examples are given and experiments are carried out according to the method. Metallographic observations showed that the nal grain size was consistent with the design goals. The maximum relative error comparing the design goal was just 5.5%. These results prove that the method is suf ciently accurate and effective.