Early fault diagnosis in complex mechanical systems such as gearbox has always been a great challenge, even with the recent development in deep neural networks. The performance of a classic fault diagnosis system predominantly depends on the features extracted and the classifier subsequently applied. Although a large number of attempts have been made regarding feature extraction techniques, the methods require great human involvements are heavily depend on domain expertise and may thus be non-representative and biased from application to application. On the other hand, while the deep neural networks based approaches feature adaptive feature extractions and inherent classifications, they usually require a substantial set of training data and thus hinder their usage for engineering applications with limited training data such as gearbox fault diagnosis. This paper develops a deep convolutional neural network-based transfer learning approach that not only entertains pre-processing free adaptive feature extractions, but also requires only a small set of training data. The proposed transfer learning architecture consists of two parts; the first part is constructed with a piece of a pre-trained deep neural network that serves to extract the features automatically from the input, the second part is a fully connected stage to classify the features that needs to be trained using gear fault experiment data. The proposed approach performs gear fault diagnosis using preprocessing free raw accelerometer data and experiments with various sizes of training data were conducted. The superiority of the proposed approach is revealed by comparing the performance with other methods such as locally trained convolution neural network and angle-frequency analysis based support vector machine. The achieved accuracy indicates that the proposed approach is not only viable and robust, but also has the potential to be readily applicable to other fault diagnosis practices.

In this research, the passive damping and active control authority of several basic active-passive hybrid piezoelectric networks are analysed and compared. The comparison is performed in a nondimensionalized manner, throughout which the importance of the generalized electro-mechanical coupling coefficient is highlighted. It is concluded that these configurations yield very similar open-loop performance for the same electro-mechanical coupling. It is shown that larger electro-mechanical coupling leads to higher passive network damping and, depending on the design and configuration, could also derive better active authority and overall performance. A method of increasing the electro-mechanical coupling coefficient by using a negative capacitance circuit is proposed, analysed and experimentally verified.

No abstract

No abstract

No abstract