No abstract

This paper presents our new rotating machinery library. Diagnosing the complex system accurately based on stochastic method requires an enormous amount of data, both with and without faults. Acquiring operation data with all kinds of faults for each components is very hard and costly. To generate data for rotating machinery diagnosis, we developed rotating machinery library using Modelica. It provides the basic components such as rotor, shaft, bearing, coupling, housing and support. Its component models are implemented on basis of rotor dynamics theory. This library makes it possible accessing rotating machinery operation data with various faults such as unbalanced rotor, shaft bending and ball bearing faults. To validate our models, we compared both Modelica simulation and experiment with a rotor kit as a test case.

Purpose: To develop a deep convolutional neural network (DCNN)‐based computer‐aided diagnosis (CAD) system for detecting the masses in digital mammographic images. Methods: A DCNN architecture, which consists of 5 convolutional layers and 3 fully connected layers, is constructed in this study. The DCNN parameters are then trained by the following two procedures. We first train the DCNN using about 1.3 million natural images for classification of 1,000 categories. Then, we modify the last fully connected layer and subsequently train the modified DCNN using 1,656 mammographic region of interest (ROI) images for two categories classification: mass and normal. Results: The trained DCNN is tested by using 198 mammographic ROI images including 99 mass images and 99 normal images. The experimental results show that the sensitivity of the mass detection is about 89.9% and the false positive is 19.2%. These results demonstrated that the DCNN has a potential for mammographic CAD. Conclusion: In recent years, the DCNN, as one of the most successful techniques in deep learning technology, made a remarkable impact on image recognition application. For medical image recognition, however, its performance is uncertainty because collecting a large amount of training image data for a particularly medical image modality is difficult. In this study, our preliminary experiments demonstrated a feasibility to apply the DCNN in mammographic CAD system. To the best of our knowledge, this study is also the first demonstration of DCNN for detecting the masses in mammographic images.

No abstract

We have created the rotating machinery library to carry out analytical investigations for diagnosis by transfer matrix method in Modelica. In this paper, rubbing components for partial rub are implemented in our rotating machinery library. In this research, the model in which the rotor come into contact from a non-contact state by a pulsating external force is analyzed. The relationship between the contact configurations and the generation of various kinds of vibration is investigated. We validated the rubbing model in one side contact case with a rotor kit. By simulation, we reproduced the time history, the orbit and the full spectrum characteristics of the rotating shaft measured by the experiment precisely.