著者
松本 心 顔 玉玲 金城 寛 山本 哲彦
出版者
一般社団法人日本機械学会
雑誌
機械材料・材料加工技術講演会講演論文集
巻号頁・発行日
vol.2001, no.9, pp.355-356, 2001-11-02

In this paper, a diagnosis method for machine faults using a neural network based on autocorrelation coefficients of wavelet transformed signals is presented. It is important for factory engineers to accurately estimate machine faults. In conventional diagnosis methods, frequency analysis using the fast Fourier transform (FFT) has often been employed. Recently, wavelet transforms have been studied and applied to many signal-processing applications. Wavelet transforms are very useful because of characteristics of time-frequency analysis. In this paper, we propose an application of wavelet transforms to machine fault diagnosis. In order to apply wavelet transforms to machine fault diagnosis, we use autocorrelation coefficients of the wavelet transformed signal. In this research, it becomes clear that the autocorrelation coefficients, represent the different classes of machine states. For the automatic diagnosis, we trained a neural network to recognize three classes of machine states based on the autocorrelation coefficients of wavelet transformed signals. Simulation and experimental results show that the trained neural network could successfully estimate machine faults.
著者
堂田 邦明 牧野 武彦 張 華玲
出版者
一般社団法人 日本機械学会
雑誌
機械材料・材料加工技術講演会講演論文集
巻号頁・発行日
vol.2006, pp.109-110, 2006

Miniature parts are needed largely due to the development of mobile phones, PCs and medical products. As a first step of a research of micro/meso-scale form rolling, the equipment is designed and manufactured. For characterizing the deformation during forming grooves on micro pins, two directional mark-off lines on the surface of pins were used. The change in the diameter, displacement in axial direction and twisting at circumferential direction is measured from the experiments.
著者
古屋 泰文 岡崎 禎子 上野 孝史 Chung Lee Gyun Spearing Mark Hagood N.
出版者
一般社団法人日本機械学会
雑誌
機械材料・材料加工技術講演会講演論文集
巻号頁・発行日
vol.2004, no.12, pp.19-20, 2004-11-05

The possibility to detect the phase transformation of stress-induced martensite in ferromagnetic shape memory alloy Fe-30.2at%Pd thin foil was investigated by using Barkhausen noise (BHN) method. Stress-induced martensite twin was observed by laser microscope above loading stress of 25 MPa. BHN caused by grain boundaries appears in the lower frequency range and BHN by martensite twin in the higher frequency range. The envelope of the BHN voltage as a function of time of magnetization shows a peak due to austenite phase at weak magnetic field. The BHN envelope due to martensite twins creates additional two peaks at intermediate magnetic field. BHN method turns out to be a powerful technique for non-destructive evaluation of the phase transformation of ferromagnetic shape memory alloy.
著者
上村 直嵩 大久保 通則
出版者
一般社団法人日本機械学会
雑誌
機械材料・材料加工技術講演会講演論文集
巻号頁・発行日
vol.2006, no.14, pp.133-134, 2006-11-25

Aluminum is superior in lightness, corrosion resistance, a strength characteristic, property to being processed in comparison with other metal. In addition, I am used as a use of various fields by adding various addition elements, and in late years the consumption is a rise course as metal helping resource saving/energy saving. This article used 2107 sheet aluminum alloy which I put GTA welding, plasma welding, YAG laser welding, disk laser welding for and performed a tension test, drop test. And I weighed data 2017 which I demanded against a basic material and each welding method and clarified a mechanical property and a shock characteristic of a welding coupling. In addition, welding was stable by stack welding and used filler A5356-BY which there was for welding room because it was not possible. In addition, I matched the strength characteristic that I put a filler in and examined.