Presentation | 2017-08-24 Anomaly Detection from Subsampled Audio Signal for Machine Diagnosis Yohei Kawaguchi, Takashi Endo, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Low-cost sound monitoring is required for maintaining machinery. We aim to reduce the cost of monitoring by reducing the sampling rate, i.e., sub-Nyquist sampling. Monitoring based on sub-Nyquist sampling requires two sub-systems; a sub-system on-site for sampling machinery sound at a low rate, and a sub-system off-site for detecting anomalies from the subsampled signal. In this paper, to achieve both subsystems, we apply non-uniform sampling methods and propose an anomaly detection method based on a demultiplexer and an end-to-end LSTM autoencoder. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | machine maintenance system / sound monitoring / sound diagnosis / predictive maintenance / sub-Nyquist non-uniform sampling / end-to-end / long short-term memory (LSTM) / autoencoder |
Paper # | SIP2017-54 |
Date of Issue | 2017-08-17 (SIP) |
Conference Information | |
Committee | SIP |
---|---|
Conference Date | 2017/8/24(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Tokyo Denki University |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Masahiro Okuda(Univ. of Kitakyushu) |
Vice Chair | Shogo Muramatsu(Niigata Univ.) / Naoyuki Aikawa(TUS) |
Secretary | Shogo Muramatsu(Chiba Inst. of Tech.) / Naoyuki Aikawa(Takushoku Univ.) |
Assistant | Masayoshi Nakamoto(Hiroshima Univ.ひろ) |
Paper Information | |
Registration To | Technical Committee on Signal Processing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Anomaly Detection from Subsampled Audio Signal for Machine Diagnosis |
Sub Title (in English) | |
Keyword(1) | machine maintenance system |
Keyword(2) | sound monitoring |
Keyword(3) | sound diagnosis |
Keyword(4) | predictive maintenance |
Keyword(5) | sub-Nyquist non-uniform sampling |
Keyword(6) | end-to-end |
Keyword(7) | long short-term memory (LSTM) |
Keyword(8) | autoencoder |
1st Author's Name | Yohei Kawaguchi |
1st Author's Affiliation | Hitachi, Ltd.(Hitachi) |
2nd Author's Name | Takashi Endo |
2nd Author's Affiliation | Hitachi, Ltd.(Hitachi) |
Date | 2017-08-24 |
Paper # | SIP2017-54 |
Volume (vol) | vol.117 |
Number (no) | SIP-180 |
Page | pp.pp.33-38(SIP), |
#Pages | 6 |
Date of Issue | 2017-08-17 (SIP) |