A Method of Detecting Abnormal Signals using Statistical Analysis for Residual Sequence of AR Model Estimation Error.
-
- Hanakuma Yoshitomo
- Production Technology Center, Idemitsu Petrochemical Co., Ltd.
-
- Nakaya Kazutoyo
- Production Technology Center, Idemitsu Petrochemical Co., Ltd.
-
- Takeuchi Kenji
- Production Technology Center, Idemitsu Petrochemical Co., Ltd.
-
- Sasaki Takashi
- Electricity & Instrumentation Section, Idemitsu Engineering Co., Ltd.
-
- Nakanishi Eiji
- Department of Chemical Engineering, Kansai University
Bibliographic Information
- Other Title
-
- 自己回帰モデルの推定残差列統計量解析を用いた異常信号の検出法
- ジコ カイキ モデル ノ スイテイ ザンサレツ トウケイリョウ カイセキ オ
Search this article
Abstract
A method of detecting abnormal process signals in fault diagnosis using statistical analysis for the residual sequence of an AR model estimation error by recursive maximum likelihood method is developed. It involves white noise tests for the residual sequence of an AR model estimation error by the recursive maximum likelihood method using a logarithmic likelihood function and an integrated square of the autocorrelation function. The method proposed in this study has the advantage of detecting online abnormal signals in industrial use. It was applied to abnormal detection of the catalyst feed flow in a linear low-density polyethylene plant to confirm the design philosophy. The actual result indicates that the proposed method is effective in detecting abnormal process signals.
Journal
-
- KAGAKU KOGAKU RONBUNSHU
-
KAGAKU KOGAKU RONBUNSHU 22 (6), 1289-1293, 1996
The Society of Chemical Engineers, Japan
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282679486905600
-
- NII Article ID
- 10002669821
-
- NII Book ID
- AN00037234
-
- ISSN
- 13499203
- 0386216X
-
- NDL BIB ID
- 4078142
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed