Threshold Learning from Samples Drawn from the Null Hypothesis for the Generalized Likelihood Ratio CUSUM Test

2006 ◽  
Author(s):  
C. Hory ◽  
A. Kokaram ◽  
W.J. Christmas
Keyword(s):  
Likelihood Ratio ◽  
Null Hypothesis ◽  
Cusum Test ◽  
Generalized Likelihood Ratio

scholarly journals THE DEVELOPMENT AND INVESTIGATION ANALYSIS OF AN ARX-BASED GENERALIZED LIKELIHOOD RATIO (GLR) STICTION DETECTION METHOD

2018 ◽  
Vol 80 (4) ◽  
Author(s):  
Nur Amalina Shairah Abdul Samat ◽  
Haslinda Zabiri ◽  
Bashariah Kamaruddin
Keyword(s):  
Case Studies ◽  
Likelihood Ratio ◽  
Null Hypothesis ◽  
Detection Method ◽  
Detection Methods ◽  
Statistical Hypothesis ◽  
Decision Threshold ◽  
Statistical Hypothesis Testing ◽  
Generalized Likelihood Ratio ◽  
Significance Level

Control valve stiction is one of the main sources of nonlinearity which can result in many deleterious effects on the control loop performance of a process. The study of stiction detection methods has now becoming one of the essential research areas in process control. In this present work, an ARX-based Generalized Likelihood Ratio (GLR) stiction detection method is proposed and its effectiveness is analyzed. The implementation of the proposed method involves three main stages; 1) ARX model identification, 2) GLR test, and 3) statistical hypothesis testing. The proposed detection method was applied to two benchmark simulated case studies. Results showed that the method effectively detect stiction. The presence of stiction is declared if the GLR test statistics,  exceeds the decision threshold limit, , and the null hypothesis is rejected at 5% significance level. On the other hand, if  value lies below , the null hypothesis is accepted and the absence of stiction is confirmed. In addition, it is also observed that the proposed method is reasonably insensitive and robust to the changes in the process gain,  and time constant,  as it generally allows up to ±10% changes in the two parameters for both case studies.

Fault Detection in Linear Discrete Dynamic Systems by a Pattern Recognition of a Generalized-Likelihood-Ratio

1990 ◽  
Vol 112 (2) ◽  
pp. 276-282 ◽  
Author(s):  
S. Tanaka ◽  
P. C. Mu¨ller
Keyword(s):  
Pattern Recognition ◽  
Likelihood Ratio ◽  
Dynamic Systems ◽  
Abrupt Change ◽  
Detection Method ◽  
Discrete Dynamical System ◽  
Generalized Likelihood Ratio ◽  
Robust Detection ◽  
Chi Squared ◽  
Discrete Dynamic Systems

The detection of an abrupt change in the parameters of a linear discrete dynamical system is considered in the framework of the easily implemented generalized-likelihood-ratio (GLR) method. This paper proposes a robust detection method based on a pattern recognition of the maximum GLR provided by the conventional step-hypothesized GLR method. A numerical example demonstrates that the proposed method is highly superior to the conventional step-hypothesized GLR method and to the Chi-squared test in both detection rate and detection speed.

Sign in / Sign up

Export Citation Format

Share Document