A method of Fault Diagnosis of non-Gaussian Property and Performance Correlation Based on Independent Component Analysis

Song, Yu; Yang, Sheng; Cheng, Chao

doi:10.1109/iai50351.2020.9262197

Cited by 3 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Upon the determination of the contribution of the stages, the PFCs contribution within the stage are to be determined. The contribution of the responsible characteristic(s) to the I 2 monitoring statistic can be obtained using equation (14) [13]…”

Section: Fault Diagnosis: Determination Of Relative Contribution Of Pfcsmentioning

confidence: 99%

“…PFC observations pertaining to complex chemical processes [6,7] are instances of cases where the data deviate appreciably from normality and employment of Gaussian variant of multivariate projection based techniques for process monitoring may lead to heightened number of false alarms. Recent developments on non-Gaussian process monitoring techniques are largely based on Independent Component Analysis (ICA) [8][9][10][11][12][13][14][15], Support Vector Data Description (SVDD) [16][17][18][19][20][21] and Gaussian Mixture Model (GMM) [22][23][24][25][26]. ICA is a non-Gaussian technique for transforming observed multivariate statistical data into statistically Independent Components (ICs), which are expressed as linear combination of observed variables.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A stage-wise non-Gaussian statistical process control strategy

Mishra

Das²

2023

Eng. Res. Express

View full text Add to dashboard Cite

The article delves into the development of a Non-Gaussian Process Monitoring Strategy for a Copper Cathode Manufacturing Unit (CCMU). The monitoring strategy being devised highlighted the issue of multi-stage process monitoring via the usage of Multi-block Independent Component Analysis (MBICA) techniques. MBICA is the multi-block variant of ICA technique which is prevalently used for process laden with non-Gaussian or non-normal data. Development of the monitoring strategy involved detection of fault(s) and their subsequent diagnosis. Detection of fault(s) was carried out by employment of I2 control chart whose control limit was established via Bootstrap procedure. The diagnosis of the detected fault was carried out by employment of fault diagnostic statistic. An amalgamation of MBICA and Multivariate Exponentially Weighted Moving Average (MEWMA) are also known as MBICA-MEWMA approach was also proposed for detection of incipient fault(s). The monitoring strategy thus developed was showcased for a CCMU which specialised in the manufacture of copper cathode which has got varied practical applications. The monitoring strategy thus devised was able to detect and diagnose the faults with appreciable accuracy.

show abstract

Section: Fault Diagnosis: Determination Of Relative Contribution Of Pfcsmentioning

confidence: 99%