A Bayesian network approach to root cause diagnosis of process variations

This thesis demonst rates a real time automated hybrid method for process monitoring. Motivation of this research comes from the fact that there is hardly any single techniques available which is decent enough for process fault detection and diagnosis simultaneously. Process history based methods are well known as early fault detectors but operators require complex analysis t o find out the root cause of the fault.Knowledge based qualitative models are worthy for root cause analysis but mostly done in off-line fashion. Moreover, modern processes are equipped with thousands of variables and structurally they are very complex in nature. All these influences make manual diagnostic task more complicated for the operators. T herefore, there is a need for automated process monitoring tool that has good detection and diagnosis performance.In this work, a hybrid method based on principal component analysis (P CA) and Bayesian belief network (BBN) is described for process monitoring. P CA is very profi cient as early faul t detector but not for faul t diagnosis. On the ot her hand , BBN is good for diagnosis. This hybrid method combines t he strong features of both P CA and BBN to an a utomated monitoring system that can detect fault early as well as diagnose the root cause precisely. Upon successful detection of fault from PCA, diagnostic information from t he P CA is passed to the BBN for root cause analysis.Pearl's message passing algorithm is used for belief updating. T his monitoring tool 11 integrates prior process knowledge along with the present observed evidence processed by the multivariate sta tistical method to come up with the most probable explanation of process fault. Efficacy of t he proposed method is verified by simulating different scenarios on a simulated dissolution tank model. The monitoring tool is also validated using indust rial data from a pure terephthalic acid (PTA) plant .iii Acknowledgements Foremost, I would like to express my sincere gratitude to my supervisor Dr. Syed A Imtiaz for all his generous help , support and valuable suggestions. Since the first day, he had been guiding me in this difficult voyage. There were t imes of frustration in research, when his patience, motivation, enthusiasm and immense knowledge provided me the right directions.

show abstract

“…Dey, 2005] used BBN for fault diagnosis. Pearl's direct message passing algorithm was implemented to update probability of each node in BBN.…”

Section: Qualitative Knowledge Based Fddmentioning

confidence: 99%

A Hybrid Method for Process Fault Detection and Diagnosis

Mallick

Imtiaz

2013

IFAC Proceedings Volumes

View full text Add to dashboard Cite

show abstract

“…In spite of the potential use of BNs, their application in machining have been mainly focused on fault cause diagnosis and tool wear prediction (Dey and Stori, 2005). Recently, some authors have extended their application to surface roughness prediction since surface roughness tends to show an important stochastic behaviour.…”

Section: Bayesian Models Applied To Part Accuracy Predictionmentioning

confidence: 99%

“…Causal relationships can be also acquired by an ANOVA analysis as it is reported by Dey and Stori (2005).…”

Section: Guidelines For Bayesian Modellingmentioning

confidence: 99%

“…Above all probabilistic inferencing techniques, Bayesian Networks (BNs) are probably the most widely applied technique. A BN provides a convenient formalism for representing conditional probabilistic relationships between attributes of interest, modelling and evaluating uncertainty (Dey and Stori, 2005).…”

Section: Introductionmentioning

confidence: 99%

“…The directionality of the arrows is essential for displaying causality and non-transitive dependencies. The causal relationships expressed through the network structure and the conditional probability tables are based on prior knowledge, experience, or statistically observed correlations learnt from experimental data (Dey and Stori, 2005). The BN performance is based on propagation probabilities when it is known a specific variable state, called evidence.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A review of artificial intelligent approaches applied to part accuracy prediction

Abellán-Nebot

2010

IJMMM

View full text Add to dashboard Cite

Nowadays, despite the large volume of worldwide academic research on various aspects of metal cutting the control of workpiece precision still relies on machine-tool operator's experience and trial and error runs. In order to increase the efficiency of machining systems, many empirical models based on Artificial Intelligent (AI) approaches have been proposed in the past, where important process improvements were reported. This paper overviews the AI approaches applied in machining operations to predict part accuracy in terms of dimensional deviations and surface roughness. Successful techniques applied in this field such as Artificial Neural Networks, Fuzzy Logic, Adaptive-Network-based Fuzzy Inference Systems and Bayesian Networks are briefly reviewed and compared to facilitate its use. For each AI approach, the most relevant research works are described and based on those works some guidelines are proposed for its implementation. In addition, advantages and drawbacks of each approach are summarised and a generic guideline for AI approaches selection is proposed.

show abstract

A Bayesian approach for control loop diagnosis with missing data

Huang

Tamayo

2009

AIChE Journal

View full text Add to dashboard Cite

This article is concerned with determination of the underlying source of problematic control performance through a data-driven Bayesian approach. This approach synthesizes information from different monitoring algorithms to isolate possible problem sources. A main issue encountered in the application of the data-driven approach is the problem of missing data or missing monitor reading. By introducing the concept of missing pattern, data missing problems are classified into single and multi missing patterns. A novel method based on marginalization over underlying complete evidence matrix is proposed to circumvent missing data problems. Performance of the proposed Bayesian approach is examined through simulations as well as an industrial application example to verify its ability of information synthesis. V V C 2009 American Institute of Chemical Engineers AIChE J, 56: 179-195, 2010

show abstract

A Bayesian network approach to root cause diagnosis of process variations

Cited by 151 publications

References 49 publications

A Hybrid Method for Process Fault Detection and Diagnosis

A Hybrid Method for Process Fault Detection and Diagnosis

A review of artificial intelligent approaches applied to part accuracy prediction

A Bayesian approach for control loop diagnosis with missing data

Contact Info

Product

Resources

About