Online citations, reference lists, and bibliographies.
← Back to Search

Framework For Enhancing Fault Diagnosis Capabilities Of Artificial Neural Networks

A. Farell, S. D. Roat
Published 1994 · Engineering

Cite This
Download PDF
Analyze on Scholarcy
Share
Abstract Neural networks have demonstrated excellent performance in facilitating automatic fault detection and diagnosis in many engineering applications. Their primary advantage over model-based and knowledge-based expert systems is that they require very little development time or expertise. However, neural networks perform only as robustly as the data from which they are trained. Therefore, understanding the content and limitations of process data used to train the network is crucial. This paper presents neural networks as part of a fault recognition framework for diagnosing process inefficiencies. In this framework, incorporating a small amount of process knowledge helps minimize data limitations and maximize the neural network's performance. Data preprocessing and filtering lead to significant improvement in recognition performance and markedly reduced training time. In addition, the framework allows detection of the “unknown” class. The fault recognition framework will be demonstrated via a simulated continuous stirred tank reactor system which operates under realistic disturbances and noisy measurements.



This paper is referenced by
10.23919/IConAC.2017.8082043
NARX models for prediction of reheater fouling
S. Anitha Kumari (2017)
A Neural Network Approach to Dependent *Reliability Estimation.
Roya Javadpour (2001)
Neural Network-based Fault Diagnosis of Satellites Formation Flight
Shima Mousavi Mirak (2013)
10.1109/ETFA.2017.8247619
Comparison of deep neural network architectures for fault detection in Tennessee Eastman process
Gavneet Singh Chadha (2017)
10.1016/J.ENBUILD.2014.10.069
Robust model-based fault diagnosis for air handling units
T. Mulumba (2015)
10.1016/S0952-1976(99)00052-4
A case-based reasoning system for identifying failure mechanisms
T. Liao (2000)
10.1080/17458080903513284
Two modelling data analytical methods applied to optimise the preparation of norcantharidin chitosan nanoparticles
W. Zhang (2010)
10.1109/ICARCV.2006.345315
Fault Isolation Using Extrinsic Curvature of Nonlinear Fault Models
A. Vemuri (2006)
Fault Detection and Classification using Kalman Filter and Hybrid Neuro-Fuzzy Systems
A. Khoukhi (2012)
10.1016/S1350-6307(98)00055-7
An integrated database and expert system for failure mechanism identification: Part I—automated knowledge acquisition
T. Liao (1999)
10.1109/ICNN.1996.549139
A real-time recurrent learning network structure for dealing with missing sensor data
K. Meert (1996)
10.1177/0142331208092028
Extrinsic curvature-based fault isolation for multi-input—multi-output systems with non-linear fault models
K. Subbarao (2009)
10.2202/1542-6580.1119
A Hybrid Methodology For On-Line Process Monitoring
R. Kumar (2004)
10.1109/ACC.2007.4282918
Fault Isolation Using Extrinsic Curvature For Multi-Input-Multi-Output Systems With Nonlinear Fault Models
K. Subbarao (2007)
10.1109/TAI.1996.560460
Development of a pumping system decision support tool based on artificial intelligence
P. W. Ilott (1996)
Distributed Sensor Fault Diagnosis for Automated Highway Systems
H. Chen (2013)
10.1016/S0098-1354(02)00160-6
A review of process fault detection and diagnosis: Part I: Quantitative model-based methods
V. Venkatasubramanian (2003)
10.1016/S0098-1354(02)00162-X
A review of process fault detection and diagnosis: Part III: Process history based methods
V. Venkatasubramanian (2003)
10.1016/S0098-1354(97)87621-1
A hybrid ANN-ES system for dynamic fault diagnosis of hydrocracking process
J. Chen (1997)
obust model-based fault diagnosis for air handling units imothy
Mulumbaa (2014)
10.1109/NAFIPS.2011.5751925
Fault detection and classification using Kalman filter and genetic neuro-fuzzy systems
Haris M. Khalid (2011)
eve tofaPu ecision Support Tool Based o In~e~~~~~nce
P. W. Ilott (1996)
10.1016/j.compeleceng.2014.12.015
Hybrid computing techniques for fault detection and isolation, a review
A. Khoukhi (2015)
Fault Modeling , Detection and Classification using Fuzzy Logic , Kalman Filter and Genetic Neuro-Fuzzy Systems
H. Khalid (2011)
10.1243/0954408971529665
Fault diagnosis of pumping machinery using artificial neural networks
P. W. Ilott (1997)
Applications of arti fi cial neural networks for thermal analysis of heat exchangers e A review
M. Mohanraj (2015)
10.1016/S0954-1810(97)00021-6
A real-time recurrent learning network structure for data reconciliation
K. Meert (1998)
10.1016/B978-0-12-083030-5.50009-6
Classification: Fault Diagnosis and Feature Categorization
D. R. Baughman (1995)
Dynamic Modeling, Sensor Placement Design, and Fault Diagnosis of Nuclear Desalination Systems
Fan Li (2011)
10.1016/J.IJTHERMALSCI.2014.11.030
Applications of artificial neural networks for thermal analysis of heat exchangers – A review
M. Mohanraj (2015)
10.14288/1.0066158
Fault monitoring in hydraulic systems using unscented Kalman filter
Mohammad Sepasi (2007)
Data-based design of fault detection and isolation (FDI) systems
G. Astolfi (2013)
See more
Semantic Scholar Logo Some data provided by SemanticScholar