Dynamic fault detection and diagnosis using neural networks

Li, R.; Olson, J.H.; Chester, Daniel

doi:10.1109/isic.1990.128602

Cited by 15 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In mid 1980's, researchers in the area of process safety proposed a potential approach to detect and diagnose fault using neural network. Venkatasubramanian and Chan [5] were among the earliest researchers to apply ANN in PFD&D. Since then many researchers have studied the implementation of neural network in this area such as Li et al [6], Becraft and Lee [7] and Leung and Ramagnoli [8]. ANN was also used to perform several functions that might also be carried by integrating with other fault detection techniques such as knowledge based expert system [9].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…From heat exchanger (E100) to VLV 102 before pump around back to column. 6 From heat exchanger (E100) to VLV 100 before discharge to storage tank. 7…”

Section: Plant Modelmentioning

confidence: 99%

“…Moving window approach is used to track dynamic data and detect transient states of fault [6]. As shown in Figure 4, two separate windows move forward with time -at each time increment the windows move by ∆t, which is called the sampling rate.…”

Section: Ann Model Elementmentioning

confidence: 99%

See 2 more Smart Citations

Process Fault Detection Using Hierarchical Artificial Neural Network Diagnostic Strategy

Othman¹,

Ali²,

Kamsah³

2012

Jurnal Teknologi

View full text Add to dashboard Cite

Kertas kerja ini menerangkan mengenai kegunaan jaringan neural tiruan (ANN) untuk mengesan dan membaiki kesilapan dalam loji proses. Dalam penyelidikan ini, ANN menggunakan dua lapisan dalam strategi diagnostik hirarki. Lapisan pertama mengenal pasti nod di mana kesilapan bermula sementara lapisan kedua membahagikan kesilapan yang berlaku pada nod tertentu. Arkitek model ANN adalah berasaskan beberapa lapisan rangkaian suapan hadapan dan menggunakan algoritma luncuran belakang dalam skema latihan. Untuk mendapatkan konfigurasi ANN yang terbaik, analisis topologi dilakukan. Keberkesanan kaedah ini ditunjukkan oleh kajian kes melibatkan turus pemecahan asid lemak. Keputusan menunjukkan sistem ini berjaya mengesan kesilapan tunggal dan fana yang terdapat dalam proses tersebut. Kata kunci: Pengenalpastian dan diagnostik kesilapan proses, strategi diagnostik hirarki, jaringan neural tiruan, turus pemecahan asid lemak This paper focuses on the use of artificial neural network (ANN) to detect and diagnose fault in process plant. In this work, the ANN uses two layers of hierarchical diagnostic strategy. The first layer diagnoses the node where the fault originated and the second layer classifies the type of faults or malfunctions occurred on that particular node. The architecture of the ANN model is founded on a multilayer feed forward network and used back propagation algorithm as the training scheme. In order to find the most suitable configuration of ANN, a topology analysis is conducted. The effectiveness of the method is demonstrated by using a fatty acid fractionation column. Results show that the system is successful in detecting original single and transient fault introduced within the process plant model. Key words: Process fault detection and diagnosis, hierarchical diagnostic strategy, artificial neural network, fatty acid fractionation column

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

“…From heat exchanger (E100) to VLV 102 before pump around back to column. 6 From heat exchanger (E100) to VLV 100 before discharge to storage tank. 7…”

Section: Plant Modelmentioning

confidence: 99%

See 1 more Smart Citation

Process Fault Detection Using Hierarchical Artificial Neural Network Diagnostic Strategy

Othman¹,

Ali²,

Kamsah³

2012

Jurnal Teknologi

View full text Add to dashboard Cite

show abstract

“…A moving window is an indispensable technique to track dynamic data and widely used for on-line fault diagnosis [5], [6], [10]. Usually it is important to select the proper time span of the moving window for fault diagnosis, which is the product of the sampling 'number (window length) in each moving window and time increment (sampling rate).…”

Section: Structure Of the Variable Moving Window Based Fault Diagnosimentioning

confidence: 99%

“…Large window sizes can consider more information, but may lead to large time delays for the classification of various process operating conditions. In most cases [5], [6],[10], after the time span of the moving is selected, it may not be changed any more. The length of the moving window can be changed with time, if HMM is used for classification.…”

Section: Structure Of the Variable Moving Window Based Fault Diagnosimentioning

confidence: 99%

A variable moving window approach for on-line fault diagnosis in industrial processes

Zhou

Xie

Wang

Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788)

View full text Add to dashboard Cite

Although there are many literatures on process online fault diagnosis, the moving window of fixed length is used in most of cases. In this study, an approach based on hidden Markov model (HMM) for on-line fault diagnosis in industrial processes is proposed. A variable moving window, the length of which is modified with time, is applied to track process dynamic variables. Before fault diagnosis, the process operating condition is monitored using principal component analysis (PCA) until abnormal operation in the process is detected. Case studies from the Tennessee Eastman plant illustrate that the proposed method is effective. Index Terms -fault diagnosis; hidden Markov model; variable moving window; principal component analysis; Tennessee Eastman plant.

show abstract

Intelligent Patient Monitoring in the Intensive Care Unit and the Operating Room

Jones

2005

Intelligent Knowledge-Based Systems

View full text Add to dashboard Cite

Dynamic fault detection and diagnosis using neural networks

Cited by 15 publications

References 4 publications

Process Fault Detection Using Hierarchical Artificial Neural Network Diagnostic Strategy

Process Fault Detection Using Hierarchical Artificial Neural Network Diagnostic Strategy

A variable moving window approach for on-line fault diagnosis in industrial processes

Intelligent Patient Monitoring in the Intensive Care Unit and the Operating Room

Contact Info

Product

Resources

About