A Self-Reconstructing Algorithm for Single and Multiple-Sensor Fault Isolation Based on Auto-Associative Neural Networks
Recently different approaches have been developed in the field of sensor fault diagnostics based on Auto-Associative Neural Network (AANN). In this paper we present a novel algorithm called Self reconstructing Auto-Associative Neural Network (S-AANN) which is able to detect and isolate single faulty...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Petroleum University of Technology
2017-01-01
|
Series: | Iranian Journal of Oil & Gas Science and Technology |
Subjects: | |
Online Access: | http://ijogst.put.ac.ir/article_44384_1ce8d36de47de45f6ebd2dbe071373af.pdf |
id |
doaj-012a4cbc486944d488567b6d1cd2a510 |
---|---|
record_format |
Article |
spelling |
doaj-012a4cbc486944d488567b6d1cd2a5102020-11-25T03:52:37ZengPetroleum University of TechnologyIranian Journal of Oil & Gas Science and Technology2345-24122345-24202017-01-0161779210.22050/ijogst.2017.4438444384A Self-Reconstructing Algorithm for Single and Multiple-Sensor Fault Isolation Based on Auto-Associative Neural NetworksHamidreza Mousavi0Mehdi Shahbazian1Nosrat Moradi2M.S. Student, Department of Instrumentation & Automation Engineering, Petroleum University of Technology, Ahwaz, Iran.Petroleum university of technologyIranian Offshore Oil CompanyRecently different approaches have been developed in the field of sensor fault diagnostics based on Auto-Associative Neural Network (AANN). In this paper we present a novel algorithm called Self reconstructing Auto-Associative Neural Network (S-AANN) which is able to detect and isolate single faulty sensor via reconstruction. We have also extended the algorithm to be applicable in multiple fault conditions. The algorithm uses a calibration model based on AANN. AANN can reconstruct the faulty sensor using non-faulty sensors due to correlation between the process variables, and mean of the difference between reconstructed and original data determines which sensors are faulty. The algorithms are tested on a Dimerization process. The simulation results show that the S-AANN can isolate multiple faulty sensors with low computational time that make the algorithm appropriate candidate for online applications.http://ijogst.put.ac.ir/article_44384_1ce8d36de47de45f6ebd2dbe071373af.pdfsensor faultfault isolationreconstruction algorithmauto-associative neural networksmultiple faults |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hamidreza Mousavi Mehdi Shahbazian Nosrat Moradi |
spellingShingle |
Hamidreza Mousavi Mehdi Shahbazian Nosrat Moradi A Self-Reconstructing Algorithm for Single and Multiple-Sensor Fault Isolation Based on Auto-Associative Neural Networks Iranian Journal of Oil & Gas Science and Technology sensor fault fault isolation reconstruction algorithm auto-associative neural networks multiple faults |
author_facet |
Hamidreza Mousavi Mehdi Shahbazian Nosrat Moradi |
author_sort |
Hamidreza Mousavi |
title |
A Self-Reconstructing Algorithm for Single and Multiple-Sensor Fault Isolation Based on Auto-Associative Neural Networks |
title_short |
A Self-Reconstructing Algorithm for Single and Multiple-Sensor Fault Isolation Based on Auto-Associative Neural Networks |
title_full |
A Self-Reconstructing Algorithm for Single and Multiple-Sensor Fault Isolation Based on Auto-Associative Neural Networks |
title_fullStr |
A Self-Reconstructing Algorithm for Single and Multiple-Sensor Fault Isolation Based on Auto-Associative Neural Networks |
title_full_unstemmed |
A Self-Reconstructing Algorithm for Single and Multiple-Sensor Fault Isolation Based on Auto-Associative Neural Networks |
title_sort |
self-reconstructing algorithm for single and multiple-sensor fault isolation based on auto-associative neural networks |
publisher |
Petroleum University of Technology |
series |
Iranian Journal of Oil & Gas Science and Technology |
issn |
2345-2412 2345-2420 |
publishDate |
2017-01-01 |
description |
Recently different approaches have been developed in the field of sensor fault diagnostics based on Auto-Associative Neural Network (AANN). In this paper we present a novel algorithm called Self reconstructing Auto-Associative Neural Network (S-AANN) which is able to detect and isolate single faulty sensor via reconstruction. We have also extended the algorithm to be applicable in multiple fault conditions. The algorithm uses a calibration model based on AANN. AANN can reconstruct the faulty sensor using non-faulty sensors due to correlation between the process variables, and mean of the difference between reconstructed and original data determines which sensors are faulty. The algorithms are tested on a Dimerization process. The simulation results show that the S-AANN can isolate multiple faulty sensors with low computational time that make the algorithm appropriate candidate for online applications. |
topic |
sensor fault fault isolation reconstruction algorithm auto-associative neural networks multiple faults |
url |
http://ijogst.put.ac.ir/article_44384_1ce8d36de47de45f6ebd2dbe071373af.pdf |
work_keys_str_mv |
AT hamidrezamousavi aselfreconstructingalgorithmforsingleandmultiplesensorfaultisolationbasedonautoassociativeneuralnetworks AT mehdishahbazian aselfreconstructingalgorithmforsingleandmultiplesensorfaultisolationbasedonautoassociativeneuralnetworks AT nosratmoradi aselfreconstructingalgorithmforsingleandmultiplesensorfaultisolationbasedonautoassociativeneuralnetworks AT hamidrezamousavi selfreconstructingalgorithmforsingleandmultiplesensorfaultisolationbasedonautoassociativeneuralnetworks AT mehdishahbazian selfreconstructingalgorithmforsingleandmultiplesensorfaultisolationbasedonautoassociativeneuralnetworks AT nosratmoradi selfreconstructingalgorithmforsingleandmultiplesensorfaultisolationbasedonautoassociativeneuralnetworks |
_version_ |
1724481856024346624 |