Fault Detection Method Using Auto-Associative Shared Nearest Neighbor Kernel Regression for Industrial Processes

As industrial systems grow larger and more interconnected, timely fault detection is essential to minimize downtime, enhance reliability, and reduce costs. However, conventional methods focus on reactive maintenance, limiting their ability to detect faults before escalation. Additionally, fault prop...

Full description

Saved in:
Bibliographic Details
Main Authors: Minseok Kim, Eunkyeong Kim, Seunghwan Jung, Baekcheon Kim, Jinyong Kim, Sungshin Kim
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/5/2251
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850225334570450944
author Minseok Kim
Eunkyeong Kim
Seunghwan Jung
Baekcheon Kim
Jinyong Kim
Sungshin Kim
author_facet Minseok Kim
Eunkyeong Kim
Seunghwan Jung
Baekcheon Kim
Jinyong Kim
Sungshin Kim
author_sort Minseok Kim
collection DOAJ
description As industrial systems grow larger and more interconnected, timely fault detection is essential to minimize downtime, enhance reliability, and reduce costs. However, conventional methods focus on reactive maintenance, limiting their ability to detect faults before escalation. Additionally, fault propagation in large-scale systems can degrade detection performance. To address these challenges, we propose an auto-associative shared nearest neighbor kernel regression method for fault detection in complex industrial processes. Inspired by attention mechanisms, the proposed approach assigns higher weights to relevant training data. Shared nearest neighbor is used to assess similarity between faults and training data, rescaling distances accordingly. These adjusted distances are then utilized in auto-associative kernel regression for fault detection. The performance of the proposed method is evaluated by applying it to benchmark data from the Tennessee Eastman Process and a real-world, unplanned shutdown case concerning a circulating fluidized bed boiler. The experimental results show that the proposed method can detect anomalies up to 2 h earlier than conventional fault detection methods.
format Article
id doaj-art-e5d17876da8a41edb56a0bad5a4406ed
institution OA Journals
issn 2076-3417
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-e5d17876da8a41edb56a0bad5a4406ed2025-08-20T02:05:23ZengMDPI AGApplied Sciences2076-34172025-02-01155225110.3390/app15052251Fault Detection Method Using Auto-Associative Shared Nearest Neighbor Kernel Regression for Industrial ProcessesMinseok Kim0Eunkyeong Kim1Seunghwan Jung2Baekcheon Kim3Jinyong Kim4Sungshin Kim5Department of Electrical and Electronics Engineering, Pusan National University, Busan 46241, Republic of KoreaDepartment of Electrical and Electronics Engineering, Pusan National University, Busan 46241, Republic of KoreaDepartment of Electrical and Electronics Engineering, Pusan National University, Busan 46241, Republic of KoreaDepartment of Electrical and Electronics Engineering, Pusan National University, Busan 46241, Republic of KoreaDepartment of Electrical and Electronics Engineering, Pusan National University, Busan 46241, Republic of KoreaDepartment of Electrical and Electronics Engineering, Pusan National University, Busan 46241, Republic of KoreaAs industrial systems grow larger and more interconnected, timely fault detection is essential to minimize downtime, enhance reliability, and reduce costs. However, conventional methods focus on reactive maintenance, limiting their ability to detect faults before escalation. Additionally, fault propagation in large-scale systems can degrade detection performance. To address these challenges, we propose an auto-associative shared nearest neighbor kernel regression method for fault detection in complex industrial processes. Inspired by attention mechanisms, the proposed approach assigns higher weights to relevant training data. Shared nearest neighbor is used to assess similarity between faults and training data, rescaling distances accordingly. These adjusted distances are then utilized in auto-associative kernel regression for fault detection. The performance of the proposed method is evaluated by applying it to benchmark data from the Tennessee Eastman Process and a real-world, unplanned shutdown case concerning a circulating fluidized bed boiler. The experimental results show that the proposed method can detect anomalies up to 2 h earlier than conventional fault detection methods.https://www.mdpi.com/2076-3417/15/5/2251fault detectionshared neighborauto-associative kernel regressionfluidized bed boiler
spellingShingle Minseok Kim
Eunkyeong Kim
Seunghwan Jung
Baekcheon Kim
Jinyong Kim
Sungshin Kim
Fault Detection Method Using Auto-Associative Shared Nearest Neighbor Kernel Regression for Industrial Processes
Applied Sciences
fault detection
shared neighbor
auto-associative kernel regression
fluidized bed boiler
title Fault Detection Method Using Auto-Associative Shared Nearest Neighbor Kernel Regression for Industrial Processes
title_full Fault Detection Method Using Auto-Associative Shared Nearest Neighbor Kernel Regression for Industrial Processes
title_fullStr Fault Detection Method Using Auto-Associative Shared Nearest Neighbor Kernel Regression for Industrial Processes
title_full_unstemmed Fault Detection Method Using Auto-Associative Shared Nearest Neighbor Kernel Regression for Industrial Processes
title_short Fault Detection Method Using Auto-Associative Shared Nearest Neighbor Kernel Regression for Industrial Processes
title_sort fault detection method using auto associative shared nearest neighbor kernel regression for industrial processes
topic fault detection
shared neighbor
auto-associative kernel regression
fluidized bed boiler
url https://www.mdpi.com/2076-3417/15/5/2251
work_keys_str_mv AT minseokkim faultdetectionmethodusingautoassociativesharednearestneighborkernelregressionforindustrialprocesses
AT eunkyeongkim faultdetectionmethodusingautoassociativesharednearestneighborkernelregressionforindustrialprocesses
AT seunghwanjung faultdetectionmethodusingautoassociativesharednearestneighborkernelregressionforindustrialprocesses
AT baekcheonkim faultdetectionmethodusingautoassociativesharednearestneighborkernelregressionforindustrialprocesses
AT jinyongkim faultdetectionmethodusingautoassociativesharednearestneighborkernelregressionforindustrialprocesses
AT sungshinkim faultdetectionmethodusingautoassociativesharednearestneighborkernelregressionforindustrialprocesses