Automated Anomaly Detection in Blast Furnace Shaft Static Pressure Using Adversarial Autoencoders and Mode Decomposition

Monitoring the blast furnace shaft static pressure is crucial for maintaining a stable ironmaking process. Traditional rule-based methods and manual inspections suffer from high labor costs and inconsistent standards. This article proposes a new unsupervised anomaly detection framework that combines...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaodong Sun, Jie Zhu, Bing Tang, Zhaohui Jiang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/11/3473
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849722452781826048
author Xiaodong Sun
Jie Zhu
Bing Tang
Zhaohui Jiang
author_facet Xiaodong Sun
Jie Zhu
Bing Tang
Zhaohui Jiang
author_sort Xiaodong Sun
collection DOAJ
description Monitoring the blast furnace shaft static pressure is crucial for maintaining a stable ironmaking process. Traditional rule-based methods and manual inspections suffer from high labor costs and inconsistent standards. This article proposes a new unsupervised anomaly detection framework that combines adversarial autoencoder with variational mode decomposition (VMD). Firstly, using VMD combined with sample entropy calculation and clustering algorithm, the trend, period, and other components of multidimensional signals are extracted, and then these components are integrated into an improved adversarial training autoencoder to detect global and local anomalies. The proposed method has an accuracy of 0.95, a recall rate of 0.91, and an F1 score of 0.93. Which demonstrates the method effectively captures multi-scale anomalies including value bias, morphological changes, and sudden fluctuations, while providing analysts with interpretable anomaly detail diagnosis.
format Article
id doaj-art-3c80ec210c5e44ddb936c6dedd8ad0a4
institution DOAJ
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-3c80ec210c5e44ddb936c6dedd8ad0a42025-08-20T03:11:20ZengMDPI AGSensors1424-82202025-05-012511347310.3390/s25113473Automated Anomaly Detection in Blast Furnace Shaft Static Pressure Using Adversarial Autoencoders and Mode DecompositionXiaodong Sun0Jie Zhu1Bing Tang2Zhaohui Jiang3School of Automation, Central South University, Changsha 410083, ChinaCISDI Information Technology (Chongqing) Co., Ltd., Chongqing 401122, ChinaCISDI Information Technology (Chongqing) Co., Ltd., Chongqing 401122, ChinaSchool of Automation, Central South University, Changsha 410083, ChinaMonitoring the blast furnace shaft static pressure is crucial for maintaining a stable ironmaking process. Traditional rule-based methods and manual inspections suffer from high labor costs and inconsistent standards. This article proposes a new unsupervised anomaly detection framework that combines adversarial autoencoder with variational mode decomposition (VMD). Firstly, using VMD combined with sample entropy calculation and clustering algorithm, the trend, period, and other components of multidimensional signals are extracted, and then these components are integrated into an improved adversarial training autoencoder to detect global and local anomalies. The proposed method has an accuracy of 0.95, a recall rate of 0.91, and an F1 score of 0.93. Which demonstrates the method effectively captures multi-scale anomalies including value bias, morphological changes, and sudden fluctuations, while providing analysts with interpretable anomaly detail diagnosis.https://www.mdpi.com/1424-8220/25/11/3473blast furnace monitoringtime-series anomaly detectionadversarial autoencodervariational mode decompositionunsupervised learning
spellingShingle Xiaodong Sun
Jie Zhu
Bing Tang
Zhaohui Jiang
Automated Anomaly Detection in Blast Furnace Shaft Static Pressure Using Adversarial Autoencoders and Mode Decomposition
Sensors
blast furnace monitoring
time-series anomaly detection
adversarial autoencoder
variational mode decomposition
unsupervised learning
title Automated Anomaly Detection in Blast Furnace Shaft Static Pressure Using Adversarial Autoencoders and Mode Decomposition
title_full Automated Anomaly Detection in Blast Furnace Shaft Static Pressure Using Adversarial Autoencoders and Mode Decomposition
title_fullStr Automated Anomaly Detection in Blast Furnace Shaft Static Pressure Using Adversarial Autoencoders and Mode Decomposition
title_full_unstemmed Automated Anomaly Detection in Blast Furnace Shaft Static Pressure Using Adversarial Autoencoders and Mode Decomposition
title_short Automated Anomaly Detection in Blast Furnace Shaft Static Pressure Using Adversarial Autoencoders and Mode Decomposition
title_sort automated anomaly detection in blast furnace shaft static pressure using adversarial autoencoders and mode decomposition
topic blast furnace monitoring
time-series anomaly detection
adversarial autoencoder
variational mode decomposition
unsupervised learning
url https://www.mdpi.com/1424-8220/25/11/3473
work_keys_str_mv AT xiaodongsun automatedanomalydetectioninblastfurnaceshaftstaticpressureusingadversarialautoencodersandmodedecomposition
AT jiezhu automatedanomalydetectioninblastfurnaceshaftstaticpressureusingadversarialautoencodersandmodedecomposition
AT bingtang automatedanomalydetectioninblastfurnaceshaftstaticpressureusingadversarialautoencodersandmodedecomposition
AT zhaohuijiang automatedanomalydetectioninblastfurnaceshaftstaticpressureusingadversarialautoencodersandmodedecomposition