Seq2Seq-based GRU autoencoder for anomaly detection and failure identification in coal mining hydraulic support systems

Abstract In coal mining operations, the stable operation of hydraulic supports is crucial for ensuring mine safety. However, the nonlinear, non-stationary characteristics and noise interference in hydraulic support pressure data pose significant challenges for anomaly detection and fault diagnosis....

Full description

Saved in:
Bibliographic Details
Main Authors: Kai Zhan, Cong Wang, Xigui Zheng, Chao Kong, Guangming Li, Wei Xin, Longhe Liu
Format: Article
Language:English
Published: Nature Portfolio 2025-01-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-84130-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850282409180790784
author Kai Zhan
Cong Wang
Xigui Zheng
Chao Kong
Guangming Li
Wei Xin
Longhe Liu
author_facet Kai Zhan
Cong Wang
Xigui Zheng
Chao Kong
Guangming Li
Wei Xin
Longhe Liu
author_sort Kai Zhan
collection DOAJ
description Abstract In coal mining operations, the stable operation of hydraulic supports is crucial for ensuring mine safety. However, the nonlinear, non-stationary characteristics and noise interference in hydraulic support pressure data pose significant challenges for anomaly detection and fault diagnosis. This study proposes an anomaly detection and failure identification method based on Gated Recurrent Unit Autoencoder (GRU-AE), aimed at achieving anomaly detection in hydraulic support pressure data and equipment failure early warning. Through in-depth analysis of data from two coal mines in China, we systematically evaluated the model’s key parameters. The study revealed that window size had a limited impact on model performance, with a window length of 144 demonstrating optimal comprehensive performance in both anomaly detection and failure mode identification. The study also investigated the effectiveness of teacher forcing techniques. Although this technique can accelerate model convergence, it may lead to training instability and reduced generalization capability, requiring careful consideration in practical applications. Our proposed Recurrent Reconstruction Network model demonstrated excellent performance in complex coal mine hydraulic support data, effectively identifying anomalous regions and potential equipment failure characteristics while revealing potential deviations between model predictions and actual data, demonstrating its superior learning capability for periodic data patterns and equipment failure characteristics. Experimental results validated the effectiveness of the GRU-AE model in hydraulic support pressure anomaly detection and equipment fault diagnosis, providing an innovative technical solution for coal mine safety monitoring.
format Article
id doaj-art-6aec3efc395e415593cd1f82a9006f44
institution OA Journals
issn 2045-2322
language English
publishDate 2025-01-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-6aec3efc395e415593cd1f82a9006f442025-08-20T01:47:59ZengNature PortfolioScientific Reports2045-23222025-01-0115111910.1038/s41598-024-84130-8Seq2Seq-based GRU autoencoder for anomaly detection and failure identification in coal mining hydraulic support systemsKai Zhan0Cong Wang1Xigui Zheng2Chao Kong3Guangming Li4Wei Xin5Longhe Liu6Shandong Succeed Mining Safety Engineering Co. LtdShandong Succeed Mining Safety Engineering Co. LtdSchool of Mines, China University of Mining and TechnologyShandong Succeed Mining Safety Engineering Co. LtdShandong Succeed Mining Safety Engineering Co. LtdSchool of Mines, China University of Mining and TechnologySchool of Mines, China University of Mining and TechnologyAbstract In coal mining operations, the stable operation of hydraulic supports is crucial for ensuring mine safety. However, the nonlinear, non-stationary characteristics and noise interference in hydraulic support pressure data pose significant challenges for anomaly detection and fault diagnosis. This study proposes an anomaly detection and failure identification method based on Gated Recurrent Unit Autoencoder (GRU-AE), aimed at achieving anomaly detection in hydraulic support pressure data and equipment failure early warning. Through in-depth analysis of data from two coal mines in China, we systematically evaluated the model’s key parameters. The study revealed that window size had a limited impact on model performance, with a window length of 144 demonstrating optimal comprehensive performance in both anomaly detection and failure mode identification. The study also investigated the effectiveness of teacher forcing techniques. Although this technique can accelerate model convergence, it may lead to training instability and reduced generalization capability, requiring careful consideration in practical applications. Our proposed Recurrent Reconstruction Network model demonstrated excellent performance in complex coal mine hydraulic support data, effectively identifying anomalous regions and potential equipment failure characteristics while revealing potential deviations between model predictions and actual data, demonstrating its superior learning capability for periodic data patterns and equipment failure characteristics. Experimental results validated the effectiveness of the GRU-AE model in hydraulic support pressure anomaly detection and equipment fault diagnosis, providing an innovative technical solution for coal mine safety monitoring.https://doi.org/10.1038/s41598-024-84130-8Mining engineeringHydraulic supportAnomaly detectionGated recurrent unitAutoencoder
spellingShingle Kai Zhan
Cong Wang
Xigui Zheng
Chao Kong
Guangming Li
Wei Xin
Longhe Liu
Seq2Seq-based GRU autoencoder for anomaly detection and failure identification in coal mining hydraulic support systems
Scientific Reports
Mining engineering
Hydraulic support
Anomaly detection
Gated recurrent unit
Autoencoder
title Seq2Seq-based GRU autoencoder for anomaly detection and failure identification in coal mining hydraulic support systems
title_full Seq2Seq-based GRU autoencoder for anomaly detection and failure identification in coal mining hydraulic support systems
title_fullStr Seq2Seq-based GRU autoencoder for anomaly detection and failure identification in coal mining hydraulic support systems
title_full_unstemmed Seq2Seq-based GRU autoencoder for anomaly detection and failure identification in coal mining hydraulic support systems
title_short Seq2Seq-based GRU autoencoder for anomaly detection and failure identification in coal mining hydraulic support systems
title_sort seq2seq based gru autoencoder for anomaly detection and failure identification in coal mining hydraulic support systems
topic Mining engineering
Hydraulic support
Anomaly detection
Gated recurrent unit
Autoencoder
url https://doi.org/10.1038/s41598-024-84130-8
work_keys_str_mv AT kaizhan seq2seqbasedgruautoencoderforanomalydetectionandfailureidentificationincoalmininghydraulicsupportsystems
AT congwang seq2seqbasedgruautoencoderforanomalydetectionandfailureidentificationincoalmininghydraulicsupportsystems
AT xiguizheng seq2seqbasedgruautoencoderforanomalydetectionandfailureidentificationincoalmininghydraulicsupportsystems
AT chaokong seq2seqbasedgruautoencoderforanomalydetectionandfailureidentificationincoalmininghydraulicsupportsystems
AT guangmingli seq2seqbasedgruautoencoderforanomalydetectionandfailureidentificationincoalmininghydraulicsupportsystems
AT weixin seq2seqbasedgruautoencoderforanomalydetectionandfailureidentificationincoalmininghydraulicsupportsystems
AT longheliu seq2seqbasedgruautoencoderforanomalydetectionandfailureidentificationincoalmininghydraulicsupportsystems