Article
Engineering, Electrical & Electronic
Shutian Chen, Qingchao Jiang
Summary: This article proposes an optimized denoising autoencoder (DAE)-based distributed monitoring method to address the challenge of complex correlations among variables in complex large-scale chemical processes.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Automation & Control Systems
Ke Jiang, Zhaohui Jiang, Yongfang Xie, Dong Pan, Weihua Gui
Summary: This article proposes a data-driven model to accurately monitor the abnormal conditions of blast furnaces. By using a stacked dynamic target-driven denoising autoencoder and a corresponding target-driven reconstruction loss function, features can be effectively extracted and the dynamic relationship between samples and targets can be described.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Engineering, Multidisciplinary
Jiazhen Zhu, Hongbo Shi, Bing Song, Yang Tao, Shuai Tan, Tianqing Zhang
Summary: In this study, a novel algorithm LWDAE is proposed to address the issues of submergence and neutralization of process variables in traditional monitoring methods. By weighted loading matrix and modifying the loss function, LWDAE effectively highlights useful information and reduces the impact of noise, demonstrating its effectiveness in continuous stirred tank reactor case studies.
Article
Engineering, Electrical & Electronic
Fan Wu, Haiyong Luo, Hongwei Jia, Fang Zhao, Yimin Xiao, Xile Gao
Summary: The paper proposes a noise covariance estimation algorithm for GNSS/INS-integrated navigation using multitask learning model to achieve accurate and robust localization results under various complex and dynamic environments. Extensive experiments demonstrate a significant reduction in positioning error compared to traditional KF-based integrated navigation algorithm with predefined fixed settings.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Chemistry, Multidisciplinary
Yuemei Xu, Mingxing Jia, Zhizhong Mao
Summary: In this paper, a novel nonlinear spatiotemporal process feature learning method is proposed for the concurrent monitoring of the static deviation and the dynamic anomaly of complex chemical processes. The method extracts high-value slow-varying spatiotemporal process features with an explicit temporal relationship model.
Article
Chemistry, Multidisciplinary
Nadeem Abbas, Tariq Umar, Rania Salih, Muhammad Akbar, Zahoor Hussain, Xiong Haibei
Summary: Due to the complexity and operational incidents of underground environments, advanced and accurate monitoring of underground metro shield tunnel structures is crucial for maintenance and accident prevention. This paper presents a deep learning-based approach for damage identification in underground metro shield tunnels.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Environmental
Abdulrahman H. Ba-Alawi, Paulina Vilela, Jorge Loy-Benitez, SungKu Heo, ChangKyoo Yoo
Summary: This study focuses on sensor validation of WWTP influent conditions using an SDAE model, achieving successful detection and reconciliation of faulty data.
JOURNAL OF WATER PROCESS ENGINEERING
(2021)
Article
Geochemistry & Geophysics
Zhangquan Liao, Yong Li, En Xia, Yingtian Liu, Rui Hu
Summary: A denoising framework for random seismic noise attenuation is proposed to address the dilemma of signal leaking and noise remaining. The framework includes a denoising autoencoder and a data generator, which can effectively suppress noise and compensate for signal leakage. Experimental results demonstrate the effectiveness of the proposed method in noise attenuation and signal leakage compensation.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Information Systems
Jianbo Yu, Xuefeng Yan
Summary: In most real-life cases, the interactions among gauged data are inevitably correlative due to the complicated behavior of process systems. Therefore, dividing the data into static and dynamic features for separate modeling is necessary. The proposed kernel slow feature analysis method and deep autoencoder model can extract static and dynamic features, construct an efficient fault detection system, and make decisions through Bayesian inference.
INFORMATION SCIENCES
(2022)
Article
Engineering, Chemical
Xu Yang, Jieshi Xiao, Jian Huang, Kaixiang Peng
Summary: This study introduces an online convolutional adversarial autoencoder (AAE) model to learn representative industrial process information. By extracting features that reflect diverse information and follow a Gaussian distribution, the model improves the accuracy of fault detection and removes redundant information through a feature selection strategy.
JOURNAL OF THE TAIWAN INSTITUTE OF CHEMICAL ENGINEERS
(2024)
Article
Engineering, Multidisciplinary
Ana Fernandez-Navamuel, Filipe Magalhaes, Diego Zamora-Sanchez, Angel J. Omella, David Garcia-Sanchez, David Pardo
Summary: This paper proposes a Deep Learning Enhanced Principal Component Analysis (PCA) approach for outlier detection to assess the structural condition of bridges. By adding residual connections, the outlier detection ability of the network is enhanced, allowing for the detection of lighter damages.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2022)
Article
Engineering, Industrial
Shengyu Jiang, Rui He, Guoming Chen, Yuan Zhu, Jiaming Shi, Kang Liu, Yuanjiang Chang
Summary: This paper incorporates the distributed optical fiber sensor (DOFS) technique and the semi-supervised learning algorithm into the pipeline health assessment framework, addressing three critical problems and validating the proposed method through a comparative experimental case study.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Energy & Fuels
Xiongjie Jia, Yang Han, Yanjun Li, Yichen Sang, Guolei Zhang
Summary: With the increasing proportion of wind power in the grid, the monitoring and maintenance of wind turbines are becoming more important. This study presents a data-driven modelling framework based on deep learning for effective monitoring of wind turbines and prediction of performance, which is validated through experiments.
Article
Engineering, Chemical
Hairong Fang, Wenhua Tao, Shan Lu, Zhijiang Lou, Yonghui Wang, Yuanfei Xue
Summary: This paper proposes a new two-step dynamic local kernel principal component analysis method, which can handle the nonlinearity and the dynamic features simultaneously.
Article
Engineering, Electrical & Electronic
Yongtao Ma, Wanru Ning, Bobo Wang, Xiuyan Liang
Summary: DFL is essential in device-free applications, where AugRF, a CNN-DAE based architecture, improves localization performance without retraining. The proposed method has been validated through simulations and real-world experiments, showing superiority and meeting real-time localization requirements.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)