☆ 4.7 Article

Incipient fault detection of nonlinear chemical processes based on probability-related randomized slow feature analysis

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Automation & Control Systems

Fault Diagnosis Methodology of Redundant Closed-Loop Feedback Control Systems: Subsea Blowout Preventer System as a Case Study

Xiangdi Kong et al.

Summary: Faults in closed-loop feedback control systems are difficult to identify. Redundancy improves system reliability but poses new challenges for fault diagnosis in multiple redundant systems. This study proposes a causality-based method using dynamic Bayesian networks for fault diagnosis, which dynamically evaluates system performance and integrates monitoring information to assist diagnosis and location.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2023)

添加到收藏夹

Article Engineering, Electrical & Electronic

A Novel Fault Detection Method Based on the Extraction of Slow Features for Dynamic Nonstationary Processes

Jie Dong et al.

Summary: This article proposes a novel fault detection framework to improve the performance of fault detection in the presence of nonstationary and stationary variables. The framework combines slow feature analysis and K-nearest neighbor based on Mahalanobis distance, and considers fault detection rate and false alarm rate by setting dynamic control limits.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2022)

添加到收藏夹

Article Automation & Control Systems

A novel kernel dynamic inner slow feature analysis method for dynamic nonlinear process concurrent monitoring of operating point deviations and process dynamics anomalies

Yuemei Xu et al.

Summary: A novel method of nonlinear dynamic inner slow feature analysis is proposed for concurrent monitoring of operating point deviations and process dynamics anomalies. The method extracts serial auto-correlated latent slow features with explicit dynamic representation. After training the model from data, a corresponding detection strategy is developed for process condition concurrent monitoring, which is demonstrated to be superior and effective in numerical simulation and actual case studies.

JOURNAL OF PROCESS CONTROL (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

An incipient fault diagnosis methodology using local Mahalanobis distance: Detection process based on empirical probability density estimation

Junjie Yang et al.

Summary: Incipient fault detection is a challenging and popular topic that focuses on detecting early subtle changes to prevent severe security issues. The proposed methodology combines a Local Mahalanobis Distance algorithm and an Empirical Probability Density estimation technique to improve detection sensitivity for non-Gaussian data conditions. Performance analysis using simulation data and a case study on the Continuous-flow Stirred Tank Reactor demonstrate the effectiveness and benefits of the proposed approach.

SIGNAL PROCESSING (2022)

添加到收藏夹

Article Engineering, Chemical

A Review on Data-Driven Process Monitoring Methods: Characterization and Mining of Industrial Data

Cheng Ji et al.

Summary: Fault detection and diagnosis (FDD) are crucial for safe and stable operation in the chemical industry. Data-driven process monitoring technologies have gained attention in recent years, but challenges exist due to the complex characteristics of industrial data. This review paper discusses the implementation framework, state-of-the-art methods, and challenges and solutions for actual industrial applications of data-driven process monitoring methods in the chemical industry.

PROCESSES (2022)

添加到收藏夹

Article Engineering, Chemical

Efficient batch process monitoring based on random nonlinear feature analysis

Xiaogang Deng et al.

Summary: This paper proposes a method called TLERFFA for effective batch process fault detection, which combines RFFA and ensemble learning to maximize the extraction of local information in batch process data.

CANADIAN JOURNAL OF CHEMICAL ENGINEERING (2022)

添加到收藏夹

Article Automation & Control Systems

Slow feature analysis-aided detection and diagnosis of incipient faults for running gear systems of high-speed trains

Chao Cheng et al.

Summary: A novel data-driven method using Hellinger distance and slow feature analysis is proposed for detecting and diagnosing incipient faults in running gear systems of high-speed trains. The method demonstrates satisfactory fault detectability and considerable robustness against high-level noises.

ISA TRANSACTIONS (2022)

添加到收藏夹

Article Engineering, Civil

Data-Driven Fault Diagnosis for Traction Systems in High-Speed Trains: A Survey, Challenges, and Perspectives

Hongtian Chen et al.

Summary: This paper provides a systematic review and categorization of data-driven FDD methods for traction systems in high-speed trains. It analyzes the challenges in implementing FDD and proposes several promising solutions.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

添加到收藏夹

Article Automation & Control Systems

Incipient fault detection for dynamic chemical processes based on enhanced CVDA integrated with probability information and fault-sensitive features

Xiaogang Deng et al.

Summary: An enhanced CVDA method, FSPRCVDA, is proposed in this paper for better monitoring incipient faults in dynamic chemical processes. By extracting fault-sensitive features and constructing an auxiliary model, the FSPRCVDA method achieves a higher fault detection rate than the basic CVDA method.

JOURNAL OF PROCESS CONTROL (2022)

添加到收藏夹

Article Engineering, Industrial

An adaptive remaining useful life prediction approach for single battery with unlabeled small sample data and parameter uncertainty

Jiusi Zhang et al.

Summary: This study proposes an adaptive approach based on Kalman filter and expectation maximum to accurately predict the remaining useful life (RUL) of a single lithium-ion battery without historical data and describe the uncertainty of parameter estimation. Experimental results demonstrate that this method outperforms existing conventional data-driven approaches.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2022)

添加到收藏夹

Article Engineering, Industrial

Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism

Jiusi Zhang et al.

Summary: This paper introduces a novel bidirectional GRU model with temporal self-attention mechanism for predicting remaining useful life (RUL). Experimental results demonstrate its superiority over existing machine learning and deep learning methods.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2022)

添加到收藏夹

Review Computer Science, Interdisciplinary Applications

An analysis of process fault diagnosis methods from safety perspectives

Rajeevan Arunthavanathan et al.

Summary: Industry 4.0 provides significant opportunities for a safer environment through online monitoring, early fault detection, and preventing fault transitions to failures. Decision-making is crucial in abnormal situation management, and assigning risk based on consequences can provide additional information to prevent accidents. This paper analyzes the interconnections between fault detection and diagnosis (FDD), risk assessment (RA), and abnormal situation management (ASM) in process safety, discussing research directions for Industry 4.0.

COMPUTERS & CHEMICAL ENGINEERING (2021)

添加到收藏夹

Article Automation & Control Systems

Decentralized dynamic process monitoring based on manifold regularized slow feature analysis

Xue Xu et al.

Summary: A novel decentralized method for monitoring large-scale industrial processes is proposed in this study, which explores serial correlations and local manifold structures of the data. The method utilizes a specific block division strategy and dimensionality reduction algorithm to capture temporal dynamics and local structure information, and combines monitoring results through Bayesian inference for decision fusion. Experimental results demonstrate the effectiveness of the proposed method.

JOURNAL OF PROCESS CONTROL (2021)

添加到收藏夹

Article Engineering, Environmental

A deep learning model for process fault prognosis

Rajeevan Arunthavanathan et al.

Summary: Early fault detection and fault prognosis are crucial for safe process operations, requiring early examination of fault symptoms. New fault prognosis methods help in predicting remaining useful life of systems and enhancing process safety.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2021)

添加到收藏夹

Article Engineering, Environmental

A novel orthogonal self-attentive variational autoencoder method for interpretable chemical process fault detection and identification

Xiaotian Bi et al.

Summary: The proposed orthogonal self-attentive variational autoencoder (OSAVA) model in this paper is capable of simultaneously performing fault detection and identification tasks, and providing interpretable results. Evaluation on the Tennessee Eastman process (TEP) demonstrates promising fault detection rate and low detection delay for the OSAVA model.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2021)

添加到收藏夹

Article Engineering, Environmental

Locality preserving randomized canonical correlation analysis for real-time nonlinear process monitoring

Ping Wu et al.

Summary: The paper presents a novel locality preserving randomized canonical correlation analysis (LPRCCA) method for real-time nonlinear process monitoring which maps original data to a randomized low-dimensional feature space and integrates local geometric structure information to improve data mining performance, reducing computational cost and showing significant advantages over kernel-based methods.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2021)

添加到收藏夹

Article Engineering, Environmental

Risk assessment on deepwater drilling well control based on dynamic Bayesian network

Zengkai Liu et al.

Summary: This paper introduces a dynamic risk assessment model for evaluating the safety of deepwater drilling operations, which can comprehensively analyze the risk factors and clarify the impact of blowouts. By analyzing risk factors, developing dynamic Bayesian network model, and conducting risk analysis, the model provides insights into the risks associated with blowouts.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2021)

添加到收藏夹

Article Engineering, Environmental

Rebooting kernel CCA method for nonlinear quality-relevant fault detection in process industries

Hongchao Cheng et al.

Summary: The newly proposed M-NAKCCA framework demonstrates excellent performance in process monitoring, better applied for nonlinear fault detection, compressing high-dimensional datasets, and enhancing method sensitivity.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2021)

添加到收藏夹

Article Construction & Building Technology

Fault detection and diagnosis of the air handling unit via an enhanced kernel slow feature analysis approach considering the time-wise and batch-wise dynamics

Hanyuan Zhang et al.

Summary: This paper presents an enhanced kernel slow feature analysis (SFA) based fault detection and diagnosis (FDD) scheme for nonlinear AHU systems, utilizing novel algorithms such as threeway data based kernel SFA (TBKSFA) and kernel discriminant SFA (KDSFA) to improve performance in capturing dynamic characteristics and identifying fault patterns. Experimental results show significant improvements compared to other popular methods.

ENERGY AND BUILDINGS (2021)

添加到收藏夹

Article Automation & Control Systems

Online Probabilistic Estimation of Sensor Faulty Signal in Industrial Processes and Its Applications

Shunyi Zhao et al.

Summary: This article proposes an online estimator for faulty sensor signals in industrial processes by using variational Bayesian inference to estimate the probability density function of the fault signal and state. It discusses a heuristic model with probabilistic features to address the issue of unavailable fault transition dynamics and employs a set of weighted particles for empirical estimation of the state pdf. The proposed algorithm demonstrates improvements over existing methods in accurately estimating fault magnitude and location in real-time.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2021)

添加到收藏夹

Article Engineering, Environmental

A data-driven Bayesian network learning method for process fault diagnosis

Md Tanjin Amin et al.

Summary: This study presents a data-driven methodology that integrates PCA with BN for fault detection and diagnosis, with the use of CD and KLD for automatic selection of principal components and development of data-driven BN learning technique. The method utilizes a combination of vine copula and Bayes' theorem to capture nonlinear dependence in high-dimensional process data, eliminating the need for discretization of continuous data.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2021)

添加到收藏夹

Article Engineering, Environmental

Process topology convolutional network model for chemical process fault diagnosis

Deyang Wu et al.

Summary: There are always potential safety risks in chemical processes, making early and accurate fault detection crucial. This paper introduces a process topology convolutional network (PTCN) model for fault diagnosis in complex chemical processes, showing improved accuracy and interpretability in experiments.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2021)

添加到收藏夹

Article Engineering, Environmental

Risk-based fault detection and diagnosis for nonlinear and non-Gaussian process systems using R-vine copula

Md Tanjin Amin et al.

Summary: This paper proposes a risk-based fault detection and diagnosis methodology using R-vine copula and event tree for nonlinear and nonGaussian process systems. The methodology shows better performance in detecting and diagnosing abnormal situations compared to conventional techniques.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Anomaly Detection Using Local Kernel Density Estimation and Context-Based Regression

Weiming Hu et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2020)

添加到收藏夹

Review Engineering, Chemical

A review of data-driven fault detection and diagnosis methods: applications in chemical process systems

Norazwan Md Nor et al.

REVIEWS IN CHEMICAL ENGINEERING (2020)

添加到收藏夹

Article Engineering, Multidisciplinary

Quality-relevant dynamic process monitoring based on dynamic total slow feature regression model

Yan Shifu et al.

MEASUREMENT SCIENCE AND TECHNOLOGY (2020)

添加到收藏夹

Article Engineering, Chemical

Two-Step Localized Kernel Principal Component Analysis Based Incipient Fault Diagnosis for Nonlinear Industrial Processes

Xiaogang Deng et al.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2020)

添加到收藏夹

Article Automation & Control Systems

Incipient fault detection for nonlinear processes based on dynamic multi-block probability related kernel principal component analysis

Peipei Cai et al.

ISA TRANSACTIONS (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Fast feature selection for interval-valued data through kernel density estimation entropy

Jianhua Dai et al.

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS (2020)

添加到收藏夹

Article Chemistry, Analytical

Nonlinear Chemical Process Fault Diagnosis Using Ensemble Deep Support Vector Data Description

Xiaogang Deng et al.

SENSORS (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Multistep Dynamic Slow Feature Analysis for Industrial Process Monitoring

Xin Ma et al.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2020)

添加到收藏夹

Article Automation & Control Systems

Trajectory-based operation monitoring of transition procedure in multimode process

Zhaojing Wang et al.

JOURNAL OF PROCESS CONTROL (2020)

添加到收藏夹

Article Automation & Control Systems

Fault detection in dynamic plant-wide process by multi-block slow feature analysis and support vector data description

Jian Huang et al.

ISA TRANSACTIONS (2019)

添加到收藏夹

Article Automation & Control Systems

Recursive Slow Feature Analysis for Adaptive Monitoring of Industrial Processes

Chao Shang et al.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2018)

添加到收藏夹

Article Automation & Control Systems

An improved incipient fault detection method based on Kullback-Leibler divergence

Hongtian Chen et al.

ISA TRANSACTIONS (2018)

添加到收藏夹

Article Automation & Control Systems

Batch process fault detection and identification based on discriminant global preserving kernel slow feature analysis

Hanyuan Zhang et al.

ISA TRANSACTIONS (2018)

添加到收藏夹

Article Geochemistry & Geophysics

Kernel Slow Feature Analysis for Scene Change Detection

Chen Wu et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2017)

添加到收藏夹

Article Engineering, Electrical & Electronic

Incipient fault amplitude estimation using KL divergence with a probabilistic approach

Jinane Harmouche et al.

SIGNAL PROCESSING (2016)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Process fault detection based on dynamic kernel slow feature analysis

Ni Zhang et al.

COMPUTERS & ELECTRICAL ENGINEERING (2015)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Online Kernel Slow Feature Analysis for Temporal Video Segmentation and Tracking

Stephan Liwicki et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2015)

添加到收藏夹

Article Engineering, Environmental

A new fault detection method for non-Gaussian process based on robust independent component analysis

Lianfang Cai et al.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2014)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.