☆ 4.6 Article

Autocorrelation Feature Analysis for Dynamic Process Monitoring of Thermal Power Plants

IEEE TRANSACTIONS ON CYBERNETICS (2023)

Related references

Note: Only part of the references are listed.

Article Automation & Control Systems

Artificial Neural Correlation Analysis for Performance-Indicator-Related Nonlinear Process Monitoring

Qing Chen et al.

Summary: This article proposes a novel fault detection and process monitoring method called artificial neural correlation analysis (ANCA). By combining artificial neural networks (ANN) and canonical correlation analysis (CCA), this method is able to effectively handle the nonlinear characteristics commonly found in complex industrial processes.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Add to Collection

Article Automation & Control Systems

A novel multivariate statistical process monitoring algorithm: Orthonormal subspace analysis

Zhijiang Lou et al.

Summary: This article introduces a new multivariate statistics-based process monitoring method called Orthonormal Subspace Analysis (OSA). OSA divides process data and KPI data into three orthogonal subspaces, allowing it to not only detect faults but also judge whether the faults are KPI-related. The method shows superior performance in fault detection and classification.

AUTOMATICA (2022)

Add to Collection

Article Automation & Control Systems

Recursive Correlative Statistical Analysis Method With Sliding Windows for Incipient Fault Detection

Yihao Qin et al.

Summary: This article proposes a new method combining correlative statistical analysis and the sliding window technique for detecting incipient faults. By utilizing information from process and quality variables, this method improves computational burden and algorithm complexity, and its effectiveness and advantages are demonstrated through a numerical example and application in thermal power plant process.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2022)

Add to Collection

Article Automation & Control Systems

Probabilistic Stationary Subspace Analysis for Monitoring Nonstationary Industrial Processes With Uncertainty

Dehao Wu et al.

Summary: This article proposes a novel algorithm called probabilistic stationary subspace analysis (PSSA) for monitoring nonstationary industrial processes with uncertainty. PSSA explicitly models process uncertainties and distinguishes them from actual process variations. Expectation maximization algorithm is used to estimate the parameters of PSSA, and two detection statistics are designed for process monitoring.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Add to Collection

Article Automation & Control Systems

Dynamic Process Monitoring Based on Variational Bayesian Canonical Variate Analysis

Jiaxin Yu et al.

Summary: A variational Bayesian CVA model is proposed for dynamic process monitoring, which effectively captures the inevitable noises in industrial processes and improves fault identification methods. The model overcomes the traditional CVA's lack of noise analysis, and introduces a fault identification approach based on fault relevance to avoid the smearing effect caused by data reconstruction.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2022)

Add to Collection

Article Automation & Control Systems

Variational Progressive-Transfer Network for Soft Sensing of Multirate Industrial Processes

Zheng Chai et al.

Summary: This article introduces a new method for the development of soft sensors in industrial multirate processes, utilizing a progressive transfer network to enhance the performance of the terminal soft sensor model.

IEEE TRANSACTIONS ON CYBERNETICS (2022)

Add to Collection

Article Automation & Control Systems

MoniNet With Concurrent Analytics of Temporal and Spatial Information for Fault Detection in Industrial Processes

Wanke Yu et al.

Summary: A cascaded monitoring network (MoniNet) method was proposed to develop a monitoring model with concurrent analytics of temporal and spatial information, showing effective detection of process anomalies.

IEEE TRANSACTIONS ON CYBERNETICS (2022)

Add to Collection

Article Automation & Control Systems

A generalized probabilistic monitoring model with both random and sequential data

Wanke Yu et al.

Summary: This study develops a generalized probabilistic monitoring model (GPMM) to analyze the connections between different monitoring methods. The model parameters are estimated using the expectation maximization (EM) algorithm, and the distributions of monitoring statistics are rigorously derived and proved for calculating control limits. Contribution analysis methods are presented for identifying faulty variables and the equivalence between classical multivariate monitoring models and their corresponding probabilistic graphic models is investigated.

AUTOMATICA (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Data-Driven Designs of Fault Detection Systems via Neural Network-Aided Learning

Hongtian Chen et al.

Summary: This article develops two data-driven fault detection designs for dynamic systems using neural networks, finding optimal architectures through self-organizing learning and establishing connections between model- and neural-network-based methods. An experiment on a three-tank system demonstrates the effectiveness of the proposed neural network-aided FD algorithms.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022)

Add to Collection

Article Automation & Control Systems

Multisource-Refined Transfer Network for Industrial Fault Diagnosis Under Domain and Category Inconsistencies

Zheng Chai et al.

Summary: This study proposes a multisource-refined transfer network to address domain and category inconsistencies in fault diagnosis. It first designs a refined adversarial adaptation strategy to reduce refined categorywise distribution inconsistency within each source-target domain pair. Then, it develops a multiple classifier complementation module to transfer different diagnostic knowledge by complementing source classifiers to the target domain.

IEEE TRANSACTIONS ON CYBERNETICS (2022)

Add to Collection

Article Automation & Control Systems

Distributed Intermittent Fault Detection for Linear Stochastic Systems Over Sensor Network

Yichun Niu et al.

Summary: This article investigates the problem of intermittent fault detection for linear stochastic systems over sensor networks. A novel residual generator is designed using the moving-horizon estimator to realize the distributed detection of IFs. Global detectability conditions and a cooperative decision-making strategy are proposed to ensure only one detection result and avoid collisions of detection results.

IEEE TRANSACTIONS ON CYBERNETICS (2022)

Add to Collection

Article Engineering, Chemical

New Nonlinear Approach for Process Monitoring: Neural Component Analysis

Zhijiang Lou et al.

Summary: The proposed Neural Component Analysis (NCA) combines artificial neural networks (ANN) with principal component analysis (PCA) to address the common nonlinearity in industrial processes. NCA, with a similar network structure as ANN and utilizing the gradient descent method for training, successfully extracts uncorrelated components from the process data with PCA's dimension reduction strategy, and constructs statistical indices for process monitoring, showing superior performance compared to other nonlinear approaches in simulation tests.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2021)

Add to Collection

Article Automation & Control Systems

Detection of intermittent faults based on an optimally weighted moving average T2 control chart with stationary observations

Yinghong Zhao et al.

Summary: The MA-type scheme, also known as the smoothing method, has been established within the MSPM framework since the 1990s. This paper introduces an optimally weighted moving average theory for detecting intermittent faults, improving on the existing MA method.

AUTOMATICA (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Explainability: Relevance based dynamic deep learning algorithm for fault detection and diagnosis in chemical processes

Piyush Agarwal et al.

Summary: This study focuses on the Statistical Process Control (SPC) of a manufacturing process using deep learning for fault detection and diagnosis (FDD). The application of explainable artificial intelligence (XAI) enhances model accuracy by quantifying explainability through a novel relevance measure of input variables, iteratively discards redundant input feature vectors/variables.

COMPUTERS & CHEMICAL ENGINEERING (2021)

Add to Collection

Article Automation & Control Systems

Output-Relevant Common Trend Analysis for KPI-Related Nonstationary Process Monitoring With Applications to Thermal Power Plants

Dehao Wu et al.

Summary: This article discusses the importance of operation safety and efficiency in power plants, and introduces the concept of KPI-related nonstationary process monitoring to detect anomalies and assess their impact. The Output-relevant Common Trend Analysis (OCTA) method is proposed to model the relationship between input and output variables in thermal power plants, showing superior monitoring performance in detecting anomalies and determining their impact on thermal efficiency.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

Add to Collection

Article Automation & Control Systems

Distributionally robust fault detection design and assessment for dynamical systems

Chao Shang et al.

Summary: This novel approach presents a distributionally robust optimization method to tackle the uncertainty of probability distributions in fault detection system design and assessment. By using two different ambiguity sets to describe uncertainty, specific statistical properties in fault detection can be achieved. Through solving tractable convex programs, the worst-case and best-case detectability under known faults can be evaluated efficiently.

AUTOMATICA (2021)

Add to Collection

Article Engineering, Chemical

Process Monitoring Using a Novel Robust PCA Scheme

Zhijiang Lou et al.

Summary: This study proposes a novel robust PCA scheme called MRPCA, which adopts a difference selection mechanism for outlier samples in the offline training stage and an outlier detection mechanism for distinguishing outliers from fault data in the online monitoring stage. With these mechanisms, MRPCA achieves high fault detection rates and low false alarm rates in tests.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2021)

Add to Collection

Article Automation & Control Systems

A Holistic Probabilistic Framework for Monitoring Nonstationary Dynamic Industrial Processes

David Scott et al.

Summary: Multivariate statistical process monitoring methods provide sensitive indicators of process conditions by utilizing large amounts of process data. A novel nonstationary probabilistic slow feature analysis algorithm is developed to comprehensively describe nonstationary and stationary variations, with the expectation-maximization algorithm used for efficient parameter estimation. Interpretable monitoring statistics are constructed to detect abnormalities in nonstationary and stationary dynamics, forming a holistic and pragmatic monitoring framework for industrial processes.

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY (2021)

Add to Collection

Article Automation & Control Systems

Semisupervised Bayesian Gaussian Mixture Models for Non-Gaussian Soft Sensor

Weiming Shao et al.

Summary: A semisupervised Bayesian GMM (S(2)BGMM) method is proposed to learn from both labeled and unlabeled datasets, addressing the issue of limited labeled samples. Case studies demonstrate the effectiveness and reliability of the proposed approach in industrial processes.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Degradation State Partition and Compound Fault Diagnosis of Rolling Bearing Based on Personalized Multilabel Learning

Xin Ma et al.

Summary: This study proposes two multilabel learning algorithms, PBR and HML-KNN, for PHM of rolling bearings. They both have a personalized search process and can help solve the problem of data imbalance. Both algorithms have achieved good results in the XJTU-SY bearing dataset.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2021)

Add to Collection

Review Engineering, Civil

A Review of Fault Detection and Diagnosis for the Traction System in High-Speed Trains

Hongtian Chen et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2020)

Add to Collection

Article Automation & Control Systems

Online Tool Condition Monitoring Based on Parsimonious Ensemble

Mahardhika Pratama et al.

IEEE TRANSACTIONS ON CYBERNETICS (2020)

Add to Collection

Article Automation & Control Systems

Recursive cointegration analytics for adaptive monitoring of nonstationary industrial processes with both static and dynamic variations

Wanke Yu et al.

JOURNAL OF PROCESS CONTROL (2020)

Add to Collection

Article Automation & Control Systems

Whole Process Monitoring Based on Unstable Neuron Output Information in Hidden Layers of Deep Belief Network

Jianbo Yu et al.

IEEE TRANSACTIONS ON CYBERNETICS (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Multistep Dynamic Slow Feature Analysis for Industrial Process Monitoring

Xin Ma et al.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2020)

Add to Collection

Article Engineering, Chemical

Dynamic Stationary Subspace Analysis for Monitoring Nonstationary Dynamic Processes

Dehao Wu et al.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2020)

Add to Collection

Article Automation & Control Systems

An Improved Mixture of Probabilistic PCA for Nonlinear Data-Driven Process Monitoring

Jingxin Zhang et al.

IEEE TRANSACTIONS ON CYBERNETICS (2019)

Add to Collection

Article Automation & Control Systems

Recent Advances in Key-Performance-Indicator Oriented Prognosis and Diagnosis With a MATLAB Toolbox: DB-KIT

Yuchen Jiang et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2019)

Add to Collection

Article Engineering, Chemical

Survey on the theoretical research and engineering applications of multivariate statistics process monitoring algorithms: 2008-2017

Youqing Wang et al.

CANADIAN JOURNAL OF CHEMICAL ENGINEERING (2018)

Add to Collection

Article Automation & Control Systems

Recursive Dynamic Transformed Component Statistical Analysis for Fault Detection in Dynamic Processes

Jun Shang et al.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2018)

Add to Collection

Article Automation & Control Systems

Weighted Linear Dynamic System for Feature Representation and Soft Sensor Application in Nonlinear Dynamic Industrial Processes

Xiaofeng Yuan et al.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2018)

Add to Collection

Article Automation & Control Systems

Canonical Variate Dissimilarity Analysis for Process Incipient Fault Detection

Karl Ezra Salgado Pilario et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2018)

Add to Collection

Article Automation & Control Systems

A novel dynamic PCA algorithm for dynamic data modeling and process monitoring

Yining Dong et al.

JOURNAL OF PROCESS CONTROL (2018)

Add to Collection

Article Engineering, Chemical

A Full-Condition Monitoring Method for Nonstationary Dynamic Chemical Processes with Cointegration and Slow Feature Analysis

Chunhui Zhao et al.

AICHE JOURNAL (2018)

Add to Collection

Article Engineering, Chemical

Two-step principal component analysis for dynamic processes monitoring

Zhijiang Lou et al.

CANADIAN JOURNAL OF CHEMICAL ENGINEERING (2018)

Add to Collection

Article Automation & Control Systems

Fault Detection for Nonlinear Process With Deterministic Disturbances: A Just-In-Time Learning Based Data Driven Method

Shen Yin et al.

IEEE TRANSACTIONS ON CYBERNETICS (2017)

Add to Collection

Article Automation & Control Systems

Recursive transformed component statistical analysis for incipient fault detection

Jun Shang et al.

AUTOMATICA (2017)

Add to Collection

Article Automation & Control Systems

A New Multivariate Approach for Prognostics Based on Extreme Learning Machine and Fuzzy Clustering

Kamran Javed et al.

IEEE TRANSACTIONS ON CYBERNETICS (2015)

Add to Collection

Article Automation & Control Systems

Decentralized Fault Diagnosis of Continuous Annealing Processes Based on Multilevel PCA

Qiang Liu et al.

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING (2013)

Add to Collection

Article Engineering, Chemical

Fault Detection and Diagnosis in Chemical Processes Using Sensitive Principal Component Analysis

Qingchao Jiang et al.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2013)

Add to Collection

Article Engineering, Chemical

Nonlinear process monitoring using kernel principal component analysis

JM Lee et al.

CHEMICAL ENGINEERING SCIENCE (2004)

Add to Collection

© Peeref 2019-2024. All rights reserved.