Fault detection and isolation of multi-variate time series data using spectral weighted graph auto-encoders

DOI10.1016/J.JFRANKLIN.2023.04.030MaRDI QIDQ6168965zbMATH OpenOpenAlexFDO

Authors Umang Goswami, Jyoti Rani, Hariprasad Kodamana, Sandeep Kumar, Prakash Kumar Tamboli

Publication date 11 July 2023

Published in Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.jfranklin.2023.04.030

Mathematics Subject Classification ID

Applications of graph theory (05C90) Multivariable systems, multidimensional control systems (93C35) Time-scale analysis and singular perturbations in control/observation systems (93C70)

Recommendations

• Fault detection and diagnosis strategy based on k-nearest neighbors and fuzzy C-means clustering algorithm for industrial processes
• Early malfunction diagnosis of industrial process units utilizing online linear trend profiles and real-time classification
• Fault identification in industrial processes using an integrated approach of neural network and analysis of variance
• Fault detection of uncertain chemical processes using interval partial least squares-based generalized likelihood ratio test
• A combined Markov chain model and generalized projection nonnegative matrix factorization approach for fault diagnosis

Cites work

• A process monitoring and fault isolation framework based on variational autoencoders and branch and bound method
• Active fault diagnosis for a class of closed-loop systems via parameter estimation
• Canonical correlation analysis-based explicit relation discovery for statistical process monitoring
• Data-driven design of fault detection and isolation method for distributed homogeneous systems
• Dynamic nonlinear process monitoring based on dynamic correlation variable selection and kernel principal component regression
• Fault detection and diagnosis strategy based on k-nearest neighbors and fuzzy C-means clustering algorithm for industrial processes
• Graph Representation Learning
• Learning Laplacian Matrix in Smooth Graph Signal Representations
• Multivariate statistical process monitoring based on principal discriminative component analysis
• Online reconstruction and diagnosibility analysis of multiplicative fault models for process-related faults
• Optimization Algorithms for Graph Laplacian Estimation via ADMM and MM
• Process monitoring using a generalized probabilistic linear latent variable model
• Sparse inverse covariance estimation with the graphical lasso

Cited in

(3)

• Analyzing business process anomalies using autoencoders
• Incipient fault detection and isolation with Cauchy-Schwarz divergence: a probabilistic approach
• An advanced data-driven method for nonlinear no-Gaussian quality-oriented fault diagnosis

This page was built for publication: Fault detection and isolation of multi-variate time series data using spectral weighted graph auto-encoders

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6168965)