A combined Markov chain model and generalized projection nonnegative matrix factorization approach for fault diagnosis
Summary: The presence of sets of incomplete measurements is a significant issue in the real-world application of multivariate statistical process monitoring models for industrial process fault detection. Since the missing data in the incomplete measurements are usually correlated with some of the available variables, these measurements can be used if an efficient algorithm is presented. To resolve the problem, a novel method combining Markov chain model and generalized projection nonnegative matrix factorization (MCM-GPNMF) is proposed to detect and diagnose the faults in industrial process. The basic idea of the approach is to use MCM-GPNMF to extract the dominant variables from incomplete process data and to combine them with statistical process monitoring techniques. \(T_G^2\) and \(\text{SPE}_G\) statistics are defined as online monitoring quantities for fault detection and corresponding contribution plots are also considered for fault isolation. The proposed method is applied to a 1000 MW unit boiler process. The simulation results clearly illustrate the feasibility of the proposed method.
- Fault detection and diagnosis strategy based on k-nearest neighbors and fuzzy C-means clustering algorithm for industrial processes
- Multimode process monitoring method based on multiblock projection nonnegative matrix factorization
- Fault detection and diagnosis of non-linear non-Gaussian dynamic processes using kernel dynamic independent component analysis
- Data-driven fault detection for industrial processes. Canonical correlation analysis and projection based methods
- Fault detection in continuous processes using multivariate statistical methods
- An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology
- scientific article; zbMATH DE number 3954111 (Why is no real title available?)
- scientific article; zbMATH DE number 3561857 (Why is no real title available?)
- scientific article; zbMATH DE number 3227378 (Why is no real title available?)
- Learning the parts of objects by non-negative matrix factorization
- Reconstruction-based contribution for process monitoring
- Semiadaptive fault diagnosis via variational Bayesian mixture factor analysis with application to wastewater treatment
- Adaptive fault detection and diagnosis using parsimonious Gaussian mixture models trained with distributed computing techniques
- Fault detection and diagnosis strategy based on k-nearest neighbors and fuzzy C-means clustering algorithm for industrial processes
- Fault detection of uncertain chemical processes using interval partial least squares-based generalized likelihood ratio test
- 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
- Data-driven fault detection for industrial processes. Canonical correlation analysis and projection based methods
- Compound fault diagnosis method based on multi-signal model and blind source separation
- An industrial process fault diagnosis method based on independent slow feature analysis and stacked sparse autoencoder network
- Fault detection and isolation of multi-variate time series data using spectral weighted graph auto-encoders
- Generating hidden Markov models from process models through nonnegative tensor factorization
- A model for real-time failure prognosis based on hidden Markov model and belief rule base
This page was built for publication: A combined Markov chain model and generalized projection nonnegative matrix factorization approach for fault diagnosis
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1993069)
