Adaptive CIPCA-based fault diagnosis scheme for uncertain time-varying processes

Data-driven is the use of data to drive knowledge and decisions. This has the potential to produce better results but can also suboptimal based on a misinterpretation of data, faulty data, and/or missing data. It is therefore interesting to study the problem of uncertainties in the data and how to integrate them into the models in order to improve performances. Principal component analysis (PCA) is one of the most popular data-driven approaches that is not designed to handle the uncertainty of the sensor measurements represented by interval type data. The complete information PCA (CIPCA) is one of the pioneering static approaches in the processing of interval data. Because the process operating conditions and their parameters may vary over time, as well as the oldest data that are not representative of the current process operation, a continuous update of the CIPCA model is necessary. The objective of this paper is to design an adaptive version of the CIPCA methodology for handling complex data, i.e., time-varying and interval data. At each time instant, when a new uncertain measurement of interval type is available, the CIPCA model is recursively updated, where recursive formulas for updating weighted mean and covariance matrix of interval-valued data are proposed. Indeed, the proposed CIPCA approach allows a robust and recursive representation, which improves fault detection and isolation decisions. Based on the updated CIPCA model, the interval $$T^2$$ and SPE statistics are calculated and used to monitor the operating conditions of a process. A wind turbine benchmark is adopted to confirm the effectiveness of the proposed method. The results show that the proposed adaptive CIPCA method for fault detection and isolation in wind turbines is quite promising.

[1]  Xiao Bin He,et al.  Variable MWPCA for Adaptive Process Monitoring , 2008 .

[2]  Donghua Zhou,et al.  On the use of reconstruction-based contribution for fault diagnosis , 2016 .

[3]  Henry Hong,et al.  Wind Turbine Fault Diagnosis and Fault-Tolerant Torque Load Control Against Actuator Faults , 2015, IEEE Transactions on Control Systems Technology.

[4]  Tianyou Chai,et al.  Fault diagnosis of continuous annealing processes using a reconstruction-based method , 2012 .

[5]  Abdelhafid Benyounes,et al.  Diagnosis of uncertain nonlinear systems using interval kernel principal components analysis: Application to a weather station. , 2018, ISA transactions.

[6]  Michel Verhaegen,et al.  Sensor Fault Diagnosis of Wind Turbines for Fault Tolerant , 2008 .

[7]  S. Wold.  Exponentially weighted moving principal components analysis and projections to latent structures , 1994 .

[8]  Weihua Li,et al.  Recursive PCA for adaptive process monitoring , 1999 .

[9]  Ahlame Douzal-Chouakria.  Extension des méthodes d'analyse factorielles à des données de type intervalle , 1998 .

[10]  Paul M. Frank,et al.  Issues of Fault Diagnosis for Dynamic Systems , 2010, Springer London.

[11]  J. E. Jackson,et al.  Control Procedures for Residuals Associated With Principal Component Analysis , 1979 .

[12]  In-Beum Lee,et al.  Adaptive multivariate statistical process control for monitoring time-varying processes , 2006 .

[13]  G. Irwin,et al.  Process monitoring approach using fast moving window PCA , 2005 .

[14]  Ivan Izonin,et al.  Model and Principles for the Implementation of Neural-Like Structures Based on Geometric Data Transformations , 2018 .

[15]  S. Joe Qin,et al.  Analysis and generalization of fault diagnosis methods for process monitoring , 2011 .

[16]  M. Kramer.  Nonlinear principal component analysis using autoassociative neural networks , 1991 .

[17]  Si-Zhao Joe Qin,et al.  Reconstruction-based contribution for process monitoring , 2009, Autom..

[18]  Chouaib Chakour,et al.  Simultaneous Fault Detection and Diagnosis Using Adaptive Principal Component Analysis and Multivariate Contribution Analysis , 2020 .

[19]  S. Joe Qin.  Statistical process monitoring: basics and beyond , 2022 .

[20]  S. Joe Qin,et al.  Subspace approach to multidimensional fault identification and reconstruction , 1998 .

[21]  Bogdan Gabrys,et al.  Review of adaptation mechanisms for data-driven soft sensors , 2011, Comput. Chem. Eng..

[22]  F. Palumbo,et al.  A PCA for interval-valued data based on midpoints and radii , 2003 .

[23]  Hamid Reza Karimi,et al.  Data-driven design of robust fault detection system for wind turbines , 2014 .

[24]  E. Diday,et al.  Extension de l'analyse en composantes principales à des données de type intervalle , 1997 .

[25]  Carlos F. Alcala,et al.  Reconstruction-based contribution for process monitoring with kernel principal component analysis , 2010, Proceedings of the 2010 American Control Conference.

[26]  Jef Vanlaer,et al.  Contribution plots for Statistical Process Control: Analysis of the smearing-out effect , 2013, 2013 European Control Conference (ECC).

[27]  Uwe Kruger,et al.  Statistical monitoring of complex multivariate processes : with applications in industrial process control , 2012 .

[28]  Chouaib Chakour,et al.  Neuronal principal component analysis for nonlinear time-varying processes monitoring , 2015 .

[29]  Antonio Irpino,et al.  Principal Component Analysis of Symbolic Data Described by Intervals , 2008 .

[30]  Natalia Kryvinska,et al.  Multiple Linear Regression Based on Coefficients Identification Using Non-iterative SGTM Neural-like Structure , 2019, IWANN.

[31]  Hazem Nounou,et al.  A Hybrid Approach for Process Monitoring: Improving Data-Driven Methodologies With Dataset Size Reduction and Interval-Valued Representation , 2020, IEEE Sensors Journal.

[32]  Junjie Wu,et al.  CIPCA: Complete-Information-based Principal Component Analysis for interval-valued data , 2012, Neurocomputing.

[33]  Lamiaa M. Elshenawy,et al.  Efficient Recursive Principal Component Analysis Algorithms for Process Monitoring , 2010 .

[34]  S. Joe Qin,et al.  Statistical process monitoring: basics and beyond , 2003 .

[35]  Peter Fogh Odgaard,et al.  Fault-Tolerant Control of Wind Turbines: A Benchmark Model , 2009, IEEE Transactions on Control Systems Technology.

[36]  Frédéric Kratz,et al.  On the application of interval PCA to process monitoring: A robust strategy for sensor FDI with new efficient control statistics , 2018 .

[37]  John Taylor,et al.  Statistical Techniques for Data Analysis , 1990 .

[38]  Thomas F. Edgar,et al.  Identification of faulty sensors using principal component analysis , 1996 .