Control Loop Performance Assessment With a Dynamic Neuro-Fuzzy Model (dFasArt)

Most of the industrial controllers have some kind of performance problem. This feature is becoming more difficult to supervise and assess because of the increasing number of control loops of the processes. A new method for monitoring and performance assessment by using a neuro-fuzzy architecture is proposed. This method is based on the dFasArt model, which allows for a self-organizing classification (nonsupervised) of dynamic signals and building categories that can be easily interpreted in terms of fuzzy theory. A new fuzzy performance index (FPI) is defined, leading to a straight online assessment of the control loops. A great advantage compared with other techniques is that the method can be also applied to find relationships between process variables and to establish propagation paths. Other advantages of this method are as follows: 1) it is not necessary to obtain the model of the plant; 2) it can be applied online, in parallel with the process, without any dedicated experiment; and 3) the results are clearly presented to plant operator to help the control engineer to decide how to improve the control performance.

[1]  J. Feng,et al.  Intelligent system architecture for process operation support , 2000 .

[2]  Eduardo Gómez-Sánchez,et al.  Automatization of a penicillin production process with soft sensors and an adaptive controller based on neuro fuzzy systems , 2004 .

[3]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[4]  J. Bendat,et al.  Random Data: Analysis and Measurement Procedures , 1971 .

[5]  N. F. Thornhilla,et al.  Spectral principal component analysis of dynamic process data , 2002 .

[6]  Nina F. Thornhill,et al.  Diagnosis of poor control-loop performance using higher-order statistics , 2004, Autom..

[7]  Md. A. A. Shoukat Choudhury,et al.  Performance Assessment of Control Loops , 2012 .

[8]  Alan J. Hugo,et al.  Performance assessment of single-loop industrial controllers , 2006 .

[9]  Wei Yu,et al.  Control performance assessment for nonlinear systems , 2010 .

[10]  G. Feng,et al.  A Survey on Analysis and Design of Model-Based Fuzzy Control Systems , 2006, IEEE Transactions on Fuzzy Systems.

[11]  Nf F. Thornhill,et al.  New directions in control loop assessment and diagnosis , 2005 .

[12]  Rachelle Howard,et al.  A novel pattern-based approach for diagnostic controller performance monitoring , 2010 .

[13]  J. Manuel Cano Izquierdo,et al.  dFasArt: Dynamic neural processing in FasArt model , 2009, Neural Networks.

[14]  P.-G. Eriksson,et al.  Some aspects of control loop performance monitoring , 1994, 1994 Proceedings of IEEE International Conference on Control and Applications.

[15]  J. R. García Cascales,et al.  MODELLING AN ABSORPTION SYSTEM ASSISTED BY SOLAR ENERGY , 2011 .

[16]  John W. Cox,et al.  A practical approach for large-scale controller performance assessment, diagnosis, and improvement , 2003 .

[17]  Bart Kosko,et al.  Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence , 1991 .

[18]  Ali Cinar,et al.  Controller performance assessment by frequency domain techniques , 1997 .

[19]  John H. L. Hansen,et al.  Discrete-Time Processing of Speech Signals , 1993 .

[20]  C. T. Seppala,et al.  A review of performance monitoring and assessment techniques for univariate and multivariate control systems , 1999 .

[21]  Alireza Fatehi,et al.  Identification, Prediction and Detection of the Process Fault in a Cement Rotary Kiln by Locally Linear Neuro-Fuzzy Technique , 2009, 2009 Second International Conference on Computer and Electrical Engineering.

[22]  Alf Isaksson,et al.  A modified index for control performance assessment , 1998, Proceedings of the 1998 American Control Conference. ACC (IEEE Cat. No.98CH36207).

[23]  Warren R. DeVries,et al.  Evaluation of process control effectiveness and diagnosis of variation in paper basis weight via multivariate time-series analysis , 1978 .

[24]  J. Manuel Cano Izquierdo,et al.  Applying neuro-fuzzy model dFasArt in control systems , 2010, Eng. Appl. Artif. Intell..

[25]  G.A. Dumont,et al.  Control loop performance monitoring , 1996, IEEE Trans. Control. Syst. Technol..

[26]  Manfred Morari,et al.  Performance monitoring of control systems using likelihood methods , 1996, Autom..