Piecewise-Linear Output-Error Methods for Parameter Estimation in Direction-Dependent Processes

In direction-dependent processes, the dynamic responses depend on the direction of the system input. The parameter estimation of these processes under noisy conditions can be somewhat problematic in terms of predictor choice and asymptotic behaviour. For parameter estimation, a convenient way to model direction dependence is to use a piecewise-linear model formulation, whose switching depends on the input direction. This paper analyses a prediction-error minimisation method for direction-dependent processes in terms of piecewise-linear dynamics. In particular, the asymptotic convergence properties are investigated and relevant conditions for the utilisation of the estimation method are given. Further, it is demonstrated that a piecewise-linear output-error predictor is preferable in situations where the impact of disturbances is predominant. The main reason for this is that it separates the disturbances from the process model.

[1]  Henrik Sandberg,et al.  Frequency-domain analysis of linear time-periodic systems , 2005, IEEE Transactions on Automatic Control.

[2]  Tore Hägglund,et al.  On identification and control tuning of cylinder dryers , 2002 .

[3]  Karl Johan Åström,et al.  A grey-box model for steam pressure dynamics in the drying section of a paper machine , 2004 .

[4]  Magnus K. Karlsson,et al.  Evaluation of models for the steam supply system to improve control of the paper dryer , 2003 .

[5]  Tore Hägglund,et al.  Automatic detection of sluggish control loops , 1999 .

[7]  Manfred Morari,et al.  Identification of piecewise affine and hybrid systems , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[8]  Karl-Erik Årzén,et al.  Implementation of a Tool for Control Structure Assessment , 2002 .

[9]  Piecewise-Linear Output-Error Models , 2003 .

[10]  E. Furusjö,et al.  Uncertainty in rate constants estimated from spectral data with baseline drift , 2000 .

[11]  R. Pearson.  Selecting nonlinear model structures for computer control , 2003 .

[12]  Keith R. Godfrey,et al.  Wiener models of direction-dependent dynamic systems , 2003, Autom..

[13]  Tore Hägglund,et al.  Criteria for Design of PID Controllers , 2003 .

[14]  W. Rugh.  Linear System Theory , 1992 .

[15]  Bengt Andersson,et al.  Experimental and Numerical Investigations of a Jet Mixing in a Multifunctional Channel Reactor: Passive and Reactive Systems , 2004 .

[16]  Effective model reduction for analysis of distributed parameter systems , 2001 .

[17]  K.J. Astrom,et al.  Modeling of a steam heated rotating cylinder - a grey-box approach , 2005, Proceedings of the 2005, American Control Conference, 2005..

[18]  Torsten Wik,et al.  A CLOSED LOOP APPROACH TO TANK REACTOR MODEL SIMPLIFICATION , 2005 .

[19]  Anders Björk,et al.  Spectra of wavelet scale coefficients from process acoustic measurements as input for PLS modelling of pulp quality , 2002 .

[20]  Yi Liu,et al.  Error Detection and Control in Grey-Box Identification of Distributed Parameter Processes , 2004 .

[21]  Modelling of forming and densification of fibre mats in twin-wire formers , 2005 .

[22]  E. Yaz.  Linear Matrix Inequalities In System And Control Theory , 1998, Proceedings of the IEEE.

[23]  Keith R. Godfrey,et al.  Identification of processes having direction-dependent responses, with gas-turbine engine applications , 1974 .

[24]  Magnus K. Karlsson,et al.  Dynamic simulation of the steam supply system for a multi-cylinder dryer , 2002 .

[25]  Wilson J. Rugh,et al.  Linear system theory (2nd ed.) , 1996 .

[26]  Rasmus Olsson,et al.  Closing the information loop in recipe-based batch production , 2005 .

[27]  Ari Ingimundarson.  PERFORMANCE MONITORING OF PI CONTROLLERS USING A SYNTHETIC GRADIENT OF A QUADRATIC COST FUNCTION , 2002 .

[28]  Magnus K. Karlsson,et al.  Modeling and control tuning of multi-cylinder dryers , 2002 .

[29]  L. Ljung.  Convergence analysis of parametric identification methods , 1978 .

[30]  Exception Handling in S88 using Grafchart , 2002 .

[31]  Magnus K. Karlsson,et al.  Reducing moisture transients in the paper-machine drying section with the mid-ranging control technique , 2005 .

[32]  Anders Björk,et al.  Extraction of distribution curves from process acoustic measurements on a TMP-process , 2004 .

[33]  Anders Björk,et al.  Predicting Pulp Quality from Process Acoustic Measurements on a Medium Concistency Pulp Stream , 2006 .

[34]  Henrik Sandberg,et al.  Periodic Modelling of Power Systems , 2001 .

[35]  Yi Liu,et al.  A control theoretic approach to mesh methods model reduction of PDESߞMoving mesh methods , 2002 .

[36]  Fredrik Rosenqvist,et al.  Modelling a thermomechanical wood-chip refiner , 2001 .

[37]  Per Hagander,et al.  Process control of an open plate reactor , 2005 .

[38]  Krister Forsman,et al.  Productivity increase from a better understanding of dynamic processes and control of the paper dryer , 2002 .

[39]  L. Ljung,et al.  Identification of hybrid systems via mixed-integer programming , 2001 .

[40]  Tore Hägglund,et al.  Robust tuning procedures of dead-time conpensating controllers , 2001 .

[41]  Pierre Roussel-Ragot,et al.  Training recurrent neural networks: why and how? An illustration in dynamical process modeling , 1994, IEEE Trans. Neural Networks.

[42]  S. Billings,et al.  Piecewise linear identification of non-linear systems , 1987 .

[43]  Per Hagander,et al.  Mid-ranging control of the cooling temperature for an Open Plate Reactor , 2004 .

[45]  Tore Hägglund,et al.  Performance comparison between PID and dead-time compensating controllers , 2002 .

[46]  Julian Morris,et al.  Nonlinear and direction-dependent dynamic process modelling using neural networks , 1996 .

[47]  Vinícius Lobosco,et al.  The stress-strain relationship of the fibre network in wet pressing , 2005 .

[48]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[49]  I-Lung Chien,et al.  Nonlinear identification and control of a high-purity distillation column: a case study , 1995 .

[50]  Vinícius Lobosco,et al.  An elastic/viscoplastic model of the fibre network stress in wet pressing: Part 2 Accounting for pulp properties and web temperature , 2001 .

[51]  Stig Stenström,et al.  Static and Dynamic Modeling of Cardboard Drying Part 2: Simulations and Experimental Results , 2005 .

[52]  Tore Hägglund,et al.  Implementation of an on-line detection procedure for oscillating control loops , 2002 .

[53]  Mixing of a Jet in a Pipe , 2004 .

[54]  Henrik Sandberg,et al.  A case study in model reduction of linear time-varying systems , 2004, Autom..

[55]  Tore Hägglund,et al.  Closed-Loop Identification of a First-Order Plus Dead-Time Model with Method of Moments , 2000 .

[56]  Stig Stenström,et al.  Static and Dynamic Modeling of Cardboard Drying Part 1: Theoretical Model , 2005 .

[57]  S. Stenström,et al.  Measurement of volume fractions of solid, liquid and gas in kraft and CTMP paper at varying moisture content , 2003 .

[58]  F. Rosenqvist,et al.  Controllability of direction-dependent processes , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[59]  Tore Hägglund.  INDUSTRIAL APPLICATIONS OF AUTOMATIC PERFORMANCE MONITORING TOOLS , 2002 .

[60]  K. R. Godfrey,et al.  Identification of processes with direction-dependent dynamic responses , 1972 .

[61]  Keith R. Godfrey,et al.  Identification of processes with direction-dependent dynamics , 2001 .

[62]  Henrik Sandberg,et al.  A Grassmannian approach to the Hankel norm approximation problem , 2003 .

[63]  Ari Ingimundarson,et al.  On a synthesis method for robust PID controllers for a class of uncertainties , 2003, 2003 European Control Conference (ECC).

[64]  Olof Svensson,et al.  Estimation of kinetic parameters from non-isothermal batch experiments monitored by in situ vibrational spectroscopy , 2003 .

[65]  Henrik Sandberg,et al.  A Bode sensitivity integral for linear time-periodic systems , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[66]  A. Rantzer,et al.  Error bounds for balanced truncation of linear time-varying systems , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[67]  Robin J. Evans,et al.  Extremal control of Wiener model processes , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[68]  A CONTROL THEORETIC APPROACH TO MODEL REDUCTION OF PDES – MOVING MESH METHODS , 2002 .

[69]  Yi Liu,et al.  On the use of reduced order models in bifurcation analysis of distributed parameter systems , 2004, Comput. Chem. Eng..

[70]  Per Hagander,et al.  Temperature control of a utility system for an Open Plate Reactor , 2004 .

[71]  Ingela Niklasson Björn,et al.  Simulation and experimental study of intermediate heat exchange in a sieve tray distillation column , 2002 .

[72]  Tore Hägglund,et al.  Robust Automatic Tuning of an Industrial PI Controller for Dead-Time Systems , 2000 .

[73]  Lennart Ljung,et al.  Nonlinear black-box modeling in system identification: a unified overview , 1995, Autom..

[74]  Fredrik Rosenqvist,et al.  Internal interconnections in TMP refining , 2002 .

[75]  Henrik Sandberg,et al.  Balanced model reduction of linear time-varying systems , 2002 .

[76]  Rasmus Olsson,et al.  A Modular Batch Laboratory Process , 2004 .

[77]  Tor Arne Johansen,et al.  On convergence proofs in system identification—a general principle using ideas from learning theory , 1998 .

[78]  Yi Liu,et al.  Grey-Box Modelling of Distributed Parameter Processes - Application to Chromatography , 2004 .

[79]  Stephen P. Boyd,et al.  Linear Matrix Inequalities in Systems and Control Theory , 1994 .

[80]  Rasmus Olsson,et al.  Exception Handling in Recipe-Based Batch Control , 2000 .