Adaptive Prediction and Predictive Control
This monograph is concerned with the prediction and control of processes expressed by discrete-time models. It is assumed that the characteristics of the process may vary over time. The processes concerned may be linear or nonlinear, periodic or nonperiodic, single input/single output or simply output-only time series. The primary aim of the work is to provide comprehensive coverage of the principles, perspectives and methods of adaptive prediction. There is also an introduction to the popular methods of predictive control. The numerical and computational aspects of prediction and control methods often influence their success in operation, and for this reason the text gives them due consideration whenever possible.
What people are saying - Write a review
We haven't found any reviews in the usual places.
SOME POPULAR METHODS OF PREDICTIONS
ADAPTIVE PREDICTION USING TRANSFERFUNCTION
KALMAN FILTER AND STATESPACE APPROACHES
ORTHOGONAL TRANSFORMATION AND MODELLING
MODELLING OF NONLINEAR PROCESSES USING GMDH
MODELLING AND PREDICTION OF NONLINEAR PROCESSE
MODELLING AND PREDICTION
SMOOTHING AND FILTERING
ahead prediction algorithm Appendix applications basic chapter columns computed considered control law cost function covariance matrix data set deterministic discussed in Sec equation example exponential follows frequency components Gaussian given GMDH Hadamard matrix Hence hidden layer implementation input input-output Kalman filter least squares linear low-pass filtering LQ control LRPC LS estimation mean square error measurement update method model based modelling and prediction multistep prediction mxn matrix nearly periodic neural network nodes noise nonlinear transformation numerical stability optimal control orthogonal matrix orthogonal transformation output parameter estimation pattern performed period length periodic component periodic series polynomial predictive control predictor present problem process model produce quasiperiodic series recursive regression regressors Remarks representation robust sampling self-tuning sequence set point signal singular value decomposition sinter smoothing state-space diagram state-space model statistical stochastic process structure submodels subset selection sunspot SVR spectrum temperature validation variables vector y(k+p|k zero