Application of Neural Networks and Other Learning Technologies in Process Engineering
This book is a follow-up to the IChemE symposium on OC Neural Networks and Other Learning TechnologiesOCO, held at Imperial College, UK, in May 1999. The interest shown by the participants, especially those from the industry, has been instrumental in producing the book. The papers have been written by contributors of the symposium and experts in this field from around the world. They present all the important aspects of neural network utilisation as well as show the versatility of neural networks in various aspects of process engineering problems OCo modelling, estimation, control, optimisation and industrial applications. Contents: Modelling and Identification; Hybrid Schemes; Estimations and Control; New Learning Technologies; Experimental and Industrial Applications. Readership: Academic and industrial researchers, chemical engineers and control engineers."
What people are saying - Write a review
We haven't found any reviews in the usual places.
Estimation and Control
New Learning Technologies
Experimental and Industrial Applications
Other editions - View all
adaptive analysis applications approach approximation artificial neural networks ARTnet back-propagation batch distillation batch reactor behaviour calculated Chem clustering Comput control actions control strategy data patterns data set developed distillate dynamic trend error estimation ethanol Extended Kalman Filter feed fermentation Figure ﬂow rate ﬂowrate forward model fuzzy GMC controller heat hidden layer hybrid model identification initial input vector inverse model Kalman filter linear liquid-liquid extraction LPCVD mass transfer matrix measured method model predictive control Mujtaba multivariable neural controller neural network model neurons nodes noise nonlinear obtained on-line optimal control optimum parameters performance phase PID controller plant plant-model mismatches polymerisation radial basis function RBFN model reaction reactor temperature recurrent neural network reﬂux ratio sampling scheme set-point shown in Fig simulation stacked neural network stepwise regression structure substrate techniques training data unsupervised update validation data value function variables wafers weights