A prediction control algorithm is presented based on least squares support vector machines (LS-SVM) model for a class of complex systems with strong nonlinearity. The nonlinear off-line model of the controlled plant i...
详细信息
A prediction control algorithm is presented based on least squares support vector machines (LS-SVM) model for a class of complex systems with strong nonlinearity. The nonlinear off-line model of the controlled plant is built by LS-SVM with radial basis function (RBF) kernel. In the process of system running, the off-line model is linearized at each sampling instant, and the generalized prediction control (GPC) algorithm is employed to implement the prediction control for the controlled *** obtained algorithm is applied to a boiler temperature control system with complicated nonlinearity and large time *** results of the experiment verify the effectiveness and merit of the algorithm.
This paper presents two soft-sensing models for predicting the product yields profile and the cracking degree of an ethylene pyrolysis furnace. The model based on single neural network with only one hidden layer train...
详细信息
ISBN:
(纸本)0780386531
This paper presents two soft-sensing models for predicting the product yields profile and the cracking degree of an ethylene pyrolysis furnace. The model based on single neural network with only one hidden layer trained by Levenberg-Marquardt algorithm with regularisation was first developed. It was found that the single neural network lack generalisation capability in that they can give undesirable performance when applied to unseen data. To improve the generalisation capability of the soft-sensing model, multi-model soft-sensors based on bootstrap aggregated neural networks with sequential training are used. In the sequential training of bootstrap aggregated networks, the first network is trained to minimise its prediction error whereas the rest of the networks are trained not only to minimise their prediction errors but also minimise the correlation among the trained networks. The overall output is obtained by combining all the individual networks. Application results show that the multi-model soft-sensors possess good generalisation capability in that they give good performance when applied to unseen data.
A synthetical method of multivariable control system performance assessment is proposed in this paper, which uses multivariable minimum variance control (MVC) benchmark to determine the stochastic performance, and nor...
详细信息
ISBN:
(纸本)0780382730
A synthetical method of multivariable control system performance assessment is proposed in this paper, which uses multivariable minimum variance control (MVC) benchmark to determine the stochastic performance, and normalized multivariate impulse response (NMIR) curve as an alternative measure of performance to test the dynamic performance, and with the help of auto-correlation function (ACF) and cross-correlation function (CCF) to analyse if there are oscillations exist. The method is applied to assess the performance of multivariable predictive control system of industrial distillation column.
controller performance assessment is a challenging task in industrial processcontrol. In this work, we review the state of research in controller performance assessment and monitoring, and present some commercial imp...
详细信息
controller performance assessment is a challenging task in industrial processcontrol. In this work, we review the state of research in controller performance assessment and monitoring, and present some commercial implementations of the technology in process industries. Challenges related to the controller performance evaluation are outlined for research and applications.
An improved Dynamic Time Warping (DTW) algorithm is presented which can be used in on-line fault detection. The two new monitoring approaches, the symmetric DTW and the simplified DTW combined with a multi-model multi...
详细信息
An improved Dynamic Time Warping (DTW) algorithm is presented which can be used in on-line fault detection. The two new monitoring approaches, the symmetric DTW and the simplified DTW combined with a multi-model multiway principal component analysis (MMPCA) are applied to the synchronization of the multivariate trajectories of an industrial batch process. The industrial application illustrates that the detection and diagnosis capabilities of the two new monitoring schemes are comparable to those achieved by primitive MMPCA and MPCA.
A control oriented hybrid model structure combining first principles models with standard black-box techniques for modelling nonlinear dynamics of reaction systems is presented in this paper. The approach is formulate...
详细信息
A control oriented hybrid model structure combining first principles models with standard black-box techniques for modelling nonlinear dynamics of reaction systems is presented in this paper. The approach is formulated in a general framework for continuous stirred tank reactors and analyzed in details through a case study of a reactive distillation column. The approach is based on easily established mass balance equations, the stoichiometry of the system as well as model reduction techniques. The choice of combined inputs and the model structure is motivated by some general control objectives for this class of systems. A progressive identification of this model structure can be performed when a dominant part exists. The application to real process data is presented. This model structure has been successfully used in an IMC scheme for an industrial reactive distillation column.
作者：
BULL, DNDaniel N. Bull
Ph.D. is a consultant in fermentation technology and president of Satori Corporation P.O. Box 1730 Montclair N.J. 07042. (201) 783-9787.REFERENCES Graff G.M. Short H. and Keene J.1983. Gene-splicing methods move from lab to plant. Chem. Eng.90: 22-27.|ISI|Broda P.1979. p. 1-3. Plasmids. W. H. Freeman Oxford and San Francisco.Donoghue D.J. and Sharp P.A.1978. Construction of a hybrid bacteriophage-plasmid recombinant DNA vector. J. Bact.136: 1192-1196.|PubMed|ISI|ChemPort|Bok S.H. Hoppe D. Mueller D.C. and Lee S.E.1983. Improving the production of recombinant DNA proteins through fermentation development. Abstract from 186th ACS Natl. Mtg. Washington D.C. Sept. 1.Maniatis T. Fritsch E.F. and Sam-brook J.1982. p. 88. Molecular Cloning. Cold Spring Harbor Laboratory. Guidelines for research involving recombinant DNA molecules June 1983
Fed. Reg.48: 24556-24581. Modifications of physical containment recommendations for large-scale uses of organisms containing recombinant DNA molecules. 1983. Recomb. DNA Tech. Bull.6: 69-70.Bull D.N. Thoma R.W. and Stinnett T.E.1983. Bioreactors for submerged culture. In:Adv. in Biotechnological Proc. A. Mizrahi and A. L. van Wezel (eds.) 1: 1-30.Schmidli B.L. and Swartz R.W.1982. Design considerations for aseptic fermentation. Presentation at 184th ACS Natl. Mtg. Kanas City MO.Sittig W.1982. The present state of fermentation reactors. J. Chem. Tech. Biotechnol.32: 47-58.|ISI|Strek F.1963. Intl. Chem. Eng.3: 533.Uhl V.W. and Gray J.B.1996. Mixing Theory and Practice Vol. I. Academic Press New York.Peters M.S. and Timmerhaus K.D.1968. p. 542. Plant Design and Economics for Chemical Engineers. McGraw-Hill New York.Dickey D.S. and Hicks R.W. Fundamentals of agitation. Chem. Eng.83: 93-100.Oldshue J.Y.1983. Fluid mixing technology and practice. Chem. Eng.90: 82-108.Kipke K.D.1981. Heat transfer in aerated non-Newtonian fluids. Abstract from 2nd Eur. Cong. Biotech. Eastbourne UK April 5-10.Blakebrough N. McM
暂无评论