Neural nets for the simulation of mineral processing operations: Part I. Theoretical principles

Abstract The ill-defined nature of processes in the metallurgical industry necessitates the quest for new modelling techniques to emulate features of processes which are poorly understood from a fundamental point of view. For this reason nonparametric regression techniques such as neural nets offer an appealing alternative to fundamental modelling. The robust associative and computational properties of neural networks make these regression tools ideally suited for the modelling of ill-defined systems. Being the most commonly-used connectionist network, sigmoidal backpropagation neural networks (SBNN's) have been shown to model metallurgical and chemical systems satisfactorily wothout any a prioir knowledge about the system provided sufficient data are available. This paper introduces the field of connectionists networks to the metallurgical process engineer and describes the fundamentals of an SBNN.

[1]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[2]  R. Bellman,et al.  V. Adaptive Control Processes , 1964 .

[3]  N.V. Bhat,et al.  Modeling chemical process systems via neural computation , 1990, IEEE Control Systems Magazine.

[4]  J. A. Leonard,et al.  Radial basis function networks for classifying process faults , 1991, IEEE Control Systems.

[5]  D. C. Psichogios,et al.  Direct and indirect model based control using artificial neural networks , 1991 .

[6]  Yih-Fang Huang,et al.  Bounds on the number of hidden neurons in multilayer perceptrons , 1991, IEEE Trans. Neural Networks.

[7]  David M. Himmelblau,et al.  FAULT DIAGNOSIS IN COMPLEX CHEMICAL PLANTS USING ARTIFICIAL NEURAL NETWORKS , 1991 .

[8]  R. Hecht-Nielsen,et al.  Application of feedforward and recurrent neural networks to chemical plant predictive modeling , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[9]  Etienne Barnard,et al.  The estimation of kinematic viscosity of petroleum crude oils and fractions with a neural net , 1993 .

[10]  Mark A. Kramer,et al.  Diagnosis using backpropagation neural networks—analysis and criticism , 1990 .

[11]  T. J. Van der Walt.  The development of connectionist networks for the modelling of chemical engineering systems , 1992 .

[12]  Dale E. Seborg,et al.  Nonlinear internal model control strategy for neural network models , 1992 .

[13]  Markus A. Reuter,et al.  Modeling of metal-slag equilibrium processes using neural nets , 1992 .

[14]  Geoffrey E. Hinton.  Connectionist Learning Procedures , 1989, Artif. Intell..

[15]  Douglas J. Cooper,et al.  Comparing two neural networks for pattern based adaptive process control , 1992 .

[16]  Masahiro Abe,et al.  Incipient fault diagnosis of chemical processes via artificial neural networks , 1989 .

[17]  David Haussler,et al.  What Size Net Gives Valid Generalization? , 1989, Neural Computation.

[18]  N. V. Bhat,et al.  Use of neural nets for dynamic modeling and control of chemical process systems , 1990 .

[19]  R. W. Dobbins,et al.  Early neural network development history: the age of Camelot , 1990, IEEE Engineering in Medicine and Biology Magazine.

[20]  David M. Himmelblau,et al.  Process control via artificial neural networks and reinforcement learning , 1992 .

[21]  Venkat Venkatasubramanian,et al.  Combining pattern classification and assumption-based techniques for process fault diagnosis , 1992 .

[22]  Ali Cinar,et al.  Approximate Dynamic Models for Chemical Processes: A Comparative Study of Neural Networks and Nonlinear Time Series Modeling Techniques , 1992 .

[23]  Josiah C. Hoskins,et al.  Artificial neural network models for knowledge representation in chemical engineering , 1990 .

[24]  Lyle H. Ungar,et al.  Adaptive networks for fault diagnosis and process control , 1990 .

[25]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[26]  Toshio Odanaka,et al.  ADAPTIVE CONTROL PROCESSES , 1990 .