Learning control strategies for chemical processes: a distributed approach

Author

Sikora, Riyaz

Author_Institution

Beckman Inst., Illinois Univ., IL, USA

Volume

7

Issue

3

fYear

1992

fDate

6/1/1992 12:00:00 AM

Firstpage

35

Lastpage

43

Abstract

The design of a distributed learning system (DLS) which combines the features of instance-space and hypothesis-space methods is described. This algorithm decomposes a data set of training examples into subsets. After applying an inductive learning program on each subset, it synthesizes the results using a genetic algorithm. It is shown that this parallel distributed approach is more efficient, since each inductive learning program works on only a subset of data. Since the genetic algorithm searches globally in the hypothesis space, this approach gives a more accurate concept description. The implementation of DLS in Common LISP is discussed, and its distributed approach is compared to C4.5 and PLS1 algorithms.<>

Keywords

adaptive control; chemical engineering computing; genetic algorithms; learning systems; parallel programming; process computer control; Common LISP; DLS; PLS1 algorithms; chemical processes; concept description; distributed approach; distributed learning system; genetic algorithm; hypothesis space; hypothesis-space methods; inductive learning program; instance-space; parallel distributed approach; process control; training examples; Algorithm design and analysis; Chemical processes; Equations; Genetic algorithms; Instruments; Joining processes; Learning systems; Particle measurements; Production facilities;

fLanguage

English

Journal_Title

IEEE Expert

Publisher

ieee

ISSN

0885-9000

Type

jour

DOI

10.1109/64.143237

Filename

143237