MULTICRITERIA OPTIMIZATION OF TECHNOLOGICAL PROCESSES BASED ON DPCA AND THE NEURAL NETWORK MODELS

UDC 681.2: 621.337.12
DOI: 10.36871/2618-9976.2023.10-2.004

Authors

Galina F. Malykhina,
Doctor of Technical Sciences, Professor, Peter the Great St. Petersburg Polytechnic University, Russia
Vyacheslav P. Shkodyrev,
Doctor of Technical Sciences, Professor, Head of the Laboratory "Intelligent Control Systems", Director of the Scientific and Technical Complex "Mathematical Modeling and Intelligent Control Systems"

Abstract

The management of largescale industrial systems has several criteria, such as ensuring high productivity, low production costs and the least environmental impact. These criteria must be established for all subsystems of the largescale system. The study is devoted to the development of a hierarchical control system that meets several criteria and allows for separate optimization of each subsystem. Multicriteria optimization is based on the processing of data characterizing production processes, which made it possible to organize a multidimensional statistical control process. Using neural networks to model technological processes and DPCA to reduce the dimensionality of control problems allows us to find more efficient solutions. Using the example of a twolevel hierarchy, we showed a variant of communication by parameters between two subsystems.

Keywords

Neural networks, Hierarchical multicriteria optimization, Pareto frontier, Dynamic PCA