An automatic selection of optimal recurrent neural network architecture for processes dynamics modelling purposes

TL;DR

This paper introduces four novel algorithms for automatically selecting optimal recurrent neural network architectures to model dynamic processes, balancing network complexity and accuracy.

Contribution

The study presents new algorithms based on evolutionary and gradient methods for neural architecture search, with specialized operators and validation on nuclear reactor process data.

Findings

Algorithms effectively balance network size and accuracy.

Validation on nuclear reactor data demonstrates practical applicability.

Proposed methods outperform baseline approaches.

Abstract

A problem related to the development of algorithms designed to find the structure of artificial neural network used for behavioural (black-box) modelling of selected dynamic processes has been addressed in this paper. The research has included four original proposals of algorithms dedicated to neural network architecture search. Algorithms have been based on well-known optimisation techniques such as evolutionary algorithms and gradient descent methods. In the presented research an artificial neural network of recurrent type has been used, whose architecture has been selected in an optimised way based on the above-mentioned algorithms. The optimality has been understood as achieving a trade-off between the size of the neural network and its accuracy in capturing the response of the mathematical model under which it has been learnt. During the optimisation, original specialised evolutionary operators have been proposed. The research involved an extended validation study based on data generated from a mathematical model of the fast processes occurring in a pressurised water nuclear reactor.