Stabilization of industrial processes with time series machine learning

TL;DR

This paper introduces a neural network-based pipeline for stabilizing industrial time series processes, significantly improving temperature control stability with reduced computational resources.

Contribution

It proposes a novel two-network pipeline replacing traditional point-wise optimization, enhancing process stability in industrial applications.

Findings

Achieved approximately 3 times better stability in temperature control.

Demonstrated the effectiveness of neural networks in industrial process stabilization.

Reduced computational resources compared to conventional methods.

Abstract

The stabilization of time series processes is a crucial problem that is ubiquitous in various industrial fields. The application of machine learning to its solution can have a decisive impact, improving both the quality of the resulting stabilization with less computational resources required. In this work, we present a simple pipeline consisting of two neural networks: the oracle predictor and the optimizer, proposing a substitution of the point-wise values optimization to the problem of the neural network training, which successfully improves stability in terms of the temperature control by about 3 times compared to ordinary solvers.