A machine learning framework for computationally expensive transient models

TL;DR

This paper introduces a machine learning framework that combines traditional simulation tools with forecasting methods to reduce computational costs in transient dynamic system modeling, maintaining accuracy.

Contribution

It presents a novel ensemble approach integrating DEM, ARIMA, and machine learning to efficiently simulate large-scale transient systems.

Findings

The framework achieves significant computational savings.

The machine learning model maintains high accuracy.

Good agreement with existing literature results.

Abstract

The promise of machine learning has been explored in a variety of scientific disciplines in the last few years, however, its application on first-principles based computationally expensive tools is still in nascent stage. Even with the advances in computational resources and power, transient simulations of large-scale dynamic systems using a variety of the first-principles based computational tools are still limited. In this work, we propose an ensemble approach where we combine one such computationally expensive tool, called discrete element method (DEM), with a time-series forecasting method called auto-regressive integrated moving average (ARIMA) and machine-learning methods to significantly reduce the computational burden while retaining model accuracy and performance. The developed machine-learning model shows good predictability and agreement with the literature, demonstrating its tremendous potential in scientific computing.