Predicting Friction System Performance with Symbolic Regression and Genetic Programming with Factor Variables

TL;DR

This paper demonstrates that genetic programming with factor variables can accurately predict friction system performance, producing less complex models than traditional one-hot encoding methods, and is comparable to neural networks.

Contribution

It introduces the use of factor variables in symbolic regression for better handling of nominal data in friction system performance prediction.

Findings

GP achieves accuracy comparable to neural networks.

Factor variables lead to simpler models than one-hot encoding.

Symbolic regression models are trustworthy for real-world friction system predictions.

Abstract

Friction systems are mechanical systems wherein friction is used for force transmission (e.g. mechanical braking systems or automatic gearboxes). For finding optimal and safe design parameters, engineers have to predict friction system performance. This is especially difficult in real-world applications, because it is affected by many parameters. We have used symbolic regression and genetic programming for finding accurate and trustworthy prediction models for this task. However, it is not straight-forward how nominal variables can be included. In particular, a one-hot-encoding is unsatisfactory because genetic programming tends to remove such indicator variables. We have therefore used so-called factor variables for representing nominal variables in symbolic regression models. Our results show that GP is able to produce symbolic regression models for predicting friction performance with predictive accuracy that is comparable to artificial neural networks. The symbolic regression models with factor variables are less complex than models using a one-hot encoding.