A fast sound power prediction tool for genset noise using machine learning

TL;DR

This paper presents a machine learning-based tool for rapid and reliable prediction of genset noise levels during early design stages, aiding marketing and sales without needing measured data.

Contribution

It introduces the use of KRR, HR, and GPR algorithms for genset noise prediction, demonstrating high accuracy with minimal data in early design phases.

Findings

KRR achieves within 5 dBA accuracy

All models effectively capture noise trends

Machine learning enables early noise estimation

Abstract

This paper investigates the application of machine learning regression algorithms Kernel Ridge Regression (KRR), Huber Regressor (HR), and Gaussian Process Regression (GPR) for predicting sound power levels of gensets, offering significant value for marketing and sales teams during the early bidding process. When engine sizes and genset enclosure dimensions are tentative, and measured noise data is unavailable, these algorithms enable reliable noise level estimation for unbuilt gensets. The study utilizes high fidelity datasets from over 100 experiments conducted at Cummins Acoustics Technology Center (ATC) in a hemi-anechoic chamber, adhering to ISO 3744 standards. By using readily available information from the bidding and initial design stages, KRR predicts sound power with an average accuracy of within 5 dBA. While HR and GPR show slightly higher prediction errors, all models effectively capture the overall noise trends across various genset configurations. These findings present a promising method for early-stage noise estimation in genset design.