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

Saurabh Pargal; Abhijit A. Sane

Home/Archive/arXiv

arXiv · 2505.20079

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

Saurabh Pargal·Abhijit A. Sane

View original source ↗Read source document ↗Export metadata ↓

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.

Explore related subjects

physics.app-ph cs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Saurabh Pargal, Abhijit A. Sane. 2025-05-26. A fast sound power prediction tool for genset noise using machine learning. https://arxiv.org/abs/2505.20079

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Measuring vacancy-type defect density in monolayer semiconductors

Two-dimensional (2D) materials have attracted wide-spread interest due to their unique and tunable properties. Their optoelectronic, mechanical, and thermal properties are greatly influenced by crystal defects, which are, in turn, used to control these properties. However, experimental quantification of the density of defects, whether deliberately introduced or inherent, is very difficult in these atomically thin materials. Here we show that helium atom micro-diffraction can be used to measure the defect density in ~15x20um monolayer MoS2, a prototypical 2D semiconductor, quickly and easily compared to standard methods. We present a simple analytic model, the lattice gas equation, that captures the relationship between atomic Bragg diffraction intensity and defect density. The model, combined with ab initio scattering calculations, shows that our technique can immediately be applied to a wide range of 2D materials, independent of sample chemistry or structure. Additionally, wafer-scale characterization is immediately possible.

physics.app-ph↗

arXiv2026

Compact Modeling of Oxide-Semiconductor, 2D Material, Carbon Nanotube, and Cryogenic Transistors with Experiment Verification

This paper presents a unified compact model for emerging transistor technologies, including oxide-semiconductor field-effect transistors (OSFETs), 2D material FETs (2DFETs), carbon nanotube FETs (CNFETs), and cryogenic MOSFETs. A unified charge-density formulation is developed to account for quantum confinement, trap charges, and band-tail states in channel charge calculations. A physics-based transport model is introduced to seamlessly capture carrier transport from the long-channel diffusive regime to the short-channel ballistic limit. Scaling models are incorporated to accurately describe 2D electrostatic effects. Cryogenic operation is modeled through the inclusion of band-tail states and temperature-dependent mobility and threshold voltage. The proposed model is validated against experimental data from the fabricated OSFETs with multiple channel lengths and published measurements of 2DFETs, CNFETs, and cryogenic MOSFETs. Excellent agreement is demonstrated across diverse device architectures, operating conditions, and material systems.

physics.app-ph↗

arXiv2026

Multiplexing approaches to thermoradiative signatureless communications

Using mid-infrared emission from semiconductor devices for covert communications remains a relatively unexplored and yet promising opportunity. The phenomenon of negative luminescence allows for a method of signatureless covert communications where the net infrared emission of an emitting optoelectronic device is balanced to be identical to the ambient thermal background. In this work we provide a practical demonstration of covert data transfer over a thermoradiative channel with data rates up to 100 kbps. In addition, we demonstrate several additional multiplexing techniques that make the proposed thermoradiative communications method more secure against interception by achieving zero instantaneous optical emission, while remaining detectable if a sufficiently spatially or spectrally discerning observation is utilised. Finally, we discuss various application scenarios in which the proposed methods can be used to achieve secure signatureless communications.

physics.app-ph↗