Title: Performance analysis of automotive exhaust muffler characteristics integrating supervised machine learning algorithms

Authors: Dilip Kumar Sahu; Trupti Ranjan Mahapatra; Priyabrata Puhan; Debadutta Mishra

Addresses: Department of Production Engineering, Veer Surendra Sai University of Technology (VSSUT), Burla, 768018, Odisha, India ' Department of Production Engineering, Veer Surendra Sai University of Technology (VSSUT), Burla, 768018, Odisha, India ' Department of Production Engineering, Veer Surendra Sai University of Technology (VSSUT), Burla, 768018, Odisha, India ' Department of Production Engineering, Veer Surendra Sai University of Technology (VSSUT), Burla, 768018, Odisha, India

Abstract: Parametric design and analysis of a conventional muffler used in a diesel engine passenger car is performed by integrating supervised machine learning (SML) technique. The 3D CAD models are developed using the dimensions captured by a 3D scanner in STAR-CCM+ workbench to perform transient analysis. The pressure drop and transmission loss are analysed by varying the shape of the expansion chamber, perforated hole shapes, and hole diameters, at constant total area of perforation and expansion chamber volume. SML regression models based on Random Forest (RF) and Gradient Boosting (GB) algorithms are developed using the input and output data obtained from the simulation and subsequently, prediction and validation are done for selected cases. The GBR model provided comprehensive accuracy in terms of all the aspects. Therefore, it is endorsed to be incorporated as a procedural step in between design and computer-aided engineering stage in the reverse engineering approach.

Keywords: exhaust muffler; simulation; pressure drop; transmission loss; SML; supervised machine learning.

DOI: 10.1504/IJVP.2023.131971

International Journal of Vehicle Performance, 2023 Vol.9 No.3, pp.314 - 335

Received: 31 May 2022
Accepted: 28 Oct 2022
Published online: 05 Jul 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article