Performance analysis of automotive exhaust muffler characteristics integrating supervised machine learning algorithms
by Dilip Kumar Sahu; Trupti Ranjan Mahapatra; Priyabrata Puhan; Debadutta Mishra
International Journal of Vehicle Performance (IJVP), Vol. 9, No. 3, 2023

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.

Online publication date: Wed, 05-Jul-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Vehicle Performance (IJVP):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com