Abstracts Engineering

Add abstract

Want to add your dissertation abstract to this database? It only takes a minute!

Search abstract

Search for abstracts by subject, author or institution

Share this abstract

Predicting eigenvalues and eigenmodes in non-rectangular rooms with machine learning techniques

by Oscar Lundin

Institution: KTH
Department: Technical Acoustics
Degree:
Year: 2022
Keywords: Machine learning; Finite elements; Plane wave decomposition; ResNet; Room acoustics; Tensorflow; Keras; Eigenfrequency prediction; Maskininlärning; Finita elementmetoden; Planvåguppdelning decomposition; Rumsakustik; ResNet; Tensorflow; Keras; Predikterin
Posted: 3/25/2025
Record ID: 2268171
Full text PDF: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-324264


Abstract

Knowing the eigenfrequencies and eigenmodes is of great importance to interior design and a common acoustic engineering problem. Challenges in noise control makes knowing the lower eigenfrequencies particularly important. Analytical solutions exist for simple room shapes while methods such as the finite element method (FEM) provide a more general numerical solution to the problem. This thesis outlines the process of generating a dataset of 2D images represent-ing pseudorandom rooms and calculating the eigenfrequencies and eigenmodes using FEM with COMSOL. A machine learning model is presented based on con- volutional neural networks (CNN) that predicts the first ten eigenfrequencies from an image input of the room’s shape with a normalized surface area. To estimate the mode shapes a plane wave decomposition is presented and evaluated com- paring the resulting sound field of the FEM calculated eigenfrequencies and the eigenfrequencies from the machine learning model. The thesis presents a proof- of-concept which predicts the eigenfrequencies with a resulting error between −4 and +6 percent for 90 % of the test set. Furthermore, the potential for predicting eigenmodes is demonstrated. Att veta egenfrekvenserna och egenmoderna är av stor vikt och ett vanligt in- genjörsproblem inom byggnads- och rumsakustik. Kunskap om de lägre egenfrekvenserna är oumbärligt för att bemöta utmaningarna inom bullerkontroll och minimera oönskade ljud. Analytiska lösningar existerar endast för några få enkla rumsformer medan metoder som finita elementmetoden (FEM) ger mer generella numeriska lösningar till problemet. Rapporten presenterar en metod som används för att generera ett dataset av pseudoslumpmässiga tvådimensionella rum samt beräkna deras egenfrekvenser och egenmoder med FEM i COMSOL. En maskininlärningsmodell baserad på convolutional neural networks (CNN) presenteras, som uppskattar de första tio egenfrekvenserna med en bild av rummet med normaliserad golvyta som insignal. Planvåguppdelning (PWD) förklaras och används för att jämföra egenmoderna från maskininlärningsmodellen med resultaten från FEM. Arbetet resulterade i ett fungerande koncept som predikterar egenfrekvenser med ett fel på −4 till +6 procent för 90 % av ett testset. Vidare påvisas framtida potential för att prediktera egenmoderna.

Add abstract

Want to add your dissertation abstract to this database? It only takes a minute!

Search abstract

Search for abstracts by subject, author or institution

Share this abstract

Relevant publications

Book cover thumbnail image
Predicting the Admission Decision of a Participant...
by Yigit Ozsert, Gozde
   
Book cover thumbnail image
Development of New Models Using Machine Learning M...
by Akgol, Derman
   
Book cover thumbnail image
The Adaptation Process of a Resettled Community to... A Study of the Nubian Experience in Egypt
by Fahmi, Wael Salah
   
Book cover thumbnail image
Development of an Artificial Intelligence System f...
by Chand, Praneel
   
Book cover thumbnail image
Theoretical and Experimental Analysis of Dissipati...
by Latour, Massimo
   
Book cover thumbnail image
Optical Fiber Sensors for Residential Environments
by García-Olcina, Raimundo
   
Book cover thumbnail image
Calibration of Deterministic Parameters Reassessment of Offshore Platforms in the Arabian ...
by Zaghloul, Hassan
   
Book cover thumbnail image
How Passion Relates to Performance A Study of Consultant Civil Engineers
by Cadieux, Trevor J.