AI supported noise analyses for structure design requirements definition

Simona Domazetovska, Viktor Gavriloski, Jovana Jovanova

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

4 Downloads (Pure)

Abstract

The artificial intelligence (AI) field has encountered a turning point mainly due to advancements in machine learning, which allows systems to learn, improve, and perform a specific task through data without being explicitly programmed. Machine learning can be utilized with machining processes to improve product quality levels and productivity rates and to optimize design and process parameters. The systems for acoustic event detection and classification (AED/C) of noise events is a process consisted of feature extraction of the signals, meaning processing acoustic signals and converting them into symbolic descriptions that correspond to the various sound events present in the signals and their sources. The main objective of the AED/C systems is to develop algorithms able to recognize and classify sound events that occur in the chosen environment, giving an appropriate response to users. By utilizing the acoustic events detection and classification systems, a clear set of design requirements can be extracted based on the noise to be attenuated. A smart structure design for noise attenuation needs clear noise input for proper smart material choice, placement and active control. This paper shows a method for detection of noise events based on machinelearning algorithm that can be further used for definition of design requirements.

Original languageEnglish
Title of host publicationProceedings of ASME 2021 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2021
PublisherASME
Number of pages6
ISBN (Electronic)978-0-7918-8549-9
DOIs
Publication statusPublished - 2021
EventASME 2021 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2021 - Virtual, Online
Duration: 14 Sep 202115 Sep 2021

Conference

ConferenceASME 2021 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS 2021
CityVirtual, Online
Period14/09/2115/09/21

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

  • Acoustic event detection and classification (AED/C)
  • Artificial Intelligence
  • Machine learning
  • Noise attenuation
  • Smart structure design

Fingerprint

Dive into the research topics of 'AI supported noise analyses for structure design requirements definition'. Together they form a unique fingerprint.

Cite this