Automatically detecting anomalous noise in vehicles and identifying their cause(s) is a challenge, which, as long as it exists, has never been resolved in any satisfactory and universal manner, until now. Given the complexity of the input variables, conventional methods of signal processing quickly reach their limits. This is where AI-based methods of detecting and classifying anomalous acoustic events promise significant advancements.

    In this paper we show how to detect anomalous vehicle noises with an AI-based approach, we evaluate the precision of the algorithm and possible optimizations, give a concept on how to integrate such a functionality into modern cars, and, finally, give an outlook on latest advancements.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    AI-Based, Automated Acoustic Diagnostics in Vehicles


    Additional title:

    Proceedings


    Contributors:

    Conference:

    International ATZ Conference on Vehicle Acoustics ; 2021 November 16, 2021 - November 17, 2021


    Published in:

    Publication date :

    2023-08-30


    Size :

    9 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    German





    Atlas Automated Propulsion Diagnostics

    Martin, F. H. / Farris, T. A. / SAE | British Library Conference Proceedings | 1995


    Acoustic diagnostics of vehicles by means of pointedly directed microphone and sound probe

    Ushakov, A. / Davidov, P. / Bulatov, V. et al. | British Library Conference Proceedings | 1994


    Atlas Automated Propulsion Diagnostics

    Martin, Fred H. / Farris, Tracy A. | SAE Technical Papers | 1995


    VEHICLE DIAGNOSTICS BASED ON INFORMATION COMMUNICATED BETWEEN VEHICLES

    FISCHER JACOB / FRAMPTON DALE / SCHMIEDEL GARY et al. | European Patent Office | 2017

    Free access