To address the problem of small sample sizes in sound signal collection for $SF_{6}$ gas leak fault detection in high-voltage switchgear equipment, an improved StyleGAN model with a U-Net structure as the discriminator is proposed. The model uses a WGAN-GP loss term to reduce the problem of training mode collapse. A consistency loss term and a gradient penalty term are added to the loss evaluation to achieve regularization effects and generate spectrograms with corresponding features for data augmentation of small sample images of leak signal spectrograms. Feasibility experiments are conducted by simulating $SF_{6}$ gas leak audio signal collection. The t-SNE method is used to visually compare the spectrograms of real gas leak data and the “Pseudo-samples” generated by the improved StyleGAN model. The results prove the effectiveness of the proposed method.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Method for generating gas leakage data based on Generative Adversarial Networks


    Beteiligte:
    Wang, Tingting (Autor:in) / Xu, Yanwu (Autor:in) / Wang, Yingming (Autor:in) / Yu, Yongsheng (Autor:in)


    Erscheinungsdatum :

    04.08.2023


    Format / Umfang :

    2186941 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Generating High-fidelity Cybersecurity Data With Generative Adversarial Networks

    Le, Joie / Viswanathan, Arun / Zhang, Yuening | AIAA | 2020


    On Generating Parametrised Structural Data Using Conditional Generative Adversarial Networks

    Tsialiamanis, G. / Wagg, D. J. / Dervilis, N. et al. | British Library Conference Proceedings | 2021


    CyberGAN: Generating High-Fidelity Cybersecurity Data with Generative Adversarial Networks (GANs)

    Viswanathan, Arun A / Zhang, Yuening / Le, Joie et al. | NTRS | 2020


    Generating Shape Transitions of Deformable Linear Objects Using Generative Adversarial Networks

    Yamazaki, Kimitoshi / Matsuura, Ryo / Arnold, Solvi | British Library Conference Proceedings | 2022


    Generative Adversarial Networks for Labelled Vibration Data Generation

    Luleci, Furkan / Catbas, F. Necati / Avci, Onur | British Library Conference Proceedings | 2022