In view of the difficulty of machine abnormal sound detection under the condition that abnormal sound samples are difficult to collect, this paper proposes an unsupervised abnormal sound detection model based on a self-coding model, which effectively improves the accuracy of abnormal sound detection under this condition. In this paper, location coding in Transformer is replaced with relational awareness self-attention to improve the representation capability of location coding. Secondly, the relevance scores in multi-head attention are mixed to enhance the understanding of context in the attention matrix. At the same time, Layer Normalization was replaced with Batch Normalization to speed up model training, and improved Transformer was introduced into the encoders and decoders of self-coding models. Finally, the improved self-coding model is used for unsupervised learning of the machine's normal sound to obtain the potential feature distribution of its normal sound. ToyADMOS and MIMII open data sets are used for experiments. Compared with traditional autoencoders and two improved self-coding models, The AUC score of toycar, Toycar, fan, slider and valve machines increased by 2.1%, 1.97%, 3.06%, 0.34% and 2.99%, respectively.
Aiming at the problem that the accuracy of abnormal sound detection under unsupervised conditions is not ideal, a novel abnormal sound detection model using composite self-coder combined with Gaussian mixture model is proposed. Firstly, the timing structure and gating mechanism of LSTM are used to improve the feature extraction ability of self-coder (including self-coder and variational self-coder), Secondly, Gaussian Mixture Model (GMM) is used to generate artificial data to improve the robustness of the self-coder against background noise. Experiments are carried out using ToyADMOS and MIMII public data sets, and the results are superior to the naive self-coder and the two improved self-coding models. On the six machines of the experimental data set, AUC increases by 6.34%, 6.65%, 4.03%, 5.57%, 2.38% and 1.07% respectively.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.