English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In an effort to advocate the research for a deep learning-based machinefailure detection system, we present a case study of our proposed system basedon a tiny sound dataset. Our case study investigates a variational autoencoder(VAE) for augmenting a small drill sound dataset from Valmet AB. A Valmetdataset contains 134 sounds that have been divided into two categories:"Anomaly" and "Normal" recorded from a drilling machine in Valmet AB, a companyin Sundsvall, Sweden that supplies equipment and processes for the productionof biofuels. Using deep learning models to detect failure drills on such asmall sound dataset is typically unsuccessful. We employed a VAE to increasethe number of sounds in the tiny dataset by synthesizing new sounds fromoriginal sounds. The augmented dataset was created by combining thesesynthesized sounds with the original sounds. We used a high-pass filter with apassband frequency of 1000 Hz and a low-pass filter with a passband frequencyof 22\kern 0.16667em000 Hz to pre-process sounds in the augmented datasetbefore transforming them to Mel spectrograms. The pre-trained 2D-CNN Alexnetwas then trained using these Mel spectrograms. When compared to using theoriginal tiny sound dataset to train pre-trained Alexnet, using the augmentedsound dataset enhanced the CNN model's classification results by 6.62\%(94.12\%when trained on the augmented dataset versus 87.5\% when trained on theoriginal dataset).

An artificial neural network-based system for detecting machine failures using tiny sound data: A case study