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

Fault detection and diagnosis of electrical motors are of utmost importancein ensuring the safe and reliable operation of several industrial systems.Detection and diagnosis of faults at the incipient stage allows correctiveactions to be taken in order to reduce the severity of faults. The existingdata-driven deep learning approaches for machine fault diagnosis relyextensively on huge amounts of labeled samples, where annotations are expensiveand time-consuming. However, a major portion of unlabeled condition monitoringdata is not exploited in the training process. To overcome this limitation, wepropose a foundational model-based Active Learning framework that utilizes lessamount of labeled samples, which are most informative and harnesses a largeamount of available unlabeled data by effectively combining Active Learning andContrastive Self-Supervised Learning techniques. It consists of a transformernetwork-based backbone model trained using an advanced nearest-neighborcontrastive self-supervised learning method. This approach empowers thebackbone to learn improved representations of samples derived from raw,unlabeled vibration data. Subsequently, the backbone can undergo fine-tuning toaddress a range of downstream tasks, both within the same machines and acrossdifferent machines. The effectiveness of the proposed methodology has beenassessed through the fine-tuning of the backbone for multiple target tasksusing three distinct machine-bearing fault datasets. The experimentalevaluation demonstrates a superior performance as compared to existingstate-of-the-art fault diagnosis methods with less amount of labeled data.

Active Foundational Models for Fault Diagnosis of Electrical Motors