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

As a substantial amount of multivariate time series data is being produced bythe complex systems in Smart Manufacturing, improved anomaly detectionframeworks are needed to reduce the operational risks and the monitoring burdenplaced on the system operators. However, building such frameworks ischallenging, as a sufficiently large amount of defective training data is oftennot available and frameworks are required to capture both the temporal andcontextual dependencies across different time steps while being robust tonoise. In this paper, we propose an unsupervised Attention-based ConvolutionalLong Short-Term Memory (ConvLSTM) Autoencoder with Dynamic Thresholding(ACLAE-DT) framework for anomaly detection and diagnosis in multivariate timeseries. The framework starts by pre-processing and enriching the data, beforeconstructing feature images to characterize the system statuses acrossdifferent time steps by capturing the inter-correlations between pairs of timeseries. Afterwards, the constructed feature images are fed into anattention-based ConvLSTM autoencoder, which aims to encode the constructedfeature images and capture the temporal behavior, followed by decoding thecompressed knowledge representation to reconstruct the feature images input.The reconstruction errors are then computed and subjected to astatistical-based, dynamic thresholding mechanism to detect and diagnose theanomalies. Evaluation results conducted on real-life manufacturing datademonstrate the performance strengths of the proposed approach overstate-of-the-art methods under different experimental settings.

An Attention-based ConvLSTM Autoencoder with Dynamic Thresholding for Unsupervised Anomaly Detection in Multivariate Time Series