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 car-body production the pre-formed sheet metal parts of the body areassembled on fully-automated production lines. The body passes through multiplestations in succession, and is processed according to the order requirements.The timely completion of orders depends on the individual station-basedoperations concluding within their scheduled cycle times. If an error occurs inone station, it can have a knock-on effect, resulting in delays on thedownstream stations. To the best of our knowledge, there exist no methods forautomatically distinguishing between source and knock-on errors in thissetting, as well as establishing a causal relation between them. Utilizingreal-time information about conditions collected by a production dataacquisition system, we propose a novel vehicle manufacturing analysis system,which uses deep learning to establish a link between source and knock-onerrors. We benchmark three sequence-to-sequence models, and introduce a novelcomposite time-weighted action metric for evaluating models in this context. Weevaluate our framework on a real-world car production dataset recorded byVolkswagen Commercial Vehicles. Surprisingly we find that 71.68% of sequencescontain either a source or knock-on error. With respect to seq2seq modeltraining, we find that the Transformer demonstrates a better performancecompared to LSTM and GRU in this domain, in particular when the predictionrange with respect to the durations of future actions is increased.

Identifying Cause-and-Effect Relationships of Manufacturing Errors using Sequence-to-Sequence Learning