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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Process variables can be separated into quality strongly related variables (QSRVs) and quality weakly related variables (QWRVs) based on the difference of correlation between process variables and quality. When the fault occurs on different types of process variables, the degree of impact on quality is different. The fault which occurs on QWRV is defined as the quality weakly related fault. This paper presents a weighted dual-step feature extraction (WDSFE) method for quality weakly related fault detection. In the first step, a QSRV block and a QWRV block are separated from original process variables. In the second step, the two variable blocks are further decomposed into a quality-direct-related subspace (QDRS), a quality-potential-related subspace (QPRS), and two quality unrelated subspaces (QUSs). Subsequently, the weighted <inline-formula> <tex-math notation="LaTeX">$T^{2}$ </tex-math></inline-formula> statistic is established based on the statistics in both QDRS and QPRS to detect the quality-related fault. The <inline-formula> <tex-math notation="LaTeX">$BIC$ </tex-math></inline-formula> statistic is established based on the statistics in two QUSs to detect the quality unrelated fault. Finally, a numerical example and a simulated industrial process are used to illustrate the effectiveness of WDSFE.

Quality Weakly Related Fault Detection Based on Weighted Dual-Step Feature Extraction