SPA-Based Modified Local Reachability Density Ratio wSVDD for Nonlinear Multimode Process Monitoring

Abstract

Many industrial processes are operated in multiple modes due to different manufacturing strategies. Multimodality of process data is often accompanied with nonlinear and non-Gaussian characteristics, which makes data-driven monitoring more complicated. In this paper, statistics pattern analysis (SPA) is introduced to extract low- and high-order statistics from raw process data. Support vector data description (SVDD), which can deal with nonlinear and non-Gaussian problems, is applied to monitor multimode process in this paper. To improve detection performance of SVDD for training multimode data with outliers, modified local reachability density ratio (mLRDR) is proposed as a weight factor to be embedded in the weighted-SVDD (wSVDD) model, in which the local neighbors in terms of both space and time are considered. Finally, the effectiveness and superiority of our proposed method are demonstrated by the Tennessee-Eastman (TE) process and wastewater treatment process (WWTP).

Çelik Levha Arıza Tespiti için Makine Öğrenimi Algoritmalarının Karşılaştırmalı Analizi

“…Traditional methods have been used for many years to detect errors such as pastry, Z-scratch, K-scratch, stains, and pollution, which are some of the defects that may occur in steel plates during production. The experts would manually examine the plates according to the characteristics of the product to be released and create a malfunction report [6], [7]. However, this method is both time-consuming and costly, as it is possible that defects could be overlooked [7].…”

“…The experts would manually examine the plates according to the characteristics of the product to be released and create a malfunction report [6], [7]. However, this method is both time-consuming and costly, as it is possible that defects could be overlooked [7].…”

Sparse representation and modified density peak clustering-based state identification for multimode processes

“…Most of them aim to remove the multimodal features from the data distribution, in which nearest-neighbor approaches are widely applied to standardize different modes [4]. For example, Wang et al [5] proposed a modified local reachability density ratio weighted support vector data description to maintain the monitoring efficiency of a single hypersphere model. In addition, adaptive modeling is another single-model scheme.…”