Multiscale Principal Component Analysis-Signed Directed Graph Based Process Monitoring and Fault Diagnosis

Abstract

The chemical process industry has become the backbone of the global economy. The complexities of chemical process systems have been increased in the last two decades due to online sensor technology, plant-wide automation, and computerized measurement devices. Principal component analysis (PCA) and signed directed graph (SDG) are some of the quantitative and qualitative monitoring techniques that have been widely applied for chemical fault detection and diagnosis (FDD). The conventional PCA-SDG algorithm is a single-scale FDD representation origin, which cannot effectively solve multiple FDD representation origins. The multiscale PCA-SDG wavelet-based monitoring technique has potential because it easily distinguishes between deterministic and stochastic characteristics. This study uses multiscale PCA-SDG to detect, diagnose the root cause and identify the fault propagation path. The proposed method is applied to a continuous stirred tank reactor system to validate its effectiveness. The propagation route of most process failures is detected, identified, and diagnosed, which is well-aligned with the fault description, demonstrating a satisfactory performance of the suggested technique for monitoring the process failures.

Multiobjective Optimization and Sustainability Assessment of an Improved Wet Sulfuric Acid-Based Ionic Liquid Process for the Utilization of Hydrogen Sulfide Using a Symmetry Approach

“…Finally, multiplying the penalty and energy components results in the FEDI damage potential. The most significant part of TDI computation is the processing unit contains a potentially dangerous product. , The physical and chemical process are evaluated consequently. They are frequently issued for the origin of the next hazardous section and the area utilized by the section due to a malfunction of relevant data collected during the product development stage; eqs – indicate how FEDI and TDI were computed. F 1 = 0.1 M × Hc K F 2 = 1.304 × 10 − 3 × Pp × V F 3 = 1 × 10 − 3 × 1 false( T + 273 false) × false( Pp − Vp false) 2 × V F 4 = M × Hr × n K Dp = ( F 1 × p n 1 + F + p n 4 + F 4 × p n 7 ) × p n …”

“…The most significant part of TDI computation is the processing unit contains a potentially dangerous product. 5 , 32 The physical and chemical process are evaluated consequently. They are frequently issued for the origin of the next hazardous section and the area utilized by the section due to a malfunction of relevant data collected during the product development stage; eqs 13 – 22 indicate how FEDI and TDI were computed.…”

Detection of Myocardial Infarction from Electrocardiography Signals with Multiscale Principal Component Analysis and Convolutional Neural Networks

“…Temel bileşen analizi (PCA), değişken kombinasyonları üreterek bu kombinasyonlara ait önemli veri çeşitlerinin yönlerini belirlemeye yarayan istatistiksel bir yöntemdir [15]. PCA özellik çıkarma ve boyut küçültme konusunda yüksek performansa sahiptir.…”

“…PCA özellik çıkarma ve boyut küçültme konusunda yüksek performansa sahiptir. Veri seti gözlem ve değişken sayısı ile bir matris üzerinde tanımlanır ve matris birim varyans ve sıfır ortalamalarla standartlaştırılır, tek değerli ayrıştırma ile yeni bir matrise yorumlanır [15]. Bu yöntem Bakshi tarafından dalgacık analizi yöntemiyle birleştirilmiş, her dalgacık ölçeğinde PCA modellerini belirleyen çok ölçekli temel bileşen analizi (Multiscale Principal Componenet Analysis, MSPCA) yöntemi ortaya çıkmıştır [16].…”

Neural Component Analysis for Key Performance Indicator Monitoring

“…Multivariate statistics-based process monitoring (MSPM) − is one of the most attractive data-driven approaches for monitoring complex processes with high-dimensional data structures, for example, biopharmaceutical and chemical processes. Its core idea is to transform high-dimensional process data to low-dimensional principal components (PCs) and monitor them using several statistical indices. − …”