Process Fault Diagnosis for Continuous Dynamic Systems Over Multivariate Time Series

Abstract

Fault diagnosis in continuous dynamic systems can be challenging, since the variables in these systems are typically characterized by autocorrelation, as well as time variant parameters, such as mean vectors, covariance matrices, and higher order statistics, which are not handled well by methods designed for steady state systems. In dynamic systems, steady state approaches are extended to deal with these problems, essentially through feature extraction designed to capture the process dynamics from the time series. In this chapter, recent advances in feature extraction from signals or multivariate time series are reviewed. These methods can subsequently be considered in a classical statistical monitoring framework, such as used for steady state systems. In addition, an extension of nonlinear signal processing based on the use of unthresholded or global recurrence quantification analysis is discussed, where two multivariate image methods based on gray level co-occurrence matrices and local binary patterns are used to extract features from time series. When considering the well-known simulated Tennessee Eastman process in chemical engineering, it is shown that time series features obtained with this approach can be an effective means of discriminating between different fault conditions in the system. The approach provides a general framework that can be extended in multiple ways to time series analysis.

Transfer Entropy-Based Automated Fault Traversal and Root Cause Identification in Complex Nonlinear Industrial Processes

“…The Tennessee Eastman process (TEP) is widely used as an industrial benchmark for time series data analysis, and fault detection, and diagnosis. − The process flow diagram of TEP is shown in Figure . The plant consists of 5 major process units: an exothermic two-phase reactor, a product stripper, a condenser, a vapor–liquid separator, and a recycle compressor (Downs & Vogel, 1993).…”

Implementasi Metode Deteksi Friksi Statik pada Katup Kontrol menggunakan Pencocokan Elips pada Standar IEC 61499

“…Metode jendela digital yang bergeser ini merupakan solusi pemrosesan aliran data secara waktu nyata (real-time) [14]. Ukuran jendela digital yang bergeser yang terlalu kecil dapat menyebabkan misinformasi, sedangkan ukuran yang terlalu besar dapat mengurangi sensitifitas dan akurasi [15]. Ukuran setiap jendela digital yang bergeser unik pada setiap karakter proses yang diobservasi.…”

Implementasi Metode Deteksi Friksi Statik pada Katup Kontrol menggunakan Pencocokan Elips pada Standar IEC 61499

“…Jendela digital yang bergeser adalah suatu struktur data majemuk. Jendela digital yang bergeser adalah sub-list yang bergerak terhadap suatu list data [15]. Sederhananya, bayangkan sebuah pemindai bergerak yang hanya mengkomputasi segala sesuatu yang nampak pada jendela pindai saja (Gambar 1).…”