Fault diagnosis is a pre-requisite for ensuring safe, efficient and optimal operation of chemical process plants. The success of any diagnosis strategy depends critically on the sensors measuring the process variables. With potentially many sensor locations, sensor placement can be optimized based on criteria like cost, reliability etc. We present formulations to perform sensor reallocation and...

Many multivariate statistical analysis methods and their corresponding probabilistic counterparts have been adopted to develop process monitoring models in recent decades. However, the insightful connections between them rarely studied. In this study, a generalized model (GPMM) is developed with both random sequential data. Since GPMM can be reduced various linear under specific restrictions, i...

In the process industry, an alarm system is one of important ways condition monitoring. Due to complexity and irregularity information in monitoring, there are too many false alarms current system. order solve problem designing system, this paper proposes a multivariate design method based on evidence reasoning (ER) rule, considering interval-valued reliability, which can make full use accurate...

The traditional data-driven process monitoring methods may not be applicable for the system which has dynamic and multimode characteristics. In this paper, a novel scheme named modified t-distribution stochastic neighbor embedding using augmented Mahalanobis-distance chemical (AKMD-t-SNE) is proposed to realize multimodal monitoring. First, matrix strategy utilized ensure sample contains autoco...

This paper presents a methodology for locating sensors in dynamic systems. It aims to maximize Kalman filtering performance by using accuracy as its main performance index. To accomplish this task, both the measurement noise and the observation matrices are manipulated. The method has been applied in two academic case studies and in the Tennessee Eastman Challenge Problem and has shown promisin...

An improved mixture of probabilistic principal component analysis (PPCA) has been introduced for nonlinear datadriven process monitoring in this paper. To realize this purpose, the technique of a mixture of probabilistic principal component analysers is utilized to establish the model of the underlying nonlinear process with local PPCA models, where a novel composite monitoring statistic is pro...

Statistical data-driven process monitoring is critical for efficient operations of industrial processes. However, deviations from normal regions in the process data may or may not lead to poor quality of products. This paper proposes a new combined index for detecting output-relevant faults, which affect the output data, and studies the output-relevant fault detectability based on total project...

Oscillations in the control loops indicate poor performance of loops. The occurrence oscillations process loop is quite high industry, so it needs to be reduced that can work properly. first step for oscillation reduction detection. One type difficult detect intermittent oscillation. smart factory concept encourages development detection system using machine learning by being implemented online...

Multivariate batch time-series data sets within Semiconductor manufacturing processes present a difficult environment for effective Anomaly Detection (AD). The challenge is amplified by the limited availability of ground truth labelled data. In scenarios where AD possible, black box modelling approaches constrain model interpretability. These challenges obstruct widespread adoption Deep Learnin...