A Bayesian approach to robust process identification with ARX models

Abstract

in Wiley Online Library (wileyonlinelibrary.com).In the context of process industries, outlying observations mostly represent a large random error resulting from irregular process disturbances, instrument failures, or transmission problems. Statistical analysis of process data contaminated with outliers may lead to biased parameter estimation and plant-model mismatch. The problem of process identification in the presence of outliers has received great attention and a wide variety of outlier identification approaches have been proposed. However, there is a great need to seek for more general solutions and a robust framework to deal with different types of outliers. The main objective of this work is to formulate and solve the robust process identification problem under a Bayesian framework. The proposed solution strategy not only yields maximum a posteriori estimates of model parameters but also provides hyperparameters that determine data quality as well as prior distribution of model parameters. Identification of a simulated continuous fermentation reactor is considered to show the effectiveness and robustness of the proposed Bayesian framework. The advantages of the method are further illustrated through an experimental case study of a pilot-scale continuous stirred tank heater.

Framework for Validation of Permanently Installed MEMS-Based Acquisition Devices Using Soft Sensor Models

“…Here, we take the view that Bayesian statistical models are the most adept at combining physical, often non-linear, models with statistical ones. There is increasing interest in, and examples of, first principles and data driven soft sensor models being constructed in a Bayesian framework [35]. There is another advantage to Bayesian approaches in that they have a structure well suited to updating the predictive densities that represent our uncertainty of, say, y t+1 as new data arrives.…”

“…Particle filters are used when the process evolves non-linearly and the observational error is potentially non-Gaussian. An accessible description of Bayesian methods for soft sensor models is provided by [29] with example process industry applications in [23,35,36]. However, examples of Kalman or particle filter models for sensor validation in CM&SI contexts are scarce.…”

An improved methodology for outlier detection in dynamic datasets

“…The first likelihood‐based method is developed by Fox for single outlier detection (AO, IO) in the autoregressive (AR) process, and it is then modified for AO and IO detection in the ARIMA process, and for detecting TCs or LSs . Since the likelihood function is key to Bayesian inference, Bayesian methods were developed to detect outliers based on analyzing posterior distribution …”

Bayesian method for simultaneous gross error detection and data reconciliation

“…The hierarchical Bayesian procedure was used to address the image modeling and restoration problem by Molina et al and Galatsanos et al Kwok and Suykens et al derived the probabilistic formulation of the least squares support vector machine within a hierarchical Bayesian evidence framework. The hierarchical Bayesian framework was utilized for process identification with outliers in the dataset by Khatibisepehr and Huang …”