Nearly 20-30% of all process control loops oscillate due to stiction and lead to loss of productivity. Thus, the detection and quantification of stiction in control valves using just the raw operating data is an important component of any automated controller performance monitoring application. Many techniques have been proposed for the detection and quantification of stiction. Pattern based id...

..................................................................................................................................... ix

I have been working in the Bayes research group of the Neural Network Research Centre, HUT. In our group, we apply variational Bayesian learning to identify different types of latent variable models such as (non)linear factor analysis, independent component analysis and their extensions. The resulting algorithms can be used for data compression, feature extraction or blind source separation. My...

In this paper, an approach of wavelet-based nonlinear PCA for statistical process monitoring is presented. The strategy utilizes the optimal wavelet decomposition in such a way that only approximation and the highest detail functions are used thus simplifying the overall structure and making the interpretation at each scale more meaningful. An orthogonal nonlinear PCA procedure is incorporated ...

Abstract: In this paper hybrid fuzzy model based predictive control (HFMBPC) is addressed, proposed and tested. The proposed hybrid fuzzy convolution model consists of a steady-state fuzzy model and a gain independent impulse response model. The proposed model is tested in model based predictive control of the concentration control in the chemical reactor, manipulating its flow rate. The paper ...

To date, sensitivity, bifurcation and singularity analysis have been employed to identify and characterize the qualitative nonlinear behaviour of chemical process systems. The phenomena of interest include multiple steady states and periodic or even chaotic oscillations. The analyses have been aiming at proper understanding of the relation between the observed behaviour on the one and the proce...