Resumen de ADVANCES ON BILINEAR MODELING OF BIOCHEMICAL BATCH PROCESSES
José María González Martínez
This thesis is aimed to study the implications of the statistical modeling approaches proposed for the bilinear modeling of batch processes, develop new techniques to overcome some of the problems that have not been yet solved and apply them to data of biochemical processes. The study, discussion and development of the new methods revolve around the four steps of the modeling cycle, from the alignment, preprocessing and calibration of batch data to the monitoring of batches trajectories. Special attention is given to the problem of the batch synchronization, and its effect on the modeling from different aspects: synchronization quality, changes in the correlation structure, capture of the process dynamics, parameters stability and accuracy to detect abnormal situations. The manuscript has been divided into four blocks. First, a state-of-the-art of the latent structures based-models in continuous and batch processes and traditional univariate and multivariate statistical process control systems is carried out. In addition, a theoretical revision of the different process modeling approaches and their effects on capturing the process dynamics is presented. The second block of the thesis is devoted to the preprocessing of batch data, in particular, to the equalization and synchronization of batch trajectories. The first section addresses the problem of the lack of equalization in the variable trajectories. The different types of unequalization scenarios that practitioners might find in batch processes are discussed and the solutions to equalize batch data are introduced. The performance of these proposals for equalization is dependent on the type of process and on the degree of unequalization the process variables are affected with. In the second section, a theoretical study of the nature of batch processes and of the synchronization of batch trajectories as a prior step to bilinear modeling is carried out. The drawbacks of the most used synchronization methods in process chemometrics are explored. The topics under discussion are i) whether the same synchronization approach must be applied to batch data in presence of different types of asynchronisms, and ii) whether synchronization is always required even though the length of the variable trajectories are constant across batches. To answer these questions, a thorough study of the most common types of asynchronisms that may be found in batch data is done. Furthermore, two new synchronization techniques are proposed to solve the current problems in post-batch and real-time synchronization. First, a synchronization strategy that copes with variable trajectories affected by multiple asynchronisms in an optimum way, maximizing synchronization quality and reducing false alarms in the monitoring schemes is presented. The second synchronization method is the so-called Relaxed Greedy Time Warping (RGTW), which enables the real-time synchronization of batch trajectories. To improve fault detection and classification, new unsupervised control charts and supervised fault classifiers based on the information generated by the batch synchronization are also proposed. In the third block of the manuscript, a research work is performed on the parameter stability associated with the most used synchronization methods and principal component analysis (PCA)-based Batch Multivariate Statistical Process Control methods. The results of this study have revealed that accuracy in batch synchronization has a profound impact on the PCA model parameters stability. Also, the parameter stability is closely related to the type of preprocessing performed in batch data, and the type of model and unfolding used to transform the three-way data structure to two-way. The setting of the parameter stability, the source of variability remaining after preprocessing and the process dynamics should be balanced in such a way that multivariate statistical models are accurate in fault detection and diagnosis and/or in online prediction. Finally, the fourth block introduces a graphical user-friendly interface developed in Matlab code for batch process understanding and monitoring. This toolbox integrates, on the one hand, the two phases of the design of a monitoring scheme (model building and exploitation), and on the other hand, the four main steps in the bilinear modeling of batch processes (alignment, preprocessing, calibration and monitoring). Additionally, a simulator to generate batch data of a fermentation process of the Saccharomyces cerevisiae cultivation is provided. In this version of the software package, the bilinear modeling is performed using the three-way structure that contains the variable trajectories of historical batches. To perform multivariate analysis, the last developments in process chemometrics, including the methods proposed in this thesis, are implemented.
