This work is concerned with the development of multivariate calibration models to establish spectrum-composition relationships for the hydrocarbon products in the H-ZSM-5catalyzed oligomerization of propylene. Regression models based on two multivariate methods were investigated in this work: leastsquares-support vector machines (LS-SVM) and partial leastsquares (PLS) regression. The performance of two nonlinear kernels, radial basis function (RBF) and polynomial, is compared with PLS as well as its variant, interval-PLS regression (i-PLSR). For comparison with i-PLSR, the Fourier transform infrared (FTIR) spectra of the products served as inputs and the respective C 1 −C 10 concentrations, obtained from gas chromatography (GC), were the outputs. The sensitivity of the product distribution to inlet operating conditions was also evaluated through the calibration methods. Spectral clusters having distinct chemical character were identified using principal component analysis (PCA) and hierarchical clustering analysis (HCA) and also used as inputs to the different regression techniques to compare with the full spectrum models. It was found that the best performing spectral regions from i-PLSR had chemical relevance and agreed with findings from HCA, improving the predictive capabilities significantly. The decreasing order of performance of the chemometric methods evaluated was: LS-SVM-RBF > LS-SVM-Polynomial > i-PLS > PLS. The prediction accuracy of RBF kernel-based LS-SVM regression technique was the highest, indicating its suitability for effective online monitoring of moderately complex processes like acid-catalyzed propylene oligomerization.

We present a data-driven approach to identifying the reaction network of the dominant chemistry in complex mixtures using model compounds representative of cellulose and lignin chemistry that are processed using hydrous pyrolysis. We present two methods for the identification of pseudocomponents: self-modeling multivariate curve resolution, which is a non-negative matrix factorization method, and Bayesian hierarchical clustering. The pseudocomponents are identified from spectroscopic data from two sources: Fourier transform infrared spectroscopy and 1H NMR spectroscopy. The data from the two sources is combined using a simple data combination method. Once pseudocomponents have been identified, Bayesian networks are used to identify directed pathways between the components, resulting in a proposed hypothesis for the reaction network or mechanism. We validate the methods by showing consistency of the derived reaction networks with the known chemistry of cellulose, lignin, and their derivatives and demonstrate the importance of data fusion in developing believable reaction networks.

No abstract

Chemometric tools to monitor the tetralin oxidation process and identify key parameters that influence product selectivity have not been investigated before.

Inferring the reaction pathways underlying the processing of complex feeds, using noisy data from spectral sensors that may contain information regarding molecular mechanisms, is challenging. This is tackled by a...