As the most important properties in the gasoline blending process, octane number is difficult to be measured in real time. To address this problem, a novel deep learning based soft sensor strategy, by using the near-infrared (NIR) spectroscopy obtained in the gasoline blending process, is proposed. First, as a network structure with hidden layer as symmetry axis, input layer and output layer as symmetric, the denosing auto-encoder (DAE) realizes the advanced expression of input. Additionally, the stacked DAE (SDAE) is trained based on unlabeled NIR and the weights in each DAE is recorded. Then, the recorded weights are used as the initial parameters of back propagation (BP) with the reason that the SDAE trained initial weights can avoid local minimums and realizes accelerate convergence, and the soft sensor model is achieved with labeled NIR data. Finally, the achieved soft sensor model is used to estimate the real time octane number. The performance of the method is demonstrated through the NIR dataset of gasoline, which was collected from a real gasoline blending process. Compared with PCA-BP (the dimension of datasets of BP reduced by principal component analysis) soft sensor model, the prediction accuracy was improved from 86.4% of PCA-BP to 94.8%, and the training time decreased from 20.1 s to 16.9 s. Therefore, SDAE-BP is proposed as a novel method for rapid and efficient determination of octane number in the gasoline blending process.
1 August 2018 in Chinese Journal of Chemical Engineering
KIT-6 silica with well-ordered three–dimensional (3D) mesopores has been synthesized as a support for nickel-based catalysts. Transmission Electron Microscopy (TEM) and low-angle X-ray Diffraction (XRD) analysis are used to ensure that the ordered 3D mesostructure is stable after NiO incorporation. In this study, the catalytic activities of the NiO/KIT-6 samples are investigated. Additionally, the results show that a 10 wt% NiO/KIT-6 catalyst exhibits high catalytic performance in methane combustion, with T10, T50 and T90 being only 386 °C, 456 °C and 507 °C, respectively. Hydrogen Temperature Programmed Reduction (H2-TPR) studies have shown that the interaction between NiO and KIT-6 in the 10 wt% NiO/KIT-6 catalyst is weak. Methane Temperature programmed Surface Reaction (CH4-TPSR) results show that the surface oxygen of the NiO/KIT-6 catalyst allows it to exhibit a high catalytic performance. NiO/KIT-6 catalysts exhibit superior activities to SBA-15, MCF and SiO2 support catalysts because KIT-6 has a higher surface area and ordered 3D mesopore connectivity, which is favorable for better NiO dispersion and peculiar diffusion for reactant and products. Furthermore, the used catalyst maintained an ordered mesostructure and reduction property.
Methane catalytic combustion, a method for efficient methane utilization, features high energy efficiency and low emissions. The key to this process is the development of highly active and stable catalysts. This study involved the synthesis of a range of catalysts, including NiO/CeO2, NiO–M/CeO2, and NiO-Ba/CeO2. In order to modify the NiO/CeO2 catalysts to improve their catalytic activity, various alkaline earth metal ions were introduced, and the catalysts were characterized to evaluate the impact of different alkaline earth metal ion doping. It was found that the introduction of Ba as a dopant yielded the highest catalytic activity among the dopants tested. Based on this, the influence of the impregnation sequence, the Ba loading amount, and other factors on the catalytic activity of the NiO/CeO2 catalysts doped with Ba were investigated, and comprehensive characterization was conducted using a variety of analytical techniques, including N2 adsorption/desorption, X-ray diffraction, Fourier transform infrared, hydrogen temperature-programmed reduction, methane temperature-programmed surface reaction, and oxygen temperature-programmed oxidation. The H2–TPR characterization results suggest that Ba introduction partially enhances the reducing property of NiO/CeO2 catalysts, and improves the surface oxygen activity in the catalysts. Meanwhile, the CH4–TPSR and O2–TPO results indicate that Ba introduction also boosts the bulk-phase oxygen liquidity in the catalysts, renders the migration of bulk-phase oxygen to surface oxygen, and increases the surface oxygen number in the catalysts. These results provide evidence of the effectiveness of this catalyst in methane catalytic combustion.