SDAE-BP Based Octane Number Soft Sensor Using Near-infrared Spectroscopy in Gasoline Blending Process

Abstract

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.

Supply Chain Design for Blending Technologies

“…The existing research results are focusing on the technological aspects of blending processes in different fields of manufacturing (oil blending [5], metallurgical industry [14], asphalt mixtures [19]) and they do not take the impact of logistics aspects on the performance of the blending process into consideration. The technological aspects are deeply analyzed in a wide range of articles (aging characteristics in blending processes [61], experimental and discrete element models in blending processes [62], recycling aspects in blending [63], monitoring and sensoring of blending processes [64,65]). The process optimization approaches are focusing on the process monitoring [31], adaptive algorithms of control processes [33], and imaging techniques to determine mixture components [35], but they are not focusing on the integrated mathematical modelling and optimization of blending processes from both the point of view of technological and logistical aspects.…”

Multi-feature optimization of QSPR model for fuel octane number

“…[4] In recent years, researchers have developed some methods using spectroscopic analysis to predict octane numbers. [5][6][7][8] However, instrument measurement is timeconsuming, labor-intensive, and expensive. Therefore, establishing a theoretical prediction model for octane number is of great significance.…”

Transfer of near infrared calibration for gasoline octane number based on screening consistent wavelengths combined with direct standardization algorithm

“…Near infrared (NIR) spectroscopy has been widely used in the petrochemical industry due to its advantages of rapid test speed, low sample consumption, non-destructive and little sample preparation. 1,2 However, due to changes in the types of NIR specrometers and experimental conditions, the multivariate calibration model established for one instrument cannot readily be shared with other instruments, which severely restricts the accurate quantitative and qualitative analysis of NIR spectra. This problem has become one of the key research directions in the field of NIR spectroscopy.…”