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.
Highlights
Since the gasoline engine became vehicle power in the 19th century, the importance of gasoline has been increasing
Based on the shortage of back propagation (BP), this study proposed the stacked denosing denosing auto-encoder auto-encoder (SDAE)
In the course of SDAE-BP training, 400 sets of samples are selected as the training samples
Summary
Since the gasoline engine became vehicle power in the 19th century, the importance of gasoline has been increasing. Research on data-driven soft sensing of octane has been carried out for decades and many excellent methods have been proposed. [12]used usedthe theneural neural network predict octane number prediction results been achieved. This indicates that neural networks have potential for further research in predicting have been achieved. Proposed performance enables auto-encoding networks to level learnabstract deeperfeatures, features. DAE should be able to efficiently reconstruct abstract features, Vincent et al [18] proposed a denoising auto-encoder (DAE), which indicated the original data be from missing or noise-containing input data.data. The achieved soft sensor model is used to estimate the real time octane number.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
