Yanfei YAO

Dr. Yanfei YAO

Xi'an University of Architecture and Technology.
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 October 2020 in Energies
Verified
Journal Article
Open access
PDF file
Yanfei YAOYanfei YAO
Yanfei YAO
SDSongxiong Ding
Songxiong Ding
YCYanxin Chen
Yanxin Chen
This paper proposes that the scope of research should be extended to the whole clinker calcination system from its single device or specific process (i.e., its functional subunits) as conventionally conducted. Mass/heat flow and effective heat were first analyzed to obtain the thermal efficiencies of its subunits (φi); a thermal efficiency model of the whole system φQY was thus established by correlating the relationship between φi and φQY. The thermal efficiency model of the whole system showed that φi had a positive linear correlation with φQY; it was found that the thermal efficiency of the decomposition and clinker calcination unit (φDC) had the greatest weight on φQY, where a 1% increase in φDC led to a 1.73% increase in φQY—improving φDC was shown to be the most effective way to improve φQY. In this paper, the developed thermal efficiency model was applied to one 5000 MT/D production line. It was found that its φQY was only 61.70%—about 2.35% lower than a representative line; such decrease was caused by its low φDC and φP which, as disclosed by model, were derived from the low decomposition rate of calcium carbonate in preheated meal put into a calciner and the high excess air coefficient of secondary air. Controlled parameter optimization of this 5000 MT/D production line was then carried out. As a result, the φDC and φP of the production line were increased from 30.03% and 64.61% to 30.69% and 65.69%, respectively; the φQY increased from 61.70% to 62.55%; the clinker output of the production line increased from 5799 MT/D to 5968 MT/D; the heat consumption of clinker was reduced from 3286.98 kJ/kg·cl to 3252.41 kJ/kg·cl.

18 January 2023 in Processes
Verified
Journal Article
Open access
PDF file
XLXuanzhi Liu
Xuanzhi Liu
YCYanxin Chen
Yanxin Chen
NHNing He
Ning He
Yanfei YAOYanfei YAO
Yanfei YAO
NOx concentration is an important indicator of the response to ammonia dosage and nitrogen emissions, and its accurate prediction allows for efficient and rational optimal control of ammonia dosage. Due to the large external noise, time lag and non-linearity of the cement denitrification process, it is difficult to derive accurate mathematical prediction models. Therefore, a new machine learning model, namely EEMD-MImRMR-BASBP, is developed. Firstly, Ensemble Empirical Mode Decomposition (EEMD) and median-averaged filtering is used to process the data and remove the noise. In order to handle the large time lags, non-linearity and non-smoothness among the variables, mutual information (MI) based on the entropy principle is proposed to calculate the lag time of the non-linear system; furthermore, according to the feature variable selection method of Max-Relevance and Min-Redundancy (mRMR), the factors with strong influence are selected as the input variables of the prediction model in combination with the results of the mechanism analysis. Then, the EEMD-MImRMR-BASBP model to predict NOX concentration is constructed, in which the initialization parameters of the Back Propagation Neural Network (BP) are searched by Beetle Antennae Search (BAS) to effectively overcome the parameter selection problem of traditional BP prediction models. Finally, the model was applied for the NOX concentration prediction of a real cement plant in Jiang xi and Fu ping and compared with the classical BP-based prediction model, BASBP model, the root means square error (RMSE) and mean absolute error (MAE) of the EEMD-MImRMR-BASBP model for the two production lines are only 0.2927, 0.3513 and 0.1795, and 0.2383, which have better prediction performance compared with the current model.