| 论文标题 |
Concentration Measurement of Three-phase Flow Based on Multisensor Data Fusion with Flow Regime Identification |
| 作者 |
Hongli Hu, Xiaoxin Wang , Lin Li, Jiebing Yan |
| 发表/完成日期 |
2015-09-25 |
| 期刊名称 |
9th International Symposium on Measurement Techniques for Multiphase Flow, Sapp |
| 期卷 |
|
| 相关文章 |
|
| 论文简介 |
In this paper, electrostatic sensor and capacitance sensor are used to measure the phase concentration of pulverized coal/biomass/air three-phase flow through data fusion technology. In order to eliminate the effects of flow regimes and improve the accuracy of phase concentration measurement, the Mel Frequency Cepstrum Coefficient (MFCC) features are extracted from electrostatic signal and the features are used to train the Continuous Gaussian Mixture Hidden Markov Model (CGHMM) for each flow regime. Support Vector Machine (SVM) regression algorithm is introduced to establish the pulverized coal and biomass concentration information fusion model under identified flow regimes. The CGHMM models and SVM models are transplanted on DSP (TMS320C6713B), meanwhile the programs that identifies the flow regime and predicts the phase concentration are developed on DSP platform to realize on-line accurate measurement. The experimental results show that the accuracy rate of flow regime identification reaches 98%, DSP flow regime identification time is 2.4ms, and the concentration predict time is 224s, which can fully meet the real-time requirement. The maximum fiducial error of the pulverized coal is 2.2% and that of the biomass is 3.5%, which meet the industry field requirements. |
(创新港)
