Xuexiang Zhang
ABSTRACT
Aiming at the problem that the traditional formula method is very complicated to calculate the pipeline pressure loss in the design process of pneumatic conveying system, the paper proposes a prediction model of pipeline pressure loss based on deep neural network (DNN). By supervising and analyzing the signals of flow parameters in the process of conveying, it can effectively extract the characteristics of signal by self-adaptive learning. The advantage of this prediction model is that it does not need to extract the characteristics of flow parameters signal in advance, and directly realizes the prediction of pipeline pressure loss end-to-end. This model avoids the complexity and signal loss in the process of artificially extracting parameter features, has higher stability and better prediction effect.
- HINTON G.E.l., Osindero S., and Teh Y. W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7): 1527--1554.Google Scholar
Digital Library
- WATANABE K. (1995). Transport of solid by pipelines with spiral tube. ASME, 234(Complete):57--64.Google Scholar
- Rinoshika A, Suzuki M. (2009). An experimental study of energy-saving pneumatic conveying system in a horizontal pipeline with dune mode. Powder Technology, 198(1):49--55.Google ScholarCross Ref
- Fei Yan, Rinoshika A. (2013). Particle fluctuation velocity of a horizontal self-excited pneumatic conveying near the minimum pressure drop. Powder Technology, 241(Complete):115--125.Google ScholarCross Ref
- LiHui Wang, Chunsheng Luo (2019). Experimental study on the energy-saving effect of self-excited flow. Journal of Jiangsu University of Science and Technology (Natural Science Edition), 33(03):49--54.Google Scholar
- Yong Li, Haiping Wang (2010). Energy-saving experiment of carbon black dense phase pneumatic conveying. Design of Sulphur and Phosphorus and Powder Engineering, 29(01):8--11+56.Google Scholar
- LiLi Gong (2009). Design and experimental study of silica pneumatic conveying system. Shandong: Qingdao University of Science and Technology.Google Scholar
- Dong Yu, Li Deng (2018). Deep learning speech recognition application book. Electronic Industry Press, Beijing.Google Scholar
- HINTON G.E. (2007). Learning multiple layers of representation. Trends in Cognitive Sciences, 11(10): 429--433.Google ScholarCross Ref
- HINTON G.E. (2010). A Practical Guide to Training Restricted Boltzmann Machines. Momentum, 9(1): 926--947.Google Scholar
Index Terms
- Study on the Optimum Design of Pneumatic Conveying System Based on DNN
Recommendations
Analysis of Influencing Factors of Pipeline Blockage in Domestic Garbage Pneumatic Conveying System
2019 IEEE International Conference on Mechatronics and Automation (ICMA)The calculation shows that, compared with the conventional material pneumatic conveying, the size and density of domestic garbage transported by the pneumatic conveying system are larger, and the pressure loss of the bend pipe section will not have ...
Comments