基于BP神经网络的旋风分离器分割粒径模化与预测

doi:10.16085/j.issn.1000-6613.2020-0640

化工进展 ›› 2021, Vol. 40 ›› Issue (2): 671-677.DOI: 10.16085/j.issn.1000-6613.2020-0640

基于BP神经网络的旋风分离器分割粒径模化与预测

刘金鹏¹^,²(), 赵兵涛¹^,²(), 钱魏锋¹^,², 李会梅¹^,²

^1.上海理工大学能源与动力工程学院，上海 200093
^2.上海市动力工程多相流动与传热重点实验室，上海 200093

收稿日期:2020-04-22 修回日期:2020-05-29 出版日期:2021-02-05 发布日期:2021-02-09
通讯作者: 赵兵涛
作者简介:刘金鹏（1996—），男，硕士研究生，研究方向为旋流流动与过程强化。E-mail：381845366@qq.com。
基金资助:
上海市自然科学基金(17ZR1419300)

Modeling and prediction of particle cutoff size of cyclone separator based on BP neural network

Jinpeng LIU¹^,²(), Bingtao ZHAO¹^,²(), Weifeng QIAN¹^,², Huimei LI¹^,²

^1.School of Energy and Power Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
^2.Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power Engineering, Shanghai 200093, China

Received:2020-04-22 Revised:2020-05-29 Online:2021-02-05 Published:2021-02-09
Contact: Bingtao ZHAO

摘要/Abstract

摘要：

为精确建立分割粒径与旋风分离器结构参数和操作参数之间的复杂映射关系，发展了基于数据驱动的BP神经网络（BPNN）的分割粒径模型。使用全局量纲分析，提出环形空间雷诺数、表征旋风分离器本体尺寸影响的量纲为1数和排气芯管插入深度尺寸比作为网络输入参数，表征空气动力等效分割粒径大小的量纲为1尺寸作为网络输出参数，分别确定了训练算法和隐含层神经元个数对BPNN分割粒径模型预测精度的影响。结果表明：贝叶斯正则化算法优于L-M算法和拟牛顿算法，并在隐含层神经元个数为7时达到最优预测性能。与理论模型、半经验模型和多元回归模型进行比较，结果表明，贝叶斯正则化BPNN分割粒径模型展现出了较好的预测能力和泛化性能，模型预测的均方误差为0.136、决定系数为0.975。

关键词: 离心分离, 分割粒径, 神经网络, 贝叶斯正则化

Abstract:

In order to establish the complex relationship between the particle cutoff size and the full dimensions and operation parameters of cyclone separator accurately, a BP neural network (BPNN) model was develop based on data-driven for particle cutoff size. The global dimensional analysis was used, where the annular Reynolds number, the dimensionless number characterizing the impact of cyclone body dimensions, and vortex finder dimension ratio were proposed as network inputs, while the dimensionless dimension which characterized the aerodynamic equivalent particle cutoff size was adopted as network output. The influences on the training algorithm and the number of hidden neurons on model accuracy were determined, respectively. The results showed that the Bayesian regularization algorithm was superior to the L-M algorithm and the quasi-newton algorithm. The optimal prediction performance was achieved when the number of hidden layer neurons is 7. Compared with theoretical model, semi-empirical model and multiple regression model, the Bayesian regularization BPNN particle cutoff size model showed better prediction ability and generalization performance, with the mean square error of the model 0.136 and the coefficient of determination 0.975.

Key words: centrifugation, particle cutoff size, neural network, Bayesian regularization

中图分类号:

TQ051.8

刘金鹏, 赵兵涛, 钱魏锋, 李会梅. 基于BP神经网络的旋风分离器分割粒径模化与预测[J]. 化工进展, 2021, 40(2): 671-677.

Jinpeng LIU, Bingtao ZHAO, Weifeng QIAN, Huimei LI. Modeling and prediction of particle cutoff size of cyclone separator based on BP neural network[J]. Chemical Industry and Engineering Progress, 2021, 40(2): 671-677.

参考文献 40

1	姜旭, 王翠苹, 张龙龙. 煤化学链燃烧装置中串联分离器的数值模拟与性能优化[J]. 化工进展, 2016, 35(2): 425-431.
	JIANG Xu, WANG Cuiping, ZHANG Longlong. Numerical simulation and optimization on the performance of double-stage cyclone separator in coal-fueled CLC facility[J]. Chemical Industry and Engineering Progress, 2016, 35(2): 425-431.
2	王敏, 吴迎亚, 石孝刚, 等. 气固循环流化床全回路数值模拟研究进展[J]. 化工进展, 2019, 38(1): 111-121.
	WANG Min, WU Yingya, SHI Xiaogang, et al. Review of full-loop simulation of gas-solid circulating fluidized bed[J]. Chemical Industry and Engineering Progress, 2019, 38(1): 111-121.
3	周先桃, 王依谋, 马良, 等. 液相射流吸收耦合气相旋流分离烟气脱硫[J]. 化工进展, 2016, 35(12): 4053-4059.
	ZHOU Xiantao, WANG Yimou, MA Liang, et al. Flue gas desulfurization research in liquid jet-absorption coupled gas cyclone-separation device[J]. Chemical Industry and Engineering Progress, 2016, 35(12): 4053-4059.
4	HOFFMANN A C, STEIN L E. Gas cyclones and swirl tubes: principles, design and operation[M]. 2nd ed. Heidelberg: Springer-Verlag Berlin, 2008: 90.
5	ZHAO Bingtao, WANG Dongshen, SU Yaxin, et al. Gas-particle cyclonic separation dynamics: modeling and characterization[J]. Separation & Purification Reviews, 2018, 49(2): 112-142.
6	LAPPLE C E. Gravity and centrifugal separation[J]. American Industrial Hygiene Association Quarterly, 1950, 11: 40-48.
7	BARTH W. Design and layout of the cyclone separator on the basis of new investigations[J]. Brennst-Warme-Kraft, 1956, 8(1): 1-9.
8	IOZIA D L, LEITH D. Effect of cyclone dimensions on gas flow pattern and collection efficiency[J]. Aerosol Science Technology, 1989, 10: 491-500.
9	ZHAO Bingtao, SU Yaxin. Particle size cut performance of aerodynamic cyclone separators: generalized modeling and characterization by correlating global cyclone dimensions[J]. Journal of Aerosol Science, 2018, 120: 1-11.
10	MOORE M E, MCFARLAND A R. Performance modeling of single-inlet aerosol sampling cyclones[J]. Environmental Science & Technology, 1993, 27(9): 1842-1848.
11	LIDÉN G, GUDMUNDSSON A. Semi-empirical modelling to generalise the dependence of cyclone collection efficiency on operating conditions and cyclone design[J]. Journal of Aerosol Science, 1997, 28(5): 853-874.
12	舒朝晖, 肖莉, 程雁, 等. 油水分离水力旋流器的人工神经网络模拟[J]. 石油机械, 2003, 31(3): 11-13, 33.
	SHU Zhaohui, XIAO Li, CHENG Yan, et al. Artificial neural network simulation of hydrocyclones for oil-water separation[J]. China Petroleum Machinery, 2003, 31(3): 11-13, 33.
13	SAFIKHANI H, HAJILOO A, RANJBAR M A. Modeling and multi-objective optimization of cyclone separators using CFD and genetic algorithms[J]. Computers & Chemical Engineering, 2011, 35(6): 1064-1071.
14	ELSAYED K, LACOR C. Modeling and Pareto optimization of gas cyclone separator performance using RBF type artificial neural networks and genetic algorithms[J]. Powder Technology, 2012, 217: 84-99.
15	HAGAN M T, MENHAJ M B. Training feedforward networks with the Marquardt algorithm[J]. IEEE Transactions on Neural Networks, 1994, 5(6): 989-993.
16	ANTONIOU A, LU Wusheng. Practical optimization: algorithms and engineering applications[M]. New York: Springer, 2007: 191-192.
17	FORESEE F D, HAGAN M T. Gauss-Newton approximation to Bayesian learning[C]// Proceedings of International Conference on Neural Networks. USA: IEEE, 1997: 1930-1935.
18	RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back propagating errors[J]. Nature, 1986, 323: 533-536.
19	HECHT-NIELSEN R. Theory of the backpropagation neural network[C]//International 1989 Joint Conference on Neural Networks. USA: IEEE, 1989: 593-605.
20	TICKNOR J L, HSU-KIM H, DESHUSSES M A. A robust framework to predict mercury speciation in combustion flue gases[J]. Journal of Hazardous Materials, 2014, 264: 380-385.
21	ELSAYED K, LACOR C. The effect of cyclone inlet dimensions on the flow pattern and performance[J]. Applied Mathematical Modelling, 2011, 35(4): 1952-1968.
22	ZHAO Bingtao, SU Yaxin. Cyclone performances depend on multiple factors: comments on “A CFD study of the effect of cyclone size on its performance parameters” by Mehdi Azadiet al. (2010)[J]. Journal of Hazardous Materials, 2016, 303: 174-176.
23	李庆生, 张译峰. 基于响应曲面法的蜗壳式旋风分离器分离效率[J]. 中国粉体技术, 2015, 21(1): 96-99.
	LI Qingsheng, ZHANG Yifeng. Separation efficiency of volute cyclone based on response surface method[J]. China Powder Science and Technology, 2015, 21(1): 96-99.
24	ZHU Yifang, LEE K W. Experimental study on small cyclones operating at high flowrates[J]. Journal of Aerosol Science, 1999, 30(10): 1303-1315.
25	XIANG Rongbiao, LEE K W. Numerical study of flow field in cyclones of different height[J]. Chemical Engineering and Processing, 2005, 44(8): 877-883.
26	DRING R P, SUO M. Particle trajectories in swirling flows[J]. Energy, 1978, 2(4): 232-237.
27	MOORE M E, MCFARLAND A R. Design methodology for multiple inlet cyclones[J]. Environmental Science & Technology, 1996, 30(1): 271-276.
28	STAIRMAND C J. The design and performance of cyclone separators[J]. Industrial and Engineering Chemistry, 1951, 29: 356-383.
29	WHITBY K T, PETERSON C M. Electrical neutralization and particle size measurement of dye aerosols[J]. Industrial & Engineering Chemistry Fundamentals, 1965, 4(1): 66-72.
30	BEECKMANS J M, KIM C J. Analysis of the efficiency of reverse flow cyclones[J]. Canadian Journal of Chemical Engineering, 1977, 55(6): 640-643.
31	SALTZMAN B E, HOCHSTRASSER J M. Design and performance of miniature cyclones for respirable aerosol sampling[J]. Environmental Science & Technology, 1983, 17(7): 418-424.
32	DIRGO J, LEITH D. Cyclone collection efficiency: comparison of experimental results with theoretical predictions[J]. Aerosol Science and Technology, 1985, 4(4): 401-415.
33	MOORE M E, MCFARLAND A R. Design of stairmand-type sampling cyclones[J]. American Industrial Hygiene Association, 1990, 51(3): 151-159.
34	MOORE M E, MCFARLAND A R. Performance modeling of single-inlet aerosol sampling cyclones[J]. Environmental Science & Technology, 1993, 27(9): 1842-1848.
35	KIM J C, LEE K W. Experimental study of particle collection by small cyclones[J]. Aerosol Science and Technology, 1990, 12(4): 1003-1015.
36	KENNY L C, GUSSMAN R A. Characterisation and modelling of a family of cyclone aerosol preseparators[J]. Journal of Aerosol Science, 1997, 28(4): 677-688.
37	XIANG R B, PARK S H, LEE K W. Effects of cone dimension on cyclone performance[J]. Journal of Aerosol Science, 2001, 32(4): 549-561.
38	ZHAO Bingtao, SHEN Henggen, KANG Yanming. Development of a symmetrical spiral inlet to improve cyclone separator performance[J]. Powder Technology, 2004, 145(1): 47-50.
39	HSIAO Ta-Chih, HUANG Sheng-Hsiu, Chia-Wei HSU, et al. Effects of the geometric configuration on cyclone performance[J]. Journal of Aerosol Science, 2015, 86: 1-12.
40	KENNARD R W, STONE L A. Computer aided design of experiments[J]. Technometrics, 1969, 11(1): 137-148.

[1]	徐晨阳, 都健, 张磊. 基于图神经网络的化学反应优劣评价[J]. 化工进展, 2023, 42(S1): 205-212.
[2]	俞俊楠, 俞建峰, 程洋, 齐一搏, 化春键, 蒋毅. 基于深度学习的变宽度浓度梯度芯片性能预测[J]. 化工进展, 2023, 42(7): 3383-3393.
[3]	张建伟, 许蕊, 张忠闯, 董鑫, 冯颖. 基于卷积神经网络的撞击流反应器浓度场混合特性[J]. 化工进展, 2023, 42(2): 658-668.
[4]	王璐, 张磊, 都健. 机器学习高效筛选用于CO₂/N₂选择性吸附分离的沸石材料[J]. 化工进展, 2023, 42(1): 148-158.
[5]	潘艳秋, 李鹏飞, 高石磊, 俞路. 基于MIC筛选规则和BP神经网络的变换装置建模及产品预测[J]. 化工进展, 2022, 41(S1): 36-43.
[6]	李国友, 张新魁, 才士文, 贾曜宇, 宁泽. 基于改进KFDA与DE优化SOM的故障诊断模型及其化工过程诊断[J]. 化工进展, 2022, 41(4): 1793-1801.
[7]	李欣铜, 陈志冰, 魏志强, 李苏桐, 陈旭, 宋凯. 具有输入数据注意力机制的卷积神经网络用于氟化工产品质量预测[J]. 化工进展, 2022, 41(2): 593-600.
[8]	李帅, 刘明言, 马永丽. 基于BP人工神经网络预测地热井中流体的结垢位置[J]. 化工进展, 2022, 41(11): 5761-5770.
[9]	朱明军, 胡大鹏. 操作参数对三相卧螺离心机油水砂分离性能影响模拟及实验分析[J]. 化工进展, 2022, 41(10): 5188-5199.
[10]	王英, 冉进业, 张今, 杨鑫, 张浩. 基于深度时间序列特征融合的西安市2015—2020年供暖季雾霾重污染过程预警[J]. 化工进展, 2022, 41(10): 5685-5694.
[11]	李芳国, 张贝克, 高东. HAZOP知识图谱构建方法[J]. 化工进展, 2021, 40(8): 4666-4677.
[12]	范峥, 田润芝, 林亮, 韩彦忠, 郭阳, 豆龙龙, 景根辉, TYOOR Agi Damian. 利用基于PSO算法的径向基人工神经网络优化重催干气脱硫[J]. 化工进展, 2021, 40(6): 3107-3118.
[13]	张梦轩, 刘洪辰, 王敏, 蓝兴英, 石孝刚, 高金森. 化工过程的智能混合建模方法及应用[J]. 化工进展, 2021, 40(4): 1765-1776.
[14]	马双忱, 林宸雨, 周权, 吴忠胜, 刘琦, 陈文通, 樊帅军, 要亚坤, 马采妮. 基于深度神经网络的脱硫系统预测模型及应用[J]. 化工进展, 2021, 40(3): 1689-1698.
[15]	杨文宇, 谢应明, 闫坤, 邹俊华, 舒胜. 基于灰色关联BP神经网络的压缩式蓄冷系统中的水合物生成量预测[J]. 化工进展, 2021, 40(2): 664-670.

基于BP神经网络的旋风分离器分割粒径模化与预测

Modeling and prediction of particle cutoff size of cyclone separator based on BP neural network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 40

相关文章 15

编辑推荐

Metrics

本文评价