基于k-means机器学习方法的气固循环流化床颗粒聚团特性

doi:10.16085/j.issn.1000-6613.2024-0132

摘要/Abstract

摘要：

循环流化床因其优良的气固接触特性在工业生产中的应用十分广泛。颗粒聚团的存在影响着气固相互作用和传热传质，进而影响产品收率和选择性。为了更高效和深入地研究循环流化床内的颗粒聚团现象，本研究利用高速摄像系统对U_g=5~9m/s、G_s=50~300kg/(m²·s)的二维循环流化床内的流场结构进行了可视化采样。采用k-means机器学习算法辅助图像处理，实现复杂流场中颗粒聚团的识别以及定量表征。结果表明，当U_g=9m/s时，随着G_s由50kg/(m²·s)增大至300kg/(m²·s)，颗粒聚团频率由116Hz增加到327Hz，增长了近2倍。平均颗粒聚团浓度在横向截面中心区域y/Y=0~0.7处分布较为均匀，在y/Y=0.7~0.9的边壁处迅速增大。边壁处平均颗粒聚团浓度的变化幅度约为中心区域的3倍。平均颗粒聚团速度以及平均颗粒等效直径在横向上均表现出相同的变化趋势，均由中心向边壁递减。结合实验数据，对不同聚团参数进行拟合，获得了定量预测各个参数的关联式。对比实验数据与预测数据发现，本实验建立的定量关联式获得的预测结果相对误差均在30%以下。本研究结果定量地揭示了循环流化床内各颗粒聚团特性的分布规律，可以为循环流化床气固流动模型开发和过程强化提供数据参考。

关键词: 流态化, 循环流化床, k-means机器学习, 颗粒聚团, 预测

Abstract:

Circulating fluidized bed is widely used in industrial production due to its good gas-solids mixing. Clustering characteristics affect the gas-solids contacting and therefore the heat/mass transfer and the yield of the products as well as the selectivity. To get more detailed information effectively, a high-speed camera was used to visualize the flow field in a two-dimensional circulating fluidized bed at the superficial gas velocity, U_g, equal to 5—9m/s, and the solids circulating rate, G_s, of 50—300kg/(m²·s). The k-means machine learning algorithm was then utilized to assist the image processing to identify the cluster effectively and quantificationally. Results showed that as G_s increased from 50kg/(m²·s) to 300kg/(m²·s) at U_g=9m/s, the cluster frequency almost doubled from 116Hz to 327Hz. The average cluster concentration was correlated with the local lateral position. The average cluster concentration was more uniformly distributed in the central region (y/Y from 0 to 0.7). Toward the near wall region (y/Y from 0.7 to 0.9) it increases rapidly. The change of the average cluster concentration near the wall was nearly three times higher than in the central region. Both the average cluster velocity and the average cluster equivalent diameter displayed a similar trend, decreasing from the center toward the wall in the lateral direction. Quantitative prediction equations for cluster parameters were obtained based on the experimental data. The relative errors were all within 30%. Cluster characteristics were studied quantitatively and systematically in this study. These results can support the development of a gas-solids flow model and process intensification for circulating fluidized beds.

Key words: fluidization, circulating fluidized bed, k-means machine learning, cluster, prediction

中图分类号:

TQ021.1

孙俭, 张海勇, 王成秀, 孙泽能, 蓝兴英, 高金森, 祝京旭. 基于k-means机器学习方法的气固循环流化床颗粒聚团特性[J]. 化工进展, 2025, 44(2): 625-634.

SUN Jian, ZHANG Haiyong, WANG Chengxiu, SUN Zeneng, LAN Xingying, GAO Jinsen, ZHU Jingxu. Cluster characteristics in gas-solids circulating fluidized bed based on k-means algorithm-assisted imaging method[J]. Chemical Industry and Engineering Progress, 2025, 44(2): 625-634.

图/表 10

图1 实验装置示意图1—主风；2—气体分布器；3—提升管；4—旋风分离器；5—切换阀；6—测量筒；7—储料罐；8—流化风；9—下料斜管；10—布袋除尘器；11—伴床；12—计算机；13—高速摄像机；14—黑箱；15—扩散板；16—光源

图2 图像处理的流程图

图3 二维床内典型气固流动原始图像及聚团分布特性

图4 不同轴向位置上颗粒聚团频率对比

图5 不同轴向位置上平均颗粒聚团浓度与平均颗粒浓度横向分布

图6 平均颗粒聚团浓度的关联与预测

图7 不同轴向位置上平均颗粒聚团速度和平均颗粒速度横向分布

图8 平均颗粒聚团速度的关联与预测

图9 不同轴向位置上平均颗粒聚团等效直径与平均颗粒速度横向分布

图10 平均颗粒聚团等效直径的关联与预测

参考文献 42

1	金涌, 程易, 白丁荣, 等. 中国流态化技术研发史略[J]. 化工进展, 2023, 42(6): 2761-2780.
	JIN Yong, CHENG Yi, BAI Dingrong, et al. Fluidization research and development in China[J]. Chemical Industry and Engineering Progress, 2023, 42(6): 2761-2780.
2	李洪钟, 郭慕孙. 回眸与展望流态化科学与技术[J]. 化工学报, 2013, 64(1): 52-62.
	LI Hongzhong, KWAUK Mooson. Review and prospect of fluidization science and technology[J]. CIESC Journal, 2013, 64(1): 52-62.
3	ZHANG Hai, Junfu LYU, YUE Guangxi. A review on research and development of CFB combustion technology in China[J]. Powder Technology, 2023, 414: 118090.
4	KOSAKA Fumihiko, SASAYAMA Tomone, LIU Yanyong, et al. Direct and continuous conversion of flue gas CO₂ into green fuels using dual function materials in a circulating fluidized bed system[J]. Chemical Engineering Journal, 2022, 450: 138055.
5	CHOI Seungyeong, YUN Maroosol, KIM Kiwoong, et al. Energy-efficient design of dual circulating fluidized bed system for CCUS by multi-tube configuration with junctions[J]. Energy, 2022, 245: 123258.
6	OSMAN Mogahid, ZAABOUT Abdelghafour, CLOETE Schalk, et al. Mapping the operating performance of a novel internally circulating fluidized bed reactor applied to chemical looping combustion[J]. Fuel Processing Technology, 2020, 197: 106183.
7	WANG Chao, ZHU Lianfeng, ZHANG Mengjuan, et al. A two-stage circulated fluidized bed process to minimize tar generation of biomass gasification for fuel gas production[J]. Applied Energy, 2022, 323: 119639.
8	NELSON Thomas O, KATARIA Atish, MOBLEY Paul, et al. RTI’s solid sorbent-based CO₂ capture process: Technical and economic lessons learned for application in coal-fired, NGCC, and cement plants[J]. Energy Procedia, 2017, 114: 2506-2524.
9	WANG Wei, LU Bona, ZHANG Nan, et al. A review of multiscale CFD for gas-solid CFB modeling[J]. International Journal of Multiphase Flow, 2010, 36(2): 109-118.
10	WANG Chengxiu, BARGHI Shahzad, ZHU Jesse. Hydrodynamics and reactor performance evaluation of a high flux gas-solids circulating fluidized bed downer: Experimental study[J]. AIChE Journal, 2014, 60(10): 3412-3423.
11	LI Yongzheng, ZHAI Guangwei, ZHANG Haitao, et al. Experimental and predictive research on solids holdup distribution in a CFB riser[J]. Powder Technology, 2019, 344: 830-841.
12	SU Xin, WANG Chengxiu, PEI Huajian, et al. Experimental study of solids motion in an 18 m gas-solids circulating fluidized bed with high solids flux[J]. Industrial & Engineering Chemistry Research, 2019, 58(51): 23468-23480.
13	LI Hongzhong, XIA Yashen, TUNG Yuanki, et al. Micro-visualization of clusters in a fast fluidized bed[J]. Powder Technology, 1991, 66(3): 231-235.
14	孔令菲, 陈延佩, 王维. 气固流态化中颗粒介尺度结构的动力学研究[J]. 化工学报, 2022, 73(6): 2486-2495.
	KONG Lingfei, CHEN Yanpei, WANG Wei. Dynamic study of mesoscale structures of particles in gas-solid fluidization[J]. CIESC Journal, 2022, 73(6): 2486-2495.
15	SHAFFER Frank, GOPALAN Balaji, BREAULT Ronald W, et al. High speed imaging of particle flow fields in CFB risers[J]. Powder Technology, 2013, 242: 86-99.
16	COCCO Ray, SHAFFER Frank, HAYS Roy, et al. Particle clusters in and above fluidized beds[J]. Powder Technology, 2010, 203(1): 3-11.
17	HARRIS A T, DAVIDSON J F, THORPE R B. The prediction of particle cluster properties in the near wall region of a vertical riser (200157)[J]. Powder Technology, 2002, 127(2): 128-143.
18	LU Huilin, SUN Qiaoqun, HE Yurong, et al. Numerical study of particle cluster flow in risers with cluster-based approach[J]. Chemical Engineering Science, 2005, 60(23): 6757-6767.
19	WANG Junwu. Continuum theory for dense gas-solid flow: A state-of-the-art review[J]. Chemical Engineering Science, 2020, 215: 115428.
20	CAHYADI Andy, ANANTHARAMAN Aditya, YANG Shiliang, et al. Review of cluster characteristics in circulating fluidized bed (CFB) risers[J]. Chemical Engineering Science, 2017, 158: 70-95.
21	FONG Kee Onn, COLETTI Filippo. Experimental analysis of particle clustering in moderately dense gas-solid flow[J]. Journal of Fluid Mechanics, 2022, 933: A6.
22	WEI Xiaoyang, YANG Jingsi, ZHU Jesse. Experimental analysis of phase segregation in gas-solid circulating fluidized bed riser with direct image calibration[J]. Chemical Engineering Journal, 2020, 379: 122301.
23	GRACE J R, WAIREGI T, BROPHY J. Break-up of drops and bubbles in stagnant media[J]. The Canadian Journal of Chemical Engineering, 1978, 56(1): 3-8.
24	LU Xuesong, LI Songgeng, DU Lin, et al. Flow structures in the downer circulating fluidized bed[J]. Chemical Engineering Journal, 2005, 112(1/2/3): 23-31.
25	GUO Yue, YIN Shangyi, LU Shibing, et al. An image processing method for feature extraction and dynamic tracking of particle clusters in CFBs[J]. Particuology, 2023, 77: 1-13.
26	FRANK Michael, DRIKAKIS Dimitris, CHARISSIS Vassilis. Machine-learning methods for computational science and engineering[J]. Computation, 2020, 8(1): 15.
27	ZHANG Yifu, WANG Chunyu, WANG Xinggang, et al. Fairmot: On the fairness of detection and re-identification in multiple object tracking[J]. International Journal of Computer Vision, 2021, 129(11): 3069-3087.
28	LI Zhuoling, DONG Minghui, WEN Shiping, et al. CLU-CNNs: Object detection for medical images[J]. Neurocomputing, 2019, 350: 53-59.
29	朱礼涛, 欧阳博, 张希宝, 等.机器学习在多相反应器中的应用进展[J]. 化工进展, 2021, 40(4): 1699-1714.
	ZHU Litao, OUYANG Bo, ZHANG Xibao, et al. Progress on application of machine learning to multiphase reactors[J]. Chemical Industry and Engineering Progress, 2021, 40(4): 1699-1714.
30	任喜伟, 何立风, 姚斌, 等. 油水界面测量过程中自适应阈值聚类优化算法[J]. 化工进展, 2019, 38(2): 779-789.
	REN Xiwei, HE Lifeng, YAO Bin, et al. Clustering optimization algorithm with adaptive threshold for oil-water interface detection process[J]. Chemical Industry and Engineering Progress, 2019, 38(2): 779-789.
31	WANG Tianyu, DENG Aiming, HE Yurong, et al. Artificial intelligence-based approach for cluster identification in a CFB riser[J]. Chemical Engineering Science, 2023, 268: 118379.
32	YIN Shangyi, ZHONG Wenqi, SONG Tao, et al. Clusters identification and meso-scale structures in a circulating fluidized bed based on image processing[J]. Advanced Powder Technology, 2019, 30(12): 3010-3020.
33	WANG Chengxiu, LAN Xingying, SUN Zeneng, et al. Cluster identification by a k-means algorithm-assisted imaging method in a laboratory-scale circulating fluidized bed[J]. Industrial & Engineering Chemistry Research, 2022, 61(1): 942-956.
34	WANG Chengxiu, LI Zhihui, WEI Jianjin, et al. Quantitative measurement of solids holdup for group A and B particles using images and its application in fluidized bed reactors[J]. Processes, 2022, 10(3): 610.
35	LIU Xinhua, XU Guangwen, GAO Shiqiu. Micro fluidized beds: Wall effect and operability[J]. Chemical Engineering Journal, 2008, 137(2): 302-307.
36	SÁNCHEZ-DELGADO S, ALMENDROS-IBÁÑEZ J A, GARCÍA-HERNANDO N, et al. On the minimum fluidization velocity in 2D fluidized beds[J]. Powder Technology, 2011, 207(1/2/3): 145-153.
37	漆小波. 循环流化床提升管气固两相流动力学研究[D]. 成都: 四川大学, 2003.
	QI Xiaobo. Gas-Solids Two Phase Flow Dynamics in Circulating Fluidized Bed Risers[D]. Chengdu: Sichuan University, 2003.
38	WEI Xiaoyang, ZHU Jesse. A comprehensive characterization of aggregative flow in a circulating fluidized bed (1): High-density riser[J]. Industrial & Engineering Chemistry Research, 2020, 59(22): 10315-10327.
39	XU Jing, ZHU Jesse. A new method for the determination of cluster velocity and size in a circulating fluidized bed[J]. Industrial & Engineering Chemistry Research, 2012, 51(4): 2143-2151.
40	YANG Jingsi, ZHU Jesse. Cluster identification using image processing[J]. Particuology, 2015, 23: 16-24.
41	WEI Xiaoyang, ZHU Jesse. Tracking the flow dynamics in circulating fluidized bed through high-speed photography[J]. Industrial & Engineering Chemistry Research, 2019, 58(37): 17540-17548.
42	WANG Chengxiu, LI Zhihui, SUN Zeneng, et al. Visualization on the meso-scale particle flow in turbulent fluidized bed reactors with lower H₀/D ratios via image processing[J]. Chemical Engineering Journal, 2023, 452: 139124.

编辑推荐 0

Metrics

阅读次数

全文

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	4	0	0	37

来源	本网站	其他网站

次数	36	5
比例	88%	12%

摘要

最新录用	在线预览	正式出版

0	0	86

来源	本网站	其他网站

次数	35	51
比例	41%	59%

[1]	潘家保, 李贻良, 王锦. 磁流变脂热效应行为的分析与预测[J]. 化工进展, 2025, 44(1): 415-423.
[2]	戴征舒, 左元浩, 陈孝罗, 张犁, 赵根, 张学军, 张华. 机器学习在喷射器研究中的应用进展[J]. 化工进展, 2024, 43(S1): 1-12.
[3]	邹志云, 于蒙, 刘英莉. 基于LSTM和BP神经网络的间歇蒸馏过程工况预测[J]. 化工进展, 2024, 43(S1): 21-31.
[4]	马永丽, 李沐阳, 马子皓, 王浩然, 王茂隆, 费瑶寒, 张露滨, 刘明言. 火星上的气固流态化模拟实验[J]. 化工进展, 2024, 43(8): 4203-4209.
[5]	丁路, 王培尧, 孔令学, 白进, 于广锁, 李文, 王辅臣. 煤气化过程反应模型研究进展[J]. 化工进展, 2024, 43(7): 3593-3612.
[6]	邹旭, 付亮亮, 胡枋伶, 宋佳, 高佳辉, 张庆瑾, 许光文, 白丁荣. 无机工业固体废弃物高温热化学转化的基础研究[J]. 化工进展, 2024, 43(7): 3756-3767.
[7]	郑锁祺, 詹凌霄, 陈恒, 李志浩, 王禹瑞, 赵宁, 吴昊, 杨林军. 基于混合模型的脱硫废水旁路蒸发系统能耗特性[J]. 化工进展, 2024, 43(6): 2968-2976.
[8]	张真, 张凡, 云祉婷. 绿氢在石化和化工行业的减碳经济性分析[J]. 化工进展, 2024, 43(6): 3021-3028.
[9]	张海霞, 朱治平, 张思源. 循环流化床高碱煤气化技术研发及应用进展[J]. 化工进展, 2024, 43(5): 2254-2278.
[10]	王欣宇, 王超, 张梦娟, 刘方正, 李晗旸, 王正林, 贾鑫, 宋兴飞, 许光文, 韩振南. 松木颗粒流态化两段气化制备清洁燃气的工艺稳定性验证[J]. 化工进展, 2024, 43(5): 2576-2586.
[11]	李欣泽, 邹炜杰, 孙晨, 付璇, 陈潜, 袁亮, 王梓丞, 邢晓凯, 熊小琴, 郭良辉. 新疆油田某超临界CO₂管道安全停输时间预测[J]. 化工进展, 2024, 43(5): 2823-2833.
[12]	郑可欣, 江雨欣, 毕可鑫, 赵祺铭, 陈少臣, 王冰冰, 任俊宇, 吉旭, 邱彤, 戴一阳. 用于蒸汽裂解产物成分预测的集成迁移学习框架[J]. 化工进展, 2024, 43(5): 2880-2889.
[13]	张玉红, 李轩宇, 冯春健, 马春迅, 张晨, 周洋洋, 毕海胜. 油气田非金属管道失效预测及防控技术研究进展[J]. 化工进展, 2024, 43(3): 1118-1132.
[14]	陈森, 殷鹏远, 杨证禄, 莫一鸣, 崔希利, 锁显, 邢华斌. 功能固体材料智能合成研究进展[J]. 化工进展, 2023, 42(7): 3340-3348.
[15]	王硕, 张亚新, 朱博韬. 基于灰色预测模型的水煤浆输送管道冲蚀磨损寿命预测[J]. 化工进展, 2023, 42(7): 3431-3442.