Data-driven approach for design and optimization of rotor-stator mixers for miscible fluids with different viscosities

被引:3
作者
Shirzadi, Mohammadreza [1 ]
Sugimoto, Takumi [2 ]
Munekata, Yuki [2 ]
Morikawa, Toshiyuki [2 ]
Fujita, Hiroya [2 ]
Komoda, Yoshiyuki [3 ]
Fukasawa, Tomonori [1 ]
Fukui, Kunihiro [1 ]
Ishigami, Toru [1 ]
机构
[1] Hiroshima Univ, Grad Sch Adv Sci & Engn, Chem Engn Program, 1-4-1 Kagamiyama, Hiroshima, Japan
[2] NOF Corp, Yebisu Graden Pl Tower,20-3 Ebisu 4 chome,Shibuya, Tokyo 1506012, Japan
[3] Kobe Univ, Grad Sch Engn, Dept Chem Sci & Engn, 1-1 Rokkodai,Nada Ku, Kobe, Hyogo 6578501, Japan
基金
日本学术振兴会;
关键词
Rotor-stator mixer; Machine learning; Optimization; Computational fluid dynamics; Miscible fluid; Viscosity ratio; RESPONSE-SURFACE METHODOLOGY; ENERGY-DISSIPATION; FLOW PATTERN; MIXING INTENSIFICATION; POWER CHARACTERISTICS; VISCOUS FLUIDS; STIRRED-TANK; SIMULATION; DISPERSION; AGITATION;
D O I
10.1016/j.cej.2024.155954
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Rotor-stator mixers (RSMs) are essential equipment used in the food, pharmaceutical, and cosmetic industries. The performance of RSMs is conventionally analyzed using three approaches based on empirical correlations and experimental and numerical analyses. This paper introduces a new approach based on a multifidelity data-driven framework for designing and optimizing RSMs that systematically combines elements of experimental and highresolution computational fluid dynamics (CFD) models to train a machine learning model to predict RSM performance. It was subsequently coupled to an optimization solver based on a genetic algorithm. The developed framework was applied to a small-scale RSM with variable rotor blade radius, rotor speed, stator mesh width, and mass flow rate that is operated to mix two miscible fluids with different viscosities. The RSM was optimized at two regimes of low and high viscosities to achieve the best performance in terms of shaft power and mixing indices. The results demonstrate the successful application of the developed frameworks. The optimization of the mixing of high-viscosity fluids yielded a higher improvement than that for low-viscosity fluids. A decrease in shaft power of approximately 50% was obtained for the high-viscosity fluids, whereas the mixing indices increased up to 20% by the optimization of the geometrical input design parameters. The proposed framework can be advantageous for designers and operators at the industrial scale.
引用
收藏
页数:17
相关论文
共 50 条
[41]   A Data-driven Approach for Sustainable Building Retrofit-A Case Study of Different Climate Zones in China [J].
He, Qiong ;
Ng, S. Thomas ;
Hossain, Md Uzzal ;
Augenbroe, Godfried L. .
SUSTAINABILITY, 2020, 12 (11)
[42]   Stalking the Materials Genome: A Data-Driven Approach to the Virtual Design of Nanostructured Polymers [J].
Breneman, Curt M. ;
Brinson, L. Catherine ;
Schadler, Linda S. ;
Natarajan, Bharath ;
Krein, Michael ;
Wu, Ke ;
Morkowchuk, Lisa ;
Li, Yang ;
Deng, Hua ;
Xu, Hongyi .
ADVANCED FUNCTIONAL MATERIALS, 2013, 23 (46) :5746-5752
[43]   Predicting bioretention pollutant removal efficiency with design features: A data-driven approach [J].
Wang, Runzi ;
Zhang, Xuewen ;
Li, Ming-Han .
JOURNAL OF ENVIRONMENTAL MANAGEMENT, 2019, 242 :403-414
[44]   A quantitative approach to design alternative evaluation based on data-driven performance prediction [J].
Zhang, Zi-jian ;
Gong, Lin ;
Jin, Yan ;
Xie, Jian ;
Hao, Jia .
ADVANCED ENGINEERING INFORMATICS, 2017, 32 :52-65
[45]   A data-driven design parameter recommendation approach based on personalized requirements for product conceptual design [J].
Cui, Haoran ;
Gong, Lin ;
Yan, Yan .
COMPUTERS & INDUSTRIAL ENGINEERING, 2025, 201
[46]   Heat transfer optimization for MH reactor using combined taguchi design and data-driven optimization method [J].
Bai, Xiao-Shuai ;
Su, Ju-Wen ;
Liu, Zhao ;
Qu, Zhi-Guo ;
Yang, Wei-Wei .
ENERGY, 2024, 307
[47]   Shear design of recycled aggregate concrete beams using a data-driven optimization method [J].
Dong, Shuxiong ;
Xie, Weili ;
Wei, Muwang ;
Liu, Kaihua .
STRUCTURES, 2023, 55 :123-137
[48]   Data-driven layout design for smart remanufacturing: a flexible optimization model and a case study [J].
Afari, J. A. ;
Gosavi, A. ;
Hu, J. ;
Marley, R. J. .
INTERNATIONAL JOURNAL OF INTERACTIVE DESIGN AND MANUFACTURING - IJIDEM, 2025,
[49]   Machine learning-based data-driven robust optimization approach under uncertainty [J].
Zhang, Chenhan ;
Wang, Zhenlei ;
Wang, Xin .
JOURNAL OF PROCESS CONTROL, 2022, 115 :1-11
[50]   Digital design and optimization of the integrated synthesis and crystallization process using data-driven approaches [J].
Ma, Yiming ;
Li, Wei ;
Liu, Jiaxu ;
Shang, Gao ;
Yang, Huaiyu ;
Gong, Junbo ;
Nagy, Zoltan K. ;
Benyahia, Brahim .
AICHE JOURNAL, 2025,