检索结果-内蒙古大学图书馆

Machine learning and genetic algorithm as tools for single and multi-objective shape optimization of micromixers with Cantor fractal structure

引用

BRAZILIAN JOURNAL OF CHEMICAL ENGINEERING 2024年第4期41卷 1327-1344页

作者： Cao, Jingzhi Chen, Xueye Ludong Univ Sch Chem & Mat Sci 186 Middle Hongqi Rd Yantai 264025 Shandong Peoples R China Ludong Univ Coll Transportat Yantai 264025 Shandong Peoples R China

shape optimization of micromixers with Cantor fractal structures on the top and bottom walls has been conducted using a combination of three-dimensional Navier-Stokes analysis, Machine Learning (ML), and multi-objective genetic algorithm (MOGA) for both single and multi-objective optimization objectives. Numerical analysis has been systematically conducted employing two distinct working fluids, namely water and ethanol, while operating at a Reynolds number (Re) of unity (Re = 1). The optimization endeavor has been executed by manipulating two design variables that pertain to dimensionless geometric parameters. The single-objective optimization is centered on the selection of mixing effectiveness as the primary objective function, whereas the multi-objective optimization entails the consideration of two objective functions, specifically, the pressure drop and the mixing index at the exit. The Latin hypercube sampling (LHS) method is employed as an experimental design technique to systematically explore the parameter space within the design domain. It is utilized for the purpose of strategically selecting design points within this domain. Additionally, surrogate models for the objective functions are established through the application of ML. In the context of single-objective optimization, the Sequential Linear Programming (SLP) method is employed to iteratively derive the optimal objective function. Meanwhile, for multi-objective optimization, the Genetic Algorithm (GA) is applied to delineate the Pareto optimal frontier (POF) of the micromixer. Subsequently, K-means clustering is utilized as a technique for the purpose of classifying the optimized outcomes, followed by the selection of representative points within the solution space. In the context of single-objective optimization, it is observed that the micromixer featuring a Cantor fractal structure exhibits a noteworthy enhancement in mixing efficiency, surpassing that of the reference design (RD) by a substant

关键词： multi-objective genetic algorithm Machine learning Pareto optimal front single and multi-objective shape optimization Cantor fractal structure

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：