Machine learning based surrogate models for microchannel heat sink optimization

被引:46
作者
Sikirica, Ante
Grbcic, Luka
Kranjcevic, Lado [1 ]
机构
[1] Univ Rijeka, Fac Engn, Vukovarska 58, Rijeka 51000, Croatia
关键词
Microchannel heat sink; Machine learning; Multi-objective optimization; Computational fluid dynamics; TRANSFER ENHANCEMENT; FLUID-FLOW; MULTIOBJECTIVE OPTIMIZATION; TRANSFER AUGMENTATION; TRANSFER PERFORMANCE; THERMAL PERFORMANCE; WAVY CHANNEL; PARAMETERS; DESIGN; CAVITIES;
D O I
10.1016/j.applthermaleng.2022.119917
中图分类号
O414.1 [热力学];
学科分类号
摘要
Microchannel heat sinks are an efficient cooling method for semiconductor packages. However, to properly cool increasingly complex and thermally dense circuits, microchannel designs should be improved and expanded on. In this paper, microchannel designs with secondary channels and with ribs are investigated using computational fluid dynamics and are coupled with a multi-objective optimization algorithm to determine and propose optimal solutions based on observed thermal resistance and pumping power. A workflow that combines Latin hypercube sampling, machine learning-based surrogate modeling and multi-objective optimization is proposed. Random forests, gradient boosting algorithms and neural networks were considered during the search for the best surrogate. We demonstrated that tuned neural networks can make accurate predictions and be used to create an acceptable surrogate model. Optimized solutions show a negligible difference in overall performance when compared to the conventional optimization approach. Additionally, solutions are calculated in one-fifth of the original time. Generated designs attain temperatures that are lower by more than 10% under the same pressure limits as a convectional microchannel design. When limited by temperature, pressure drops are reduced by more than 25%. Finally, the influence of each design variable on the thermal resistance and pumping power was investigated by employing the SHapley Additive exPlanations technique. Overall, we have demonstrated that the proposed framework has merit and can be used as a viable methodology in microchannel heat sink design optimization.
引用
收藏
页数:18
相关论文
共 65 条
[1]  
A. Inc, 2020, ANSYS FLUENT 20 US M
[2]  
Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
[3]   Computational heat transfer analysis and combined ANN-GA optimization of hollow cylindrical pin fin on a vertical base plate [J].
Balachandar, C. ;
Arunkumar, S. ;
Venkatesan, M. .
SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES, 2015, 40 (06) :1845-1863
[4]   Investigation of double-layered wavy microchannel heatsinks utilizing porous ribs with artificial neural networks [J].
Bayer, Ozgur ;
Oskouei, Seyedmohsen Baghaei ;
Aradag, Selin .
INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER, 2022, 134
[5]   Numerical investigation of the effects of geometric structure of microchannel heat sink on flow characteristics and heat transfer performance [J].
Bayrak, Ergin ;
Olcay, Ali Bahadir ;
Serincan, Mustafa Fazil .
INTERNATIONAL JOURNAL OF THERMAL SCIENCES, 2019, 135 :589-600
[6]   jMetalPy: A Python']Python framework for multi-objective optimization with metaheuristics [J].
Benitez-Hidalgo, Antonio ;
Nebro, Antonio J. ;
Garcia-Nieto, Jose ;
Oregi, Izaskun ;
Del Ser, Javier .
SWARM AND EVOLUTIONARY COMPUTATION, 2019, 51
[7]   Fluid flow and heat transfer in microchannel heat sink based on porous fin design concept [J].
Chuan, Leng ;
Wang, Xiao-Dong ;
Wang, Tian-Hu ;
Yan, Wei-Mon .
INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER, 2015, 65 :52-57
[8]  
Druzeta S., 2020, Indago-Python module for numerical optimization
[9]   Fluid flow and heat transfer in microchannel heat sinks: Modelling review and recent progress [J].
Gao, Jie ;
Hu, Zhuohuan ;
Yang, Qiguo ;
Liang, Xing ;
Wu, Hongwei .
THERMAL SCIENCE AND ENGINEERING PROGRESS, 2022, 29
[10]   Heat transfer enhancement in microchannel heat sink using hybrid technique of ribs and secondary channels [J].
Ghani, Ihsan Ali ;
Sidik, Nor Azwadi Che ;
Mamat, Rizal ;
Najafi, G. ;
Ken, Tan Lit ;
Asako, Yutaka ;
Japar, Wan Mohd Arif Aziz .
INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER, 2017, 114 :640-655