Topology Optimization and Fast Iterative Method for Power Module Heat Sink Based on Neural Network Synchronous Learning
朱高嘉 1何函宇 1李龙女 1朱建国 2梅云辉1
扫码查看
点击上方二维码区域，可以放大扫码查看
作者信息
1. 天津工业大学电气工程学院,天津 300387
2. 悉尼大学电气与信息工程学院,悉尼 2006
折叠
摘要
随着功率模块集成化程度的提高,其散热结构优化已成为研发中的关键.拓扑优化可通过变换散热器形貌、结构来最大化地提升散热效果,因此受到了广泛关注.但在拓扑优化过程中,每步迭代均需要计算模块与散热器温度分布,占用较庞大的计算资源和计算时间.为加速传统散热器拓扑优化进程,在基于传统固体各向同性材料惩罚SIMP(solid isotropic material with penalization)散热器拓扑优化方法的基础上,提出一种嵌套神经网络NN(neural network)同步学习的快速迭代方法.首先,构建散热器基于编码器-解码器结构的NN预测模型,即基于散热器形貌迭代进化过程实现优化结构的快速预测;其次,将NN模型与散热器SIMP拓扑优化流程相嵌套,利用迭代过程中的中间形貌同步训练NN;最后,针对单芯片、两芯片模块结构,对比所提方法与传统迭代方法的拓扑优化结果,验证了所提NN同步学习方法的准确性和快速性.
Abstract
With the improvement of the integration degree of power modules, the optimization of their heat transfer structures has become a focus in the development. The topology optimization(TO) can maximize the cooling performance by transforming the morphology and structure of heat sinks, thus receiving extensive attention. However, in the TO process, the temperature distribution of modules and heat sinks needs to be calculated in each iteration step, consuming a large amount of computing resource and calculation time. To accelerate the TO process of traditional heat sinks, a fast iterative method combining neural network(NN) synchronous learning and the traditional solid isotropic material with penalization (SIMP)-based TO methods is put forward. First, an NN pre-diction model based on the encoder-decoder structure is con-structed, which can iteratively evolve the shape of heat sinks to achieve a fast prediction of optimized structures. Second, the NN model is integrated into the TO process of the heat sink based on the SIMP method, and the NN is trained syn-chronously using the intermediate morphology obtained in the iteration process. Finally, aimed at the single-chip and dual-chip modules, the results obtained by the new method and tra-ditional iterative methods are compared to validate the accura-cy and rapidity of the proposed NN synchronous leaning method.
关键词
散热器结构优化设计/拓扑优化/变密度法/神经网络同步深度学习
Key words
Optimization and design of heat sink structure/topology optimization (TO)/density variation method/neural network synchronous deep learning
维普
万方数据