Scholarlink

<p>To address the thermal management challenges in heterogeneous integrated chip design, this study proposed an intelligent thermal resistance prediction model that integrated physical mechanisms with a backpropagation (BP) neural network. Unlike traditional black-box data-driven approaches, the proposed method was grounded in fundamental heat transfer principles and systematically constructed a physics-informed feature set encompassing geometric configurations, material properties, power distribution, and boundary conditions. Domain knowledge was explicitly encoded into the neural network architecture by introducing a physics-constrained layer with weight sign constraints and an attention-based feature interaction layer. Within a multi-task learning framework, the model simultaneously optimized the prediction of total thermal resistance, maximum temperature, and temperature non-uniformity. Experimental results demonstrated that the proposed model significantly outperformed baseline methods on the test set. Specifically, the coefficient of determination (R<sup>2</sup>) for total thermal resistance prediction reached 0.982, with a mean squared error of 0.021&#xa0;K<sup>2</sup>/W<sup>2</sup> and a mean absolute error of 0.103&#xa0;K/W. For maximum temperature prediction, the R<sup>2</sup> value reached 0.969. Compared with a single-task model that predicted only total thermal resistance, the multi-task architecture improved the primary task performance by 0.004. This study provided a fast, accurate, and physically interpretable intelligent tool for chip thermal design, and offered a valuable practical example of physics-informed machine learning applied to complex engineering problems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A thermal resistance prediction model for heterogeneous integrated chips incorporating an AI-based BP neural network

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月18日

查看全文
  • Ying Li,
  • Shujun Xu,
  • Longjian Guo

摘要

To address the thermal management challenges in heterogeneous integrated chip design, this study proposed an intelligent thermal resistance prediction model that integrated physical mechanisms with a backpropagation (BP) neural network. Unlike traditional black-box data-driven approaches, the proposed method was grounded in fundamental heat transfer principles and systematically constructed a physics-informed feature set encompassing geometric configurations, material properties, power distribution, and boundary conditions. Domain knowledge was explicitly encoded into the neural network architecture by introducing a physics-constrained layer with weight sign constraints and an attention-based feature interaction layer. Within a multi-task learning framework, the model simultaneously optimized the prediction of total thermal resistance, maximum temperature, and temperature non-uniformity. Experimental results demonstrated that the proposed model significantly outperformed baseline methods on the test set. Specifically, the coefficient of determination (R2) for total thermal resistance prediction reached 0.982, with a mean squared error of 0.021 K2/W2 and a mean absolute error of 0.103 K/W. For maximum temperature prediction, the R2 value reached 0.969. Compared with a single-task model that predicted only total thermal resistance, the multi-task architecture improved the primary task performance by 0.004. This study provided a fast, accurate, and physically interpretable intelligent tool for chip thermal design, and offered a valuable practical example of physics-informed machine learning applied to complex engineering problems.