Scholarlink

<p>With the growing demand for efficient thermal management in electric motors, spiral water jackets have become widely used to enhance cooling performance. However, achieving a balance between effective cooling, uniform temperature distribution, and energy-efficient pump power remains a significant challenge. This study proposes a multi-objective optimization design for spiral liquid jackets, aiming to improve cooling efficiency, temperature uniformity, and minimize pump power consumption. The optimization process considers geometric parameters and boundary conditions as design variables. A radial basis function surrogate model, developed using the Latin hypercube sampling method, is employed to filter geometric constraints and create a database for training and testing. The model’s accuracy is enhanced through <i>k-fold</i> cross-validation. Non-dominated Sorting Genetic Algorithm-II (NSGA-II) is used to search for the Pareto front, providing a set of optimal trade-offs. Two selection strategies are applied: one based on multi-criteria decision-making and another tailored to system design requirements. Results show that the optimized designs reduce the maximum temperature by at least 5.49%, the static pressure by at least 24.72%, and increase temperature uniformity by up to 1.27%, demonstrating improved cooling performance and reduced pump power consumption. The proposed optimization procedure effectively addresses the challenges in spiral water jacket design, providing a more efficient and reliable solution for electric motor cooling.</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

Multi-objective optimization procedure for electric motor water jacket based on surrogate model

  • 期刊论文

  • 发表日期：

    2026年1月4日

查看全文
  • Rui Li,
  • Shu Yang,
  • Chang Qi,
  • Dong-Ming Guo

摘要

With the growing demand for efficient thermal management in electric motors, spiral water jackets have become widely used to enhance cooling performance. However, achieving a balance between effective cooling, uniform temperature distribution, and energy-efficient pump power remains a significant challenge. This study proposes a multi-objective optimization design for spiral liquid jackets, aiming to improve cooling efficiency, temperature uniformity, and minimize pump power consumption. The optimization process considers geometric parameters and boundary conditions as design variables. A radial basis function surrogate model, developed using the Latin hypercube sampling method, is employed to filter geometric constraints and create a database for training and testing. The model’s accuracy is enhanced through k-fold cross-validation. Non-dominated Sorting Genetic Algorithm-II (NSGA-II) is used to search for the Pareto front, providing a set of optimal trade-offs. Two selection strategies are applied: one based on multi-criteria decision-making and another tailored to system design requirements. Results show that the optimized designs reduce the maximum temperature by at least 5.49%, the static pressure by at least 24.72%, and increase temperature uniformity by up to 1.27%, demonstrating improved cooling performance and reduced pump power consumption. The proposed optimization procedure effectively addresses the challenges in spiral water jacket design, providing a more efficient and reliable solution for electric motor cooling.