首页> 外文会议>High performance and optimum design of structures and materials >Performance of surrogate models in reliability-based design optimization
【24h】

Performance of surrogate models in reliability-based design optimization

机译:替代模型在基于可靠性的设计优化中的性能

获取原文
获取原文并翻译 | 示例

摘要

Structural designs are progressively more conditioned by uncertainty in a wide range of fields, and new designs have to meet the requirements of safety and efficiency. Probabilistic optimization is a powerful tool able to improve and optimize initial designs into others which are more efficient. In spite of the continuous growth of computational power, this kind of optimization usually turns out to be unaffordable, due to the computational cost of the methods involved. However, parallel computing and surrogate models can overcome this drawback by reducing drastically the total computational cost of the process. In this paper, a survey of the performance of several surrogate models combined with reliability-based design optimization is presented. Two examples are selected to show the behavior of the methods when applied to different models.
机译:结构设计越来越受到广泛领域不确定性的制约,新设计必须满足安全性和效率的要求。概率优化是一个功能强大的工具,能够将初始设计改进和优化为其他更有效的设计。尽管计算能力在不断增长,但由于所涉及方法的计算成本高昂,因此这种优化通常无法负担。但是,并行计算和代理模型可以通过大大减少该过程的总计算成本来克服此缺点。本文对几种替代模型的性能进行了调查,并结合了基于可靠性的设计优化。选择了两个示例来展示方法应用于不同模型时的行为。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号