• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Proceedings of the 2009 spring technical conference of the ASME Internal Combustion Engine Division >ASSESSMENT OF MULTI-OBJECTIVE GENETIC ALGORITHMS WITH DIFFERENT NICHING STRATEGIES AND REGRESSION METHODS FOR ENGINE OPTIMIZATION AND DESIGN
【24h】

ASSESSMENT OF MULTI-OBJECTIVE GENETIC ALGORITHMS WITH DIFFERENT NICHING STRATEGIES AND REGRESSION METHODS FOR ENGINE OPTIMIZATION AND DESIGN

机译：优化设计的多目标遗传算法和递归方法的多目标遗传算法评估

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In previous study [1] the Non-dominated Sorting Genetic Algorithm II (NSGA II) [2] performed better than other popular Multi-Objective Genetic Algorithms (MOGA) in engine optimization that sought optimal combinations of the piston bowl geometry, spray targeting, and swirl ratio. NSGA II is further studied in this paper using different niching strategies that are applied to the objective- space and design-space, which diversify the optimal objectives and design parameters accordingly. Convergence and diversity metrics are defined to assess the performance of NSGA II using different niching strategies. It was found that use of the design niching achieved more diversified results with respect to design parameters, as expected.rnRegression was then conducted on the design datasets that were obtained from the optimizations with two niching strategies. Four regression methods, including K-nearest neighbors (KN), Kriging (KR), Neural Networks (NN), and Radial Basis Functions (RBF), were compared. The results showed that the dataset obtained from optimization with objective niching provided a more fitted learning space for the regression methods. The KN, KR, outperformed the other two methods with respect to the prediction accuracy. Furthermore, a log transformation to the objective-space improved the prediction accuracy for the KN, KR, and NN methods but not the RBF method.rnThe results indicate that it is appropriate to use a regression tool to partly replace the actual CFD evaluation tool in engine optimization designs using the genetic algorithm. This hybrid mode saves computational resources (processors) without losing optimal accuracy. A Design of Experiment (DoE) method (the Optimal Latin Hypercube method) was also used to generate a dataset for the regression processes. However, the predicted results were much less reliable than results that were learned using the dynamically increasing datasets from the NSGA II generations. Applying the dynamical learning strategy duringrnthe optimization processes allows computationally expensive CFD evaluations to be partly replaced by evaluations using the regression techniques. The present study demonstrates the feasibility of applying the hybrid mode to engine optimization problems, and the conclusions can also extend to other optimization studies (numerical or experimental) that feature time-consuming evaluations and have highly non-linear objective-spaces.
机译：在先前的研究中[1]，非主导排序遗传算法II（NSGA II）[2]在引擎优化方面的表现优于其他流行的多目标遗传算法（MOGA），后者寻求活塞碗几何形状，喷雾目标，和涡流比。本文对NSGA II进行了进一步的研究，使用了适用于目标空间和设计空间的不同小生境策略，这些策略相应地优化了最佳目标和设计参数。定义了收敛和多样性指标，以使用不同的固定策略来评估NSGA II的性能。结果发现，如预期的那样，使用设计位准可以在设计参数方面实现更加多样化的结果。然后对通过两种位准策略从优化中获得的设计数据集进行了回归。比较了四种回归方法，包括K最近邻（KN），Kriging（KR），神经网络（NN）和径向基函数（RBF）。结果表明，通过客观定位优化获得的数据集为回归方法提供了更合适的学习空间。就预测精度而言，KN，KR优于其他两种方法。此外，对目标空间的对数转换提高了KN，KR和NN方法的预测精度，但没有改善RBF方法。rn结果表明，使用回归工具部分替代实际的CFD评估工具是适当的。使用遗传算法的发动机优化设计。这种混合模式可节省计算资源（处理器），而不会损失最佳精度。实验设计（DoE）方法（最优拉丁超立方体方法）也用于生成回归过程的数据集。但是，预测结果的可靠性远低于使用NSGA II代动态增加的数据集获得的结果。在优化过程中应用动态学习策略可以使计算量大的CFD评估部分被使用回归技术的评估所替代。本研究证明了将混合模式应用于发动机优化问题的可行性，其结论还可以扩展至其他具有耗时评估且具有高度非线性目标空间的优化研究（数值或实验）。

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