首页> 外文会议>INCOSE 2009 symposium: East meets west: the human dimension to systems engineering >Applying Machine Learning Methods to the AirframeStructural Design Cost Estimation – A Case Study ofWing-Box Project
【24h】

Applying Machine Learning Methods to the AirframeStructural Design Cost Estimation – A Case Study ofWing-Box Project

机译:机器学习方法在机身结构设计成本估算中的应用-以机翼盒项目为例

获取原文
获取原文并翻译 | 示例

摘要

This research used two machine leaning methods, the Support Vector Regression (SVR) andrnBack-Propagation Neural Network (BPN), to create the cost prediction models for airplanernwing-box structural design, and verified the feasibility and efficiency for both methods. In the casernstudy, four different main structural part groups of the wing-box, Spars/Ribs/Skins/Stringers, werernchosen. In the parts data base, the part dimensions were included and used for classifying the partrngroups. Each part group has 150 bill of parts, 100 bill of parts used for training samples, 50 bill ofrnparts used for predicting samples, to test there accuracy. After verified through wing-box casernstudy, the results showed either SVR or BPN can precisely predicting the design costs. Butrncompare to the BPN, SVR can get the global optimal solution while using less decision parameters.rnThis can save lots of time for searching the best parameters combination when creating thernprediction model.
机译:这项研究使用了两种机器学习方法,即支持向量回归(SVR)和反向传播神经网络(BPN),来创建飞机机翼盒结构设计的成本预测模型,并验证了这两种方法的可行性和效率。在案例研究中,选择了翼盒的四个不同的主要结构零件组,即Spars / Ribs / Skins / Stringers。在零件数据库中,零件尺寸已包括在内,并用于对零件组进行分类。每个零件组有150个零件清单,100个零件清单用于训练样本,50个零件清单用于预测样本,以测试那里的准确性。经过机翼盒案例研究验证,结果表明SVR或BPN都能准确预测设计成本。与BPN相比,SVR可以在使用较少决策参数的情况下获得全局最优解。这可以在创建预测模型时节省大量时间来搜索最佳参数组合。

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