Optimum Shape Design of Double-Layer Grids by Particle Swarm Optimization Using Neural Networks
Publish place: 6th National Congress on Civil Engineering
Publish Year: 1390
نوع سند: مقاله کنفرانسی
زبان: English
View: 1,739
This Paper With 7 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
این Paper در بخشهای موضوعی زیر دسته بندی شده است:
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
NCCE06_1123
تاریخ نمایه سازی: 28 مرداد 1390
Abstract:
In this paper, an efficient method is proposed for optimum shape design of double-layer grids. In optimization process, the weight of structure is considered as objective function. The design variables are the number of spans divisions of grid in two directions, the height of between two layers and the cross sectional area of elements. The design constraints are considered as limitations of the stress and slenderness of elements and the displacement requirements of joints. The optimization is carried out by particle swarm algorithm that is suitable for discrete and continuous variables. To reduce the computational time of optimization process, the structural responses are predicted using properly trained radial basis function neural network. This network is a robust network for predicting the structural responses. The numerical results demonstrate the robustness and high performance of the suggested method for the optimum shape design of double-layer grids in.
Keywords:
Authors
S. Gholizadeh
Assistant Prof. of Civil Engineering Department, Urmia University, Urmia, Iran
P. Torkzadeh
Assistant Prof. of Civil Engineering Department, University of Kerman, Kerman, Iran
S. Jabbarzadeh
M.S. Student of Kerman Graduate University of Technology, Kerman, Iran
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :