استفاده از الگوریتم های تکاملی برای طرح بندی بهینه از ارتباط Truss-Z در یک محیط با موانع
|کد مقاله||سال انتشار||تعداد صفحات مقاله انگلیسی||ترجمه فارسی|
|78903||2013||17 صفحه PDF||سفارش دهید|
نسخه انگلیسی مقاله همین الان قابل دانلود است.
هزینه ترجمه مقاله بر اساس تعداد کلمات مقاله انگلیسی محاسبه می شود.
این مقاله تقریباً شامل 6274 کلمه می باشد.
هزینه ترجمه مقاله توسط مترجمان با تجربه، طبق جدول زیر محاسبه می شود:
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Advances in Engineering Software, Volume 65, November 2013, Pages 43–59
Truss-Z (TZ) is a concept of a modular system for creating free-form links and ramp networks. It is intended as a universal transportation system for cyclists and pedestrians, especially ones with strollers or carts, and in particular – by persons on wheelchairs, the elders, etc. In other words, TZ is for people who have difficulties using regular stairs or escalators. With only two types of modules, TZ can be designed for nearly any situation and therefore is particularity suited for retrofitting to improve the mobility, comfort and safety of the users. This paper presents an application of evolution strategy (ES) and genetic algorithm (GA) for optimization of the planar layout of a TZ linkage connecting two terminals in a given environment. The elements of the environment, called obstacles, constrain the possible locations of the TZ modules. Criteria of this multi-objective optimization are: the number of modules to be the smallest, which can be regarded as quantitative economical optimization, and the condition that none of the modules collides with any other objects, which can be regarded as qualitative satisfaction of the geometrical constraints. Since TZ is modular, the optimization of its layout is discrete and therefore has combinatorial characteristic. Encoding of a planar TZ path, selection method, objective (cost) function and genetic operations are introduced. A number of trials have been performed; the results generated by ES and GA are compared and evaluated against backtracking-based algorithm and random search. The convergence of solutions is discussed and interpreted. A visualization of a realistic implementation of the best solution is presented. Further evaluation of the method on three other representative layouts is presented and the results are briefly discussed.