مقاله انگلیسی رایگان در مورد صرفه جویی انرژی قطار با الگوریتم ژنتیک – IEEE 2018

مقاله انگلیسی رایگان در مورد صرفه جویی انرژی قطار با الگوریتم ژنتیک – IEEE 2018

 

مشخصات مقاله
انتشار مقاله سال ۲۰۱۸
تعداد صفحات مقاله انگلیسی ۶ صفحه
هزینه دانلود مقاله انگلیسی رایگان میباشد.
منتشر شده در نشریه IEEE
نوع مقاله ISI
عنوان انگلیسی مقاله Optimization of train energy saving based on golden ratio genetic algorithm
ترجمه عنوان مقاله بهینه سازی صرفه جویی در انرژی قطار بر اساس الگوریتم ژنتیک نسبت طلایی
فرمت مقاله انگلیسی  PDF
رشته های مرتبط مهندسی برق
گرایش های مرتبط مهندسی الکترونیک، مهندسی کنترل، مکاترونیک
مجله کنفرانس سالانه علمی جوانان انجمن چینی از اتوماسیون – Youth Academic Annual Conference of Chinese Association of Automation
دانشگاه Faculty of Information Technology – Beijing University of Technology – China
کلمات کلیدی قطار مترو؛ بهینه سازی صرفه جویی در انرژی؛ الگوریتم ژنتیک؛ بهینه مطلوب؛ نسبت طلایی
کلمات کلیدی انگلیسی Subway train; Energy-saving optimization; Genetic algorithm; Local optimum; Golden ratio
شناسه دیجیتال – doi
https://doi.org/10.1109/YAC.2018.8406493
کد محصول E8517
وضعیت ترجمه مقاله  ترجمه آماده این مقاله موجود نمیباشد. میتوانید از طریق دکمه پایین سفارش دهید.
دانلود رایگان مقاله دانلود رایگان مقاله انگلیسی
سفارش ترجمه این مقاله سفارش ترجمه این مقاله

 

بخشی از متن مقاله:
I. INTRODUCTION

With the rapid development of urban rail transit, huge energy consumption has attracted widespread attention of scholars. The energy consumption accounts for nearly half of the total energy consumption of the subway system. Therefore, the reduction in energy consumption of the subway makes a lot of sense. Domestic and foreign scholars have done a lot of research on the optimization of urban rail transit trains and achieved many results. Generally, research methods are divided into two categories [1]: analytical algorithms and numerical algorithms. The analytical algorithm is based on the factors of trains and lines and solves the problem of train energy saving in the form of mathematical expressions. Howlett [2] used maximum principle to search for the key operating points and then got the optimal solution of the problem. Khmelnitsky [3] used the maximum value principle to optimum the control of train with different road conditions; Liu [4] used the maximum value principle to optimize the train running curve combining the optimal control strategy with the train motion model; In order to minimize energy consumption, Liang[5] made the analysis of the optimal control under different road conditions, taking slopes and speed limits into consideration. In general, it is more likely to get the best results using analytical method, but it requires complex derivation, which appears to be the difficulty of solving the problem. On the other hand, the numerical method is also based on the train and road condition, but it is a method to complete the solution within a specified time in an iterative way. Compared with the analytical method, the numerical method is easier to deal with complex objective functions, so it has attracted the attention of many scholars. Wong [6] applied genetic algorithm to determine the number of coasting point; Jin [7] applied the neural network combined with genetic algorithm to optimize the speed curve of the train. However, the use of neural network for optimization may cause the problem of long training time and slow calculation speed; In 2016, Mohammad [8] established a multi-mass train motion model of the train and compared the optimization performance of the ant colony algorithm and the genetic algorithm. And it turned out to be better when using genetic algorithm to solve the problem of energy-saving of train; Li [9] proposed the principle of handle-level variation of the dichotomy of slopes, and used genetic algorithm to solve the relationship between train handle level and train position; Wang [10] used an adaptive genetic algorithm based on a phaseadapted adaptive strategy to search for the operating point.. However, this method has a good effect at the later stage of evolution, but is not favorable to evolution in the early stage of evolution which is more likely to fall into a local optimum during evolution. For these purposes, this paper aims at finding the optimal solution of energy-saving problem. The main organization of this paper is as follows: the motion model of the train is established and control strategies are analyzed in sectionĊ. The golden ratio genetic algorithm is introduced to solve the problem of optimal controlling of the train in section ċ. The method is verified under actual subway conditions in section Č and conclusions are shown in sectionč.

ثبت دیدگاه