Views
12
Downloands
1
Yapay zekâ algoritmalarıyla son yıllarda birçok bilim dalında başarılı uygulamalar geliştirilmektedir. Deneysel veya benzetim programlarından elde edilen veriler söz konusu algoritmalarla işlenmektedir. Tasarlanan algoritma mimarileri ile veriler işlenerek tahmin ve sınıflandırma çalışmaları yapılmaktadır. Bu algoritmalardan, amaca ve veri kümesine uygun olan algoritmanın seçilmesi büyük önem taşımaktadır. Bu kapsamda, fizik alanındaki yenilikçi çalışmalarda yapay sinir ağı algoritması kullanmak yüksek performans değerleri elde etmeyi sağlamaktadır. Biyolojik nöronlardan esinlenen yapay sinir ağı (YSA), öğrenme yeteneğine sahip paralel hesaplama sistemidir. Bu çalışmada, üç katmanlı yapay sinir ağı kullanılarak beş elemanlı elektrostatik silindir lenslerin paralel demet modu belirlenmektedir. Çalışmada kullanılan veri kümesi, yüksek doğrulukta hesaplama yapabilen CPO(Yüklü Parçacık Optiği) programı yardımıyla elde edilmiştir. Verilerin analizi Matlab R2012b programı kullanılarak gerçekleştirilmiştir. Elde edilen sonuçlara göre, yapay sinir ağının fizik alanında paralel demet modunu belirlemede yüksek performans değerlerine sahip olan ve elektrostatik problem çözümlerinde sonlu fark ve sınır eleman metoduna alternatif bir metot olduğu ortaya konulmuştur. Oluşturulan YSA algoritması, test verilerinin %85,7’sini doğru olarak sınıflandırmıştır.
Artificial intelligence algorithms have been developing successful applications in many fields of science in recent years. Data obtained from experimental or comparative programs is processed by the algorithms concerned. Designed algorithm architectures and data processing are predicting and classification work. From these algorithms, the choice of the algorithm that fits the purpose and data set is of great importance. In this context, the use of artificial nerve network algorithm in innovative studies in the field of physics ensures the achievement of high performance values. An artificial neuron network (YSA) is a parallel calculation system that has the ability to learn. In this study, the parallel set mode of the five-elements electrostatic cylindrical lenses is determined using the three-layer artificial nerve network. The data set used in the study was obtained with the help of the CPO (Called Particle Optics) program that can calculate with high accuracy. The analysis of the data was carried out using the Matlab R2012b program. According to the results obtained, the artificial nerve network has high performance values in determining the parallel set mode in the field of physics and is found to be an alternative method to the final difference and the limit element method in the electrostatic problem solutions. The YSA algorithm correctly classified 85.7% of the test data.
Successful applications have been developed in many disciplines with artificial algorithms in recent years. The data obtained from experimental or simulation programs have been processed with the corresponding algorithms. Prediction and classification studies are carried out by processing the data with the designed algorithm architectures. From these algorithms, it is of great importance to select the algorithm that is appropriate for the purpose and data set. In this context, using artificial neural network algorithms in innovative studies in the field of physics ensures high performance values. Artificial neural network (ANN), inspired by biological neurons, is parallel computing system having learning ability. In this study, the parallel beam mode of the five-element electrostatic cylindrical lenses is determined using a three layer artificial neural network. The data set used in the study was obtained with the aid of the CPO (Charged Particle Optics) program enabling highly accurate calculation. Analysis of the data was performed using Matlab R2012b program. According to the obtained results, it has been revealed that the artificial neural network has high performance values in determining the parallel beam mode in the field of physics and it is an alternative method to the finite difference and boundary element method in electrostatic problem solutions. The generated YSA algorithm correctly classifies 85.7% of the test data.
Field : Mimarlık, Planlama ve Tasarım; Mühendislik
Journal Type : Uluslararası
Article Detail 
Similar Articles
Download PDF
Journal Information
Listen Paper
Cite
Print This Page
Share
Mendeley
