Neural network based beamforming for linear and cylindrical array applications

---

Tezin Türü: Yüksek Lisans

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, Türkiye

Tezin Onay Tarihi: 2009

Öğrenci: MURAT GÜREKEN

Danışman: MEVLÜDE GÜLBİN DURAL ÜNVER

Özet:

In this thesis, a Neural Network (NN) based beamforming algorithm is proposed for real time target tracking problem. The algorithm is performed for two applications, linear and cylindrical arrays. The linear array application is implemented with equispaced omnidirectional sources. The influence of the number of antenna elements and the angular seperation between the incoming signals on the performance of the beamformer in the linear array beamformer is studied, and it is observed that the algorithm improves its performance by increasing both two parameters in linear array beamformer. The cylindrical array application is implemented with twelve microstrip patch antenna (MPA) elements. The angular range of interest is divided into twelve sectors. Since three MPA elements are used to form the beam in each sector, the input size of the neural network (NN) is reduced in cylindrical array. According to the reduced size of NN, the training time of the beamformer is decreased. The reduced size of the NN has no degradation in forming the beams to the desired directions. The angular separation between the targets is an important parameter in cylindrical array beamformer.