利用函數鏈結類神經模糊網路增強正交分頻多工系統之通道估測效能

Enhancement of Channel Estimation in OFDM Systems Using Functional Link Neural Fuzzy Network

黄燿宏(Yao-Hung Huang)

指導教授 ： 鄭佳炘

國立虎尾科技大學/電機資訊學院/電機工程研究所/碩士(2014年)

https://doi.org/10.6827/NFU.2014.00185

摘要

本論文針對正交分頻多工(Orthogonal Frequency-Division Multiplexing, OFDM)系統提出利用函數鏈結類神經模糊網路(Functional Link Neural Fuzzy Network, FLNFN) 增強正交分頻多工系統之通道估測效能研究。在無線通訊系統中，訊號傳遞過程中因受環境影響會造成訊號失真與衰減，如：通道延遲(Delay Spread)、快速移動(Mobility)、多路徑效應(Multipath Effect)和都卜勒位移(Doppler Shift)等。為了要減少接收訊號受到的干擾，本文透過通道估測來知道通道的脈衝響應(Channel Impulse Response, CIR)，然後再進行補償。本論文將學習利用傳統的最小平方法(Least Square, LS)、最小均方誤差法(Minimum Mean Square Error, MMSE)、倒傳遞類神經網路(Back Propagation Neural Network, BPNN)和基因演算法結合倒傳遞類神經網路(Genetic Algorithm Based Back Propagation Neural Network, GABPNN)通道估測法並與我們所提通道估測法比較之間的位元錯誤率(Bit Error Rate, BER)。模擬結果可知，我們所提出FLNFN方法可有效的改善系統的效能，且趨近於MMSE演算法的效能。

關鍵字

正交分頻多工 ； 倒傳遞類神經網路 ； 基因演算法結合倒傳遞類神經網路 ； 函數鏈結類神經模糊網路 ； 通道估測

並列摘要

In this thesis, a new application of Functional Link Neural Fuzzy Network (FLNFN) to enhance performance channel estimation in OFDM systems is investigated. In wireless communications, it is necessary to estimate the channel to overcome the impairments caused by fading channels, including delay spread, multipath effect and Doppler shift. To eliminate these, the receiver needs to get the channel impulse response (CIR) of radio channel. In this thesis, we exploit traditional channel estimations, such as Least Square (LS), Minimum Mean Square Error (MMSE). Back Propagation Neural Network (BPNN) and Genetic Algorithm Based Back Propagation Neural Network (GABPNN) algorithms . Finally, FLNFN is also proposed for channel estimation in OFDM systems. Compared to LS, MMSE, BPNN and GABPNN algorithms, simulation results indicate that the proposed schemes can improve the system performance and approach the performance of MMSE algorithm.

並列關鍵字

OFDM ； Back Propagation Neural Network (BPNN) ； Genetic Algorithm Based Back Propagation Neural Network (GABPNN) ； Functional Link Neural Fuzzy Network ； Channel Estimation.

參考文獻

[26] 鄭永沛, “在OFDM系統以基於基因演算法之倒傳遞類神經網路進行通道估測之研究,” 國立虎尾科技大學電機工程研究所碩士論文, 100.06

[1] L. J. Cimini, “Analysis and simulation of digital mobile channel using orthogonal frequency multiplex,” IEEE Trans. Commun., pp. 665-675 vol. 33, July 1985.

[2] V. Mignone and A. Morello, “CD3-OFDM: A novel demodulation schemes for fixed and mobile receivers,” IEEE Trans. Commun., pp. 1144-1151 vol. 44, September 1996.

[4] C. T. Lin and C. S. G. Lee, Neural Fuzzy Systems: a neuro-fuzzy Synergism to intelligent systems, NJ: Prentice Hall PTR, 1996.

[5] J. S. R. Jang, C. T. Sun and E. Mizutani, Neural-fuzzy and soft computing: a computational approach to learning and machine intelligence, NJ: Prentice Hall, 1997.