本文選題：功率放大器 + 數(shù)字預(yù)失真�。� 參考：《北京交通大學(xué)》2017年碩士論文

【摘要】：隨著通信行業(yè)的不斷發(fā)展,衛(wèi)星通信的重要性日益明顯,可靠性是其最顯著的特點(diǎn)。衛(wèi)星通信系統(tǒng)中的功率放大器對(duì)信號(hào)質(zhì)量有很大的影響,當(dāng)輸入信號(hào)功率過(guò)大時(shí),會(huì)產(chǎn)生非線性失真,不僅效率低下還會(huì)影響相鄰頻域,因此功放的線性化技術(shù)勢(shì)在必行。本文著重介紹了數(shù)字預(yù)失真技術(shù)對(duì)改善功放非線性失真的重要性,并對(duì)預(yù)失真模型進(jìn)行了深入的研究。本文的主要工作與創(chuàng)新點(diǎn)如下:(1)以自適應(yīng)理論為基礎(chǔ),建立Volterra級(jí)數(shù)預(yù)失真系統(tǒng),使用最小均方算法進(jìn)行參數(shù)提取,信號(hào)經(jīng)過(guò)預(yù)失真后的鄰道干擾有12dB左右的改善。建立記憶多項(xiàng)式預(yù)失真系統(tǒng),使用遞歸最小二乘算法進(jìn)行參數(shù)提取,信號(hào)經(jīng)過(guò)預(yù)失真后的鄰道干擾改善約14dB。(2)重點(diǎn)研究了人工神經(jīng)網(wǎng)絡(luò)類(lèi)的BP神經(jīng)網(wǎng)絡(luò)和RBF神經(jīng)網(wǎng)絡(luò)。建立RBF神經(jīng)網(wǎng)絡(luò)的信號(hào)預(yù)測(cè)模型,使用K-means聚類(lèi)的方法得到徑向基中心,并利用LMS算法進(jìn)行權(quán)值的更新,實(shí)驗(yàn)證明在對(duì)功放建模時(shí),使用RBF神經(jīng)網(wǎng)絡(luò)比Volterra級(jí)數(shù)和記憶多項(xiàng)式具有更高的精確度。通過(guò)分析復(fù)數(shù)域函數(shù)的特性,闡述了神經(jīng)網(wǎng)絡(luò)中激勵(lì)函數(shù)的局限性,提出了基于BP神經(jīng)網(wǎng)絡(luò)的DUAF結(jié)構(gòu)并建立預(yù)失真系統(tǒng)。仿真結(jié)果表明,信號(hào)經(jīng)過(guò)預(yù)失真后的鄰道干擾改善約7dB,其預(yù)失真效果驗(yàn)證了 DUAF結(jié)構(gòu)處理復(fù)數(shù)的局限性。(3)重點(diǎn)研究復(fù)數(shù)域的神經(jīng)網(wǎng)絡(luò)模型。建立全連接遞歸神經(jīng)網(wǎng)絡(luò)(FCRNN)預(yù)失真系統(tǒng),使用RTRL算法進(jìn)行參數(shù)提取。仿真結(jié)果表明,在處理復(fù)數(shù)信號(hào)時(shí),FCRNN相比于DUAF結(jié)構(gòu)具有更高的精確度。(4)提出了改進(jìn)的短時(shí)記憶遞歸神經(jīng)網(wǎng)絡(luò)(STMRNN)。FCRNN模型的神經(jīng)元反饋信號(hào)采用全連接的方式,其模型復(fù)雜度較大,而STMRNN模型將FCRNN模型中的輸出層反饋信號(hào)改用短時(shí)記憶的方式,在保證精確度的同時(shí)能減少模型復(fù)雜度。(5)提出了改進(jìn)的全反饋短時(shí)記憶遞歸神經(jīng)網(wǎng)絡(luò)(AFSMRNN)。AFSMRNN模型將STMRNN模型中的隱含層反饋信號(hào)改用短時(shí)記憶的方式,進(jìn)一步地降低了模型復(fù)雜度,并且能達(dá)到與記憶多項(xiàng)式相同的精確度。
[Abstract]:With the development of communication industry, the importance of satellite communication is becoming more and more obvious. The power amplifier in the satellite communication system has a great influence on the signal quality. When the input signal power is too large, it will produce nonlinear distortion, which will not only affect the efficiency but also affect the adjacent frequency domain, so the linearization technology of power amplifier is imperative. In this paper, the importance of digital predistortion technology in improving nonlinear distortion of power amplifier is introduced, and the predistortion model is deeply studied. The main work and innovation of this paper are as follows: (1) based on the adaptive theory, the Volterra series predistortion system is established, and the parameters are extracted by using the least mean square algorithm. After the signal is predistorted, the adjacent channel interference is improved by 12dB or so. A memory polynomial predistortion system is established and the parameters are extracted by using the recursive least square algorithm. The BP neural network and the RBF neural network of the artificial neural network are studied emphatically after the signal is improved by the adjacent channel interference (about 14 dB.m-2) after the signal is predistorted. The signal prediction model of RBF neural network is established, the radial basis function center is obtained by K-means clustering method, and the weight is updated by using LMS algorithm. Using RBF neural network is more accurate than Volterra series and memory polynomial. By analyzing the characteristics of complex function, the limitation of excitation function in neural network is expounded, and the DUAF structure based on BP neural network is proposed and the predistortion system is established. The simulation results show that the signal is improved by about 7db after predistortion, and its predistortion effect verifies the limitation of DUAF structure in complex number processing. (3) the neural network model in complex domain is mainly studied. A fully connected recurrent neural network (RNN) predistortion system is established and the parameters are extracted by RTRL algorithm. The simulation results show that FCRNN has a higher accuracy than DUAF structure in processing complex signals.) an improved STMRNNN-. FCRNN model is proposed. The neural feedback signal of STMRNNU. FCRNN model is fully connected, and the complexity of the model is high. The STMRNN model changes the output layer feedback signal in the FCRNN model to short-term memory. This paper presents an improved full feedback short time memory recurrent neural network (AFSMRNN + AFS MRNN), which converts the hidden layer feedback signals in the STMRNN model to short time memory, and further reduces the complexity of the model. And can achieve the same accuracy as memory polynomial.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TN722.75;TN927.2

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 谷林海;葛利嘉;;功放數(shù)字預(yù)失真技術(shù)現(xiàn)狀及未來(lái)發(fā)展[J];通信技術(shù);2015年11期

2 劉佳;;塔頂放大器三階截取點(diǎn)和1dB壓縮點(diǎn)間關(guān)系分析[J];數(shù)字通信世界;2012年05期

3 趙東明;唐康淞;李實(shí);夏克文;;抑制空間行波管三階交調(diào)失真的信號(hào)注入技術(shù)[J];真空電子技術(shù);2010年03期

4 李軍,劉君華;一種新型廣義RBF神經(jīng)網(wǎng)絡(luò)在混沌時(shí)間序列預(yù)測(cè)中的研究[J];物理學(xué)報(bào);2005年10期

5 林茂六,楊智偉,許洪光;CDMA信號(hào)前向鏈路頻譜增生和鄰道功率比估計(jì)[J];重慶郵電學(xué)院學(xué)報(bào)(自然科學(xué)版);2005年01期

相關(guān)碩士學(xué)位論文 前2條

1 祝樂(lè)芳;功率放大器的非線性預(yù)失真技術(shù)的研究[D];沈陽(yáng)理工大學(xué);2012年

2 馮華;預(yù)失真線性功率放大器的研究[D];電子科技大學(xué);2009年

，

本文編號(hào)：1812122