(3.238.186.43) 您好!臺灣時間:2021/02/25 01:45
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:林哲弘
研究生(外文):LIN, CHE-HUNG
論文名稱:適應性權重部分更新法用於主動式噪音控制之硬體實現
論文名稱(外文):Hardware Implementation of Adaptive Weight Partial Update Active Noise Controller
指導教授:翁萬德
指導教授(外文):WENG,WAN-DE
口試委員:陳永隆竇奇
口試委員(外文):CHEN,YOUNG-LONGDOU,CHIE
口試日期:2020-07-23
學位類別:碩士
校院名稱:國立雲林科技大學
系所名稱:電機工程系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:中文
論文頁數:57
中文關鍵詞:FPGA類神經網路主動式噪音控制器FSLMSIAMBT部份更新
外文關鍵詞:FPGAneural networkactive noise controlFSLMSIAMBTpartial update
相關次數:
  • 被引用被引用:0
  • 點閱點閱:25
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
在本論文中,主要探討權重部分更新用於主動式噪音控制器之硬體設計,其基本原理是透過反向聲波來形成破壞性相加,以達到消除噪音的目的,架構上採用FLANN (functional link artificial neural network)並配合FSLMS (filtered-s least mean square) 演算法之主動式噪音控制器做為其架構,再加上簡化的IAMBT(interval adaptive maximum between two)架構加以改善其效能。
我們在FLANN中加入部分更新技術,來達到減少運算量和加快系統的效率,在完成FSLMS的基本硬體架構後,分別加上IA(interval adaptive)架構來減少系統的運算量;加上MBT(maximum between two) 架構來加快系統收斂效能;最後將兩者作結合即可得到簡化的IAMBT-FSLMS架構,並且我們跟原始FSLMS架構相比,在效能上有相當大的改善,且相當接近軟體模擬的結果。

The design of partial updating (PU) technique for the weights in an active noise controller (ANC) is discussed in this thesis. The basic principle is to form a destructive addition through reverse sound waves to achieve the purpose of eliminating noise. The architecture uses functional link artificial neural network (FLANN) and the active noise controller with filtered-s least mean square (FSLMS) algorithm as its architecture, and a simplified interval adaptive maximum-between-two (IAMBT) architecture to improve its performance.
We added some update technology to FLANN to reduce the amount of calculation and speed up the efficiency of the system. After completing the basic hardware architecture of FSLMS, add interval adaptive (IA) architecture to reduce the amount of calculation of the system; add maximum between two (MBT) architecture to accelerate the system convergence performance; finally, the combination of the two can get a simplified IAMBT-FSLMS architecture, and we have a considerable improvement in performance compared with the original FSLMS architecture, and it is quite close to the results of software simulation.

摘要 i
Abstract ii
誌謝 iii
目錄 iv
表目錄 v
圖目錄 vi
第一章 緒論 1
1.1研究動機 1
1.2研究目的 2
1.3研究方法與內容 3
1.4各章提要 3
第二章 原理及概念介紹 4
2.1類神經網路 4
2.3 FSLMS介紹 7
2.4全部更新與部分更新技術介紹 11
第三章 FSLMS之主動式噪音控器之設計 15
3.1 系統架構 15
3.2 整體硬體電路架構 17
3.3 硬體效能評估 27
第四章 IAMBT-FSLMS之主動式噪音控器之設計 30
4.1 IA-FSLMS系統架構 30
4.2 MBT-FSLMS系統架構 38
4.3 IAMBT-FSLMS系統架構 42
第五章 系統比較及結論 46
參考文獻 47


[1]C. M. Harris, Handbook of Acoustical Measurements and Noise Control. 3rd ed., New York: McGraw-Hill, 1991.
[2]J. N. Denenberg, “Anti-noise,” IEEE Potentials Magazine, Vol. 11, no. 2, pp. 36-40, April 1992.
[3]T. Zhao, “A New FXLMS Algorithm with Offline and Online Secondary-Path Modeling Scheme for Active Noise Control of Power Transformers,” IEEE Transactions on Industrial Electronics, Vol. 64, No. 8, August 2017.
[4]Y. Xiao, “A New Feedforward Hybrid Active Noise Control System,” IEEE Signal Processing Letters, Vol. 18, No. 10, October 2011.
[5]W. D. Weng and C. T. Yen, “Reduced-decision feedback FLANN nonlinear channel equalizer for digital communication system,” IEE Proceedings, Vol. 151, No. 4, pp. 305-311, 2004.
[6]Y. C. Tsai, “Design of a Reduced Neural Network Based Active Noise Controller,” Master Thesis of National Yunlin University of Science & Technology, June 2006.
[7]D. P. Das, D. J. Moreau, and B. S. Cazzolato, “Multichannel FSLMS algorithm based active headrest,” International Conference on Advanced Systems (ICAES), 2013.
[8]S. M. Kuo, “Nonlinear Adaptive Bilinear Filters for Active Noise Control Systems” IEEE Transactions On Circuits and Systems—I: Regular Papers, Vol. 52, No. 3, March 2005.
[9]D. Bismor, “Partial Update LMS Algorithms in Active Noise Control,” 7 th Forum Acusticum, Kraków, Poland, 7-12 September, 2014.

[10]S. Douglas. Simplified stochastic gradient adaptive filters using partial updating. In: Digital Signal Processing Workshop, 1994., 1994 Sixth IEEE. 265–268.
[11]C. Y. Wong, “Design of Adaptive Weight Partial Update Active Noise Controller,” Master Thesis of National Yunlin University of Science & Technology, June 2016.
[12]Y. Y. Cheng, “Design of Adaptive Weight Partial Update Active Noise Controller,” Master Thesis of National Yunlin University of Science & Technology, June 2019.
[13]Y. H. Pao and Y. Takefuji, “Functional-link net computing: theory, system architecture, and functionalities,” Computer, Vol. 25, Issue. 5, pp. 76-79, May 1992.
[14]E. F. Moore Gedanken-experiments on Sequential Machines. Automata Studies, Annals of Mathematical Studies, 34, 129–153. Princeton University Press, Princeton, N.J., 1956

電子全文 電子全文(網際網路公開日期:20250806)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔