跳到主要內容

臺灣博碩士論文加值系統

(18.204.48.64) 您好!臺灣時間:2021/08/01 08:32
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:林洋印
研究生(外文):Yang -Yin Lin
論文名稱:針對動態系統處理的遞迴式自我演化的第二類型模糊類神經網路和其FPGA實現
論文名稱(外文):A Recurrent Self-Evolving Interval Type-2 Fuzzy Neural Network for Dynamic System Processing and Its FPGA Implementation
指導教授:莊家峰
學位類別:碩士
校院名稱:國立中興大學
系所名稱:電機工程學系所
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:2008
畢業學年度:96
語文別:英文
論文頁數:48
中文關鍵詞:遞迴式的第二類型模糊類神經網路動態系統
外文關鍵詞:RSEIT2FNNDynamic system
相關次數:
  • 被引用被引用:0
  • 點閱點閱:105
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本論文提出一個遞迴式自我演化的區間第二類型模糊類神經網路(RSEIT2FNN)針對動態系統處理,RSEIT2FNN 中的每一條遞迴的模糊規則的前件部都是第二類型的模糊集合而後件部是使用TSK型式的區間權重值。在架構中,RSEIT2FNN的前件部每個規則激發量形成一個內部反饋回到本身。 TSK類型後件部是外部輸入一個線性模型。RSEIT2FNN最初不包含規則,並且所有規則是經過網上架構學習和參數學習。架構學習是使用線上的第二類型模糊分群。在參數學習,後件部參數的學習是由排序後規則的Kalman濾波器演算法調整可具有高精確度學習的表現。前件部的參數和內部迴授的權重值則利用梯度下降法去學習。RSEIT2FNN的模擬在動態系統辨識和混沌和混亂信號預言在無噪聲和喧鬧的情況下。 與其他第一類型遞迴式模糊神經網絡的比較驗証RSEIT2FNN的性能。
This paper proposes a Recurrent Self-Evolving Interval Type-2 Fuzzy Neural Network (RSEIT2FNN) for dynamic system processing. The antecedent parts in each recurrent fuzzy rule of the RSEIT2FNN are interval type-2 fuzzy sets and the consequent part is of the Takagi-Sugeno-Kang (TSK) type with interval weights. In structure, the antecedent part of RSEIT2FNN forms a locally internal feedback loop by feeding the rule firing strength of each rule back to itself. The TSK-type consequent part is a linear model of exogenous inputs. The RSEIT2FNN contains no rules initially and all rules are learned on-line via structure and parameter learning. Structure learning uses on-line type-2 fuzzy clustering. For parameter learning, the consequent part parameters are tuned by a rule-ordered Kalman filter algorithm for high accuracy learning performance. The antecedent type-2 fuzzy sets and internal feedback loop weights are learned by a gradient descent algorithm. The RSEIT2FNN is applied to simulations on dynamic system identifications and chaotic signal prediction under noise-free and noisy conditions. Comparisons with other type-1 recurrent fuzzy neural networks verify the performance of the RSEIT2FNN.
Contents

Abstract (in Chinese).………………………………………………i
Abstract (in English)………………………………………………ii
Contents………………………………………………………………iv
List of Figures………………………………………………………v
List of Tables………………………………………………………vii

Chapter 1 : Introduction……………………………………………1

Chapter 2 : Structure of RSEIT2FNN………………………………4

Chapter 3 : Learning of RSEIT2FNN………………………………11
3.1 Structure Learning……………………………………………11
3.2 Parameter Learning……………………………………………12

Chapter 4 : FPGA Implementation…………………………………19
4.1 Structure of IT2FNN……………………………………………19

4.2 Hardware Implementation of IT2FNN(H-IT2FNN)……………20

Chapter 5 : Simulations and Experiments………………………28
5.1 Software Implementation Simulations………………………28
5.2 Hardware Implementation Experiments………………………40

Chapter 6 : Conclusions……………………………………………45

Bibliography…………………………………………………………46

List of Figures
Figure 1 Structure of the Recurrent Self-Evolving Interval Type-2 Fuzzy Neural Network (RSEIT2FNN)………………………4
Figure 2 An interval type-2 fuzzy set with uncertain mean………………………………………………………………………6
Figure 4.1 The architecture of H-IT2FNN………………………21
Figure 4.2 Input Fuzzifier module………………………………22
Figure 4.3 Separation calculation module…………………… 23
Figure 4.4 Meet module…………………………………………… 24
Figure 4.5 Temporal firing module………………………………25
Figure 4.6 Output processing module……………………………26
Figure 4.7 The 2’s Complement Module…………………………26
Figure 4.8 The Output Module…………………………………… 27
Figure 3 Outputs of the dynamic plant and RSEIT2FNN in Example 1…………………………………………………………… 29
Figure 4 Test errors between the RSEIT2FNN and actual plant outputs in Example 1………………………………………30
Figure 5 Outputs of the dynamic plant and RSEIT2FNN with while Gaussian noise(STD=0.1) in Example 1…………………33
Figure 6 Outputs of the dynamic plant and RSEIT2FNN with while Gaussian noise(STD=0.5) in Example 1…………………33
Figure 7 Outputs of the dynamic plant and RSEIT2FNN with while Gaussian noise(STD=0.7) in Example 1…………………34
Figure 8 Results of the phase plot for the chaotic system and RSEIT2FNN in Example 2………………………………………35
Figure 9 Outputs of the MIMO plant and model RSEIT2FNN in Example 3(a)Output .(b)Outputs …………………………… 38
Figure 10 Identification results of the software and hardware implemented IT2FNN………………………………………41
Figure 11 The distribution of left separation point………43
Figure 12 The distribution of right separation point…… 44

List of Tables
Table 1. Performance of RSEIT2FNN and other recurrent models for SISO plant identification in example 1……………………………………………………………………… 31
Table 2 Performance of RSEIT2FNN and TRFN with different noise level in example 1…………………………………………31
Table 3 Performance of RSEIT2FNN and other recurrent models in example 2…………………………………………………35
Table 4 Performance of RSEIT2FNN AND TRFN-S with different Noise levels in Example 2……………………………………… 36
Table 5 Performance of RSEIT2FNN and recurrent models for MIMO plant Identification in example 3………………………39
Table 6 Performance of RSEIT2FNN and TRFN-S with different noise Levels in example 3………………………………………40
Table7. The Parameters Of H-IT2FNN……………………………42
Table8. The sizes of each module and the whole IT2FNN chip with results simulated by Xilinx ISE 7.1i.…………………42
[1] J. Zhang and A. J. Morris, “Recurrent neuro-fuzzy networks for nonlinear process modeling,” IEEE Trans. Neural Networks, vol. 10, no. 2, pp. 313-326, Feb. 1999.
[2] P. A. Mastorocostas and J. B. Theocharis, “A recurrent fuzzy-neural model for dynamic system identification,” IEEE Trans. Syst., Man and Cyber., Part B: Cybernetics, vol. 32, no. 2, pp. 176-190, Feb. 2002.
[3] J. B. Theocharis, “A high-order recurrent neuro-fuzzy system with internal dynamics: Application to the adaptive noise cancellation,” Fuzzy Sets and Systems, vol. 157, no. 4, pp. 471-500, 2006.
[4] C. H. Lee and C. C. Teng, “Identification and control of dynamic systems using recurrent fuzzy neural networks,” IEEE Trans. Fuzzy Systems, vol. 8, no. 4, pp. 349-366, Aug. 2000.
[5] C. J. Lin and C. C. Chin, “Prediction and identification using wavelet-based recurrent fuzzy neural networks,” IEEE Trans. Systems, Man and Cybernetics - Part B: Cybernetics, vol. 34, no. 5, 2144-2154, 2004.
[6] C.F. Juang and C.T. Lin, “A recurrent self-organizing neural fuzzy inference network,” IEEE Trans. Neural Networks, vol.10, no. 4, pp. 828-845, Jul. 1999.
[7] C. F. Juang, “A TSK-type recurrent fuzzy network for dynamic systems processing by neural network and genetic algorithm,” IEEE Trans. Fuzzy Systems, vol. 10, no. 2, pp. 155-170, April 2002.
[8] Y. C. Wang, C. J. Chien, and C. C. Teng, “Direct adaptive iterative learning control of nonlinear systems using an output-recurrent fuzzy neural network,” IEEE Trans. Syst., Man, and Cyber., Part B-Cybernetics, vol. 34, no. 3, pp. 1348-1359, 2004.
[9] J. M. Mendel and R. I. John, “Type-2 fuzzy sets made simple,” IEEE Trans. On Fuzzy Systems, vol. 10, no. 2, pp. 117-127, 2002.
[10] J. M. Mendel, Uncertain Rule-Based Fuzzy Logic System: Introduction and New Directions, Prentice Hall, Upper Saddle River, NJ, 2001.
[11] Q. Liang and J. M. Mendel, “Equalization of nonlinear time-varying channels using type-2 fuzzy adaptive filters,” IEEE Trans. Fuzzy systems, vol. 8, no. 551-563, 2000.
[12] H. Hagras, “A hierarchical type-2 fuzzy logic control architecture for autonomous mobile robots,” IEEE Trans. Fuzzy Systems, vol. 12, no. 524-539, 2004.
[13] J. Zeng and Z. Q. Liu, “Type-2 fuzzy hidden Markov models and their application to speech recognition,” IEEE Trans. Fuzzy Systems, vol. 14, no. 3, pp. 454-467, June 2006.
[14] C. H. Lee, Y. C. Lin, and W. Y. Lai, “Systems identification using type-2 fuzzy neural network (Type-2 FNN) systems,” Proc. IEEE Int. Symp. Computational Intelligence in Robotics and Automation, vol. 3, pp. 1264-1269, 2003.
[15] C. H. Wang, C. S. Cheng, and T. T. Lee, “Dynamical optimal training for interval type-2 fuzzy neural network (T2FNN),” IEEE Trans. on Syst., , Man, and Cyber. - Part B: Cybernetics, vol. 34, no. 3, pp. 1462-1477, 2004.
[16] J. M. Mendel, “Computing derivatives in interval type-2 fuzzy logic system,” IEEE Trans. On Fuzzy Systems, vol. 12. no. 1, pp. 84-98, Feb. 2004.
[17] H. Hagras, “Comments on dynamical optimal training for interval type-2 fuzzy neural network (T2FNN),” IEEE Trans. Syst., Man and Cyber. - Part B: Cybernetics, vol. 36, no. 5, pp. 1206-1209, Oct. 2006.
[18] G. M. Mendez and O. Castillo, “Interval type-2 TSK fuzzy logic systems using hybrid learning algorithm,” Proc. IEEE Int. Conf. Fuzzy Systems, pp. 230-235, May 22-25, 2005.
[19] Q. Liang and J. M. Mendel, “Interval type-2 fuzzy logic systems: theory and design,” IEEE Trans. On Fuzzy Systems, vol. 8, no. 5, pp. 535-550, 2000.
[20] C. F. Juang and C. T. Lin, “An on-line self-constructing neural fuzzy inference network and its applications,” IEEE Trans. Fuzzy Systems, vol. 6. no. 1, pp. 12-32, Feb. 1998.
[21] J. L. Elman, “Finding structure in time,” Connit. Sci., vol. 14, pp. 179-211, 1990.
[22] P. S. Sastry, G. Ssntharam, and K. P. Unnikrishnan, “Memory neural networks for identification and control of dynamic systems,” IEEE Trans. Neural Networks, vol. 5, pp. 306-319, 1994.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top