以類神經網路學習及模糊滑動模式控制為基礎實現雙氣壓肌肉驅動手臂之快速追跡控制

簡易檢索 / 詳目顯示

回結果列表

研究生：	陳映辰 Ying-Chen Chen
論文名稱：	以類神經網路學習及模糊滑動模式控制為基礎實現雙氣壓肌肉驅動手臂之快速追跡控制 Fast Tracking Control of a Dual Pneumatic Muscle Actuated Manipulator based on Neural Network Learning and Fuzzy Sliding Mode Control
指導教授：	姜嘉瑞 Chia-Jui Chiang
口試委員:	姜嘉瑞 Chia-Jui Chiang 江茂雄 Mao-Hsiung Chiang 蘇順豐 Shun-Feng Su 林紀穎 Chi-Ying Lin 林志哲 Chih-Jer Lin
學位類別：	博士 Doctor
系所名稱：	工程學院 - 機械工程系 Department of Mechanical Engineering
論文出版年：	2018
畢業學年度：	106
語文別：	中文
論文頁數：	104
中文關鍵詞：	氣壓肌肉致動器、模糊滑動模式控制、類神經網路、徑向基底函數神經網路
外文關鍵詞：	Pneumatic muscles actuator, Fuzzy sliding mode control, Neural network, Radial basis function neural network
相關次數：	點閱：363 下載：9
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

上一筆

氣壓肌肉致動器(Pneumatic muscle actuator, PMA)具有潔淨、容易維護、低成本、高動力體積比和高動力重量比的優點，相似於人體肌肉柔軟性的特質，特別適合應用於人類肌肉輔助和協作機器人之發展。但氣體的溫度變化和可壓縮性等不確定性，使氣壓肌肉致動器具有高非線性、時變和遲滯的特性，造成氣壓肌肉致動器難以達到高速和精確的控制效果。為了克服這些問題，實現單軸氣壓肌肉手臂高速且精確的追蹤控制性能，本文提出以模糊滑動模式積分(Fuzzy sliding mode integral, FSMI)控制為基礎之控制架構，並且藉由類神經網路(Neural network)調整控制增益之參數，成功實現了精確的追蹤控制性能。其中，模糊控制器是被用來補償系統複雜的非線性動態，並採用滑動模式降低其輸入變數之維度。積分控制器能夠有效的減少系統的穩態誤差。透過類神經網路學習調整最佳的控制增益參數，使其追蹤誤差最小化。實驗結果證明本文提出之控制架構，能夠有效的調整系統最佳控制增益，實現單軸氣壓肌肉手臂精確追蹤控制目的。透過實驗驗證梯形波追蹤控制和正弦波軌跡追蹤控制，其參考追蹤頻率到達1 Hz。

為了進一步提升其控制精度和軌跡追蹤之頻率，本文加入參考輸入變化的前饋控制器結合模糊滑動模式控制策略，藉由徑向基底函數神經網路(Radial basis function neural network, RBFNN)估測氣壓肌肉手臂的系統數學模型，利用此模型提供類神經網路更精確地調整控制之增益參數，透過實驗驗證高頻正弦波軌跡追蹤控制。實驗結果證明徑向基底函數神經網路能夠精確的估測系統數學模型，並提供倒傳遞神經網路調整最佳控制增益參數，結合前饋控制和模糊滑動模式控制策略，能夠更進一步的提高其控制精度，使氣壓肌肉手臂達到優異的追蹤控制性能，其參考追蹤頻率達到3 Hz。軌跡追蹤平均絕對誤差達到0.98度。

The pneumatic muscle actuator (PMA) is one of the most promising actuators especially for the applications that require greater proximity between the humans and the robots. The advantages of PMA include high power-to-weight and power-to-volume ratios, cleanness, ease of maintenance, pliability, inherent safety, low cost and ready availability. Fast and precise control of PMA, however, is difficult to achieve due to the compressibility of the air and the elasticity of the PMA. In order to achieve accurate and consistent tracking performance of a dual PMA actuated manipulator over a considerably wide range of frequency, an intelligent adaptive control algorithm is first developed in this thesis. The adaptive learning is enabled by a neural network in which the control gains to a fuzzy sliding mode controller (FSMC) and an integrator are adjusted to minimize the tracking error. Experimental results show that the proposed control strategy achieves fast, accurate and consistent performance tracking sinusoidal reference trajectories up to 1~Hz in frequency with the compressed air regulated to 4 bar. Results also show that the proposed control strategy, with a more aggressive learning for the control gain to the FSMC, achieves satisfactory performance tracking a trapezoidal reference trajectory.

In order to further improve the control performance tracking of even higher frequencies, a reference input differential feedforward compensator is augmented and the FSMC in the feedback loop with each control gain adjusted by the back-propagation neural network. In the neural network learning algorithm, a radial basis function neural network (RBFNN) is applied to estimate the mathematical model of the dual PMA actuated manipulator. The experimental results show that the proposed radial basis function neural network fuzzy sliding mode control (RBFNNFSMC) strategy achieves accurate tracking of sinusoidal trajectories up to 3 Hz in frequency. The mean absolute error (MAE) achieved by the RBFNNFSMC tracking a sinusoidal trajectory of 3~Hz is about 0.98 degrees.

目 錄
摘要.......................................................................................................................................i
英文摘要................................................................................................................................ ii
致謝....................................................................................................................................iii
本目錄................................................................................................................................v
圖目錄................................................................................................................................viii
表目錄...............................................................................................................................ix
第一章 導論.......................................................................................................................... 1
1 研究背景............................................................................................................... 1
2 文獻回顧............................................................................................................... 3
3 研究動機與貢獻................................................................................................... 6
4 論文架構............................................................................................................... 7
第二章 系統架構.................................................................................................................. 8
1 氣壓肌肉手臂架構與特性................................................................................... 8
2 實驗設備介紹....................................................................................................... 15
2.1 比例流量控制閥 (Proportional control valve)..................................... 16
2.2 氣壓肌肉致動器 (Pneumatic muscle actuator).................................... 18
2.3 增量型旋轉編碼器 (Incremental rotary encoder)................................ 20
2.4 解碼 IC(Decoder integrated circuit)..................................................... 21
2.5 PCI-1710 控制介面卡 (Control interface card) 和 PCLD-8710 接線端子板 (Wiring Board)......................................................................... 25
2.6 FESTO SPAW 壓力感測器 (Pressure sensor) ..................................... 30
2.7 FESTO 空氣調節單元組 ..................................................................... 31
3 應用軟體說明....................................................................................................... 32
第三章 控制器設計.............................................................................................................. 33
1 模糊滑動模式積分控制 (Fuzzy sliding mode integral control).......................... 33
1.1 滑動模式理論 (Sliding mode theory).................................................. 34
1.2 模糊化 (Fuzzification).......................................................................... 36
1.3 模糊知識庫 (Fuzzy Knowledge Base)................................................. 37
1.4 模糊推論 (Fuzzy Interence)................................................................. 37
1.5 解模糊化 (Defuzzification).................................................................. 38
2 類神經網路模糊滑動模式積分控制 (Neural network fuzzy sliding mode
integral control, NNFSMIC)................................................................................. 40
2.1 類神經網路 (Neural Network) 之介紹................................................ 40
2.2 類神經網路模糊滑動模式積分 (NNFSMI) 控制之學習演算法....... 41
3 徑向基底函數神經網路模糊滑動模式控制 (Radial Basis Function Neural
Network Fuzzy Sliding Mode Control)................................................................ 43
3.1 徑向基底函數神經網路 (Radial Basis Function neural network) ...... 43
3.2 徑向基底函數神經網路模糊滑動模式控制 (RBFNNFSMC) 之學
習演算法............................................................................................... 45
第四章 實驗結果驗證與討論.............................................................................................. 48
1 實驗規劃與參數設計........................................................................................... 48
1.1 NNFSMI 之實驗規劃與參數設計 ...................................................... 48
1.2 RBFNNFSMC 之實驗規劃與參數設計 ............................................. 50
2 類神經網路模糊滑動模式積分 (Neural Network Fuzzy Sliding Mode Inte-
gral Control, NNFSMI) 控制之實驗結果........................................................52
2.1 NNFSMI 之梯形波軌跡追蹤控制 ...................................................... 52
2.2 NNFSMI 之正弦波波軌跡追蹤控制 .................................................. 54
2.3 0.05 Hz 正弦波波軌跡追蹤控制......................................................... 54
2.4 0.25 Hz 正弦波波軌跡追蹤控制......................................................... 57
2.5 0.5 Hz 正弦波波軌跡追蹤控制........................................................... 60
2.6 1 Hz 正弦波波軌跡追蹤控制.............................................................. 63
2.7 討論 FSMI 和 NNFSMI 之正弦波波軌跡追蹤控制性能.................. 66
3 RBFNNFSMC 之正弦波軌跡追蹤控制之實驗結果 ......................................... 68
3.1 0.5 Hz 正弦波波軌跡追蹤控制........................................................... 68
3.2 1 Hz 正弦波波軌跡追蹤控制.............................................................. 72
3.3 2 Hz 正弦波波軌跡追蹤控制.............................................................. 76
3.4 3 Hz 正弦波波軌跡追蹤控制.............................................................. 80
3.5 討論 RBFNNFSMC 之正弦波波軌跡追蹤控制性能 ........................ 84
第五章 總結與未來展望...................................................................................................... 86
1 總結....................................................................................................................... 86
2 未來展望............................................................................................................... 87
附 錄 ...................................................................................................................................... 88
參考文獻................................................................................................................................ 89

圖 目 錄
1 FESTO 氣壓肌肉致動器 . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
2 FESTO 氣壓肌肉致動器斷面圖 . . . . . . . . . . . . . . . . . . . . . . . 2
1 氣壓肌肉手臂架構圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2 氣壓肌肉手臂平台 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
3 氣壓肌肉手臂開迴路方波控制響應圖 . . . . . . . . . . . . . . . . . . . 10
4 氣壓肌肉手臂開迴路正弦波控制響應圖 . . . . . . . . . . . . . . . . . . 11
5 控制訊號與氣壓肌肉致動器壓力差之關係圖 . . . . . . . . . . . . . . . . 12
6 氣壓肌肉致動器壓力差與手臂角度之關係圖 . . . . . . . . . . . . . . . . 13
7 控制訊號與與手臂角度之關係圖 . . . . . . . . . . . . . . . . . . . . . . 13
8 控制訊號與與手臂角度變化量之關係圖 . . . . . . . . . . . . . . . . . . 14
9 FESTO 比例流量控制閥結構示意圖 . . . . . . . . . . . . . . . . . . . . 16
10 FESTO 比例流量控制閥剖面圖 . . . . . . . . . . . . . . . . . . . . . . . 17
11 FESTO 比例流量控制閥實體圖 . . . . . . . . . . . . . . . . . . . . . . . 17
12 FESTO 比例流量控制閥輸入電壓與流量之關係圖 . . . . . . . . . . . . . 17
13 FESTO 氣壓肌肉致動器 . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
14 FESTO 氣壓肌肉致動器拉力與內部壓力關係圖 . . . . . . . . . . . . . . 19
15 Nemicon HES-2048-2MD 增量型旋轉編碼器 . . . . . . . . . . . . . . . . 20
16 Agilent HCTL-2020 decoder IC . . . . . . . . . . . . . . . . . . . . . . . 21
17 Agilent HCTL-2020 decoder IC 腳位圖 . . . . . . . . . . . . . . . . . . . 24
18 Advantech PCI-1710 多功能控制介面卡 . . . . . . . . . . . . . . . . . . . 25
19 Advantech PCLD-8710 接線端子板 . . . . . . . . . . . . . . . . . . . . . 26
20 Advantech PCI-1710 內部工作流程方塊圖 . . . . . . . . . . . . . . . . . 27
21 FESTO SPAW 壓力感測器 . . . . . . . . . . . . . . . . . . . . . . . . . . 30
22 FESTO 空氣調節單元組 . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
23 氣壓肌肉手臂實驗介面 . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
1 模糊滑動模式控制架構圖 . . . . . . . . . . . . . . . . . . . . . . . . . . 34
2 模糊滑動模式積分控制架構圖 . . . . . . . . . . . . . . . . . . . . . . . 34
3 滑動平面圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
4 輸入變數之三角形隸屬函數 . . . . . . . . . . . . . . . . . . . . . . . . . 36
5 模糊推論過程 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
6 高度法示意圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38
7 輸出模糊規則表示意圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . 39
8 類神經網路模糊滑動模式積分控制架構圖 . . . . . . . . . . . . . . . . . 40
9 類神經網路架構圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
10 sigmoid 函數 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
11 徑向基底函數神經網路模糊滑動模式控制架構圖 . . . . . . . . . . . . . 43
12 徑向基底函數神經網路架構圖 . . . . . . . . . . . . . . . . . . . . . . . 44
13 加入前饋項之倒傳遞類神經網路架構圖 . . . . . . . . . . . . . . . . . . 46
1 輸入三角形隸屬度函數與輸出模糊規則圖 . . . . . . . . . . . . . . . . . 49
2 RBFNNFSMC 之輸入三角形隸屬度函數與輸出模糊規則圖 . . . . . . . . 50
3 FSMI 和 NNFSMI 梯形軌跡追蹤控制響應圖 . . . . . . . . . . . . . . . . 53
4 NNFSMI 控制器於 0.05 Hz 正弦波軌跡追蹤控制響應圖 ( η u = 0.00005 和
η i = 0.001 ) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55
5 比較 FSMI 和 NNFSMI 控制器於 0.05 Hz 正弦波軌跡追蹤控制響應圖
( η u = 0.0005 和 η i = 0.01 ) . . . . . . . . . . . . . . . . . . . . . . . . . 56
6 比較 FSMI 和 NNFSMI 控制器於 0.25 Hz 正弦波軌跡追蹤控制響應圖
( η u = 0.0005 和 η i = 0.01 ) . . . . . . . . . . . . . . . . . . . . . . . . . 58
7 比較 NNFSMI 控制有無 G u 修正之 0.25 Hz 正弦波軌跡追蹤控制響應放
大圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59
8 比較 FSMI 和 NNFSMI 控制器於 0.5 Hz 正弦波軌跡追蹤控制響應圖
( η u = 0.00005 和 η i = 0.001 ) . . . . . . . . . . . . . . . . . . . . . . . . 61
9 比較 FSMI 和 NNFSMI 控制 0.5 Hz 正弦波軌跡追蹤控制實驗暫態和穩態
放大圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 62
10 比較 FSMI 和 NNFSMI 控制器於 1 Hz 正弦波軌跡追蹤控制響應圖
( η u = 0.00005 和 η i = 0.001 ) . . . . . . . . . . . . . . . . . . . . . . . . 64
11 比較 FSMI 和 NNFSMI 控制 1 Hz 正弦波軌跡追蹤控制實驗暫態和穩態放
大圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65
12 比較 FSMI 和 NNFSMI 控制於 0.05 Hz ∼ 1 Hz 正弦波軌跡追蹤控制穩態性
能圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 67
13 RBFNNFSMC 控制追蹤 0.5 Hz 正弦波軌跡追蹤控制實驗響應圖 . . . . . 69
14 RBFNN 預先訓練後之 RBFNNFSMC 控制追蹤 0.5 Hz 正弦波軌跡追蹤控
制實驗響應圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 70
15 RBFNNFSMC 控制追蹤 0.5 Hz 正弦波軌跡追蹤控制實驗穩態響應放大圖 71
16 RBFNNFSMC 控制追蹤 1 Hz 正弦波軌跡追蹤控制實驗響應圖 . . . . . . 73
17 RBFNN 預先訓練後之 RBFNNFSMC 控制追蹤 1 Hz 正弦波軌跡追蹤控制
實驗響應圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 74
18 RBFNNFSMC 控制追蹤 1 Hz 正弦波軌跡追蹤控制實驗暫態響應與穩態
響應放大圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 75
19 RBFNNFSMC 控制追蹤 2 Hz 正弦波軌跡追蹤控制實驗響應圖 . . . . . . 77
20 RBFNN 預先訓練後之 RBFNNFSMC 控制追蹤 2 Hz 正弦波軌跡追蹤控制
實驗響應圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 78
21 RBFNNFSMC 控制追蹤 2 Hz 正弦波軌跡追蹤控制實驗暫態響應與穩態
響應放大圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 79
22 RBFNNFSMC 控制追蹤 3 Hz 正弦波軌跡追蹤控制實驗響應圖 . . . . . . 81
23 RBFNN 預先訓練後之 RBFNNFSMC 控制追蹤 3 Hz 正弦波軌跡追蹤控制
實驗響應圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 82
24 RBFNNFSMC 控制追蹤 3 Hz 正弦波軌跡追蹤控制實驗暫態響應與穩態
響應放大圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 83
25 RBFNNFSMC 控制於 0.5 Hz ∼ 3 Hz 正弦波軌跡追蹤控制穩態性能圖 . . . 85

表 目 錄
1 比例流量控制閥規格表 . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
2 氣壓肌肉致動器規格表 . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
3 增量型旋轉編碼器規格表 . . . . . . . . . . . . . . . . . . . . . . . . . . 20
4 解碼 IC 規格表 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
5 解碼 IC 腳位說明表 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
6 PCI-1710 類比輸入規格表 . . . . . . . . . . . . . . . . . . . . . . . . . . 28
7 PCI-1710 類比輸出規格表 . . . . . . . . . . . . . . . . . . . . . . . . . . 28
8 PCI-1710 數位輸入和輸出規格表 . . . . . . . . . . . . . . . . . . . . . . 28
9 PCI-1710 計數與計時規格表 . . . . . . . . . . . . . . . . . . . . . . . . 29
10 FESTO 壓力感測器規格表 . . . . . . . . . . . . . . . . . . . . . . . . . 30
1 模糊集合符號說明表 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36
A.1 List of parameters and their values, if constant. . . . . . . . . . . . . . . 88
                                

參考文獻
[1] Kyoung Kwan Ahn and Huynh Thai Chau Nguyen. Intelligent switching control of a pneumatic muscle robot arm using learning vector quantization neural network. Mechatronics, 17(4-5):255–262, May–June 2007.
[2] Rezoug Amar, Hamerlain Mustapha, and Tadjine Mohamed. Decentralized RBFNN type-2 fuzzy sliding mode controller for robot manipulator driven by artificial muscles. International Journal of Advanced Robotic Systems, 9(5):182, November 2012.
[3] G. Andrikopoulos, G. Nikolakopoulos, and S. Manesis. Advanced nonlinear PID-based antagonistic control for pneumatic muscle actuators. IEEE Transactions on Industrial Electronics, 61(12):6926–6937, December 2014.
[4] George Andrikopoulos, George Nikolakopoulos, and Stamatis Manesis. Pneumatic arti-
ficial muscles:a switching model predictive control approach. Control Engineering Prac-
tice, 21(12):1653–1664, December 2013.
[5] Ho Pham Huy Anh. Online tuning gain scheduling MIMO neural PID control of the
2-axes pneumatic artificial muscle robot arm. Expert Systems with Applications, 37(9):
6547–6560, September 2010.
[6] Ho Pham Huy Anh and Kyoung Kwan Ahn. Hybrid control of a pneumatic artificial
muscle robot arm using an inverse NARX fuzzy model. Engineering Applications of
Artificial Intelligence, 24(4):697–716, June 2011.
[7] Ho Pham Huy Anh and Kyoung Kwan Ahn. Hybrid control of a pneumatic artificial
muscle robot arm using an inverse NARX fuzzy model. Engineering Applications of
Artificial Intelligence, 24(4):697–716, June 2011.
[8] Harald Aschemann and Dominik Schindele. Sliding-mode control of a high-speed linear
axis driven by pneumatic muscle actuators. IEEE Transactions on Neural Systems and
Rehabilitation Engineering, 55(11):3855–3864, November 2008.
[9] D. X. Ba and K. K. Ahn. Indirect sliding mode control based on gray-box identification
method for pneumatic artificial muscle. Mechatronics, 32:1–11, December 2015.
[10] Dang Xuan Ba, Truong Quang Dinh, and Kyoung Kwan Ahn. An integrated intelligent
nonlinear control method for a pneumatic artificial muscle. IEEE/ASME Transactions on
Mechatronics, 21(4):1835 – 1845, August 2016.
[11] K. Balasubramanian and K. S. Rattan. Fuzzy logic control of a pneumatic muscle system
using a linearizing control scheme. pages 432–436. International Conference of the North
American Fuzzy Information Processing Society, IEEE, July 2003.
[12] Stephen Boyd and Lieven Vandenberghe. Convex Optimization. Cambridge University
Press, New York, first edition, 2004.
[13] Darwin G. Caldwell, Gustavo A. Medrano-Cerda, and Mike Goodwin. Control of pneu-
matic muscle actuators. IEEE Control Systems Magzine, 15(1):40–48, February 1995.
[14] S. W. Chan, John H. Lilly, D. W. Repperger, and J. E. Berlin. Fuzzy PD+I learning con-
trol for a pneumatic muscle. pages 278–283. IEEE International Conference on Fuzzy
Systems, IEEE, May 2003.
[15] Xiao Guang Chang and John H. Lilly. Fuzzy control for pneumatic muscle tracking via
evolutionary tuning. Intelligent Automation and Soft Computing, 9(4):227–244, March
2003.
[16] Tae-Yong Choi, Byoung-Suk Choi, and Kap-Ho Seo. Position and compliance control
of a pneumatic muscle actuated manipulator for enhanced safety. IEEE Transactions on
Control Systems Technology, 19(4):832–842, July 2010.
[17] Tae-Yong Choi and Ju-Jang Lee. Control of manipulator using pneumatic muscles for en-
hanced safety. IEEE Transactions on Industrial Electronics, 57(8):2815–2825, November
2010.
[18] Shameek Ganguly, Akash Gargb, Akshay Pasricha, and S.K. Dwivedy. Control of pneu-
matic artificial muscle system through experimental modelling. Mechatronics, 22(8):
1135–1147, December 2012.
[19] Ted Hesselroth, Kakali Sarkar, P. Patrick Van Der Smagt, and Klaus Schulten. Neural
network control of a pneumatic robot arm. IEEE Transactions on Systems Man and Cy-
bernetics, 24(1):28–38, January 1994.
[20] Alexander Hošovský, Jozef Novák-Marcinčin, Ján Pitel’, Jana Boržíková, and Kamil
Židek. Model-based evolution of a fast hybrid fuzzy adaptive controller for a pneumatic
muscle actuator. International Journal of Advanced Robotic Systems, 9(2):40, January
2012.
[21] Shahid Hussain, Sheng Q. Xie, and Prashant K. Jamwal. Control of a robotic orthosis for
gait rehabilitation. Robotics and Autonomous Systems, 61(9):911–919, September 2013.
[22] M.IskarousandK.Kawamura. Intelligentcontrolusinganeuro-fuzzynetwork. volume3,
pages 350–355, Pittsburgh, PA, August 1995. IEEE International Conference on Human
Robot Interaction and Cooperative Robots, IEEE.
[23] Xianzhi Jiang, Zenghuai Wang, Chao Zhang, and Liangliang Yang. Fuzzy neural network
control of the rehabilitation robotic arm driven by pneumatic muscles. Industrial Robot:
An International Journal, 42(5):36–43, January 2015.
[24] Sung Woo Kim and Ju Jang Lee. Design of a fuzzy controller with fuzzy sliding surface.
Fuzzy Sets and Systems, 71(3):359–367, May 1995.
[25] Heejin Lee, Euntai Kim, Hyung-Jin Kang, and Mignon Park. A new sliding-mode control
with fuzzy boundary layer. Fuzzy Sets and Systems, 120(1):135 – 143, May 1995.
[26] Thananchai Leephakpreeda. Fuzzy logic based pwm control and neural controlled-
variable estimation of pneumatic artificial muscle actuators. Expert Systems with Ap-
plications, 38(6):7837 – 7850, June 2011.
[27] J. H. Lilly. Adaptive tracking for pneumatic muscle actuators in bicep and tricep config-
urations. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 11(3):
333–339, September 2003.
[28] Chih-Jer Lin, Chii-Ruey Lin, Shen-Kai Yu, and Chun-Ta Chen. Hysteresis modeling and
tracking control for a dual pneumatic artificial muscle system using prandtl–ishlinskii
model. Mechatronics, 28:35–45, June 2015.
[29] Tri Vo Minh, Tegoeh Tjahjowidodo, Herman Ramon, and Hendrik Van Brussel. Cas-
cade position control of a single pneumatic artificial muscle-mass system with hysteresis
compensation. Mechatronics, 20(3):402–414, April 2010.
[30] Aron Pujana-Arrese, Anjel Mendizabal, Javier Arenas, Ramon Prestamero, and Josebam
Landaluze. Modelling in modelica and position control of a 1-DOF set-up powered by
pneumatic muscles. Mechatronics, 20(5):535–552, August 2010.
[31] D. W. Repperger, K. R. Johnson, and C. A. Philips. Nonlinear feedback controlier design
ofapneumaticmuscleactuatorsystem. volume3, pages1525–1529, SanDiego, CA,June
1999. American Control Conference, IEEE.
[32] Ryan M. Robinson, Curt S. Kothera, Robert M. Sanner, and Norman M. Wereley. Nonlin-
ear control of robotic manipulators driven by pneumatic artificial muscles. IEEE/ASME
Transactions on Mechatronics, 21(1):55 – 68, February 2016.
[33] Xiang Rong Shen. Nonlinear model-based control of pneumatic artificial muscle servo
systems. Control Engineering Practice, 18(3):311–317, March 2010.
[34] J. E. Slightam and M. L. Nagurka. Robust control law for pneumatic artificial muscles.
page V001T01A009, Sarasota, Florida, October 2017. Proceedings of the ASME/Bath
2017 Symposium on Fluid Power and Motion Control.
[35] Jean-Jacques E. Slotine and Weiping Li. Applied Nonlinear Control. Prantice Hall Inc,
New Jersey, first edition, 1991.
[36] N.N. Son, C.V. Kien, and H.P.H.Anh. A novel adaptive feed-forward-PID controller of a SCARA parallel robot using pneumatic artificial muscle actuator based on neural network and modified differential evolution algorithm. Robotics and Autonomous Systems, 96:65–80,
October 2017.
[37] Chunsheng Song, Shengquan Xie, Zude Zhou, and Yefa Hu. Modeling of pneumatic
artificial muscle using a hybrid artificial neural network approach. Mechatronics, 31(12):
124 – 131, October 2015.
[38] Tu Diep Cong Thanh and Kyoung Kwan Ahn. Intelligent phase plane switching control of
pneumatic artificial muscle manipulators with magneto-rheological brake. Mechatronics,
16(2):85 – 95, May–June 2006.
[39] Tu Diep Cong Thanh and Kyoung Kwan Ahn. Nonlinear PID control to improve the con-
trol performance of 2 axes pneumatic artificial muscle manipulator using neural network.
Mechatronics, 16(9):577–587, November 2006.
[40] B. Tondu and P. Lopez. Modeling and control of mckibben artificial muscle robot actua-
tors. IEEE Control Systems Magzine, 20(2):15–38, april 2000.
[41] Ming-LeiTsengandMin-ShinChen. Chatteringreductionofslidingmodecontrolbylow-
pass filtering the control signal. Asian Journal of Control, 12(3):392–398, May 2010.
[42] Shaofei Wang and Kaiji Sato. High-precision motion control of a stage with pneumatic
artificial muscles. Precision Engineering, 43:448–461, January 2016.
[43] Ying-Tsai Wang, Ray-Hwa Wong, and C-W Yu. Fuzzy control: 2d pneumatic muscle
actuator’s arm. Measurement and Control, 42(1):24–27, February 2009.
[44] S. Xie, H. liu J. Mei, and Y. Wang. Hysteresis modeling and trajectory tracking control of
the pneumatic muscle actuator using modified prandtl-ishlinskii model. Mechanism and
Machine Theory, 120:213–224, February 2018.
[45] S. Q. Xie and P. K. Jamwal. An iterative fuzzy controller for pneumatic muscle driven
rehabilitation robot. Expert Systems with Applications, 38(7):8128–8137, July 2011.
[46] K. Xing, J. Huang, Y. Wang, J. Wu, Q. Xu, and J. He. Tracking control of pneumatic
artificial muscle actuators based on sliding mode and non-linear disturbance observer.
IET Control Theory and Applications, 4(10):2058–2070, October 2010.
[47] Kexin Xing, Yongji Wang, Quanmin Zhu, and Hanying Zhou. Modeling and control
of mckibben artificial muscle enhanced with echo state networks. Control Engineering
Practice, 20(5):477–488, November 2012.
[48] TakayukiYamadaandTetsuroYabuta. Neuralnetworkcontrollerusingautotuningmethod
fornonlinearfunctions. IEEETransactionsonNeuralNetworks,3(4):595–601,July1992.
[49] Wenjing Yang and Yuanguo Zhu. A fuzzy method for signal smoothing. pages 28–31,
Huangshan, China, May 2010. 2010 Third International Joint Conference on Computa-
tional Science and Optimization.
[50] B. Yao, Z. Zhou, Q. Liu, and Q. Ai. Empirical modeling and position control of single
pneumatic artificial muscle. Journal of Control Engineering and Applied Informatics,
18(2):86–94, 2016.
[51] Daohui Zhang, Daohui Zhang, and Jianda Han. Active model-based control for pneu-
matic artificial muscle. IEEE/ASME Transactions on Mechatronics, 64(2):1686 – 1695,
February 2016.
[52] Jie Zhao, Jun Zhong, and Jizhuang Fan. Position control of a pneumatic muscle actuator
using rbf neural network tuned pid controller. Mathematical Problems in Engineering,
2015:1–16, April 2015.
[53] Lijun Zhu, Xianyi Shi, Zhiyong Chen, Hai-Tao Zhang, and Cai-Hua Xiong. Adaptive
servomechanism of pneumatic muscle actuators with uncertainties. IEEE Transactions on
Industrial Electronics, 64(4):3329 – 3337, April 2017.

簡易檢索 / 詳目顯示

相關論文