(3.236.214.19) 您好!臺灣時間:2021/05/07 12:35
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:王志偉
研究生(外文):Chih-Wei Wang
論文名稱:含未知擾動之非線性系統類神經網路模式預測控制的設計
論文名稱(外文):Neural Network Model Predictive Control Design for Nonlinear Processes with Unmeasured Disturbances
指導教授:陳榮輝陳榮輝引用關係
指導教授(外文):Jung-Hui Chen
學位類別:碩士
校院名稱:中原大學
系所名稱:化學工程研究所
學門:工程學門
學類:化學工程學類
論文種類:學術論文
論文出版年:2001
畢業學年度:89
語文別:中文
論文頁數:78
中文關鍵詞:類神經網路模式預測控制未知擾動
外文關鍵詞:model predictive controlneural networksdisturbance
相關次數:
  • 被引用被引用:2
  • 點閱點閱:85
  • 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
化工程序中未知擾動的存在,常是造成產品產生缺陷的原因,因此系統中存有擾動之模式識別與控制是很重要的。本研究所發展的類神經網路模式預測控制(NNMPC),將對含有未知擾動的非線性系統提出由預測模式的建立到控制器設計。在模式建立中,結合類神經網路ARX模式(NNARX)與AR擾動模式將稱為:NNARX+AR模式。而NNARX模式與AR模式分別代表,系統之輸入輸出的行為及系統之未知擾動。這兩種模式將同步進行訓練,其中Levenberg-Marquardt演算法使用於NNARX模式,而最小平方法使用於AR擾動模式。在控制器設計部份,將利用SQP(Seuqential quadratic programming)演算法,對含有限制條件之NNARX+AR模式搜尋其最適化控制區間。然後,將此策略應用於CSTR系統,非線性差分方程式與pH中和反應槽之模擬控制,以驗證此方法的效用。
Unmeasured disturbances usually plague the process and result in the defect products in chemical plants; hence, the identification and control of the process with the presence of disturbances is important. This paper completely develops the neural network model predictive control (NNMPC) from the model design to the controller design for nonlinear processes with unmeasured disturbances. In the model design, an input-driven output neural network ARX model (NNARX) combining with a disturbance AR model, called NNARX+AR, is proposed. NNARX and AR represent the input-output characteristics without the corrupted disturbances and with the disturbances respectively. The Levenberg-Marquardt algorithm for NNARX and the least square algorithm for AR are synchronously used to train the process model. In the control design, a constrained NNMPC based on NNARX+AR via the successive quadratic programming is developed to search the optimal control actions. To demonstrate the proposed identification and predictive control strategies, two multivariable cases with the presence of unmeasured disturbances, including a nonlinear mathematical equations and a pH neutralization system, are presented.
目錄
摘要…………………………………………………………I
Abstract…………………………………………………………II
目錄…………………………………………………………III
圖目錄…………………………………………………………V
表目錄…………………………………………………………VII
第一章 前言…………………………………………………1
1-1擾動模式預測控制………………………………………1
1-2研究動機…………………………………………………6
第二章 單變數非線性預測擾動模式的建立…………………7
2-1SISO之NNARMAX模式 ……………………………8
2-2SISO之NNARX+AR模式 ……………………………10
2-3NNARX+AR模式訓練法則……………………………18
2-4SISO之NNARX+遞迴式AR模式……………………22
第三章 單變數非線性預測在限制條件下控制器的設計…24
3-1目標函數之建立…………………………………………24
3-2SQP演算法………………………………………………25
3-3單變數非線性控制器的推導與歸納……………………28
3-4模擬測試…………………………………………………32
第四章 多變數非線性預測擾動模式的建立…………………38
4-1MIMO之NNARX+AR模式……………………………38
4-2MIMO之NNARX+遞迴式AR模式……………………49
第五章 多變數非線性預測在限制條件下控制器的設計…50
5-1目標函數之建立…………………………………………50
5-2多變數非線性控制器的推導與歸納……………………51
5-3模擬測試…………………………………………………55
第六章 結論…………………………………………………71
符號說明………………………………………………………72
參考文獻………………………………………………………75
圖目錄
圖1-1擾動模式預測控制之結構圖 …………………………2
圖1-2步階應答圖 ……………………………………………3
圖2-1單變數非線性動態模式的建立 ………………………7
圖2-21步超前預測之單變數NNARMAX模式 ……………9
圖2-3單變數線性AR模式輸入狀況一之結構圖 …………17
圖2-4單變數線性AR模式輸入狀況二之結構圖……………17
圖2-51步超前預測之單變數NNARX+AR模式……………17
圖2-6類神經網路結構圖 ……………………………………19
圖2-7即時線上修正AR模式之結構…………………………22
圖2-81步超前預測之單變數NNARX+遞迴式AR模式……23
圖3-1模式預測控制之結構圖 ………………………………30
圖3-2連續攪拌反應槽 ………………………………………33
圖3-3單變數NNARX+AR模式之訓練數據…………………36
圖3-4單變數NNARX+AR模式之測試結果…………………36
圖3-5單變數CSTR系統去除未知擾動之控制結果( , , )…………………………………………37
圖4-1多變數非線性動態模式的建立 ………………………38
圖4-2多變數線性AR模式輸入狀況一之結構圖……………46
圖4-3多變數線性AR模式輸入狀況二之結構圖……………46
圖4-41步超前預測之多變數NNARX+AR模式 …………47
圖4-51步超前預測之多變數NNARX+遞迴式AR模式…49
圖5-1多變數數學模式之訓練數據…………………………58
圖5-2多變數數學模式之驗證結果…………………………58
圖5-3多變數含未知擾動預測模式控制之控制結果( , , )………………………59
圖5-4開環路下多變數之原模式與變動後模式的比較結果60
圖5-5模式改變後多變數含未知擾動預測模式控制之控制結果( , , )……………………61
圖5-6pH酸鹼中和反應槽 …………………………………63
圖5-7多變數pH酸鹼中和反應系統之訓練數據 …………66
圖5-8多變數pH酸鹼中和反應系統之驗證結果 …………66
圖5-9多變數pH酸鹼中和反應系統設定點改變之控制結果( , , )………………………67
圖5-10多變數pH酸鹼中和反應系統去除擾動之控制結果( , , )…………………………68
圖5-11多變數pH酸鹼中和反應系統設定點改變及擾動變數變動之控制結果( , , )……69
圖5-12多變數pH酸鹼中和反應系統相對增益值的變化 …70
表目錄
表3-1連續式反應槽之參數與穩態操作條件 …………………34
表3-2模式訓練及驗證誤差在不同延遲項數下之結果 ………35
表5-1模式訓練及驗證誤差在不同 及 延遲項數下之結果…57
表5-2比較固定式AR模式及遞迴式AR模式之擾動預測控制的ISE值……………………………………………………62
表5-3pH酸鹼中和反應槽參數與穩態操作條件 ………………64
表5-4模式訓練誤差在不同延遲項個數下之結果 ……………65
表5-5pH酸鹼中和反應系統之ISE值 …………………………68
1.Astrom, K. and McAvoy, T. J., “Intelligent Control,” J. Proc. Cont., 2, 115 (1992).2.Baratti, R.; Vacca, G. and servida, A., “Neural Network Modeling of Distillation Columns,” Hydrocarbon Processing, June, 35 (1995). 3.Bequette B. W., “Nonlinear Predictive Control Using Multi-Rate Sampling,” Can. J. Chem. Eng., 69, 136 (1991).4.Bhat, N. and McAvoy, T. J., “Use of Neural Nets for Dynamic Modeling and Control of Chemical Process Systems,” Computers chem. Engng, 14, 573 (1990).5.Chen, J., “Systematic Derivations of Model Predictive Control Based on Artificial Neural Network,” Chem. Eng. Comm., 164, 35 (1998).6.Chen. J. and Yea, Y., “Neural Network Model Predictive Control on Multivariable Systems,” Automatic Control Conference, 498, Hsin-Chu, R.O.C. (2000).7.Chen, Q. and Weigand, W. A., “Dynamic Optimization of Nonlinear Process by Combining Neural Net Model with UDMC,” AIChE J., 14, 1488 (1994).8.Chen, S.; Cowan, C. F. N.; Billings, S. A. and Grant, P. M., “Parallel Recursive Prediction Error Algorithm for Training Layered Neural Networks,” Int. J. Contr., 6, 51, 1215 (1990).9.Culter, C. R. and Ramaker, B. L., “Dynamic Matrix Control-A Computer Control Algorithm,” in AICHE 86 Annual Meeting, Houston, U.S.A (1979).10.Hagan, M. T.; Demuth, H. B. and Beale, M., Neural Network Design, PWS Publishing Company (1996).11.Henson, M. A., “Nonlinear Model Predictive Control:Current Status and Future Directions,” Computers chem. Engng, 23, 2, 187 (1998).12.Hornik, K.; Stinchcombe, M. and White, H., “Mutliplayer Feedforward Neural Networks are Universal Approximators,” Neural Networks, 2, 359 (1989).13.Hornik, K.; Stinchcombe, M. and White, H., “Universal Approximation of an Unknown Mapping and its Derivatives Using Mutliplayer Feedforward Networks,” Neural Networks, 3, 551 (1990).14.Lakshminarayanan, S.; Shah, S. L. and Nandakumar, K., “Modeling and Control of Multivariable Process:Dynamic PLS Approach,” AIChE J., 43, 9, (1997).15.Lee, M. and Park, S., “A New Scheme Combining Neural Feedforward Control with Model-Predictive Control,” AIChE J., 38, 2, 193 (1992).16.Li, M.; Wang, F. and Gao, F., “Identification and Control of Nonlinear Processes in the Presence of Unmeasured Load Disturbances, ” Ind. Eng. Chem. Res., 40, 2275-2282 (2001).17.Luyben, W. L., Process Modeling, Simulation and Control for Chemical Engineers, McGraw-Hill International Editions (1990).18.Morris, A. J.; Montague, G. A. and Willis, M. J., “Artificial Neural Networks: Studies in Process Modeling and Control,” Chem. Eng. Res. Develop., 72, 3, (1994).19.Mukhopadhyay, S.; Kumpati, S. and Narendra., “Disturbance Rejection in Nonlinear Systems Using Neural Networks,” IEEE Trans. Neural Networks., 4, 1, 63 (1993).20.Nahas, E. P.; Henson, M. A. and Seborg, D. E., “Nonlinear Internal Model Control Strategy for Neural Network Models,” Computers chem. Engng, 12, 16, 1039 (1992).21.Narendra, K. S. and Parthasarathy, K., “Identicfication and Control of Dynamic Systems Using Neural Networks,” IEEE Trans. Neural Networks, 1, 1, 4 (1990).22.Ohshima, M.; Ohno, H.; Hashimoto, I.; Sasajima, M.; Maejima, M.; Tsuto, K. and Ogawa, T., “Model Predictive Control with Adaptive Disturbance Prediction and its Application to Fatty Acid Distillation Column Control,” J. Proc. Cont., 5, 1 ,41 (1994).23.Pollard, J. F.; Broussard, H. R.; Garrison, D. B. and San, K. Y., “Processing Identification Using Neural Networks,” Computers chem. Engng, 16, 253 (1992).24.Prasad, G.; Swidenbank, E. and Hogg B. W., “A Neural Net Modle-Based Multivariable Long-Range Predicitve Control Strategy Applied in Thermal Power Plant Control,” IEEE Trans. Energy Conversion, 13, 2, 176 (1998).25.Pröll, T. and Karim, M. N., “Model- Predictive pH Control Using Real-Time NARX Approach,” AIChE J., 2, 40, 269 (1994).26.Psichogios, D. C. and Ungar, L. H., “Direct and in Direct Model Based Control Using Artificial Neural Networks,” Ind. Eng. Chem. Res., 30, 2564 (1991).27.Ramasamy, S.; Deshpande, P. B.; Paxton, G. E. and Hajare, R. P., “Consider Neural Networks for Process Identification,” Hydrocarbon Processing, June, 59 (1995).28.Song, J. J. and Park, S., “Neural Model Predictor Control for Nonlinear Chemical Process,” J. Chem. Eng. Japan, 26, 347, (1993)29.Su, H. T. and McAvoy, T. J., “Integration of Multilayer Perceptron Networks and Linear Dynamic Models:A Hammerstein Modeling Approach,” Ind. Eng. Chem. Res., 32, 1927 (1993).30.Tsypkin, Y. Z.; Mason, J. D.; Avedyan, E. D.; Warwick, K. and Levin, I. K., “Neural Networks for Identification of Nonlinear Systems under Random Piecewise Polynomial Disturbances,” IEEE Trans. Neural Networks, 10, 2, 303 (1999).31.Yu, D. L.; Gomm, J. B. and Williams, D., “On-Line Predictive Control of a Chemical Process Using Neural Network Models,” in IFAC 14th Triennial World Congress, Beijing, P. R. China, 121 (1999).
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