(3.238.174.50) 您好!臺灣時間:2021/04/20 22:48
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:余文宏
研究生(外文):Yu, Wen Hung
論文名稱:壓吸染色於浸軋製程中染色均勻性控制之研究
論文名稱(外文):The Study of Dyeing Uniformity Control in Pad-Batch of Padding Dyeing
指導教授:黃昌群
指導教授(外文):Huang, Chang Chiun
學位類別:博士
校院名稱:國立臺灣科技大學
系所名稱:高分子工程系
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:2004
畢業學年度:92
語文別:中文
論文頁數:113
中文關鍵詞:壓吸染色浸軋製程模糊控制類神經網路基因演算法
外文關鍵詞:Padding dyeingPad-batchFuzzy controlNeural networkGenetic algorithm
相關次數:
  • 被引用被引用:0
  • 點閱點閱:506
  • 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
壓吸染色是屬於連續染色的一種,浸軋工程為壓吸染色之重要程序,其影響染色之結果,基於浸軋工程於壓吸染色之重要性,本文主要針對浸軋工程中對於染色均勻度之影響來進行研究,其包含pH值之控制、壓輥荷重之控制、及染色瑕疵之自動檢測。
pH值控制主要是以連續染色及批次染色來進行。在連續染色時,所考量的是布匹經過前處理時帶有殘留鹼之情況,另考量補充浸軋槽之處理液時之pH值。而在批次染色時,主要是考量到溫度變化對pH值的影響。由於系統模式具有時變特性且不易求得,若以傳統固定增益法很難達到染液pH值控制,因此採用模糊增益表PID控制器染液pH值控制,因其具有自調性與強健性,在不需系統模式條件下,控制法則使用模糊規則與推理來自動調整PID增益值,為克服找尋增益值穩定範圍的困難,本文提出一個修正的方法,根據兩個實驗結果,證實所提出之控制器可成功應用於染色pH控制系統中。
不均一之壓力會發生染色瑕疵,因此控制壓輥接觸面之受力均一是很重要的,接觸面之壓力牽涉壓輥外觀及兩端荷重均一性。一般當壓輥未經過中高弧度之設計時,其兩端之壓力比中間大,因此本文採用兩物體接觸時變化量之理論來設計壓輥,而模擬結果說明壓輥外觀經由設計後,表面受力情形有較為均一之改善。而考量到兩端荷重控制之系統模式不易推得,因此採用傳統模糊控制來進行,在傳統模糊控制中,歸屬函數及模糊規則之設計是非常主觀的,常常無法得到很好之性能,因此藉由基因演算法之最佳化技術來歸屬函數而產生自調模糊控制器,經由實驗結果得知,自調模糊控制器所得之結果比傳統模糊控制佳。
應用影像處理及模糊類神經網路系統來分類浸軋工程中常見之色段、斑點、雲斑、油污、頭尾異色、布中異色及布邊異色等七種染色瑕疵。模糊類神經分類系統是以類神經網路為模糊推論機制之模糊專家系統所構成,類神經網路透過樣本之學習訓練成推論機制,模糊類神經網路系統為合併模糊邏輯及類神經網路,因此於圖形辨識與分類問題較具智慧,而影像是以區域成長直接檢測不同瑕疵區域,而以70個樣本(每個瑕疵有十個樣本)來學習與測試,實驗結果說明模糊類神經網路作法可藉由水平投射長度、垂直投射長度、灰階強度、邊界長度等四個特徵之選擇完全精確地辨識這些樣本。
Padding dyeing is one category of the continuous dyeing. Pad-batch is the most important process in padding dyeing, and affects the dyeing outcome. This study is aim at the dyeing uniformity in pad-batch, which includes the pH control, the loads control of padders, and automatic inspections of dyeing defects.
In pH control, two cases, simplified continuous dyeing and batch dyeing, are implemented in experiments. In continuous dyeing, the residual alkali in preparation and the pH of padding solution in padding trough are taken into account. In batch dyeing, the temperature change will affect the pH value. Conventional fixed gains are hard to achieve dyebath pH control, since it is difficult to model the process and the scheme is not adaptive to time-varying characteristics. Thus, a fuzzy gain-scheduled PID controller is adopted for dyebath pH control because of its self-adaptation and robustness. The control scheme uses fuzzy rules and reasoning to self tune PID gains without the need of modeling. A modification to overcome the difficulty in finding the ranges of gains for stability is proposed. The experiment results of two cases demonstrate that the proposed controller can be successfully applied in pH control of dyeing.
Uneven loads will result in dyeing defects. Therefore, maintaining contact loads in evenness becomes important. The contact loads in evenness can be achieved by aspect design and even two-end loads of padders. In general, the pressures at two ends are bigger than the center part when two rollers contact before aspects design. Crown design is proposed and two-body contact theorem is adopted in this study. The simulation results show that the pressures of the contact area trend to become even after design. The model is not easily acquired when controlling the evenness in two-end loads of padders. Therefore, the conventional fuzzy control is adopted. In conventional fuzzy control, membership functions and control rules are designed based on subjective criteria of a man. Very often, the design attempt may not lead to an excellent performance. Therefore, membership functions are tuned based on an optimization technique of genetic algorithms to yield self-tuning fuzzy control. The experiment results indicate that the self-tuning fuzzy controller is better than the conventional fuzzy controller in controlling the evenness of two-end of padder.
Classification of seven kinds of padding dyeing defects, filling band in shade, dye and carrier spots, mist, oil stain, tailing, listing, and uneven dyeing on selvage, is proposed using image processing and fuzzy neural network approaches. The fuzzy neural classification system is constructed by a fuzzy expert system with the neural network as a fuzzy inference engine. The neural network is trained to become the inference engine using sample data. The fuzzy neural network system possesses merits of both fuzzy logic and neural networks, and thus is more intelligent in handling pattern recognition and classification problems. Region growing is adopted to directly detect different defect regions in an image. Seventy samples, ten samples for each defect, are obtained for training and testing. The experiment results demonstrate that the fuzzy neural network approach can precisely classify these samples by four features of horizontal projection lengths, vertical projection lengths, intensity, and boundary length.
摘 要 I
Abstract II
誌 謝 IV
目 錄 V
符號表 VIII
圖索引 XI
表索引 XIV
第一章 緒論 1
1.1 前言 1
1.2 研究動機與目的 3
1.3 研究方法 6
第二章 浸軋製程之簡介 7
2.1 浸軋製程之原理 7
2.1.1 浸漬製程 9
2.1.2 壓吸製程 10
2.2 浸軋製程之瑕疵 12
第三章 控制理論 14
3.1 模糊邏輯控制理論 14
3.1.1 模糊化 15
3.1.2 知識庫 17
3.1.3 決策邏輯 23
3.1.4 解模糊化 26
3.2 PID控制理論 26
3.2.1 比例控制器 28
3.2.2 積分控制器 28
3.2.3 微分控制器 29
3.3 參數估測理論 29
3.4 倒傳遞類神經網路 32
3.4.1 前向計算 34
3.4.2 回傳調整 36
3.5 基因演算法 39
3.5.1 字串編碼與解碼 41
3.5.2 定義目標函數及評估性能指標 41
3.5.3 再生 43
3.5.4 交配 45
3.5.5 突變 45
3.5.6 取代 46
3.6 模糊增益自調PID控制 46
3.6.1 PID控制參數 47
3.6.2 模糊增益自調PID控制參數之設計 48
3.7 應用基因演算法自調模糊歸屬函數 54
3.7.1 自調模糊歸屬函數之參數設定 55
3.7.2 基因演算法求解步驟 56
3.8 模糊類神經網路系統 58
3.8.1 模糊化與解模糊化 60
3.8.2 類神經網路為推論機制 60
3.9 三維物體接觸表面之變形原理 60
第四章 理論驗證與實驗結果 64
4.1 應用模糊增益自調PID控制器於pH值控制 64
4.1.1 應用參數估測原理推導系統模式 65
4.1.2 控制器之設計 69
4.1.3 連續式染色之pH控制 72
4.1.4 批次式染色之pH控制 75
4.1.5 結果討論 78
4.2 壓輥荷重控制之探討 78
4.2.1 壓輥外觀之設計 79
4.2.2 壓輥兩端荷重均勻度之控制 85
4.2.3 結果討論 94
4.3 應用模糊類神經網路於染色瑕疵分類 95
4.3.1 染色瑕疵樣本擷取 96
4.3.2 影像分割 97
4.3.3 樣本特徵之分析 98
4.3.4 模糊類神經網路之應用 101
4.3.5 結果討論 104
第五章 結論 105
參考文獻 107
作者簡介 113
[1] Adams, R. and Bischof, L., “Seed Region Growing,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 16, No. 6, pp. 641-647 (1994).
[2] , K. J. and Wittenmark, B., Adaptive Control, Addison-Wesley, MA (1989).
[3] Batur, C. and Kasparian, V., “Predictive Fuzzy Expert Controllers,” Computers and Industrial Engineering, Vol. 20, pp. 199-209 (1991).
[4] Beck, K. R., Madderra, T. A., and Smith, C. B., “Real-Time Data Acquisition in Batch Dyeing,” Textile Chemist and Colorist, Vol. 23, pp. 23-27 (1991).
[5] Burley, R., Wai, P. C., and McGuire, G., “Process Engineering Approach to Dyeing Machinery - A study of Package Dyeing Machine Dynamics,” Chemical Engineering Research & Design, Vol. 65, pp. 505-513 (1987).
[6] Chan, H. C. and Yu, C. C., “Autotuning of Gain-Scheduled pH Control: An Experimental Study,” Industrial and Engineering Chemistry Research, Vol. 34, pp. 1718-1729 (1995).
[7] Revol, C. and Jourlin, M., ”A New Minimum Variance Region Growing Algorithm for Image Segmentation,” Pattern Recognition Letters, Vol. 18, pp. 249-258 (1998).
[8] Chao, C. T. and Teng, C. C., “A PD-Like Self-Tuning Fuzzy Controller Without Steady-State Error,” Fuzzy Sets and Systems, Vol. 87, pp. 141-154 (1997).
[9] Chen, P. W., Liang, T. C., Yau, H. F., Sun, W. L., Wang, N. C., Lin, H. C. and Lien, R. C., “Classifying Textile Faults with a Back-Propagation Neural Network Using Power Spectra,” Textile Research Journal, Vol. 68, No. 2, pp. 121-126 (1998).
[10] Gen, M. and Cheng, R., Genetic Algorithms and Engineering Design, John Wiley & Sons, NY (1997).
[11] Gonzalez, R. C. and Woods, R. E., Digital Image Processing, Addison-Wesley, NY (1993).
[12] Goodwin, G. C. and Sin, K. S., Adaptive Filtering Prediction and Control, Prentice-Hall, NJ (1984).
[13] Gore, D. C., “Practical Experiences in Garment Dyeing: Problems and Solutions,” Textile Chemist and Colorist, Vol. 27, No. 3, pp. 37-40 (1995).
[14] , H. B., “A Genetic-Algorithm-Based Method for Tuning Fuzzy Logic Controllers,” Fuzzy Sets and Systems, Vol. 108, pp. 39-47 (1999).
[15] He, W., Zhang, Y. F., Lee, K. S., Fuh, J. Y. H., and Nee, A. Y. C., “Automated Process Parameter Resetting for Injection Moulding: A Fuzzy-Neuro Approach,” Journal of Intelligent Manufacturing, Vol. 9, pp. 17-27 (1998).
[16] Herrera, F., Lozano, M., and Verdegay, J. L., “Tuning Fuzzy Logic Controllers by Genetic Algorithms,” International Journal of Approximate Reasoning, Vol. 12, pp. 299-315 (1995).
[17] Homaifar, A., Qi, C. X., and Lai, S. H., “Constrained Optimization Via Genetic Algorithm,” Simulation, Vol. 62, pp. 242-254 (1994).
[18] Huang, C. C. and Yu, W. H., “Application of a Fuzzy Gain-Scheduled PID Controller to Dyebath pH,” Textile Research Journal, Vol. 71, No. 12, pp. 1074-1078 (2001).
[19] Huang, C. C. and Yu, W. H., “Control of Dye Concentration, pH, and Temperature in Dyeing Processes,” Textile Research Journal, Vol. 69, No. 12, pp. 914-918 (1999).
[20] Huang, C. C. and Yu, W. H., “Fuzzy-Neural Network Approach to Classifying Dyeing Defects,” Textile Research Journal, Vol. 71, No. 2, pp. 100-104 (2001).
[21] Huang, C. C., Su, C. Y., and Yu, W. H., “Self-Tuning pH Control in Dyeing,” Textile Research Journal, Vol. 70, No. 3, pp. 195-200 (2000).
[22] Jang, R. J.-S., “ANFIS: Adaptive-Network-Based Fuzzy Inference System,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 23, pp. 665-685 (1993).
[23] Ju, Y. and Zhang L., “A Full Numerical Solution for the Elastic Contact of Three-Dimensional Real Rough Surfaces,” Wear, Vol. 157, pp. 151-161 (1992).
[24] Karr, C. L. and Gentry, E. J., “Fuzzy Control of pH Using Genetic Algorithms,” IEEE Transactions on Fuzzy Systems, Vol. 1, pp. 46-53 (1993).
[25] Klir, G. J. and Yuan, B, Fuzzy Sets and Fuzzy Logic, Prentice-Hall, NJ, (1995).
[26] Kulkarni, A. D., “Neural-Fuzzy Models for Multispectral Image Analysis,” Applied Intelligence, Vol. 8, pp. 173-187 (1998).
[27] Lee, C. C., “Fuzzy Logic in Control Systems: Fuzzy Logic Controller, Part I,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 20, pp. 404-418 (1990).
[28] Lee, C. C., “Fuzzy Logic in Control Systems: Fuzzy Logic Controller, Part II,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 20, pp. 419-435 (1990).
[29] Li, H. X. and Gatland, H. B., “A New Methodology for Designing a Fuzzy Logic Controller,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 25, pp. 505-512 (1995).
[30] Liang, X. and Linqing, Z., “A Numerical Model for the Elastic Contact of Three-Dimensional Real Rough Surfaces,” Wear, Vol. 148, pp. 91-100 (1991).
[31] Lin, C. T. and Lee, C. S. G., Neural Fuzzy Systems, Prentice-Hall, NJ, (1996).
[32] Ljung, L. and Gunnarsson, S., “Adaptation and Tracking in System Identification - A Survey,” Automatica, Vol. 26, No. 1, pp. 7-21 (1990).
[33] McAvoy, T. J., “Time Optimal Control and Ziegler-Nichols Control,” Industrial and Engineering Chemistry Process Design and Development, Vol. 11, No. 1, 1972, pp. 71-78.
[34] McAvoy, T. J., Hsu, E. and Lowenthal, S., “Dynamics of pH in Controlled Stirred Tank Reactor,” Industrial and Engineering Chemistry Process Design and Development, Vol. 11, No. 1, pp. 68-70 (1972).
[35] Menzl, S., , M., and Bens, R., “A Self Adaptive Computer-Based pH Measurement and Fuzzy-Control System,” Water Research, Vol. 30, No. 4, pp. 981-991 (1996).
[36] Ogata, K., Discrete-Time Control Systems, Prentice-Hall, NJ, (1995).
[37] Ogata, K., Modern Control Engineering, Prentice-Hall, NJ, (1990).
[38] Pal, S. K. and Ghosh, A., “Neuro-Fuzzy Computing for Image Processing and Pattern Recognition,” International Journal of Systems Science, Vol. 27, pp. 1179-1193 (1996).
[39] Park, D., Kandel, A., and Langholz, G., “Genetic—Based New Fuzzy Reasoning Models with Application to Fuzzy Control,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 24, pp. 39-47 (1994).
[40] Park, J., A Practical Introduction to Computer Colour Matching, Dymatecs Limited, U. K. (1989).
[41] Perkins, W. S., Textile Coloration and Finishing, Carolina Academic Press (1996).
[42] Sette, S., Boullart, L. and Kiekens, P., “Self-Organizing neural Nets: A New Approach to Quality in Textiles,” Textile Research Journal, Vol. 65, No. 4, pp. 196-202 (1995).
[43] Sung, S. W. and Lee, I. B., “pH Control Using an Identification Reactor,” Industrial and Engineering Chemistry Research, Vol. 34, pp. 2418-2426 (1995).
[44] Tang, K. L. and Mulholland, R. J., “Comparing Fuzzy Logic with Classical Controller Designs,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 17, No. 6, pp. 1085-1087 (1987).
[45] Timoshenko, S. P. and Goodier, J. N., Theory of Elasticity, McGraw-Hill, NY (1970).
[46] Tsai, I. S., Lin, C. H., and Lin, J. J., “Applying an Artifical Neural Network to Pattern Recognition in Fabric Defects,” Textile Research Journal, Vol. 65, No. 3, pp. 123-130 (1995).
[47] Wang, X. and Bide, M., “Factors Affecting the Levelness of Dyeing in Reused Acid Dyebaths for Nylon,” Textile Chemist and Colorist, Vol. 30, No. 4, pp. 45-52 (1998).
[48] Woodard, S. E. and Garg, D. P., “A Numerical Optimization Approach for Tuning Fuzzy Logic Controllers,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 29, pp. 565-569 (1999).
[49] Wu, J. C. and Liu, T. S., “Fuzzy Control of Rider-Motorcycle System Using Genetic Algorithm and Auto-Tuning,” Mechatronics, Vol. 5, pp. 441-455 (1995).
[50] Zadeh, L. A., “Fuzzy sets,” Information and Control, Vol. 8, No. 3, pp. 338-353 (1965).
[51] Zhang, Y. F. and Bresee, R. R., “Fabric Defect Detection and Classification Using Image Analysis,” Textile Research Journal, Vol. 65, No. 1, pp. 1-9 (1995).
[52] Zhao, Z. Y., Tomizuka, M., and Isaka, S., “Fuzzy Gain Scheduling of PID Controllers,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 23, No. 5, pp. 1392-1398 (1993).
[53] Zurada, J. M., Introduction to Artificial Neural Systems, West, NY, (1992).
[54] 邱永亮, 魏盛德, 劉泰庠, “染色化學”, 徐氏基金會出版, (1980).
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊
 
系統版面圖檔 系統版面圖檔