跳到主要內容

臺灣博碩士論文加值系統

(44.220.62.183) 您好!臺灣時間:2024/03/01 18:39
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:羅見明
研究生(外文):Jamin Luo
論文名稱:主成份分析法輔助類神經網路之研究建立端銑表面粗糙度預測模型
論文名稱(外文):Using the principal component analysis assisted neural network in predicting of the surface roughness for end-milling operations (PCA-ANNIPSR)
指導教授:周永燦周永燦引用關係
指導教授(外文):Yt Jou
學位類別:碩士
校院名稱:中原大學
系所名稱:工業與系統工程研究所
學門:工程學門
學類:工業工程學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:中文
論文頁數:71
中文關鍵詞:端銑表面粗糙度主成份分析法類神經網路
外文關鍵詞:the principal component analysisNeural Networkend-millingsurface roughness
相關次數:
  • 被引用被引用:2
  • 點閱點閱:188
  • 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
表面粗糙度是端銑加工中重要品質指標之一,一般而言,手工量測浪費了許多時間與成本,如何使製程自動調整參數? 就可以解決時間與成本浪費問題,過去有許多研究開始解決此問題,同時也顯示端銑加工中表面粗糙度受到切削速度、切削深度、進給速率等加工參數的影響。因此,在要求效率與品質的前提下,如何能使製程自我學習,事先掌握加工結果的預測以及加工參數的線上自動調整,確有其必要性。
在過去文獻中只考量端銑製程參數是不夠的,本研究將應力因子列入考量。為此,力量檢知器被使用在監控這不易控制的切削系統中,以增加表面粗糙度控制的準確度。從觀察發現,一個適當的切削力量信號是在XY平面的平均端點力量(Fap_xy軸)和Z軸力量絕對值(Fa_z軸)的交互作用。這兩種力量表現在表面粗糙度中關係密切,證明了切削刀具對粗糙度的影響和切削力與粗糙度之間的關係。實驗中,利用表面粗糙度預測來調整製程參數,其精確度已經達到93%以上之結果。
為了精益求精,本研究以端铣加工之實驗數據,依照主成份分析法轉換加工參數成為類神經網路的訓練來源,透過類神經網路進行訓練與測試,最後利用未轉換數據訓練之結果來驗證本研究之績效,結果發現誤差函數MSE比原始數據小於4倍以上的差距,績效相當顯著。另外發現,若能將 5個變數以主成份分析轉變後輸入比少於5個變數(降維處理) 以主成份分析轉變後輸入之誤差函數MSE更小。
Surface roughness is an important indicator of the quality of machined parts. Commonly, manual technique of direct measurement is utilized to assess surface roughness and part quality, which is found to be very time-consuming and costly. How can the surface roughness prediction and machining parameters automatic control? For that reason, this research develop to solve problems and in the end-milling; the Surface roughness is a common quality characteristic which is affected by factors such as spindle speed, feed rate, and depth of cut. So with the goal of improving efficiency and processing quality, how can we develop a prediction model that will by necessity automatically adjust the parameters?
In the past, the research only considers whether the processing parameters are not enough. For that reason, the dynamometer sensor was used to monitor the uncontrolled cutting tool conditions to increase the accuracy of the surface roughness control. An empirical approach was applied to discover the proper cutting force signals, the average resultant peak force in XY plane (Fap) and the absolute average force in the Z direction (Faz). These two forces were employed to represent the uncontrollable cutting tool conditions for surface roughness control. A statistical method was employed to prove that the cutting tools could influence the surface roughness, and obtain the correlation between surface roughness and the cutting force signals. The accuracy of MSE was well in advance of 93 %.
However the goal of this research is to continuously keep improving the result. So in order to foster continual improvement, data collected from a manufacturing plant was utilized and treated with principle component analysis (PCA) to develop input variables for input to the neural network. This process is able to train the system to improve its predictive ability. Results provided from the original literature are used for comparison to prove the performance improvements of this research. As a result of this research it was discovered the predictive ability could be improved resulting in a 5 fold reduction of MSE. This is an obvious improvement. Another discovery is that in utilizing PCA developed input variables, input of five variables in comparison to four or less results in a lower MSE.
摘要 I
ABSTRACT II
誌謝辭 III
目錄 IV
表目錄 VII
圖目錄 VIII
附錄 IX
第一章、緒論 1
1.1研究背景 1
1.2研究動機 2
1.3研究目的 2
1.4研究方法與研究流程 3
1.5研究範圍與限制 3
1.6論文架構 3
第二章文獻探討 6
2.1CNC設備之機器控制單元(MCU) 6
2.2設備動態(MACHINING DYNAMIC) 6
2.3表面特性(SURFACE CHARACTERISTICS) 8
2.4檢知技術(SENSING TECHNOLOGY) 9
2.5在銑削工序中的切割力和表面粗糙度的關係 10
2.6多變量分析 12
2.7主成份分析法理論與模式 12
2.8類神經網路(ARTIFICIAL NEURAL NETWORK;ANN) 15
2.8.1類神經網路基本概念 16
2.8.2類神經網路在表面粗糙度預測模型的應用 17
2.8.3類神經網路模式理論與系統架構 18
2.8.4類神經網路模式 19
2.8.5倒傳遞類神經 22
2.9參考文獻小結 24
第三章研究方法與步驟 26
3.1硬體設計(HARDWARE SETUP) 26
3.2軟體設定(SOFTWARE SETUP) 27
3.2.1相關軟體說明 27
3.3實驗設計 28
3.4方法總結(SUMMARY OF METHODOLOGIES) 29
3.5主成份分析法突顯變數之間共同解釋變異量 30
3.5.1主成份分析之步驟與結果 31
3.6類神經網路模式之建構 32
3.6.1網路模式選擇 32
3.6.2網路參數設定 33
3.6.3決定終止條件 33
3.6.4類神經網路設計與資料訓練 34
3.6.5確定訓練及測試樣本的筆數 34
3.6.6網路參數設定 34
第四章研究結果 39
第五章結論、貢獻與未來研究方向 43
參考文獻 44
附錄 56


表目錄

表1檢知器比較表 10
表2網路學習策略 20
表3類神經網路預測模式 21
表4倒傳遞類神經架構 22
表5特徵值共相關矩陣分析(Eigenanalysis of the Correlation Matrix) 31
表6訓練和測試組之數量比各為300:84與192:192之訓練比較 40
表7同一條件下,選擇LOGSIG與TANSIG函數進行類神經網路訓練比較 40
表8同一條件下,選擇隱藏層數量1,2,3進行類神經網路訓練比較 40
表9同一條件下,選擇隱藏層中神經結點點1 ,5,10進行類神經網路訓練比較 40
表10條件實驗小結 41
表11原始數據與主成份轉換數據比較表 41
表12主成份轉換數據累積成份比較表 42
表13原始數據降維處理比較表 42
表14主成份分析參數降維後比較 42
表15主成份分析實驗小結 43


圖目錄
圖1研究架構流程圖 5
圖2圓周銑削Peripheal milling[ 13] 8
圖3端銑End milling[ 13] 8
圖4表面結構剖面圖[27] 9
圖5端銑系統之鐘擺路徑 [35] 11
圖6端銑系統中表面產生方式[35] 12
圖7生物神經元模型[1] 16
圖8人工神經元模型[1] 17
圖9前向式網路架構[43] 21
圖10回饋式網路架構[43] 21
圖11前饋系統結構structure of a feedforward 2-3-2 neural networks [24] 23
圖12倒傳遞關鍵操作Key operation of BP[4] 23
圖13邏輯函數Logistic function[4] 24
圖14硬體設計示意圖 26
圖15主成份輔助類神經網路流程圖 30
圖16特徵值陡坡圖 32
圖17參數設定圖 38
圖 18均方誤差(MSE)績效圖 38


附錄

附錄1原始參數輸入後之表面粗糙度預測值 56
附錄2主成份轉換變數之300個抽樣訓練樣本 58
附錄3 原始5個數據輸入之類神經網路 59
附錄4 主成份轉換5個參數輔助類神經網路 61
[1]李柏甫,(2004),TFT-LCD濺鍍製程之智慧型診斷系統發展,國立成功大學製造工程研究所碩士論文。
[2]葉怡成,(2000),類神經網路模式應用與實作,儒林圖書公司。
[3]葉怡成,(2002),應用類神經網路,儒林書局有限公司。
[4]羅華強,(2008),類神經網路-MATLAB的應用,高立圖書有限公司,台北。
[5]Blessing G. V., Slotwinski, J. A. Eitzen, D. G. & Ryan, H. M. (1993). Ultrasonic measurements of surface roughness. Applied Optics, Vol. 32, No. 19, pp. 3433-3437.
[6]Bregler, C. and Omohundro, S. M. (1994). Surface learning with applications to lip-reading, Morgan Kaufmann Publishers, 43-50.
[7]Chang, S. I. and Aw, C. A. (1996). A neural fuzzy control chart for detecting and classifying process means shifts, International Journal of Production Research, 34, 2265-2278.
[8]Cheng, C. S. (1995). A multi-layer neural network model for detecting changes in the process mean, Computers and Industrial Engineering, 28, 51-61.
[9]Chen, J. and Liao, C. M. (2002). Dynamic process fault monitoring based on neural network and PCA, Journal of Process Control, 12, 277-289.
[10]Chen, Y. M. and Lee, M. L. (2002). Neural networks-based scheme for system failure detection and diagnosis, Mathematics and Computers in Simulation, 58, 101-109.
[11]Cherian, R. P., Smith, L. N. and Midha, P. S. (2000). A neural network approach for selection of power metallurgy materials and process parameters, Artificial Intelligence in Engineering, 14, 29-44.
[12]Cui, X. & Shin, K. G. (1993). Direct control and coordination using neural networks. IEEE Trans. System, Man, and Cybernation. Vol. 23, No. 3, pp. 686-697.
[ 13]DeGarmo E. P., Black J. T. & Kohser R. A. (1997). Materials and processes in manufacturing-8th edition. NJ: Prentice Hall.
[14]Dornfield, D. A. & Fei, R. Y. (1986). In-process surface finish characterization. Manufacturing Simulation Processes, Vol. 20, pp. 191-204.
[15]El-Mounayri, H.a; Kishawy, H.b; Briceno, J.a. (2005). Optimization of CNC ball end milling: a neural network-based model, Journal of Materials Processing Tech. Vol: 166, pp. 50-62
[16]Elbestawi, M. A., Ismail, F. & Yuen, K. M. (1994). Surface topography characterization in finish milling. Int. J. Mach. Tools Manufact.. Vol. 34, No. 2, pp. 245-255.
[17]Fuh, K. H. & Wu, C. F. (1995). A proposed statistical model for surface quality prediction in end-milling of Al alloy. Int. J. Mach. Tools Manufacture... Vol. 35, No. 8, pp. 1187-1200.
[18]Hemerly, E. M. & Nascimento, C. L. (1999). An NN-based approach for tuning servocontrollers. Neural Networks, Vol. 12, pp. 513-518.
[19]Hush, D. R., and Horne, B. G., 1993, Progress in supervised neural network: what’s new since lippmann, IEEE Signal Processing Magine, January, 8-39.
[20]Ismail, F., Elbestawi, M. A., Du, R. & Urbasik, K. (1993). Generation of milled surface including tool dynamics and wear. Journal of Engineering for Industry, Vol. 115, pp. 245-252.
[21]Inasaki I. (1985). In-process measurement of surface roughness during cylindrical grinding process. Precision Engineering, Vol. 7, No. 2, pp. 73-76.
[22]Jackson, J. E., (1980), Principal components and factor analysis: part Ⅰ- principal components, Journal of Quality Technology, 12, 201-213.
[23]Jackson, J.E., and Mudholkar, G. S., (1979), Control procedures for residuals associated with principal component analysis, Technometrics, 21, 341-349.
[24]Jang, J. S., Sun, C. T. & Mizutani, E. (1997). Neuro-Fuzzy and Soft Computing. NJ: Prentice Hall.
[25]Johnson, R. A. and Wichern, D. W., (2002), Applied Multivariate Statistical Analysis, 5th ed., Prentice Hall, New Jersey.
[26]Jung, C. Y. & Oh, J. H. (1991). Improvement of surface waviness by cutting force control in milling. Int. J. Mach. Tools Manufacture... Vol. 31, No. 1, pp. 9-21.
[27]Kalpakjian S. (1995). Manufacturing Engineering and Technology, 3rd edition. NY: Addison-Wesley.
[28]Landau, I. D. & M’Saad M. (1998). Adaptive control. NY: Springer
[29]Li, S. & Elbestawi, M. A. (1996). Tool condition monitoring in machining by fuzzy neural networks. Journal of Dynamic Systems, Measurement, and Control, Vol. 118, pp. 665-672.
[30]Lin, S.C. (1994). Computer numerical control-from programming to networking. NY: Delmar.
[31] Lou, S. J. (1997). Development of four in-process surface recognition systems to predict surface roughness in end milling. Doctoral dissertation, IA: Iowa State University

[32] Lou, M. S. & Chen, J. C. (1999). In-process surface roughness recognition system in end-milling operations. International Journal of Advanced Manufacturing Technology, Vol. 15, pp. 200-209.
[33] MacGregor, J. F., (1990), A different view of the funnel experiment, Journal of Quality Technology, 22, 255-259.
[34] MacGregor, J. F., Jaeckle, C., Kiparissides, C. and Koutoudi, M., (1994), Process monitoring and diagnosis by multiblock methods, American Institute of Chemical Engineering Journal, 40, 826-838.
[35] Martelloti, M. E. (1941), An analysis of the milling process. Transactions of the ASME, Vol. 63, pp. 677-700.
[36] Melkote, S. N. & Thangaraj, A. R. (1994). An enhanced end milling surface texture model including the effects of radial rake and primary relief angles. Journal of Engineering for Industry, Vol. 116, pp. 166-174.
[37] Misra, M., Yue, H. H.,Qin, S. J. and Ling, C., (2002), Multivariate process monitoring and fault diagnosis by multi-scale PCA, Computers and Chemical Engineering, 26, 1281-1293.
[38] Mou, J. (1997). A method of using neural networks and inverse kinematics for machine tools error estimation and correction. Journal of Manufacturing Science and Engineering, Vol. 119, pp. 247-254.
[39]Oktem, Hasana; Erzurumlu, Tuncayb; Erzincanli, Fehmib (2006).Prediction of minimum surface roughness in end milling mold parts using neural network and genetic algorithm, Materials and Design ,Vol: 27, pp. 735-744
[40]Raksiri, Chanaa; Parnichkun, Manukida(2004), Geometric and force errors compensation in a 3-axis CNC milling machine, International Journal of Machine Tools and Manufacture Vol: 44, pp. 1283-1291
[41]Raich, A. and Cinar, A., (1996), Statistical process monitoring and disturbance diagnosis in multivariable continuous process, American Institute of Chemical Engineering Journal, 42, 995-1009.
[42] Roverso, D., (2000), Soft computing tools for transient classification, Information Sciences, 127, 137-156.
[43] Po-Tsang Bernie Huang.(2002).A neural networks-based in-process adaptive surface roughness control (NN-IASRC) system in end-milling operations. Copyright © Wilbur Terrance Johnson, (2002). All rights reversed. Graduate College Iowa State University
[44] Smith, S. & Tlusty, J. (1991). An overview of modeling and simulation of the milling process. Journal of Engineering for Industry, Vol. 113, pp. 169-175.
[45] Stark, G. A. & Moon, K. S. (1999). Modeling surface texture in the peripheral milling process using neural network, spline, and fractal methods with evidence of chaos. Journal of Engineering for Industry, Vol. 121, pp. 251-256.
[46] Susic, E. & Grabec, I. (1995). Application of a neural network to the estimation of surface roughness from AE signals generated by friction process. . Int. J. Mach. Tools Manufact.. Vol. 35, No. 8, pp. 1077-1086.
[47] Takeyama, H., Sekiguchi, H., Murata, R. & Matsuzaki, H. (1976). In-process detection of surface roughness in machining. Annals of the CIRP, Vol. 25, No. 1, pp. 467-471.
[48] Tarng,Y. S. & Lee, B. Y. (1993). A sensor for the detection of tool breakage in NC milling,” Journal of Materials Processing Technology, Vol. 36, pp.259-272.
[49] Tsai, Y., Chen, J. C., & Lou, M. S. (1999). In-process surface recognition system based on neural networks in end milling operations. Int. J. Mach. Tools Manufact., Vol. 39, pp. 583-605.
[50] Williams, R. J. and Zipser, D., (1989), A learning algorithm for continually running fully recurrent neural networks, Neural Computation, 1, 271-279.
[51]Wang, X. Chen, P. Tansel, I.N. A, Yenilmezb, Transformations in machining. Part 1. enhancement of wavelet transformation neural network (WT-NN) combination with a preprocessor, International Journal of Machine Tools and Manufacture Vol: 46, pp. 36-42
[52] You, S. J. & Ehmann, K. F. (1991). Synthesis and generation of surface milled by ball nose end mills under tertiary cutter motion. Journal of Engineering for Industry, Vol. 113, pp. 17-24.
[53]Yoon, Moon-Chula; Kim, Young-Gukb(2007), Chatter stability boundary analysis using RBNN, Journal of Materials Processing Tech. Vol: 184, pp. 251-256
[54]Zuperl, U.a; Cus,F (2004), Tool cutting force modeling in ball-end milling using multilevel perceptron, Journal of Materials Processing Tech. Vol: 153-154, Complete , pp. 268-275
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊