智慧型基因演算法在粗糙度的建模與預測

Intelligent genetic algorithm (IGA) for modeling and prediction of surface roughness

梁宏維(Hung-Wei Liang)

指導教授 ： 何信璋

國立虎尾科技大學/工程學院/機械與機電工程研究所/碩士(2009年)

摘要

在本論文中，IGA的高性能主要是合併傳統基因演算法(GA)和以直交實驗設計為基礎的智慧型交配機制來提升其搜尋能力。使用直交表可以同時分析數個因子，用n次實驗加以分析後便可推論出最佳解的組合方式，可以有效探索2n的實驗空間組合。
由於在製造業對於表面粗糙度的重視，它是用來評估端銑加工上工件品質的準則。例如在表面密封、滾珠軸承、齒輪、凸輪或軸頸等應用場合，表面粗糙度對於設備的功能影響很大。而本文中智慧型基因演算法(IGA)配合模糊神經網路(FNN)是用來預測工件端銑加工的表面粗糙度。IGA是GA配合直交實驗設計的智慧型演算法，可有效推理出近似最佳解。本文建模使用前人文獻中的125組訓練數據、18組驗證數據，使用FNN架構，總共有50個模型參數。由實驗結果得知，以FNN的架構配合IGA來搜尋最好的FNN模型參數，能夠準確的預測出誤差較小的表面粗糙度，並且優於前人文獻及MATLAB的ANFIS 方法所預測出來的結果。因此本方法能夠有效地提升預測的精準度，來達到更接近預期粗糙度目標的加工。MATLAB 是屬於高階的程式語言，有許多內建函數可以應用於工程領域，方便使用者進行開發，但是在執行迴圈效率並沒有很高，所以利用C語言之優點來改善MATLAB需大量計算的子程序，提升程式運行效率。

關鍵字

智慧型基因演算法(IGA) ； 粗糙度 ； 模糊神經網路(FNN) ； 直交實驗設計

並列摘要

In this dissertation, high performance in IGA arises mainly from intelligent crossover based on orthogonal experimental designs. Using OED with both orthogonal array (OA) and factor analysis, it can analyze the effect of several factors simultaneously.
Accurate estimation of surface roughness of workpieces in turning operations play an important role in the manufacturing industry. It is used to assess the workpiece in the end milling process of performance criterion. For example：surface seals, ball bearing, gear, cam and journal. Surface roughness has very great impact for the equipment. In this paper, Intelligent Genetic Algorithm(IGA) with Fuzzy Neural Network(FNN) is used to model and predict the workpiece surface roughness for the end milling process. IGA is powerful by using the Orthogonal Experimental Design’s algorithm. It can effectively reason to near-optimal solutions. In this paper, the model of the FNN uses previously researcher’s 125 training data and 18 validation data. There are 50 parameters to be optimized. Experimental results show that IGA with FNN model can improve the accuracy of modeling and prediction, and outperforms the ANFIS methods by MATLAB and reported recently in the literature. We use MATLAB and built C++ complied function in our application for improving computation time.

並列關鍵字

Intelligent Genetic Algorithm (IGA) ； Roughness ； Fuzzy Neural Networks (FNN) ； Orthogonal Experimental Design(OED)

參考文獻

[1] S.-Y. Ho, C,-C. Liu, and S. Liu, “Design of an Optimal Nearest Neighbor Classifier Using an Intelligent Genetic Algorithm,” Pattern Recognition Letters, vol. 23, no. 13, pp. 1495-1503, May 2002.

[2] S.-Y. Ho, S.-J. Ho, and T.-K. Chen, “Design of High Performance Fuzzy Controllers Using Flexible Parameterized Membership Functions and Intelligent Genetic Algorithms,” International Journal JSME Series C, vol. 46, no. 1, pp. 252-262, 2003.

[3] Shinn-Ying Ho, Li-Sun Shu, Jian-Hung Chen, “Intelligent Evolutionary Algorithms for Large Parameter Optimization Problems”, Evolutionary Computation, IEEE, pp. 522 -541, 2004.

[4] S.-J. Ho, S.-Y. Ho, M.-H. Hung, and L.-S. Shu, H.-L. Huang, “Designing Structure-Specified Mixed H2/H∞ Optimal Controllers Using an Intelligent Genetic Algorithm IGA,” IEEE Trans. Control Syst. Tech., vol. 13, no. 6, pp. 1119-1124, Nov. 2005.

[5] Li-Sun hu, “Orthogonal Experimental Design Based Evolutionary Algorithms and Their Applications to Optimal Designs,” Ph.D. thesis, 2004.