臺灣博碩士論文加值系統

Searching optimum problem is very important in engineering field. There are many methods to solve this problem but no one can assure that the optimum found is the global optimum. We can only have a conclusion that one method can find a better optimum solution than another method. One conventional approach to find optimum is Taguchi method which was applied very widely and successfully in many disciplines. Another approach is Neurogenetic method which includes artificial neural network and genetic algorithm. This method has emerged as a very effective and powerful method to search optimum solution. The purpose of this study is to compare the conventional method with the new method in finding optimum design and calculating contribution of each factor. Thus, these two methods were applied for finding optimal solution of the lag screw which plays a very important role in curing patients. Because the lag screw needs bending strength which resists breakage and pullout strength which resists loosening, the two methods were exploited to find optimal solution for each bending case and pullout case separately.
From the results, the optimum found by Neurogentic method is better than the optimum found by Taguchi method, especially in the bending case which is the more complex case compared to pullout case. It means that the more complicated relationship between factors and response the better optimum solution can be found by Neurogenetic method compared to Taguchi method. Besides, using artificial neural network, the contribution of each factor could be calculated by Modified Profile method and the results were similar to the contribution calculated by analysis of variance in Taguchi method.
This study is an objective suggestion for engineers in choosing method to find the optimum solution. The Taguchi method should be applied if the case is simple because the Taguchi method is systematic, simple and easy to achieve the result. The Neurogenetic method should be applied if the case is complex because using Neurogenentic method can obtain better optimum solutions. It is a notice that if the artificial neural network is well-trained, the Neurogenetic can be very powerful and can be applied in many situations, like: multi-objective optimization.

Chapter 1 Introduction 1
1.1 Motive 1
1.2 Taguchi Method 2
1.2.1 Calculating Optimum Designs in Taguchi Method 3
1.2.2 Analysis of Variance 4
1.3 Neurogenetic Method 4
1.3.1 Artificial Neural Network 5
1.3.2 Genetic Algorithm 6
1.3.3 Searching Optimums with Neurogenetic Method 7
1.3.4 Calculating the Contribution by Artificial Neural Network 8
1.4 Lag Screw 9
1.5 Literature Review 12
1.6 Structure of Dissertation 20
Chapter 2 Materials and Methods 21
2.1 Finite Element Analysis 21
2.2 Searching Optimal Designs 24
2.2.1 Taguchi Method 24
2.2.2 Neurogenetic Method 27
2.2.2.1 Training an Artificial Neural Network 27
2.2.2.2 The Hybrid of Artificial Neural Network with Genetic Algorithm 36
2.3 Calculating the Contribution 42
2.3.1 Analysis of Variance in Taguchi Method 42
2.3.2 Using Artificial Neural Network for Calculating the Contribution 44
2.3.2.1 Profile Method 44
2.3.2.2 Modified Profile Method 45
Chapter 3 Results 47
3.1 Optimum Design Results 47
3.1.1 Taguchi Method 47
3.1.1.1 Bending Case 47
3.1.1.2 Pullout Case 49
3.1.2 Neurogenetic Method 51
3.1.2.1 Bending Case 52
3.1.2.2 Pullout Case 70
3.1.3 Comparison of Optimum Designs 88
3.2 Calculating the Contribution Resutls 94
3.2.1 Analysis of Variance Results 94
3.2.1.1 Bending Case 94
3.2.1.2 Pullout Case 94
3.2.2 The Contribution by Using Artificial Neural Network Results 94
3.2.2.1 Profile Method 94
3.2.2.1.1 Bending Case 95
3.2.2.1.2 Pullout Case 95
3.2.2.2 Modified Profile Method Results 96
3.2.2.2.1 Bending Case 96
3.2.2.2.2 Pullout Case 96
3.2.3 Comparison of Contributions 97
Chapter 4 Discussion 99
Chapter 5 Conclusions and Future Works 102
References 104

[1]Barrado, E., Vega, M., Pardo, R., Grande, P., and Del Valle, J. L., "Optimisation of a purification method for metal-containing wastewater by use of a Taguchi experimental design," Water Research, vol. 30, pp. 2309-2314, 1996.
[2]Chiang, K.-T., "Optimization of the design parameters of Parallel-Plain Fin heat sink module cooling phenomenon based on the Taguchi method," International Communications in Heat and Mass Transfer, vol. 32, pp. 1193-1201, 2005.
[3]Khoei, A. R., Masters, I., and Gethin, D. T., "Design optimisation of aluminium recycling processes using Taguchi technique," Journal of Materials Processing Technology, vol. 127, pp. 96-106, 2002.
[4]Kim, K. D., Choi, D. W., Choa, Y.-H., and Kim, H. T., "Optimization of parameters for the synthesis of zinc oxide nanoparticles by Taguchi robust design method," Colloids and Surfaces A: Physicochemical and Engineering Aspects, vol. 311, pp. 170-173, 2007.
[5]Venkata Mohan, S., Sirisha, K., Sreenivasa Rao, R., and Sarma, P. N., "Bioslurry phase remediation of chlorpyrifos contaminated soil: Process evaluation and optimization by Taguchi design of experimental (DOE) methodology," Ecotoxicology and Environmental Safety, vol. 68, pp. 252-262, 2007.
[6]Yang, W. H. and Tarng, Y. S., "Design optimization of cutting parameters for turning operations based on the Taguchi method," Journal of Materials Processing Technology, vol. 84, pp. 122-129, 1998.
[7]Yusoff, N., Ramasamy, M., and Yusup, S., "Taguchi's parametric design approach for the selection of optimization variables in a refrigerated gas plant," Chemical Engineering Research and Design, vol. In Press, Corrected Proof, 2010.
[8]Zhang, J. Z., Chen, J. C., and Kirby, E. D., "Surface roughness optimization in an end-milling operation using the Taguchi design method," Journal of Materials Processing Technology, vol. 184, pp. 233-239, 2007.
[9]Hsu, C.-C., Lin, J., and Chao, C.-K., "Comparison of multiple linear regression and artificial neural network in developing the objective functions of the orthopaedic screws," Computer Methods and Programs in Biomedicine, vol. In Press, Corrected Proof, 2010.
[10]Kuzmanovski, I. and Aleksovska, S., "Optimization of artificial neural networks for prediction of the unit cell parameters in orthorhombic perovskites. Comparison with multiple linear regression," Chemometrics and Intelligent Laboratory Systems, vol. 67, pp. 167-174, 2003.
[11]Altan, M., "Reducing shrinkage in injection moldings via the Taguchi, ANOVA and neural network methods," Materials & Design, vol. 31, pp. 599-604, 2010.
[12]Schollhorn, W. I., "Applications of artificial neural nets in clinical biomechanics," Clinical Biomechanics, vol. 19, pp. 876-898, 2004.
[13]Ozcelik, B. and Erzurumlu, T., "Comparison of the warpage optimization in the plastic injection molding using ANOVA, neural network model and genetic algorithm," Journal of Materials Processing Technology, vol. 171, pp. 437-445, 2006.
[14]Panneerselvam, K., Aravindan, S., and Noorul Haq, A., "Hybrid of ANN with genetic algorithm for optimization of frictional vibration joining process of plastics," The International Journal of Advanced Manufacturing Technology, vol. 42, pp. 669-677, 2008.
[15]Sheu, J.-J. and Chen, C.-Y., "An Integration Method of Artificial Neural Network and Genetic Algorithm for Structure Design of a Scooter," Intelligent Computing, vol. 4113, pp. 655-662, 2006.
[16]Fowlkes, W. Y., Engineering Methods For Robust Product Design, Using Taguchi Methods in Technology and Product Development Addison-Wesley Publishing company, 1998.
[17]Jain, A. K., Mao, J., and Mohiuddin, K. M., "Artificial Neural Networks: A Tutorial " in IEEE, ed, 1996.
[18]"Neural networks: A requirement for intelligent systems," in http://www.learnartificialneuralnetworks.com/, ed.
[19]"Feed-forward networks " in http://www-cs-faculty.stanford.edu/~eroberts/courses/soco/projects/2000-01/neural-networks/Architecture/feedforward.html, ed.
[20]마유승, 김., "Genetic Algorithm/Programming," in ai.kaist.ac.kr/~jkim/cs570-2000/Lectures/GA.ppt, ed.
[21]Bouten, I. W., "Applications of Artificial Neural Networks in Ecology A critical review of the used techniques," ed, 2005.
[22]Gevrey, M., "Review and comparison of methods to study the contribution of variables in artificial neural network models," Ecological Modelling, vol. 160, pp. 249-264, 2003.
[23]Lek, S., Belaud, A., Baran, P., Dimopoulos, I., and Delacoste, M., "Role of some environmental variables in trout abundance models using neural networks," 1995.
[24]Olden, J. D., Joy, M. K., and Death, R. G., "An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data," Ecological Modelling, vol. 178, pp. 389-397, 2004.
[25]Olden, J. D. and Jackson, D. A., "Illuminating the "black box": a randomization approach for understanding variable contributions in artificial neural networks," Ecological Modelling, vol. 154, pp. 135-150, 2002.
[26]"Femur " in http://www.daviddarling.info/encyclopedia/F/femur.html, ed.
[27]"Femur, Knee, Ankle " in http://ticklemyulnarnerve.blogspot.com/2011/02/1.html, ed.
[28]Kubiak, E. N., Bong, M., Park, S. S., Kummer, F., Egol, K., and Koval, K. J., "Intramedullary Fixation of Unstable Intertrochanteric Hip Fractures," J Opthop Trauma vol. 18, 2004.
[29]Amis, A. A., Bromage, J. D., and Larvin, M., "Fatige fracture of a femoral sliding compression screw-plate device after bone union," 1986.
[30]Cho, S. H., Lee, S. H., Cho, H. L., Ku, J. H., Choi, J. H., and Lee, A. J., "Additional Fixations for Sliding Hip Screws in Treating Unstable Pertrochanteric Femoral Fractures (AO Type 31-A2): Short-Term Clinical Results," Clinics in Orthopedic Surgery, vol. 3, p. 107, 2011.
[31]Lin, J., "Encouraging Results of Treating Femoral Trochanteric Fractures With Specially Designed Double-Screw Nails," The Journal of Trauma: Injury, Infection, and Critical Care, vol. 63, pp. 866-874, 2007.
[32]Morihara, T., Arai, Y., Tokugawa, S., Fujita, S., Chatani, K., and Kubo, T., "Proximal femoral nail for treatment of trochanteric femoral fractures," Journal of Orthopaedic Surgery, 2007.
[33]Spivak, J. M., Zuckerman, J. D., Kummer, F. J., and Frankel, V. H., "Fatigue Failure of the Sliding Screw in Hip Fracture Fixation: A Report of Three Cases," Journal of Orthopaedic Trauma, vol. 5, pp. 325-331, 1991.
[34]Strauss, E. J., Kummer, F. J., Koval, K. J., and Egol, K. A., "The “Z-effect” phenomenon defined: A laboratory study," Journal of Orthopaedic Research, vol. 25, pp. 1568-1573, 2007.
[35]Su, C.-T. and Chiang, T.-L., "Optimizing the IC wire bonding process using a neural networks/genetic algorithms approach," Journal of Intelligent Manufacturing, vol. 14, pp. 229-238, 2003.
[36]Hsu, C.-C., Chao, C.-K., Wang, J.-L., and Lin, J., "Multiobjective optimization of tibial locking screw design using a genetic algorithm: Evaluation of mechanical performance," Journal of Orthopaedic Research, vol. 24, pp. 908-916, 2006.