研究生: |
李哲逸 Che-yi Li |
---|---|
論文名稱: |
應用田口品質法及神經-遺傳法於椎弓足螺絲最佳化設計及參數貢獻度之研究 Design Optimization Study of Spinal Pedicle Screws and Contribution Analyses: Comparison between Taguchi Method and Neuro-Genetic Method |
指導教授: |
趙振綱
Ching-kong Chao 林晉 Jinn Lin |
口試委員: |
徐慶琪
Ching-chi Hsu |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 機械工程系 Department of Mechanical Engineering |
論文出版年: | 2014 |
畢業學年度: | 102 |
語文別: | 中文 |
論文頁數: | 83 |
中文關鍵詞: | 椎弓足螺絲 、田口品質法 、神經-遺傳法 、類神經網路 、基因演算法 、最佳化設計 、因子之貢獻度 |
外文關鍵詞: | pedicle screw, Taguchi method, Neuro-Genetic method, artificial neural network, genetic algorithm, black box, contribution |
相關次數: | 點閱:352 下載:26 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
椎弓足螺絲(pedicle screw)是用來矯正脊椎側彎的植入物,然而椎弓足螺絲會因受到彎曲負荷而斷裂或是椎體骨質疏鬆而螺絲鬆脫等併發症問題。彎曲強度與椎弓足螺絲斷裂有關,抗拉強度則與螺絲鬆脫有關,而此兩種強度皆與螺紋設計有很大的關係。本研究使用田口品質法(Taguchi Method)和神經遺傳法(Neuro-Genetic Method)來找出螺紋之最佳化設計。本次研究的目的是比較這兩種方法,哪一個找出的最佳化設計有較好的結果,另一個是計算及分析各個因子的貢獻度。
本次研究用有限元素法(Finite Element Method)模擬出椎弓足螺絲的彎曲強度和抗拉強度,其L25直交表之資料皆代入田口品質法與神經-遺傳法之中。田口品質法運用L25直交表找出最佳設計,並使用變異數分析(Analysis of Variation)統計出每個因子的貢獻度。神經-遺傳法則是將直交表算出的結果匯入類神經網路(Artificial Neural Networks)訓練出六個模型,這六個模型輸入基因演算法(Genetic Algorithms)中找出最佳設計。以變異數分析當標準,計算貢獻度的方法有Garson權重計算法(Garson weight method)、Olden權重計算法(Olden weight method)、因子權重移除法(Weight elimination)、偏微分法(Partial derivative)、敏感度分析(Sensitivity analysis)之全因子配置法(Profile method)與單因子分割法(Factor division),比較這些類神經網路計算貢獻度的方法並找出何種方法能找出最準確之貢獻度。
在本研究之結果,最佳設計的彎曲強度方面,神經-遺傳法的最佳設計所受到的最大拉應力比田口品質法低3.01%。而在抗拉強度,神經-遺傳法比田口品質法高10.14%。在計算貢獻度方面,因子權重移除法與單因子分割法與變異數分析最為類似。
Pedicle screws used for fixation of hip trochanteric fractures should have higher bending strength to resist breakage and bone holding power to resist migration. The present optimization study is to find screws with the highest bending or bone holding power. Besides, the “black box” problem of ANN was not disclosed. We could get the predictive value from the artificial neural networks conveniently, but the less information about the relative influence of the independent variables was provided. The purpose of the study is to find the optimal solution and illuminate the black box by calculating contribution of each factor with different methods.
The bending and pullout functions of the pedicle screws were first simulated by finite element models (FEM). With L25 orthogonal arrays, optimal screw designs with highest bending or bone holding power were then investigated by Taguchi robust design methods and Neuro-Genetic method hybridizing artificial neural networks (ANN) and genetic algorithm (GA). The mechanical performances of the optimal designs, the predictability of the performances and the contribution of the design factors obtained in these methods were compared. On the aspect of contribution, the result of analysis of variance (ANOVA) is considered as standard. The weight method, weight elimination, partial derivative and sensitivity analysis are compared to find which one’s contribution is the most accurate.
For optimization studies, Neuro-Genetic method could yield better results than Taguchi methods by -3.01% in bending and 10.14% in pullout analyses. For predicting the performances, the errors of NG algorithm were 0.65% and 1.42% for bending and pullout analyses respectively, much lower than -21.26% and 15.95% of Taguchi method. In addition, using weight elimination or factor division could calculate accurate contribution of the design factors.
[1] H. Kurtaran, B. Ozcelik, and T. Erzurumlu, "Warpage optimization of a bus ceiling lamp base using neural network model and genetic algorithm," Journal of Materials Processing Technology, vol. 169, pp. 314-319, Nov 10 2005.
[2] K. Panneerselvam, S. Aravindan, and A. Noorul Haq, "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.
[3] J. D. Olden, M. K. Joy, and R. G. Death, "An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data," Ecological Modelling, vol. 178, pp. 389-397, 2004.
[4] M. Gevrey, I. Dimopoulos, and S. Lek, "Review and comparison of methods to study the contribution of variables in artificial neural network models," Ecological Modelling, vol. 160, pp. 249-264, 2003.
[5] M. H. Shojaeefard, M. Akbari, M. Tahani, and F. Farhani, "Sensitivity Analysis of the Artificial Neural Network Outputs in Friction Stir Lap Joining of Aluminum to Brass," Advances in Materials Science and Engineering, vol. 2013, pp. 1-7, 2013.
[6] X. R. Cui, M. F. Abbod, Q. Liu, J. S. Shieh, T. Y. Chao, C. Y. Hsieh, et al., "Ensembled artificial neural networks to predict the fitness score for body composition analysis," J Nutr Health Aging, vol. 15, pp. 341-8, May 2011.
[7] Q. Zhu, W. W. Lu, A. D. Holmes, Y. Zheng, S. Zhong, and J. C. Leong, "The effects of cyclic loading on pull-out strength of sacral screw fixation: an in vitro biomechanical study," Spine (Phila Pa 1976), vol. 25, pp. 1065-9, May 1 2000.
[8] H. Matsuzaki, Y. Tokuhashi, F. Matsumoto, M. Hoshino, T. Kiuchi, and S. Toriyama, "Problems and solutions of pedicle screw plate fixation of lumbar spine," Spine (Phila Pa 1976), vol. 15, pp. 1159-65, Nov 1990.
[9] S. D. Cook, S. L. Salkeld, T. Stanley, A. Faciane, and S. D. Miller, "Biomechanical study of pedicle screw fixation in severely osteoporotic bone," Spine J, vol. 4, pp. 402-8, Jul-Aug 2004.
[10] J. L. Stambough, F. El Khatib, A. M. Genaidy, and R. L. Huston, "Strength and fatigue resistance of thoracolumbar spine implants: an experimental study of selected clinical devices," J Spinal Disord, vol. 12, pp. 410-4, Oct 1999.
[11] F. A. A. M.R. Mikles, E.P. Frankenburg et al., "Biomechanical Study of Lumbar Pedicle Scres in a Corpectomy Model Assessing Significance of Screw Height," Journal of Spinal Disorders & Techniques, vol. 17, pp. 272-276, 2004.
[12] C. C. Hsu, C. K. Chao, J. L. Wang, S. M. Hou, Y. T. Tsai, and J. Lin, "Increase of pullout strength of spinal pedicle screws with conical core: biomechanical tests and finite element analyses," Journal of Orthopaedic Research, vol. 23, pp. 788-794, Jul 2005.
[13] S. J. L. P.Q. Chen, S.S. Wu, H. So, "Mechanical Performance of the New Posterior Spinal Implant: Effect of Materials, Connecting Plant, and Pedicle Screw Design," Spine, vol. vol. 28, pp. pp. 881-886, 2003.
[14] B. W. Cunningham, J. C. Sefter, Y. Shono, and P. C. McAfee, "Static and cyclical biomechanical analysis of pedicle screw spinal constructs," Spine (Phila Pa 1976), vol. 18, pp. 1677-88, Sep 15 1993.
[15] G. D. Garson, "Interpreting neural-network connection weights," AI Expert, vol. 6, pp. 46-51, 1991.
[16] Y. Dimopoulos, P. Bourret, and S. Lek, "Use of Some Sensitivity Criteria for Choosing Networks with Good Generalization Ability," Neural Processing Letters, vol. 2, pp. 1-4, Nov 1995.
[17] S. Lek, A. Belaud, P. Baran, I. Dimopoulos, and M. Delacoste, "Role of some environmental variables in trout abundance models using neural networks," Aquatic Living Resources, vol. 9, pp. 23-29, 1996.
[18] M. Scardi and L. W. Harding, "Developing an empirical model of phytoplankton primary production: a neural network case study," Ecological Modelling, vol. 120, pp. 213-223, Aug 17 1999.
[19] J. D. Olden and D. A. Jackson, "Illuminating the "black box": a randomization approach for understanding variable contributions in artificial neural networks," Ecological Modelling, vol. 154, pp. 135-150, Aug 15 2002.
[20] C. C. Hsu, C. K. Chao, J. L. Wang, and J. Lin, "Multiobjective optimization of tibial locking screw design using a genetic algorithm: Evaluation of mechanical performance," Journal of Orthopaedic Research, vol. 24, pp. 908-916, May 2006.
[21] T. C. Chang and E. Faison, "Shrinkage behavior and optimization of injection molded parts studied by the Taguchi method," Polymer Engineering and Science, vol. 41, pp. 703-710, May 2001.
[22] J. Podani, "Extending Gower's general coefficient of similarity to ordinal characters," Taxon, vol. 48, pp. 331-340, May 1999.
[23] J. C. Gower, "A General Coefficient of Similarity and Some of Its Properties," Biometrics, vol. 27, pp. 857-871, 1971.
[24] I. Dimopoulos, J. Chronopoulos, A. Chronopoulou-Sereli, and S. Lek, "Neural network models to study relationships between lead concentration in grasses and permanent urban descriptors in Athens city (Greece)," Ecological Modelling, vol. 120, pp. 157-165, Aug 17 1999.
[25] T. Tchaban, M. J. Taylor, and J. P. Griffin, "Establishing impacts of the inputs in a feedforward neural network," Neural Computing & Applications, vol. 7, pp. 309-317, 1998.
[26] J. J. Montano and A. Palmer, "Numeric sensitivity analysis applied to feedforward neural networks," Neural Computing & Applications, vol. 12, pp. 119-125, 2003.
[27] S. Lek, M. Delacoste, P. Baran, I. Dimopoulos, J. Lauga, and S. Aulagnier, "Application of neural networks to modelling nonlinear relationships in ecology," Ecological Modelling, vol. 90, pp. 39-52, Sep 1996.
[28] Q. Liu, X. Cui, M. F. Abbod, S.-J. Huang, Y.-Y. Han, and J.-S. Shieh, "Brain death prediction based on ensembled artificial neural networks in neurosurgical intensive care unit," Journal of the Taiwan Institute of Chemical Engineers, vol. 42, pp. 97-107, 2011.
[29] C. T. Su and T. L. Chiang, "Optimizing the IC wire bonding process using a neural network/genetic algorithms approach," Journal of Intelligent Manufacturing, vol. 14, pp. 229-238, 2003.
[30] C. J. Willmott and K. Matsuura, "Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance," Climate Research, vol. 30, pp. 79-82, Dec 19 2005.