近年來，茲因環保意識提升，各國對馬達運轉之效率等已訂定環保規範，因此不論是設計端或是相關生產設備之製造工藝水平也提升，然而業界目前對於馬達生產設備參數設定並沒有一套設定規範，往往是仰賴試誤法與經驗法則，十分耗時，且調整結果無法保證為最佳解，進而導致最終產品端性能不如預期，有鑒於此，本研究提出利用智能化協助繞線機製程參數之調整，透過權重調整，可獲得所需之建議繞線製程參數，毋須實際繞線與量測實驗。
本文提出利用XGboost模型結合最佳化演算法PSO的架構來最佳化繞線機製程參數，與原樣品相比，於相同繞線條件下，最佳化參數之效率區間比原樣品提高了3~5%，整體製程成本銅線用量也降低了10%。對於繞線機，最佳化參數能使槽滿率從44%提高57%，整體馬達效率操作區間內也能提高了12% ~ 14%，驗證本研究提出之方法除了能夠改善馬達實際運轉效率，更可藉此改善製程端限制與降低製程生產成本。

In recent years, environmental protection awareness has been on the increase, various countries has enacted regulations on agents that promote environmental degradation such as low electric motor efficiency. To meet these regulation, motor design processes and manufacturing equipment have to be improved. However, the electric motor manufacturing industry currently does not have parameter tuning functions in their motor production equipment such as winding machine. The tuning method always relies on trial and error or empirical rules which are time-consuming, and the individual result cannot guarantee a global optimal solution, resulting to unreliable performance of the final product. In the sight of this, this thesis proposes the use of artificial intelligence to assist the tuning of electric motor winding machine parameters. Through the cost function weight adjustment, the required winding machine parameters can be obtained without any actual winding experiments and measurements.
This thesis proposes the XGboost model combined with the PSO algorithm to optimize the winding machine parameters. Compared with the prototype, under the same winding conditions, the operation range of the motor efficiency is 3% ~5% higher. The overall process cost of copper wire has also reduced by 10%. For the winding machine, the optimized parameters can increase the slot filled factor from 44% to 57%, and the overall of motor efficiency can also increase by 12% to 14% in the operating range. This thesis verified that the proposed approach in this study can not only increase the actual operation of the motor efficiency but also improve process-end restrictions and reduce process production costs.

[1] 路昌工業股份有限公司，馬達繞線設備介紹，
[Avalible]:https: https://lutron-ind.weebly.com/
[2] R. Fischer. Elektrische Maschinen. 12th Edition, Munich. Vienna: Carl Hanser Verlag, 2004.
[3] A. Riedel, A. Roessert, A. Kuehl and J. Franke, "Calculation of the Copper Filling Factor of Electric Traction Drives including Graphical Representation," 2019 22nd International Conference on Electrical Machines and Systems (ICEMS), Harbin, China, pp. 1-6, 2019.
[4] J. Bönig, B. Bickel, M. Spahr, C. Fischer and J. Franke, "Simulation of orthocyclic windings using the linear winding technique," 2015 5th International Electric Drives Production Conference (EDPC), Nuremberg, pp. 1-6, 2015.
[5] J. Hofmann, A. Komodromos, J. Fleischer and A. E. Tekkaya, "Optimization of the Linear Coil Winding Process by Combining New Actuator Principles on the Basis of Wire Forming Analysis," 2018 8th International Electric Drives Production Conference (EDPC), pp. 1-6, 2018.
[6] A. Komodromos, C. Löbbe and A. E. Tekkaya, "Development of forming and product properties of copper wire in a linear coil winding process," 2017 7th International Electric Drives Production Conference (EDPC), pp. 1-7, 2017.
[7] J. Bönig, B. Bickel, M. Spahr, C. Fischer and J. Franke, "Explicit dynamics process simulation of linear coil winding for electric drives production," 2014 4th International Electric Drives Production Conference (EDPC), pp. 1-7, 2014.
[8] J. Hofmann, B. Bold, C. Baum and J. Fleischer, "Investigations on the tensile force at the multi-wire needle winding process," 2017 7th International Electric Drives Production Conference (EDPC), pp. 1-6, 2017.
[9] K. L. Kim et al., "Effect of winding tension on electrical behaviors of a noinsulation ReBCO pancake coil," IEEE. Trans. Appl. Supercond., vol. 24, no. 3, Jun. 2014.
[10] J. Hagrn, F. S.-L. Blanc, and J. Fleischer, Handbook of Coil Winding, Technologies for efficient electrical wound products and their automated production. Berlin, Germany : Springer Vieweg, 2017.
[11] M. Eftekhari, M. Moallem, S. Sadri, and M. F. Hsieh, "Online detection of induction motors stator winding short-circuit faults, " IEEE Syst. J., vol. 8, no. 4, pp. 1272-1282, Dec. 2014.
[12] F. S. Blanc, J. Fleischer, S. Sautter, T. Delzs and J. Hagedorn, "Fault analysis of linear winding processes for noncircular orthocyclic coils: Investigation of winding scheme dependencies within the winding process development," 2014 4th International Electric Drives Production Conference (EDPC), pp. 1-8, 2014.
[13] Dobrzanski, L. A., J. Domaga, and J. F. Silva. "Application of Taguchi method in the optimisation of filament winding of thermoplastic composites." Archives of Materials Science and Engineering, pp133-140, 2017.
[14] R. Ramprasad, R. Batra, G. Pilania, A. Mannodi-Kanakkithodi, and C. Kim, "Machine learning in materials informatics: recent applications and prospects," Computational Materials, 2017.
[15] Zhao P, Zhou H, Li Y, and Li D "Process parameters optimization of injection molding using a fast strip analysis as a surrogate model." The International Journal of Advanced Manufacturing Technology , pp1436-1444.
[16] J. Pfrommer, C. Zimmerling, J. Z. Liu, L. Kärger, F. Henning, and J. Beyerer, “Optimisation of manufacturing process parameters using deep neural networks as surrogate models,” Procedia CIRP , vol. 72, pp.426-431, Mar. 2018.
[17] A. Mayr, D. Kißkalt, A. Lomakin, K. Graichen, and J. Franke, "Towards an intelligent linear winding process through sensor integration and machine learning techniques, " Procedia CIRP, 2021
[18] R. Pupadubsin, N. Chayopitak, S. Karukanan, P. Champa, P. Somsiri and K. Tungpimolrut, "Comparison of winding arrangements of three phase switched reluctance motor under unipolar operation," 2012 15th International Conference on Electrical Machines and Systems (ICEMS), Oct. 2012.
[19] A. Riedel, A. Roessert, A. Kuehl and J. Franke, "Calculation of the Copper Filling Factor of Electric Traction Drives including Graphical Representation," 2019 22nd International Conference on Electrical Machines and Systems (ICEMS), Harbin, China, pp. 1-6, 2019.
[20] P. Ponomarev, Y. Alexandrova, I. Petrov, P. Lindh, E. Lomonova, and J. Pyrhonen, "Inductance calculation of tooth-coil permanent-magnet synchronous machines, " IEEE Trans. Ind. Electron., vol. 61, no. 11, pp. 5966-5973, Nov. 2014.
[21] M. Hsieh, Y. Hsu, D. G. Dorrell and K. Hu, "Investigation on End Winding Inductance in Motor Stator Windings," in IEEE Transactions on Magnetics, vol. 43, no. 6, pp. 2513-2515, June 2007.
[22] F. Sell-Le Blanc, J. Hofmann, R. Simmler and J. Fleischer, "Coil winding process modelling with deformation based wire tension analysis, " CIRP Annals – Manufacturing Technology, vol. 65, pp. 65-68, 2016.
[23] J.G. Cintron-Rivera, "Fault Mitigation in Permanent Magnet Synchronous Motors under an Internal Turn-to-turn Failure, " Michigan State University, 2014.
[24] N. Piotrowski, "AC vs. DC dielectric withstand testing: Allowing AC or DC testing in 61010-1 3rd edition," 2017 IEEE Symposium on Product Compliance Engineering (ISPCE), pp. 1-3, 2017.
[25] ACOUSTIC EMISSION TESTS ON THE ANALYSIS OF CRACKED SHAFTS OF DIFFERENT CRACK DEPTHS - Scientific Figure on ResearchGate.
[Available]:https://www.researchgate.net/figure/a-Negative-skewness-b-Normal-curve-c-Positive-skewness-Durkhure-and-Lodwal-2014_fig5_294890337
[26] T. Chen and C. Guestrin, "Xgboost: A scalable tree boosting system, " in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, pp. 785-794, 2016.
[27] N. Yusup, A. M. Zain, and S. Z. M. Hashim, "Overview of PSO for optimizing process parameters of machining," Procedia Engineering, vol. 29, pp. 914-923, 2012.
[28] Ou, C. and Lin, W. "Comparison between PSO and GA for parameters optimization of PID controller. " Proc. IEEE International Conference on Mechatronics and Automation. Luoyang, China, pp. 2471-2475, 2006.