| 研究生: |
鄭爲中 Cheng, Wei-Chung |
|---|---|
| 論文名稱: |
基於卷積神經網路之馬達噪音舒適度與轉子設計研究 Motor Acoustic Comfort Improvement Based on Rotor Design with Convolutional Neural Network |
| 指導教授: |
謝旻甫
Hsieh, Min-Fu |
| 共同指導教授: |
朱威達
Chu, Wei-Ta 黃柏維 Huang, Po-Wei |
| 學位類別: |
碩士 Master |
| 系所名稱: |
電機資訊學院 - 電機工程學系 Department of Electrical Engineering |
| 論文出版年: | 2021 |
| 畢業學年度: | 109 |
| 語文別: | 中文 |
| 論文頁數: | 48 |
| 中文關鍵詞: | 卷積神經網路 、機器學習 、馬達設計 、噪音抑制 |
| 外文關鍵詞: | Convolutional neural network, machine learning, motor design, acoustic noise |
| 相關次數: | 點閱:136 下載:3 |
| 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 |
隨著自動化的蓬勃發展,工業上馬達的應用需求日益增加,不論是加工場、製造商,只要林立在住宅區附近都是住戶們的噩夢,由於工業生產總會不可避免的帶來噪音,干擾到居民們的生活與睡眠品質,因此安靜的居家環境便成了經濟提升與發展的犧牲品。近年來欲對抗噪音這種資本主義帶來的外部成本,業界也針對馬達異音訊號的診斷技術發展,但隨之也需付出較高時間與金錢的成本才能加以改善。若能於馬達設計過程中,先行模擬出實際聲音,便能提升音質的舒適度,設計出環境友善的馬達。
本文將分為四部分,第一部分為有關馬達設計抑制噪音與神經網路文獻蒐集。第二部分為馬達的逆向與實測,透過比對電氣特性與模擬噪音、實測噪音驗證有限元素分析軟體之準確度。第三部分為設計、訓練卷積神經網路,將聲音依照著醫學上定義舒適與不適的程度做分類,提供定義噪音的指標。第四部分蒐集不同轉子設計下在有限元素分析軟體內模擬輸出噪音的分類結果,並透過迴歸分析演算法找出神經網路所定義能產出最舒適噪音的轉子設計,最後以有限元素分析做驗證。
With manufacturing companies moving into automated processes, the demand for industrial motors have being on the rise in recent time. It has been observed however, that some of these companies located close to residential areas constitute a huge source of noise pollution. Noise pollution are caused due to the processes of industrial production, and these economic improvement and development are to the detriment of a quiet residential environment. It is then pertinent for industries to develop diagnostic technology for acoustic noise signal caused by electric motors, but implementing this requires a lot of time and money to bring into realization. In view of this, by modelling and simulating electric motors such that its acoustic output can be obtained and controlled, an environmentally friendly motor can be designed.
[1] 全國法規資料庫https://law.moj.gov.tw/LawClass/LawAll.aspx?pcode=O0030001
[2] 路昌工業股份有限公司https://lutron1980.pixnet.net/blog/post/172687029
[3] https://www.sphs.hc.edu.tw/ischool/public/resource_view/open.php?file=6fc14831d3be4f60363d776c6bea9344.pdf
[4] 杰里設計工作室http://jerry0985.blogspot.com/2014/09/blog-post_6.html
[5] 路昌工業股份有限公司https://lutron1980.pixnet.net/blog/post/172687029
[6] https://www.ozeninc.com/contact/?subject=support
[7] Durrant J D., Lovrinic J H. 1984. Bases of Hearing Sciences. Second Edition. United States of America: Williams & Wilkins
[8] J. Hur, J. Reu, B. Kim and G. Kang, "Vibration Reduction of IPM-Type BLDC Motor Using Negative Third Harmonic Elimination Method of Air-Gap Flux Density," in IEEE Transactions on Industry Applications, vol. 47, no. 3, pp. 1300-1309, May-June 2011
[9] X. Sun et al., "Skew Angle Optimization Analysis of a Permanent Magnet Synchronous Motor for EVs," 2018 IEEE International Conference on Applied Superconductivity and Electromagnetic Devices (ASEMD), 2018, pp. 1-2, doi: 10.1109/ASEMD.2018.8558826.
[10] S. Nian, L. Zhu, X. Luo and Z. Huang, "Analytical Methods for Optimal Rotor Step-Skewing To Minimize Cogging Torque in Permanent Magnet Motors," 2019 22nd International Conference on Electrical Machines and Systems (ICEMS), 2019, pp. 1-5
[11] https://lutron1980.pixnet.net/blog/post/170810662
[12] S. Albawi, T. A. Mohammed and S. Al-Zawi, "Understanding of a convolutional neural network," 2017 International Conference on Engineering and Technology (ICET), 2017, pp. 1-6, doi: 10.1109/ICEngTechnol.2017.8308186.
[13] 周志華, 機器學習, 清華大學出版社, 2016
[14] [Hanselman, Duane C.] Brushless Permanent Magnet Motor Design
[15] https://kknews.cc/zh-tw/news/m2abjx9.html
[16] https://zh.wikipedia.org/wiki/Pearson%20product-moment%20correlation%20coefficient
[17] [Freesound – Freesound ]https://freesound.org
[18] https://chih-sheng-huang821.medium.com/%E5%8D%B7%E7%A9%8D%E7%A5%9E%E7%B6%93%E7%B6%B2%E8%B7%AF-convolution-al-neural-network-cnn-%E5%8D%B7%E7%A9%8D%E9%81%8B%E7%AE%97-%E6%B1%A0%E5%8C%96%E9%81%8B%E7%AE%97-856330c2b703
[19] https://en.wikipedia.org/wiki/Regression_analysis
[20] P. Trebuňa, J. Halčinová, M. Fil'o and J. Markovič, "The importance of normalization and standardization in the process of clustering," 2014 IEEE 12th International Symposium on Applied Machine Intelligence and Informatics (SAMI), 2014, pp. 381-385