簡易檢索 / 詳目顯示

研究生: 郭昇桓
Sheng-Huan Kuo
論文名稱: 應用影響辨識系統於家用電風扇之智能控制研究
Research on Intelligent Control of Household Fan by Using Image Recognition System
指導教授: 蕭鈞毓
Chun-Yu Hsiao
蘇順豐
Shun-Feng Su
口試委員: 蕭鈞毓
Chun-Yu Hsiao
楊念哲
Nien-Che Yang
蕭弘清
Horng-Ching Hsiao
謝秀明
Hsiu-Ming Hsieh
王順源
Shun-Yuan Wang
學位類別: 碩士
Master
系所名稱: 電資學院 - 電機工程系
Department of Electrical Engineering
論文出版年: 2022
畢業學年度: 110
語文別: 中文
論文頁數: 157
中文關鍵詞: 直流無刷電動機人體辨識新型智能風扇SSD
外文關鍵詞: BLDC motor, human detection, intelligent fan, SSD
相關次數: 點閱:157下載:0
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

目前市售的風扇無論是傳統風扇或者BLDC風扇皆為定速定角度擺頭,傳統風扇為透過齒輪結構,而BLDC風扇雖為使用直流馬達作為擺頭馬達,但也無角度功能。至於風量部分傳統風扇只有一般大、中、小三種段速,且傳統風扇為使用交流感應馬達作為風扇轉動之馬達,因此掛上葉片或有負載時轉速便會有所變動;而BLDC風扇雖然歸功於直流無刷馬達的特性可以達到更多段轉速的設定,但現今在風扇智慧功能方面相當不普遍。
為了將智慧功能結合家用風扇,本論文應用影像辨識系統於家用電風扇之智能控制系統之設計研究,是在現今市售風扇外觀及基礎功能下,將擺頭變換為可控制角度之馬達,而風扇馬達沿用現今主流BLDC直流風扇所使用的直流無刷馬達,結合人體影像辨識技術以及紅外線溫度感測,達到多人員風量自動控制系統,預期透過新增這些智慧化系統,讓一般的家用風扇在智能模式功能方面提升更大幅度的便利。
本研究系統是以樹莓派為主要控制核心,結合周邊硬體:微控制器、紅外線溫度感測器、影像辨識鏡頭、馬達驅動器以及硬體電路等,並透過自行訓練符合本智能風扇之影像辨識系統以及各項硬體間的軟體控制,來達到本研究新型智能風扇的完整系統。
根據功能測試結果,於有效範圍內,人體影像辨識與紅外線溫度感測在作為人員辨識下的相互搭配有相當高的準確度,並且在準確的辨識人員存在依據後,再根據人體影像辨識所偵測之人員數量達到風扇自動多段調速之功能。而透過對人體影像辨識進行準確度的評估,可得知本系統自行建立之人體影像辨識模型有高達92.5%之準確度,且可大致辨識家中人員所處的姿勢與多人員彼此的位置狀況。最後透過參考文獻有效風量的風量節能效益新的評估公式,分別計算市售風扇的風量效益與本研究新型智能風扇的風量評估效益,並且與市售風扇的有效風量效益作為比較;在智慧功能狀況下,有效風量效益最高可達89.5%,且在實測不同情況下之有效風量的節能效益皆有明顯提升。由此證實,本文所提出之新型智能風扇的智慧功能,具有高度實用性且符合智慧化控制,達到有效運用風量之最終目的。


Currently, all commercially available fans, whether they are traditional fans or BLDC fans, have a fixed speed and angle swinging head. As for airflow, traditional fans only have three speeds: large, medium, and small. Moreover, traditional fans use AC induction motor as the motor for fan rotation, so the rotation speed will change when the blades are hung or when there is a load.
In order to integrate intelligent functions into home fans, the thesis applied the image recognition system to design the of intelligent control system for home electric fans. It is expected that by adding these intelligent systems, the general household fans will be more convenient in terms of intelligent mode functions.
This research is based on the Raspberry Pi as the main control core According to the functional test results, the interplay between human image recognition and infrared temperature sensing is highly accurate in the effective range of human identification, and the fan can automatically adjust the speed according to the number of people detected by human image recognition after the accurate identification of the presence of people. The accuracy evaluation of the human image recognition shows that the human image recognition model built by the system has 92.5% accuracy, and can roughly identify the posture of the people in the home and the position of multiple people with each other. Finally, by referring to the new evaluation formula of the effective airflow efficiency, the airflow efficiency of the commercially available fan and the airflow efficiency of the new intelligent fan in this study were calculated separately, and compared with the effective airflow efficiency of the commercially available fan, the effective airflow efficiency was up to 89.5% under the smart function condition, and the effective airflow efficiency was significantly improved under different conditions. This proved that the intelligent function of the new intelligent fan proposed in this thesis is highly practical and meets the ultimate goal of intelligent control and effective airflow utilization.

摘要 I Abstract III 誌謝 IV 目錄 V 圖目錄 VIII 表目錄 XIII 第一章 緒論 1 1.1 研究背景與動機 1 1.2 市售風扇介紹 3 1.2.1 市售風扇能源效率規範與種類 3 1.2.2 傳統風扇與DC直流風扇差異比較 5 1.3 本研究的貢獻及市場應用 5 1.4 相關文獻回顧 6 1.5 論文大綱 15 第二章 新型智能風扇硬體架構與功能設計 19 2.1 前言 19 2.2 新型智能風扇硬體架構 19 2.3 新型智能風扇智慧功能系統 21 2.4 本章結語 23 第三章 直流無刷馬達及步進馬達的數學模型建構與控制 24 3.1 前言 24 3.2 直流無刷馬達之機械結構與相關特性 24 3.3 直流無刷馬達之數學模型 28 3.4 直流無刷電動機驅動原理 35 3.4.1 三相變頻器原理 35 3.4.2 脈波寬度調變 36 3.4.3 六步方波控制 39 3.5 步進馬達之結構 43 3.6 步進馬達驅動控制 46 3.6.1 步進馬達驅動方式 47 3.6.2 步進馬達控制原理 48 3.7 步進馬達之特性 53 3.8 本章結語 53 第四章 影像處理與人體辨識技術 54 4.1 前言 54 4.2 影像處理技術流程與種類 54 4.2.1 影像處理流程 55 4.2.2 影像辨識神經網路架構 57 4.2.3 影像辨識模型種類 61 4.3 影像訓練處理之工具 65 4.4 SSD人體辨識技術 69 4.5 本章結語 77 第五章 新型智能風扇實驗硬體電路與程式設計 78 5.1 前言 78 5.2 驗硬體架構規劃與電路設計 78 5.2.1 紅外線溫度感測電路 79 5.2.2 多段風速調速控制電路 80 5.2.3 擺頭轉動之控制電路 83 5.2.4 兩微控制器間的簡易通訊電路 86 5.3 實驗程式流程 88 5.3.1 主程式流程 88 5.3.2 人體辨識系統程式流程 89 5.3.3 紅外線溫度感測器系統流程 91 5.3.4 風扇自動多段調速控制系統程式流程 92 5.3.5 擺頭擺角控制系統程式流程 93 5.4 本章節語 95 第六章 新型智能風扇實驗成果 96 6.1 前言 96 6.2 新型智能風扇實驗平台 96 6.3 實驗結果與分析 97 6.3.1 新型智能風扇功能實測 98 6.3.2 人體辨識與風扇多段轉速準確度評估 110 6.4 風扇之有效風量及節能效益新評估法探討 125 6.5 本章節語 132 第七章 未來研究建議 133 7.1 結論 133 7.2 未來研究建議 134 參考文獻 135

[1]Technavio, (2020), "Electric Fan Market by Product and Geography-Forecast and Analysis 2020-2024," Retrieved from https://www.technavio.com/report/electric-fan-market-industry-analysis。
[2]Momo購物,【五月花】14吋高級立扇(MYF-1435),檢自https://www.momoshop.com.tw/goods/GoodsDetail.jsp?i_code=7927703&Area=search&mdiv=403&oid=1_20&cid=index&kw=AC%E9%9B%BB%E6%89%87。
[3]Yahoo購物,HERAN禾聯 14吋 12段速微電腦遙控DC直流電風扇 HDF-14AH770,檢自https://tw.buy.yahoo.com/gdsale/HERAN%E7%A6%BE%E8%81%AF-14%E5%90%8B-12%E6%AE%B5%E9%80%9F%E5%BE%AE%E9%9B%BB%E8%85%A6%E9%81%99%E6%8E%A7DC%E7%9B%B4%E6%B5%81-8897389.html。
[4]Dyson,無葉風扇,檢自https://shop.dyson.tw/fans-and-heaters。
[5]Research Nester, (2022), "BLDC Fan Market Segmentation By Rotor Type (Inner and Outer); By Fan Speed (<550 rpm, 551 – 3000 rpm, 3001 – 10000 rpm and >10000 rpm); By End User (Domestic and Commercial) – Global Demand Analysis & Opportunity Outlook 2028," Retrieve from https://www.researchnester.com/reports/bldc-fan-market/2526.
[6]節能標章網頁,電扇節能標章能源效率基準與標示方法(民108年11月19日),檢自https://www.energylabel.org.tw/applying/efficiency/upt.aspx?Cid=8。
[7]每日頭條,這樣的也能叫風扇?(2016年05月31日)。檢自https://kknews.cc/digital/4xrvvp3.html。
[8]好神生活誌,傳統電扇、DC直流扇、循環扇差在哪?從價格、空間、耗電量教你挑選不出錯(2021年05月03日)。檢自https://online.senao.com.tw/Article/detail/1288。
[9]Momo購物,【Hunter 杭特】14吋微電腦ECO智慧遙控擺頭DC節能風扇(HTF-DC1411),檢自https://m.momoshop.com.tw/goods.momo?i_code=10167474&mdiv=searchEngine&oid=1_2&kw=%E3%80%90%E7%BE%8E%E5%9C%8B%E7%99%BE%E5%B9%B4%E5%93%81%E7%89%8C%20Hunter%E3%80%9114%E5%90%8B%E5%BE%AE%E9%9B%BB%E8%85%A6ECO%E6%99%BA%E6%85%A7%E9%81%99%E6%8E%A7%E6%93%BA%E9%A0%ADDC%E7%AF%80%E8%83%BD%E9%A2%A8%E6%89%87(HTF%20DC1411)。
[10]F. Zhai, L. Yang, W. Fu, H. Tong, and T. Zhao, "The Effects of Permanent Magnet Segmentations on Electromagnetic Performance in Ironless Brushless DC Motors." Energies 2022, 15, 621.
[11]王進猷、余元利、陳嘉偉 (2011)。微型永磁無刷直流馬達性能分析研究成果報告(精簡版)。行政院國家科學委員會專題研究計畫成果報告(編號:NSC 98-2622-E-230-008-CC3),未出版。
[12]鄭竹軒(民109),三相永磁同步波浪發電機設計與研製(未出版之碩士論文),國立臺灣科技大學,臺北市。
[13]黃勁嘉(民107),小容量直流無刷電動機的驅動控制電路設計(未出版之碩士論文),國立臺灣科技大學,臺北市。
[14]Y. V. Zubkov, Y. A. Makarichev and Y. N Ivannikov, "Comparison of surface-mounted permanent magnet and interior-mounted permanent starters for gas turbine engines electrical start," International Conference on Electrotechnical Cpplexes and Systems(ICOECS), Ufa, Russia, pp.1-5, 2019.
[15]劉呈軒(民109),應用於電動機車之永磁同步電動機控制策略研究,國立臺灣大學電機資訊學院電機工程學系碩士論文。
[16]鄭義威,無感測器三相永磁同步電動機驅控系統於風機濾網積塵監測之應用研究,國立臺灣科技大學電機工程所碩士論文,民國109年7月。
[17]M. P. Donsión, "Permanent magnet synchronous motors: Influence of the parameters on the control of a PMSM," The International journal for computation and mathematics in electrical and electronic engineering (COMPEL), vol. 27, no. 4, pp. 946-957, 2008.
[18]張育誠(民110),直流無刷電動手工具機兩段式精確轉矩控制策略之研製,國立臺灣科技大學電機工程所碩士論文。
[19] Y. Hu, S. Huang, X. Wu, and X. Li, "Control of Dual Three-Phase Permanent Magnet Synchronous Machine Based on Five-Leg Inverter," in IEEE Transactions on Power Electronics, vol. 34, no. 11, pp. 11071-11079, Nov. 2019, doi: 10.1109.
[20]Microcontrollers Lab, "Introduction to PWM – Pulse width modulation," Retrieved from https://microcontrollerslab.com/pwm-introduction-types/#Pulse_width_modulation_generation_techniques.
[21]N. Tadrist, and H. Zeroug, "Development of brushless DC motor drive system for teaching purposes using various PWM control techniques for speed control," IEEE 15th Workshop on Control and Modeling for Power Electronics, 2014.
[22]吳昱錚(民97)。應用於三相直流無刷馬達之150度12步方波無感測驅動技術與速度控制,國立交通大學電機與控制工程系碩士論文。
[23]A. S. Al-Adsani, M. E. AlSharidah, and O. Beik, "BLDC Motor Drives: A Single Hall Sensor Method and a 160° Commutation Strategy," in IEEE Transactions on Energy Conversion, vol. 36, no. 3, pp. 2025-2035, Sept. 2021, doi: 10.1109.
[24]H.-J. Kim, H.-S. Park, and J.-M. Kim, "Expansion of Operating Speed Range of High-Speed BLDC Motor Using Hybrid PWM Switching Method Considering Dead Time." Energies 2020, 13, 5212.
[25]Dilip Raja, (2019), "Three Phase Inverter Circuit - 120 Degree and 180 Degree Conduction Mode," Circuit Digest. Retrieved from https://circuitdigest.com/tutorial/three-phase-inverter-circuit-diagram-120-degree-and-180-degree-conduction-mode.
[26]李孟哲(民110),多目標人員自動追蹤控制系統應用於智慧風扇,國立臺灣科技大學電機工程所碩士論文。
[27]Muhammad H. Rashid, "POWER ELECTRONICS HANDBOOK DEVICES, CIRCUITS, AND APPLICATIONS (Third Edition)," pp. 915-990, 2011.
[28]MPS, "Stepper Motors Basics: Types, Uses, and Working Principles," Retrieved from https://www.monolithicpower.com/en/stepper-motors-basics-types-uses.
[29]X. Wang, S. Lu, and S. Zhang, "Rotating Angle Estimation for Hybrid Stepper Motors with Application to Bearing Fault Diagnosis," in IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 8, pp. 5556-5568, Aug. 2020.
[30]Danielle Collins, "Stepper motors: Differences between permanent magnet, variable reluctance, and hybrid types. Linear Motion Tips," Retrieved from https://www.linearmotiontips.com/stepper-motors-differences-between-permanent-magnet-variable-reluctance-and-hybrid-types/.
[31]黃正杰(民105),二相步進馬達多軸同動控制系統設計與研製,國立交通大學電控工程研究所碩士論文。
[32]Z. Peng, and C. Bi, "A Position Sensorless Closed-Loop Control Mode of a Three-Phase Hybrid Stepper Motor," Energies 2022, 15, 804.
[33]Xinda Hu, "An Introduction to Stepper Motors," University of Arizona College of Optical Sciences.
[34]K. Li, and L. Cao, "A Review of Object Detection Techniques," 2020 5th International Conference on Electromechanical Control Technology and Transportation (ICECTT), 2020, pp. 385-390, doi: 10.1109/ICECTT50890.2020.00091.
[35]J. Ruiz-Santaquiteria, G. Bueno, O. Deniz, N. Vallez, and G. Cristobal, "Semantic versus instance segmentation in microscopic algae detection," Engineering Applications of Artificial Intelligence, Volume 87, 2020, 103271, ISSN 0952-1976.
[36]N. C. A. Sallang, M. T. Islam, M. S. Islam, and H. Arshad, "A CNN-Based Smart Waste Management System Using TensorFlow Lite and LoRa-GPS Shield in Internet of Things Environment," in IEEE Access, vol. 9, pp. 153560-153574, 2021, doi: 10.1109.
[37]C. Kuo, (2018, November 8) "What Is Image Recognition?" Retrieved from https://medium.com/dataman-in-ai/module-6-image-recognition-for-insurance-claim-handling-part-i-a338d16c9de0.
[38]C. Tang, Y. Feng, X. Yang, C. Zheng, and Y. Zhou, "The Object Detection Based on Deep Learning," 2017 4th International Conference on Information Science and Control Engineering (ICISCE), 2017, pp. 723-728, doi: 10.1109/ICISCE.2017.156.
[39]J. Wang, T. Zhang, Y. Cheng, and N. Al-Nabhan, "Deep learning for object detection: a survey," Computer Systems Science and Engineering, vol. 38, no.2, pp. 165–182, 2021.
[40]Jenn Yuen, B. Russell, Ce Liu, and A. Torralba, “LabelMe video: Building a video database with human annotations,” 2009 IEEE 12th International Conference on Computer Vision, 2009, pp. 1451-1458, doi: 10.1109/ICCV.2009.5459289.
[41]李謦伊(2021, 9月),Segmentation Label 標註教學。檢自https://medium.com/ching-i/segmentation-label-%E6%A8%99%E8%A8%BB%E6%95%99%E5%AD%B8-26b8179d661。
[42]J. Sigut, M. Castro, R. Arnay, and M. Sigut, "OpenCV Basics: A Mobile Application to Support the Teaching of Computer Vision Concepts," in IEEE Transactions on Education, vol. 63, no. 4, pp. 328-335, Nov. 2020, doi: 10.1109.
[43]Serdar Yegulalp, (2019 June 18), "What is TensorFlow? The machine learning library explained," Retrieved from https://www.infoworld.com/article/3278008/what-is-tensorflow-the-machine-learning-library-explained.html.
[44]Rajesh Kumar, (2022 March 21), "What is TensorFlow and How it works? An Overview and Its Use Cases," Retrieved from https://www.devopsschool.com/blog/what-is-tensorflow-and-how-it-works-an-overview-and-its-use-cases/.
[45]S. Kanimozhi, G. Gayathri, and T. Mala, "Multiple Real-time object identification using Single shot Multi-Box detection," 2019 International Conference on Computational Intelligence in Data Science (ICCIDS), 2019, pp. 1-5, doi: 10.1109/ICCIDS.2019.8862041.
[46]Z. Lyu, H. Jin, T. Zhen, F. Sun, and H. Xu, "Small Object Recognition Algorithm of Grain Pests Based on SSD Feature Fusion," in IEEE Access, vol. 9, pp. 43202-43213, 2021.
[47]X. Gao, J. Xu, C. Luo, J. Zhou, P. Huang, and J. Deng, "Detection of Lower Body for AGV Based on SSD Algorithm with ResNet." Sensors 2022, 22.
[48]Eddie Forson, (2017 November 18), "Understanding SSD MultiBox — Real-Time Object Detection In Deep Learning," Retri-eved from https://towardsdatascience.com/understanding-ssd-multibox-real-time-object-detection-in-deep-learning-495ef744fab.
[49]Jonathan Hui, (2018 March 14), "SSD object detection: Single Shot MultiBox Detector for real-time processing," Retrieved from https://jonathan-hui.medium.com/ssd-object-detection-single-shot-multibox-detector-for-real-time-processing-9bd8deac0e06.
[50]M. Zimoch, U. Markowska-Kaczmar, "Human flow recognition using deep networks and vision methods," Engineering Applications of Artificial Intelligence, Volume 104, 2021, 104346, ISSN 0952-1976.
[51]Tommy Huang, (2018年9月28日) "機器/深度學習: 物件偵測 Non-Maximum Suppression (NMS)",檢自https://chih-sheng-huang821.medium.com/%E6%A9%9F%E5%99%A8-%E6%B7%B1%E5%BA%A6%E5%AD%B8%E7%BF%92-%E7%89%A9%E4%BB%B6%E5%81%B5%E6%B8%AC-non-maximum-suppression-nms-aa70c45adffa。
[52]Melexis, "MLX90614 family Single and Dual Zone Infra Red Thermometer in TO-39 datasheet," Retrieve from https://www.melexis.com/en.
[53]Nidec Corporation, "48F Series(Standard Power) Brushless DC motors," Retrieved from https://www.nidec.com/en/product/search/category/B101/M102/S100/NCJ-48F-Type-A/.
[54]Dejan, "How Brushless Motor and ESC Work," How To Mechatronics. Retrieve from https://howtomechatronics.com/how-it-works/how-brushless-motor-and-esc-work/.
[55]STMicroelectronics, "L298N Dual H-Bridge Motor Drive Datasheet," Retrieved from https://www.st.com/content/st_com/en.html.

無法下載圖示 全文公開日期 2024/08/19 (校內網路)
全文公開日期 本全文未授權公開 (校外網路)
全文公開日期 本全文未授權公開 (國家圖書館:臺灣博碩士論文系統)
QR CODE