系統識別號 | U0002-2001202122424200 |
---|---|
DOI | 10.6846/TKU.2021.00496 |
論文名稱(中文) | 人工智慧物聯網之蛋雞飼養環境分析 |
論文名稱(英文) | Analysis of Laying Hens Feeding Environment Using Artificial Intelligence of Things (AIoT) |
第三語言論文名稱 | |
校院名稱 | 淡江大學 |
系所名稱(中文) | 電機工程學系博士班 |
系所名稱(英文) | Department of Electrical and Computer Engineering |
外國學位學校名稱 | |
外國學位學院名稱 | |
外國學位研究所名稱 | |
學年度 | 109 |
學期 | 1 |
出版年 | 110 |
研究生(中文) | 廖于德 |
研究生(英文) | Yu-De Liao |
學號 | 803440022 |
學位類別 | 博士 |
語言別 | 繁體中文 |
第二語言別 | 英文 |
口試日期 | 2021-01-11 |
論文頁數 | 77頁 |
口試委員 |
指導教授
-
李揚漢
委員 - 蘇木春 委員 - 楊淳良 委員 - 梁佑全 委員 - 郭博昭 委員 - 林劭品 委員 - 許獻聰 |
關鍵字(中) |
人工智慧飼養 多合一環境感測 滑軌式移動辨識 分區預警 微型區域伺服器 |
關鍵字(英) |
Artificial Intelligence Breeding All-in-One Environment Sensing Sliding Track Type Movement Identification Zone Warning Micro Zone Server |
第三語言關鍵字 | |
學科別分類 | |
中文摘要 |
為了解決禽畜場域智慧化生產與數位化服務等問題,將結合人工智慧(AI)、機器人、物聯網(IoT)、大數據等技術,建置人工智慧雲端感測整合平台,建立AI腦、AI雲、AI端,以精準投放、快速取樣、即時篩檢建立人工智慧生態圈(AI Ecosystem)。本論文提出關鍵技術,智慧環境全方位監控管理系統,設計E27燈頭式多合一環境感測預警裝置可快速佈署於禽畜場,結合雲端蒐集環境數據使用無線通訊建立網路拓撲,以低成本、快速安裝、分區檢測等創新,達到全方位量測效果;人工智慧禽畜行為影像辨識技術,因禽畜個體的健康狀態可由動物行為判斷,針對可研發之動物行為進行技術開發,以禽畜數據庫建立、行為檢測等創新,搭配人工智慧演算法進行禽畜行為影像辨識。實現禽畜預診斷健康檢測技術,透過人工智慧禽畜行為影像辨識技術與禽畜場域管理者、專家討論,藉由動物行為延伸進行動物健康預檢測,以滑軌式移動攝影系統、健康預診斷等創新,達到預防禽畜疫情發生,降低禽畜場主損失的效果;智慧禽畜產能品質分析雲平台,整合多種數據,結合環境資料與禽畜健康狀況,從中比對禽畜產量、品質等資訊,進行產能品質的趨勢分析,以專家技術知識、多種大數據分析、產出品質分析等創新,提供禽畜場管理者更詳細的管理資訊,使其確保禽畜場個體安全、環境安全及食物安全。 |
英文摘要 |
In order to solve the problems of intelligent production and digital services in poultry farms, it will combine artificial intelligence (AI), robotics, internet of things (IoT), big data and other technologies to build an AI cloud sensing integration platform, and establish Brain AI, Cloud AI, and Edge AI, an AI ecosystem is established with precise placement, rapid sampling, and real-time screening. This paper proposes the key technology, an All-in-One monitoring and management system for smart environments, and the design of an E27 lamp-head type All-in-One environmental sensing and early warning device that can be quickly deployed in poultry farms. It combines the cloud to collect environmental data and uses wireless communication to establish a network topology. Innovations such as cost, quick installation, and zone detection achieve a full range of measurement results; an AI poultry behavior image recognition technology, because the health status of individual poultry can be judged by animal behavior, and technology development is carried out for researchable animal behaviors. Animal database establishment, behavior detection and other innovations, with an AI algorithm for image recognition of poultry behavior. Realize the pre-diagnosis and health detection technology of poultry, discuss with poultry farm managers and experts through AI and poultry behavior image recognition technology, and carry out pre-detection of animal health through extension of animal behavior. Diagnosis and other innovations can achieve the effect of preventing poultry epidemics and reducing the loss of poultry farmers; the intelligent poultry productivity and quality analysis cloud platform integrates multiple data, combining environmental data and poultry health conditions, and compares poultry production and quality carry out the trend analysis of production quality and other information, expert's know-how, a variety of big data analysis, output quality analysis and other innovations to provide more detailed management information for poultry farm managers to ensure individual safety, environmental safety of poultry farms and food safety. |
第三語言摘要 | |
論文目次 |
目錄 中文摘要 I 英文摘要 II 目錄 IV 圖目錄 VII 表目錄 XI 第一章 緒論 1 1.1 前言 1 1.2 研究動機 2 1.3 研究目的 3 1.4 相關研究文獻探討 5 1.4.1 人工智慧技術於禽畜飼養應用 5 1.4.2 無線網路技術新穎性應用 6 1.4.3 禽畜行為影像與健康辨識技術之應用 7 1.4.4 物聯網技術於禽畜飼養應用 8 1.5 研究主題與主要貢獻 8 1.6 論文架構 9 第二章 人工智慧物聯網蛋雞飼養環境分析之系統架構 10 2.1 智慧環境全方位監控管理系統 10 2.2 人工智慧蛋雞飼養生態圈 12 第三章 蛋雞場之智慧裝置資料收集閘道設計 15 3.1 蛋雞場之智慧裝置與環境感測資料收集系統 15 3.1.1 智慧環境感測裝置研發 15 3.1.2 智慧環境感測裝置與中繼站研製成本分析 21 3.1.3 蛋雞場域環境挑戰 22 3.1.4 “蛋雞一條龍”控制中心APP與網頁 23 3.2 蛋雞場之智慧裝置資料收集閘道優化 28 3.3 環境數據與蛋雞生理數據關聯性分析 30 第四章 人工智慧蛋雞飼養系統 32 4.1 人工智慧之雞隻行為影像辨識系統 32 4.2 雞隻行為之滑軌式移動攝影系統設計 37 4.3 AI Money智慧蛋雞飼養之雞蛋成本與獲利評估系統 44 第五章 蛋雞場雞檢體取樣裝置設計 46 5.1 智慧裝置球型機器人聯合機構設計 46 5.2 球中球結構於蛋雞場雞檢體取樣設計 47 5.3 拖曳裝置結構於蛋雞場雞檢體取樣設計 49 第六章 智慧裝置資料收集閘道於蛋雞場田野實際架設 51 6.1 蛋雞場介紹 51 6.1.1 傳統開放式蛋雞場 51 6.1.2 密閉水簾式蛋雞場 52 6.2 蛋雞場實際架設成果 53 第七章 結論與未來展望 69 7.1 結論 69 7.2 未來展望 69 參考文獻 71 圖目錄 圖1. 1 人工智慧物聯網之蛋雞飼養環境分析系統架構 4 圖1. 2 人工智慧物聯網之蛋雞飼養環境分析系統主要功能介紹 4 圖2. 1 智慧環境全方位監控管理系統 11 圖2. 2 人工智慧蛋雞飼養生態圈系統架構 14 圖3. 1 智慧環境感測裝置產品化開發史 15 圖3. 2 環境感測系統架構 17 圖3. 3 智慧環境感測裝置 17 圖3. 4 智慧環境感測裝置V2 滑蓋式壓克力外殼設計 18 圖3. 5 智慧環境感測裝置V4滑動卡槽上蓋設計 18 圖3. 6 智慧環境感測裝置V4內部紗網及抽風設計 18 圖3. 7 智慧環境感測裝置V5上蓋通風孔設計 18 圖3. 8 智慧環境感測裝置V5底部壁掛式開孔設計 18 圖3. 9 二氧化碳感測儀 19 圖3. 10 氨氣感測儀 19 圖3. 11 智慧環境感測裝置V5&V6 電路設計 20 圖3. 12 蛋雞場環境架設問題 23 圖3. 13 蛋雞場環境架設解決 23 圖3. 14 “蛋雞一條龍” APP 操作介面 24 圖3. 15 “蛋雞一條龍”控制中心網頁 25 圖3. 16 蛋雞場田野試驗大數據環境感測資訊 27 圖3. 17 LINE群組環境異常預警通知 28 圖3. 18 智慧環境感測裝置組與中繼站 29 圖3. 19 分區建立微型區域伺服器系統測試環境平面圖 29 圖3. 20 關聯度分析之柱狀圖結果 30 圖3. 21 關聯度分析之數值結果 31 圖3. 22 環境溫度與產蛋量分析 31 圖4. 1 人工智慧之雞隻行為影像辨識流程[37] 32 圖4. 2 YOLOv4辨識雞隻與張嘴結果 33 圖4. 3 YOLOv4性能比較 33 圖4. 4 CSP連接方法 34 圖4. 5 CmBN 35 圖4. 6 YOLOv4 Modified SAM 36 圖4. 7 YOLOv4 Modified PAN 36 圖4. 8 Mish Activation Function 37 圖4. 9 雞隻熱緊迫前兆之張嘴呼吸行為 37 圖4. 10 滑軌式移動攝影系統示意圖 38 圖4. 11 滑軌式移動攝影系統架設環境 38 圖4. 12 滑軌式移動攝影系統之設計 39 圖4. 13 雞隻張嘴辨識數量結果 41 圖4. 14 無張嘴辨識數量結果 43 圖4. 15 AI Money智慧蛋雞飼養之生產力評估系統架構圖 44 圖4. 16 AI Money生產力評估計算介面 45 圖5. 1 球型機器人機構剖面圖 47 圖5. 2 聯合機構實體圖 47 圖5. 3 球中球雞檢體取樣機器人 48 圖5. 4 外殼摩擦力優化初步設計 48 圖5. 5 球中球結構雞檢體取樣示意圖 48 圖5. 6 球中球結構雞檢體取樣結構圖 48 圖5. 7 拖曳裝置雞檢體取樣機器人 49 圖5. 8 拖曳裝置結構雞檢體取樣示意圖 50 圖5. 9 拖曳裝置雞檢體取樣結構圖 50 圖6. 1 拋棄式防塵衣 51 圖6. 2 消毒式隔離衣 51 圖6. 3 傳統開放式蛋雞場平面圖 52 圖6. 4 密閉水簾式蛋雞場平面圖 53 圖6. 5 智慧環境感測裝置進駐蛋雞場架設時程 53 圖6. 6 彰化雞場安裝環境 54 圖6. 7 嘉義雞場安裝環境 55 圖6. 8 屏東蛋雞場安裝環境 56 圖6. 9 回收之智慧環境感測裝置V2版 57 圖6. 10 感測器內部遭蟲隻侵入 57 圖6. 11 屏東蛋雞場之智慧環境感測裝置架設位置圖 59 圖6. 12 智慧環境感測裝置與中繼站架設A區入口左側 59 圖6. 13 智慧環境感測裝置架設A區末端左側 60 圖6. 14 屏東蛋雞場優化安裝環境 60 圖6. 15 增設中繼站實際平面位置圖 61 圖6. 16 增設中繼站之線路防咬保護措施 62 圖6. 17 手機APP遠端控制抽風扇 62 圖6. 18 平板網頁遠端控制抽風扇 62 圖6. 19 電源延長線路架設 63 圖6. 20 智慧環境感測裝置V4架設 63 圖6. 21 嘉義蛋雞場第一棟6部智慧環境感測裝置V4版安裝位置 63 圖6. 22 智慧環境感測裝置6部與中繼站2部實際架設 64 圖6. 23 Mesh WiFi之3部實際架設 65 圖6. 24 智慧環境感測裝置架設位置平面圖 65 圖6. 25 Mesh WiFi線路保護加工 66 圖6. 26 智慧環境感測裝置線路脫落 67 圖6. 27 智慧環境感測裝置內部加工 67 圖6. 28 雞場內改善智慧環境感測裝置訊號 68 圖6. 29 智慧環境感測裝置架設位置平面圖 68 圖7. 1 實現人工智慧雞隻行為之滑軌式移動攝影系統 70 圖7. 2 AI Money智慧蛋雞飼養之雞蛋成本與獲利評估系統 70 表目錄 表3. 1 智慧環境感測裝置規格 21 表3. 2 研製硬體成本 22 表3. 3 “蛋雞一條龍” APP 各功能說明 25 表5. 1球中球雞檢體取樣機器人規格 47 表5. 2 拖曳裝雞檢體取樣機器人規格 49 |
參考文獻 |
[1] 李盼, “全球智慧畜禽產業分析與案例研究,” 台灣經濟研究月刊, vol. 40, no. 3, pp. 48-57, 2017. [2] 李盼, 余祁暐, 吳明哲, “全球智慧生乳產業代表性案例研究,” 台灣經濟研究月刊, vol. 57, pp. 21-33, 2019. [3] M. H. Lashari, A. A. Memon, S. A. A. Shah, K. Nenwani and F. Shafqat, “IoT Based Poultry Environment Monitoring System,” 2018 IEEE International Conference on Internet of Things and Intelligence System (IOTAIS), pp. 1-5, Nov., 2018. [4] M. F. H. Hambali, R. K. Patchmuthu and A. T. Wan, “IoT Based Smart Poultry Farm in Brunei,” 2020 8th International Conference on Information and Communication Technology (ICoICT), pp. 1-5, June, 2020. [5] K. F. Ho, H. W. Hirai, Y. H. Kuo, H. M. Meng and K. K. Tsoi, “Indoor air monitoring platform and personal health reporting system: big data analytics for public health research,” 2015 IEEE International Congress on Big Data, pp. 309-312, June, 2015. [6] L. D. Quach, N. P. Quoc, N. H. Thi, D. C. Tran and M. F. Hassan, “Using SURF to Improve ResNet-50 Model for Poultry Disease Recognition Algorithm,” 2020 International Conference on Computational Intelligence (ICCI), pp. 317-321, Oct., 2020. [7] K. A. Sudduth, M. J. Woodward-Greene, B. W. Penning, M. A. Locke, A. R. Rivers and K. S. Veum, “AI down on the farm,” IT Professional, vol. 22, no. 3, pp. 22-26, 2020. [8] Y. Qun, Y. Zhang, X. Wang, Z. Zhou, P. Xian and F. Zhang, “Research on master-slave distributed large-scale poultry farming measurement and control system,” 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), pp. 552-557, July, 2019. [9] Y. Wu, J. D. Cui and H. F Cao, “Design of Bluetooth Mesh Network Switch Control System,” 2018 Eighth International Conference on Instrumentation & Measurement, Computer, Communication and Control (IMCCC), pp. 1604-1609, July, 2018. [10] R. Li and X. Li, “Directional Multi-path Routing Algorithm Based on BLE Mesh,” 2019 Cross Strait Quad-Regional Radio Science and Wireless Technology Conference (CSQRWC), pp. 1-3, July, 2019. [11] R. Li, X. Li and Y. Ding, “Link Prediction Algorithm for BLE Mesh Network in Health Monitoring System,” 2020 Chinese Control And Decision Conference (CCDC), pp. 1997-2001, Aug., 2020. [12] M. Jürgens, D. Meis, D. Möllers, F. Nolte, E. Stork, G. Vossen and H. Winkelmann, “Bluetooth Mesh Networks for Indoor Localization,” 2019 20th IEEE International Conference on Mobile Data Management (MDM), pp. 397-402, June, 2019. [13] Z. Hongxiang, D. Qing and L. Ming, “Telemetry System Based on MESH Network and Its Application,” 2020 IEEE International Conference on Artificial Intelligence and Information Systems (ICAIIS), pp. 217-220, Mar., 2020. [14] O. Esrafilian, R. Gangula and D. Gesbert, “Autonomous UAV-aided Mesh Wireless Networks,” IEEE INFOCOM 2020-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), pp. 634-640, July, 2020. [15] L. Wang, Y. Zhang and Z. Chen, “Automated Production Line Monitoring Base on Wireless Mesh Sensor Network,” 2020 39th Chinese Control Conference (CCC), pp. 6023-6027, July, 2020. [16] A. M. M. Chandran, M. Zawodniok and A. Phillips, “Convergence Communication over Heterogeneous Mesh Network for Disaster and Underserved Areas,” 2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC), pp. 1-4, Jan., 2020. [17] R. Kashyap, M. Azman and J. G. Panicker, “Ubiquitous Mesh: A Wireless Mesh Network for IoT Systems in Smart Homes and Smart Cities,” 2019 IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT), pp. 1-5, Feb., 2019. [18] T. Y. Lee, P. H. Truong, C. K. Lee and G. M. Jeong, “Range extension of LED control systems using a Bluetooth mesh network,” 2017 IEEE International Conference on Consumer Electronics (ICCE) ,pp. 166-167, Jan., 2017. [19] S. N. Chaitra, S. Singha, S. Ghorai, V. Nagesh and B. Samuel, “Getting Information about the Neighbour Street Light Using WIFI Mesh Network,” 2018 International Conference on Design Innovations for 3Cs Compute Communicate Control (ICDI3C), pp. 130-132, Apr., 2018. [20] M. Labraoui, M. M. Boc amd A. Fladenmuller, “Opportunistic SDN-controlled wireless mesh network for mobile traffic offloading,” 2017 International Conference on Selected Topics in Mobile and Wireless Networking (MoWNeT), pp. 1-7, May, 2017. [21] R. Widyastuti and C. K. Yang, “Cat’s nose recognition using you only look once (YOLO) and scale-invariant feature transform (SIFT),” 2018 IEEE 7th Global Conference on Consumer Electronics (GCCE), pp. 55-56, Oct., 2018. [22] J. Redmon, S. Divvala, R. Girshick and A. Farhadi, “You only look once: Unified, real-time object detection,” Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779-788, 2016. [23] J. Redmon and A. Farhadi, “YOLO9000: better, faster, stronger,” Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7263-7271, 2017. [24] J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018. [25] A. Bochkovskiy, C. Y. Wang and H. Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv preprint arXiv:2004.10934, 2020. [26] A. A. G. Raj and J. G. Jayanthi, “IoT-based real-time poultry monitoring and health status identification,” 2018 11th International Symposium on Mechatronics and its Applications (ISMA), pp. 1-7, Mar., 2018. [27] N. Monburinon, S. M. S. Zabir, N. Vechprasit, S. Utsumi and N. Shiratori, “A Novel Hierarchical Edge Computing Solution Based on Deep Learning for Distributed Image Recognition in IoT Systems,” 2019 4th International Conference on Information Technology (InCIT), pp. 294-299, Oct., 2019. [28] Deepika, Nagarathna, Channegowda, “Monitoring and Detection of Heat Stress of Layers in Poultry Farm using Multiple Linear Regression,” 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT), pp. 1186-1191, 2020. [29] J. Marder and Z. Arad, “Panting and acid-base regulation in heat stressed birds,” Comparative Biochemistry and Physiology Part A: Physiology, vol. 94, no. 3, pp. 395-400, 1989. [30] L. J. Lara and M. H. Rostagno, “Impact of heat stress on poultry production,” Animals, vol. 3, no.2, pp. 356-369, 2013. [31] M. N. Elham, M. S. Sabeghi, F. S. Al-Rasbi, S. M. Daud, N. Q. Noor, R. Sahak and A. A. Mazlan, “A Preliminary Study on Poultry Farm Environmental Monitoring using Internet of Things and Blockchain Technology,” 2020 IEEE 10th Symposium on Computer Applications & Industrial Electronics (ISCAIE), pp. 273-276, Apr., 2020. [32] R. D. M. Nicolas, W. S. Zhou, S. C. Kitamura and M. J. C. Samonte, “An IoT Monitoring Assistant for Chicken Layer Farms,” 2019 International Conference on Information and Communication Technology Convergence (ICTC), pp. 71-75, Oct., 2019. [33] N. Manshor, A. R. A. Rahiman and M. K. Yazed, “Iot based poultry house monitoring,” 2019 2nd International Conference on Communication Engineering and Technology (ICCET), pp. 72-75, Apr., 2019. [34] Y. H. Lee, H. W. Tseng, Y. D.Liao, T. W. Lin, Y. L. Chen and Y. S. Ho, “Study on Environmental Parameters and Wearing Electrocardiogram,” Sensors and Materials, vol. 31, no. 3, pp. 993-1006, 2019. [35] Y. H. Lee, H. W. Tseng, T. W. Lin, Y. D. Liao, Y. C. Chang, Y. G. Liu and M. Y. Tsai, “Smart Fan Control Using Kalman Filter and Fuzzy Control Algorithm on Bluetooth Received Signal Strength Indicator (RSSI),” Journal of Environmental Protection and Ecology, vol. 18, no. 3, pp. 985-992, 2017. [36] Jan, Y. G., Tseng, H. W., Lee, Y. H., Lo, C. Y., & Yen, L. Y. (2014). Accurate bluetooth positioning using weighting and large number of devices measurements. Wireless personal communications, 79(2), 1129-1143. [37] 黃聖智, “人工智慧之雞隻行為影像判定系統,” 淡江大學電機工程學系碩士班學位論文, pp. 1-56, 2020. [38] C. Y. Wang, H. Y. Mark Liao, Y. H. Wu, P. Y. Chen, J. W. Hsieh and I. H..Yeh, “CSPNet: A new backbone that can enhance learning capability of cnn,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 390-391, 2020. [39] Z. Yao, Y. Cao, S. Zheng, G. Huang and S. Lin, “Cross-iteration batch normalization,” arXiv preprint arXiv:2002.05712, 2020. [40] S. Woo, J. Park, J. Y. Lee and I. So Kweon, “Cbam: Convolutional block attention module,” Proceedings of the European conference on computer vision (ECCV), pp. 3-19, 2018. [41] S. Liu, L. Qi, H. Qin, J. Shi and J. Jia, “Path aggregation network for instance segmentation,” Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 8759-8768, 2018. [42] D. Misra, “Mish: A self regularized non-monotonic neural activation function,” arXiv preprint arXiv:1908.08681, 2019. |
論文全文使用權限 |
如有問題,歡迎洽詢!
圖書館數位資訊組 (02)2621-5656 轉 2487 或 來信