研究生: |
簡梓婷 Tzu-Ting Chien |
---|---|
論文名稱: |
結合IoT網路與人工智慧於即時追蹤隧道內機具狀態之研究 Research on Integrating IoT Networking and Artificial Intelligence for Real-time Tracking of Machinery Status Inside Tunnels |
指導教授: |
謝佑明
Yo-Ming Hsieh |
口試委員: |
陳鴻銘
Hung-Ming Chen 莊子毅 Tzu-Yi Chuang 謝佑明 Yo-Ming Hsieh |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 營建工程系 Department of Civil and Construction Engineering |
論文出版年: | 2023 |
畢業學年度: | 111 |
語文別: | 中文 |
論文頁數: | 100 |
中文關鍵詞: | 工程機具 、物聯網 、機器學習 、數據分析 、線形無線感測器網路 |
外文關鍵詞: | Construction Machinery, IoT, Machine Learning, Data Analysis, Linear Wireless Sensor Networks (LWSNs) |
相關次數: | 點閱:269 下載:12 |
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 |
於隧道開挖過程中,機具需不斷向內深入,一項工程中也有多工作面同時進行的情況,不易掌握各機具工作情況,作業環境的實態監測中,若能即時追蹤機具狀態,並且將其統整量化像是工作時間等,雇主則可根據結果進行現場改善。
本研究設計在每台隧道內工作之機具上安裝一自行開發之IoT裝置記錄機具之三軸向之加速度、三方向之角速度讀值等訊號,經過分析處理後推論出該機具目前之狀態後,將機具狀態透過藍牙發送,由IoT無線電收發站接收後向隧道洞口外發送,即可達成即時機具狀態的記錄。
為了快速取得相關資料進行分析確認其可行性,本研究初期使用智慧型手機,撰寫其上之應用程式進行資料的採集,並將採集結果所得數據進行監督式機器學習分類,由辨別準確率來評估其可行性。
本研究擬以低功耗長距離無線電LoRa建構隧道內之通訊網路,以將隧道內所收集到的資料傳出洞外至工務所供後續分析利用。為避免LoRa直接傳遞的廣播風暴不利於耗電量優化,及LoRaWAN星狀拓樸架構不利於隧道內線形傳遞,本研究自行開發網路並透過傳遞成功率來了解其可行性。
During tunnel excavation, machinery needs to continuously advance inward. In projects with multiple faces active simultaneously, it becomes challenging to monitor the individual machinery operations effectively. Real-time tracking of machinery status in the context of operational environment monitoring, coupled with quantitative parameters such as working hours, could enable employers to make on-site improvements based on the results.
In this study, we designed an IoT device to be installed on each piece of machinery working inside the tunnel. This device records signals such as three-axis acceleration and three-axis angular velocity of the machinery . After analyzing and processing these signals, the current state of the machinery is inferred. The machinery status is then transmitted via Bluetooth to an IoT wireless station, which forwards the information to the tunnel entrance. This achieves real-time recording and management of machinery status.
To quickly obtain relevant data for analysis and confirm its feasibility, in the initial stage of this study, a smartphone was used. An application was developed on the smartphone for data collection. The collected data was then subjected to supervised machine learning classification to evaluate its feasibility based on recognition accuracy.
This study aims to establish a communication network within the tunnel using Low-Power Wide-Area Network (LPWAN) technology, specifically Long Range (LoRa). This network will transmit the collected data from inside the tunnel to the engineering office for subsequent analysis. To mitigate data storms caused by direct LoRa transmission, which can negatively impact power consumption optimization, and to address the limitations of a LoRaWAN star topology that hinders linear transmission within the tunnel, this study has developed its own network architecture. The feasibility of this network is assessed through transmission success rates.
[1] Ahn, C.R., S. Lee, and F. Peña-Mora, Monitoring System for Operational Efficiency and Environmental Performance of Construction Operations Using Vibration Signal Analysis, in Construction Research Congress 2012. 2012. p. 1879-1888.
[2] Ahn, C.R., S. Lee, and F. Peña-Mora, Acceleromter-Based Measurement of Construction Equipment Operating Efficiency for Monitoring Environmental Performance, in Computing in Civil Engineering (2013). 2013. p. 565-572.
[3] Ahn, C.R., S. Lee, and F. Peña-Mora, Application of Low-Cost Accelerometers for Measuring the Operational Efficiency of a Construction Equipment Fleet. Journal of Computing in Civil Engineering, 2013. 29(2): p. 04014042.
[4] Mathur, N., et al., Automated Cycle Time Measurement and Analysis of Excavator’s Loading Operation Using Smart Phone-Embedded IMU Sensors, in Computing in Civil Engineering 2015. 2015. p. 215-222.
[5] Gao, G., et al., Human Behavior Recognition Model Based on Feature and Classifier Selection. Sensors, 2021. 21(23): p. 77-91.
[6] Rogage, K., et al., Beyond digital shadows: A Digital Twin for monitoring earthwork operation in large infrastructure projects. AI in Civil Engineering, 2022. 1(1): p. 7.
[7] Kennedy, G.A. and M.D. Bedford, Underground wireless networking: A performance evaluation of communication standards for tunnelling and mining. Tunnelling and Underground Space Technology, 2014. 43: p. 157-170.
[8] Mekki, K., et al., A comparative study of LPWAN technologies for large-scale IoT deployment. ICT Express, 2019. 5(1): p. 1-7.
[9] Zimmerling, M., W. Dargie, and J.M. Reason, Energy-Efficient Routing in Linear Wireless Sensor Networks, in 2007 IEEE International Conference on Mobile Adhoc and Sensor Systems. 2007. p. 1-3.
[10] Jawhar, I., N. Mohamed, and D.P. Agrawal, Linear wireless sensor networks: Classification and applications. Journal of Network and Computer Applications, 2011. 34(5): p. 1671-1682.
[11] Al Imran, M.A., et al., Optimal operation mode selection for energy-efficient light-weight multi-hop time synchronization in linear wireless sensor networks. EURASIP Journal on Wireless Communications and Networking, 2020. 2020(1): p. 109.
[12] Deepa, S., Bidirectional Linear Wireless Sensor Networks, in 2022 International Interdisciplinary Humanitarian Conference for Sustainability (IIHC). 2022. p. 1059-1065.
[13] Supervised Learning Workflow and Algorithms. from: https://www.mathworks.com/help/stats/supervised-learning-machine-learning-workflow-and-algorithms.html?s_tid=srchtitle_site_search_5_support%20vector%20machine%20%20%20memory%20usage.
[14] Xioumi Pocophone F1 Photo. from: https://m.media-amazon.com/images/I/61LghzBuGzL._SL1000_.jpg.
[15] SHARP. AQUOS V 智慧型手機. 2020; from: https://tw.sharp/products/aquos_v.
[16] Leica DISTO D510 雷射測距儀. from: https://geosystems.com.tw/leica-disto/leica-disto-d510/.
[17] Inc., B. Brinno BCC100 縮時攝影相機. from: https://brinno.com/zh/pages/product-bcc100.
[18] Ltd., P. LoPy4. 2017; from: https://docs.pycom.io/datasheets/development/lopy4/.
[19] HelTec Automation Technology Co., L. Wireless Stick – Heltec Automation. 2020; from: https://heltec.org/project/wireless-stick/.
[20] GY-91. from: https://ae01.alicdn.com/kf/H4a97d03865ad49e19ee29d0525a17454U/MPU-9250-MPU9250-BMP280-SPI-IIC-I2C-10DOF-Acceleration-Gyroscope-Compass-9-Axis-Sensor-Board-Module.jpg.
[21] GY-9255. from: https://5.imimg.com/data5/SELLER/Default/2023/1/SC/GU/CI/23669504/1483-gy9255-9dof-sensor-module-ai.jpg.
[22] NCR18650B. from: https://cdn.shopify.com/s/files/1/0448/9583/0172/products/panasonic-ncr18650-b-3400mah-10a-battery-protected-button-top-269477_800x.jpg?v=1637046753.
[23] 認識 Android Studio. from: https://developer.android.com/studio/intro?hl=zh-tw.
[24] MATLAB - Wikipedia. from: https://zh.wikipedia.org/zh-tw/MATLAB.
[25] Pymakr - Visual Studio Marketplace. from: https://marketplace.visualstudio.com/items?itemName=pycom.Pymakr.
[26] Arduino. Overview of the Arduino IDE 1. from: https://docs.arduino.cc/software/ide-v1/tutorials/Environment.
[27] Getting Started with Arduino IDE 2. from: https://docs.arduino.cc/software/ide-v2/tutorials/getting-started-ide-v2.
[28] LoRa Alliance. from: https://lora-alliance.org/.
[29] OSI模型. from: https://zh.wikipedia.org/zh-tw/OSI%E6%A8%A1%E5%9E%8B