全國中小學科展

工程學

開發影像辨識系統應用於離岸流偵測預警

離岸流是海灘安全的重大隱患,台灣有30處海岸經衛星拍攝到離岸流。其發生時間和地點不定,且會迅速將人帶離岸邊,最遠約100公尺。民眾常因掙扎而體力不支,導致溺斃。為減少此類事故,本研究開發了一套離岸流偵測預警系統,構建出準確度超過95%的辨識模型。 因台灣無離岸流圖庫,本研究除國外圖庫,也加入台灣GoOcean等平台的即時影像,以貼合台灣實際狀況。經影像前處理後,共約四萬張圖片和五十部影片用於訓練YOLO v8模型。當偵測到離岸流,即時透過Discord發送警報至救難中心。我們也加入人形辨識功能,若系統同時偵測到人與離岸流,則加強警戒等級,從而提升救援效率。 完成離岸流辨識系統後,我們著手開發預警功能。將辨識模型應用於各地監視器,蒐集更多離岸流資料,再先後使用YOLO v8和Transformer提取生成特徵,預測其發生,以達成預警的功能。

Autonomous Ecosystem Surveillance Vehicle

As of 2021, there are 368 harmful algae blooms and over 6000 invasive species in the United States of America. Furthermore, it is reported that the United States spends more than 11.1 billion dollars per year on clean-up methods for marine debris. However, there currently isn’t a method to monitor aquatic problems simultaneously, autonomously, and efficiently, creating a capability in the aquatic biosecurity sector. To combat this, we have created an autonomous vehicle that can conduct long-term monitoring of freshwater bodies for up to 60 hours.

Design and Simulation of a Honeycomb Sandwich Panel as a Heat-resistant and Durable Construction Material

One of the main factors that contribute to fire incidents and the excessive heat people feel during a heat wave is the building materials used, and one such material that possesses durable and heat-resistant properties is sandwich panels. A possible structure that can be used to model sandwich panels is honeycomb structures; however, further research has yet to be conducted on its applications as a heat-resistant urban construction material. This study aims to design a three-dimensional model of a honeycomb sandwich panel and simulate its performance under different thermal and structural stressors. A 3D model of the honeycomb sandwich panel was generated using Autodesk Fusion 360. Then, multiple versions of the panel were generated with varying heat-resistant core materials—namely, aluminum, nickel, nickel-copper alloy 400, and copper—along with polystyrene as the core material for the control model. The following properties of every panel were assessed using finite element analysis (FEA): static deformation, stress distribution, strain distribution, total heat flux, and thermal gradient. Results showed that when subjected to varying structural loads (2 kN, 5 kN, 7 kN), the nickel-core panel demonstrated the best results in terms of static deformation and strain distribution due to its relatively lower deformation and elongation values, respectively. Meanwhile, under the same structural loads, the aluminum-core panel performed better than other core materials in terms of stress distribution due to it having the relatively highest difference between its simulated von Mises stress and its yield strength. The honeycomb sandwich panels have also shown to possess heat-resistivity when subjected to a thermal load of 90°C, with polystyrene being the most promising material overall in terms of heat-resistance due to its relatively lower heat flux and thermal gradient. The results from this study would contribute to future research on honeycomb sandwich panels and may be used in real-life applications.

點亮絲路:碳量子點螢光蠶絲的製備與光降解環境污染物之應用

本研究以電紡絲法製作光動力活性的碳量子點(carbon quantum dots, CQDs)螢光蠶絲,用於光降解環境染劑汙染物與抗菌的應用探討。不同顏色螢光的碳量子點 紅、綠、藍色)的合成是以檸檬酸作為主要碳源,分別參雜尿素與葉綠素用以合成三種螢光的碳量子點。接著將絲素蛋白、聚乙二醇與量子點溶液為原料,以電紡絲法分別製作成藍色、綠色與紅色的螢光蠶絲。螢光光譜儀 PL)與穿透式電子顯微鏡 TEM)結果呈現量子點的光學特性與尺寸呈現預期的量子效應。拉曼光譜則證實電紡絲法之螢光蠶絲具有絲素蛋白、聚乙二醇與量子點的特徵訊號。本研究使用之電紡絲法製備之螢光蠶絲,與我們之前使用蠶寶寶桑葉餵食法生產之螢光蠶絲來比較,電紡絲螢光蠶絲具有更加優異及穩定的光降解環境汙染物效率,未來可用於自清潔、抗菌織物與醫療敷料之應用。

基於LSTM行為與活動力之樂齡關懷系統

本研究開發基於RNN和LSTM的獨居者居家行為監控系統,利用樹莓派、多種無侵入式感測器及鏡頭實現獨居者日常活動的實時監控與情緒評估。系統收集各感應器數據,透過 LSTM 進行學習與預測,並使用隨機森林演算法分析行為狀態,提供客製化數據處理與預測性能優化。 長期數據收集可觀察獨居者的活動力及情緒變化,早期發現健康風險,針對現有求救設備頻繁異常通知的問題,我們開發了能夠識別長期身心狀況變化的監測系統,並整合人體紅外線感應器、都卜勒雷達感應器、日夜感測器等技術,透過Python程式及MQTT進行數據收集與處理。模型訓練使用SQLite資料庫數據,經過多次測試選擇最佳參數以提高預測準確度,隨機 森林演算法也強化決策準確性。 通過長期的數據收集和分析,本系統能夠觀察並預測獨居者的活動力和情緒的變化,早期發現獨居者的身心健康是否有風險。

影像辨識 在 智慧運輸系統 的應用 自動跟隨

本研究旨在開發一款能自動跟隨人的AI智慧運輸車,應用在 醫院、商場等環境,能減輕工作人員的負擔。本系統融合YOLOv8影像辨識技術和物聯網,使運輸車具備跟隨人體的能力。該系統通過物聯網,將車上攝影機接收的影像傳送至電腦,進行即時運算,不必在車上配備高階的微型電腦或GPU以降低成本。使用YOLOv8模型辨識人體與手勢,以arduino ESP32開發板作為主控單元控制減速馬達,使運輸車能自動跟隨人員。本研究不像傳統自動導引車(AGV),因為依賴固定路徑,而無法用在多變的場景,且不適合與人協同工作。將本系統應用於醫療院所或零售業商場等 ,經常出現 變障礙物的場所時,能與人員配合執行任務,例如當作病人的點滴架、輔助護理師工作的醫務車,以及賣場中協助工作人員上貨的籠車,能有效降低勞力負擔。

以農電共生方式提升台灣太陽能總發電量

台灣現行的「毀農式種電」政策犧牲農地以增進太陽能發電,導致農業用地縮減、農民收入減少,能源需求與農業發展間產生衝突。我們參考日本成功的農電共生模式,提出一種可滑動的太陽能發電系統,利用Arduino控制太陽能板的開合,兼顧農地種植與發電效能。此系統結合植物光合作用原理,特別適合種植半日照作物或具有光合午休特性的植物。當植物進行光合午休時,太陽能板滑動展開以提高發電量;在強光高溫時段,太陽能板則可遮蔽陽光,避免植物葉片受損。此方案不僅能恢復「毀農式種電」土地的種植功能,也讓農民獲得穩定收入,實現農業與綠能發展的平衡。這套模型提供具體且可行的解決方案,期望在提升台灣總發電量的同時,達成淨零減碳目標,並促進農業的永續發展。

Mattress Ventilation System

One of the worldwide hidden problems with lack of attention is Bedsores. Simply, These are ulcers, that happen on the areas of the skin that are under pressure while lying on the bed for a prolonged time. This can be infected to anyone in the world. The common group who face these bed sores are..... •Elderly patients, •Spinal cord injury patients, •Stroke patients, •Coma patients, •People who have faced accidents Bed sores develop when the blood supply is cut off for more than 2-3 hours to the skin, (Position changing time depends on the patient's condition) The continuous pressure is the cause for that and also the temperature generated between the skin and the bed surface increases the metabolism of the tissues. When the skin temperature increases by 1°C, the risk of bed sores increases approximately 14 times. So, The skin temperature in the range of 29.4°C to 37.1°C is correlated with the tissue damage score. Not only that shearing and moisture are the other considerable factors for this problem. This infection has 4 stages. Sometimes in the 4th stage of the bed sores can cause death.

A Study on Hybrid Electromechanical Actuators

An actuator [7,22,28,29] is a motion control mechanism. Depending on the type of actuator, it can convert one type of energy (e.g. chemical, electromagnetic, thermal) into mechanical energy. The field that laid the foundations for the realization of actuators is the field of electromechanics, whose evolution was common with that of actuators. Thus, a periodization of the electromechanics paradigm includes 3 major stages [7,6,25,28,29]: I.1830-1950 Old electromechanics. It is the period when the development of electric cars is significant, which imposed the appearance of classical or primary electromechanical drives. It was a generous nineteenth century, dominated by the scientific results of the triumvirate: Michel Faraday (initiator of fundamental empirical experiments in the history of electricity; the law of induction, of the principle of electric motor, of the magnetic circuit, initiator of electro-chemistry), James Clerk Maxwell, (the genius theorist who put into mathematical form the equations of electric and magnetic fields, as well as the connection between them), and Werner Siemens (engineer and capitalist genius manager who managed to exploit and validate the relationship research-technology-economic development), triumvirate that can be disputed in the sense that other scientists also made outstanding contributions to the history of electricity: Edison, Ampere, Ohm (to name but a few who do not exhaust a significant list). Industrial production of electric machines also appeared and the first signs that will announce the emergence of electromechanical actuators as a basis for military applications. II.1950-1970, Traditional electromechanics, in which electrical power drives appear, a theoretical and experimental development on the emergence of new material and electromechanical principles. Much military research (such as missile control or ship and torpedo control) influences and produces the transfer of applications in ordinary life, including the actuator subfield. III. 1970-2020, Avant-garde electromechanics, representing according to Thomas Kuhn's theory, a paradigm forcing [30]. It is worth noting the contributions of the new scientific revolution. - Specific technologies of miniaturization, by material deposition. - Elastomeric polymeric materials with the help of which it was possible to make electrostrictive actuators, - Very special means of investigation, mainly the development of microscopy, - Gradient of applications in the field of medical engineering, with outstanding contributions both in investigation and microsurgery, applications of actuators in biological micropumps, etc. [25,27,28,29].

開發影像辨識系統應用於離岸流偵測預警

離岸流是海灘安全的重大隱患,台灣有30處海岸經衛星拍攝到離岸流。其發生時間和地點不定,且會迅速將人帶離岸邊,最遠約100公尺。民眾常因掙扎而體力不支,導致溺斃。為減少此類事故,本研究開發了一套離岸流偵測預警系統,構建出準確度超過95%的辨識模型。 因台灣無離岸流圖庫,本研究除國外圖庫,也加入台灣GoOcean等平台的即時影像,以貼合台灣實際狀況。經影像前處理後,共約四萬張圖片和五十部影片用於訓練YOLO v8模型。當偵測到離岸流,即時透過Discord發送警報至救難中心。我們也加入人形辨識功能,若系統同時偵測到人與離岸流,則加強警戒等級,從而提升救援效率。 完成離岸流辨識系統後,我們著手開發預警功能。將辨識模型應用於各地監視器,蒐集更多離岸流資料,再先後使用YOLO v8和Transformer提取生成特徵,預測其發生,以達成預警的功能。