全國中小學科展

工程學

聲子晶體結合共振腔與其聲音放大效果之研究

本研究以 zig-zag path 管道自製、設計聲子晶體,並結合空腔(cavity)形成類似電路學的 RLC 共振結構,透過 COMSOL 軟體模擬出其理論之特徵頻率,使空腔中心聲壓達到穩定的放大效果。利用無響室的環境進行實驗,藉由放大電路將聲壓轉為電訊號並以聲源頻率、裝置距離和空腔尺寸作為變因,發現我們自製的聲子晶體可成功將電壓放大約 2.6 倍。此種聲子晶體具有體積小、構造簡單、可擴充為多晶體結構等特性,在未來可結合壓電材料,將其製成兼具發電與降噪功能之環保裝置。

運用LSTM深度學習技術調整PID控制於倒單擺應用之探討

本研究以深度學習 RNN(Recurrent Neural Network)演算法中的 LSTM(Long Short Term memory)改善 PID,利用其時間序列的保留資料方法,預測 PID 參數值,使控制器得以精確且快速的調整非線性系統。此研究從 peak amplitude 及transient time,以及倒單擺振幅的圖表收斂情形等層面去做探討。當單擺質量大於下方 pendulum cart 的質量時,傳統的 PID 控制方法無法精準的調整系統,而LSTM 深度學習模型能夠產生較佳且較顯著的效果。且KP 數值在倒單擺系統中, 小於 1 無法收斂,KP 數值越小時,圖形越趨發散。此訓練之 LSTM 深度學習模型可以應用於非線性系統中,以增加其穩定性,並能夠更快速的為系統找到適合 的 PID 參數值。

Design a program on identifying Proliferation rate of HABs

Due to global population growth and industrialization, excessive inflow of causative nitrogen into rivers, and the increase in water temperature due to global warming, the occurrence of harmful algal blooms (HABs) is increasing. HABs can cause not only ecological destruction but also various social and economic problems. Additionally, consuming water from lakes with abundant toxic cyanobacteria can lead to liver damage, vomiting, abdominal pain, and even death if consumed over a long period. The first recorded occurrence of animal mortality due to HABs was in Australia in 1878, and since then, livestock and wildlife have suffered damages from HABs worldwide. Furthermore, the United States' Lake Erie has experienced frequent HAB occurrences since 2011, and in 2007, China faced social disruption when a massive HAB outbreak in Lake Tai, one of the freshwater lakes, resulted in a suspension of the water supply. In order to address these HAB occurrence issues and assess the severity of HAB events, several systems have already been established and potential solutions have been proposed. However, these systems have limitations such as being highly systematic and advanced in terms of equipment and configuration. They are often located only in periodically affected areas, and they involve substantial costs. Therefore, we aim to overcome these limitations and design a system that can effectively manage HABs.

探討護木漆塗層對於抑制金屬升溫之影響

本研究探討將護木漆塗在不鏽鋼及鋁片上對於熱輻射吸收及降溫效果的影響,從實驗結果中可以看到塗上護木漆後的不鏽鋼樣品在可見光範圍的吸收雖增加 29.7W/m²,但在 8µm~12µm紅外光範圍的熱輻射增加 38.2W/m²,約增加 11.2倍,而鋁片樣品在可見光範圍的吸收減少 1W/m²,紅外光範圍的熱輻射則增加 38.6W/m²,約增加 25.9倍,故護木漆能有效增加熱輻射效率,減少能量吸收,而本研究亦證實樣品的輻射冷卻效 能,在晴天時樣品溫度最多可降低 3.4度及 2.7度,故此種方法能有效抑制升溫,並希望未來能應用於建築及儲油槽外壁上,以減少冷氣使用及火災發生頻率。

Look your eyes,know your life~A portable body detection device

本研究是基於去年的 PBC(Protect Brain Cylinder)作品[1],並根據評審指導將作品做了大幅度修改。相較於 PBC 需要一個額外的裝置,本研究僅須在手機相機前方,安裝光源處理模組,搭配本團隊開發的 App,即可清楚地拍攝出瞳孔影像。並經由 App 中的影像分析功能,即可在影像拍攝完成後的兩秒內完成分析, 並將結果繪圖呈現在手機螢幕上。偵測的時間相較 PBC,大幅縮短了 60%。 相較 PBC 僅能偵測患者瞳孔直徑對光刺激的反應速度。本研究除了大幅縮短偵測的時間外,在結果分析及應用上更有長足的進步,能判斷出以下的五種身體狀況: (1)瞳孔形狀 (2)虹膜脂質堆積環 (3)鞏膜血絲分布及比例 (4)水晶體混濁與白內障關係 (5)瞳孔直徑對光刺激的反應速度與酒測值的關係 本研究除了藉由偵測瞳孔來判定身體狀況外,更開發出了身體『傷口大小量化』功能。希望協助醫護人員一機在手,即可解決上列的臨床問題。

以CFD模擬探討熱對流發電裝置之效率

本研究為 111 年度綠色化學創意競賽《熱對流發電裝置之效率研究》之延續性作品,該作品中,我們已得知高度、內外溫度差以及儲氣量對發電效率的影響,因此我們想要進行更深入的研究。 本研究中,有兩個主要的研究方向,分別是管路材質以及風扇數量對熱對流發電裝置之風速影響。本實驗使用AnsysFluent 軟體進行CFD 模擬,在模擬結果中,我們發現鐵管相對於PVC 管,能使流速提高。風扇數量的增加,也會使流速提高,進而推測可使發電效率增加。 我們也希望能開發綠能智慧路燈、模擬導流板對流速的影響以及風扇葉片轉動的效率,讓整個研究更完備。

Utilization of Coffee Protein and its Antimicrobial and Antioxidant Properties for Biodegradable Active Packaging Membranes

隨著全球咖啡市場擴大,永續的咖啡生產成為必須探討的議題。咖啡生產過程中會產生大量富含蛋白質與抑菌成分的副產物和廢棄物,有潛力可做為膠膜和塗層的原料。本研究從生咖啡豆中萃取出粗蛋白質,將其與海藻酸鈉混合烘乾成膠膜,再進行抑菌與水果保鮮和水蒸氣阻隔測試。 由結果得知:咖啡豆蛋白膠膜液對大腸桿菌有抑制生長的效果。沒封膜的蘋果切片失水率 12.72%,有膠膜封口的失水率在 6.84%~8.47%,比沒封膜的失水率降低 46.5%~33.1%,顯示膠膜保水性佳,可提高保鮮效果。微波加熱試驗沒封膜的水蒸氣散失率為 2.45%,膠膜試驗組中最 低為 0.15%,比沒封膜的散失率降低 93%,顯示具有良好的水蒸氣阻隔性。 本研究結果顯示咖啡豆蛋白質膠膜有抑制大腸桿菌生長的效果和良好的氣體阻隔性,可作為可生物降解的食品包裝材料,以替代傳統保鮮膜,有助於減少環境污染。

利用六軸加速度計回饋控制之車輛動態防側傾駕駛輔助系統

車輛在轉彎時會產生法線方向的加速度導致側傾。本研究以 Arduino、MPU-9250 加速度傳感器模組、光電傳感器等,換算成速度、側傾角資料後,回饋控制車輛移動,再利用其它設備的輔助觀察感測器的準確性。本實驗計畫利用加速度計的資料開發一個車輛防側傾駕駛輔助系統。首先,利用 MATLAB Simulink 模擬車輛在不同環境下傾倒時的各項感測器數值變化,以縮短實際實驗所需的時間。接著計算出車輛發生傾倒所需要跨越的數值門檻,並在電腦中撰寫一套防側傾的策略,分析側傾的原因以及量值後,控制車輛的轉彎方向以及速度,使其回到正常行駛的平面。最後模擬完成後,再將模擬的系統實裝回到原本的模型車實驗驗證系統的可行性,並討論其成功率。

Beyond Limits: An Intelligent Wheelchair for Inclusive Living

The aim of this project is to enhance the mobility of individuals with disabilities, particularly aiding them in navigating stairs and challenging terrains. Across the world, powered wheelchair employ various methods, primarily categorized into two: 1) tracked mechanisms and 2) robotic wheelchair utilizing intricate robotic systems. The design presented by our team belongs to the latter category, which is recognized for its lighter build when contrasted with the former. However, despite its lightweight structure, this wheelchair design incorporates equipment that renders it more cost-effective and practical than conventional designs within the same category. Our design integrates three distinct mechanisms to adjust the height and center of mass of the passenger during stair climbing and maintain balance and surface contact. Utilizing an array of sensors, it continuously monitors the position of the person on the wheelchair and the wheelchair on the surface. This data guides adjustments in the mechanisms, ensuring stability. This innovation harbors the potential for enhancing various functionalities, including: GPS integration for user navigation. Real-time monitoring of vital signs (e.g., heart rate, blood pressure, body temperature). In an emergency, this data can be transmitted to ambulance centers to pinpoint the individual's location and immediate assistance. A simplified ambulance request system, accessible via a single button press. Overall, this innovative wheelchair prototypes aims to revolutionize accessibility, granting enhanced mobility and independence to individuals with disabilities.

AGRO-GUARD:Machine Learning-Driven Plant Real-Time Disease Detection,Clustering and Community Notifications

Agro-guard aims to revolutionize disease identification and community-based projects in the field of agriculture. Integrating Machine learning, Computer vision, clustering, and community-based technology, this project helped farmers to detect their plant disease with their solution and for early warning of plant disease which was spreading in their community which helped in crop management. The research project is divided into three parts.First,Integrating Machine learning to detect and classify plant disease with their solutions.Second,Integrating Density-Based Spatial Clustering of Applications with Noise (DBSCAN),to identify disease and analyze the pattern within agricultural regions.Third,Establishing notification system to notify real-time alerts to farmers about disease spreading in particular region.The research is crucial because it solve one of the crucial problem of our community which is untimely detection of disease.The finding of the research highlight the effectiveness of Agro-Guard framework in early disease detection and community detection.The machine learning models achieved high accuracy in identifying common plant disease and clustering results the pattern in diseases that were very important for notifying the community.The significance of these findings is that it can build powerful system which will overall grow the production of crops and plants due to timely update of the disease prevailing in the community.It contributes in sustainability production of crops and plants which ultimately ensure the good livelihood of farmer.