https://ir.lib.ncu.edu.tw/handle/987654321/107 Search the Channel s https://ir.lib.ncu.edu.tw/simple-search https://ir.lib.ncu.edu.tw/handle/987654321/111465 title: 擴散接合技術發展評估及鋁/銅實作;A Review of Diffusion Bonding Technology Development and Experimental Verification with Aluminum-to-Copper Bonding abstract: 擴散接合（diffusion bonding， DB）是一種在低於母材熔點的溫度下，藉外加壓力與保溫促進界面原子互擴散而形成冶金鍵結的固態接合技術。相較於熔融銲接與釬焊，可避免熔池凝固缺陷、熱影響區軟化與填料引入，適用於鋁合金、異質金屬與精密結構之接合。本研究以「擴散接合技術發展評估」與「鋁/銅異質材料實作驗證」為主題，先由固態接合原理、表面接觸、原子擴散、孔洞消除與界面反應建立分析架構，再依材料系統分為同質鋁及鋁合金與異質鋁/銅兩條主線，整合文獻並釐清各自的關鍵限制。在同質鋁及鋁合金部分，本研究整合純鋁、AA2024、AA6061、AA6061-AA1050 與Al-Li 合金等文獻，指出鋁合金並非不能擴散接合，其困難主要來自熱力學穩定且緻密的Al2O3 原生氧化膜、表面粗糙峰所形成的空氣袋與殘留孔洞，以及熱處理型鋁合金在接合熱循環後析出強化狀態的改變。文獻顯示，若能降低表面粗糙度、破壞或分散氧化膜、提高真實接觸面積、控制真空或保護氣氛，並於接合後施以適當的T4/T6 後熱處理，鋁合金擴散接合仍可獲得高完整性界面與具工程意義的接合強度。在異質鋁/銅部分，鋁與銅在電性與熱性上互補，並具輕量化與成本優勢，但兩者化學親和性強，界面易生成多種Al-Cu 金屬間化合物（如Al2Cu、AlCu、Al3Cu4、Al2Cu3、Al4Cu9 等）。薄而連續的反應層有助於冶金鍵結，過厚則會提高界面硬度、降低延性並形成脆性裂紋路徑。因此本研究將鋁/銅擴散接合的核心歸納為「破膜、貼合與控相」之平衡，並以作者實作之T2 銅與1060 鋁擴散接合、依ASTM D1002 單搭接拉伸剪切概念進行力學驗證。結果顯示，在595 至615 ?C、10 MPa、真空5 × 10?5 torr 的製程窗口 下，接合界面強度均高於1060 鋁母材，所有拉伸試片皆破斷於鋁母材並伴隨延性變形；斷面光學顯微觀察可見連續且無明顯缺陷的界面，並形成約28 至52 ? <br> Tue, 20 Oct 2026 10:19:51 GMT https://ir.lib.ncu.edu.tw/handle/987654321/111313 title: 應用影像追蹤技術於凸輪輪廓逆向重建方法之建立：以木製仿生蜂鳥機構為例;Development of an Image-Tracking-Based Reverse Reconstruction Method for Cam Profiles: A Case Study of a Wooden Biomimetic Hummingbird Mechanism abstract: 本研究以Derek Hugger設計之Colibri木製仿生蜂鳥機構為對象，建立一套以單視角公開影片之外部週期位移為輸入，逆向重建等效凸輪輪廓的方法。公開影片經解析度重取樣與影格插值後，以Tracker完成尺度標定、座標設定與特徵點追蹤，取得撲翼垂向位移、尾羽展收與胸腔起伏三個子系統之時間－位移資料。尾羽與胸腔資料先扣除撲翼相關構件之共同位移。其後以Mathematica進行單週期切分、端點閉合、Hampel異常點抑制及 Fourier 週期擬合，建立角度域位移函數。再依等效基圓與滾子幾何生成節曲線及滾子補償後凸輪輪廓。本文建立10條主要理論關係式，並以閉合、曲率／欠切、自交／非鄰近間距及法向一致性四類條件進行建模前幾何檢核。各凸輪輪廓於單週期輸出2，000點。驗證階段依購得之原廠設計資料建立兩組同架構 CAD／ADAMS模型。原廠凸輪工作輪廓不參與影像量測、訊號處理與重建參數選定，僅於重建完成後作為獨立基準，以避免重建與驗證資料互相回饋。除凸輪幾何外，兩組模型其餘條件一致。三子系統之均方根誤差分別為0.307、0.294與0.362 mm，升距幅值比分別為0.978、1.003與0.965；對應總升距差異為−2.2%、+0.3%與−3.5%。結果顯示，重建模型可再現原廠基準模型之週期位移特徵與總升距。本方法僅需單視角公開影片與少數固定構件尺寸，無須拆解實體或接觸式量測，即可取得可供CAD與多體動力學分析之等效凸輪輪廓。研究成果定位為運動功能等效重建，不主張唯一復原原廠凸輪幾何。;This study develops an image-tracking-based method for reverse reconstruction of equivalent cam profiles from observable periodic motion in Derek Hugger’s Colibri wooden biomimetic hummingbird mechanism. After spatial-resolution resampling and frame interpolation， Tracker is used for scale calibration， coordinate definition， and feature-point tracking. Time-displacement data are obtained for wing vertical displacement， tail deployment and retraction， and chest oscillation; common wing-related motion is removed from the tail and chest data to obtain relative displacement. Mathematica is then used for single-cycle extraction， endpoint closure， Hampel outlier suppression， and Fourier periodic fitting to establish angular-domain displacement functions. The formulation comprises ten principal theoretical relations. Pitch curves and roller-compensated cam profiles are generated and checked against four pre-modeling geometric criteria: closure， curvature/undercut， self-intersection/non-adjacent spacing， and normal consistency; each profile is exported with 2，000 points per cycle. For validation， purchased design data are used to construct two CAD/ADAMS models with the same mechanism architecture. The original cam working profiles are excluded from image measurement， signal processing， and reconstruction-parameter selection and are introduced only after reconstruction as an independent validation reference， thereby preventing feedback between reconstruction and validation data. Except for the cam profiles， the two models share identical non-cam geometry， assembly relationships， and simulation conditions. Root-mean-square errors are 0.307， 0.294， and 0.362 mm， while lift-amplitude ratios are 0.978， 1.003， and 0.965， corresponding to total-lift differences of −2.2%， +0.3%， and −3.5%. The reconstructed models therefore reproduce the principal periodic displacement characteristics and total lift of the reference models. The method requires only a single-view publicly available video and a few fixed-component dimensions， without physical disassembly or contact measurement， and yields equivalent cam profiles suitable for CAD and multibody-dynamics analysis. The results represent functional-equivalence reconstruction rather than unique recovery of the original cam geometry. <br> Tue, 20 Oct 2026 09:15:26 GMT https://ir.lib.ncu.edu.tw/handle/987654321/111309 title: 應用CAD二次開發技術於低背隙滾子凸輪設計與傳動性能驗證;Application of CAD Secondary Development Technology to the Design of Low-Backlash Roller Cam and Transmission Performance Verification abstract: 本研究針對既有滾子凸輪研究較少整合CAD運動軌跡建模、槽寬比較、曲線修正與雙向動態驗證之問題，建立低背隙滾子凸輪之設計驗證流程。首先利用SolidWorks Motion取得滾子相對主動輪之運動軌跡，反推槽道中心螺旋曲線，再串接VBA、Mathematica與SolidWorks完成點位擷取、偏移計算及模型重建，並以ADAMS進行單向完整週期與雙向運轉模擬。原始曲線共取樣801點，平均相鄰點距0.3066 mm，最大局部弦高量級約1.3 μm，低於10 μm偏移修正尺度。結果顯示，單側名義間隙30 μm之W1006僅完成約10%理論輸出而判定失效；有效模型中，W1008相較W1010之傳動誤差角均方根值降低34.8%，輸出端等效背隙角降低40.1%，但W1010具有較低接觸負載，顯示槽寬設計存在傳動精度、背隙與接觸負載之取捨。固定10.10 mm槽寬並施加最大10 μm漸進式偏移後，P75之反向響應時間差由0.031 s降至0.012 s，降低61.3%，輸出端等效背隙角由4.446″降至0.522″，降低88.3%。結果顯示，在不進一步縮小槽寬之前提下，微量修正槽道中心曲線可有效改善低背隙反向響應；所建立流程可於實體加工前比較槽寬調整與曲線修正策略，並降低試作與修模需求，作為後續滾子凸輪槽道設計與動態驗證之參考。;This study develops an integrated design and verification process for low-backlash roller cams by combining CAD-based motion trajectory modeling， groove-width comparison， curve correction， and multibody dynamics simulation. SolidWorks Motion was used to obtain the roller trajectory relative to the driving cam and derive the groove center curve; VBA and Mathematica were then applied for point extraction， offset calculation， and model reconstruction， followed by ADAMS simulations. The curve was sampled at 801 points with a mean spacing of 0.3066 mm and a maximum local chord-height magnitude of approximately 1.3 μm， below the 10 μm correction scale. W1006， with a nominal single-side clearance of 30 μm， completed only about 10% of the theoretical output and was classified as invalid. Among the valid models， W1008 reduced the RMS transmission error by 34.8% and the equivalent backlash angle by 40.1% compared with W1010， whereas W1010 produced a lower contact load， indicating a trade-off among accuracy， backlash， and contact load. With the groove width fixed at 10.10 mm， the P75 correction reduced the reverse response delay from 0.031 s to 0.012 s and the equivalent backlash angle from 4.446 arcsec to 0.522 arcsec， corresponding to reductions of 61.3% and 88.3%， respectively. The proposed process enables groove-width and curve-correction strategies to be evaluated before manufacturing， reducing prototyping and rework requirements. <br> Tue, 20 Oct 2026 09:15:08 GMT https://ir.lib.ncu.edu.tw/handle/987654321/111305 title: 特種重型車輛懸吊參數優化與減振性能分析;特種重型車輛懸吊參數優化與減振性能分析 abstract: 本研究針對搭載精密設備之特種重型車輛進行懸吊系統優化分析，由於此類車輛具有高重心與載重集中特性，於不平整路面行駛時容易產生較大振動與側傾現象，進而影響車輛操安性與車廂內部之振動環境，因此，本研究以降低車廂振動反應為目標，建立結合TruckSim、多體動力學分析、ISO 8608隨機路面模型與代理模型優化之分析流程。首先利用TruckSim建立整車模型，並依據實車量測資料設定車輛幾何尺寸、質量分布與懸吊參數，再透過定圓迴轉試驗進行模擬與實車結果比對，以驗證模型於穩態轉向及車身側傾反應之可信度，接著依據ISO 8608建立隨機不平整路面模型，並以車廂垂直加速度均方根值(RMS)作為減振性能評估指標，在優化部分，本研究採用均勻設計法規劃實驗樣本，並結合Isight、徑向基底函數(RBF)代理模型與多島遺傳演算法(MIGA)進行懸吊參數優化分析，模擬結果顯示，優化後之懸吊參數可降低車廂垂直振動反應，車廂垂直加速度RMS較原始設定降低約10.2%，經定圓迴轉與循跡能力比較後，優化後車輛仍可維持與原車相近之操安表現，顯示本研究所建立之優化流程可應用於特種重型車輛懸吊參數分析，並作為後續懸吊設計與振動分析之參考。;This study investigates suspension optimization for special heavy-duty vehicles equipped with precision instruments. Due to their high center of gravity and concentrated payload distribution， such vehicles are prone to excessive vibration and body roll when traveling on uneven roads， which may affect vehicle stability and the vibration environment inside the cabin. Therefore， this research aims to reduce cabin vibration responses by developing an integrated optimization framework combining TruckSim， multi-body dynamic simulation， ISO 8608 random road modeling， and surrogate-based optimization techniques. A full-vehicle dynamic model was first established in TruckSim using measured vehicle data， including geometric dimensions， mass distribution， and suspension parameters. The model was validated for steady-state cornering and body-roll responses through constant-radius cornering tests by comparing the simulation results with real vehicle test data. Random road profiles based on the ISO 8608 standard were then generated， and the RMS value of cabin vertical acceleration was adopted as the evaluation index for vibration performance. In the optimization process， the Uniform Design method was applied to generate experimental samples， while Isight， the Radial Basis Function (RBF) surrogate model， and the Multi-Island Genetic Algorithm (MIGA) were integrated to perform suspension parameter optimization. The simulation results show that the optimized suspension system effectively reduced cabin vibration responses. Compared with the original suspension configuration， the cabin vertical acceleration RMS was reduced by approximately 10.2%， while the subsequent constant-radius cornering and path-following evaluations showed that the optimized vehicle maintained handling performance comparable to the original configuration. These results indicate that the proposed optimization framework can be applied to suspension parameter analysis of special heavy-duty vehicles and can serve as a reference for subsequent suspension design and vibration analysis. <br> Tue, 20 Oct 2026 09:14:50 GMT