查詢結果分析
相關文獻
- 胚料特性對內齒輪冷精鍛製程的影響分析與預測
- 以有限元素模擬及類神經網路進行內齒輪冷精鍛模具應力分析與預測
- 類神經網路應用於型材彎曲之研究
- 材料特性對鍛粗凸脹變形影響及預測模式建構
- Neural Network Procedures for Taguchi's Dynamic Problems
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
- 專家系統振動訊號圖型判別之研究
- 反傳遞模糊類神經網路於流量推估之應用
- 類神經網路(Neural Networks)的種類及其在影像處理上的應用
- C++Fuzzy類神經網路物件導向發展系統之建立
頁籤選單縮合
題名 | 胚料特性對內齒輪冷精鍛製程的影響分析與預測=An Influence Analysis and Prediction of Billet's Characters on the Cold Precision Forging for Internal Gear |
---|---|
作者姓名(中文) | 許源泉; 林萬益; 萬國禎; |
作者姓名(外文) | Hsu, Yuan-chuan; Lin, Wann-yih; Hwang, Gwo-jen; |
書刊名 | 國立虎尾科技大學學報 |
卷期 | 26:1 2007.03[民96.03] |
頁次 | 頁1-10 |
分類號 | 446.886 |
語文 | chi |
關鍵詞 | 內齒輪; 冷精鍛; 有限元素模擬; 類神經網路; Internal gear; Cold precision forging; Finite element simulation; Neural network; |
中文摘要 | 齒輪是各類機械中應用極為廣泛的重要傳動零件,以冷精鍛成形的齒輪因具有節省材料、強度高、抗疲勞性能佳等等諸多優點,因此以塑性成形法來加工齒輪已倍受重視。本研究乃應用三維剛塑性有限元素數值模擬技術進行內齒輪的冷精鍛塑性成形分析,並探討內徑、外徑、應變硬化指數、材料強度係數及表面粗糙度等胚料特性對冷精鍛負荷的影響,其後利用類神經網路建構出這五種胚料特性與冷精鍛負荷的關係預測模式。研究發現,胚料之內徑、外徑、高度等對內齒輪冷精鍛的變形及品質有相當影響,但對成形負荷的影響並不顯著,而胚料之應變硬化指數、材料強度係數及表面粗糙度等對成形負荷則有較為顯著的影響,這三者數值越大,所需負荷也越高。此外,利用類神經網路進行胚料特性與內齒輪冷精鍛負荷的預測具有相當的方便性與信賴性。 |
英文摘要 | Gear is an important component or part used in mechanical system to transmit power. The process of precision gear forging has been developed recently because of its advantage of material and cost reduction, improved gear strength and fatigue resistance. Therefore, the forming process used for manufacturing gears has been a focus technique now. In the current study, the 3D rigid-plastic finite element simulation technique was used to analyze the plastic forming of cold forging for internal gear. The influences of characters such as inside diameter, outside diameter, harden-strained exponent, strength coefficient and surface roughness, on cold forging loads were explored firstly. Then, the relation predictive model of the five billets’ characters to the cold forging load was constructed through the neural network. The results indicated that the inside diameter, outside diameter and height of billet had obvious influence on the forging deformation and product quality, but their influence on forging load was less. The harden-strained exponent, strength coefficient and surface roughness of billet had obvious influence on forging load, and the larger values the three characters had, the higher forging load it needed. The predictive model constructed by neural network can also provide valuable references in predicting the forging deformation and forging load for internal gear. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。