查詢結果分析
相關文獻
- Monitoring Surface Roughness Using Force Signals for Turning
- 劈裂式鑽頭鑽削複合材料之力學模式研究
- 回轉圓盤刀具木材三次元切削之研究
- 燒結鍛造時燒結體自由表面粗度的變化
- 杉木壓縮木材二次元切削之研究
- 磁力研磨應用於去毛頭的技術
- 由金屬切削力學談刀具切削相關問題
- 限制接觸正交切削的切削力預測
- 表面粗度對纖維強化高分子複合材料高溫氧化壽命影響之預測與實證
- A Study of Effects of Polishing Parameters on Surface Roughness and Flatness of Aluminum Based Rigid Disk
頁籤選單縮合
題 名 | Monitoring Surface Roughness Using Force Signals for Turning=運用切削力訊號監測車削工件表面粗度 |
---|---|
作 者 | 黃文鴻; 林士傑; | 書刊名 | 中國機械工程學刊 |
卷 期 | 18:1 1997.02[民86.02] |
頁 次 | 頁23-29 |
分類號 | 446.893 |
關鍵詞 | 切削力; 車削工件; 表面粗度; Surface roughness; Monitoring; |
語 文 | 英文(English) |
中文摘要 | 本文利用切削力的分析來監測車削工件表面粗度。我們採用類神經網路以及回歸 模式來建立表面粗度與切削力訊號的關係。我們以進給以及在三個不同方向的切削力標準差 與切削力平均值作為輸入訊號。實驗發現我們可以利用訓練好之類神經網路作表面粗度監測 。而利用類神經網路作表面粗度監測準確性略高於回歸模式。 |
英文摘要 | The primary objective of this research is to monitor surface roughness generated during turning operations. In this paper, surface roughness monitoring is carried out by measuring and analyzing force signals. Neural network, using a cumulative back-propagation algorithm, is adopted to monitor surface roughness based on force signals measured. Inputs to the neural network are feedrate and the ratios between standard deviations and mean values of force signals. It is confirmed experimentally that the surface roughness can be well estimated by trained neural networks. The feasibility of using regression model to monitor surface roughness is also studied. It is found that the accuracy of surface roughness estimation using the neural network is slightly better than that using regression model. |
本系統中英文摘要資訊取自各篇刊載內容。