透過您的圖書館登入
IP:54.198.146.224
  • 學位論文

建構以銑削尺寸為依據之灰色刀具壽命預警系統

Construction of Grey Tool Life Alerting System Based on Milling Dimension

指導教授 : 黃博滄

摘要


隨著近年來市場趨勢的改變,機械製造加工從過去的大量生產,漸漸演變成了少量多樣高品質及客製化為主流,因為產品週期急遽縮短,必須快速達到客戶的要求,所以各界紛紛提出許多模型、方法進行生產前的預測、模擬、回歸分析、各種軟性計算的方式建立出系統,但是以上種種方法都有一個缺點,皆必須使用大量的數據進行建立模型,這對於現今加工的方式並不合用,甚至會因為不同加工條件需要重新調整參數,使用上極為不方便。故本研究透過灰色理論,針對銑削尺寸建立出一套刀具壽命預測系統,希望透過少量數據投入系統,可預測出刀具壽命,且不會受到加工參數、材料的影響。 本研究所建立的灰色刀具壽命預測系統,利用灰色理論中的灰色生成,將投入的數據找出期趨勢,並利用灰色預測只需要小樣本的優勢作為基本架構,然而在將數據投入灰色預測是利用AGO累加生成,利用數據間的趨勢特性建立模型預測資料。本研究則是運用於CNC銑削加工,能透過少量數據去預測刀具壽命,不僅不需要考量刀具、材料、參數,就能迅速預測出刀具壽命。 為了驗證本研究所提出的方法有其準確性及穩定性,設置一組相同參數及另一組不同參數,投入少量的尺寸數據進行灰色預測系統,進行尺寸趨勢的預測,藉此判斷刀具的使用壽命,並分析本系統的準確性,用以驗證本研究所提出的預測系統的可用性。 對於預測可加工數與實際可加工數之間的誤差進行預測的準確度分析,實驗的預測準確度皆高於90%,且三組實驗的平均預測準確度為94.14%,可見在本研究所建立的刀具壽命灰色預測系統有其一定的準確度,修正過後的預測值能提早預警於實際可加工數,避免加工過程中已經有不良品出而還未發出警報。

並列摘要


As the market trend changes these years, small volume, large variety and customization substitute mass production in mechanical manufacturing process. We have to reach customers’ request quickly because of sharp product cycle declination. Consequently, many researchers have proposed models and methods, such as prediction, simulate, and soft computing before production to build system. However, there is a disadvantage above the methods. That is, we must use large amounts of data to build models, which is unfavorable to productions nowadays. It’s inconvenient that we even need to change parameter because of different manufacturing conditions. This research will build a tool life predict system through grey theory which is aimed at milling dimension. We hope that we can get predictions of tools by less data used in the system. Besides, the system won’t be influenced by manufacturing parameter and materials. This research build a grey tool life prediction system, using the Grey Generating Operation in grey theory. A method which emphasizes the input data trend and uses its small sample feature as the fundamental structure for building a real time prediction system. Grey prediction is a small-scale prediction model built upon accumulated generating sequence and the forecasting characteristics among data. When data input grey prediction system be used Accumulated Generating Operation (AGO). It is used on CNC milling process in this research in which a tool’s operating life is predicted based on a small amount of dimension data. To prove the proposed method is both accurate and reliable, setting same parameters and other a parameter. Input the less data is going to predict in grey prediction system, taking determine tool's life and investigate its accuracy to verify the feasibility of the prediction system proposed in this research. In the actual value and predicted value error to do accurate analysis. Predictive accuracy were higher than 90% in experiment. So this grey tool life prediction system is up to par. Correct predict value can alert earlier than actual value. To avoid there have been bad for a while yet alert in milling process.

並列關鍵字

Milling dimension Grey theory Tool life Insert MR chart

參考文獻


洪國禎、吳國榮. (2008). 改良式GM(1,1)灰預測模型於台電電量需求預測之研究.
陳嘉聲. (2008). 改良式非等間距灰預測模型. (碩士), 國立成功大學, 台南市.
陳金聖、邱駿展、林士傑. (2007). 基於灰色預測與模糊推論之工業檢測高速自動對焦.
何建霖. (2001). 電腦輔助塑膠模具設計製造 能力本位訓練教材 訂定公差: 行政院勞工委員會職業訓練局.
Ahilan, C., Kumanan, S., Sivakumaran, N., & Edwin Raja Dhas, J. (2013). Modeling and prediction of machining quality in CNC turning process using intelligent hybrid decision making tools. Applied Soft Computing. 13(3). 1543-1551.

延伸閱讀