運用倒傳遞類神經網路於端銑削表面粗糙度預測系統

The Development of a Neural Network Surface Roughness Prediction System in End Milling Operations

莊英川(Ying-Chuan Chuang)

指導教授 ： 黃博滄

中原大學/電機資訊學院/工業與系統工程研究所/碩士(2016年)

https://doi.org/10.6840/cycu201600562

摘要

近年來隨著工業的進步及各項產品的創新與開發，電腦輔助製造中的電腦數值控制(Computer Numerical Control, CNC)工具機銑削加工的需求也隨之增大,藍圖上加工尺寸的精度要求也越來越高，使得CNC 銑削技術的研究成為各自動化產業注重的議題。在CNC銑削加工後，對於表面粗糙度的掌控會對品質的好壞產生極大的影響，為了能達到準確的表面粗糙度，許多學者希望利用預測的方式，透過預測可以減少加工參數的設定時間來達到所要的表面粗糙度，來降低其額外成本，並且提高產品品質。許多學者仍然大都使用感測器來做預測，但是感測器實際在安裝上並不是想像中來得容易，而且還需要額外的感測器費用，在實際業界使用上並不多見。
因此本研究主要是利用在無感測器的情況下加入硬度這項因子去收集數據，再以倒傳遞類神經網路去預測出表面粗糙度來驗證其方法會比無加入硬度因子來得有效性及準確性。在倒傳遞類神經網路中需要輸入因子才能得到所需的預測值，但是輸入因子過多或是過少皆可能影響到其網路的預測準確性，故本研究在類神經網路訓練前，先利用相關度分析，將各因子與硬度作關聯性的分析，並且把不必要的因子剔除，再進行類神經網路的訓練及預測，本研究經實驗證明使用相關分析篩減因子後，經過類神經網路訓練可達到理想的預測結果。
為證明所提出方法之可靠性及準確性，本研究方法先後使用了相關度分析、倒傳遞類神經網路及假設檢定中的t檢定做分析與驗證，建置出表面粗糙度預測系統，最後再使用兩母體進行t檢定，分別假設為有加入硬度因子為實驗組，無加入硬度因子為對照組，最後比較出在t檢定下有加入硬度因子會比無加入硬度因子的結果更顯著，進而證明出有加入硬度因子的表面粗糙度預測系統比無加入硬度因子的預測系統來得較可靠性及準確性。

關鍵字：硬度、表面粗糙度、倒傳遞類神經網路、預測系統

關鍵字

硬度 ； 表面粗糙度 ； 倒傳遞類神經網路 ； 預測系統

並列摘要

Because of progressions of industries as well as innovations of products, the requirement for CNC (Computer Numerical Control) machining process of computer assisted manufacturing and demands for accuracy of dimensions is growing up, which makes studies about CNC milling process essential topics when it comes to automatic industries. After CNC machining, the influence of surface roughness affects the quality profoundly, and many savants wish to employ approaches of prediction to curtail the time consumed by setting parameters and obtain ideal surface roughness that not only cut down extra costs but also provide quality improvements. However, many of them still stick to utilizing sensors to accomplish those predictions, but installations of that equipment are far more arduous than that we can imagine. These methods are rare in real practice in that high costs are required.
In this study, adding the factor of hardness to collect data without any sensor is presented, and higher accuracy as well as effectiveness, comparing to conditions without factor of hardness, are achieved by employing BPNN (Back-Propagation Neural Network) for prediction of surface roughness. Elements inputted into BPNN lead to reasonable predictions, but the number of them affects the accuracies of predictions. This study analyzes the correlations between input elements and hardness using grey relation analysis before training for BPNN. After removing unnecessary elements, training for BPNN and predicting, this study proves that ideal prediction can be obtained by utilizing BPNN with deletion of peripheral factors.
For not only certifying but also analyzing the reliability and accuracy of the approach, this research employs correlation analysis, Back-Propagation Neural Network and t-test of hypothesis testing before establishing a surface roughness prediction system. These two systems are put to the t-test, which includes experimental group with hardness factors and control group without them. Base on the results of tests mentioned above, the prediction system with hardness factors possesses higher reliability and accuracy than those without.

Keyword: hardness, surface roughness, BPNN(Back-Propagation Neural Network), prediction system.

並列關鍵字

hardness ； surface roughness ； BPNN(Back-Propagation Neural Network) ； prediction system

參考文獻

陳久弘，運用灰關聯因子分析與類神經網路於銑削表面粗糙度即時預測系統，碩士論文，中原大學，2012。

Bhuiyan, M. S. H., Choudhury, I. A., & Dahari, M. (2014). Monitoring the tool wear, surface roughness and chip formation occurrences using multiple sensors in turning. Journal of Manufacturing Systems, 33(4), 476-487.

Cakir, M. C., & Isik, Y. (2005). Detecting tool breakage in turning aisi 1050 steel using coated and uncoated cutting tools. Journal of Materials Processing Technology, 159(2), 191-198.

Chen, J. C., & Huang, B. (2003). An in-process neural network-based surface roughness prediction (INN-SRP) system using a dynamometer in end milling operations. The International journal of Advanced Manufacturing Technology,21(5), 339-347.

Chen, J. C., & Lou, M. S. (2000). Fuzzy-nets based approach to using an accelerometer for an in-process surface roughness prediction system in milling operations. International Journal of Computer Integrated Manufacturing, 13(4), 358-368.