:::

詳目顯示

回上一頁
題名:應用類神經網路技術於III-V族化合物半導體磊晶片電流增益預測
書刊名:品質學報
作者:鄭春生陳佩雯李聰智
作者(外文):Cheng, Chuen-shengChen, Pei-wenLee, Tsung-chih
出版日期:2012
卷期:19:4
頁次:頁393-404
主題關鍵詞:化合物半導體類神經網路反應曲面法預測Compound semiconductorArtificial neural networkResponse surface methodologyPrediction
原始連結:連回原系統網址new window
相關次數:
  • 被引用次數被引用次數:期刊(0) 博士論文(0) 專書(0) 專書論文(0)
  • 排除自我引用排除自我引用:0
  • 共同引用共同引用:0
  • 點閱點閱:27
在過去,類神經網路已經被成功地應用於建立預測模型。本論文說明如何建立一個類神經網路,來預測生產微波主動元件之磊晶製程的電流增益。本研究利用實驗設計之反應曲面法,來決定類神經網路之連續型重要參數。為了進一步提升類神經網路之預測績效,我們提出以分割資料子集之方式,來訓練多個類神經網路,產生數個預測模型來進行預測。本研究是以平均絕對百分比誤差作為績效指標,利用實際之製程數據來建立類神經網路並驗證其績效。根據經驗及專業知識,我們以電力(power)來作為分割資料子集之基礎。研究結果顯示,利用本研究所提出之分割資料子集法來訓練類神經網路,可以有效地提升預測之績效。
In recent years, the photoelectric technology has been successfully and widely applied to wireless communication, fiber-optical, solar power, display and illumination industry. The function of photoelectric products is relied on the device performance of compound semiconductor epitaxy wafer with quality and yield that are dominated by substrate and epitaxy technology mainly. The destroyed test with high cost and sampling risk is implemented to assure the current gain of epitaxy wafer.This study proposes a prediction model for current gain based on artificial neural networks (ANNs). Response surface methodology was employed to optimize the parameters of ANN prediction model. In order to enhance the prediction accuracy, the training dataset was partitioned off into three subsets and trained by three separate ANN models. Real data collected from manufacturing process are provided in this study to demonstrate the superiority of the proposed ANN prediction model. The results indicate that the proposed ANN prediction model performs better than traditional regression analysis method. Neural networks trained by partitioned data subsets can predict better than the neural network trained by the whole dataset.
其他
1.M. O. Alade, S. F. Akande, G. R. Fajinmi, A. S. Adewumi and M. Alade(2009)。Prediction of the breakdown voltage of n-GaN schottky diodes at high temperatures using online neural network analysis。  new window
2.T. Chen and Y.-C. Lin(2009)。A fuzzy back propagation network ensemble with example classification for lot output time prediction in a wafer fa。  new window
3.W. S. Choi, M. T. Lim and B. Kim(2004)。Prediction of etch profile uniformity using wavelet and neural network, International Journal of Control。  new window
4.Y.-S. Kim and B.-J. Yum(2004)。Robust design of multilayer feedforward neural networks: an experimental approach。  new window
5.F. S. Lasheras, J. A. V. Vilán, P. J. G. Nieto and J. J. D. C. Díaz(2010)。The use of design of experiments to improve a neural network model in order to predict the thickness of the chromium layer in a hard chromium plating process。  new window
6.Y.-H. Liang(2009)。Combining seasonal time series ARIMA method and neural networks with genetic algorithms for predicting the production value of the mechanical industry in Taiwan。  new window
7.D. C. Montgomery(2008)。Design and Analysis of Experiments。  new window
8.Y. Pan, B. Yan, S. Haider, H. Wang, H. Zheng and N. G. Ing(1999)。High gain high power-added-efficiency self-aligned AlGaAs/GaAs HBTs suitable for wireless communication application。  new window
9.P. K. Patowari, P. Saha and P. K. Mishra(2010)。Artificial neural network model in surface modification by EDM using tungsten-copper powder metallurgy sintered electrodes。  new window
10.W. Sukthomya and J. Tannock(2005)。The optimisation of neural network parameters using Taguchi’s design of experiments approach: an application in manufacturing process modelling。  new window
11.A. G. Williamson(1995)。Refining a neural network credit application vetting system with a genetic algorithm。  new window
12.W. Zou, Y. Li and A. Tang(2009)。Effects of the number of hidden nodes used in a structured-based neural network on the reliability of image classification。  new window
 
 
 
 
第一頁 上一頁 下一頁 最後一頁 top
QR Code
QRCODE