中国物理B ›› 2009, Vol. 18 ›› Issue (6): 2441-2444.doi: 10.1088/1674-1056/18/6/053

• • 上一篇    下一篇

Prediction of the plasma distribution using artificial neural network

王腾1, 李炜2, 陈俊芳2   

  1. (1)School of Computer, South China Normal University, Guangzhou 510631, China; (2)School of Physics and Telecommunication Engineering, South China Normal University, Guangzhou 510006, China
  • 收稿日期:2008-12-02 修回日期:2008-12-19 出版日期:2009-06-20 发布日期:2009-06-20
  • 基金资助:
    Project supported by the National Natural Science Foundation of China (Grant No 10575039).

Prediction of the plasma distribution using an artificial neural network

Li Wei(李炜)a), Chen Jun-Fang(陈俊芳)a)†, and Wang Teng(王腾)b)   

  1. a School of Physics and Telecommunication Engineering, South China Normal University, Guangzhou 510006, China; b School of Computer, South China Normal University, Guangzhou 510631, China
  • Received:2008-12-02 Revised:2008-12-19 Online:2009-06-20 Published:2009-06-20
  • Supported by:
    Project supported by the National Natural Science Foundation of China (Grant No 10575039).

PDF (PC)

1008

赞

摘要： In this work, an artificial neural network (ANN) model is established using a back-propagation training algorithm in order to predict the plasma spatial distribution in an electron cyclotron resonance (ECR) --- plasma-enhanced chemical vapor deposition (PECVD) plasma system. In our model, there are three layers: the input layer, the hidden layer and the output layer. The input layer is composed of five neurons: the radial position, the axial position, the gas pressure, the microwave power and the magnet coil current. The output layer is our target output neuron: the plasma density. The accuracy of our prediction is tested with the experimental data obtained by a Langmuir probe, and ANN results show a good agreement with the experimental data. It is concluded that ANN is a useful tool in dealing with some nonlinear problems of the plasma spatial distribution.

关键词: artificial neural network, ECR-PECVD plasma, distribution

Abstract: In this work, an artificial neural network (ANN) model is established using a back-propagation training algorithm in order to predict the plasma spatial distribution in an electron cyclotron resonance (ECR) --- plasma-enhanced chemical vapor deposition (PECVD) plasma system. In our model, there are three layers: the input layer, the hidden layer and the output layer. The input layer is composed of five neurons: the radial position, the axial position, the gas pressure, the microwave power and the magnet coil current. The output layer is our target output neuron: the plasma density. The accuracy of our prediction is tested with the experimental data obtained by a Langmuir probe, and ANN results show a good agreement with the experimental data. It is concluded that ANN is a useful tool in dealing with some nonlinear problems of the plasma spatial distribution.

Key words: artificial neural network, ECR-PECVD plasma, distribution

中图分类号:  (Plasma-based ion implantation and deposition)

  • 52.77.Dq
52.25.-b (Plasma properties) 52.70.Ds (Electric and magnetic measurements) 52.70.Gw (Radio-frequency and microwave measurements)