等离子体刻蚀工艺中的光学发射光谱仪数据的模型研究(英文)

原位光学发射光谱仪(OES)已经成为等离子体刻蚀工艺控制过程中的一种非常有潜力的在线传感器系统。采用光谱仪实时采集高密度等离子体刻蚀机中的OES光谱数据,利用BP神经网络算法对特定波长的OES数据进行分析及建模,以便对等离子体刻蚀工艺过程进行反馈控制。由刻蚀产物SiCl发出的405nm谱线被选为特征谱线来确定刻蚀工艺过程的终点。

Modelling of Optical Eemission Spectrometer Data for Plasma Etching Processes

In situ optical emission spectrometer has been a promising technology for in-line sensor systems for plasma etching process control. The neural network offers great promise in modeling complex fabrication processes such as high density plasma (HDP) etching process. The plasma etching process is monitored in real time with optical emissions spectrometer (OES). Using neural network to model the real time in suit OES data for real time, model based feedback control of plasma etching process is investigated. The SiCl 405 nm from OES spectra range is chosen as the characterized wavelength to call the endpoint detection of the etching process.