ИСТИНА |
Войти в систему Регистрация |
|
ИСТИНА ЦЭМИ РАН |
||
Optical emission spectroscopy is widely used for monitoring of low-temperature plasmas in science and technology. However, determination of temperature from optical emission spectra is an inverse problem that is often very difficult to solve steadily by conventional methods. This paper reports successful application of artificial neural networks (ANN) and group method of data handling (GMDH) for determination of gas temperature from model optical emission spectra analogous to those recorded in a DC-discharge CVD reactor used for diamond film deposition.