• Journal of the Semiconductor & Display Technology
• /
• v.18 no.2
• /
• pp.48-52
• /
• 2019

Virtual metrology, which is one of APC techniques, is a method to predict characteristics of manufactured films using machine learning with saving time and resources. As the photoresist is no longer a mask material for use in high aspect ratios as the CD is reduced, hard mask is introduced to solve such problems. Among many types of hard mask materials, amorphous carbon layer(ACL) is widely investigated due to its advantages of high etch selectivity than conventional photoresist, high optical transmittance, easy deposition process, and removability by oxygen plasma. In this study, VM using different machine learning algorithms is applied to predict the thickness of ACL and trained models are evaluated which model shows best prediction performance. ACL specimens are deposited by plasma enhanced chemical vapor deposition(PECVD) with four different process parameters(Pressure, RF power, $C_3H_6$ gas flow, $N_2$ gas flow). Gradient boosting regression(GBR) algorithm, random forest regression(RFR) algorithm, and neural network(NN) are selected for modeling. The model using gradient boosting algorithm shows most proper performance with higher R-squared value. A model for predicting the thickness of the ACL film within the abovementioned conditions has been successfully constructed.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.13 no.6
• /
• pp.297-303
• /
• 2003

Mn-Ni-Co type thin films were prepared at various conditions by a rf magnetron sputtering system. At the condition. or substrate temperature of $300^{\circ}C$ and $Ar/O_2$= 10/0, a cubic spinel phase was obtained. When oxygen was included in process gas, a cubic spinel phase was not formed even after the thermal annealing at $900^{\circ}C$. The thermistor thin film had no other elements except Mn, Ni and Co. The infrared reflection spectra of the thermistor thin films showed that the films had somewhat high reflectance for incoming infrared ray with some angle. The etch rate of the thermistor thin films was about 63nm/min at a condition of DI water : $HNO_3$: HCl = 60 : 30 : 10 vol%. The B constant and temperature coefficient of resistance of the thermistor thin films were 3500 K and -3.95 %/K, respectively. The voltage responsivity of the thermistor thin film infrared sensor was 108.5 V/W and its noise equivalent power and specific detectivity were $5.1\times 10^{-7}$ W/$Hz^{-1/2}$ and $0.2\times 10^6$cm $Hz^{1/2}$/W, respectively.

• Journal of the Korean Vacuum Society
• /
• v.20 no.6
• /
• pp.416-421
• /
• 2011

In this paper, the relationship of chamber contamination and the intensity change of specific wavelength was investigated. "diff_CO" formula was introduced to rule out background noise caused by external conditions and to detect when the polymer is removed from the chamber. As RF time increased, diff_CO trend showed the decrease of the maximum peak and increased number of small intensity peaks. From the diff_CO change, it was possible to determine when the chamber needs to be cleaned without opening the chamber.