Model-based purge gas flow
Embodiments herein provide for a method of processing a semiconductor substrate. The method described herein may include receiving a first input corresponding to a first geometric hardware configuration of a process chamber, receiving a second input corresponding to a first process recipe of the process chamber, determining, based on the first input and the second input, a first purge gas flow rate for the process chamber, measuring a deposition characteristic of the process chamber via a first sensor, determining, based on the first input, the second input, and the measured deposition characteristic, a second purge gas flow rate, the second purge gas flow rate different from the first purge gas flow rate, and flowing a purge gas at the second purge gas flow rate during a deposition process.
1 . A method for optimizing purge gas flow during processing of a semiconductor substrate in a process chamber, comprising:
positioning a substrate on a surface of a substrate support within the process chamber, the process chamber comprising an upper window and a lower window opposite the upper window, the substrate support in between the upper window and the lower window, and one or more sensors positioned outside the lower window such that the one or more sensors have a direct line of sight to the lower window, a backside of the substrate support, or both the lower window and the backside of the substrate support;
receiving, by a controller operatively coupled to the process chamber, a first input corresponding to a first process recipe of a deposition process to be performed in the process chamber;
receiving, by the controller, a second input corresponding to a first hardware configuration of the process chamber;
determining, by the controller and based on the first input and the second input, a first purge gas flow rate for the process chamber, the determining the first purge gas flow rate comprising:
utilizing a machine learning model comprising a digital twin model of the process chamber to simulate fluid dynamics within the process chamber based on the first process recipe and the first hardware configuration, and to predict a first deposition characteristic of at least one of the backside of the substrate support and the lower window in the process chamber;
performing, by the controller, a first deposition process to deposit material on the substrate positioned on the surface of the substrate support in the process chamber using the first process recipe at the first purge gas flow rate in the process chamber, wherein the substrate support protects a bottom surface of the substrate from unwanted deposition;
measuring, by the one or more sensors, a measured deposition characteristic of at least one of the backside of the substrate support and the lower window in the process chamber;
determining, by the controller utilizing the machine learning model and based on the first input, the second input, and a difference between the predicted first deposition characteristic and the measured deposition characteristic, a second purge gas flow rate, the second purge gas flow rate different from the first purge gas flow rate; and
performing, by the controller, a second deposition process to deposit material on the substrate positioned on the surface of the substrate support in the process chamber using the first process recipe at the second purge gas flow rate.
2 . The method of claim 1 ,
wherein the method increases deposition uniformity on the substrate and reduces unwanted deposition on chamber components thereby improving throughput and reducing maintenance requirements.
3 . The method of claim 1 , wherein the one or more sensors comprises a pyrometer or an optical spectrometer or a camera, each positioned to measure the first deposition characteristic of at least one of the backside of the substrate support or the lower window in the process chamber.
4 . The method of claim 3 , further comprising one or more second sensors within the process chamber, each configured to provide real-time feedback on deposition characteristics at different chamber locations.
5 . The method of claim 1 , wherein the first hardware configuration comprises a non-vented or vented liner, a circular or elliptical preheating ring, and/or the substrate support overlapping the preheating ring.
6 . The method of claim 1 , wherein the digital twin model comprises a digital simulation of physical characteristics of the process chamber, the physical characteristics comprising the first hardware configuration of the process chamber.
7 . The method of claim 1 , wherein determining the first purge gas flow rate further comprises referencing a database of hardware configuration and process recipes based on user input.
8 . The method of claim 1 , wherein the first process recipe is updated to include the second purge gas flow rate, thereby enabling adaptive process control.
9 . The method of claim 6 , wherein the second purge gas flow rate or a difference between the first purge gas flow rate and the second purge gas flow rate is displayed for an operator.
10 . The method of claim 1 , wherein the measured deposition characteristic comprises a thickness, a mass fraction, a transmissivity, a transparency, an emissivity, or any combination thereof.
11 . The method of claim 1 , wherein the controller automatically adjusts the purge gas flow rate in real time from the first purge gas flow rate to the second purge gas flow rate in response to feedback from the one or more sensors.
12 . The method of claim 1 , wherein measuring the first deposition characteristic of the process chamber via the one or more sensors occurs more than once throughout the first deposition process, enabling real-time adjustment of the purge gas flow rate.
13 . The method of claim 1 , wherein a purge gas of the first purge gas flow rate is a flow module purge gas, a slit purge gas, a rotational purge gas, or a liner purge gas.
14 . A method for optimizing purge gas flow during processing of a semiconductor substrate in a process chamber, comprising:
positioning a substrate on a surface of a substrate support within the process chamber, the process chamber comprising an upper window and a lower window opposite the upper window, the substrate support in between the upper window and the lower window, and one or more sensors positioned outside the lower window such that the one or more sensors have a direct line of sight to the lower window, a backside of the substrate support, or both the lower window and the backside of the substrate support;
receiving, by a controller operatively coupled to the process chamber, a first input corresponding to a first process recipe of a deposition process to be performed in the process chamber;
receiving, by the controller, a second input corresponding to a first hardware configuration of the process chamber;
determining, by the controller and based on the first input and the second input a first purge gas flow rate for the process chamber, the determining the first purge gas flow rate comprising:
utilizing a machine learning model comprising a digital twin model of the process chamber to simulate fluid dynamics within the process chamber based on the first process recipe and the first hardware configuration, and to predict a first deposition characteristic of at least one of the backside of the substrate support and the lower window in the process chamber;
performing, by the controller, a first deposition process to deposit material on the substrate positioned on the surface of the substrate support in the process chamber using the first process recipe at the first purge gas flow rate in the process chamber, wherein the substrate support protects a bottom surface of the substrate from unwanted deposition;
measuring, by the one or more sensors, a measured deposition characteristic of at least one of the backside of the substrate support and the lower window in the process chamber during the first deposition process;
determining, by the controller utilizing the machine learning model and based on the first input, the second input, and the measured deposition characteristic, a second purge gas flow rate, the second purge gas flow rate different from the first purge gas flow rate;
performing, by the controller, a second deposition process to deposit a material on the substrate positioned on the surface of the substrate support in the process chamber using the first process recipe at the second purge gas flow rate in the process chamber;
measuring, by the one or more sensors, the measured deposition characteristic of at least one of the backside of the substrate support and the lower window in the process chamber during the second deposition process;
determining, by the controller utilizing the machine learning model, based on a change in the measured deposition characteristic of the second deposition process, a third purge gas flow rate, the third purge gas flow rate different from the second purge gas flow rate; and
performing, by the controller, a third deposition process to deposit a material on the substrate positioned on the surface of the substrate support in the process chamber using the first process recipe at the third purge gas flow rate in the process chamber.
15 . The method of claim 14 , wherein the measured deposition characteristic includes a thickness of a film.
16 . The method of claim 14 , wherein the controller automatically adjusts the purge gas flow rate in real time from the first purge gas flow rate to the second purge gas flow rate in response to feedback from the one or more sensors.
17 . The method of claim 1 , wherein the first deposition process comprises co-flowing a precursor gas and a first purge gas, the first purge gas flowing at the first purge gas flow rate and the precursor gas comprises at least one of dichlorosilane (DCS) and trichlorosilane (TCS).
18 . The method of claim 1 , wherein the first deposition process comprises co-flowing a precursor gas and a first purge gas at the first purge gas flow rate, the precursor gas comprises disilane (DS).
19 . The method of claim 14 , wherein the first deposition process comprises co-flowing a precursor gas and a first purge gas, the first purge gas flowing at the first purge gas flow rate and the precursor gas comprises at least one of dichlorosilane (DCS) and trichlorosilane (TCS).
20 . The method of claim 14 , wherein the first deposition process comprises co-flowing a precursor gas and a first purge gas at the first purge gas flow rate, the precursor gas comprises disilane (DS).