Concentration sensor for precursor delivery system

1 . A method, comprising:

receiving first sensor data indicative of a first mass flow rate of a first gas flowing to a vaporization chamber, the vaporization chamber comprising a compound to be transitioned into a gaseous state;

receiving second sensor data indicative of a second mass flow rate of a second gas flowing out of the vaporization chamber, wherein the second gas comprises the compound and the first gas;

receiving third sensor data indicative of a third mass flow rate of the compound into the vaporization chamber;

determining an estimated concentration of the compound within the second gas based on processing the first sensor data, the second sensor data, and the third sensor data; and

modifying a flow rate of the first gas based on the estimated concentration of the compound within the second gas.

2 . The method of claim 1 , wherein at least one of the first sensor data, the second sensor data, or the third sensor data is received from a mass flow rate controller.

3 . The method of claim 1 , further comprising:

selectively opening and closing a first valve to modify the first mass flow rate of the first gas.

4 . The method of claim 1 , further comprising:

selectively opening and closing a second valve to modify the second mass flow rate of the second gas.

5 . The method of claim 1 , further comprising:

determining a depletion rate of the compound within the vaporization chamber based on the estimated concentration of the compound in the second gas.

6 . The method of claim 1 , further comprising:

receiving fourth sensor data indicative of a temperature of the vaporization chamber; and

determining the estimated concentration of the compound within the second gas based on processing the fourth sensor data along with the first sensor data, the second sensor data, and the third sensor data.

7 . The method of claim 1 , further comprising:

training an untrained machine learning model to produce a trained machine learning model for processing the first sensor data, the second sensor data, and the third sensor data, wherein the untrained machine learning model is trained using a training data set comprising a plurality of flow rate values for the first gas, for the second gas, and for the compound, and a plurality of associated compound concentration values.

8 . A method, comprising:

receiving first sensor data indicative of a first mass flow rate of a first gas flowing to a vaporization chamber, the vaporization chamber comprising a compound to be transitioned into a gaseous state;

receiving second sensor data indicative of a second mass flow rate of a second gas flowing out of the vaporization chamber, wherein the second gas comprises the compound and the first gas;

receiving third sensor data indicative of a third mass flow rate of the compound into the vaporization chamber; and

training an untrained machine learning model to produce a trained machine learning model, wherein the untrained machine learning model is trained using the first sensor data, the second sensor data, and the third sensor data, and wherein the trained machine learning model is trained to determine an estimated concentration of the compound within the second gas.

9 . The method of claim 8 , wherein training the untrained machine learning model comprises:

inputting the first sensor data, the second sensor data, and the third sensor data into the untrained machine learning model;

receiving an output from the untrained machine learning model comprising a predicted concentration;

comparing the predicted concentration to a known concentration associated with the first sensor data, the second sensor data, and the third sensor data;

determining an error based on a difference between the predicted concentration and the known concentration; and

adjusting one or more weights of one or more nodes of the untrained machine learning model based on the error.

10 . The method of claim 8 , wherein the trained machine learning model is further trained to classify the compound based on the first sensor data, the second sensor data, and the third sensor data.

11 . The method of claim 8 , wherein the trained machine learning model is further trained to output an estimated depletion rate of the compound within the vaporization chamber based on the first sensor data, the second sensor data, and the third sensor data.

12 . A non-transitory machine-readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to:

receive first sensor data indicative of a first mass flow rate of a first gas flowing to a vaporization chamber, the vaporization chamber comprising a compound to be transitioned into a gaseous state;

receive second sensor data indicative of a second mass flow rate of a second gas flowing out of the vaporization chamber, wherein the second gas comprises the compound and the first gas;

receive third sensor data indicative of a third mass flow rate of the compound into the vaporization chamber;

determine an estimated concentration of the compound within the second gas based on processing the first sensor data, the second sensor data, and the third sensor data; and

modify a flow rate of the first gas based on the estimated concentration of the compound within the second gas.

13 . The non-transitory machine-readable storage medium of claim 12 , wherein at least one of the first sensor data, the second sensor data, or the third sensor data is received from a mass flow rate controller.

14 . The non-transitory machine-readable storage medium of claim 12 , wherein the processing device is further to:

selectively open and close a first valve to modify the first mass flow rate of the first gas.

15 . The non-transitory machine-readable storage medium of claim 12 , wherein the processing device is further to:

selectively open and close a second valve to modify the second mass flow rate of the second gas.

16 . The non-transitory machine-readable storage medium of claim 12 , wherein the processing device is further to:

determine a depletion rate of the compound within the vaporization chamber based on the estimated concentration of the compound in the second gas.

17 . The non-transitory machine-readable storage medium of claim 12 , wherein the processing device is further to:

receive fourth sensor data indicative of a temperature of the vaporization chamber; and

determine the estimated concentration of the compound within the second gas based on processing the fourth sensor data along with the first sensor data, the second sensor data, and the third sensor data.

18 . The non-transitory machine-readable storage medium of claim 12 , wherein the processing device is further to:

train an untrained machine learning model to produce a trained machine learning model for processing the first sensor data, the second sensor data, and the third sensor data, wherein the untrained machine learning model is trained using a training data set comprising a plurality of flow rate values for the first gas, for the second gas, and for the compound, and a plurality of associated compound concentration values.

19 . The non-transitory machine-readable storage medium of claim 18 , wherein the trained machine learning model is trained to determine the estimated concentration of the compound within the second gas.

20 . The non-transitory machine-readable storage medium of claim 18 , wherein the processing device is further to:

input the training data set into the untrained machine learning model;

receive an output from the untrained machine learning model comprising a predicted concentration;

compare the predicted concentration to a known concentration associated with the training data set;

determine an error based on a difference between the predicted concentration and the known concentration; and

adjust one or more weights of one or more nodes of the untrained machine learning model based on the error.