Deep learning model in high-mix semiconductor manufacturing
Disclosed techniques for applying a neural network deep learning model in a fabrication strategy for high-mix semiconductor manufacturing, such as deposition, chemical-mechanical polishing (CMP), etching, photolithography, plating, etc. Training and normal operation modes of the fabrication strategy are described.
1. A method to set at least one processing parameter for manufacturing a semiconductor device, the method comprising:
receiving context information regarding the at least one processing parameter for performing a processing step by a manufacturing machine to manufacture the semiconductor device;
inputting the context information into a machine learning network;
receiving a predicted value for the at least one processing parameter from the machine learning network;
setting the at least one processing parameter for the manufacturing machine based on the predicted value to perform the processing step to manufacture the semiconductor device;
receiving, from a metrology instrument, a measured result of the processing step on the semiconductor device associated with the at least one processing parameter; and
feeding back the measured result into the machine learning network,
wherein the machine learning network is trained based on a plurality of features identified by performing a regression technique to estimate a variance of the at least one processing parameter to identify the plurality of features as having a direct relationship to the variance,
wherein the plurality of features includes at least one manufacturing context feature, at least one equipment hardware parameter feature, and at least one upstream parametric data feature.
2. The method of claim 1 , wherein the machine learning network includes a recurrent neural network (RNN) deep learning model.
3. The method of claim 1 , wherein the machine learning network is trained to generate the predicted value using a training process comprising:
retrieving data associated with historical production;
selecting a subset of the data based on a plurality of features relevant to the at least one processing parameter, wherein the plurality of features are independent; and
inputting the subset in the machine learning network for training.
4. The method of claim 3 , wherein the training process further comprises:
filtering the subset of the data to remove outlier values.
5. The method of claim 3 , wherein the training process further comprises:
converting string data in the subset of the data to numerical values.
6. The method of claim 3 , wherein the training process further comprises:
scaling the subset of the data to generate normalized data.
7. The method of claim 3 , wherein the training process further comprises:
tuning at least one hyperparameter associated with the machine learning network.
8. A control system comprising:
at least one hardware processor; and
at least one memory storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations comprising:
receiving context information regarding at least one processing parameter for performing a processing step by a manufacturing machine to manufacture a semiconductor device;
inputting the context information into a machine learning network;
receiving a predicted value for the at least one processing parameter from the machine learning network;
setting the at least one processing parameter for the manufacturing machine based on the predicted value to perform the processing step to manufacture the semiconductor device;
receiving, from a metrology instrument, a measured result of the processing step on the semiconductor device associated with the at least one processing parameter; and
feeding back the measured result into the machine learning network,
wherein the machine learning network is trained based on a plurality of features identified by performing a regression technique to estimate a variance of the at least one processing parameter to identify the plurality of features as having a direct relationship to the variance,
wherein the plurality of features includes at least one manufacturing context feature, at least one equipment hardware parameter feature, and at least one upstream parametric data feature.
9. The control system of claim 8 , wherein the machine learning network includes a recurrent neural network (RNN) deep learning model.
10. The control system of claim 8 , wherein the machine learning network is trained to generate the predicted value using a training process comprising:
retrieving data associated with historical production;
selecting a subset of the data based on a plurality of features relevant to the at least one processing parameter, wherein the plurality of features are independent; and
inputting the subset in the machine learning network for training.
11. The control system of claim 10 , wherein the training process further comprises:
filtering the subset of the data to remove outlier values.
12. The control system of claim 10 , wherein the training process further comprises:
converting string data in the subset of the data to numerical values.
13. The control system of claim 10 , wherein the training process further comprises:
scaling the subset of the data to generate normalized data.
14. The control system of claim 10 , wherein the training process further comprises:
tuning at least one hyperparameter associated with the machine learning network.
15. A machine-storage medium embodying instructions that, when executed by a machine, cause the machine to perform operations comprising:
receiving context information regarding at least one processing parameter for performing a processing step by a manufacturing machine to manufacture a semiconductor device;
inputting the context information into a machine learning network;
receiving a predicted value for the at least one processing parameter from the machine learning network;
setting the at least one processing parameter for the manufacturing machine based on the predicted value to perform the processing step to manufacture the semiconductor device;
receiving, from a metrology instrument, a measured result of the processing step on the semiconductor device associated with the at least one processing parameter; and
feeding back the measured result into the machine learning network,
wherein the machine learning network is trained based on a plurality of features identified by performing a regression technique to estimate a variance of the at least one processing parameter to identify the plurality of features as having a direct relationship to the variance,
wherein the plurality of features includes at least one manufacturing context feature, at least one equipment hardware parameter feature, and at least one upstream parametric data feature.
16. The machine-storage medium of claim 15 , wherein the machine learning network includes a recurrent neural network (RNN) deep learning model.
17. The machine-storage medium of claim 15 , wherein the machine learning network is trained to generate the predicted value using a training process comprising:
retrieving data associated with historical production;
selecting a subset of the data based on a plurality of features relevant to the at least one processing parameter, wherein the plurality of features are independent; and
inputting the subset in the machine learning network for training.
18. The machine-storage medium of claim 17 , wherein the training process further comprises:
filtering the subset of the data to remove outlier values.
19. The machine-storage medium of claim 17 , wherein the training process further comprises:
converting string data in the subset of the data to numerical values.
20. The machine-storage medium of claim 17 , wherein the training process further comprises:
scaling the subset of the data to generate normalized data.