Etching processing apparatus, etching processing system, analysis apparatus, etching processing method, and storage medium
An etching processing apparatus includes a storage that stores a learned model of each group generated by each learning processing in a case where each processing condition acquired during execution of a specific step of an etching processing, is classified into a plurality of groups according to a difference in effects when executing the specific step, and the learning processing is performed for each group; an updating unit that updates the learned model of a specific group when an effect of executing the specific step on a test wafer using setting data included in a processing condition associated with the specific group is not equivalent to an effect associated with the specific group; and a searching unit that searches for, using the updated learned model, setting data capable of obtaining the effect associated with the specific group when the specific step is executed on the test wafer.
1 . An etching processing apparatus, comprising:
a memory to store a learned model of each group generated by each learning processing in a case where each processing condition acquired during execution of a specific step of an etching processing is classified into a plurality of groups according to a difference in effects when the specific step is executed, and the learning processing is performed for each group;
a gauge to measure cross-sectional shape data of a wafer; and
processing circuitry configured to execute instructions stored in the memory to:
update the learned model of a specific group when an effect calculated based on the cross-sectional shape data of the wafer measured by the gauge before and after executing the specific step using setting data included in a processing condition associated with the specific group is not equivalent to an effect associated with the specific group, wherein the effect associated with the specific group represents a change in cross-sectional shape data; and
search for, using the learned model updated by the processing circuitry, setting data which results in the effect associated with the specific group when the specific step is executed on the wafer.
2 . The etching processing apparatus according to claim 1 , wherein the processing circuitry is further configured to set the setting data when the specific step is executed on the wafer.
3 . The etching processing apparatus according to claim 2 , wherein the learned model is learned such that output data, when inputting cross-sectional shape data of the wafer before executing the specific step and the processing condition associated with the specific group, approaches cross-sectional shape data of the wafer after executing the specific step.
4 . The etching processing apparatus according to claim 3 , wherein the processing circuitry updates a model parameter of the learned model of the specific group such that the effect calculated based on the cross-sectional shape data is equivalent to the effect associated with the specific group.
5 . The etching processing apparatus according to claim 1 , wherein the processing circuitry searches for the setting data such that an effect calculated based on a predicted value of the cross-sectional shape data of the wafer after processing in a case of inputting the cross-sectional shape data of the wafer before processing, to the learned model updated by the processing circuitry, and the cross-sectional shape data of the wafer before processing, approaches the effect associated with the specific group.
6 . The etching processing apparatus according to claim 1 , wherein the wafer has a same elemental composition, film density, and film structure of a target film to be etched as the processing wafer.
7 . An etching processing method, comprising:
storing a learned model of each group generated by each learning processing in a case where each processing condition acquired during execution of a specific step of an etching processing, is classified into a plurality of groups according to a difference in effects when the specific step is executed, and the learning processing is performed for each group;
measuring, with a gauge, cross-sectional shape data of a wafer;
updating the learned model of a specific group when an effect calculated based on the cross-sectional shape data of the wafer measured by the gauge before and after executing the specific step using setting data included in a processing condition associated with the specific group is not equivalent to an effect associated with the specific group, wherein the effect associated with the specific group represents a change in cross-sectional shape data; and
searching for, using the learned model updated in the updating, setting data which results in the effect associated with the specific group when the specific step is executed on the wafer.
8 . The etching processing method according to claim 7 , further comprising:
setting the setting data searched at the searching when the specific step is executed on the wafer.
9 . The etching processing method according to claim 8 , wherein the learned model is learned such that output data, when inputting cross-sectional shape data of the wafer before executing the specific step and the processing condition associated with the specific group, approaches cross-sectional shape data of the wafer after executing the specific step.
10 . The etching processing method according to claim 9 , wherein the updating updates a model parameter of the learned model of the specific group such that the effect calculated based on the cross-sectional shape data is equivalent to the effect associated with the specific group.
11 . The etching processing method according to claim 7 , wherein the searching searches for the setting data such that an effect calculated based on a predicted value of the cross-sectional shape data of the wafer after processing in a case of inputting the cross-sectional shape data of the wafer before processing, to the learned model updated at the updating, and the cross-sectional shape data of the wafer before processing, approaches the effect associated with the specific group.
12 . A non-transitory computer-readable storage medium having stored therein an analysis program that causes a computer to execute a process comprising:
storing a learned model of each group generated by each learning processing in a case where each processing condition acquired during execution of a specific step of an etching processing, is classified into a plurality of groups according to a difference in effects when the specific step is executed, and the learning processing is performed for each group;
measuring, with a gauge, cross-sectional shape data of a wafer;
updating the learned model of a specific group when an effect calculated based on the cross-sectional shape data of the wafer measured by the gauge before and after executing the specific step using setting data included in a processing condition associated with the specific group is not equivalent to an effect associated with the specific group, wherein the effect associated with the specific group represents a change in cross-sectional shape data; and
searching for, using the learned model updated in the updating, setting data which results in the effect associated with the specific group when the specific step is executed on the wafer.
13 . The non-transitory computer-readable storage medium according to claim 12 , wherein the process further comprises:
setting the setting data searched at the searching when the specific step is executed on the wafer.
14 . The non-transitory computer-readable storage medium according to claim 13 , wherein the learned model is learned such that output data, when inputting cross-sectional shape data of the wafer before executing the specific step and the processing condition associated with the specific group, approaches cross-sectional shape data of the wafer after executing the specific step.
15 . The non-transitory computer-readable storage medium according to claim 14 , wherein the updating updates a model parameter of the learned model of the specific group such that the effect calculated based on the cross-sectional shape data is equivalent to the effect associated with the specific group.
16 . The non-transitory computer-readable storage medium according to claim 12 , wherein the searching searches for the setting data such that an effect calculated based on a predicted value of the cross-sectional shape data of the wafer after processing in a case of inputting the cross-sectional shape data of the wafer before processing, to the learned model updated at the updating, and the cross-sectional shape data of the wafer before processing, approaches the effect associated with the specific group.