Machine learning on overlay management
The current disclosure describes techniques for managing vertical alignment or overlay in semiconductor manufacturing using machine learning. Alignments of interconnection features in a fan-out WLP process are evaluated and managed through the disclosed techniques. Big data and neural networks system are used to correlate the overlay error source factors with overlay metrology categories. The overlay error source factors include tool related overlay source factors, wafer or die related overlay source factors and processing context related overlay error source factors.
1. A method, comprising:
receiving, by a computing device, a data set including a first tool position of a tool with respect to forming a first feature on a first wafer, a first item position of a first portion of the first wafer corresponding to the forming the first feature, and a first overlay metrology of the first feature formed on the first wafer;
generating, by the computing device, a function correlating one or more of a tool position or an item position on a first side of the function with an overlay metrology on a second side of the function through machine learning based on the data set;
receiving, by the computing device, a second tool position of the tool with respect to forming a second feature on a second wafer and a second item position of a second portion of the second wafer corresponding to the forming the second feature;
estimating, by the computing device, a second overlay metrology of the second feature on the second wafer based on the function, the second tool position and the second item position; and
adjusting, by a controller coupled to the computing system, one or more of the second tool position or the second item position in a semiconductor manufacturing process of forming the second feature on the second wafer based on the estimated second overlay metrology.
2. The method of claim 1 , wherein each of the first or second tool position includes one or more of a wafer stage position, a stepper position, a reticle key position or an exposure position.
3. The method of claim 1 , wherein each of the first or second item position includes one or more of a wafer offset or a wafer rotation of the first wafer positioned on a wafer stage.
4. The method of claim 3 , wherein each of the first or second item position further includes one or more of a die offset or a die rotation of a die positioned on the first portion of the first wafer.
5. The method of claim 1 , wherein each of the first or second tool position includes one or more of a measured position, a pre-alignment position and a post-alignment position.
6. The method of claim 1 , wherein each of the first or second item position includes one or more of a measured position, a pre-alignment position and a post-alignment position.
7. The method of claim 1 , further comprising:
determining a context of forming the first feature on the first wafer; and
generating the data set including the context.
8. The method of claim 7 , wherein the context includes one or more of a measurement position of an enhanced global alignment operation on the first wafer, an exposure field with respect to forming the first feature, and a metrology position on the first wafer where the overlay metrology is measured.
9. The method of claim 1 , further comprising:
determining a previous tool position of the tool with respect to forming a first feature on a previous first wafer; and
generating the data set including the previous tool position.
10. The method of claim 1 , wherein the generating the function includes generating the function using machine learning through a neural networks system.
11. The method of claim 1 , further comprising evaluating the function through comparing the estimated overlay metrology of the second wafer with a measured overlay metrology of the second wafer.
12. An non-transitory storage medium having executable instructions stored thereon, which when executed by a processor enable the processor to implement acts comprising:
receiving a data set including a first tool position of a tool with respect to forming a first feature on a first wafer, a first item position of a first portion of the first wafer corresponding to the forming the first feature, and a first overlay metrology of the first feature formed on the first wafer;
generating a function correlating one or more of a tool position or an item position on a first side of the function with an overlay metrology on a second side of the function through machine learning based on the data set;
receiving a second tool position of the tool with respect to forming a second feature on a second wafer and a second item position of a second portion of the second wafer corresponding to the forming the second feature;
estimating a second overlay metrology of the second feature on the second wafer based on the function, the second tool position and the second item position; and
adjusting one or more of the second tool position or the second item position based on the estimated second overlay metrology.
13. The storage medium of claim 12 , wherein each of the first or second tool position includes one or more of a wafer stage position, a stepper position, a reticle key position or an exposure position.
14. The storage medium of claim 12 , wherein each of the first or second item position includes one or more of a wafer offset or a wafer rotation of the first wafer positioned on a wafer stage.
15. The storage medium of claim 14 , wherein each of the first or second item position further includes one or more of a die offset or a die rotation of a die positioned on the first portion of the first wafer.
16. The storage medium of claim 12 , wherein the acts include:
determining a previous tool position of the tool with respect to forming a first feature on a previous first wafer; and
generating the data set including the previous tool position.
17. A computing system, comprising:
a processor; and
a storage unit having executable instructions stored thereon which, when executed by the processor, configures the processor to implement actions including:
receiving a data set including a first tool position of a tool with respect to forming a first feature on a first wafer, a first item position of a first portion of the first wafer corresponding to the forming the first feature, and a first overlay metrology of the first feature formed on the first wafer;
generating a function correlating one or more of a tool position or an item position on a first side of the function with an overlay metrology on a second side of the function through machine learning based on the data set;
receiving a second tool position of the tool with respect to forming a second feature on a second wafer and a second item position of a second portion of the second wafer corresponding to the forming the second feature;
estimating a second overlay metrology of the second feature on the second wafer based on the function, the second tool position and the second item position; and
adjusting one or more of the second tool position or the second item position based on the estimated second overlay metrology.
18. The computing system of claim 17 , wherein each of the first or second tool position includes one or more of a wafer stage position, a stepper position, a reticle key position or an exposure position.
19. The computing system of claim 17 , wherein each of the first or second item position includes one or more of a wafer offset or a wafer rotation of the first wafer positioned on a wafer stage.
20. The computing system of claim 17 , wherein each of the first or second tool position includes one or more of a measured position, a pre-alignment position and a post-alignment position.