Automated method for integrated analysis of back end of the line yield, line resistance/capacitance and process performance

• US 10,303,829 B2
• Filed: 05/31/2017
• Issued: 05/28/2019
• Est. Priority Date: 05/31/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bhosale, Prasad, Rizzolo, Michael, Yang, Chih-Chao
• Primary Examiner(s): Siek, Vuthe
• Application Number:
  US15/609,559
• Publication Number:
  US 20180349535A1
• Time in Patent Office: 727 Days
• CPC Class Codes: G06F 2119/18 Manufacturability analysis or optimisation for manufacturability
• CPC Class Codes: G06F 30/367 Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
• CPC Class Codes: G06F 30/398 Design verification or optimisation, e.g. using design rule check [DRC], layout versus schematics [LVS] or finite element methods [FEM] optical proximity correction [OPC] design processes G03F1/36
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: H01L 22/12 for structural parameters, e.g. thickness, line width, refractive index, temperature, warp, bond strength, defects, optical inspection, electrical measurement of structural dimensions, metallurgic measurement of diffusions electrical measurement of diffusions H01L22/14
• CPC Class Codes: H01L 22/14 for electrical parameters, e.g. resistance, deep-levels, CV, diffusions by electrical means
• CPC Class Codes: H01L 22/20 Sequence of activities consisting of a plurality of measurements, corrections, marking or sorting steps

Abstract

A method of electrical device manufacturing that includes measuring a first plurality of dimensions and electrical performance from back end of the line (BEOL) structures; and comparing the first plurality of dimensions with a second plurality of dimensions from a process assumption model to determine dimension variations by machine vision image processing. The method further includes providing a plurality of scenarios for process modifications by applying machine image learning to the dimension variations and electrical variations in the in line electrical measurements from the process assumption model. The method further includes receiving production dimension measurements and electrical measurements at a manufacturing prediction actuator. The at least one of the dimensions or electrical measurements received match one of the plurality of scenarios the manufacturing prediction actuator using the plurality of scenarios for process modifications effectuates a process change.

Claims

1. A system of electrical device manufacturing comprising:

an optical measuring device for measuring a first plurality of dimensions from a back end of the line (BEOL) structure of an electrical device;

an in line electrical performance measuring apparatus for measuring in line resistance of BEOL structures;

a machine vision image processor for comparing the first plurality of dimensions with a second plurality of dimensions from a process assumption model to determine dimension variations;

a machine learning engine for applying machine learning to the dimension variations and electrical variations in the in line electrical measurements from the process assumption model, wherein the plurality of scenarios for process modifications are responsive to dimension and electrical variations in production BEOL structures;

manufacturing prediction actuator for receiving production dimension measurements and production electrical measurements from a production track, wherein when at least one of the dimensions or electrical measurements received match one of the plurality of scenarios the manufacturing prediction actuator effectuates a process change to bring production of the BEOL within the process assumption model; and

a production track manufacturing an electrical device with said process change to bring production of the BEOL structures within the process assumption model.

2. The system of claim 1, wherein said optical measuring device comprises an optical diffraction apparatus.

3. The system of claim 1, wherein the machine learning engine is provided by a learning scheme selected from the group consisting of tree learning, associated rule learning, artificial neural networks, deep tree learning, inductive logic programming, support vector machines, clustering, bayesian networks, reinforcement learning, representation learning, similarity and metric learning, sparse dictionary learning, genetic algorithms, rule-based machine learning, learning classifier systems and combinations thereof.

4. The system of claim 1, wherein the plurality of scenarios for process modifications are responsive to dimension and electrical variations is an production apparatus adjustment that is selected from the group consisting of etch apparatus, process modifications for lithography apparatus, process modifications for metallization apparatus, and combinations thereof.

5. The system of claim 1, wherein the BEOL structure comprises a metal line.

6. The system of claim 1, wherein the first plurality of dimensions from the BEOL structure comprises a metal line width, metal line height or a combination thereof.

7. A non-transitory computer readable storage medium comprising a computer readable program for electrical device manufacturing, wherein the non-transitory computer readable program when executed on a computer causes the computer to perform the steps of:

comparing a first plurality of dimensions measured from a back end of the line (BEOL) structure with a second plurality of dimensions from a process assumption model to determine dimension variations by machine vision image processing;

providing a plurality of scenarios for process modifications by applying machine learning to the dimension variations and electrical variations measured with in line electrical measurements from the process assumption model;

receiving production dimension and electrical measurements at a manufacturing prediction actuator, wherein when at least one of the dimensions or electrical measurements received match one of the plurality of scenarios, the manufacturing prediction actuator using the plurality of scenarios for process modifications effectuates a process change to bring production of the BEOL structures within the process assumption model; and

manufacturing an electrical device with said process change to bring production of the BEOL structures within the process assumption model.

8. The non-transitory computer readable storage medium of claim 7, the method further comprising mapping the first plurality of dimensions taken from back end of the line (BEOL) structures from historical samples to a cross sectional image taken by transmission electron microscope (TEM).

9. The non-transitory computer readable storage medium of claim 7, wherein the first plurality of dimensions from the BEOL structure comprises a metal line width, metal line height or a combination thereof.

10. The non-transitory computer readable storage medium of claim 7, wherein the first plurality of dimensions from the BEOL structure comprises a stud height, top variation in the metal line height, side variation in the metal line height, or a combination thereof.