KR-20260066759-A - Comprehensive Digital Twin Fleet for PCB Manufacturing Equipment

KR20260066759AKR 20260066759 AKR20260066759 AKR 20260066759AKR-20260066759-A

Abstract

Methods, apparatuses, and systems for controlling a physical twin chamber configured to process substrates are described herein. In some embodiments, the method includes the step of determining the characteristics of the physical twin chamber and generating control inputs for controlling the physical twin chamber by means of a digital twin device. The digital twin device includes one or more computational models for determining the characteristics of the physical twin and generating control inputs. The digital twin device determines a first data set associated with the physical twin chamber. The first data set includes process data collected by sensors configured to measure the properties of the physical twin chamber. Based on the first data, the digital twin device automatically generates a second data set based on the generated control inputs and transmits the second data set to the physical twin chamber to control the process performed on the substrates by the physical twin chamber.

Inventors

알렌, 아돌프 밀러
동, 시치
킬리, 폴 제라드
프라카쉬, 밀란
라마나탄, 카르틱
벤카타찰라파티, 기리쉬
켈카, 우메쉬 엠.
사랑, 카스투리 툴라시다스
류, 이멍
후, 웨이제
텡, 잉
천, 세준

Assignees

어플라이드 머티어리얼스, 인코포레이티드

Dates

Publication Date: 20260512
Application Date: 20240807
Priority Date: 20230908

Claims (20)

As a digital twin system for controlling a physical twin chamber configured to process substrates, It includes a digital twin device that determines the characteristics of a physical twin chamber and generates control inputs for controlling the physical twin chamber; The digital twin device comprises one or more computational models for determining the features of the physical twin and generating the control inputs; The digital twin device determines a first data set associated with the physical twin chamber; The first data set above includes process data collected by sensors configured to measure the properties of the physical twin chamber; The digital twin device automatically generates a second data set based on the generated control inputs and transmits the second data set to the physical twin chamber to control the process performed on the substrates by the physical twin chamber; A digital twin system in which the second data set is automatically generated by the digital twin device based at least partially on the first data set and by executing one or more computational models of the digital twin device.
A digital twin system according to claim 1, wherein the digital twin generates the second data set and transmits the second data set to the physical twin chamber while simultaneously receiving the first data set from the physical twin chamber.
In paragraph 1, One or more computational models of the digital twin device include a model of the physical twin chamber; The above model is configured to model one or more of fluid dynamics, direct Monte Carlo (DSMC) simulations, magnetohydrodynamic particle-in-cell simulations, EM solvers, optical modeling tools, or direct calculations of mathematical equations representing the properties of the physical twin chamber; The digital twin device is a digital twin system that performs real-time monitoring and control of the physical twin chamber using at least the model.
A digital twin system according to claim 1, wherein one or more computational models of the digital twin device include one or more models of electrical, mechanical, fluid flow, or vacuum environment features.
In paragraph 1, The digital twin device models the features and processes of the physical twin chamber using models comprising one or more of centralized parameter system modeling networking tools, network models for solving systems of electrical circuits, or derivatives of network models; The first data set above includes features and characteristics of the substrate, including the responses of the substrate to processing performed by the components of the physical twin chamber; The above digital twin is a digital twin system that models the features and characteristics of the above substrate.
In paragraph 3, the model is a digital twin system empirically constructed from measured data from the physical twin chamber.
In paragraph 3, the model of the digital twin device is: Evaluate the performance of the physical twin chamber as described above against the expected or historical performance of the physical twin chamber as established by previous data; By comparing the performance characteristics of the digital twin device and the physical twin chamber, the accuracy of the model is evaluated with respect to the results of the physical twin chamber; A digital twin system that generates actionable insights to improve the performance of the physical twin chamber by using an evaluation of data from both the physical twin chamber and the digital twin device.
As a method for controlling a physical twin chamber for substrate processing, Step of determining a first data set associated with a physical twin chamber by a digital twin device - The digital twin device comprises one or more computational models for determining the features of the physical twin and generating control inputs; The first data set above includes direct measurements of physical processes collected and reported by sensors implemented in the physical twin chamber, and data collected and reported by internal sensors of the digital twin device. A step of automatically generating a second data set including the control inputs by the digital twin device, and transmitting the second data set to the physical twin chamber by the digital twin device to control substrate processing by the physical twin chamber. Includes; A method in which the second data set is automatically generated by the digital twin device based at least partially on the first data set and by executing one or more computational models of the digital twin device.
A method according to claim 8, wherein the digital twin simultaneously receives the first data set from the physical twin chamber, generates the second data set, and transmits the second data set to the physical twin.
In paragraph 8, One or more computational models of the digital twin device include a model of the physical twin chamber; The above model is configured to model one or more of fluid dynamics, direct Monte Carlo (DSMC) simulations, magnetohydrodynamic particle-in-cell simulations, EM solvers, optical modeling tools, or direct calculations of mathematical equations representing the properties of the physical twin chamber; A method in which the digital twin device performs real-time monitoring and control of the physical twin chamber using at least the model.
In paragraph 8, One or more computational models of the above digital twin device include one or more models of electrical, mechanical, fluid flow, or vacuum environment features; The above one or more computational models capture corresponding chemical actions reported by subsystems; The above-mentioned corresponding chemical actions include one or more of heat transfer, transmission of electricity, electric pulses, EM radiation, chemical reactions, material phases, erosion, or wear caused by physical contact.
In paragraph 8, The digital twin device models the features and processes of the physical twin chamber using models comprising one or more of centralized parameter system modeling networking tools, network models for solving systems of electrical circuits, or derivatives of network models; The first data set above includes features and characteristics of the substrate, including the responses of the substrate to processing performed by the components of the physical twin chamber; The above digital twin is a method for modeling the features and characteristics of the above substrate.
In paragraph 10, the method wherein the above model is empirically constructed from measured data from the physical twin chamber.
In Clause 10, the model of the above digital twin device is: Evaluate the performance of the physical twin chamber as described above against the expected or historical performance of the physical twin chamber as established by previous data; By comparing the performance characteristics of the digital twin device and the physical twin chamber, the accuracy of the model is evaluated with respect to the results of the physical twin chamber; A method for generating actionable insights to improve the performance of the physical twin chamber by using an evaluation of data from both the physical twin chamber and the digital twin device.
As a substrate processing system, It includes a digital twin device that determines the characteristics of a physical twin chamber and generates control inputs for controlling the physical twin chamber; The digital twin device comprises one or more computational models for determining the features of the physical twin and generating the control inputs; The above digital twin device includes a processor and a memory coupled to the processor, and the memory is: Determining a first data set associated with the physical twin chamber by the digital twin device above - The first data set above includes direct measurements of physical processes collected and reported by sensors implemented in the physical twin chamber, and data collected and reported by internal sensors of the digital twin device. To automatically generate a second data set including the control inputs by the digital twin device, and to transmit the second data set to the physical twin chamber for substrate processing by the physical twin chamber by the digital twin device. It stores instructions executable by the above processor; A substrate processing system in which the second data set is automatically generated by the digital twin device based at least partially on the first data set and by executing one or more computational models of the digital twin device.
A substrate processing system according to claim 15, wherein the digital twin simultaneously receives the first data set from the physical twin chamber, generates the second data set, and transmits the second data set to the physical twin.
In paragraph 15, One or more computational models of the digital twin device include a model of the physical twin chamber; The above model is configured to model one or more of fluid dynamics, direct Monte Carlo (DSMC) simulations, magnetohydrodynamic particle-in-cell simulations, EM solvers, optical modeling tools, or direct calculations of mathematical equations representing the physical twin chamber; The digital twin device performs real-time monitoring and control of the physical twin chamber using at least the model; A substrate processing system in which the digital twin device monitors and controls the physical twin chamber by executing one or more high-speed execution network models and empirically constructed relational data models.
In paragraph 15, One or more computational models of the above digital twin device include one or more of models of electrical transmission, models of mechanical transmission, models of fluid transmission, or models of vacuum systems; The above one or more computational models capture corresponding physical and chemical actions reported by subsystems; A substrate processing system in which the above-mentioned corresponding chemical actions include one or more of heat transfer, transmission of electricity, electric pulses, EM radiation, chemical reactions, material phases, erosion, or wear due to physical contact.
In paragraph 15, The digital twin device models the features and processes of the physical twin chamber using models comprising one or more of centralized parameter system modeling networking tools, network models for solving systems of electrical circuits, or derivatives of network models; The first data set above includes features and characteristics of the substrate, including the responses of the substrate to processing performed by the components of the physical twin chamber; The above digital twin is a substrate processing system that models the features and characteristics of the above substrate.
In paragraph 17, the above model is a substrate processing system that is empirically constructed from measured data from the physical twin chamber.

Description

Comprehensive Digital Twin Fleet for PCB Manufacturing Equipment The embodiments of the present disclosure generally relate to an apparatus and method for processing a substrate. Substrate manufacturing methods, as well as related tools and physical chambers, utilize a wide variety of physical and chemical processes. Examples of processes may include depositing films on corresponding media, controlling the manner in which materials are deposited, and modifying deposition processes to ensure their accuracy. The functionality and repeatability of processes are based on their accuracy, precision, and reliability, which are ultimately considered in the design, operation, and control of the devices used for substrate manufacturing. Substrate manufacturing devices are generally operated and controlled by hardware, firmware, software, or any combination thereof. Designing devices typically begins with defining the physical chamber hardware and software configurations; then, determining startup configurations and chamber calibration parameters; and finally, engineering and maintaining the devices expected to manufacture substrates effectively and precisely. A physical chamber typically includes thousands of components and numerous electromechanical subsystems designed to control physical processes for manufacturing substrates. Typically, the chamber receives many key input recipe parameters, which are then applied to multiple recipe steps executed by the chamber's processes. However, many of the subsystems may exhibit transient responses to input parameters, for example, due to changes in the physical states of the chamber's components or drift in one or more of their physical properties over time. This can make the management and calibration of the chambers, their components, and their processes significantly difficult. Some of the problems described above can be resolved by using control systems to monitor and control the processes of the chambers involved in substrate manufacturing. Tools can enable monitoring, for example, warnings or faults related to system hardware, and values related to control commands for managing substrate manufacturing processes, such as limits on power, voltage, current, or temperature. However, the delay between the time anomalies are observed and the time correction commands are implemented within the physical chamber can sometimes be unacceptable. Furthermore, performing this type of monitoring can often be time-consuming, and correcting the corresponding faults can be labor-intensive. Therefore, it is necessary to develop a framework for automatically tracking and controlling chamber performance over time. Methods, apparatuses, and systems for controlling a physical twin chamber configured to manufacture substrates are described herein. In some embodiments, the method includes the step of receiving a first data set associated with a physical twin chamber through one or more communication interfaces by a digital twin device. Generally, a digital twin is a computational model (or a set of combined computational models) that evolves to continuously represent the structure, behavior, and context of a unique physical asset, such as a component, system, or process. In the context of this disclosure, a digital twin device is a device configured to capture and model the features and processes of a physical twin chamber and to generate control inputs for controlling the physical twin chamber. The digital twin device may also be configured to model the features and characteristics of a substrate processed by the physical twin. The features and processes of the physical chambers, the processes of the chambers, the substrates, etc., may be captured in the corresponding models. Models of digital twin devices can be constructed based on physical models of physical twins, physical models of processes running on physical twins, physical models of substrates, interactions between processes running on physical twins, reactions occurring on substrates, etc. Models of digital twin devices can also be constructed based on statistical/AI/ML models and hybrid models that combine physics and data. One aspect of the models executed by digital twin devices is that the models can be constructed based on skilled designs of corresponding possible models of physical components, and may include physical models, statistical models, AI/ML, hybrids, etc. The validity of physical models enables rapid and fast execution of corresponding models by digital twin devices. In some implementations, specific digital models can be executed by the digital twin device within a fraction, or so. A digital twin device may include various computational models, components, and subsystems for modeling features and processes and generating control inputs. Communication between the digital twin device and the physical twin chamber may be facilitated using communication interfaces. Data communicated to the digital twin device (also ref