System and method for process system matching and optimization based on digital twinning and neural networks

Abstract

The application discloses a system and method for process system matching and optimization based on digital twinning and neural networks. The method constructs digital twins of single and group process systems, and the group digital twins can guide the matching of the group process systems. The neural network trained by simulation data and measurement data can improve the calculation efficiency and realize accurate matching and compatibility of the process systems.

Description

[0001] Cross-references to related applications

[0002] This invention claims priority to U.S. Patent Application No. 18 / 964,345, filed on November 29, 2024. Technical Field

[0003] This invention relates to the field of semiconductor manufacturing, with a focus on advanced process system management and optimization technologies, particularly addressing the critical need for precise matching and calibration of cluster process systems. Background Technology

[0004] In the semiconductor industry, as processing technology becomes increasingly complex, the demands for atomic-level control precision are becoming more stringent, making the need for advanced process system management solutions ever more urgent. Semiconductor manufacturing processes are evolving towards finer geometries and more complex structures, significantly reducing error tolerance. This trend highlights the importance of achieving precise matching of process systems; only in this way can the consistency and high quality of output from different manufacturing equipment and platforms be guaranteed.

[0005] Traditional process system management methods in semiconductor manufacturing often fail to meet the stringent requirements of modern manufacturing processes. These traditional methods typically rely on general specifications and parameters, making it difficult to fully consider the unique characteristics and differences of individual process systems. This deficiency can lead to inconsistent processing, decreased yield, and increased operating costs due to inefficiency and frequent manual intervention.

[0006] Furthermore, the increasing complexity of semiconductor processing necessitates more dynamic system calibration and optimization methods. This includes seamlessly integrating new process systems into existing production lines and recalibrating systems identified as having operational anomalies through in-situ sensors or post-processing metrology. Current process system management methods lack the necessary flexibility and intelligence to maintain overall operational consistency while meeting the specific needs of each system.

[0007] Currently, the industry urgently needs a method that can achieve intelligent matching and calibration of process systems with high precision and adaptability to address subtle operational differences between systems. This method will significantly improve the efficiency and output quality of semiconductor manufacturing processes, addressing the challenges the industry faces as it evolves towards more complex and precise manufacturing technologies.

[0008] This invention addresses these problems by introducing a novel method for matching and optimizing advanced process systems using digital twins and neural networks. This method is specifically designed to meet the stringent requirements of the semiconductor industry, ensuring precise control and consistency in complex manufacturing processes. Summary of the Invention

[0009] The method described in this invention employs advanced digital twin and neural network technologies to provide a comprehensive solution for process system matching within a group of process systems. It can achieve operational consistency and optimization in diverse process environments, combining adaptability and accuracy.

[0010] The core of this method is the digital twin of the grouped system, which encompasses the overall characteristics and performance indicators of the grouped process systems. This digital twin serves as a key reference model, providing a benchmark for evaluating individual process systems, ensuring that each system meets established standards, and maintaining consistency in performance and quality.

[0011] Each process system in the group is represented by a digital twin specific to that process system. This specific model captures the unique characteristics and operating parameters of each individual process system, enabling detailed evaluation and optimization of each system while ensuring compliance with the group's criteria.

[0012] A key feature of this method is its versatility. In some embodiments, specific parameters of the selected process system are compared in detail with the digital twin of the group system. This comparison goes beyond the parameter level, also evaluating the overall operational adaptability of the process system within the group. This method can autonomously generate process recipes using system-specific parameters, verify its compatibility with the group, and improve operational efficiency through targeted optimization.

[0013] This method offers significant advantages in integrating new process systems into existing clusters and in evaluating anomalous systems identified through measurement data generated by the measurement engine. This adaptability ensures high efficiency and consistency throughout the operation of the process system.

[0014] In this approach, the development of digital twins adopts a bottom-up method, covering various subsystems such as radio frequency (RF), gas distribution, and temperature control. This enables detailed and effective characterization of each subsystem, laying the foundation for building accurate digital twins of specific process systems.

[0015] By combining the detailed analysis of digital twins with the computational efficiency of neural networks, this method provides an advanced solution for process system matching, which can improve the consistency of system groups, optimize the performance of individual systems, and ensure the efficiency, reliability, and adaptability of the overall system. Attached Figure Description

[0016] To make the description clearer, the following explanation is provided in conjunction with the accompanying drawings:

[0017] Figure 1A The following example illustrates the key components and configuration of a process system (taking atomic layer etching (ALE) as an example).

[0018] Figure 1B This illustrates the operating logic and control mechanism of the system controller used to control the ALE process.

[0019] Figure 2A The following diagram shows the timing of each step in the ALE process under different plasma conditions.

[0020] Figure 2B The diagram shows the timing of the ALE process during the gas exchange step.

[0021] Figure 2C The diagram shows the structure of the substrate before and after the ALE process.

[0022] Figure 3 This diagram illustrates the digital twin of the ALE process system.

[0023] Figure 4 The diagram shows a schematic of the neural network of the system's digital twin.

[0024] Figure 5 This diagram illustrates the process of training a digital twin of an ALE system using multiple neural networks.

[0025] Figure 6A This diagram illustrates the process of determining the resonant frequency using a trained neural network model.

[0026] Figure 6B This diagram illustrates the process of determining the setpoint of a vacuum valve based on neural network prediction.

[0027] Figure 6C This diagram illustrates the process of determining heating and cooling parameters using setpoints derived from a neural network.

[0028] Figure 7 This diagram illustrates a group process system consisting of multiple devices.

[0029] Figure 8A An example is shown: a group subsystem neural network (including a specific chamber subsystem neural network).

[0030] Figure 8B This shows the input and output of the inverse neural network of the group subsystem.

[0031] Figure 9A This diagram illustrates a process for generating the statistical distribution of a subsystem output using a digital twin of the group subsystem.

[0032] Figure 9B A flowchart illustrating the process of training a group subsystem inverse neural network using data generated by the group subsystem neural network.

[0033] Figure 10AThis diagram illustrates an inverse neural network that generates specific chamber parameters for a new process system.

[0034] Figure 10B This diagram illustrates the construction of a neural network for a specific chamber subsystem in a new chamber.

[0035] Figure 11A The diagram illustrates the process of constructing a group system neural network (using the ALE process system as an example).

[0036] Figure 11B The diagram illustrates the process flow for constructing a neural network for a new process system (taking the ALE process system as an example).

[0037] Figure 12A This diagram illustrates a method for determining whether an anomaly exists in a process system.

[0038] Figure 12B This diagram illustrates another method for determining whether an anomaly exists in a process system.

[0039] Figure 13 Table 1 summarizes the parameter information of the structure to be etched and the structure after ALE treatment.

[0040] Figure 14 Table 2 summarizes the parameter information regarding process formulation parameters. Detailed Implementation

[0041] To facilitate a full understanding of the invention, specific embodiments thereof will be described in detail below. While specific details are provided for ease of explanation, any modifications and variations consistent with the technical principles of the invention are considered appropriate. Certain well-known procedures and components are described selectively only to highlight the unique features of the invention.

[0042] Terminology definition:

[0043] Atomic Layer Etching (ALE): A plasma-based etching technique that removes material from a substrate layer by layer through alternating surface modification and sputtering steps.

[0044] Process Recipe: A set of predetermined steps, conditions, and durations used in a semiconductor manufacturing process (including surface modification, sputtering, deposition, and other optional steps).

[0045] Recipe Parameters: Variables that limit the content of the process recipe, including the number of cycles, gas flow rate, RF power setting, substrate temperature, and optional deposition time.

[0046] Subsystem Control Parameters: Operating settings for each subsystem, such as RF resonant frequency, vacuum valve position, gas flow rate, and heater or cooler settings.

[0047] System Digital Twin: A virtual mapping of a semiconductor manufacturing system that simulates the interactions between subsystems, thereby predicting process outcomes and enabling real-time control.

[0048] Reactor Digital Twin: A subset of the system digital twin (including subsystem models of RF, gas, temperature, and plasma, etc.) used for detailed predictions of ion and neutral particle fluxes, substrate surface temperature, and plasma dynamics.

[0049] Chamber Plasma Digital Twin: A component of the reaction chamber digital twin used to simulate plasma behavior, including the distribution of electrons, ions, and neutral particles, plasma sheath properties, and plasma-related phenomena within the chamber.

[0050] RF Digital Twin: A model of an RF subsystem, including a power generator, resonator, and plasma source components, designed to optimize RF power delivery, impedance matching, and plasma ignition.

[0051] Gas Digital Twin: A model that simulates the dynamic characteristics of gas. It can simulate the inflow and outflow of gas, as well as the dynamic changes in gas conductivity and pressure in the chamber, based on parameters such as gas flow rate, vacuum valve position, and chamber geometry.

[0052] Temperature Digital Twin: A model that simulates the thermal environment inside the chamber, including the substrate surface temperature, the dynamic characteristics of the heater and cooler, and the thermal conductivity characteristics of the suction cup.

[0053] Chamber Surface Digital Twin: A model that captures changes in the chamber surface caused by plasma exposure, including material corrosion, surface roughness, compositional variations, and their impact on process performance.

[0054] Substrate Edge Digital Twin: A model for edge-specific behavior that takes into account the effects of variations in plasma, gas flow, and thermal conditions on uniformity and edge ring losses.

[0055] Process Digital Twin: A model that simulates the evolution of substrate structure during process steps, integrating process formulation parameters, material properties, and structural dynamics.

[0056] Group System Digital Twin: A digital twin representing a group of process systems, capturing the statistical distribution of system parameters, and supporting group-level optimization.

[0057] Group Subsystem Digital Twin: A digital twin consisting of specific models of multiple subsystems of a group process system, which can be used to statistically evaluate the behavior of individual subsystems.

[0058] Group Subsystem Neural Network: A neural network based on digital twins of group subsystems, which, after training, can predict the statistical distribution and differences of subsystems within a group.

[0059] Group-System Neural Network: A neural network based on digital twins of group systems, used for real-time evaluation and optimization of group-level process systems.

[0060] Neural Network: A computational model trained using simulation and measurement data that can replicate the behavior of a digital twin, providing fast and real-time predictions for process optimization.

[0061] Subsystem Neural Networks: Neural networks trained for individual subsystems (such as RF, gas, temperature, or chamber surfaces) can improve the prediction accuracy of specific subsystems and enable real-time control.

[0062] System Neural Network: A neural network built based on a system digital twin, used to characterize the entire process system, thereby enabling real-time prediction and optimization.

[0063] Inverse Neural Network: A type of neural network that, when trained, can infer specific parameters of a subsystem or a process system based on input parameters and observed outputs.

[0064] Group Subsystem Inverse Neural Network: An inverse neural network trained using digital twin data of group subsystems can infer the parameters of subsystems in a group process system.

[0065] Measurement Engine: A component of the system controller, used to collect real-time data (such as optical critical dimension (CD) measurement data) to optimize the digital twin model and dynamically adjust process parameters.

[0066] Plasma Sheath: A plasma boundary layer near the surface of the chamber that accelerates the movement of ions toward the substrate and plays a key role in controlling surface modification and sputtering.

[0067] Ion and Neutral Fluxes: The flow rate of ions and neutral particles toward the substrate surface determines the etching or deposition behavior of plasma-based processes.

[0068] Plasma Impedance: This parameter represents the impedance of plasma to RF power and is crucial for optimizing power transmission and impedance matching.

[0069] Cost Function: A mathematical function that evaluates process performance by comparing predicted results with target specifications, and is used to guide optimization algorithms.

[0070] Statistical distribution: used to characterize the differences in subsystem parameters or outputs within a group of process systems, to identify deviations and guide adjustments.

[0071] Deviation Function: A function that compares a specific parameter of the current process with its nominal value, identifying and quantifying problematic parameters through weighting factors.

[0072] Edge Ring: Consumable components near the edge of the substrate inside the cavity are susceptible to wear due to plasma exposure and are crucial for maintaining uniformity.

[0073] Optimization Procedure: A method that uses digital twins or neural networks to iteratively adjust parameters and optimize process formulations to improve performance.

[0074] Figure 1AAn exemplary embodiment of an ALE process system (also referred to as an ALE system) 100A is shown. The inventive concept is illustrated herein using an ALE system as an example, but the invention is not limited thereto and is equally applicable to other similar process systems, such as reactive ion etching (RIE) systems, plasma-enhanced chemical vapor deposition (PECVD) systems, atomic layer deposition (ALD) systems, thermal etching systems, or thermal deposition systems. The ALE system 100A includes a chamber 104 that maintains the vacuum environment required for plasma processes. In this system, a plasma source 106 is configured to receive RF power from an RF power generator 108 via a resonator 110. The plasma source 106 can be configured in various ways, including, but not limited to, an inductively coupled plasma (ICP) source or a transformer-coupled plasma (TCP) source.

[0075] The RF power generator 108 can operate in single-frequency or multi-frequency mode, such as 13.56 MHz and / or 2.0 MHz. Considering the impedance characteristics of the transmission line, the resonator 110 is used to match the output impedance of the RF power generator 108 with the impedance of the plasma chamber 104. The resonator 110 typically consists of an inductor and a capacitor, and in some cases also includes a mechanically adjustable capacitor. Alternatively, in some embodiments, the resonator 110 may not include a mechanically adjustable capacitor. Impedance adjustment can be achieved by changing the operating frequencies of the RF power generator 108 and the resonator 110. In the ALE process, the plasma exhibits different states, resulting in different impedance levels. To maintain efficient energy transfer and minimize the power reflected back to the resonator 110 from the plasma chamber 104, the frequency needs to be adjusted for each different plasma state to ensure that the resonator 110 is always in a resonant state.

[0076] The plasma chamber 104 also includes a chuck 112 for supporting the substrate 114. Depending on process requirements, the chuck 112 can be designed as an electrostatic chuck (ESC) or a vacuum chuck. In a preferred embodiment using an ESC, the chuck 112 is electrically connected to the RF power generator 116 via a resonator 118. Similar to the resonator 110 mentioned earlier, the resonator 118 can be brought to a resonant state by adjusting its operating frequency. It should be noted that the operating frequency of the RF power generator 116 may differ from the operating frequency of the RF power generator 108. For example, the operating frequency of the RF power generator 116 may be much lower than the operating frequency of the RF power generator 108.

[0077] RF power generator 116 provides bias voltage to suction cup 112. This bias voltage is supplied through a conventional blocking capacitor ( Figure 1A (Not shown) Transmission. Optionally, in some embodiments, a custom waveform generator 117 is used to provide bias to the chuck 112. The application of a custom waveform can significantly limit the energy distribution of ions generated by the plasma 115 within the plasma chamber 104. Depending on the specific implementation, the custom waveform generator 117 can be directly connected to the chuck 112 without the need for the RF power generator 116 and / or resonator 118, or it can be used in conjunction with them to provide the required bias to the chuck 112.

[0078] The RF subsystem includes an RF power generator, a resonator, and a plasma source, and its operating status can be monitored via... Figure 1B The plasma chamber 104 is managed by an RF controller 134. The RF controller 134 is communicatively connected to the system controller 132, and its control level is lower than that of the system controller 132. Furthermore, the plasma chamber 104 also includes a gas distribution unit 122 for delivering process gas from the gas source 120 to the plasma chamber 104. The gas distribution unit 122 can take various forms, such as a gas injector or spray head, and may also include a side injection structure disposed near the inner surface of the chamber. The gas source 120 is typically connected to a central gas supply unit and uses a combination of valves and a mass flow controller (MFC) to regulate the gas flow rate entering the chamber.

[0079] A pump 124, which can be a turbomolecular pump or other suitable type, is also provided within the plasma chamber 104 to expel gases and byproducts from the plasma chamber 104. A vacuum valve 126 is typically located above the pump 124 to regulate the exhaust rate of the chamber. The chamber pressure is controlled by a pressure gauge (…). Figure 1A(Not shown) is monitored, and pressure control is achieved by adjusting the position of the moving part of the vacuum valve 126 via an actuator. The position of this moving part corresponds to the set value of the vacuum valve 126. The gas distribution subsystem includes a gas distribution unit 122, a gas source 120, a pump 124, and a vacuum valve 126, and its operating status can be monitored by... Figure 1B The gas controller 136 manages the system. This gas controller is also integrated with the system controller 132 to enable the coordinated operation of the ALE process system.

[0080] In one embodiment, the top of chamber 104 is sealed by a dielectric window 107 to maintain the vacuum environment required for the ALE process. The window may have an opening to accommodate a gas ejector that delivers process gas into the chamber. This opening must be properly sealed to ensure the vacuum tightness of chamber 104. If a spray head is used, the spray head itself can serve as a sealing component. The surface condition of the window, spray head, and gas ejector significantly affects process performance parameters such as defect number and etching rate, but the detailed mechanisms of these effects are still under investigation.

[0081] Chamber 104 also includes a temperature control subsystem to maintain the required thermal environment within the chamber. For example... Figure 1A As shown, the temperature of suction cup 112 is controlled by temperature controller 138 (see...) Figure 1B The controller regulates the heater 128, cooler 130, and temperature sensor. Figure 1A (Not shown) Operation. The suction cup 112 may have multiple temperature zones, each of which can be controlled independently. In addition, temperature regulation may also be required for other chamber components such as the gas distribution unit 122 and the chamber surface, which can be achieved using industry-standard methods.

[0082] In state-of-the-art etching chambers, edge rings 113 are typically used to regulate plasma, gas flow, and temperature conditions at the edge of substrate 114. Edge rings 113 can be made of materials such as silicon, quartz, silicon carbide, or ceramic, and may include mechanisms for regulating their own operating temperature or potential. As a vulnerable component, the edge ring gradually decreases in thickness after prolonged exposure to ions and free radicals in plasma 115.

[0083] An exemplary ALE process alternates between a surface modification step (Step A) and a sputtering step (Step B) in a cyclical manner. In Step A, chemically active radicals generated in plasma 115 interact with the substrate surface, chemically modifying it. The plasma is generated by plasma source 106, which is powered by RF power generator 108. Halogen-based gases such as chlorine are typically used to generate the desired radicals. In this step, the bias voltage of chuck 112 is set to zero to minimize ion bombardment and ensure the integrity of the ALE process. Conversely, in Step B, an inert gas such as argon is introduced to generate high-energy ions, thereby physically removing the chemically modified material layer by sputtering. During this stage, a bias voltage is typically applied to chuck 112 using RF power generator 116, resonator 118, or a custom waveform generator 117 (which may also be used in combination for optimal performance). A purging step may be incorporated between Step A and Step B to facilitate gas switching.

[0084] For high aspect ratio (HAR) structures, an additional deposition step (step C) can be inserted into the ALE cycle sequence, but step C is less frequent than steps A and B. Step C is mainly used to protect the sidewalls of the etched structure to avoid lateral etching caused by ion angular momentum distribution.

[0085] Figure 1B The diagram illustrates the ALE process system 100A operating as an autonomous entity, thanks to the advanced functionality of the system controller 132. The system controller 132 is described in detail through a functional block diagram of the autonomous control system 100B. The system controller 132 is integrated with the RF controller 134, gas controller 136, and temperature controller 138 to ensure the coordinated operation of these subsystems. In one embodiment, a key innovation of the invention is the integration of a system digital twin 140 into the system controller 132, which effectively replicates the behavior of the ALE process system 100A. This design uses the system controller 132 as an intermediary between the real-world process system and its virtual counterpart.

[0086] The system digital twin 140 contains components such as RF digital twin 146, gas digital twin 148, and temperature digital twin 150, which respectively simulate the operation of their respective subsystems.

[0087] The RF digital twin 146 is used to simulate an RF subsystem, which includes an RF power generator and a resonator; its implementation may involve a simulation model (e.g., a SPICE model) or a neural network trained using a combination of simulated data and actual measurement data. In some embodiments, a hybrid approach combining a model and a neural network may be used to improve accuracy.

[0088] The gas digital twin 148 replicates the functionality of a gas distribution subsystem, which includes a gas source 120, a gas distribution unit 122, a pump 124, a vacuum valve 126, and a pressure gauge. Figure 1A Devices (not shown). The gas digital twin 148 can employ fluid dynamics models, analytical models, empirical models, or neural networks trained based on both simulated and actual measurement data. The gas digital twin 148 can also combine these models and neural networks.

[0089] Temperature digital twin 150 is used to simulate a temperature control subsystem, which includes a heater 128, a cooler 130, and a temperature sensor. Figure 1A (Not shown). The temperature digital twin can also provide temperature regulation for other chamber components (e.g., gas distribution unit 122). The temperature digital twin 150 can be implemented using numerical models and analytical models, or using a neural network trained with simulated data and actual measurement data, or a combination of both.

[0090] Within a specific chamber, each subsystem produces slightly different outputs due to variations in the manufacturing process. To achieve real-time process control, the RF digital twin 146, gas digital twin 148, and temperature digital twin 150 must be periodically calibrated to reflect the actual performance of their respective subsystems. Calibration ensures that the digital twins can capture any significant drift in the subsystem outputs over time.

[0091] In plasma processes such as ALE, the inner surface of chamber 104 is exposed to high-energy ions and free radicals for extended periods. Over time, the material thickness of these surfaces may decrease, causing etching parameters (especially those near the substrate edges) to drift. Therefore, monitoring and quantifying such changes within the chamber is crucial. Preventative maintenance procedures can also significantly impact process performance due to the treatment effects on the inner surfaces of the chamber.

[0092] The chamber surface digital twin 149 aims to capture changes in the chamber surface over time with plasma exposure, including the effects of preventative maintenance procedures. This digital twin focuses on selected surfaces, such as the plasma-facing inner surfaces of windows, spray nozzles, and gas ejectors. Given the lack of a fully established mechanistic model and the rapid development of plasma-resistant materials, the digital twin 149 can employ empirical models, lookup tables, neural networks, analytical models, numerical models, or any combination of these methods.

[0093] A digital twin 151 for substrate edges addresses the challenge of performance consistency at substrate edges—where plasma, gas flow, and temperature behaviors differ from those at the substrate center. An edge ring 113 is used to adjust the processing performance of the edge region, but prolonged exposure to plasma can lead to a reduction in edge ring thickness. The digital twin 151 can employ empirical models, lookup tables, neural networks, analytical models, numerical models, or combinations of these methods to address these edge-specific effects.

[0094] The chamber plasma digital twin 152 simulates the plasma dynamics within chamber 104. It integrates inputs from other digital twins (such as the RF digital twin 146, gas digital twin 148, temperature digital twin 150, chamber surface digital twin 149, and substrate edge digital twin 151) to construct a comprehensive model of the behavior of electrons, ions, and neutral particles. This model can depict the distribution of particles in three-dimensional space or a simplified two-dimensional space. Modeling can be continuous over a period of time or composed of discrete snapshots. Furthermore, the model can characterize various particle properties such as energy, momentum, and density.

[0095] For example, when using an ICP source, the ICP source obtains RF power from an RF power generator 108 via a resonator 110. The RF power generates an electromagnetic field within the cavity, thereby generating electrons near the ICP source. These electrons then diffuse and interact with the field, generating ions and neutral particles, as is well known in the art. The chamber plasma digital twin 152 can simulate the formation of a plasma sheath located near the inner surfaces of the substrate 114 and the cavity 104, taking into account the effects of real-time control factors such as frequency adjustment, pressure regulation, and temperature control on the particle distribution evolution process.

[0096] The chamber plasma digital twin 152 may require complex numerical models, which demand significant computational resources. To improve efficiency, neural networks trained on the output of numerical modeling can be employed. Actual measurement data, such as magnetic field distribution recorded by a B-dot probe or electron density measured by a hairpin probe, can enhance the prediction accuracy of the neural network. In some implementations, analytical models can complement both numerical and neural network methods.

[0097] Understanding particle behavior in ALE process systems is crucial for simulating the flux of ions and neutral particles to the substrate surface. Plasmonic sheath characteristics are key to accurate flux calculations and are therefore an important component of these models. These fluxes are critical to the ALE process and can also be measured using specialized equipment to further optimize neural network training data.

[0098] The RF digital twin 146, gas digital twin 148, temperature digital twin 150, and chamber plasma digital twin 152 together constitute the reaction chamber digital twin 154. The chamber surface digital twin 149 and substrate edge digital twin 151 further improve model accuracy by capturing the "drift" effect caused by plasma exposure on chamber components. This integrated reaction chamber digital twin 154 provides key outputs, including the flux of ions and neutral particles to the substrate surface, temperature distribution, and bonding distribution, thereby enabling precise real-time process control.

[0099] The overall system digital twin 140 also includes a process digital twin (e.g., an ALE process digital twin) 156. The process digital twin 156 integrates the output of the reaction chamber digital twin 154 to simulate the evolution of the substrate structure during the ALE process. Its input substrate characteristic data includes mask layer, thickness, material properties, dimensions and structural profile, as well as the characteristics of the target layer to be etched.

[0100] Furthermore, the ALE process digital twin 156 also handles process formulation parameters, such as the duration of steps A and B, the total number of ALE cycles, the insertion point and duration of step C, and pulse modulation-related parameters applied in the ALE steps (such as pulse duration and duty cycle). Other parameters, especially those related to subsystems such as RF power settings, are already included in their respective RF digital twins 146, gas digital twin 148, and temperature digital twin 150. It should be noted that there are various variations in the implementation of the ALE process. For example, step C is optional; for specific applications such as etching thin films with a thickness less than 100 nm, step C may not be necessary. In addition, there are various implementations of the plasma source and bias pulse scheme. All these variations fall within the scope of this invention.

[0101] In terms of implementation, while Monte Carlo simulators or other numerical simulators may offer high accuracy, they often require significant computational resources, which can be a drawback for real-time applications. Another approach is to deploy a neural network for the ALE process digital twin 156. The neural network is initially trained using simulated data, and then further optimized using empirical data to build a robust and responsive system. In some implementations, the ALE process digital twin 156 can be a hybrid configuration, employing both analytical and numerical models, or combining analytical models with neural networks. The self-constraining behavior of the ALE process is well-suited for analytical modeling, effectively capturing the fundamental characteristics of ALE. Numerical models or neural networks can address deviations from the ideal process, such as lateral etching or depth loading effects. This trade-off between models improves prediction accuracy while maintaining computational efficiency.

[0102] The system controller 132 is also equipped with a measurement engine 142 and a real-time (RT) process recipe generator 144, which work together to autonomously generate ALE process recipes and subsystem control parameters. The measurement engine 142 is specifically designed to capture real-time data. For example, optical sensors can collect optical critical dimension data in real time to assess the evolution of the structure at specific steps of the ALE process. Furthermore, subsystem control parameters may deviate from target values ​​due to changes and drift in subsystem components. The measurement engine 142 captures subsystem control parameters in real time, thereby improving the predictive accuracy of the digital twin.

[0103] The real-time process recipe generator 144 is used to generate process recipes before the substrate is loaded onto the chuck for processing. Simultaneously, the real-time process recipe generator 144 can also receive the output of the measurement engine 142 in real time and apply the system digital twin 140 to adjust the process recipes and subsystem control parameters for the remaining steps of the ALE process.

[0104] System controller 132 is also connected to device controller 160 and group controller 162. Figure 7 The demonstration showcases a group of process systems installed on different devices (702, 704, 706) (using three devices as an example; the actual group may contain more devices). Each device includes a device controller 160, and groups of multiple devices are equipped with a central controller (i.e., group controller 162). Additionally, each device includes an Equipment Front End Module (EFEM) 710, an Atmosphere Transfer Module (ATM) 712, and a Vacuum Transfer Module (VTM) 714.

[0105] The various embodiments of the present invention will be described in detail below. In all embodiments, digital twin technology is used to improve system performance; in some embodiments, the formula and subsystem control parameters are first formulated through advanced optimization procedures, and then iteratively optimized.

[0106] Figure 2A The states for steps A, B, and C are shown. (State) This represents a state in the surface modification step (step A) 202, in which the plasma source 106 receives RF power from the RF power generator 108, while the bias voltage of the chuck 112 is set to zero. This state is crucial for achieving chuck-free biased surface modification, preventing high-energy ion impacts on the substrate surface. This represents a state in the sputtering step (step B) 204, in which the chuck receives a bias voltage via an RF power generator 116 and / or a custom waveform generator 117. This bias voltage is critical to the sputtering process because it controls the energy and trajectory of ions toward the substrate.

[0107] state This represents another state in surface modification step 202, in which both plasma source 106 and chuck 112 stop receiving RF power. This state is significant because... The free radicals generated in this state will continuously chemically modify the substrate surface. This represents a state in sputtering step 204, in which both the bias and plasma source are turned off. This state is important for allowing byproducts to diffuse out of the HAR structure.

[0108] state and state All are related to deposition step (step C) 206. State Used to generate the ions and neutral particles required for deposition, while state This allows the generated neutral particles to diffuse to the target location of the HAR structure. These states help deposit a protective film to protect the sidewalls of the structure to be etched during the ALE process.

[0109] Figure 2B An example is shown of an ALE process using process system 100A, including the switching process between process gases. (In state) During this process, the flow rate of the first gas used in the surface modification step 202 gradually decreases, while the flow rate of the second gas used in the sputtering step 204 gradually increases. This switching is crucial for the transition between the two different steps (step A and step B) in the ALE process. Conversely, the state... The first gas flow rate for the surface modification step 202 gradually increases, while the second gas flow rate for the sputtering step 204 gradually decreases, indicating that the process will return to the modification step.

[0110] Figure 2C An example is shown of an input structure 210 to be etched and an output structure 212 after ALE process processing. The input structure (i.e., the initial substrate) 210 includes a mask layer 214, a target layer 216 to be etched in the ALE process, and a layer 218 located below the target layer. Figure 13Table 1 describes the dataset for the input masks, including but not limited to the material, thickness, mask size, contour, uniformity, and loading effects of previous process steps. In some implementations, the mask stack is a photoresist layer. In other implementations, the mask layer may be a hard mask, such as a carbon layer, a silicon oxide layer, a silicon nitride layer, or a combination of these layers. All these properties need to be considered to enable digital twinning of the ALE process. The dataset also includes relevant information for the target layer 216, such as material properties and thickness, as well as the material properties of the underlying layer (i.e., layer 218) (the underlying material may affect the contour near the bottom of the structure after the ALE process).

[0111] As shown in Table 1, the parameters describing the output structure 212 after ALE processing include, but are not limited to, size, profile, uniformity, and loading effects. The profile can be described by several parameters, such as the dimensions of the top and bottom, and the bow shape and its location. Loading effects include the size and depth differences between sparse and dense patterns after ALE processing. The reduction in mask layer thickness and the change in profile indicate the selectivity of the ALE process, which is an important performance indicator.

[0112] Figure 3 A schematic diagram of a system digital twin 140 for the ALE system 100A is provided, which is a complete digital replica of the real-world ALE system. System digital twin 140 includes a reaction chamber digital twin 154, which integrates various subsystem control parameters and chamber structural parameters into its computational framework. These inputs are crucial for accurately simulating the physical interactions and phenomena occurring within the ALE reaction chamber. Process formulation parameters are also incorporated to predict plasma performance within chamber 104.

[0113] The reaction chamber digital twin 154 outputs detailed predicted results such as ion and neutral particle flux and substrate surface temperature. These outputs serve as key inputs to the ALE process digital twin 156, bridging the gap between subsystem control parameters and process results. The ALE process digital twin 156 further integrates ALE process-specific parameters, including initial substrate mask parameters and parameters for the target layer of the ALE process (as shown in Table 1). Furthermore, it integrates detailed ALE process formulation parameters, such as specific states (…). to The duration of steps A through C, the insertion point of step C, and the total number of iterations for each step (e.g., ...). Figure 14 (As shown in Table 2). The digital twin also incorporates spatial location data of the structure to be processed on the substrate. These inputs enable the ALE process digital twin 156 to predict outputs, including the characteristics of the structure after the ALE process (as shown in Table 1) and the total process time of the ALE cycle.

[0114] In terms of implementation, the ALE process digital twin 156 can employ a model-based approach, neural networks, or a combination of both, depending on the complexity of the ALE process, real-time feedback requirements, and prediction accuracy requirements. If a neural network is chosen, advanced computing techniques (such as Monte Carlo simulation) can be used to generate data based on the system digital twin 140. The simulation data generated by the system digital twin 140 can be used to train the neural network. By combining actual measurement results to verify and refine the simulation data, stability and reliability can be improved.

[0115] This digital twin framework can virtually and accurately represent the ALE process, thereby enabling a better understanding, control, and optimization of the complex interactions and parameters that determine the performance of the ALE process system.

[0116] Figure 4 An exemplary process system is shown, represented as an ALE neural network (also known as an ALE system neural network) 400, where each subsystem is represented by a different neural network. For example, an RF digital twin 146 forms the basis for training the RF neural network 402. Taking a plasma source 106 connected to an RF power generator 108 and a resonator 110 as an example, the generator, resonator, and their transmission lines can be simulated using a SPICE model. The SPICE model provides the initial AC current and voltage of the coils in the plasma source 106, thus necessitating the assumption of an initial impedance for the plasma 115. Subsequently, a numerical simulator applies Maxwell's equations to predict the electric field distribution within the plasma chamber 104.

[0117] The simulated data generated by the RF digital twin 146 will be used as the training set for the RF neural network 402. The inputs to the RF neural network 402 include the RF circuit topology and parameters (e.g., the values ​​of inductors, capacitors, resistors, and transistors within the RF power generator and resonator), as well as transmission line effects. Other parameters of the plasma source (e.g., size, location, resistivity, number of coil turns) are also incorporated into the training process. The RF neural network 402 also considers chamber structural parameters (e.g., size, location of chucks and windows, and material properties). During training, parameters that can be measured by sensors are given higher weights. As an example, sensors can track changes in current and voltage in the coils or the reflected power at the output node of resonator 110. A B-dot sensor with multiple small coils can be placed within the chamber to map the magnetic field distribution, ensuring that the RF neural network 402 conforms to observed real-world behavior.

[0118] The bias portion of the RF subsystem is modeled using a neural network, focusing on the electric field initially generated based on the applied RF power. Unlike the magnetic field generated by plasma, the bias involves the electric field affecting the substrate surface.

[0119] Next, the gas dynamics within the system are analyzed. The gas distribution neural network 404 is derived from the gas digital twin 148. Numerical fluid dynamics is fundamental to determining the gas distribution within chamber 104. This complex interaction involves the gas inflow into gas distribution unit 122 and the gas outflow managed by pump 124 and vacuum valve 126, and is influenced by the chamber's gas conductivity and volumetric parameters. While numerical simulation can improve accuracy, its computational resource requirements and time constraints necessitate a more efficient method for real-time applications; therefore, the gas distribution neural network 404 was developed.

[0120] The gas distribution neural network 404 is trained using simulated data reflecting various parameters, including gas type and flow rate, the design of the gas distribution unit 122, the capacity of the pump 124, the position of the moving parts of the vacuum valve 126, chamber dimensions, and gas conductivity. The position of the moving parts of the vacuum valve 126 is controlled by the setpoint of the valve 126. The gas distribution unit 122 can be an ejector or a spray head, or a combination of both, thus affecting the gas distribution in chamber 104. The size, number, and distribution of the internal channels of the ejector and spray head are important design parameters. The gas pressure within the chamber, monitored by a pressure gauge, provides realistic measurement data, thereby enhancing the training of the gas distribution neural network 404. These measurements are typically weighted higher than the simulated data to ensure the model's accuracy in real-world scenarios.

[0121] A temperature control neural network 406 was created based on a temperature digital twin 150. The temperature control neural network 406 is used to map the heat distribution within the chamber (especially on the substrate surface). The temperature control neural network 406 is trained based on a numerical model simulating thermal interactions and distribution. The inputs to the temperature control neural network 406 include chuck parameters and chamber parameters that affect heat conduction. In scenarios involving ESC (Electrical Heat Sink), the thermal characteristics and heat conduction efficiency of the ESC are crucial and can be affected by the helium pressure used as the medium. The setpoints of heating and cooling elements such as heater 128 and cooler 130, as well as other chamber parameter information such as dimensions and build materials, are necessary inputs to the temperature control neural network 406. Temperature readings from sensors within chuck 112 and chamber 104 provide available actual measurement data, which, when used to train the temperature control neural network 406, have higher weights than simulated data because they are obtained through direct measurement of the physical environment. This balance between simulated and measured data ensures accurate predictions from the neural network and its application to the ALE process system.

[0122] The inner surfaces of the chamber (such as windows, gas ejectors, and spray heads) age after prolonged exposure to plasma. A chamber surface neural network 403 can simulate these "memory" effects. Its input parameters include surface material, accumulated ion and free radical exposure, and processing history. Output parameters include surface structure, composition, roughness, and adhesion coefficient, which collectively influence the distribution of free radicals and ions within the chamber. The training data for the chamber surface neural network 403 originates from a chamber surface digital twin 149, and can also be expanded using measurement data acquired through specially designed testing equipment. This neural network can simulate the behavior of a digital twin with significantly improved computational efficiency.

[0123] Vulnerable components (such as edge rings) in chamber 104 undergo dimensional changes after prolonged plasma exposure. For example, a reduction in edge ring thickness can significantly impact process performance at substrate edges. A substrate edge neural network 405 can simulate the behavior of a substrate edge digital twin 151 with higher computational efficiency. Input parameters include structural parameters such as edge ring material and initial height, as well as the history of ions and free radicals exposed to the plasma. Output parameters include the remaining height of the edge ring. In some embodiments, the temperature and potential of the edge region can also be used as input parameters to predict the corrosion rate of the edge ring; or as output parameters provided to the chamber plasma digital twin or neural network.

[0124] Figure 4 The diagram further demonstrates how the output of the subsystem neural network serves as the input to a chamber plasma neural network 408 within the ALE reaction chamber. This chamber plasma neural network 408, based on a chamber plasma digital twin 152, accurately represents the plasma dynamics within the etching chamber. To simulate particle motion within the plasma, Monte Carlo or numerical plasma simulators can be used to visually represent the three-dimensional distribution of electrons, ions, and neutral particles. Because electrons are much lighter than ions and move much faster, they form a plasma sheath on the chamber surface. This sheath plays a crucial role in the acceleration of ions towards the substrate, making this process essential for sputtering but potentially counterproductive during surface modification.

[0125] The training of the chamber plasma neural network 408 incorporates simulated data, thereby improving computational speed and efficiency. To refine predictive capabilities, the training of the chamber plasma neural network 408 can also incorporate measurement data collected by sensors within the chamber, such as optical sensors that detect the emission of neutral particles and hairpin sensors that measure electron density. The measurement data is given greater weight than the simulated data to ensure that the output of the plasma neural network 408 is as realistic as possible.

[0126] The recurrent neural network (RNN) design of the chamber plasma neural network 408 is capable of processing time series data, enabling the network to incorporate snapshots of plasma conditions into the model for future predictions, thus presenting the dynamic evolution of the plasma state. Once the chamber plasma neural network 408 calculates the three-dimensional distribution, the ion flux and neutral particle flux on the substrate surface can be determined using the surface flux neural network 410. Then, the ion flux, neutral particle flux, and substrate surface temperature are used as inputs to the ALE process neural network 412.

[0127] The ALE process neural network 412 can be trained based on data generated from the ALE process digital twin. The output of the ALE process neural network 412 includes the total process time and the post-ALE process structural parameters listed in Table 1. The chamber plasma neural network 408 and the surface flux neural network 410 work together to provide valuable information such as surface temperature and chemical bonding distribution, in addition to flux information. These outputs are crucial for optimizing the ALE process to achieve precise etching and a high-quality substrate surface.

[0128] Figure 5 A flowchart illustrating the method for training the ALE neural network 400 is presented. Flow 500 begins at step 502, where the subsystem neural networks (402, 404, 406, 403, and 405) are trained using simulated data. Subsequently, in step 504, neural networks 408 / 410 are trained using simulated data. In step 506, the ALE process neural network 412 is trained using simulated data (including the outputs of steps 502 and 504). The training scheme for each neural network is further optimized by integrating measurement data relevant to the subsystem, plasma chamber, and the ALE process itself. Various techniques can be employed to increase the weight of the measurement data, including assigning higher weights to the measurement data when constructing the cost function, or reusing the measurement data by artificially adding low-interference elements to improve system stability.

[0129] Figure 6A A flowchart is shown for determining the resonant frequency corresponding to each plasma state in the ALE process, characterized by different plasma impedances. Flow 602 begins at step 608, where the plasma impedance is calculated using a chamber plasma digital twin 152. Subsequently, in step 610, the resonant frequency corresponding to each plasma state is determined based on an RF digital twin 146. Thereafter, in step 612, the RF digital twin 146 is updated to reflect the newly determined resonant frequency.

[0130] Figure 6BThis is a flowchart illustrating the operation of determining the position of a moving part of a vacuum valve based on a gas digital twin 148. Process 604 begins at step 614, where the chamber pressure is calculated using the gas digital twin 148 based on the initial position of the moving part of valve 126. Step 616 involves determining the optimal position of the moving part to achieve the desired chamber pressure. Subsequently, at step 618, the gas digital twin 148 is updated to include the optimized position and relevant setpoints.

[0131] Figure 6C A flowchart illustrating the determination of heater and cooler setpoints is shown. Process 606 begins at step 620, calculating the substrate surface temperature using the temperature digital twin 150 and initial setpoints for heater 128 and cooler 130. Step 622 involves using the temperature digital twin 150 to determine optimized setpoints that maintain the substrate temperature within the desired range. Finally, in step 624, the temperature digital twin 150 is updated to include the optimized setpoints.

[0132] Figure 8A An exemplary group subsystem digital twin 800 is shown. This digital twin 800 exemplary includes subsystem neural networks 802, 804, and 806. Typically, a group subsystem digital twin 800 may contain more subsystem neural networks. These neural networks are all connected to the output of a subsystem selector 808, which is configured to receive subsystem input parameters and select one from the available neural networks during each simulation. The selection process is implemented by a random number generator controlled by a group controller 162. In one particular embodiment, each neural network has an equal probability of being selected. After the subsystem selector 808 selects a subsystem neural network, that network processes the specific subsystem parameters and subsystem input parameters to generate a specific subsystem output.

[0133] The invention concept is illustrated using an RF subsystem as an example: Specific parameters of the RF subsystem may include values ​​of RF circuit components (these values ​​may differ between different RF subsystems) and coil parameters of the plasma source. These parameters can be determined during subsystem manufacturing or after the subsystem is integrated into the chamber. The output of the RF subsystem may include the current, voltage, and phase delivered to the plasma source in the chamber, obtained through SPICE model simulation or measurement by corresponding sensors, and may also include the resonant frequency. Furthermore, it may include the reflected power at a specific operating frequency detected by a directional coupler placed at the output of the RF power generator.

[0134] Multiple simulations can be performed, and the simulation output is processed through the subsystem output engine 810. When the number of simulations is sufficient, the digital twin generates a statistical distribution of the subsystem output and stores the generated statistical distribution in a database.

[0135] Figure 8B An inverse neural network 812 for group subsystems is demonstrated. This inverse neural network takes the subsystem input parameters and the specific subsystem output as inputs, and the specific subsystem parameters as outputs. During training, it retrieves data constituting the statistical distribution from a database; after training, the inverse neural network 812 can infer new specific subsystem parameters using the measurement data of the subsystem outputs.

[0136] Figure 9A The diagram illustrates process 900, which records the simulated statistical distribution of subsystem outputs in a database: Process 900 begins with step 902: constructing a group subsystem digital twin 800, which contains multiple specific subsystem neural networks. Step 904: executing a simulation program (typically repeated multiple times) to generate statistically significant subsystem outputs, with each simulation selecting a subsystem neural network via a random number generator. Step 906: typically generating specific subsystem outputs through neural network inference. Step 908: storing these outputs, along with subsystem input parameters and specific subsystem parameters, in a database using an appropriate data structure for later use.

[0137] Figure 9B A schematic diagram of process 910 is shown, which details the construction process of the inverse neural network 812 for the group subsystem: Process 910 begins with step 912: constructing the inverse neural network 812 and assigning initial weights to it. Step 914: retrieving stored data from the database to obtain the subsystem inputs, outputs, and related specific subsystem parameters. Step 916: training the inverse neural network using this data. After training, the inverse neural network 812 can infer specific subsystem parameters of a new subsystem using the subsystem inputs and measured subsystem outputs.

[0138] Figure 10A A schematic diagram illustrating the application of a group subsystem inverse neural network 812 to a new process system is shown. The trained inverse neural network 812, in inference mode, takes the subsystem input parameters and the newly measured subsystem output as input, and generates new specific subsystem parameters as output.

[0139] Figure 10B A schematic diagram of process 1004 is shown, which is used to construct a subsystem neural network for a new subsystem: Process 1004 begins with step 1006: introducing the new subsystem. Step 1008: performing a measurement procedure on the subsystem to collect and record data. Step 1010: inputting the measurement results along with the subsystem input parameters into the inverse neural network 812 to generate new specific subsystem parameters. Step 1012: constructing the new subsystem neural network. It should be noted that "new subsystem" can refer to a completely new subsystem, a refurbished subsystem, or a subsystem that has undergone preventative maintenance.

[0140] Figure 11A The flowchart illustrates the process of generating an ALE neural network characterizing the operation of a grouped ALE process system: Flow 1100 begins with step 1102: generating a grouped subsystem neural network for each subsystem (including but not limited to the RF subsystem, gas distribution subsystem, temperature control subsystem, chamber surface subsystem, and substrate edge subsystem). Step 1104: generating the ALE neural network for the grouped ALE system based on these grouped subsystem neural networks.

[0141] Figure 11B A schematic diagram of process 1106 is shown, which focuses on generating an ALE neural network for a new process system: Process 1106 begins with step 1108: introducing the new ALE process system. Step 1110: executing process 1004 to determine specific subsystem parameters for all identified subsystems of the new process system. Step 1112: constructing the ALE neural network based on the process system-specific subsystem neural network. It should be noted that the new process system can also be a system that has undergone preventative maintenance—after replacing consumable components and cleaning the inner surfaces of the chamber, the performance of the process system typically changes significantly.

[0142] It should be emphasized that the present invention is illustrated using the ALE process system as an example, but the process systems covered by the present invention are not limited to this, and also include various other plasma process systems and thermal process systems mentioned above.

[0143] Figure 12A A method flow for determining whether a selected process system has anomalies is illustrated: Flow 1200 begins with step 1204: Group controller 162 selects a process system for evaluation. The selected process system can be a new system after installation at the manufacturing site. The process system can be a system whose abnormal behavior is detected by a measurement engine. Step 1206: The system controller 132 of the selected process system executes a measurement procedure; the measurement can be performed on one or all subsystems. Step 1208: Specific process system parameters are determined based on a preset model. In one embodiment, the preset model is one or more inverse neural networks (the specific number depends on the measurement procedure). Step 1210: The group controller 162 compares the determined parameters with the statistical distribution of that parameter within the group (the statistical distribution is retrieved from a database).

[0144] Group controller 162 uses the statistical distribution of new specific process system parameters and historical data to calculate the value of a preset deviation function, which can be expressed as:

[0145]

[0146] in, This is the deviation value. As weight, For specific process system parameters, This is the nominal value of the parameter. The number of parameters is specified. In step 1210, the calculated deviation value is compared with the target value; if the deviation value does not reach the target value, step 1212 is executed to identify the problematic parameters. During the identification process, the degree of deviation between each parameter and its nominal value needs to be analyzed in conjunction with weighting factors.

[0147] Figure 12B Another method for detecting anomalies, flow 1202, is illustrated. Flow 1202 differs from flow 1200 in that it adds step 1209: a process recipe generator 144 autonomously generates a process recipe based on determined specific process system parameters. In one embodiment, the process recipe is generated by the system controller 132 through an optimization program. Taking the ALE process as an example, the system controller receives initial substrate parameters as listed in Table 1. The optimization program minimizes a cost function to determine the process recipe and subsystem control parameters. This cost function can be constructed as the least square error function between the simulated output of one or more structures to be etched and the target output. In step 1214, if the generated process recipe meets the output specifications, flow 1202 ends; otherwise, steps 1210 and 1212 are executed to identify the problematic parameters.

[0148] The present invention is illustrated here using the ALE process system as an example, but the process systems covered by the present invention include, but are not limited to, ALE process systems, RIE process systems, PECVD process systems and ALD process systems.

Claims

1. A method for detecting anomalies within a group process system, characterized in that, include: A process system is selected from a group process system by a group controller, wherein the selected process system is characterized by a digital twin of a specific process system, and the group process system is characterized by a digital twin of the group system. Perform the measurement procedure on the selected process system; Specific process system parameters are determined based on a pre-set model; The specific process system parameters are compared and evaluated with the statistical distribution of group parameters; as well as Anomaly detection is performed based on specific process system parameters.

2. The method according to claim 1, wherein, The method further includes: generating process recipes and subsystem control parameters based on determined specific process system parameters, using a digital twin of the specific process system and combining it with an optimization program.

3. The method according to claim 2, wherein, The anomaly detection includes comparing the results of the process formulation with the specified output specifications.

4. The method according to claim 1, wherein, The specific process system parameters are determined by a subsystem inverse neural network, which is trained using simulated data generated by the group subsystem digital twin.

5. The method according to claim 4, wherein, The inverse neural network takes the measurement data obtained by the measurement program and the subsystem input parameters as input.

6. The method according to claim 1, wherein, The digital twin of the specific process system includes neural networks trained for each subsystem.

7. The method according to claim 6, wherein, The subsystem includes an RF subsystem, a gas distribution subsystem, and a temperature control subsystem.

8. The method according to claim 7, wherein, The specific subsystem neural network contains models for capturing the aging effects of plasma on selected chamber surfaces and substrate edges.

9. The method according to claim 4, wherein, The group subsystem digital twin includes multiple specific subsystem digital twins, and a specific subsystem is selected during the simulation process using a random number generator.

10. The method according to claim 1, wherein, The process system includes an atomic layer etching process system, a reactive ion etching process system, a plasma-enhanced chemical vapor deposition process system, and / or an atomic layer deposition process system.

11. A semiconductor manufacturing process system in a cluster process system, characterized in that, include: RF subsystem, gas distribution subsystem, and temperature control subsystem; A system controller, which includes a system digital twin, a measurement engine, and a recipe generator; The system digital twin includes a subsystem digital twin, a chamber plasma digital twin, and a process digital twin; and A group controller, which includes a digital twin of the group system and a digital twin of the group subsystem; The system controller works in collaboration with the group controller to identify process system anomalies through a process recipe autonomous generation program based on digital twins.

12. The system according to claim 11, wherein, The process formula is generated autonomously by the system controller or group controller through an optimization program.

13. The system according to claim 11, wherein, Anomaly identification is performed by using a subsystem inverse neural network and based on the generated specific subsystem parameters.

14. The system according to claim 13, wherein, The inverse neural network takes the measurement data obtained by the measurement program and the subsystem input parameters as input.

15. The system according to claim 14, wherein, The inverse neural network is trained using simulated data generated by the group subsystem digital twin.

16. The system according to claim 15, wherein, Anomaly detection is performed by analyzing specific subsystem parameters determined by the inverse neural network.

17. The system according to claim 11, wherein, The neural network is trained using simulated data from a digital twin for digital twin representation.

18. The system according to claim 11, wherein, The system's digital twin includes models for simulating the aging effects of plasma on selected chamber surfaces and substrate edges.

19. The system according to claim 11, wherein, The group subsystem digital twin includes multiple specific subsystem digital twins, and a specific subsystem is selected during the simulation process using a random number generator.

20. The system according to claim 11, wherein, The process system includes an atomic layer etching process system, a reactive ion etching process system, a plasma-enhanced chemical vapor deposition process system, and / or an atomic layer deposition process system.

Images