Digital twin for laser material processing

Abstract

The method includes determining first data indicating processing parameters for processing a material within a laser processing system including a digital twin. The method further includes providing the first data as input to a trained machine learning model, the digital twin including the trained machine learning model. The method further includes obtaining one or more outputs of the trained machine learning model, the one or more outputs indicating predicted performance data associated with processing parameters for processing a material. The method further includes ensuring that the material is processed according to the processing parameters based on the predicted performance data.

Description

Technical Field

[0001]

[0001] The present specification generally relates to laser material processing. More specifically, the present specification relates to a digital twin for laser material processing.

Background Art

[0002]

[0002] Laser material processing can utilize a laser material processing system to process materials. Laser material processing systems can be costly in terms of resources spent on prototyping and constructing the system, time spent during operation, and materials used. Using digital twins for laser material processing can reduce waste of resources, time, and materials.

Summary of the Invention

[0003]

[0003] What follows is a simplified summary of the present disclosure in order to provide a basic understanding of some aspects of the present disclosure. This summary is not an exhaustive overview of the present disclosure. It is not intended to define any scope of specific embodiments of the present disclosure or any scope of the claims. The sole purpose of this summary is to present some concepts of the present disclosure in a simplified form as a prelude to the more detailed description that is presented later.

[0004]

[0004] Technologies relating to advanced methods for laser material processing are described. In some embodiments, the method comprises determining first data indicative of processing parameters for processing a material within a laser processing system that includes a digital twin. The method further comprises providing the first data as input to a trained machine learning model, wherein the digital twin includes the trained machine learning model. The method further comprises obtaining one or more outputs of the trained machine learning model, wherein the one or more outputs are indicative of predicted performance data associated with the processing parameters for processing the material. The method further comprises causing the material to be processed in accordance with the processing parameters based on the predicted performance data.

[0005]

[0005] In some embodiments, the system includes a memory and a processing device coupled to the memory. The processing device determines first data indicating processing parameters for processing a material in a laser processing system including a digital twin. The processing device further provides the first data as input to a trained machine learning model, the digital twin including the trained machine learning model. The processing device further obtains one or more outputs of the trained machine learning model, the one or more outputs indicating predicted performance data associated with processing parameters for processing a material. The processing device further ensures that the material is processed according to the processing parameters based on the predicted performance data.

[0006]

[0006] In some embodiments, a non-temporary machine-readable storage medium includes instructions, when executed by the processing device, causing the processing device to determine first data indicating processing parameters for processing a material in a laser processing system including a digital twin. The processing device further provides the first data as input to a trained machine learning model, the digital twin including the trained machine learning model. The processing device further retrieves one or more outputs of the trained machine learning model, the one or more outputs indicating predicted performance data associated with the processing parameters for processing the material. The processing device further ensures that the material is processed according to the processing parameters based on the predicted performance data.

[0007]

[0007] The aspects and embodiments of this disclosure will be better understood from the detailed description and accompanying drawings given below. The aspects and embodiments described below are intended to be illustrative rather than restrictive. [Brief explanation of the drawing]

[0008] [Figure 1]This is a block diagram illustrating an exemplary system architecture according to a specific embodiment. [Figure 2] This invention provides a dataset generator for obtaining predicted performance data associated with processing parameters for processing a material, according to a specific embodiment, and for creating a dataset for a machine learning model associated with ensuring that the material is processed according to the processing parameters, based on the predicted performance data. [Figure 3] This block diagram shows a specific embodiment of obtaining predicted performance data associated with processing parameters for processing a material, and determining, based on the predicted performance data, how to ensure that the material is processed according to the processing parameters and the associated predicted data. [Figure 4] This is an example of a predicted profile of a material processed by a laser material processing system according to several embodiments. [Figure 5A] This is a flowchart of a method associated with obtaining predicted performance data associated with processing parameters for processing a material, according to a specific embodiment, and ensuring that the material is processed according to the processing parameters based on the predicted performance data. [Figure 5B] This is a flowchart of a method associated with obtaining predicted performance data associated with processing parameters for processing a material, according to a specific embodiment, and ensuring that the material is processed according to the processing parameters based on the predicted performance data. [Figure 6] This is a block diagram of a computer system according to a specific embodiment. [Modes for carrying out the invention]

[0009]

[0014] Embodiments of this disclosure relate to systems and methods for laser material processing using digital twins (e.g., the use of digital twin technology to enhance advanced manufacturing for laser material processing tools and control strategies). In laser material processing, lasers are used to manipulate and modify various types of materials (e.g., for etching, drilling, etc.). To achieve precise and desirable results, laser material processing systems incorporate numerous adjustable settings and parameters. These settings and parameters may include laser pulse frequency, gas pressure, beam intensity, focal length, scanning speed, beam diameter, material composition, and many others. The specific combinations and adjustments of these settings can play a crucial role in determining the results of laser material processing.

[0010]

[0015] For example, one specific challenge in laser material processing is drilling uniform holes in a substrate. This task can be complicated by several factors. For instance, problems such as punch-through, where the hole tapers or widens towards the exit, can occur. Furthermore, necking, which refers to narrowing of the hole near the opening, may also occur. These examples highlight some of the complexities and potential problems associated with processing substrates using laser material processing systems.

[0011]

[0016] Traditionally, process spaces (e.g., the range of parameters, conditions, and results related to the laser processing of a particular semiconductor substrate) have been manually mapped (e.g., by processing the material in numerous iterations to adjust parameters and record results). However, this manual mapping approach is costly in terms of time spent and materials used, resource-intensive in terms of tools and personnel, and has limitations in its ability to cover large process spaces.

[0012]

[0017] Aspects and embodiments of this disclosure address the aforementioned and other shortcomings of conventional systems by optimizing the setpoints and parameters of a laser material processing system using a digital twin. The digital twin can encompass critical components, setpoints, and parameters of the actual system, enabling real-time simulation and optimization of laser material processing. In some embodiments, the digital twin includes a machine learning model trained to predict performance data associated with the processed material. The predicted performance data may include a predicted profile for the material processing. Predicted profiles for laser material processing may include, for example, predicted profiles for laser cutting, laser welding, laser drilling, laser engraving, laser cladding, laser annealing, laser ablation, laser micromachining, laser scribing, laser marking, laser thermal treatment, laser cleaning, laser peening, laser surface texturing, laser surface alloying, laser shock peening, and / or similar. In some embodiments, predicted profiles may be generated for any material processing, including those that do not use laser processing.

[0013]

[0018] In some embodiments, processing parameters for a material are determined (for example, based on user input specifying the processing parameters) for processing the material within a laser processing system including a digital twin. These processing parameters may include, for example, material type, material strength, material thermal conductivity, material reflectivity, laser type, laser wavelength, pulse energy, pulse duration, repetition rate, hatch distance, beam diameter, beam shape, beam alignment, beam incidence, gas pressure, focal length, polarization, marking rate, milling strategy, scanning rate, scanning pattern, beam collimation, or focal position. The processing parameters are provided as input to a trained machine learning model within the digital twin, and one or more outputs of the trained machine learning model may be obtained, where one or more outputs represent predicted performance data associated with the material processing parameters. The predicted performance data may then be used to process the material according to the processing parameters.

[0014]

[0019] In some embodiments, preferred processing parameters can be determined based on whether predicted performance data satisfies performance criteria, which may be uniformity criteria.

[0015]

[0020] In some embodiments, a machine learning model is trained using training input data that includes historical processing parameter data and training target output data that includes historical performance data associated with the historical processing parameters.

[0016]

[0021] The aspects and embodiments of this disclosure offer technical advantages. Specifically, the aspects of this disclosure eliminate the need for manual mapping of the process space, saving valuable time and reducing the consumption of materials and human resources. Furthermore, the aspects of this disclosure enable the optimization of each setting and parameter of the laser material processing system, improving accuracy and efficiency.

[0017]

[0022] While some embodiments of this disclosure describe laser material processing of semiconductor substrates in semiconductor processing systems, this disclosure can be used for laser material processing or any type of manufacturing of any material and / or substrate in any type of processing system.

[0018]

[0023] Figure 1 is a block diagram showing an exemplary system 100 (exemplary system architecture) according to a particular embodiment. System 100 (e.g., processing execution component 122 and / or prediction component 114) can perform the methods described herein (e.g., methods 500A-C in Figures 5A-C). System 100 includes a client device 120, manufacturing equipment 124, sensors 126, measuring equipment 128, a prediction server 112, and a data store 140. In some embodiments, the prediction server 112 is part of the prediction system 110. In some embodiments, the prediction system 110 further includes server machines 170 and 180.

[0019]

[0024] In some embodiments, one or more of the client device 120, manufacturing equipment 124, sensor 126, measuring instrument 128, prediction server 112, data store 140, server machine 170, and / or server machine 180 are connected to each other via network 130 to generate prediction data 160 and perform laser material processing operations. In some embodiments, network 130 is a public network that provides the client device 120 with access to the prediction server 112, data store 140, and other publicly available computing devices. In some embodiments, network 130 is a private network that provides the client device 120 with access to the manufacturing equipment 124, sensor 126, measuring instrument 128, data store 140, and other privately available computing devices. In some embodiments, the network 130 includes one or more wide area networks (WANs), local area networks (LANs), wired networks (e.g., Ethernet networks), wireless networks (e.g., 802.11 networks or Wi-Fi networks), cellular networks (e.g., LTE networks), routers, hubs, switches, server computers, cloud computing networks, and / or combinations thereof.

[0020]

[0025] In some embodiments, the client device 120 comprises a computing device such as a personal computer (PC), a laptop, a mobile phone, a smartphone, a tablet computer, and a netbook computer. In some embodiments, the client device 120 includes a processing execution component 122. In some embodiments, the processing execution component 122 may also be included in the prediction system 110 (e.g., a machine learning processing system). In some embodiments, the processing execution component 122 is alternatively included in the prediction system 110 (instead of being included in the client device 120, for example). The client device 120 includes an operating system that enables a user to perform one or more of integrating, generating, viewing or editing data, providing data to the prediction system 110 (e.g., a machine learning processing system), and the like.

[0021]

[0026] In some embodiments, the processing execution component 122 receives one or more of the following: user input (e.g., via a graphical user interface (GUI) displayed via a client device 120), processing parameter data 132, characteristic data (e.g., of the processed substrate / material), performance data 152, etc. In some embodiments, the processing parameter data 132 includes processing parameters that may be, for example, material type, material strength, material thermal conductivity, material reflectivity, laser type, laser wavelength, pulse energy, pulse duration, repetition rate, hatch distance, beam diameter, beam shape, beam alignment, beam incidence, gas pressure, focal length, polarization, marking speed, milling strategy, scanning speed, scanning pattern, beam collimation, or focal position. In some embodiments, the processing parameters include processing parameter values ​​(e.g., laser wavelength value, gas pressure value, etc.) and processing setpoints. In some embodiments, the processing parameters may be adjustable setpoints in a processing operation (e.g., laser material operation). In some embodiments, the processing parameters may be variable characteristics of a processing operation, such as material type. In some embodiments, the processing execution component 122 transmits data (e.g., user input, processing parameter data 132, characteristic data (e.g., processed substrate / material), performance data 152, etc.) to the prediction system 110, receives prediction data 160 from the prediction system 110, determines processing parameters based on the prediction data 160, and ensures that the processing parameters are implemented. In some embodiments, the prediction data 160 is associated with processing parameters (e.g., preferred processing parameters). In some embodiments, the prediction data 160 is associated with the results of processing operations using the processing parameters (e.g., preferred processing parameters).In some embodiments, the process performed according to the processing parameter is associated with one or more of material type, material strength, material thermal conductivity, material reflectivity, laser type, laser wavelength, pulse energy, pulse duration, repetition rate, hatch distance, beam diameter, beam shape, beam alignment, beam incidence, gas pressure, focal length, polarization, marking speed, milling strategy, scanning speed, scanning pattern, beam collimation, or focal position, computational process control (CPC), statistical process control (SPC) (e.g., SPC compared with 3-sigma graphs), advanced process control (APC), model-based process control, design optimization, update of manufacturing parameters, modification of wafer recipes, feedback control, modification of machine learning, and / or the like.

[0022]

[0027] In some embodiments, the process execution component 122 stores data in the data store 140 (e.g., user input, processing parameter data 132, characteristic data (of a processed substrate / material, for example), performance data 152, etc.), and the prediction server 112 acquires the data from the data store 140. In some embodiments, the prediction server 112 stores the output of the trained machine learning model 190 (e.g., prediction data 160) in the data store 140, and the client device 120 acquires the output from the data store 140. In some embodiments, the process execution component 122 receives an indication of a processing parameter from the prediction system 110 (e.g., based on the processing parameter associated with the prediction data 160), and causes execution of a processing operation (e.g., a laser material processing operation) (e.g., causes execution of a process according to the processing parameter) using the processing parameter.

[0023]

[0028] In some embodiments, the prediction server 112, server machine 170, and server machine 180 each include one or more computing devices such as a rack-mount server, router computer, server computer, personal computer, mainframe computer, laptop computer, tablet computer, desktop computer, graphics processing unit (GPU), and accelerator application-specific integrated circuit (ASIC) (e.g., a tensor processing unit (TPU)).

[0024]

[0029] The prediction server 112 includes a prediction component 114. In some embodiments, the prediction component 114 identifies processing parameter data 132 (e.g., processing parameters) (e.g., receives from a client device 120, reads from a data store 140, etc.) and generates prediction data 160 associated with the execution of processing according to the processing parameter data (e.g., laser material processing operation, etc.). In some embodiments, the prediction component 114 uses a digital twin 195 to determine the prediction data 160. In some embodiments, the digital twin 195 includes one or more trained machine learning models 190 for determining the prediction data 160. In some embodiments, the trained machine learning models 190 are trained using historical processing parameter data 134 and historical performance data 154.

[0025]

[0030] In some embodiments, the prediction system 110 uses a digital twin (e.g., a digital representation) of the laser material processing system to determine the results of performing a laser material processing operation with specific processing parameters. The digital twin of the laser material processing system can employ principles and / or equations specific to laser-material interaction, optics, and thermodynamics to model the system's behavior during the laser material processing operation. The digital twin can simulate the interaction between the laser beam and the target material by utilizing fundamental principles such as absorption, reflection, and scattering of the laser and material. Equations relating to the laser's energy distribution, beam profile, and intensity modulation can be incorporated to accurately represent the laser's behavior within the digital twin.

[0026]

[0031] In addition, digital twins can incorporate equations and models that govern the thermal processes within the material being processed. Heat transfer equations, such as the heat conduction equation, can be used to simulate the propagation and dissipation of thermal energy within the material. This is useful for predicting temperature gradients, heat-affected zones, and thermal processes such as melting, recrystallization, or phase changes. Integrating these principles and equations into a digital twin of a laser material processing system makes it possible to represent the physical phenomena that occur during laser material processing.

[0027]

[0032] To reliably predict and / or estimate the results of laser material processing operations using specific parameters, a machine learning model may be included as part of a digital twin or otherwise used by the digital twin. The machine learning model 190 may be a physically guided machine learning model, which is informed by the digital twin. Based on the model's output, the digital twin 195 can determine performance data associated with performing laser material processing operations using specific parameters. For example, for a given type of material (e.g., aluminum), the digital twin 195 can determine a predicted profile, which may be a representation or description of the predicted results or properties of the processed material after the laser material processing operation. For example, the predicted profile may include parameters such as the shape, dimensions, surface quality, and other relevant features of the processed material, as predicted by the model 190. The predicted profile enables evaluation and optimization of the processing parameters of the laser material processing operation, ensuring desired results and meeting specific requirements. In some embodiments, the predicted profile may be a three-dimensional rendering of the predicted results of the material and / or substrate processed by a processing system (e.g., a laser material processing system).

[0028]

[0033] As mentioned above, the digital replica may include a physical-based model of one or more physical assets of the laser material processing system. The processing parameter data 132 may summarize relationships, parameters, specifications, etc., associated with one or more aspects of the physical-based model. For example, within a laser material processing system, the physical-based model can provide insights into the relationship between laser beam characteristics (power, wavelength, spot size, etc.) and the resulting material processing results. The model can show how variations in these parameters affect aspects such as material ablation, melting, or modification. Furthermore, the physical-based model can establish a connection between the optical properties of the material being processed (absorption coefficient, reflectance, and thermal conductivity, etc.) and the heat transfer dynamics during the interaction between the laser and the material. This helps predict and optimize factors such as temperature distribution, heat-affected zone, and thermal stress within the processed material. The processing parameters can be associated with modifications to system components such as laser beam supply optics, focusing lenses, or beam shaping devices. These adjustments aim to optimize the interaction between the laser and the material and achieve desired processing results, such as precise material removal, surface texturing, or drilling.

[0029]

[0034] As described herein, Model 190 may operate in conjunction with a digital twin (e.g., digital twin 195). Hereinafter, a digital twin is a digital replica of a physical asset, such as a manufactured part or processing chamber. The digital twin may include, but is not limited to, characteristics of the physical asset at each stage of laser material processing, including, but are not limited to, material type, material strength, material thermal conductivity, material reflectivity, laser type, laser wavelength, pulse energy, pulse duration, repetition rate, hatch distance, beam diameter, beam shape, beam alignment, beam incidence, gas pressure, focal length, polarization, marking speed, milling strategy, scanning speed, scanning pattern, beam collimation, or focal position.

[0030]

[0035] In some embodiments, the digital twin 195 and / or model 190 may employ statistical modeling to predict laser material processing results corresponding to processing parameter data 132. The predicted or estimated results (e.g., predicted performance data 162, predicted data 160, etc.) may include a predicted profile of the processed material. In some embodiments, the predicted profile may include parameters such as the shape, dimensions, surface quality, and other relevant characteristics of the processed material, as predicted by the digital twin 195 and / or model 190. A statistical model may be used to process the predicted performance data 162 based on previously processed historical performance data 154, using statistical operations to validate, predict, and / or transform the predicted performance data 162. In some embodiments, the statistical model is generated using statistical process control (SPC) analysis to determine control limits for the data and identify whether the data is highly or poorly reliable based on those control limits. In some embodiments, the statistical model is associated with univariate and / or multivariate data analysis. For example, various parameters can be analyzed using statistical models, and patterns and correlations can be determined through statistical processing (e.g., range, minimum value, maximum value, quartiles, variance, standard deviation, etc.). In another example, regression analysis, path analysis, factor analysis, multivariate statistical process control (MCSPC), and / or multivariate analysis of variance (MANOVA) can be used to examine the relationships between multiple variables.

[0031]

[0036] In some embodiments, the prediction system 110 (e.g., prediction server 112, prediction component 114) generates prediction data 160 using supervised machine learning (e.g., supervised dataset, historical performance data 154, labeled historical processing parameter data 134, etc.). In some embodiments, the prediction data 160 may include predicted performance data 162. In some embodiments, the prediction system 110 generates prediction data 160 (including predicted performance data 162) using semi-supervised learning (e.g., semi-supervised dataset, performance data 152 are predicted percentages, etc.). In some embodiments, the prediction system 110 generates prediction data 160 (including predicted performance data 162) using unsupervised machine learning (e.g., unsupervised dataset, clustering, clustering based on historical processing parameter data 134, etc.).

[0032]

[0037] In some embodiments, the manufacturing equipment 124 includes one or more of the following: processing chambers, deposition chambers, cluster tools, wafer backgrinding systems, wafer sawing equipment, die bonding machines, wire bonders, die overcoating systems, molding equipment, airtight sealing equipment, metal can welding machines, deflash / cut / form / pieceping (DTFS) machines, branding equipment, lead finishing equipment, and / or similar. In some embodiments, the manufacturing equipment 124 includes a laser material processing system 125. In some embodiments, the manufacturing equipment 124 is part of a substrate processing system (e.g., an integrated processing system). The manufacturing equipment 124 includes one or more of the following: a controller, an enclosure system (e.g., a substrate carrier, a forward-opening unified pod (FOUP), an auto-teaching FOUP, a process kit enclosure system, a substrate enclosure system, a cassette, etc.), a lateral storage pod (SSP), an aligner device (e.g., an aligner chamber), a factory interface (e.g., an equipment front-end module (EFEM)), a load lock, a transfer chamber, one or more processing chambers, a robotic arm (e.g., positioned in the transfer chamber, positioned in the front interface, etc.), and / or similar. The enclosure system, SSP, and load lock are mounted to the factory interface, and the robotic arm positioned in the factory interface transfers contents (e.g., substrates, process kit rings, carriers, verification wafers, etc.) between the enclosure system, SSP, load lock, and factory interface. The aligner device is positioned in the factory interface to align the contents. The load lock and processing chamber are mounted in the transfer chamber, and a robotic arm positioned within the transfer chamber transfers contents (e.g., substrates, process kit rings, carriers, verification wafers, etc.) between the load lock, processing chamber, and transfer chamber. In some embodiments, the manufacturing equipment 124 includes components of the substrate processing system.In some embodiments, the performance data 152 of the laser material processing system 125 is the result of the laser material processing system 125 performing one or more laser material processing operations (e.g., laser drilling, laser etching, laser annealing, laser ablation, laser doping, laser scribing, laser welding, laser deposition, laser trimming and repair, etc.).

[0033]

[0038] In some embodiments, laser material processing using the laser material processing system 125 involves converting the laser beam from the light source into circularly polarized light by utilizing a quarter-wave plate to prevent anisotropic absorption on the ablation surface. The beam can then be directed toward an aperture Garbo scan head containing an F-theta lens after passing through a suitable beam expander. The beam can be focused onto the material surface to produce a specific beam spot size. To ensure optimal results, meticulous manual optimization is required throughout the entire process, including adjusting parameters such as wavelength, pulse energy, average power, repetition rate, hatch distance, marking speed, milling strategy, optical bench setup, and beam alignment. The implementation of digital twin technology enables the realization of optimization goals for the laser processing process, such as improved product quality, increased yield, reduced energy consumption, minimized material waste, and improved process stability. Advanced process control using digital twins can be beneficial to achieve these goals in real time and optimize the economic model of the laser material processing tool.

[0034]

[0039] In some embodiments, the sensor 126 provides performance data 152 of the laser material processing system (e.g., sensor values ​​such as past and current sensor values) (e.g., laser drilling performance data, laser etching performance data, laser annealing performance data, laser ablation performance data, laser doping performance data, laser scribing performance data, laser welding performance data, laser deposition performance data, laser trimming and repair performance data, etc.).

[0035]

[0040] In some embodiments, the sensor 126 and / or measuring instrument 128 may include an optical microscope (used to determine the properties and surface of laser-treated materials by measuring material properties such as hole depth and hole uniformity), an ellipsometer (used to determine the properties and surface of thin films by measuring material properties such as layer thickness, optical constants, surface roughness, composition, and optical anisotropy), an ion mill (used to prepare heterogeneous bulk materials when it is necessary to uniformly thin a large area of ​​material), a capacitance-voltage (CV) system (used to measure the capacitance-voltage and capacitance-time (Ct) properties of substrates such as semiconductor devices), an interferometer (used to measure distance in terms of wavelength or to determine the wavelength of a particular light source), a source measuring unit (SME), a magnetometer, and optical and imaging systems. This includes one or more measuring tools such as a profilometer, wafer prober (used to test semiconductor wafers before separating them into individual dies or chips), imaging station, scanning electron microscope (CD-SEM, used to ensure the stability of the manufacturing process by measuring the critical dimensions of the substrate), reflectometer (used to measure reflectance and radiance from a surface), resistance probe (used to measure the resistivity of thin films), resistance fast electron diffraction (RHEED) system (used to measure or monitor the crystal structure or crystal orientation of epitaxial thin films of silicon or other materials), X-ray diffractometer (used to clearly determine the crystal structure, crystal orientation, film thickness, and residual stress in silicon wafers, epitaxial films, or other substrates), and / or similar.

[0036]

[0041] In some embodiments, performance data 152 is used for product health (e.g., product quality). In some embodiments, performance data 152 is received over a period of time.

[0037]

[0042] In some embodiments, the sensor 126 and / or measuring instrument 128 provides performance data 152 including one or more of the following: morphological data, size attribute data, dimensional attribute data, image data, optical microscope images, scanning electron microscope (SEM) images, energy-dispersive X-ray (EDX) images, spatial position data, elemental analysis data, wafer signature data, chip layer, chip layout data, edge data, gray level data, signal-to-noise data, temperature data, interval data, current data, power data, voltage data, etc.

[0038]

[0043] In some embodiments, the performance data 152 includes morphological data (e.g., data related to the morphology of the substrate, such as laser etching depth, laser etching uniformity, and surface topography). In some embodiments, the performance data 152 includes size attribute data (e.g., data representing the size of the substrate attributes). In some embodiments, the performance data 152 includes dimensional attribute data (e.g., data representing the dimensions of the substrate attributes). In some embodiments, the performance data 152 includes SEM images (e.g., images captured by a scanning electron microscope that uses a focused beam of electrons to scan the surface of the substrate and produce high-resolution images). In some embodiments, the performance data 152 includes EDX images (e.g., images generated from data collected using X-ray technology to identify the elemental composition of the material). In some embodiments, the performance data 152 includes defect distribution data (e.g., data representing the spatial distribution, temporal distribution, etc., of defects on the substrate). In some embodiments, the performance data 152 includes spatial location data (e.g., data representing the spatial location of substrate attributes, defects, elements, etc.). In some embodiments, performance data 152 includes elemental analysis data (e.g., data representing the elemental composition of the substrate). In some embodiments, performance data 152 includes wafer signature data (e.g., data representing the distribution of wafer defects on the substrate due to a single manufacturing problem). In some embodiments, performance data 152 includes chip layer data (e.g., associated with layers or operations in the substrate manufacturing process). In some embodiments, performance data 152 includes chip layout data (e.g., data representing the layout of the substrate in terms of planar geometric shape). In some embodiments, performance data 152 includes edge data (e.g., data representing the edges of the wafer). For example, edge data may represent chipped edges, wafer edge thickness, wafer curvature, wafer distortion, etc.In some embodiments, the performance data 152 includes gray level data (e.g., data representing the brightness of pixels in an image of the substrate) and signal-to-noise data (e.g., data representing the signal-to-noise ratio of the substrate measured using a spectroscopic instrument).

[0039]

[0044] In some embodiments, performance data 152 (e.g., historical performance data 154, current performance data 156, etc.) is processed by the client device 120 and / or the prediction server 112. In some embodiments, processing of performance data 152 includes generating features. In some embodiments, features are patterns in the performance data 152 (e.g., slope, width, height, peak, etc.) or combinations of values ​​from the performance data 152 (e.g., power derived from voltage and current, etc.). In some embodiments, performance data 152 includes features used by the prediction component 114 to obtain prediction data 160.

[0040]

[0045] In some embodiments, the measuring instrument 128 may be included as part of the manufacturing equipment 124. For example, the measuring instrument 128 may be contained inside or connected to the processing chamber and configured to generate measurement data (e.g., performance data 152, current performance data 156, etc.) of the substrate and / or material while the substrate remains in the processing chamber during and / or after undergoing a laser material process (e.g., laser drilling process, laser etching process, laser annealing process, laser ablation process, laser doping process, laser scribing process, laser welding process, laser deposition process, laser trim and repair process, etc.). In some cases, the measuring instrument 128 may be referred to as an in-situ measuring instrument. In another example, the measuring instrument 128 may be connected to another station of the manufacturing equipment 124. For example, the measuring instrument may be connected to a transfer chamber, load lock, or factory interface.

[0041]

[0046] In some embodiments, measuring instruments 128 (e.g., ellipsometry instruments, imaging instruments, spectrometers, etc.) are used to determine measurement data (e.g., inspection data, image data, spectroscopic data, ellipsometry data, material composition, optical, or structural data, etc.) corresponding to the substrate and / or material manufactured by the manufacturing equipment 124 (e.g., laser material processing system 125, laser material processing equipment, etc.). In some examples, after the manufacturing equipment 124 has processed the substrate, measuring instruments 128 are used to inspect the substrate. In some examples, after the manufacturing equipment 124 (e.g., laser material processing system 125) has processed the substrate, sensors 126 are used to inspect the substrate and / or the processed material. In some embodiments, measuring instruments 128 perform scanning ultrasonic microscopy (SAM), ultrasound, X-ray inspection, and / or computed tomography (CT) inspection. In some embodiments, after a manufacturing device 124 (e.g., a laser material processing system 125) has performed a laser material processing on a substrate, the measuring device 128 is used to determine the quality of the processed substrate (e.g., uniformity and quality of laser drilling, laser etching, laser annealing, laser ablation, laser doping, laser scribing, laser welding, laser deposition, laser trimming and repair, etc.). In some embodiments, the measuring device 128 includes an imaging device (e.g., a scanning electron microscope, optical microscope, SAM equipment, ultrasonic equipment, X-ray equipment, and / or CT equipment). In some embodiments, the performance data 152 includes sensor data from sensor 126 and / or measurement data from the measuring device 128.

[0042]

[0047] In some embodiments, performance data 152 includes sensor data from a sensor 126 located in the insite (e.g., within the laser material processing chamber) and / or measurement data from a measuring instrument 128. In some embodiments, performance data 152 includes user input via a client device 120 and / or measurement data from the measuring instrument 128.

[0043]

[0048] In some embodiments, performance data 152 may be derived from measurement data and / or sensor data. Measurement data may be data describing measurements of the substrate. Sensor data may be data representing the state and characteristics of the substrate, or the state and characteristics inside a processing chamber (e.g., a laser material processing chamber).

[0044]

[0049] In some embodiments, the datastore 140 is memory (e.g., random access memory), a drive (e.g., a hard drive, a flash drive), a database system, or another type of component or device capable of storing data. In some embodiments, the datastore 140 includes multiple storage components (e.g., multiple drives or multiple databases) spanning multiple computing devices (e.g., multiple server computers). In some embodiments, the datastore 140 stores one or more of the following: processing parameter data 132, performance data 152, and / or prediction data 160.

[0045]

[0050] In some embodiments, the data store 140 may be configured to store data that is inaccessible to users of the manufacturing system. For example, process data, spectral data, and context data obtained about substrates being processed in the manufacturing system are inaccessible to users of the manufacturing system (e.g., operators). In some embodiments, all data stored in the data store 140 can be made inaccessible to users of the manufacturing system. In some embodiments, some parts of the data stored in the data store 140 can be made inaccessible to users, while other parts of the data stored in the data store 140 can be made accessible to users. In some embodiments, one or more parts of the data stored in the data store 140 can be encrypted using an encryption mechanism unknown to the user (e.g., the data is encrypted using a secret encryption key). In some embodiments, the data store 140 may include multiple data stores, where data inaccessible to users is stored in one or more first data stores, and data accessible to users is stored in one or more second data stores.

[0046]

[0051] Performance data 152 may include historical performance data 154 and current performance data 156. In some embodiments, at least a portion of the performance data 152 is from the sensor 126 and / or measuring instrument 128. Performance data 152 may indicate whether the substrate is properly designed, properly manufactured, uniform with other substrates, and / or properly functioning. Performance data 152 may indicate whether the substrate processing operation (e.g., laser material processing operation) was performed correctly.

[0047]

[0052] For example, performance data 152 for laser drilling operations may indicate hole diameter, hole depth, hole quality (e.g., drilled holes must accurately and consistently meet expected dimensions and have minimal thermal damage or recast layers). Performance data 152 for laser etching operations may indicate feature accuracy (etched features must have accurate dimensions, shape, and edge quality), etching depth control (the etching process must achieve the desired depth accurately and uniformly across the entire substrate), and surface finish (the etched surface must be smooth, free from roughness, and have the desired texture or pattern). Performance data 152 for laser annealing operations may indicate dopant activation (the annealing process must effectively activate dopants and achieve the desired electrical properties in the treated area), and crystal structure recovery (the annealing process must eliminate amorphous regions or crystal defects). Performance data 152 for laser ablation operations may indicate material removal accuracy (the laser ablation process must accurately remove the material), surface quality (the ablated surface must have minimal heat-affected zone or recast layer), etc. Performance data 152 for laser doping operations may indicate dopant incorporation (the laser doping process must successfully introduce dopant atoms to the desired area and achieve the desired doping concentration), etc. Performance data 152 for laser scribing operations may indicate line accuracy (the laser scribing process must create accurate and clear scribe lines with the desired width, depth, and edge quality), scribe width control (the scribing process must precisely control the width of the scribe line to avoid electrical or structural problems), etc.Performance data 152 for laser welding operations may indicate bond strength (laser welding must provide a strong and reliable bond between joined components and meet specified mechanical and electrical requirements), heat-affected zone control (the laser welding process must minimize the size and influence of the heat-affected zone to prevent damage to surrounding materials or components). Performance data 152 for laser deposition operations may indicate layer thickness control (laser deposition must achieve the desired thickness and uniformity of the deposited layer), adhesion, and integrity (the deposited layer must adhere well to the substrate and exhibit good integrity without cracks, delamination, or voids). Performance data 152 for laser trim and repair operations may indicate component correction accuracy (the laser trim and repair process must accurately correct circuits or structures as needed, achieving the desired correction without causing unintended damage or changes).

[0048]

[0053] In some embodiments, at least a portion of the performance data 152 is associated with the quality of the substrate produced by the manufacturing equipment 124 (e.g., the laser material processing system 125). In some embodiments, at least a portion of the performance data 152 is based on measurement data from the measuring equipment 128 (e.g., past performance data 154 includes measurement data, substrate characteristic data, yield, etc., indicating a properly processed substrate). In some embodiments, at least a portion of the performance data 152 is based on substrate inspection (e.g., current performance data 156 based on actual inspection). In some embodiments, the performance data 152 includes user input (e.g., via the client device 120) indicating the quality of the substrate. In some embodiments, the performance data 152 includes representations of absolute values ​​(e.g., indicating that the substrate inspection data is off the threshold data by a calculated value, the deformation value is off the threshold deformation value by a calculated value) or relative values ​​(e.g., indicating that the substrate inspection data is off the threshold data by 5%, the deformation is off the threshold deformation by 5%, the hole uniformity is off the threshold uniformity by 5%, etc.). In some embodiments, the performance data 152 indicates that threshold error amounts (e.g., at least 5% error in laser etching uniformity after laser material processing operation, at least 5% error in manufacturing, at least 5% error in flow, at least 5% error in deformation, specification limits, etc.) are met.

[0049]

[0054] In some embodiments, historical data includes one or more of the historical processing parameter data 134 and / or historical performance data 154 (e.g., at least a portion for training the machine learning model 190). Current data includes one or more of the current processing parameter data 136 and / or current performance data 156 (e.g., at least a portion that is input to the trained machine learning model 190 after the model 190 has been trained using the historical data). In some embodiments, current data is used to retrain the trained machine learning model 190.

[0050]

[0055] In some embodiments, the prediction data 160 is used to predict the results of a laser processing operation based on processing parameter data (e.g., using specific processing parameters). Performing multiple laser material processing operations (e.g., each with different processing parameters) on multiple products to determine performance data using each set of processing parameters is costly in terms of time spent, materials used, etc. By providing processing parameter data 132 to model 190 and receiving prediction data 160 from model 190, system 100 has the technical advantage of saving time and materials (e.g., substrates) by avoiding the costly process of performing multiple laser material processing operations (e.g., each with different processing parameters) on multiple products to determine performance data using each set of processing parameters.

[0051]

[0056] Using manufacturing equipment 124 to perform a manufacturing process (e.g., laser material processing operation) and employing specific processing parameters that result in defective products or damage to the manufacturing equipment is costly in terms of time, energy, products, and the manufacturing equipment 124. By providing processing parameter data 132 to model 190, receiving predictive data 160 from model 190, and obtaining predicted performance data 162 based on the predictive data 160, system 100 has the technical advantage of avoiding the costs of manufacturing, identifying, and disposing of defective substrates.

[0052]

[0057] In some embodiments, the prediction system 110 further includes server machines 170 and 180. Server machine 170 includes a dataset generator 172, which can generate datasets (e.g., a set of data inputs and a set of target outputs) for training, validating, and / or testing a machine learning model 190. The dataset generator 172 has the capability to collect, edit, reduce, and / or partition data to make it suitable for machine learning. In some embodiments (e.g., for small datasets), partitioning for post-training validation (e.g., explicit partitioning) is not used. Iterative cross-validation (e.g., 5-fold cross-validation, skip-one cross-validation) may be used during training, in which case the given dataset is substantially iteratively partitioned into different training and validation sets during training. From the vector of models on automatically separated combined subsets, a model (e.g., the best model, the most accurate model, etc.) is selected. In some embodiments, the dataset generator 172 can explicitly split historical data (e.g., historical processing parameter data 134 and corresponding historical performance data 154) into a training set (e.g., 60 percent of the historical data), a validation set (e.g., 20 percent of the historical data), and a test set (e.g., 20 percent of the historical data). Some operations of the dataset generator 172 are described in detail below with reference to Figure 2 according to some embodiments. In some embodiments, the prediction system 110 generates multiple sets of features (e.g., training features) (e.g., via a prediction component 114).In some examples, the first set of features corresponds to the first set of trait data types corresponding to each dataset (e.g., a training set, a validation set, and a test set) (e.g., a first combination of values ​​from a first set of sensors, a first pattern of values ​​from a first set of sensors), and the second set of features corresponds to the second set of trait data types corresponding to each dataset (e.g., a second combination of values ​​from a second set of sensors different from the first set of sensors, different from the first combination, a second pattern different from the first pattern).

[0053]

[0058] The server machine 180 includes a training engine 182, a validation engine 184, a selection engine 185, and / or a test engine 186. In some embodiments, the engines (e.g., training engine 182, validation engine 184, selection engine 185, and test engine 186) refer to hardware (e.g., circuits, dedicated logic, programmable logic, microcode, processing devices, etc.), software (e.g., instructions executed on processing devices, general-purpose computer systems, or dedicated machines), firmware, microcode, or a combination thereof. The training engine 182 can train a machine learning model 190 using one or more sets of features associated with a training set from a dataset generator 172. In some embodiments, the training engine 182 generates multiple trained machine learning models 190, where each trained machine learning model 190 corresponds to a separate set of parameters from the training set (e.g., processing parameter data 132) and a corresponding response (e.g., performance data 152). In some embodiments, multiple models are trained with the same parameters having different targets to model multiple effects.

[0054]

[0059] In some examples, a first trained machine learning model was trained using 152 performance data from all 126 sensors (e.g., sensors 1-5), a second trained machine learning model was trained using a first subset of performance data (e.g., from sensors 1, 2, and 4), and a third trained machine learning model was trained using a second subset of performance data (e.g., from sensors 1, 3, 4, and 5) that partially overlapped with the first subset of features.

[0055]

[0060] In some examples, a first trained machine learning model was trained using processing parameter data 132 from all sensors 126 (e.g., sensors 1-5), a second trained machine learning model was trained using a first subset of processing parameter data (e.g., from sensors 1, 2, and 4), and a third trained machine learning model was trained using a second subset of processing parameter data (e.g., from sensors 1, 3, 4, and 5) that partially overlapped with the first subset of features.

[0056]

[0061] The validation engine 184 can validate the trained machine learning models 190 using the corresponding set of features from the validation set of the dataset generator 172. For example, a first trained machine learning model 190 trained using a first set of features from the training set is validated using the first set of features from the validation set. The validation engine 184 determines the accuracy of each trained machine learning model 190 based on the corresponding set of features from the validation set. The validation engine 184 evaluates trained machine learning models 190 that have an accuracy that does not meet a threshold accuracy and flags them (e.g., to be discarded). In some embodiments, the selection engine 185 can select one or more trained machine learning models 190 that have an accuracy that meets a threshold accuracy. In some embodiments, the selection engine 185 can select the trained machine learning model 190 with the highest accuracy among the trained machine learning models 190.

[0057]

[0062] The test engine 186 can test the trained machine learning models 190 using the corresponding set of features from the test set derived from the dataset generator 172. For example, a first trained machine learning model 190 trained using a first set of features from the training set is tested using a first set of features from the test set. Based on the test set, the test engine 186 determines which trained machine learning model 190 is the most accurate among all the trained machine learning models.

[0058]

[0063] In some embodiments, the machine learning model 190 (e.g., used for classification) refers to a model artifact created by the training engine 182 using a training set that includes data inputs and corresponding target outputs (e.g., correctly classifying a state or ordinal level for each training input). Patterns in the dataset can be found that map data inputs to target outputs (correct classifications or levels), and mappings that capture these patterns are provided to the machine learning model 190. In some embodiments, the machine learning model 190 uses one or more of the following: Gaussian process regression (GPR), Gaussian process classification (GPC), Bayesian neural networks, neural network Gaussian processes, deep belief networks, Gaussian mixture models, or other probabilistic learning methods. Non-probabilistic methods may also be used, including one or more of the following: support vector machines (SVM), radial basis functions (RBF), clustering, nearest neighbor algorithm (k-NN), linear regression, random forest, neural networks (e.g., artificial neural networks), etc. In some embodiments, the machine learning model 190 is a multivariate analysis (MVA) regression model.

[0059]

[0064] The prediction component 114 provides the current processing parameter data 136 (e.g., as input) to the trained machine learning model 190 and runs the trained machine learning model 190 (e.g., on the input to obtain one or more outputs). The prediction component 114 can determine (e.g., extract) prediction data 160 (e.g., including prediction performance data 162) from the trained machine learning model 190 and determine (e.g., extract) uncertainty data indicating the level of confidence that the prediction data 160 corresponds to the current performance data 156. In some embodiments, the prediction component 114 or the processing execution component 122 uses uncertainty data (e.g., uncertainty function, or acquisition function derived from uncertainty function) to determine whether to use the prediction data 160 to perform a laser material processing operation according to the processing parameters, or to further train the model 190.

[0060]

[0065] In aspects of this disclosure, for illustrative purposes rather than limiting purposes, we describe training one or more machine learning models 190 using historical data (e.g., previous data, historical processing parameter data 134, and historical performance data 154) and providing current processing parameter data 136 to one or more trained probabilistic machine learning models 190 to determine predictive data 160. In other embodiments, a heuristic model or rule-based model is used to determine predictive data 160 (e.g., without using a trained machine learning model). In other embodiments, a non-probabilistic machine learning model may be used. The predictive component 114 monitors the historical processing parameter data 134 and historical performance data 154. In some embodiments, any of the information described with respect to the data input 210 in Figure 2 is monitored or used by the heuristic model or rule-based model.

[0061]

[0066] In some embodiments, the functions of client device 120, prediction server 112, server machine 170, and server machine 180 are provided by fewer machines. For example, in some embodiments, server machines 170 and 180 are integrated into a single machine, while in some other embodiments, server machine 170, server machine 180, and prediction server 112 are integrated into a single machine. In some embodiments, client device 120 and prediction server 112 are integrated into a single machine.

[0062]

[0067] In general, functions described in one embodiment as being performed by the client device 120, prediction server 112, server machine 170, and server machine 180 may, in other embodiments, be performed on the prediction server 112, where appropriate. Furthermore, functions belonging to a particular component may be performed by different components or by multiple components working together. For example, in some embodiments, the prediction server 112 determines whether to perform a laser material processing operation according to processing parameters based on prediction data 160. In other examples, the client device 120 determines the prediction data 160 based on data received from a trained machine learning model.

[0063]

[0068] Furthermore, the functionality of a particular component can be performed by different components or by multiple components working together. In some embodiments, one or more of the prediction server 112, server machine 170, or server machine 180 are accessed as services provided to other systems or devices via an appropriate application programming interface (API).

[0064]

[0069] The manufacturing system can perform one or more processes (e.g., laser material processes) on the substrate. The substrate can be a planar article of fixed dimensions with any suitable hardness (e.g., a silicon-containing disk or wafer, a patterned wafer, a glass plate, etc.) that is suitable for fabricating electronic devices or circuit components on it.

[0065]

[0070] A laser material processing chamber can perform any number of processes on a substrate. The same or different substrate processes may be performed within each individual processing chamber. The laser material processing chamber may include one or more sensors configured to capture substrate data before, after, or during the substrate processing. For example, one or more sensors may be configured to capture the diameter, depth, and uniformity of holes in the substrate.

[0066]

[0071] The processing chamber can perform each substrate manufacturing process (e.g., laser material processing operation) according to a process recipe (e.g., according to processing parameters). The process recipe defines a specific set of operations to be performed during the process and may include one or more settings or parameters associated with each operation. For example, a laser material processing operation may include material type, material strength, material thermal conductivity, material reflectivity, laser type, laser wavelength, pulse energy, pulse duration, repetition rate, hatch distance, beam diameter, beam shape, beam alignment, beam incidence, gas pressure, focal length, polarization, marking speed, milling strategy, scanning speed, scanning pattern, beam collimation, or focal position, etc.

[0067]

[0072] In some embodiments, “User” is represented as a single individual. However, other embodiments of this disclosure include the fact that “User” is an entity controlled by multiple users and / or automated sources. In some examples, a set of individual users, united as a group of administrators, is considered “User.”

[0068]

[0073] While embodiments of this disclosure are discussed in terms of determining predictive data 160 for determining the results of a laser material processing operation based on processing parameter data 132 for laser material processing within a manufacturing facility (e.g., a substrate processing facility), in some embodiments, this disclosure may generally be applicable to laser material processing in any type of manufacturing facility.

[0069]

[0074] Figure 2 shows a dataset generator 272 (e.g., dataset generator 172 in Figure 1) for creating a dataset for a machine learning model (e.g., related to obtaining predicted performance data associated with processing parameters for processing a material, and based on the predicted performance data, processing the material according to the processing parameters, methods 500A-C, etc.) (e.g., model 190 in Figure 1). In some embodiments, the dataset generator 272 is part of the server machine 170 in Figure 1. The dataset generated by the dataset generator 272 in Figure 2 can be used to train a machine learning model to obtain predicted performance data associated with processing parameters for processing a material, and based on the predicted performance data, processing the material according to the processing parameters (see, for example, Figure 5B).

[0070]

[0075] The dataset generator 272 (e.g., dataset generator 172 in Figure 1) creates a dataset for a machine learning model (e.g., model 190 in Figure 1). The dataset generator 272 uses historical processing parameter data 244 (e.g., historical processing parameter data 134 in Figure 1) and historical performance data 254 (e.g., historical performance data 154 in Figure 1) to create the dataset. The system 200 in Figure 2 shows the dataset generator 272, data input 210, and target output 220 (e.g., target data).

[0071]

[0076] In some embodiments, the dataset generator 272 generates a dataset (e.g., training set, validation set, test set) containing one or more data inputs 210 (e.g., training input, validation input, test input). In some embodiments, the dataset generator 272 does not generate target outputs (e.g., for unsupervised learning). In some embodiments, the dataset generator generates one or more target outputs 220 (e.g., for supervised learning) corresponding to the data inputs 210. The dataset may also include mapping data that maps the data inputs 210 to the target outputs 220. The data inputs 210 are also referred to as “features,” “attributes,” or “information.” In some embodiments, the dataset generator 272 provides the dataset to a training engine 182, a validation engine 184, or a test engine 186, where the dataset is used to train, validate, or test a machine learning model 190 (e.g., related to obtaining predicted performance data related to processing parameters for processing a material, and, based on the predicted performance data, ensuring that the material is processed according to processing parameters, methods 500A-C, etc.).

[0072]

[0077] In some embodiments, the dataset generator 272 generates a data input 210 and a target output 220. In some embodiments, the data input 210 includes one or more sets of historical processing parameter data 244 (for example, to obtain predicted performance data associated with processing parameters for processing a material, and to ensure that the material is processed according to processing parameters, methods 500A to 500C, etc., based on the predicted performance data). In some embodiments, the historical performance data 254 includes one or more of the following: performance data from one or more sensors and / or measuring instruments, combinations of performance data from one or more sensors and / or measuring instruments, patterns from performance data from one or more sensors and / or measuring instruments, and / or homogeneous ones.

[0073]

[0078] In some embodiments, the dataset generator 272 generates a first data input corresponding to a first set 244A of historical processing parameter data for training, validating, or testing a first machine learning model, and the dataset generator 272 generates a second data input corresponding to a second set 244B of historical processing parameter data for training, validating, or testing a second machine learning model (for example, one that obtains predicted performance data associated with processing parameters for processing a material, and based on the predicted performance data, is associated with ensuring that the material is processed according to processing parameters, methods 500A-500C, etc.).

[0074]

[0079] In some embodiments, the dataset generator 272 discretizes (e.g., segments) one or more of the data inputs 210 or target outputs 220 (e.g., for use in a classification algorithm for a regression problem). Discretization of the data inputs 210 or target outputs 220 (e.g., segmentation via a sliding window) converts continuous values ​​of a variable into discrete values. In some embodiments, the discrete values ​​of the data inputs 210 represent discrete historical processing parameter data 134 for obtaining the target outputs 220 (e.g., discrete historical performance data 154 associated with obtaining predicted performance data associated with processing parameters for processing a material, and based on the predicted performance data, processing parameters, methods 500A-500C, etc.).

[0075]

[0080] The data inputs 210 and target outputs 220 for training, validating, or testing a machine learning model may include information about a specific facility (e.g., a specific substrate manufacturing facility). In some examples, the historical processing parameter data 244 and historical performance data 254 relate to the same manufacturing facility (e.g., obtaining predicted performance data associated with processing parameters for processing a material, and using the predicted performance data to ensure the material is processed according to processing parameters, methods 500A-500C, etc.).

[0076]

[0081] In some embodiments, the information used to train a machine learning model is from a specific type of manufacturing equipment 124 (e.g., a laser material processing system 125) of a manufacturing facility having specific characteristics, and the trained machine learning model (e.g., taking predicted performance data associated with processing parameters for processing a material and, based on the predicted performance data, ensuring that the material is processed according to the processing parameters, methods 500A-500C, etc.) can determine the results of a particular group of manufacturing equipment 124 based on inputs of current parameters (e.g., current processing parameter data 136) associated with one or more components that share the characteristics of that particular group. In some embodiments, the information used to train a machine learning model is about components from two or more manufacturing facilities, and the trained machine learning model can determine the results of a component based on inputs from one of the manufacturing facilities.

[0077]

[0082] In some embodiments, a dataset is generated, and a machine learning model 190 is trained, validated, or tested using that dataset (for example, to obtain predicted performance data associated with processing parameters for processing a material, and based on the predicted performance data, to ensure that the material is processed according to the processing parameters, methods 500A-500C, etc.). After that, the machine learning model 190 is further trained, validated, or tested (for example, the current performance data 156 in Figure 1), or tuned (for example, to adjust the weights associated with the input data of the machine learning model 190, such as the connection weights of a neural network).

[0078]

[0083] A machine learning model processes inputs and generates outputs (for example, obtaining predicted performance data associated with processing parameters for processing a material, and, based on the predicted performance data, ensuring the material is processed according to processing parameters, methods 500A-500C, etc.). An artificial neural network includes an input layer consisting of values ​​at data points. The next layer is called a hidden layer, and each node in the hidden layer receives one or more input values. Each node contains parameters (e.g., weights) to apply to the input values. Thus, each node essentially inputs the input values ​​into a multivariate function (e.g., a nonlinear mathematical transformation) to generate output values. The next layer can be another hidden layer or an output layer. In either case, the nodes in the next layer receive output values ​​from the nodes of the previous layer, each node applies weights to these values, and then generates its own output values. This can be done in each layer. The final layer is the output layer, where there is one node for each class, prediction, and / or output that the machine learning model may generate.

[0079]

[0084] Therefore, the output may include one or more predictions or estimations (for example, obtained with respect to processing parameters for processing a material, and based on the predicted performance data, the material is processed according to the processing parameters, methods 500A-500C, etc.). For example, the output predictions or estimations may include one or more predictions such as the uniformity and quality of laser drilling, the uniformity and quality of laser etching, the uniformity and quality of laser annealing, the uniformity and quality of laser ablation, the uniformity and quality of laser doping, the uniformity and quality of laser scribing, the uniformity and quality of laser welding, the uniformity and quality of laser deposition, and the uniformity and quality of laser trimming and repair.

[0080]

[0085] For example, predictive data for laser drilling operations (e.g., predictive data 160, predicted performance data 162, etc.) may indicate hole diameter, hole depth, hole quality (e.g., drilled holes must accurately and consistently meet expected dimensions and have minimal thermal damage or recast layers). Predictive data for laser etching operations may indicate feature accuracy (etched features must have accurate dimensions, shape, and edge quality), etching depth control (the etching process must achieve the desired depth accurately and uniformly across the entire substrate), and surface finish (the etched surface must be smooth, free from roughness, and have the desired texture or pattern). Predictive data for laser annealing operations may indicate dopant activation (the annealing process must effectively activate dopants and achieve the desired electrical properties in the treated area), and crystal structure recovery (the annealing process must eliminate amorphous regions or crystal defects). Predictive data for laser ablation operations may indicate material removal accuracy (the laser ablation process must accurately remove the material) and surface quality (the ablated surface must have minimal heat-affected zone or recast layer). Performance data for laser doping operations may indicate dopant incorporation (the laser doping process must successfully introduce dopant atoms to the desired area and achieve the desired doping concentration). Predictive data for laser scribing operations may indicate line accuracy (the laser scribing process must create accurate and clear scribe lines with the desired width, depth, and edge quality) and scribe width control (the scribing process must precisely control the width of the scribe line to avoid electrical or structural problems).Predictive data for laser welding operations may indicate bond strength (laser welding must provide a strong and reliable bond between joined components and meet specified mechanical and electrical requirements), heat-affected zone control (the laser welding process must minimize the size and influence of the heat-affected zone to prevent damage to surrounding materials or components). Predictive data for laser deposition operations may indicate layer thickness control (laser deposition must achieve the desired thickness and uniformity of the deposited layer), adhesion, and integrity (the deposited layer must adhere well to the substrate and exhibit good integrity without cracks, delamination, or voids). Predictive data for laser trimming and repair operations may indicate component correction accuracy (the laser trimming and repair process must accurately correct circuits or structures as needed, achieving the desired correction without causing unintended damage or changes).

[0081]

[0086] In some embodiments, the processing logic determines an error (e.g., classification error) based on the difference between the output of the machine learning model (e.g., prediction or inference) and the target label associated with the input training data. The processing logic adjusts the weights of one or more nodes in the machine learning model based on the error. An error term or delta may be determined for each node in the artificial neural network. Based on this error, the artificial neural network adjusts its one or more parameters (weights for one or more inputs of the node) for its one or more nodes. Parameters may be updated in a backpropagation manner, with the top layer nodes being updated first, followed by the nodes of the next layer, and so on. The artificial neural network contains multiple layers of "neurons," each layer receiving values ​​as input from the neurons of the previous layer. The parameters of each neuron include weights associated with the values ​​received from each neuron of the previous layer.

[0082]

[0087] Therefore, adjusting the parameters may involve adjusting the weights assigned to each input for one or more neurons in one or more layers within the artificial neural network.

[0083]

[0088] After one or more rounds of training, the processing logic can determine whether the stopping criteria have been met. The stopping criteria can be a target level of accuracy, a target number of images processed from the training dataset, a target change in parameters relative to one or more previous data points, a combination thereof, and / or other criteria. In one embodiment, the stopping criteria are met when at least a minimum number of data points have been processed and at least a threshold accuracy has been achieved. The threshold accuracy can be, for example, 70%, 80%, or 90% accuracy. In one embodiment, the stopping criteria are met when the accuracy of the machine learning model no longer improves. If the stopping criteria are not met, further training is performed. If the stopping criteria are met, training may be complete. Once training of the machine learning model is complete, the remaining portion of the training dataset may be used to test the model.

[0084]

[0089] Figure 3 is a block diagram showing a system 300 for generating predictive data 360 (e.g., predictive data 160 in Figure 1) according to a particular embodiment. The system 300 is used to determine the predictive data 360 via a trained machine learning model (e.g., model 190 in Figure 1), which is associated with obtaining predicted performance data associated with processing parameters for processing a material and ensuring that the material is processed according to the processing parameters based on the predicted performance data (e.g., performing a laser material processing operation if the predicted performance data indicates that the use of a particular processing parameter is acceptable).

[0085]

[0090] In block 310, system 300 (e.g., prediction system 110 in Figure 1) performs data partitioning (e.g., via dataset generator 172 on server machine 170 in Figure 1) of historical data (e.g., historical processing parameter data 344 and / or historical performance data 354 for model 190 in Figure 1) to generate a training set 302, a validation set 304, and a test set 306 (e.g., related to obtaining predicted performance data associated with processing parameters for processing a material, and based on the predicted performance data, ensuring that the material is processed according to processing parameters, methods 500A-C, etc.). In some examples, the training set is 60% of the historical data, the validation set is 20% of the historical data, and the test set is 20% of the historical data. System 300 generates multiple sets of features for each of the training set, validation set, and test set. In some examples, if past data includes features derived from 20 sensors (e.g., sensor 126 in Figure 1, sensors for manufacturing equipment and / or measuring instruments) and 100 products (e.g., each product corresponding to characteristic data from the 20 sensors), then the first set of features would be sensors 1-10, the second set of features would be sensors 11-20, the training set would be products 1-60, the validation set would be products 61-80, and the test set would be products 81-100. In this example, the first set of features in the training set would be the parameters from sensors 1-10 for products 1-60.

[0086]

[0091] In block 312, system 300 performs model training using training set 302 (via training engine 182 in Figure 1, which is associated with, for example, obtaining predicted performance data related to processing parameters for processing a material, and, based on the predicted performance data, ensuring that the material is processed according to processing parameters, methods 500A-500C, etc.). In some embodiments, system 300 trains multiple models using multiple sets of features from training set 302 (e.g., a first set of features from training set 302, a second set of features from training set 302, etc.). For example, system 300 trains machine learning models to produce a first trained machine learning model using a first set of features in the training set (e.g., performance data from sensors 1-10 for products 1-60) and a second trained machine learning model using a second set of features in the training set (e.g., performance data from sensors 11-20 for products 1-60). In some embodiments, a first trained machine learning model and a second trained machine learning model are combined to produce a third trained machine learning model (for example, in some embodiments, which is a better predictor than the first or second trained machine learning model on its own). In some embodiments, the sets of features used when comparing the models are redundant (for example, the first set of features is performance data from sensors 1-15, and the second set of features is performance data from sensors 5-20). In some embodiments, hundreds of models are generated, including models with various feature swaps and combinations of models.

[0087]

[0092] In block 314, system 300 performs model validation using validation set 304 (for example, via validation engine 184 in Figure 1). System 300 validates each of the trained models (for example, associated with obtaining predicted performance data associated with processing parameters for processing a material, and ensuring that the material is processed according to processing parameters, methods 500A-500C, etc., based on the predicted performance data) using the corresponding set of features in validation set 304. For example, system 300 validates a first trained machine learning model using a first set of features in the validation set (e.g., parameters from sensors 1-10 for products 61-80), and validates a second trained machine learning model using a second set of features in the validation set (e.g., parameters from sensors 11-20 for products 61-80). In some embodiments, system 300 validates hundreds of models generated in block 312 (e.g., models with various feature swaps, combinations of models, etc.). In block 314, system 300 determines the accuracy of each of the one or more trained models (e.g., through model validation) and whether one or more of the trained models have an accuracy that meets a threshold accuracy. In response to the determination that none of the trained models have an accuracy that meets a threshold accuracy, the flow returns to block 312, where system 300 performs model training using a different set of features from the training set. In response to the determination that one or more of the trained models have an accuracy that meets a threshold accuracy, the flow continues to block 316. System 300 discards any trained machine learning models that have an accuracy below a threshold accuracy (e.g., based on the validation set).

[0088]

[0093] In block 316, system 300 performs model selection (e.g., via selection engine 185 in Figure 1) to determine which of the one or more trained models that satisfy the threshold accuracy has the highest accuracy (e.g., selected model 308 based on the validation in block 314). In response to the determination that two or more trained models that satisfy the threshold accuracy have the same accuracy, the flow returns to block 312, where system 300 performs model training using a more refined training set corresponding to a more refined set of features to determine the trained model with the highest accuracy.

[0089]

[0094] In block 318, system 300 performs a model test using test set 306 (e.g., via test engine 186 in Figure 1) to test the selected model 308. System 300 tests a first trained machine learning model using a first set of features in the test set (e.g., performance data from sensors 1-10 for products 81-100) and determines that the first trained machine learning model meets a threshold accuracy (e.g., based on the first set of features in test set 306). In response that the accuracy of the selected model 308 does not meet the threshold accuracy (e.g., the selected model 308 is overfitted to training set 302 and / or validation set 304 and is not applicable to other datasets such as test set 306), the flow proceeds to block 312, where system 300 performs model training (e.g., retraining) using different training sets corresponding to different sets of features (e.g., performance data from different sensors). In response to a determination based on the test set 306 that the selected model 308 has an accuracy that meets a threshold accuracy, the flow proceeds to block 320. In at least block 312, the model learns patterns in historical data for making predictions, and in block 318, the system 300 applies the model to the remaining data (e.g., the test set 306) to test the predictions (e.g., obtain predicted performance data related to processing parameters for processing a material, and based on the predicted performance data, ensure that the material is processed according to the processing parameters, methods 500A-C, etc.).

[0090]

[0095] In block 320, the system 300 uses a trained model (e.g., selected model 308) to receive current processing parameter data 346 (e.g., current processing parameter data 136 in Figure 1), obtain predicted performance data associated with processing parameters for processing a material, and, based on the predicted performance data, determines (e.g., extracts) predicted data 360 (e.g., predicted data 160 in Figure 1) from the trained model, which is associated with ensuring that the material is processed according to the processing parameters (e.g., causing the execution of the processing based on the predicted performance data indicating that certain processing parameters are acceptable). In some embodiments, the current processing parameter data 346 corresponds to the same type of features in the historical processing parameter data 344. In some embodiments, the current processing parameter data 346 corresponds to the same type of features as a subset of the type of features in the historical processing parameter data 344 used to train the selected model 308 (e.g., obtained predicted performance data associated with processing parameters for processing a material, and based on the predicted performance data, associated with ensuring that the material is processed according to processing parameters, methods 500A-C, etc.).

[0091]

[0096] In some embodiments, current data is received. In some embodiments, the current data includes current performance data 356 (e.g., current performance data 156 in Figure 1) and / or current processing parameter data 346 (e.g., obtained associated with predicted performance data related to processing parameters for processing a material, and based on the predicted performance data, associated with processing parameters, methods 500A-500C, etc.). In some embodiments, at least a portion of the current data is received from a measuring instrument (e.g., measuring instrument 128 in Figure 1) or via user input. In some embodiments, the model is retrained based on the current data. In some embodiments, a new model is trained based on the current performance data 356 and the current processing parameter data 346.

[0092]

[0097] In some embodiments, one or more of blocks 310-320 are performed in various orders and / or together with other operations not presented and described herein. In some embodiments, one or more of blocks 310-320 are not performed. For example, in some embodiments, one or more of the data partitioning in block 310, model validation in block 314, model selection in block 316, and / or model testing in block 318 are not performed.

[0093]

[0098] Figure 4 shows examples of predicted profiles of materials processed by laser material processing systems according to several embodiments.

[0094]

[0099] In some embodiments, the predicted profiles 402A to 402L may be predictions of cross-sectional images of the processed material (e.g., a substrate during and / or after a laser material processing operation). In some embodiments, the predicted profiles 402A to 402L may be predicted optical micrographs. In some embodiments, the predicted profiles may be extrapolations generated from a training set. In some embodiments, the training set may include images similar to the predictions (e.g., cross-sectional images of the processed material). In some embodiments, the validation set may include images similar to the predictions and / or training set (e.g., cross-sectional images of the processed material).

[0095]

[0100] In some embodiments, the predicted profiles 402A-402L may be a map of the process space 400. For example, in some embodiments, the predicted profiles 420A-420L may be arranged in rows and columns. Rows 411-414 correspond to a first processing parameter (e.g., pressure), and columns 421-425 correspond to a second processing parameter (e.g., pulse time). In some embodiments, the intersection of rows and columns represents the predicted profile of a substrate and / or material processed using the processing parameters defined by the respective rows and columns. For example, predicted profile 402G represents the predicted profile of a substrate perforated by a laser material processing system under a pressure of 1 bar and a laser pulse time of 249 femtoseconds.

[0096]

[0101] In some embodiments, the processing parameters used to generate the predicted profile 402G (e.g., a pressure of 1 bar and a laser pulse time of 249 femtoseconds) may be determined to be preferred processing parameters due to the uniformity and quality of the drilled hole. In some embodiments, for example, the processing parameters used to generate the predicted profile 402B (e.g., a pressure of 2.4 bar and a laser pulse time of 6 picoseconds) may not be preferred processing parameters due to a lack of uniformity and quality of the drilled hole. For example, region 460 of the predicted profile 402B shows tapering. In some embodiments, tapering is an undesirable quality of hole resulting from a laser drilling operation. Furthermore, the processing parameters used to generate the predicted profile 402L (e.g., a pressure of 0.5 bar and a laser pulse time of 8 picoseconds) may not be preferred processing parameters due to a lack of uniformity and quality of the drilled hole. For example, region 470 of the predicted profile 402L shows tapering. In some embodiments, tapering is an undesirable quality of the hole resulting from the laser drilling operation. Furthermore, region 472 of the predicted profile 402L exhibits necking. In some embodiments, necking is an undesirable quality of the hole resulting from the laser drilling operation.

[0097]

[0102] Figures 5A and 5B are flowcharts of methods 500A and 500B associated with obtaining predicted performance data associated with processing parameters for processing a material, and ensuring that the material is processed according to the processing parameters based on the predicted performance data, according to a particular embodiment. In some embodiments, methods 500A and 500B are executed by processing logic including hardware (e.g., circuits, dedicated logic, programmable logic, microcode, processing devices, etc.), software (e.g., instructions executed on processing devices, general-purpose computer systems, or dedicated machines), firmware, microcode, or a combination thereof. In one embodiment, method 500A may be executed by a computer system such as the one shown in Figure 1. In other embodiments or similar embodiments, one or more operations of method 500A may be executed by one or more other machines not shown in the figures. In some embodiments, methods 500A and 500B are executed at least partially by a prediction system 110. In some embodiments, method 500A is executed by a client device 120 (e.g., a processing execution component 122) and / or the prediction system 110 (e.g., a prediction component). In some embodiments, method 500B is executed by a server machine 180 (e.g., a training engine 182). In some embodiments, a non-temporary storage medium, when executed by a processing device (e.g., a prediction system 110, a server machine 180, a prediction server 112, a client device 120, etc.), stores instructions that cause the processing device to execute one or more of methods 500A to 500B.

[0098]

[0103] For the sake of simplicity, methods 500A and B are illustrated and described as a series of operations. However, the operations relating to this disclosure may be performed in various orders and / or simultaneously with other operations not presented and described herein. Furthermore, in some embodiments, not all illustrated operations are performed in order to carry out methods 500A and B in accordance with the disclosed subject matter. In addition, those skilled in the art will understand and recognize that methods 500A and B may alternatively be represented as a series of interrelated states via a state diagram or events.

[0099]

[0104] Figure 5A is a flowchart of a method associated with an aspect of the present disclosure, which involves obtaining predicted performance data associated with processing parameters for processing a material, and ensuring that the material is processed according to the processing parameters based on the predicted performance data. In some embodiments, Figure 5A includes using a trained machine learning model (e.g., Model 190 in Figure 1) to provide one or more outputs showing predicted performance data associated with processing parameters for processing a material, and ensuring that the material is processed according to the processing parameters based on the predicted performance data.

[0100]

[0105] Referring to Figure 5A, in some embodiments, in block 502, the processing logic implementing method 400A determines first data indicating processing parameters for processing a material in a laser processing system. In some embodiments, the laser material processing system includes a digital twin.

[0101]

[0106] In some embodiments, processing parameters include at least one of the following: material type, material strength, material thermal conductivity, material reflectivity, laser type, laser wavelength, pulse energy, pulse duration, repetition rate, hatch distance, beam diameter, beam shape, beam alignment, beam incidence, gas pressure, focal length, polarization, marking speed, milling strategy, scanning speed, scanning pattern, beam collimation, focal position, and / or similar. In some embodiments, processing parameters for processing a material within a laser processing system are determined based on user input.

[0102]

[0107] In block 504, the processing logic provides the first data as input to the trained machine learning model. In some embodiments, the digital twin includes the trained machine learning model.

[0103]

[0108] In block 506, the processing logic retrieves one or more outputs from a trained machine learning model, where one or more outputs represent predicted performance data associated with processing parameters for processing the material.

[0104]

[0109] In some embodiments, the predicted performance data includes a predicted profile of the processed material.

[0105]

[0110] In some embodiments, the processing logic may further determine preferred processing parameters, which are determined based on the predicted performance data meeting a performance criterion. In some embodiments, the performance criterion is a uniformity criterion.

[0106]

[0111] In block 508, the processing logic ensures that the material is processed according to processing parameters based on predicted performance data.

[0107]

[0112] In some embodiments, the processing logic can further train a machine learning model using training input data that includes historical processing parameter data (e.g., data from past processing operations) and training target output data that includes historical performance data associated with the historical processing parameters (e.g., substrate quality using the historical processing parameters, material uniformity after processing using specific processing parameters, etc.).

[0108]

[0113] In some embodiments, the processing logic may further determine second data indicating updated processing parameters for processing a material within a laser processing system, the second data being based on performance data of the material processed according to the processing parameters. In some embodiments, the processing logic may further provide the second data as input to a trained machine learning model. In some embodiments, the processing logic may further obtain one or more second outputs of the trained machine learning model, the one or more second outputs indicating updated predicted performance data associated with the updated processing parameters for processing the material. In some embodiments, the processing logic may further ensure that the material is processed according to the updated processing parameters based on the updated predicted performance data.

[0109]

[0114] In some embodiments, Method 500A may include providing one or more outputs showing predicted performance data associated with processing parameters for processing a material, and training a machine learning model to ensure that the material is processed according to the processing parameters based on the predicted performance data (e.g., generating a trained machine learning model using a data input containing historical processing parameter data and / or a target output containing historical performance data). In some embodiments, Method 500A may include using a trained machine learning model to predict the outcome of a processing operation (e.g., a laser material processing operation) based on processing parameters (e.g., processing parameter values, processing setting values, etc.) (e.g., using a data input containing processing parameter data and / or a target output containing predicted performance data).

[0110]

[0115] The predicted data can be associated with predicted performance data based on the predicted data (e.g., performance data of the substrate, or performance data of the material after undergoing a processing operation (e.g., a laser material processing operation)). Depending on whether the predicted performance data meets a threshold (e.g., the processed material / substrate meets the performance criteria after being processed using specific parameters), the processing logic can be made to execute a processing operation according to the processing parameters (e.g., a laser material processing operation using a pressure of 1 bar and a laser pulse time of 249 femtoseconds). In some embodiments, depending on whether the predicted performance data does not meet a threshold (e.g., the processed material / substrate does not meet the performance criteria after being processed using specific parameters), the processing logic can be made to prevent the execution of a processing operation according to the processing parameters (e.g., a laser material processing operation using a pressure of 0.5 bar and a laser pulse time of 8 picoseconds), and the prediction can be made based on updated processing parameters (e.g., updated parameter values, updated process recipes, etc.). Depending on whether the predicted performance data meets the threshold, the processing logic can be made to execute a processing operation according to the updated processing parameters (for example, a laser material processing operation using a pressure of 1 bar and a laser pulse time of 249 femtoseconds).

[0111]

[0116] Figure 5B is a flowchart of a method relating to an aspect of the present disclosure for training a machine learning model (e.g., Model 190 in Figure 1) to obtain predicted performance data related to processing parameters for processing a material, and to determine, based on the predicted performance data, predicted data (e.g., predicted data 160 in Figure 1) associated with processing the material according to the processing parameters.

[0112]

[0117] Referring to Figure 5B, in block 510 of method 500B, the processing logic identifies past processing parameter data (e.g., past processing parameter data 134 in Figure 1). Past processing parameter data may include data from past laser material processing operations, past laser material processing recipes, etc.

[0113]

[0118] In some embodiments, in block 512, the processing logic identifies historical performance data (e.g., historical performance data 154 in Figure 1) of substrates, processed materials, and / or similar items. The historical performance data may include data from past substrates and / or materials processed in a laser material processing system (e.g., laser material processing system 125 in Figure 1) according to processing parameters. The performance data, including historical performance data, may include measurement data or user inputs indicating the performance of the substrate in meeting specific parameters or achieving a specific level of performance (e.g., uniformity measurement, quality measurement, ability to pass probe tests measuring voltage, etc.). The performance data, including historical performance data, may include measurement data or user inputs indicating the performance of the processed material in meeting specific parameters or achieving a specific level of performance (e.g., meeting a uniformity threshold, meeting a conductivity threshold, etc.). At least a portion of the historical processing parameter data and historical performance data may be associated with new substrate processing equipment components (e.g., used for benchmarking). At least a portion of the historical processing parameter data and historical performance data may be associated with manufactured substrates and / or processed materials. At least a portion of past processing parameter data and past performance data can be associated with the laser-treated material.

[0114]

[0119] In block 514, the processing logic trains a machine learning model using a data input containing historical processing parameter data 134 and / or a target output containing historical performance data 154, thereby generating a trained machine learning model.

[0115]

[0120] In some embodiments, past processing parameter data are past processing parameters used to process past substrates, and / or past performance data correspond to past processing parameters used to process past substrates. In some embodiments, past processing parameter data includes past processing parameters used to process past substrates, and / or past performance data corresponds to past substrates (e.g., processed using past processing parameters). In some embodiments, past performance data includes past measurements of past substrates (e.g., processed using past processing parameters). Past performance data may be associated with substrate quality, such as substrate measurement data, substrate uniformity, quality of operation results, and substrate defects. Past performance data may be associated with the quality of materials and / or substrates processed by the laser material processing system, substrate / material measurement data, etc.

[0116]

[0121] In block 514, to generate a trained machine learning model configured to predict the results of a laser material processing operation by a laser material processing system and to ensure that the material is processed according to processing parameter data (e.g., processing parameter data in block 502 of Figure 5A), the machine learning model may be trained using a target output that includes historical processing parameter data and / or historical performance data. In some embodiments, the machine learning model may be trained using a target output that includes historical processing parameter data and / or historical performance data to provide one or more outputs that show predicted performance data associated with processing parameters for processing a material, and to generate a trained machine learning model configured to ensure that the material is processed according to the processing parameters based on the predicted performance data.

[0117]

[0122] In some embodiments, the trained machine learning model may be configured to predict performance data 152 (e.g., performance data of a substrate / material processed using processing parameters, preferred processing parameters, etc.) based on processing parameter data 132 (e.g., processing parameter data of blocks 502 and 504 in Figure 5A). Depending on whether the predicted performance data meets a threshold (e.g., the processed material / substrate meets the performance criteria after being processed using specific parameters), the processing logic may be made to perform a processing operation according to the processing parameters (e.g., a laser material processing operation using a pressure of 1 bar and a laser pulse time of 249 femtoseconds).

[0118]

[0123] In some embodiments, if the predicted performance data does not meet a threshold (e.g., the processed material / substrate does not meet the performance criteria after being processed using certain parameters), the processing logic may prevent the processing operation according to the processing parameters (e.g., a laser material processing operation using a pressure of 0.5 bar and a laser pulse time of 8 picoseconds) from being performed, and the prediction may be made based on updated processing parameters (e.g., updated parameter values, updated process recipes, etc.). If the predicted performance data meets the threshold, the processing logic may allow the processing operation according to the updated processing parameters (e.g., a laser material processing operation using a pressure of 1 bar and a laser pulse time of 249 femtoseconds) to be performed.

[0119]

[0124] In some embodiments, the historical processing parameter data in block 510 is for past substrates and / or past materials, and the historical performance data in block 512 corresponds to past substrates and / or past materials. In some embodiments, the historical processing parameter data in block 510 is associated with historical processing parameters used during processing of past substrates / materials, and the historical performance data in block 512 corresponds to past substrates / materials (e.g., processed using historical processing parameters).

[0120]

[0125] Figure 6 is a block diagram showing a computer system 600 according to a particular embodiment. In some embodiments, the computer system 600 is one or more of the following: a client device 120, a prediction system 110, a server machine 170, a server machine 180, and / or a prediction server 112.

[0121]

[0126] In some embodiments, the computer system 600 is connected to other computer systems (for example, via a network such as a local area network (LAN), intranet, extranet, or the Internet). In some embodiments, the computer system 600 operates as a server or client computer in a client-server environment, or as a peer computer in a peer-to-peer or distributed network environment. In some embodiments, the computer system 600 is provided by a personal computer (PC), tablet PC, set-top box (STB), personal digital assistant (PDA), mobile phone, web appliance, server, network router, switch or bridge, or any device capable of executing a set of instructions (sequential or otherwise) that specify actions to be performed by the device. Furthermore, the term “computer” includes any collection of computers that individually or collectively execute a set of instructions (or sets of instructions) to perform any one or more of the methods described herein.

[0122]

[0127] In a further embodiment, the computer system 600 includes a processing device 602, a volatile memory 604 (e.g., random access memory (RAM)), a non-volatile memory 606 (e.g., read-only memory (ROM) or electrically erasable programmable ROM (EEPROM)), and a data storage device 618, all of which communicate with each other via a bus 608.

[0123]

[0128] In some embodiments, the processing device 602 is provided by one or more processors, such as a general-purpose processor (e.g., a composite instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a microprocessor implementing other types of instruction sets, or a microprocessor implementing a combination of multiple types of instruction sets) or a dedicated processor (e.g., an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), or a network processor).

[0124]

[0129] In some embodiments, the computer system 600 further includes a network interface device 622 (e.g., connected to a network 674). In some embodiments, the computer system 600 also includes a video display unit 610 (e.g., a liquid crystal display (LCD)), an alphanumeric input device 612 (e.g., a keyboard), a cursor control device 614 (e.g., a mouse), and a signal generation device 620.

[0125]

[0130] In some embodiments, the data storage device 618 includes a non-temporary computer-readable storage medium 624 that stores instructions 626 for encoding any one or more of the methods or functions described herein, including instructions for encoding the components of Figure 1 (e.g., the processing execution component 122, the prediction component 114, etc.) and instructions for performing the methods described herein (e.g., one or more of methods 500A to C).

[0126]

[0131] In some embodiments, instruction 626 is also entirely or partially present in volatile memory 604 and / or processing device 602 while being executed by computer system 600, and therefore, in some embodiments, volatile memory 604 and processing device 602 also constitute a machine-readable storage medium.

[0127]

[0132] Although the computer-readable storage medium 624 is shown as a single medium in the illustrated examples, the term “computer-readable storage medium” includes a single medium or multiple mediums that store one or more sets of executable instructions (e.g., a centralized or distributed database, and / or associated caches and servers). The term “computer-readable storage medium” also includes any tangible medium capable of storing or encoding a set of instructions for execution by a computer, which causes the computer to execute any one or more of the methods described herein. The term “computer-readable storage medium” includes, but is not limited to, solid memory, optical media, and magnetic media.

[0128]

[0133] The methods, components, and features described in this document may be implemented by individual hardware components or integrated into the functionality of other hardware components such as application-specific integrated circuits (ASICs), FPGAs, DSPs, or similar devices. Furthermore, the methods, components, and features may be implemented by functional circuits within firmware modules or hardware devices. Moreover, the methods, components, and features may be implemented in any combination of hardware devices and computer program components, or in computer programs.

[0129]

[0134] Unless otherwise specified, terms such as “determine,” “provide,” “obtain,” “cause,” “train,” “receive,” “identify,” “execute,” “cause,” “access,” “add,” and “use” refer to actions and processes performed or implemented by a computer system that manipulate data represented as physical quantities (electronic quantities) in the computer system’s registers or memory, and convert it into other data similarly represented as physical quantities in the computer system’s memory, registers, or other information storage, transmission, and display devices. Furthermore, terms such as “first,” “second,” “third,” and “fourth” as used herein are used as labels to distinguish different elements and do not imply any numerical order.

[0130]

[0135] The examples described herein also relate to apparatus for carrying out the methods described herein. Such apparatus may include a general-purpose computer system that is either specifically constructed for carrying out the methods described herein or selectively programmed by a computer program stored in the computer system. Such a computer program may be stored in a computer-readable tangible storage medium.

[0131]

[0136] The methods and examples described herein are not inherently related to any particular computer or other device. Various general-purpose systems can be used in accordance with the teachings provided herein, or it may be convenient to construct more specialized devices to perform each of the methods and / or their individual functions, routines, subroutines, or operations described herein. Examples of the construction of a wide variety of such systems are described above.

[0132]

[0137] The above description is illustrative and not limiting. While this disclosure has been described with reference to specific exemplary embodiments and implementations, it should be recognized that this disclosure is not limited to those described embodiments and implementations. The scope of this disclosure should be determined with reference to the following claims, together with the entire scope of equivalents to which the claims are entitled.

Claims

1. To determine first data indicating processing parameters for processing a material within a laser processing system including a digital twin, Providing the first data as input to a trained machine learning model, wherein the digital twin provides the first data, including the trained machine learning model. Obtaining one or more outputs of the trained machine learning model, wherein the one or more outputs represent predicted performance data associated with the processing parameters for processing the material, Based on the predicted performance data, the material is processed according to the processing parameters. A method that includes this.

2. The method according to claim 1, wherein the processing parameters include at least one of the following: material type, material strength, material thermal conductivity, material reflectivity, laser type, laser wavelength, pulse energy, pulse duration, repetition rate, hatch distance, beam diameter, beam shape, beam alignment, beam incidence, gas pressure, focal length, polarization, marking speed, milling strategy, scanning speed, scanning pattern, beam collimation, and focal position.

3. The method according to claim 1, wherein the predicted performance data includes a predicted profile of the processed material.

4. The method according to claim 1, further comprising determining preferred processing parameters, the preferred processing parameters being determined on the basis that the predicted performance data meets performance criteria.

5. The method according to claim 4, wherein the performance criterion is a uniformity criterion.

6. The method according to claim 1, wherein the processing parameters for processing the material within the laser processing system are determined based on user input.

7. The method according to claim 1, further comprising training the machine learning model using training input data including historical processing parameter data and training target output data including historical performance data associated with the historical processing parameters.

8. Determining second data indicating updated processing parameters for processing the material within the laser processing system, wherein the second data is based on performance data of the material processed according to the processing parameters; Providing the second data as input to the trained machine learning model, Obtaining one or more second outputs of the trained machine learning model, wherein the one or more second outputs represent updated predicted performance data associated with updated processing parameters for processing the material, Based on the updated predicted performance data, the material is processed according to the updated processing parameters. The method according to claim 1, further comprising:

9. Memory and A processing device connected to the aforementioned memory, A system comprising, the processing device, To determine first data indicating processing parameters for processing a material within a laser processing system including a digital twin, Providing the first data as input to a trained machine learning model, wherein the digital twin provides the first data, including the trained machine learning model. Obtaining one or more outputs of the trained machine learning model, wherein the one or more outputs represent predicted performance data associated with the processing parameters for processing the material, Based on the predicted performance data, the material is processed according to the processing parameters. A system designed to perform a specific task.

10. The system according to claim 9, wherein the processing parameters include at least one of the following: material type, material strength, material thermal conductivity, material reflectivity, laser type, laser wavelength, pulse energy, pulse duration, repetition rate, hatch distance, beam diameter, beam shape, beam alignment, beam incidence, gas pressure, focal length, polarization, marking speed, milling strategy, scanning speed, scanning pattern, beam collimation, and focal position.

11. The processing device further, The system according to claim 9, for determining preferred processing parameters, wherein the preferred processing parameters are determined on the basis that the predicted performance data meets performance criteria.

12. The system according to claim 11, wherein the performance criterion is a uniformity criterion.

13. The processing device further, The system according to claim 9, for training a machine learning model using training input data including past processing parameter data and training target output data including past performance data associated with past processing parameters.

14. The processing device further, Determining second data indicating updated processing parameters for processing the material within the laser processing system, wherein the second data is based on performance data of the material processed according to the processing parameters; Providing the second data as input to the trained machine learning model, Obtaining one or more second outputs of the trained machine learning model, wherein the one or more second outputs represent updated predicted performance data associated with updated processing parameters for processing the material, Based on the updated predicted performance data, the material is processed according to the updated processing parameters. The system according to claim 9, which is for performing the following.

15. A non-temporary machine-readable storage medium containing instructions, wherein, when the instructions are executed by a processing device, the processing device receives, To determine first data indicating processing parameters for processing a material within a laser processing system including a digital twin, Providing the first data as input to a trained machine learning model, wherein the digital twin provides the first data, including the trained machine learning model. Obtaining one or more outputs of the trained machine learning model, wherein the one or more outputs represent predicted performance data associated with the processing parameters for processing the material, Based on the predicted performance data, the material is processed according to the processing parameters. A non-temporary, machine-readable storage medium that enables the following process.

16. The non-temporary machine-readable storage medium according to claim 15, wherein the processing parameters include at least one of the following: material type, material strength, material thermal conductivity, material reflectivity, laser type, laser wavelength, pulse energy, pulse duration, repetition rate, hatch distance, beam diameter, beam shape, beam alignment, beam incidence, gas pressure, focal length, polarization, marking speed, milling strategy, scanning speed, scanning pattern, beam collimation, and focal position.

17. The aforementioned instruction further instructs the processing device, A non-temporary machine-readable storage medium according to claim 15, wherein the system is configured to determine preferred processing parameters, the preferred processing parameters being determined on the basis that the predicted performance data meets performance criteria.

18. The non-temporary machine-readable storage medium according to claim 17, wherein the performance criterion is a uniformity criterion.

19. The aforementioned instruction further instructs the processing device, A non-temporary machine-readable storage medium according to claim 15, which allows the machine learning model to be trained using training input data including past processing parameter data and training target output data including past performance data associated with past processing parameters.

20. The aforementioned instruction further instructs the processing device, Determining second data indicating updated processing parameters for processing the material within the laser processing system, wherein the second data is based on performance data of the material processed according to the processing parameters; Providing the second data as input to the trained machine learning model, Obtaining one or more second outputs of the trained machine learning model, wherein the one or more second outputs represent updated predicted performance data associated with updated processing parameters for processing the material, Based on the updated predicted performance data, the material is processed according to the updated processing parameters. A non-temporary machine-readable storage medium according to claim 15, which causes the following to occur.

Images