Process monitoring and regulation using predictive models

Abstract

A method for monitoring the performance of a manufacturing process is described. The method includes: receiving one or more input signals that convey information related to the geometry of a substrate produced by the manufacturing process; and determining changes in the manufacturing process using a prediction model based on the one or more input signals. A method for predicting substrate geometry associated with a manufacturing process is also described. The method includes: receiving input information, the input information including substrate geometry information and manufacturing process information; and using a machine learning prediction model, based on the input information, predicting an output substrate geometry. The method also includes adjusting the predicted output substrate geometry. The adjustment includes: comparing the output substrate geometry with corresponding physical substrate measurements and / or predictions from different non-machine learning prediction models; generating a loss function based on the comparison; and optimizing the loss function.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to U.S. Application No. 62 / 909,668, filed on October 2, 2019, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The description herein generally relates to systems and methods for manufacturing process monitoring and regulation using predictive models. Background Art

[0004] Lithographic projection apparatus may be used, for example, in the manufacture of integrated circuits (ICs). In such cases, a patterning device (e.g., a mask) may provide a pattern corresponding to a single layer of the IC (a "design layout"), and this pattern may be transferred to a target portion of the substrate by methods such as irradiating a target portion (e.g., comprising one or more dies) on (e.g., a silicon wafer) coated with a layer of radiation-sensitive material ("resist") through the pattern on the patterning device. Typically, a single substrate comprises a plurality of adjacent target portions to which the pattern is transferred successively, one target portion at a time, by the lithographic projection apparatus. In one type of lithographic projection apparatus, in one operation, the entire pattern on the patterning device is transferred to one target portion. Such an apparatus is generally referred to as a stepper. In an alternative apparatus, generally referred to as a step-and-scan apparatus, the projection beam is scanned over the patterning device in a given reference direction (the "scanning" direction) while the substrate is synchronously moved in a direction parallel or antiparallel to the reference direction. Different portions of the pattern on the patterning device are gradually transferred to one target portion. Since typically the lithographic projection apparatus will have a reduction ratio M (eg 4), the rate F at which the substrate is moved will be 1 / M times the rate at which the projection beam scans the patterning device.More information on lithographic apparatus as described herein can be gleaned, for example, from US 6,046,792, which is incorporated herein by reference.

[0005] Before the pattern is transferred from the pattern forming device to the substrate, the substrate may undergo various processes, such as primer coating, resist coating, and soft baking. After exposure, the substrate may undergo other processes ("post-exposure processes"), such as post-exposure baking (PEB), development, hard baking, and measurement / inspection of the transferred pattern. This series of processes is used as the basis for manufacturing a single layer of a device (e.g., an IC). The substrate may then undergo various processes, such as etching, ion implantation (doping), metallization, oxidation, chemical mechanical polishing, etc., all of which are intended to ultimately complete a single layer of the device. If the device requires multiple layers, the entire process or a variation thereof is repeated for each layer. Ultimately, the device will be set in each target portion on the substrate. These devices are then separated from each other by techniques such as slicing or cutting, whereby the individual devices can be mounted on a carrier, connected to pins, etc.

[0006] Manufacturing devices (such as semiconductor devices) typically involves using multiple manufacturing processes to process a substrate (e.g., a semiconductor wafer) to form various features and multiple layers of the device. These layers and features are typically manufactured and processed using, for example, deposition, lithography, etching, chemical mechanical polishing, and ion implantation. Multiple devices can be manufactured on multiple dies on a substrate and then separated into separate devices. This device manufacturing process can be considered a patterning process. The patterning process involves a patterning step, such as optical and / or nanoimprint lithography using a patterning device in a lithography apparatus to transfer the pattern on the patterning device to the substrate, and typically but optionally involves one or more related pattern processing steps, such as resist development by a developing apparatus, substrate baking using a baking tool, etching using a pattern using an etching apparatus, etc. In addition, one or more measurement processes are typically involved in the patterning process.

[0007] Photolithography is a step in the manufacture of devices, such as ICs, in which patterns formed on a substrate define the functional elements of the device, such as microprocessors, memory chips, etc. Similar photolithography techniques are also used to form flat panel displays, microelectromechanical systems (MEMS), and other devices.

[0008] As semiconductor manufacturing processes continue to advance, the size of functional elements has been continuously reduced over the decades while the number of functional elements (such as transistors) per device has been steadily increasing, following a trend commonly referred to as "Moore's Law." In the current state of the art, multiple layers of a device are fabricated using a lithography projection apparatus that projects a design layout onto a substrate using illumination from a deep ultraviolet illumination source, thereby forming a single functional element having a size well below 100 nm (i.e., less than half the wavelength of the radiation from the illumination source (e.g., a 193 nm illumination source)).

[0009] This process in which features with dimensions smaller than the classical resolution limit of the lithographic projection apparatus are printed is generally referred to as low-k1 lithography, and is based on the resolution formula CD = k1 × λ / NA, where λ is the wavelength of the radiation employed (currently 248 nm or 193 nm in most cases), NA is the numerical aperture of the projection optics in the lithographic projection apparatus, CD is the "critical dimension" (usually the smallest feature size printed), and k1 is an empirical resolution factor. In general, the smaller k1 is, the more difficult it becomes to reproduce a pattern on a substrate that resembles the shape and dimensions planned by the designer in order to achieve specific electrical functionality and performance. To overcome these difficulties, complex fine-tuning steps are applied to the lithographic projection apparatus, the design layout, or the patterning device. These steps include, for example, but are not limited to: optimization of NA and optical coherence settings, customized illumination schemes, use of phase-shifting patterning devices, optical proximity correction (OPC, sometimes also called "optical and process correction") in the design layout, or other methods generally defined as "resolution enhancement techniques" (RET). The term "projection optics" as used herein should be broadly interpreted to cover various types of optical systems, including, for example, refractive optics, reflective optics, apertures, and reflective-refractive optics. The term "projection optics" may also include components that operate according to any of these design types for guiding, shaping or controlling a projection radiation beam, either collectively or individually. The term "projection optics" may include any optical component in a lithographic projection apparatus, regardless of where the optical component is located on the optical path of the lithographic projection apparatus. Projection optics may include optical components for shaping, adjusting and / or projecting radiation from a source before the radiation passes through a pattern forming device, or optical components for shaping, adjusting and / or projecting the radiation after the radiation passes through a pattern forming device. Projection optics typically do not include a source and a pattern forming device. Summary of the invention

[0010] According to an embodiment, a method for monitoring the performance of a manufacturing process is provided. The method includes: receiving one or more input signals conveying information about the geometry of a substrate produced by the manufacturing process; and determining changes in the manufacturing process based on the one or more input signals using a predictive model.

[0011] In an embodiment, the substrate is associated with a semiconductor device and the fabrication process comprises a semiconductor device fabrication process.

[0012] In an embodiment, the method further includes determining adjustments for semiconductor device manufacturing equipment based on the changes in the manufacturing process.

[0013] In an embodiment, the receiving and the determining are performed in real time or near real time during the semiconductor device manufacturing process.

[0014] In an embodiment, the one or more input signals comprise overlapping signals.In an embodiment, the one or more input signals comprise alignment signals.

[0015] In an embodiment, the changes in the semiconductor device manufacturing process include one or more of the following: changes in processing parameters of the manufacturing process, changes in material properties of one or more materials used in the manufacturing process, or changes in optical properties of the one or more materials.

[0016] In an embodiment, the prediction model comprises a machine learning model. In an embodiment, the prediction model comprises a neural network (as just one example) and / or other machine learning techniques.

[0017] In an embodiment, the substrate includes a layer stack associated with a semiconductor device.

[0018] In an embodiment, the method further comprises: training the prediction model based on known disturbances in the manufacturing process.

[0019] According to another embodiment, a method for predicting substrate geometry associated with a manufacturing process is provided, the method comprising: receiving input information, the input information comprising substrate geometry information and manufacturing process information; and using a machine learning prediction model to predict output substrate geometry based on the input information.

[0020] In an embodiment, the substrate includes a layer stack associated with a semiconductor device.

[0021] In an embodiment, the method further comprises adjusting the predicted output substrate geometry. The adjusting comprises: comparing the output substrate geometry with corresponding physical substrate measurements and / or predictions from different non-machine learning prediction models; generating a loss function based on the comparison; and optimizing the loss function.

[0022] In an embodiment, the adjustment comprises stack adjustment. Stack adjustment input comprises: (1) a signal associated with a measurement result from a corresponding physical stack; (2) the geometry information, wherein the geometry information comprises a nominal geometry of the physical stack; and (3) the manufacturing process information. Stack adjustment output comprises the output substrate geometry. The output substrate geometry is adjusted so that an analog signal determined based on the output substrate geometry corresponds to a signal associated with a measurement result from the physical stack and / or the nominal geometry of the physical stack.

[0023] In an embodiment, the method further comprises predicting an overlay signal based on the output substrate geometry using the machine learning prediction model.

[0024] In an embodiment, the method further comprises predicting an alignment signal based on the output substrate geometry using the machine learning prediction model.

[0025] In an embodiment, the machine learning prediction model comprises a neural network.

[0026] In an embodiment, the geometry information includes one or more dimensions of a target or mark design for one or more layers of the semiconductor device.

[0027] In an embodiment, the manufacturing process information includes one or more parameters of one or more manufacturing processes performed on one or more layers of the semiconductor device.

[0028] In an embodiment, the method further comprises: training the machine learning prediction model using training information describing the geometry, pattern, and manufacturing process parameters of the training substrate and corresponding physical substrate measurement results and / or prediction results from different non-machine learning prediction models.

[0029] According to another embodiment, a method for detecting changes in one or more semiconductor device manufacturing processes and determining adjustments to the one or more semiconductor device manufacturing process steps is provided. The method includes receiving input information, the input information including geometric shape information and manufacturing process information of the semiconductor device. The method includes using a machine learning prediction model to predict output semiconductor device geometry changes based on the input information. The method includes detecting changes in the semiconductor manufacturing process based on the prediction results of the semiconductor device geometry changes from the machine learning prediction model. The method includes determining one or more semiconductor device manufacturing process parameter changes based on the detected changes in the semiconductor device manufacturing process. The method includes determining adjustments to the one or more semiconductor device manufacturing process steps based on the one or more determined semiconductor device manufacturing process parameter changes.

[0030] In an embodiment, the input information is for a stack associated with a semiconductor device.

[0031] In an embodiment, detecting the change in the semiconductor manufacturing process includes: predicting an overlap signal based on the output semiconductor device geometry change using the machine learning prediction model. In an embodiment, detecting the change in the semiconductor manufacturing process includes: predicting an alignment signal based on the output semiconductor device geometry change using the machine learning prediction model.

[0032] In an embodiment, the method further comprises adjusting the predicted output semiconductor device geometry variation. The adjusting comprises comparing the output semiconductor device geometry variation with corresponding physical measurements and / or predictions from different non-machine learning physical models, generating a loss function based on the comparison, and optimizing the loss function.

[0033] In an embodiment, the geometry information includes one or more dimensions of a target design for one or more layers of a semiconductor device.

[0034] In an embodiment, the manufacturing process information includes one or more etching process parameters, one or more deposition process parameters, and / or one or more chemical mechanical polishing process parameters.

[0035] In an embodiment, the adjustment to the semiconductor device manufacturing process includes one or more of the following: a change in an etching process parameter from a first etching process parameter value to a second etching process parameter value; a change in a deposition process parameter from a first deposition process parameter value to a second deposition process parameter value; or a change in a chemical mechanical polishing process parameter from a first chemical mechanical polishing process parameter to a second chemical mechanical polishing process parameter value.

[0036] According to another embodiment, a computer program product is provided, including a non-transitory computer-readable medium having instructions recorded thereon, the instructions implementing any one of the methods described above when executed by a computer. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which are incorporated into and constitute a part of this specification, illustrate one or more embodiments and, together with the specification, explain these embodiments. Embodiments of the present invention will now be described by way of example only with reference to the accompanying schematic drawings, in which corresponding reference numerals indicate corresponding components, and in which:

[0038] Figure 1 A lithographic apparatus according to an embodiment is schematically depicted.

[0039] Figure 2 Embodiments of a lithography cell or lithography cluster according to embodiments are schematically depicted.

[0040] Figure 3A is a flow chart illustrating various stages of a design for controlling a process flow according to an embodiment.

[0041] Figure 3B is a block diagram illustrating various stages for visualization according to an embodiment.

[0042] Figure 3C is a flow chart illustrating how a design for controlling a process determines a measurement target design that is robust against process disturbances according to an embodiment.

[0043] Figure 4 The diagram illustrates the operation of a method for monitoring the performance of a manufacturing process according to an embodiment.

[0044] Figure 5 The diagram illustrates the use of geometry and process information (eg, including purposeful changes to said information) as input to predict an output signal indicative of a predicted geometry (as opposed to the present method), according to an embodiment.

[0045] Figure 6 The diagram shows a schematic diagram of a method for use with the present system and method according to an embodiment (relative to Figure 5 ) The reverse process of the process shown in .

[0046] Fig. 7A is a first illustration of receiving input signals and using a predictive model to predict and / or otherwise determine variations in a manufacturing process according to an embodiment.

[0047] Figure 7B is a second illustration of receiving input signals and using a predictive model to predict and / or otherwise determine variations in a manufacturing process according to an embodiment.

[0048] Figure 8 The diagram illustrates the operation of a method for overlay adjustment using a machine learning prediction model, according to an embodiment.

[0049] Fig. 9 An example of an overlay adjustment flow according to an embodiment is shown.

[0050] Fig.10 is a block diagram of an example computer system according to an embodiment.

[0051] Fig.11 is similar to Figure 1 Schematic diagram of a lithography projection apparatus.

[0052] Fig.12 According to the embodiment Fig.11 A more detailed view of the device in FIG.

[0053] Fig.13 According to the embodiment Fig.11 and Fig.12 A more detailed view of the source collector module SO of the device. DETAILED DESCRIPTION

[0054] Description herein generally relates to systems and methods for monitoring and using predictive models to adjust manufacturing processes. Manufacturing processes may include semiconductor manufacturing processes as described below. However, these examples are not intended to be limiting. Operations identical or similar to those described herein may be applied to other manufacturing processes. Maintaining a stable semiconductor manufacturing process is important. Undesirable changes in the manufacturing process (such as lithography, deposition, etching, chemical mechanical polishing (CMP) and / or other semiconductor manufacturing processes) often have a negative impact on the final process yield. Detecting changes in real time or near real time (e.g., within a few seconds or minutes of the change) allows the manufacturing process to be adjusted in a timely manner to prevent the production of defective devices and increase process yield. Thus, a simple, fast and non-destructive solution is desired that can monitor process changes and provide information about which processes have changed and how much during typical manufacturing.

[0055] Existing systems have limitations that reduce their usefulness. For example, an ellipsometer, or ellipsometer, can measure film thickness in a non-destructive manner, but only one layer at a time. Therefore, the process of reconstructing the entire stack can take a very long time, sometimes up to several days or even several weeks. Cross-sectional inspection using a scanning electron microscope (SEM) can provide accurate process variation information, but this type of inspection is destructive and time-consuming. An atomic force microscope (AFM) can provide localized topographic information with high accuracy, but the AFM can only provide information about the top layer of the stack, and the AFM is very slow. Existing modeling systems can indicate that the process has changed, but cannot provide detailed information about which process or process parameter has changed or how much it has changed. Sometimes, these modeling systems take several hours to several days to produce output, which prevents these modeling systems from being used for real-time or near real-time manufacturing process monitoring.

[0056] Advantageously, the present system and method provide for real-time or near real-time monitoring of the performance of a (e.g., semiconductor) manufacturing process. In the present system and method, one or more input signals conveying information about the geometry of a substrate produced during the manufacturing process are received, and a predictive model (e.g., a machine learning model) is used to determine changes in the manufacturing process based on the one or more input signals. For example, the input signal may include overlap, alignment, and / or other signals. The determined changes may provide quantitative process feedback that facilitates various manufacturing process adjustments.

[0057] The present system and method are configured to provide real-time or near real-time response. The prediction process performed using the model is almost instantaneous, which makes the present system and method suitable for real-time or near real-time process monitoring. The prediction can also provide detailed information about how much the process has changed. The present system and method are universal. They can be used to monitor many different types of process changes. For example, they can be used to monitor thickness changes, changes in material optical properties (e.g., changes in n and / or k (i.e., the real and imaginary parts of the complex refractive index of the material)), changes in side wall angle (SWA), changes in etching tilt angles, changes in chemical mechanical polishing, and the like. The present system and method are also configured to provide accurate indications of how much changes have occurred in any of these types of process changes, and / or other types of process changes. Importantly, the present system and method can be used to simultaneously monitor these and other types of changes in, for example, multiple layers of a stack.

[0058] The present system and method are non-destructive and easy to apply. The implementation cost of the present system and method is low, does not (negatively) affect the process yield, and is very accurate. For example, the present system and method use overlapping, alignment and / or other signals including measurement data to predict process changes. It is convenient and inexpensive to obtain overlapping, alignment, or other signals that have been generated as part of a typical manufacturing process. Obtaining and using the information in these signals to make predictions is not destructive to the manufactured device, and does not require additional measurements (e.g., causing the process yield to be negatively affected).

[0059] Turning to the tuning aspects of the present systems and methods, stack tuning is a process that utilizes corresponding predictions from an electronic model (e.g., a D4C model) to enhance consistency between overlay, alignment, and / or other measurement data. Typical stack tuning is performed in an iterative manner through a series of operations to produce an optimized stack. The iterations are guided by optimization algorithms (such as gradient descent and trust regions) to produce an optimized stack whose optical key performance indicators (KPIs), for example, match or nearly match KPIs associated with the measurement data.

[0060] The iterative nature of typical overlay tuning, and the fact that predictions from (non-machine learning) electronic models often take hours or even days, causes typical overlay tuning to run very slowly. For example, it may take days or weeks to complete a typical overlay tuning process. The overlay tuning process speed will not be increased simply by adding more processing resources, because the (e.g., geometry) output for subsequent iterations depends on the output from the previous iteration. Thus, in order to reduce the overlay tuning time, it is necessary to shorten the run time of individual iterations.

[0061] Advantageously, the present systems and methods replace typical time-consuming predictions from (non-machine learning) electronic and / or optical models with faster predictions from improved machine learning models. The present systems and methods utilize trained machine learning prediction models that are configured to produce prediction results almost immediately / instantly.

[0062] Although specific reference may be made herein to the manufacture of integrated circuits (ICs), it should be understood that the description herein has many other possible applications. For example, the description herein may be used to manufacture integrated optical systems, guidance and detection patterns for magnetic domain memories, liquid crystal display panels, thin film magnetic heads, etc. Those skilled in the art should understand that in the context of such alternative applications, any use of the terms "reticle", "wafer" or "die" herein should be considered to be interchangeable with the more general terms "mask", "substrate" and "target portion", respectively.

[0063] As an introduction, Figure 1 An embodiment of a lithographic apparatus LA which may be included in and / or associated with the present system and / or method is schematically depicted. The apparatus comprises:

[0064] - an illumination system (illuminator) IL configured to condition a radiation beam B (e.g. UV radiation, DUV radiation or EUV radiation);

[0065] - a support structure (eg mask table) MT configured to support a patterning device (eg mask) MA and connected to a first positioner PM configured to accurately position the patterning device according to certain parameters;

[0066] - a substrate table (e.g. wafer stage) WT (e.g. WTa, WTb or both) configured to hold a substrate (e.g. a resist coated wafer) W and connected to a second positioning device PW configured to accurately position the substrate according to certain parameters; and

[0067] - a projection system (e.g., a refractive projection lens system) PS configured to project the pattern imparted to the radiation beam B by the patterning device MA onto a target portion C (e.g., comprising one or more dies and often referred to as a field) of the substrate W, the projection system being supported on a reference frame (RF).

[0068] As depicted, the device is of the transmissive type (eg, using a transmissive mask). Alternatively, the device may be of the reflective type (eg, using a programmable mirror array of the type mentioned above, or using a reflective mask).

[0069] The illuminator IL receives a radiation beam from a radiation source SO. For example, when the source is an excimer laser, the source and the lithographic apparatus may be separate entities. In such a case, the source is not considered to form part of the lithographic apparatus, and the radiation beam is transferred from the source SO to the illuminator IL by means of a beam delivery system BD comprising, for example, suitable directional mirrors and / or a beam expander. In other cases, for example, when the source is a mercury lamp, the source may be an integral part of the apparatus. The source SO and the illuminator IL together with the beam delivery system BD (where necessary) may be referred to as a radiation system.

[0070] The illuminator IL may vary the intensity distribution of the beam. The illuminator may be arranged to limit the radial extent of the radiation beam so that the intensity distribution within an annular region in a pupil plane of the illuminator IL is non-zero. Additionally or alternatively, the illuminator IL may be operable to limit the distribution of the beam in the pupil plane so that the intensity distribution in a plurality of equally spaced segments in the pupil plane is non-zero. The intensity distribution of the radiation beam in the pupil plane of the illuminator IL may be referred to as an illumination pattern.

[0071] The illuminator IL may include an adjuster AD configured to adjust the (angular / spatial) intensity distribution of the beam. Typically, at least the outer radial extent and / or the inner radial extent (typically referred to as σ-outer and σ-inner, respectively) of the intensity distribution in a pupil plane of the illuminator may be adjusted. The illuminator IL may be operable to change the angular distribution of the beam. For example, the illuminator may be operable to change the number and angular extent of the segments in the pupil plane where the intensity distribution is non-zero. By adjusting the intensity distribution of the beam in the pupil plane of the illuminator, different illumination modes may be achieved. For example, by limiting the radial extent and the angular extent of the intensity distribution in the pupil plane of the illuminator IL, the intensity distribution may have a multipolar distribution, such as a dipole, quadrupole or hexapole distribution. The illumination mode may be obtained, for example, by inserting an optical device providing the desired illumination mode into the illuminator IL or by using a spatial light modulator.

[0072] The illuminator IL may be operable to change the polarization of the beam and may be operable to adjust the polarization using an adjuster AD. The polarization state of the radiation beam across the pupil plane of the illuminator IL may be referred to as a polarization mode. Using different polarization modes may allow a greater contrast to be achieved in the image formed on the substrate W. The radiation beam may be unpolarized. Alternatively, the illuminator may be arranged to polarize the radiation beam linearly. The polarization direction of the radiation beam may vary across the pupil plane of the illuminator IL. The polarization direction of the radiation may be different in different zones in the pupil plane of the illuminator IL. The polarization state of the radiation may be selected depending on the illumination mode. For a multipolar illumination mode, the polarization of each pole of the radiation beam may generally be perpendicular to the position vector of the pole in the pupil plane of the illuminator IL. For example, for a dipole illumination mode, the radiation may be linearly polarized in a direction substantially perpendicular to a line of two opposing segments bisecting a dipole. The radiation beam may be polarized in one of two different orthogonal directions, which may be referred to as an X polarization state and a Y polarization state. For a quadrupole illumination mode, the radiation in the segments of each pole may be linearly polarized in a direction substantially perpendicular to a line bisecting the segments. This polarization mode may be referred to as XY polarization. Similarly, for a hexapole illumination mode, the radiation in the segments of each pole may be linearly polarized in a direction substantially perpendicular to a line bisecting the segments. This polarization mode may be referred to as TE polarization.

[0073] In addition, the illuminator IL typically includes various other components, such as an integrator IN and a condenser CO. The illumination system may include various types of optical components for directing, shaping or controlling the radiation, such as refractive, reflective, magnetic, electromagnetic, electrostatic or other types of optical components, or any combination thereof. Thus, the illuminator provides a conditioned radiation beam B having a desired uniformity and intensity distribution in cross-section.

[0074] The support structure MT supports the pattern forming device in a manner that depends on the orientation of the pattern forming device, the design of the lithographic apparatus, and other conditions such as whether the pattern forming device is maintained in a vacuum environment. The support structure can use mechanical, vacuum, electrostatic or other clamping techniques to hold the pattern forming device. The support structure can be, for example, a frame or a table, which can be fixed or movable as required. The support structure can ensure that the pattern forming device is in a desired position, for example relative to a projection system. Any use of the term "reticle" or "mask" in the present invention can be regarded as synonymous with the more general term "pattern forming device".

[0075] The term "patterning device" as used in the present invention should be broadly interpreted as referring to any device that can be used to impart a pattern in a target portion of a substrate. In an embodiment, the patterning device is any device that can be used to impart a pattern to a radiation beam in its cross-section so as to produce a pattern in the target portion of the substrate. It should be noted that, for example, if the pattern imparted to the radiation beam includes phase-shifting features or so-called assist features, the pattern may not exactly correspond to the desired pattern in the target portion of the substrate. Typically, the pattern imparted to the radiation beam will correspond to a specific functional layer in a device (such as an integrated circuit) produced in the target portion.

[0076] The patterning device may be transmissive or reflective. Examples of patterning devices include masks, programmable mirror arrays, and programmable LCD panels. Masks are well known in lithography and include mask types such as binary, alternating phase shift, and attenuated phase shift, as well as various hybrid mask types. An example of a programmable mirror array uses a matrix arrangement of small mirrors, each of which can be individually tilted so as to reflect an incident radiation beam in different directions. The tilted mirrors impart a pattern in the radiation beam reflected by the mirror matrix.

[0077] The term "projection system" as used herein should be interpreted broadly to cover any type of projection system, including refractive, reflective, catadioptric, magnetic, electromagnetic and electrostatic optical systems, or any combination thereof, as appropriate to the exposure radiation used or to other factors such as the use of an immersion liquid or the use of a vacuum. Any use of the term "projection lens" in this disclosure may be considered synonymous with the more general term "projection system".

[0078] The projection system PS has an optical transfer function that may be non-uniform and may affect the pattern imaged onto the substrate W. For unpolarized radiation, such effects can be fairly well described by two scalar maps that describe the transmission (apodization) and relative phase (aberration) of the radiation exiting the projection system PS as a function of the position in the pupil plane of the radiation. These scalar maps, which can be referred to as transmission maps and relative phase maps, can be expressed as linear combinations of a full set of basis functions. A particularly suitable set is the Zernike polynomials, which form a set of orthogonal polynomials defined on the unit circle. The determination of each scalar map may involve determining coefficients in such an expansion. Since the Zernike polynomials are orthogonal on the unit circle, the Zernike coefficients may be determined by calculating the inner product of the measured scalar map with each Zernike polynomial in turn and dividing this inner product by the square of the norm of the Zernike polynomial.

[0079] The transmission map and the relative phase map are field and system dependent. That is, in general, each projection system PS will have a different Zernike expansion for each field point (i.e., for each spatial location in the image plane of the projection system). The relative phase of the projection system PS in its pupil plane can be determined by projecting radiation, for example, from a point-like source in the object plane of the projection system PS (i.e., the plane of the patterning device MA) through the projection system PS and measuring the wavefront (i.e., the trajectory of points with the same phase) using a shearing interferometer. The shearing interferometer is a common path interferometer and therefore advantageously, no secondary reference beam is required to measure the wavefront. The shearing interferometer may comprise a diffraction grating (e.g., a two-dimensional grating) in the image plane of the projection system (i.e., the substrate table WTa or WTb), and a detector arranged to detect an interference pattern in a plane conjugate to the pupil plane of the projection system PS. The interference pattern is related to the derivative of the phase of the radiation and the coordinates in the pupil plane in the shear direction. The detector may comprise an array of sensing elements such as, for example, a charge coupled device (CCD).

[0080] The projection system PS of the lithographic apparatus may not produce visible fringes, and therefore a phase stepping technique (such as moving a diffraction grating) may be used to enhance the accuracy of the wavefront determination. Stepping may be performed in the plane of the diffraction grating and in a direction perpendicular to the scanning direction of the measurement. The stepping range may be one grating period, and at least three (uniformly distributed) phase steps may be used. Thus, for example, three scanning measurements may be performed in the y direction, each scanning measurement being performed for a different position in the x direction. Such stepping of the diffraction grating effectively converts phase changes into intensity changes, allowing the phase information to be determined. The grating may be stepped in a direction perpendicular to the diffraction grating (z direction) to calibrate the detector.

[0081] The diffraction grating may be scanned sequentially in two perpendicular directions, which may coincide with the axes (x and y) of the coordinate system of the projection system PS or may be at an angle (such as 45 degrees) to these axes. The scanning may be performed over an integer number of grating periods (e.g., one grating period). The scanning averages the phase changes in one direction, allowing reconstruction of the phase changes in the other direction. This allows the wavefront to be determined as a function of the two directions.

[0082] The transmission (apodization) of the projection system PS in its pupil plane may be determined by projecting radiation, e.g. from a point-like source in the object plane of the projection system PS (i.e. the plane of the patterning device MA) through the projection system PS and measuring the intensity of the radiation in a plane conjugate to the pupil plane of the projection system PS using a detector. The same detector may be used as the one used to measure the wavefront to determine the aberrations.

[0083] The projection system PS may include a plurality of optical (e.g., lens) elements, and may further include an adjustment mechanism configured to adjust one or more of the optical elements in order to correct aberrations (phase variations in the pupil plane across the entire field). To achieve such adjustments, the adjustment mechanism may be operable to manipulate one or more optical (e.g., lens) elements within the projection system PS in one or more different ways. The projection system may have a coordinate system in which the optical axis of the projection system extends in the z direction. The adjustment mechanism may be operable to perform any combination of the following: displacing one or more optical elements; tilting one or more optical elements; and / or deforming one or more optical elements. The displacement of the optical element may be performed in any direction (x, y, z, or a combination thereof). The tilting of the optical element is typically performed outside the plane perpendicular to the optical axis by rotating around an axis in the x and / or y direction, but rotation around the z axis may be used for non-rotationally symmetric aspheric optical elements. The deformation of the optical element may include low-frequency shapes (e.g., astigmatism) and / or high-frequency shapes (e.g., free-form aspheric surfaces). Deformation of the optical element may be performed, for example, by using one or more actuators to apply forces to one or more sides of the optical element and / or by using one or more heating elements to heat one or more selected regions of the optical element. Typically, it is not possible to adjust the projection system PS to correct for apodization (variations in transmission across a pupil plane). A transmission map of the projection system PS may be used when designing a patterning device (e.g., mask) MA for the lithographic apparatus LA. Using computational lithography techniques, the patterning device MA may be designed to at least partially correct for apodization.

[0084] The lithographic apparatus may be of a type having two (dual stage) or more tables (e.g. two or more substrate tables WTa, WTb, two or more patterning device tables, substrate table WTa and table WTb below the projection system without dedicated substrates for use, for example, to facilitate measurement and / or cleaning, etc.). In these "multi-stage" machines, the additional tables may be used in parallel, or preparatory steps may be carried out on one or more tables while one or more other tables are being used for exposure. For example, alignment measurements may be made using an alignment sensor AS and / or level (height, inclination, etc.) measurements may be made using a level sensor (or leveling sensor) LS.

[0085] The lithographic apparatus may also be of a type in which at least a portion of the substrate may be covered by a liquid having a relatively high refractive index, such as water, so as to fill the space between the projection system and the substrate. Immersion liquid may also be applied to other spaces in the lithographic apparatus, such as the space between the patterning device and the projection system. Immersion techniques are well known in the art and are used to increase the numerical aperture of the projection system. The term "immersion" as used in the present invention does not mean that structures such as the substrate must be immersed in the liquid, but only means that the liquid is located between the projection system and the substrate during exposure.

[0086] In operation of the lithographic apparatus, a radiation beam is conditioned and provided by an illumination system IL. The radiation beam B is incident on a patterning device (e.g. a mask) MA held on a support structure (e.g. a mask table) MT and is patterned by the patterning device. Having traversed the patterning device MA, the radiation beam B passes through a projection system PS which focuses the beam onto a target portion C of a substrate W. With the aid of a second positioning device PW and a position sensor IF (e.g. an interferometer, a linear encoder, a 2-D encoder or a capacitive sensor), the substrate table WT can be accurately moved, for example in order to position different target portions C in the path of the radiation beam B. Similarly, the first positioning device PM and a further position sensor (in Figure 1 The support structure MT may be used to accurately position the pattern forming device MA relative to the path of the radiation beam B, for example after mechanical retrieval from a mask library or during scanning. Typically, movement of the support structure MT may be achieved with the aid of a long-stroke module (coarse positioning) and a short-stroke module (fine positioning) forming part of the first positioning device PM. Similarly, movement of the substrate table WT may be achieved using a long-stroke module and a short-stroke module forming part of the second positioning device PW. In the case of a stepper (as opposed to a scanner), the support structure MT may be connected only to the short-stroke actuator, or may be fixed. The pattern forming device MA and the substrate W may be aligned using pattern forming device alignment marks M1, M2 and substrate alignment marks P1, P2. Although the substrate alignment marks as illustrated occupy dedicated target portions, the marks may be located in the spaces between target portions (these marks are referred to as scribe alignment marks). Similarly, in the case where more than one die is provided on the pattern forming device MA, the pattern forming device alignment marks may be located between the dies.

[0087] The depicted device may be used in at least one of the following modes:

[0088] 1. In step mode, a pattern imparted to the radiation beam is projected onto a target portion C at one time (i.e. a single static exposure) while the support structure MT and the substrate table WT are kept substantially stationary. Subsequently, the substrate table WT is shifted in the X and / or Y direction so that a different target portion C can be exposed. In step mode, the maximum size of the exposure field limits the size of the target portion C imaged in a single static exposure.

[0089] 2. In scan mode, the support structure MT and substrate table WT are scanned synchronously while a pattern imparted to the radiation beam is projected onto a target portion C (i.e. a single dynamic exposure). The speed and direction of the substrate table WT relative to the support structure MT may be determined by the (de-)magnification and image reversal characteristics of the projection system PS. In scan mode, the maximum size of the exposure field limits the width of the target portion in a single dynamic exposure (in the non-scanning direction), while the length of the scanning movement determines the height of the target portion (in the scanning direction).

[0090] 3. In another mode, the support structure MT is held substantially stationary, thereby holding the programmable patterning device, and the substrate table WT is moved or scanned while a pattern imparted to the radiation beam is projected onto a target portion C. In this mode, a pulsed radiation source is typically used and the programmable patterning device is updated as required after each movement of the substrate table WT or between successive radiation pulses during a scan. This mode of operation can be readily applied to maskless lithography utilizing a programmable patterning device, such as a programmable mirror array of the type mentioned above.

[0091] Combinations and / or variations on the above-described modes of use or entirely different modes of use may also be used.

[0092] The substrates referred to in the present invention may be processed before or after exposure in, for example, a coating and developing system or track (a tool that typically applies a resist layer to a substrate and develops the exposed resist), or a measurement or inspection tool. Where applicable, the disclosure of the present invention may be applied to these and other substrate processing tools. In addition, the substrate may be processed more than once, for example to produce a multi-layer IC, so that the term substrate used in the present invention may also refer to a substrate that already includes multiple processed layers.

[0093] The terms "radiation" and "beam" as used in the present invention encompass all types of electromagnetic radiation, including ultraviolet (UV) or deep ultraviolet (DUV) radiation (e.g., having a wavelength of 365, 248, 193, 157 or 126 nm) and extreme ultraviolet (EUV) radiation (e.g., having a wavelength in the range of 5 to 20 nm), as well as particle beams, such as ion beams or electron beams.

[0094] Various patterns on or provided by a pattern forming device may have different process windows, i.e., the space of process variables within which patterns within specifications will be produced. Examples of pattern specifications related to potential systematic defects include checking for necking, line pullback, line thinning, CD, edge placement, overlap, resist top loss, resist undercut and / or bridging. The process windows of all patterns on a pattern forming device or a region thereof may be obtained by merging the process windows of each individual pattern (e.g., overlapping the process windows). The boundaries of the process windows of all patterns contain the boundaries of the process windows of some of the individual patterns. In other words, these individual patterns limit the process windows of all patterns. These patterns may be referred to as "hot spots" or "process window limiting patterns (PWLP)", which are used interchangeably in the present invention. It is possible and economical to focus on hot spots when controlling a portion of a patterning process. When hot spots are defect-free, it is most likely that all patterns are defect-free.

[0095] like Figure 2 As shown in , the lithography equipment LA can form part of a lithography unit LC (sometimes also referred to as a lithography cell or lithography cluster), which also includes equipment for performing pre-exposure and post-exposure processes on a substrate. Conventionally, these equipment include one or more spin coaters SC for depositing one or more resist layers, one or more developers for developing the exposed resist, one or more chill plates CH and / or one or more baking plates BK. The substrate conveyor, or robot RO, picks up one or more substrates from the input port I / O1 and the output port I / O2, moves these substrates between different process equipment and transfers these substrates to the feed station LB of the lithography equipment. These equipment, which are often collectively referred to as coating and developing systems or tracks, are controlled by a coating and developing system control unit or a track control unit TCU, which is itself controlled by a management control system SCS, which also controls the lithography equipment via a lithography control unit LACU. Thus, different equipment can be operated to maximize throughput and processing efficiency.

[0096] In order to correctly and consistently expose a substrate exposed by the lithographic apparatus and / or to monitor a portion of a patterning process (e.g., a device manufacturing process) that includes at least one pattern transfer step (e.g., an optical lithography step), it is desirable to inspect a substrate or other object to measure or determine one or more properties, such as alignment, overlay (the overlay may be, for example, an overlay between multiple structures in multiple overlapping layers, or an overlay between multiple structures in the same layer that have been separately provided to the layer by, for example, a double patterning process), line thickness, critical dimension (CD), focus offset, material properties, etc. Therefore, a manufacturing facility in which a lithography cell LC is located typically also includes a metrology system that measures the substrate W ( Figure 1 ) or other objects in the lithographic cell. The metrology system may be part of the lithographic cell LC, for example it may be part of the lithographic apparatus LA (such as an alignment sensor AS ( Figure 1 )).

[0097] For example, the one or more measured parameters may include: alignment, overlay between successive layers formed in or on a patterned substrate, critical dimensions (CD) of features formed in or on a patterned substrate (e.g., critical line width), focus or focus error of an optical lithography step, dose or dose error of an optical lithography step, optical aberration of an optical lithography step, etc. Such measurements may be performed on a target on the product substrate itself and / or on a dedicated metrology target disposed on the substrate. The measurements may be performed after resist development but before etching, after etching, after deposition, and / or at other times.

[0098] There are various techniques for measuring the structure formed in the patterning process, including the use of scanning electron microscopes, image-based measurement tools and / or various special tools. As discussed above, a fast and non-invasive form of a special measurement tool is a measurement tool in which a radiation beam is directed to a target on the surface of the substrate and the properties of the scattered (diffracted / reflected) beam are measured. By evaluating one or more properties of the radiation scattered by the substrate, one or more properties of the substrate can be determined. This can be referred to as diffraction-based measurement. One such application of this diffraction-based measurement is in the measurement of feature asymmetry within a target. This can be used as a measure of overlap, for example, but other applications are also known. For example, asymmetry can be measured by comparing opposite parts of the diffraction spectrum (for example, comparing the -1 order and +1 order in the diffraction spectrum of a periodic grating). This can be performed as described above and as described in, for example, U.S. Patent Application Publication No. US2006-066855, which is incorporated herein by reference in its entirety. Another application of diffraction-based metrology is in the measurement of feature width (CD) within a target.

[0099] Thus, during a device fabrication process (e.g., a patterning process, a lithography process, etc.), a substrate or other object may be subjected to various types of measurements during or after the process. The measurements may determine whether a particular substrate is defective, may adjust the process and equipment used in the process (e.g., aligning two layers on the substrate, or aligning the pattern forming device with the substrate), may measure the performance of the process and equipment, or may be used for other purposes. Examples of measurements include optical imaging (e.g., optical microscopy), non-imaging optical measurements (e.g., diffraction-based measurements, such as ASML YieldStar metrology tools, ASML SMASH metrology systems), mechanical measurements (e.g., profiling / contour probing using a stylus, atomic force microscopy (AFM)), and / or non-optical imaging (e.g., scanning electron microscopy (SEM)). The Smart Alignment Sensor Hybrid (SMASH) system as described in U.S. Pat. No. 6,961,116, which is incorporated herein by reference in its entirety, employs a self-referencing interferometer that produces two overlapping and relatively rotated images of an alignment mark, detects intensity in a pupil plane where Fourier transforms of the images cause interference, and extracts position information from the phase difference between the diffraction orders of the two images, which is expressed as intensity variations in the interference orders.

[0100] The metrology results may be provided directly or indirectly to the supervisory control system SCS. If an error is detected, the exposure of subsequent substrates (especially if the inspection can be completed quickly and quickly enough that one or more other substrates of the batch remain to be exposed) and / or the subsequent exposure of the exposed substrate may be adjusted. In addition, the exposed substrate may be stripped and reworked to improve yield, or discarded, thereby avoiding further processing of substrates known to be defective. In the case where only some target portions of the substrate are defective, further exposure may be performed only on those target portions that meet the specifications.

[0101] Within the metrology system MET, metrology equipment is used to determine one or more properties of the substrate, and in particular, to determine how one or more properties of different substrates vary, or how different layers of the same substrate vary from layer to layer. As mentioned above, the metrology equipment may be integrated into the lithographic apparatus LA or the lithographic cell LC, or may be a separate device.

[0102] In order to enable the measurement, one or more targets may be provided on the substrate. In an embodiment, the target is specially designed and may include a periodic structure. In an embodiment, the target is part of a device pattern, for example, a periodic structure of the device pattern. In an embodiment, the device pattern is a periodic structure of a memory device (for example, a bipolar transistor (BPT), a bit line contact, i.e., a shared bit bus (BLC), etc.).

[0103] In an embodiment, the target on the substrate may include one or more one-dimensional periodic structures (e.g., gratings) that are printed such that after development, the periodic structural features are formed by solid resist lines. In an embodiment, the target may include one or more two-dimensional periodic structures (e.g., gratings) that are printed such that after development, the one or more periodic structures are formed by solid resist posts or vias in the resist. The bars, posts or vias may alternatively be etched into the substrate (e.g., etched into one or more layers on the substrate).

[0104] In an embodiment, one of the parameters of interest in the patterning process is overlap. Overlap can be measured using dark field scatterometry, in which the zeroth order of diffraction (corresponding to specular reflection) is blocked and only higher orders are processed. Examples of dark field measurements can be found in PCT patent application publications WO 2009 / 078708 and WO 2009 / 106279, which are hereby incorporated by reference in their entirety. Further developments of the technology have been described in U.S. patent application publications US2011-0027704, US2011-0043791, and US2012-0242970, which are hereby incorporated by reference in their entirety. Diffraction-based overlap using dark field detection of diffraction orders enables overlap measurement of smaller targets. These targets can be smaller than the irradiation spot and can be surrounded by device product structures on the substrate. In an embodiment, multiple targets can be measured in one radiation capture.

[0105] As lithography nodes continue to shrink, increasingly complex wafer designs can be implemented. Various tools and / or techniques can be used by designers to ensure that complex designs are accurately transferred to physical wafers. These tools and techniques can include mask optimization, source mask optimization (SMO), OPC, design for control, and / or other tools and / or techniques. For example, a source mask optimization process is described in U.S. Patent No. 9,588,438, entitled "Optimization Flows of Source, Mask and Projection Optics," which is incorporated by reference in its entirety.

[0106] Figure 3A A flow chart listing the main stages of the "Design for Control" (D4C) method is shown. In stage 310, materials to be used in the lithography process are selected. The materials can be selected from a material library interfaced with D4C via an appropriate GUI. In stage 320, the lithography process is defined by entering each of the process steps and building a computer simulation model for the entire process sequence.

[0107] For example, the simulation may be used to configure one or more features of the patterned device pattern (e.g., to perform optical proximity effect correction), one or more features of the illumination (e.g., to change one or more characteristics of the spatial / angular intensity distribution of the illumination, such as to change the shape), one or more features of the projection optics (e.g., numerical aperture, etc.), one or more features of multiple individual lithography operations such as etching, deposition, CMP, etc., and / or other aspects of the process sequence. In some embodiments, the simulation may include multiple individual models for multiple individual aspects of the process sequence (e.g., etching, deposition, CMP, etc.), where outputs from models of previous process steps are used as inputs for models of subsequent process steps.

[0108] In some embodiments, the model can be used to optimize (the steps (operations) in) the wafer manufacturing process. The optimization process of the manufacturing process can be expressed as a cost function. The optimization process can include finding a set of parameters (design variables, process variables, etc.) of the system that minimizes the cost function. The cost function can have any suitable form depending on the goal of the optimization. For example, the cost function can be the weighted root mean square (RMS) of the deviations of certain characteristics (evaluation points) of the system relative to the expected values ​​(e.g., ideal values) of these characteristics. The cost function can also be the maximum value (i.e., the worst deviation) of these deviations. The term "evaluation point" should be broadly interpreted to include any characteristic of the system or manufacturing method. Due to the practicality of the embodiments of the above-mentioned systems and / or methods, the design and / or process variables of the system can be limited to a limited range and / or be interdependent. In the case of a lithographic projection device, the constraints are often associated with the physical properties and characteristics of the hardware (such as, adjustable range, and / or pattern forming device manufacturability design rules). The evaluation points can include physical points on the image on the substrate, as well as non-physical characteristics.

[0109] In some embodiments, a given model associated with and / or included in an integrated circuit manufacturing process may be an empirical model that models the operation of a corresponding processing method. The empirical model may predict outputs based on correlations between various inputs (e.g., one or more characteristics of a mask or wafer image, one or more characteristics of a design layout, one or more characteristics of the pattern forming device, one or more characteristics of the lithography process (e.g., etching, deposition, CMP, etc.)).

[0110] As an example, the empirical model can be a machine learning model and / or any other parameterized model. In some embodiments, the machine learning model (for example) can be and / or include a mathematical equation, an algorithm, a plotted graph, a chart, a network (e.g., a neural network), and / or other tools and machine learning model parts or components. For example, the machine learning model can be and / or include one or more neural networks having an input layer, an output layer, and one or more intermediate layers or hidden layers. In some embodiments, the one or more neural networks can be and / or include a deep neural network (e.g., a neural network having one or more intermediate layers or hidden layers between the input layer and the output layer).

[0111] As an example, the one or more neural networks may be based on a large collection of neural units (or artificial neurons). The one or more neural networks may loosely, i.e., not strictly, mimic the way a biological brain works (e.g., via multiple large clusters of multiple biological neurons connected by axons). Each neural unit of the neural network may be connected to many other neural units of the neural network. Such connections may strengthen or inhibit their influence on the activation state of the connected neural units. In some embodiments, each individual neural unit may have a summation function that combines the values ​​of all its inputs. In some embodiments, each connection (or neural unit itself) may have a threshold function so that the signal must exceed the threshold before it is allowed to propagate to other neural units. These neural network systems may be self-learning and trained, rather than explicitly programmed, and may perform significantly better in certain problem-solving areas than traditional computer programs. In some embodiments, the one or more neural networks may include multiple layers (e.g., where the signal path traverses from the front-end layer to the back-end layer). In some embodiments, backpropagation techniques may be applied by the neural network, in which forward stimulation is used to reset the weights of the "front-end" neural units. In some embodiments, stimulation and inhibition of the one or more neural networks may flow more freely, with connections interacting in a more chaotic and complex manner. In some embodiments, intermediate layers of the one or more neural networks include one or more convolutional layers, one or more recurrent layers, and / or other layers.

[0112] The one or more neural networks may be trained (i.e., parameters of the neural networks are determined) using a set of training data. The training data may include a set of training samples. Each sample may be a pair including an input object (usually a vector, which may be referred to as a feature vector) and a desired output value (also referred to as a management signal). A training algorithm analyzes the training data and adjusts the behavior of the neural network by adjusting the parameters of the neural network (e.g., the weights of one or more layers) based on the training data. For example, given the form A set of N training samples such that x i is the feature vector of the ith example and y i is its management signal, then the training algorithm seeks a neural network g: X→Y, where X is the input space and Y is the output space. A feature vector is an n-dimensional vector representing the numerical features of an object (e.g., a chip design, a fragment, etc. as in the above example). The vector space associated with these vectors is often referred to as the feature space. After training, the neural network can be used to make predictions using new samples. In some embodiments, the one or more neural networks may include a convolutional neural network (CNN), a deep neural network (DNN), and / or other types of neural networks. In some embodiments, the one or more neural networks may include various types of artificial intelligence (AI) and / or work with various types of artificial intelligence.

[0113] In stage 330, the measurement target is defined, that is, the dimensions and other characteristics of the various features included in the target are entered into the D4C program. For example, if a grating is included in the structure, the number of grating elements, the width of a single grating element, the spacing between two grating elements, and so on must be defined. In stage 340, a 3D geometry is generated. This step also takes into account whether there is any information related to the multi-layer target design, such as the relative displacement between different layers. This feature enables multi-layer target design. In stage 350, the final geometry of the designed target is visualized. As will be explained in more detail below, not only is the final design visualized, but as the designer applies the various steps of the lithography process, the designer can visualize how the 3D geometry is formed and changes due to process-induced effects. For example, the 3D geometry after resist patterning is different from the 3D geometry after resist removal and etching.

[0114] Different visualization tools called "viewers" are built into the D4C software. For example, Figure 3B, the designer can view a material plot 360 (and can also obtain a run time estimate plot) based on the defined lithography process and objectives. Once the lithography model is generated, the designer can view the model parameters through the model viewer tool 375. The design layout viewer tool 380 can be used to view the design layout (e.g., a visual presentation / rendering of a GDS file). The resist profile viewer tool 385 can be used to view the pattern profile in the resist. The geometry viewer tool 390 can be used to view the 3D structure on the substrate. The pupil viewer tool 395 can be used to view the simulated response to the measurement tool. Those skilled in the art will understand that these viewing tools can be used to enhance the designer's understanding during design and simulation. In some embodiments of the D4C software, one or more of these tools may not be present, and in some other embodiments, additional viewing tools may be present.

[0115] Figure 3C A flowchart illustrating how the D4C process increases efficiency in the overall simulation process by reducing the number of measurement targets selected for the actual simulation of the lithography process. As mentioned previously, D4C enables designers to design thousands or even millions of designs. Not all of these designs can be stable or robust relative to changes in the process steps. In order to select a subset of the target design that can tolerate process changes, the lithography personnel can intentionally disturb one or more steps of the defined lithography process, as shown in block 352. The introduction of the disturbance changes the entire process sequence in terms of how it was originally defined. Therefore, applying the disturbed process sequence (block 354) will also change the 3D geometry of the designed target. The lithography personnel only selects the disturbances that show non-zero changes in the original design target, and creates a subset of the selected process disturbances (block 356). This subset of process disturbances is then used to simulate the lithography process (block 358).

[0116] The use of the lithography process (or, generally, the patterning process) to manufacture or produce a substrate generally involves process variations. The process variations are not uniform across the entire substrate. For example, during the deposition process, the film tends to be thicker at the center of the substrate and thinner when close to the edge. These systematic variations are generally reflected in the measurement data as a "fingerprint" or "feature identification", which is a characteristic of the substrate based on known process conditions. In other words, there is a stack on the substrate, and the stack has a spatial variation as a function of the substrate coordinates. The stack includes a plurality of layers formed on the substrate during the patterning process to form a selected pattern (e.g., a design pattern) on the substrate. Each layer of the stack can be associated with thickness, material properties, and features and related parameters of the patterning process (e.g., CD, spacing, overlap, etc.).

[0117] The present systems, and / or methods may be used as a standalone tool and / or technique, in conjunction with a D4C process, and / or in conjunction with other semiconductor manufacturing processes modeled using the process to enhance the accurate transfer of complex designs to physical wafers.

[0118] As described above, it is important to maintain a stable semiconductor manufacturing process. The present system and method are provided for monitoring the performance of a (e.g., semiconductor) manufacturing process in real time or near real time. In the present system and method, one or more input signals are received that transmit information related to the geometry of the substrate produced during the manufacturing process, and a prediction model (e.g., a machine learning model) is used to determine the changes in the manufacturing process based on the one or more input signals and / or other information. The predicted changes may include prediction results related to the geometry of the features in the substrate, prediction results related to a specific manufacturing process (e.g., deposition, etching, chemical mechanical polishing, etc.), prediction results related to a separate parameter of one or more manufacturing processes in those manufacturing processes (e.g., as described below), and / or other information. For example, the input signal may include overlap, alignment, and / or other signals. The determined changes may provide quantitative process feedback that facilitates adjustment of various manufacturing processes.

[0119] By way of non-limiting example, Figure 4 The diagram illustrates operations of a method 400 for monitoring the performance of a manufacturing process. In some embodiments, the method 400 includes: training 402 a prediction model; receiving 404 one or more input signals; determining 406 a change in the manufacturing process based on the one or more input signals using the prediction model; and adjusting 408 a manufacturing process and / or manufacturing equipment based on the determined change in the manufacturing process. In some embodiments, the substrate is associated with a semiconductor device, and the manufacturing process includes a semiconductor device manufacturing process. In some embodiments, the substrate includes, for example, a stack associated with a semiconductor device, and / or other substrates. The operations of method 400 are intended to be illustrative. In some embodiments, method 400 may be implemented using one or more additional operations not described, and / or without using one or more of the operations discussed. For example, operation 408, and / or other operations may be optional. Additionally, in Figure 4 The order in which the operations of method 400 are illustrated and described below is not intended to be limiting.

[0120] Figure 4The method 400 shown in (wherein input (e.g., alignment, overlap, etc.) signals are used to predict process variations) is contrasted with typical methods that operate in the opposite manner, using geometry and process information (e.g., including purposeful variations of such information) as inputs to predict output signals (e.g., overlap, alignment, etc.) indicative of predicted geometry. Figure 5 An example of a typical method is shown in FIG. Figure 5 The diagram shows the use of geometry and process information 500 as input to predict 501 an output signal 502 indicative of the predicted geometry (as opposed to the present method). Figure 5 A typical (eg, D4C) simulation flow 504 is shown. For a given input geometry and process information (such as a stackup 506), the corresponding process parameters (in Figure 5 504 ) and / or target pattern definition 508, output signal 502, the output signal 502 includes, for example, different KPI swing curves 510, 512 (e.g., SS, DE, etc.). A swing curve is a curve that describes the wavelength dependence, i.e., the wavelength dependency, of a KPI (e.g., SS). Using such a curve, it can be determined which wavelength is optimal for overlay and alignment measurements. SS stands for stack sensitivity. DE stands for diffraction efficiency. The swing curve shows, for example, the change in a given process parameter. Mathematically, process 504 can be represented as:

[0121]

[0122] where f indicates a simulation engine or simulation function, is the example geometry information input for each layer (eg, of the stack) in this example—i.e., thickness, and is (for example) the wavelength at which the KPI is calculated (predicted). In this example equation, the input parameter changes are limited to thickness changes only, but the input parameter changes may also include changes related to n and / or k changes, SWA changes, tilt angle changes, and other process parameter changes. Continuing with this example, if the above equation is rewritten in vector form using the thickness of each layer as the input vector and the corresponding KPI swing curve as the output vector, then the (e.g., D4C) process 504 may be described as:

[0123] .

[0124] Rather, the present systems and methods may be considered to operate in reverse order relative to the process in process 504. For example, Figure 6The figure shows a reverse (relative to process 504) process 600 for the present system and method. Process 600 includes: receiving 602 one or more input signals 604, 606 (in this example, measured SS curves); and using a prediction model, predicting and / or otherwise determining 608 changes 610 in the manufacturing process based on the one or more input signals 604, 606. The predicted changes can include predictions related to the geometry of features in the substrate, predictions related to specific manufacturing processes (e.g., deposition, etching, chemical mechanical polishing, etc.), predictions related to individual parameters of one or more of those manufacturing processes, and / or other information. In this example, the input signals 604, 606 convey information (e.g., physically measured) of the substrate (e.g., the stack and / or other substrates) related to the geometry produced by the manufacturing process, and / or other information. For example, the predicted changes 610 may include information such as the stack geometry (including the thickness of each layer (e.g., t1, t2, ..., t n )), corresponding changes in process parameters (such as changes in n and / or k), SWA changes, tilt angle changes, and other process parameter changes (in Figure 6 not listed in the ), and / or other information.

[0125] Similar to Figure 5 The process 504 shown in (eg, reverse D4C) 600 may also be represented as a vector in the form of:

[0126]

[0127] This inversion or reverse relationship involves complex nonlinear mappings in high-dimensional space and is difficult to solve analytically or using numerical simulations. However, since both the input and output are vectors of fixed length, and the swing curve (for example) and / or other measured information can be used to encode rich information describing process variations, this problem is suitable for solving using machine learning algorithms, neural networks, and / or other predictive models.

[0128] Back to Figure 4 , and as described above, at operation 402, a prediction model is trained. In some embodiments, the prediction model comprises a machine learning model. In some embodiments, the prediction model and / or the machine learning model comprises one or more neural networks. Machine learning typically requires a large amount of information to train the model. Fortunately here, such training information can be obtained from previous or existing (e.g., D4C) simulations based on a large number of random (but known) perturbations to the nominal stack.

[0129] The prediction model is trained using training information. The training information may include multiple pairs or groups of input objects and corresponding measured or expected output values. The training information may include one or more of the following: electronic signals associated with substrate geometry, images, target patterns, patterning process parameters, and / or other information, and corresponding physical substrate measurement results, known process parameters and / or process parameter changes, and / or other information. By way of non-limiting example, the prediction model is trained based on known disturbances in the manufacturing process. Known process disturbances can be caused by intentionally changing one or more manufacturing process parameters (variables) in a known manner, physically measuring the resulting substrate, i.e., physical measurements, and / or other activities. The resulting substrate can be used to measure electronic signals (e.g., overlap signals, alignment signals, etc.), which represent the resulting substrate generated using known process disturbances. The known disturbances and corresponding electronic signals can be paired. These pairs can be provided to the prediction model as training information. The prediction model can use the provided multiple pairs of training information for self-learning (e.g., when the model is a neural network or includes a neural network). The trained prediction model may be used to make new predictions (eg, predict new process disturbances) based on different input information (such as different electronic signals and / or other information).

[0130] At operation 404, one or more input signals are received. The input signals may be different input information described above with respect to training, and / or may be included in the different input information described above with respect to training. The input signals convey information related to the geometry of the substrate produced by the manufacturing process, and / or other information. In some embodiments, the input signals include overlap signals. In some embodiments, the one or more input signals include alignment signals. For example, as described above, the one or more input signals may include measured SS, DE, K, and / or other signals. These example signals are not intended to be limiting.

[0131] At operation 406, the prediction model is used to predict and / or otherwise determine changes in the manufacturing process. The changes are predicted and / or otherwise determined based on the one or more input signals and / or other information. The predicted and / or otherwise determined changes may include predictions and / or determinations related to the geometry of features in the substrate (e.g., the thickness of a layer in a stack), predictions and / or determinations related to a specific manufacturing process (e.g., deposition, etching, chemical mechanical polishing, etc.), predictions and / or determinations related to individual parameters of one or more manufacturing processes in those manufacturing processes, and / or other information. In some embodiments, the changes in the manufacturing process include one or more of the following: changes in processing parameters of the manufacturing process, changes in material properties of one or more materials used in the manufacturing process, changes in optical properties of the one or more materials, and / or other changes. In some embodiments, the processing parameters of the manufacturing process may include etch depth, deposition parameters, sidewall angles, etch floor inclination angles, etch biases, photolithography CD biases, and / or other parameters. In some embodiments, the material and / or optical properties of the one or more materials used in the manufacturing process may include optical properties such as n or k that changes in reflectivity at different wavelengths, and / or other properties.

[0132] By way of non-limiting example, Fig. 7A and Figure 7B The diagram shows receiving an input signal 700 and using a predictive model 704 to predict and / or otherwise determine 702 a change in a manufacturing process. Fig. 7A and Figure 7B The input signal 700 includes signals for different wavelengths. SS KPI swing curve. Fig. 7A Two separate sets of SS signals 706, 708 are shown, while Figure 7B A rough combined set of SS signals 710 is shown. Fig. 7A The figure shows output 712 from the model 704, which includes material property information 714, such as stacked layer thicknesses t1, t2, ..., t n . Figure 7B Output 712 from model 704 is shown, including material property information 714 (such as stacked layer thicknesses t1, t2, ..., t n ) and optical property information 716 (such as n1, n2, ..., n k ). These examples are not intended to be limiting. Figure 7BThe diagram illustrates the versatility of the present system and method. By slightly modifying the output 712, the same model 704 can be used to predict not only thickness changes (e.g., 714), but also changes in n and / or k (e.g., 716). Using similar techniques, asymmetric process changes, as evidenced by tilt angle and sidewall angle, and / or other process changes can also be predicted. These examples are not intended to be limiting.

[0133] Fig. 7A and Figure 7B The figure shows how the prediction model 704 can be and / or include a neural network 720 (the neural network 720 has an input layer 722, a hidden layer 724, and an output layer 726) configured to predict and / or otherwise determine the thickness of each layer based on the rocking curve for stack sensitivity measurement. It should be noted that while the neural network 720 is suitable for solving this type of problem, the model 704 is not limited to neural networks. Although Fig. 7A and Figure 7B The diagram shows a neural network as an example of a machine learning mechanism, but the present disclosure is not intended to be limited to only neural networks. Any other machine learning technique may be applied if it produces acceptable results.

[0134] It should be noted that even Fig. 7A and Figure 7B The diagram shows individual values ​​of individual parameters predicted and / or otherwise determined, and the prediction model 704 can also be configured (e.g., trained) to predict and / or otherwise determine corresponding changes in these parameters (e.g., over time, from target or set values, relative to each other, etc.), predict and / or otherwise determine the manufacturing process associated with these parameters, and / or determine other changes in the manufacturing process. In some embodiments, process changes can be determined based on the individual values ​​predicted and / or determined for the individual parameters. For example, one or more mathematical operations can be used with multiple prediction results of the same parameter change over time to determine the change of the parameter over time, and / or how much it has changed.

[0135] Back to Figure 4, in operation 408, adjusting the manufacturing process and / or manufacturing equipment based on the determined change in the manufacturing process. In some embodiments, operation 408 includes determining an adjustment for the manufacturing process and / or manufacturing equipment (e.g., a parameter to be adjusted, a device to be adjusted, an amount to adjust the parameter, an amount to adjust the device, etc.), and then adjusting the manufacturing process and / or manufacturing equipment based on the determined adjustment. In some embodiments, the receiving (operation 404), the determining (operation 406), the adjusting (operation 408), and / or other operations are performed in real time or near real time during the manufacturing process. In some embodiments, real time or near real time can be and / or include a time that occurs within seconds or minutes of the change, and allows the manufacturing process to be adjusted in a timely manner to prevent the production of defective devices and increase process yield.

[0136] In some embodiments, adjustments can be based on predictions and / or determinations of how much the manufacturing process has changed and has changed. Additionally, adjustments can be made based on predictions and / or determinations for entire stacks (and / or other substrates) with multiple types of process changes. For example, adjustments can be simultaneously based on predicted and / or otherwise determined thickness changes, SWA changes, tilt angle changes, and / or other changes to multiple layers of a stack, n and / or k changes to multiple materials in a stack, and the like.

[0137] Turning to the adjustment aspect of the present systems and methods, as described above, overlay adjustment is a process that utilizes corresponding predictions from an electronic model (e.g., a non-machine learning D4C model) to enhance consistency between overlay, alignment, and / or other measurement data. Typical overlay adjustment is performed in an iterative manner through a series of operations to produce an optimized overlay. The iterative nature of typical overlay adjustment, and the fact that predictions from (non-machine learning) electronic models often take several hours or even several days, causes typical overlay adjustment to run very slowly. Advantageously, the present systems and methods replace the typical time-consuming predictions from (non-machine learning) physical models with faster predictions from improved machine learning models. The present systems and methods utilize a trained machine learning prediction model that is configured to generate predictions almost immediately, i.e., almost instantly.

[0138] Figure 8The diagram illustrates operations of a method 800 for performing stack adjustment using a machine learning prediction model. In some embodiments, method 800 includes: training 802 a machine learning prediction model; receiving 804 input information; predicting 806 an output substrate geometry based on the input information using the machine learning prediction model; and adjusting 808 the predicted output substrate geometry (e.g., adjusting the model). In some embodiments, the substrate includes, for example, a stack associated with a semiconductor device. The operations of method 800 are intended to be illustrative. In some embodiments, method 800 may be implemented utilizing one or more additional operations not described, and / or implemented without using one or more of the operations discussed. Additionally, in Figure 8 The order in which the operations of method 800 are illustrated and described below is not intended to be limiting.

[0139] As described above, at operation 802, the machine learning prediction model is trained. In some embodiments, the machine learning model is a neural network, or includes a neural network. The machine learning prediction model includes training information. In some embodiments, operation 802 includes: using training information describing the geometry, pattern, and manufacturing process parameters of the training substrate and corresponding physical substrate measurement results and / or prediction results from different non-machine learning prediction models (e.g., previous D4C models) to train the machine learning prediction model. The training information may include multiple pairs or groups of input objects and corresponding measured or expected output values. These pairs can be provided to the machine learning prediction model as training information. The machine learning prediction model can use the multiple pairs of training information provided to perform self-learning (e.g., when the model is a neural network, or includes a neural network). The trained machine learning prediction model can be used to make new predictions based on different input information (such as different stacks, different process parameters, and / or other information).

[0140] At operation 804, input information is received. The input information includes geometric information and manufacturing process information of a substrate (e.g., a stack and / or other substrate), and / or other information. In some embodiments, the input information is for a stack and / or other substrate associated with the semiconductor device. In some embodiments, the geometric information includes, for example: one or more dimensions of a target or mark design for one or more portions of a semiconductor device (e.g., the distance from one feature to another; the thickness of a layer; the length, width, diameter, etc. of each feature; etc.); an initial guess and / or other determination results about the thickness of the layer; previously simulated KPIs; distances, angles, and / or other information indicating the spatial orientation of one or more features of a pattern relative to each other (e.g., along the "x", "y" and / or "z" directions); and a .GDS file; the relative positions of design targets from different layers and the resulting overlap; and / or other geometric information.

[0141] The manufacturing process information includes one or more parameters for one or more manufacturing processes performed on a substrate associated with a semiconductor device, and / or other information. For example, the manufacturing process information may include one or more etching process parameters, one or more deposition process parameters, one or more chemical mechanical polishing process parameters, and / or other process parameters. Examples of etching parameters, deposition parameters, and CMP parameters may include etching rate (e.g., vertical etching rate and / or horizontal etching rate), deposition rate, CMP pressure, speed, etc., and / or other parameters. Process parameters may include values ​​for process settings, values ​​for maximum and / or minimum process window parameter setting points, etchable materials, etching depth, etching SWA, CMP formation of dishing, depth, etc., and / or any other information for defining and / or adjusting the manufacturing process.

[0142] At operation 806, the output substrate geometry is predicted using the machine learning prediction model. In some embodiments, the output substrate geometry change (e.g., relative to the target geometry, relative to the previous geometry, and / or other geometry) is predicted. In some embodiments, the electronic signal (e.g., overlap, alignment, etc.) can be predicted based on the output substrate geometry, the geometry change, and / or other information. The output substrate geometry, geometry change, and / or electronic signal are predicted based on the input information and / or other information. In some embodiments, operation 806 includes: using the machine learning prediction model to predict an overlap signal, an alignment signal, and / or other information based on the output substrate geometry. In some embodiments, the overlap signal, the alignment signal, and / or other information can be predicted based on the output semiconductor device geometry, the geometry change, and / or other information. In some embodiments, operation 806 includes: detecting changes in the semiconductor manufacturing process based on the semiconductor device geometry, geometry change, the overlap signal, the alignment signal, and / or other prediction results from the machine learning prediction model.

[0143] At operation 808, the predicted output substrate geometry, electronic signals (e.g., overlap signals, alignment signals, etc.), and / or other information predicted by the machine learning prediction model are adjusted. This can be understood as adjusting the machine learning prediction model itself. For example, in an embodiment where the substrate includes a stack, this can be understood as stack adjustment. In some embodiments, operation 808 includes one or both of operations 806 and 804. In some embodiments, the adjustment includes: comparing the output substrate geometry with corresponding physical substrate measurements and / or predictions from different non-machine learning prediction models; generating a loss function based on the comparison; optimizing the loss function; and / or other operations. In some embodiments, operation 808 includes receiving a stack adjustment input and outputting the substrate geometry. For example, in some embodiments, the stack adjustment input includes a signal associated with a measurement from a corresponding physical stack, the geometry information, the manufacturing process information, and / or other information. The geometry information may include the nominal geometry of the physical stack, and / or other information. The output substrate geometry is adjusted such that analog signals (eg, overlay, alignment, etc.) determined based on the adjusted output substrate geometry correspond to signals associated with measurements from the physical stack and / or a nominal geometry of the physical stack.

[0144] Fig. 9The figure shows an example of a new stack adjustment process 900. The stack adjustment process 900 includes a training operation 802, an adjustment operation 808, an input operation 804, a prediction operation 806, and other operations. Fig. 9 As shown in FIG. 8 , the two operations of the adjustment process 900 include a training operation 802 and an adjustment operation 808. In the training operation 802, a machine learning prediction model (e.g., including a neural network and / or other algorithms) is trained. In the adjustment operation 808, the trained prediction model 910 is used to replace 912 a traditional non-machine learning model, so as to greatly reduce the total time required to complete the adjustment operation 808. The existing stack adjustment process may include Fig. 9 The lower portion of the flow, from 804 to 956, includes operation 960. As shown and described, in the new flow 900, operation 806 is performed by Fig. 9 is replaced by the machine learning model described in the upper portion 802.

[0145] like Fig. 9 As shown in FIG. 8 , the training operation 802 includes generating training information 920 and then actually training 922 the machine learning prediction model. In some embodiments, generating the training information 920 may include generating a large number of random process parameter variations 924, performing corresponding simulations using a non-machine learning model 926, and outputting a prediction signal indicative of substrate geometry 928. In some embodiments, actually training 922 the machine learning prediction model may include training 930 one or more machine learning algorithms, such as neural networks and / or other algorithms. The random process parameter variations 924 and the prediction signal indicative of substrate geometry 928 may be used as training information for training 930.

[0146] In some embodiments, the adjustment operation 808 includes operation 804 (e.g., making an initial guess about process parameters and performing simulations to generate starting signals (such as KPIs)), performing 950 an initial correlation of predictions with actual measurements, determining 952 whether the correlation is good (or good enough), and assuming that the correlation is not good (or not good enough), generating 954 a loss function, optimizing 956 the loss function, using the trained machine learning prediction model to predict (via operation 806) a new substrate (e.g., stack) geometry (e.g., and / or an electronic signal indicative of the substrate (stack) geometry), and performing 958 correlating the newly predicted substrate (stack) geometry with the actual measurements. Steps 952 to 958 may be repeated in an iterative manner until an acceptable correlation is achieved 960. For example, an acceptable correlation may include a correlation that satisfies a correlation criterion.

[0147] In some embodiments, the loss function is configured to determine how well the predictive model models the data set. If the predictive model does not accurately model the data set, the loss function is configured to output an indication of inaccuracy. As the model is adjusted in an iterative manner, the output from the loss function indicates an increasingly accurate model. The loss function is optimized using an optimization algorithm. Some of the most commonly used optimization algorithms may include local optimization algorithms and / or global optimization algorithms, such as Newton's method, gradient descent, trust region or confidence region, BFGS, etc.; the global optimization algorithm is such as annealing, genetic algorithm, etc.

[0148] Advantageously, if Fig. 9 As shown in FIG. 8 , the adjustment operation 808 utilizes machine learning based on a predictive model to replace the time-consuming non-machine learning model simulation in each iteration of traditional adjustment to reduce the overall stack adjustment time. The adjustment operation 808 can fully utilize the available computing resources during the training operation 802, and thus can easily scale up the adjustment speed with the increased processing power. Fig. 9 The stack adjustment described in the above description only takes a few seconds or less to iterate. Multiple iterative adjustment processes can be completed in a relatively short amount of time. This makes the stack adjustment described herein suitable for real-time or near real-time process monitoring. In comparison, previous stack adjustment times increase linearly with the number of iterations (and may take hours or more to complete). In addition, the trained machine learning model of the present system and method can make predictions for inputs that are not within the training information.

[0149] Back to Figure 8 In some embodiments, operation 808 includes determining one or more semiconductor device manufacturing process parameter changes. For example, operation 808 may include determining whether the process parameter change is within a tolerance window, or outside a tolerance window, and / or has other changes. The process parameter change may be determined based on the semiconductor device geometry, geometry changes, the overlap signal, the alignment signal, the adjusted stack, and / or other information. In some embodiments, operation 808 includes determining adjustments to one or more of the semiconductor device manufacturing process steps based on the one or more determined semiconductor device manufacturing process parameter changes and / or other information, and / or adjusting one or more of the semiconductor device manufacturing process steps. For example, operation 808 may include adjusting mask design, pattern feature geometry, dose, focus, etching parameters, deposition parameters, and / or other parameters of the semiconductor device manufacturing process. These adjustments may be made based on the determined process parameter changes.

[0150] Fig.10 1 is a block diagram illustrating a computer system 100 that can assist in implementing the methods, processes, or systems disclosed herein. The computer system 100 includes a bus 102 or other communication mechanism for communicating information, and a processor 104 (or multiple processors 104 and 105) coupled to the bus 102 for processing information. The computer system 100 also includes a main memory 106, such as a random access memory (RAM) or other dynamic storage device, coupled to the bus 102 for storing information and instructions to be executed by the processor 104. The main memory 106 can also be used to store temporary variables or other intermediate information during the execution of instructions to be executed by the processor 104. The computer system 100 also includes a read-only memory (ROM) 108 or other static storage device coupled to the bus 102 for storing static information and instructions for the processor 104. A storage device 110, such as a magnetic disk or optical disk, is provided and coupled to the bus 102 for storing information and instructions.

[0151] The computer system 100 may be coupled to a display 112 via the bus 102, such as a cathode ray tube (CRT) or a flat panel or touch panel display for displaying information to a computer user. An input device 114 including alphanumeric and other keys is coupled to the bus 102 for communicating information and command selections to the processor 104. Another type of user input device is a cursor control 116, such as a mouse, trackball, or cursor direction keys, for communicating direction information and command selections to the processor 104 and for controlling movement of a cursor on the display 112. This input device typically has two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), which allows the device to specify a position in a plane. A touch panel (screen) display may also be used as an input device.

[0152] According to one embodiment, a portion of one or more methods described herein may be performed by computer system 100 in response to processor 104 executing one or more sequences of one or more instructions contained in main memory 106. Such instructions may be read into main memory 106 from another computer-readable medium such as storage device 110. Executing the sequence of instructions contained in main memory 106 causes processor 104 to perform the process steps described herein. One or more processors in a multi-processing arrangement may also be employed to execute the sequence of instructions contained in main memory 106. In alternative embodiments, hard-wired circuitry may be used in place of, or in combination with, software instructions. Thus, the description herein is not limited to any specific combination of hardware circuitry and software.

[0153] As used herein, the term "computer-readable medium" refers to any medium that participates in providing instructions to the processor 104 for execution. Such media can take many forms, including but not limited to non-volatile media, volatile media, and transmission media. Non-volatile media include, for example, optical or magnetic disks, such as storage device 110. Volatile media include dynamic memory, such as main memory 106. Transmission media include coaxial cables, copper wires, and optical fibers, including cables that constitute bus 102. Transmission media can also take the form of sound waves or light waves, such as those generated during radio frequency (RF) and infrared (IR) data communications. Common forms of computer-readable media include, for example, floppy disks, flexible disks, hard disks, magnetic tapes, any other magnetic media, CD-ROMs, DVDs, any other optical media, punch cards, paper tapes, any other physical media with hole patterns, RAM, PROMs and EPROMs, FLASH-EPROMs, any other memory chips or cartridges, and carrier waves described below, or any other media from which a computer can read.

[0154] Various forms of computer readable media may be involved in carrying one or more sequences of one or more instructions to the processor 104 for execution. For example, the instructions may be initially carried on a disk of a remote computer. The remote computer may load the instructions into its dynamic memory and send the instructions over a telephone line using a modem. A modem local to the computer system 100 may receive data on the telephone line and convert the data into an infrared signal using an infrared transmitter. An infrared detector connected to the bus 102 may receive the data carried in the infrared signal and place the data on the bus 102. The bus 102 carries the data to the main memory 106, from which the processor 104 retrieves and executes the instructions. The instructions received by the main memory 106 may optionally be stored on the storage device 110 before or after being executed by the processor 104.

[0155] The computer system 100 may also include a communication interface 118 coupled to the bus 102. The communication interface 118 provides bidirectional data communication coupled to a network link 120 connected to a local network 122. For example, the communication interface 118 may be an integrated services digital network (ISDN) card or a modem to provide a data communication connection to a corresponding type of telephone line. As another example, the communication interface 118 may be a local area network (LAN) card to provide a data communication connection to a compatible LAN. A wireless link may also be implemented. In any such implementation, the communication interface 118 sends and receives electrical, electromagnetic, or optical signals carrying digital data streams representing various types of information.

[0156] The network link 120 typically provides data communication to other data devices through one or more networks. For example, the network link 120 can provide a connection to a host computer through a local area network 122 or to a data device operated by an Internet Service Provider (ISP) 126. The ISP 126 in turn provides data communication services through a global packet data communication network, now commonly referred to as the "Internet" 128. Both the local area network 122 and the Internet 128 use electrical, electromagnetic or optical signals that carry digital data streams. The signals through the various networks and the signals on the network link 120 and through the communication interface 118, which carry the digital data to and from the computer system 100, are exemplary forms of carrier waves that transport the information.

[0157] The computer system 100 can send messages and receive data, including program code, through the network, network link 120, and communication interface 118. In the example of the Internet, the server 130 can transmit the requested code for the application program through the Internet 128, ISP 126, local area network 122, and communication interface 118. For example, one such downloaded application can provide all or part of the methods described herein. The received code can be executed by the processor 104 when it is received, and / or stored in the storage device 110 or other non-volatile storage device for later execution. In this way, the computer system 100 can obtain application code in the form of a carrier wave.

[0158] Fig.11 Schematically depicts a device that can be used in conjunction with the techniques described herein. Figure 1 An exemplary lithographic projection apparatus similar and / or identical to the apparatus shown in . The apparatus comprises:

[0159] - an illumination system IL for conditioning the radiation beam B. In this particular case, the illumination system further comprises a radiation source SO;

[0160] - a first object table (eg patterning device table) MT having a patterning device holder for holding a patterning device MA (eg mask table) and connected to a first positioner for accurately positioning the patterning device relative to the item PS;

[0161] - a second object table (substrate table) WT having a substrate holder for holding a substrate W (e.g. a silicon wafer coated with resist) and connected to a second positioner for accurately positioning the substrate relative to the item PS;

[0162] - a projection system ("lens") PS (eg a refractive, reflective or catadioptric optical system) for imaging the irradiated portion of the patterning device MA onto a target portion C of the substrate W (eg comprising one or more dies).

[0163] As described herein, the apparatus is of the transmissive type (e.g., employing a transmissive patterning device). However, in general, it may be of the reflective type (e.g., employing a reflective patterning device). The apparatus may employ a different kind of patterning device than a classical mask; examples include a programmable mirror array or an LCD matrix.

[0164] A source SO (e.g. a mercury lamp or an excimer laser, laser produced plasma (LPP) EUV source) generates a radiation beam. This beam is fed into an illumination system (illuminator) IL, for example directly or after having traversed a conditioning device such as a beam expander Ex. The illuminator IL may include adjustment means for setting the outer radial extent and / or the inner radial extent (commonly referred to as σ-outer and σ-inner, respectively) of the intensity distribution in the beam. In addition, the illuminator IL will typically include various other components, such as an integrator and a condenser. In this way, the beam B impinging on the pattern forming device MA has a desired uniformity and intensity distribution in its cross section.

[0165] about Fig.11 It should be noted that, although the source SO may be within the housing of the lithographic projection apparatus (this is often the case when the source SO is, for example, a mercury lamp), it may also be remote from the lithographic projection apparatus, the radiation beam it generates being directed into the apparatus (for example, with the aid of appropriate directing mirrors); the latter situation is often the case when the source SO is an excimer laser (for example, based on KrF, ArF or F2 laser action).

[0166] The beam is then intercepted at the patterning device MA which is held on the patterning device table MT. Having traversed the patterning device MA, the beam PB passes through a lens PL which focuses said beam B onto a target portion C of the substrate W. With the aid of the second positioning device (and the interferometric measurement device), the substrate table WT can be accurately moved, for example in order to position a different target portion C in the path of the beam. Similarly, the first positioning device may be used to accurately position the patterning device MA relative to the path of the beam B, for example after mechanically acquiring the patterning device MA from a patterning device library or during a scan. Typically, movement of the object table MT, WT will be realized with the aid of a long-stroke module (coarse positioning) and a short-stroke module (fine positioning), which are not explicitly depicted. However, in the case of a stepper (as opposed to a step-and-scan tool), the patterning device table MT may be connected to the short-stroke actuator only, or may be fixed.

[0167] The depicted tool can be used in two different modes:

[0168] - in step mode, the patterning device table MT is kept substantially stationary and the entire patterning device image is projected in one operation (i.e. a single "flash") onto a target portion C. The substrate table WT is then shifted in the x and / or y direction so that a different target portion C can be irradiated by the beam;

[0169] - In scan mode, essentially the same applies, except that a given target portion C is not exposed in a single "flash". Alternatively, the patterning device table MT can be moved at a velocity v in a given direction (the so-called "scanning direction", e.g. the y-direction) so that the projection beam B is scanned over the patterning device image; while the substrate table WT is simultaneously moved in the same or opposite direction at a velocity V=Mv, where M is the magnification of the lens PL (typically M=1 / 4 or 1 / 5). In this way, a relatively large target portion C can be exposed without having to compromise on resolution.

[0170] Fig.12 The apparatus 1000 is shown in more detail, including a source collector module SO, an illumination system IL, and a projection system PS. The source collector module SO is constructed and arranged to maintain a vacuum environment in an enclosure 220 of the source collector module SO. A plasma 210 emitting EUV radiation may be formed by a discharge-generated plasma source. EUV radiation may be generated by a gas or vapor, such as xenon, lithium vapor, or tin vapor, wherein a very hot plasma 210 is generated to emit radiation in the EUV range of the electromagnetic spectrum. For example, a hot plasma 210 is generated by causing a discharge of an at least partially ionized plasma. In order to effectively generate radiation, it may be necessary to have, for example, a partial pressure of 10 Pa of Xe, Li, Sn vapor, or any other suitable gas or vapor. In an embodiment, an excited tin (Sn) plasma is provided to generate EUV radiation.

[0171] The radiation emitted by the hot plasma 210 is transferred from the source chamber 211 to the collector chamber 212 via an optional gas barrier or contaminant trap 230 (also referred to as a contaminant barrier or foil trap in some cases) positioned in or behind an opening in the source chamber 211. The contaminant trap 230 may include a channel structure. The contaminant trap 230 may also include a gas barrier, or a combination of a gas barrier and a channel structure. As is known in the art, the contaminant trap or contaminant barrier 230 further shown herein includes at least a channel structure.

[0172] The collector chamber 211 may include a radiation collector CO which may be a so-called grazing incidence collector. The radiation collector CO has an upstream radiation collector side 251 and a downstream radiation collector side 252. Radiation traversing the collector CO may be reflected by the grating spectral filter 240 and then focused at a virtual source point IF along the optical axis indicated by the line "O". The virtual source point IF is often referred to as an intermediate focus, and the source collector module is arranged so that the intermediate focus IF is located at or near an opening 221 in the enclosure structure 220. The virtual source point IF is an image of the radiation emitting plasma 210.

[0173] The radiation then traverses an illumination system IL which may include a faceted field mirror arrangement 22 and a faceted pupil mirror arrangement 24 arranged to provide a radiation beam 21 having a desired angular distribution at the patterning device MA, and a radiation intensity having a desired uniformity at the patterning device MA. After reflection of the radiation beam 21 at the patterning device MA held by the support structure MT, a patterned beam 26 is formed and the patterned beam 26 is imaged by the projection system PS via reflective elements 28, 30 onto a substrate W held by a substrate table WT.

[0174] There may typically be more elements than shown in the illumination optics unit IL and the projection system PS. Depending on the type of lithographic apparatus, a grating spectral filter 240 may optionally be present. Furthermore, there may be more mirrors than shown in the figures, for example there may be more than 200 in the projection system PS. Fig.11 1 to 6 additional reflective elements beyond the elements shown.

[0175] like Fig.12 The collector optics CO illustrated in FIG. 1 is depicted as a nested collector with grazing incidence reflectors 253, 254 and 255, merely as an example of a collector (or collector mirror). The grazing incidence reflectors 253, 254 and 255 are arranged axially symmetrically around the optical axis O, and this type of collector optics CO can be used in combination with a discharge produced plasma source, often referred to as a DPP source.

[0176] Alternatively, the source collector module SO may be as follows Fig.13 A portion of an LPP radiation system is shown. The laser LA is arranged to deposit laser energy into a fuel such as xenon (Xe), tin (Sn) or lithium (Li), thereby producing a highly ionized plasma 210 with an electron temperature of several tens of electron volts. High-energy radiation produced during deexcitation and recombination or recombination of these ions is emitted from the plasma, collected by a near normal incidence collector optic CO, and focused onto an opening 221 in an enclosure 220.

[0177] The concepts disclosed herein can simulate or mathematically model any general imaging system for imaging sub-wavelength features, and may be particularly useful in emerging imaging technologies that are capable of producing wavelengths with increasingly smaller sizes. Emerging technologies already in use include extreme ultraviolet (EUV) lithography that can produce 193 nm wavelengths by using ArF lasers and even 157 nm wavelengths by using fluorine lasers. In addition, EUV lithography can produce wavelengths in the range of 20 to 5 nm by using a synchrotron or by using high energy electrons to impinge on a material (solid or plasma) in order to produce photons in this range.

[0178] The embodiments of the present disclosure may be further described in the following aspects.

[0179] 1. A method for detecting changes in a semiconductor device manufacturing process and determining adjustments to the semiconductor device manufacturing process, the method comprising:

[0180] receiving input information, wherein the input information includes geometric shape information and manufacturing process information of the semiconductor device;

[0181] Using a machine learning prediction model, based on the input information, predict a change in the geometry of an output semiconductor device;

[0182] detecting changes in the semiconductor manufacturing process based on the prediction results of the semiconductor device geometry change from the machine learning prediction model;

[0183] determining one or more semiconductor device manufacturing process parameter changes based on the detected changes in the semiconductor device manufacturing process; and

[0184] Adjustments to the semiconductor device manufacturing process are determined based on the one or more determined changes in semiconductor device manufacturing process parameters.

[0185] 2. The method of clause 1, wherein the input information is for a stack associated with a semiconductor device.

[0186] 3. The method of clause 2, wherein detecting the variation in the semiconductor manufacturing process comprises: predicting an overlap signal based on the output semiconductor device geometry variation using the machine learning prediction model.

[0187] 4. The method of clause 2, wherein detecting the variation in the semiconductor manufacturing process comprises: predicting an alignment signal based on the output semiconductor device geometry variation using the machine learning prediction model.

[0188] 5. The method according to any one of Aspects 1 to 4 further includes adjusting the predicted output semiconductor device geometry variation, wherein the adjustment includes: comparing the output semiconductor device geometry variation with corresponding physical measurement results and / or prediction results from different non-machine learning prediction models, generating a loss function based on the comparison, and optimizing the loss function.

[0189] 6. The method of any one of clauses 1 to 5, wherein the geometric information comprises one or more dimensions of a target design for one or more layers of a semiconductor device.

[0190] 7. The method of any one of clauses 1 to 6, wherein the manufacturing process information comprises one or more etching process parameters, one or more deposition process parameters, and / or one or more chemical mechanical polishing process parameters.

[0191] 8. The method according to any one of clauses 1 to 7, wherein the adjustment to the semiconductor device manufacturing process comprises one or more of the following:

[0192] a change in an etch process parameter from a first etch process parameter value to a second etch process parameter value;

[0193] a change in a deposition process parameter from a first deposition process parameter value to a second deposition process parameter value; or

[0194] A change in a CMP process parameter from a first CMP process parameter to a second CMP process parameter value.

[0195] 9. A method according to any one of aspects 1 to 8, wherein the detected changes in the semiconductor device manufacturing process include one or more of the following: changes in processing parameters of the manufacturing process, changes in material properties of one or more materials used in the manufacturing process, or changes in optical properties of the one or more materials.

[0196] 10. A method for predicting substrate geometry associated with a manufacturing process, the method comprising:

[0197] receiving input information, the input information including geometric shape information of the substrate and manufacturing process information; and

[0198] An output substrate geometry is predicted based on the input information using a machine learning prediction model.

[0199] 11. The method of clause 10, wherein the substrate comprises a layer stack associated with a semiconductor device.

[0200] 12. The method according to any one of Aspects 10 to 11 further includes adjusting the predicted output substrate geometry, wherein the adjustment includes: comparing the output substrate geometry with corresponding physical substrate measurement results and / or prediction results from different non-machine learning prediction models; generating a loss function based on the comparison; and optimizing the loss function.

[0201] 13. The method of clause 12, wherein the adjusting comprises stacking adjustment, wherein:

[0202] The stack adjustment input includes: (1) a signal associated with a measurement result from a corresponding physical stack; (2) the geometric shape information, the geometric shape information including a nominal geometry of the physical stack; and (3) the manufacturing process information, and

[0203] The stack-up adjustment output includes the output substrate geometry,

[0204] And wherein the output substrate geometry is adjusted such that a simulated signal determined based on the output substrate geometry corresponds to a signal associated with measurements from the physical stack and / or the nominal geometry of the physical stack.

[0205] 14. The method according to any one of aspects 10 to 13 further comprises: predicting an overlap signal based on the output substrate geometry using the machine learning prediction model.

[0206] 15. The method according to any one of aspects 10 to 13 further comprises: predicting an alignment signal based on the output substrate geometry using the machine learning prediction model.

[0207] 16. A method according to any one of aspects 10 to 15, wherein the machine learning prediction model comprises a neural network.

[0208] 17. The method of any one of clauses 10 to 16, wherein the geometric information comprises one or more dimensions of a target or mark design for one or more layers of a semiconductor device.

[0209] 18. The method of any one of clauses 10 to 17, wherein the manufacturing process information comprises one or more parameters of one or more manufacturing processes performed on one or more layers of the semiconductor device.

[0210] 19. The method according to any one of Aspects 10 to 18 further includes: training the machine learning prediction model using training information describing the geometry, pattern, and manufacturing process parameters of the training substrate and corresponding physical substrate measurement results and / or prediction results from different non-machine learning prediction models.

[0211] 20. A method for monitoring the performance of a manufacturing process, the method comprising:

[0212] receiving one or more input signals conveying information related to a geometry of a substrate resulting from said manufacturing process; and

[0213] A change in the manufacturing process is determined based on the one or more input signals using a predictive model.

[0214] 21. The method of clause 20, wherein the substrate is associated with a semiconductor device and the manufacturing process comprises a semiconductor device manufacturing process.

[0215] 22. The method of clause 21, further comprising determining adjustments to semiconductor device manufacturing equipment based on changes in the manufacturing process.

[0216] 23. The method of any one of clauses 21 to 22, wherein the receiving and the determining are performed in real time or near real time during the semiconductor device manufacturing process.

[0217] 24. A method according to any one of aspects 20 to 23, wherein the one or more input signals comprise overlapping signals.

[0218] 25. A method according to any one of aspects 20 to 24, wherein the one or more input signals comprises an alignment signal.

[0219] 26. A method according to any one of aspects 20 to 25, wherein the changes in the semiconductor device manufacturing process include one or more of the following: changes in processing parameters of the manufacturing process, changes in material properties of one or more materials used in the manufacturing process, or changes in optical properties of the one or more materials.

[0220] 27. A method according to any one of aspects 18 to 26, wherein the predictive model comprises a machine learning model.

[0221] 28. A method according to any one of aspects 18 to 27, wherein the predictive model comprises a neural network.

[0222] 29. The method of any one of clauses 18 to 28, wherein the substrate comprises a layer stack associated with a semiconductor device.

[0223] 30. The method according to any one of aspects 18 to 29 further comprises: training the prediction model based on known disturbances in the manufacturing process.

[0224] 31. A computer program product, comprising a non-transitory computer-readable medium having instructions recorded thereon, wherein the instructions, when executed by a computer, implement the method according to any one of aspects 1 to 30 above.

[0225] Although the concepts disclosed herein can be used for wafer fabrication on substrates such as silicon wafers, it should be understood that the disclosed concepts can be used with any type of manufacturing system, for example, a manufacturing system for fabrication on substrates other than silicon wafers. In addition, combinations and subcombinations of the disclosed elements can include multiple separate embodiments. For example, a method for predicting process changes and a method for adjusting can include multiple separate embodiments, and / or these methods can be used together in the same embodiment.

[0226] The above description is intended to be illustrative rather than limiting. Accordingly, those skilled in the art will appreciate that modifications may be made as described without departing from the scope of the claims set forth below.

Claims

1. A method for predicting substrate geometry associated with a semiconductor manufacturing process, the method comprising: receiving input information, wherein the input information includes geometric shape information and manufacturing process information of the substrate; and predicting an output substrate geometry based on the input information using a machine learning prediction model, wherein the substrate comprises a stack comprising a plurality of layers, and Therein, the output substrate geometry comprises a thickness of a layer, and the input information comprises a result of an overlay adjustment.

2. The method according to claim 1, wherein: The method also includes adjusting the predicted output substrate geometry based on the prediction, the adjustment comprising: comparing the output substrate geometry with corresponding physical substrate measurement results and / or prediction results from different non-machine learning prediction models; generating a loss function based on the comparison; and optimizing the loss function.

3. The method according to claim 2, wherein: The adjustment includes a stacking adjustment, wherein: The stack adjustment input includes: (1) a signal associated with a measurement result from a corresponding physical stack; (2) the geometry information, the geometry information including a nominal geometry of the physical stack; and (3) the manufacturing process information, and A result of the overlay adjustment includes an overlay adjustment output including the output substrate geometry.

4. The method according to claim 3, wherein: The output substrate geometry is adjusted such that a simulated signal determined based on the output substrate geometry corresponds to a signal associated with measurements from the physical stack and / or the nominal geometry of the physical stack.

5. The method according to claim 1, wherein: The method also includes predicting an overlay signal based on the output substrate geometry using the machine learning prediction model.

6. The method according to claim 1, further comprising: An alignment signal is predicted based on the output substrate geometry using the machine learning prediction model.

7. The method according to claim 1, wherein: The geometric information includes one or more dimensions of a target or mark design for one or more layers of a semiconductor device.

8. The method according to claim 1, wherein: The manufacturing process information includes one or more parameters of one or more manufacturing processes performed on one or more layers of the semiconductor device.

9. The method according to claim 1, wherein: The method also includes: training the machine learning prediction model using training information including geometry, pattern, and manufacturing process parameters for training substrates and corresponding physical substrate measurement results and / or prediction results from non-machine learning prediction models.

10. The method according to claim 1, wherein: The method also includes determining changes in the manufacturing process based on the input information using the machine learning prediction model.

11. The method according to claim 10, wherein: The method further includes determining adjustments for semiconductor device manufacturing equipment based on the changes in the manufacturing process, wherein determining the adjustments is performed substantially in real time with receiving the overlay signal and / or the alignment signal during the semiconductor device manufacturing process.

12. The method according to claim 10, wherein: The change in the manufacturing process includes one or more of the following: a change in a processing parameter of the manufacturing process, a change in material properties of one or more materials used in the manufacturing process, or a change in optical properties of the one or more materials.

13. The method according to claim 9, wherein: The training includes: training the machine learning prediction model based on known disturbances in the manufacturing process.

14. A method for monitoring the performance of a manufacturing process, the method comprising: receiving one or more input signals conveying information related to a geometry of a substrate resulting from said manufacturing process; as well as determining, using a predictive model, a change in the manufacturing process based on the one or more input signals, wherein the substrate is associated with a semiconductor device and the manufacturing process comprises a semiconductor device manufacturing process, wherein the substrate comprises a stack, the stack comprising a plurality of layers, and The output substrate geometry predicted by the prediction model based on the one or more input signals comprises a thickness of a layer, and the one or more input signals comprise a result of an overlay adjustment.

15. The method of claim 14, further comprising determining adjustments to semiconductor device manufacturing equipment based on the changes in the manufacturing process.

16. The method according to claim 14, wherein: The receiving and the determining are performed in real time or near real time during the semiconductor device manufacturing process.

17. The method according to claim 14, wherein: The one or more input signals include overlapping signals or aligned signals.

18. The method according to claim 14, wherein: The changes in the semiconductor device manufacturing process include one or more of the following: changes in processing parameters of the manufacturing process, changes in material properties of one or more materials used in the manufacturing process, or changes in optical properties of the one or more materials.

19. The method according to claim 14, wherein: The predictive model includes a machine learning model. 20 . A computer program product, comprising a non-transitory computer-readable medium having instructions recorded thereon, wherein the instructions implement the method according to any one of claims 1 to 19 when executed by a computer.

Images