Systems and methods for generating post-polishing topography for enhanced wafer manufacturing

Abstract

A computer device is programmed to: store a model for converting shape images to simulate a portion of an assembly line; receive scan data of a first inspection of an assembled product; generate a shape image from the scan data of the first inspection; use the shape image as an input to execute the model to generate a final shape image of the product; compare the final shape image with one or more threshold values; determine whether the final shape image exceeds at least one of the one or more threshold values; and if the determination is that the final shape image exceeds at least one of the one or more threshold values, cause an adjustment of a first device.

Description

[Technical Field]

[0001] This field is generally about enhanced wafer fabrication, and more specifically, about enhanced wafer analysis using nano-morphology. [Previous Technology]

[0002] Semiconductor wafers (such as silicon wafers) are commonly used as substrates in the production of integrated circuit (IC) chips. Chip manufacturers require wafers to have extremely flat and parallel surfaces to ensure that the maximum number of chips can be manufactured from each wafer. After being sliced ​​from a wafer ingot, wafers typically undergo grinding and polishing processes, which are designed to improve specific surface characteristics, such as flatness and parallelism.

[0003] To identify and address topography degradation issues, device and semiconductor material manufacturers consider the nanoscale topography of wafer surfaces. For example, the Semiconductor Equipment and Materials International (SEMI), a global trade association for the semiconductor industry (SEMI document 3089), defines nanoscale topography as deviations on a wafer surface within a spatial wavelength range of approximately 0.2 mm to approximately 20 mm. This spatial wavelength corresponds very closely to the surface features at the nanoscale of a processed semiconductor wafer. Nanoscale topography measures the height deviation of a wafer surface without considering wafer thickness variations (as with conventional planarity measurements). Two techniques (light scattering and interferometry) are generally used to measure nanoscale topography. These techniques use light reflected from the surface of a polished wafer to detect very small surface variations.

[0004] In the semiconductor industry, companies are competing to produce high-quality silicon wafers at lower costs. Therefore, a highly efficient production process with minimal losses provides a competitive advantage. Production processes such as wire sawing and grinding result in morphological features on the wafer that can lead to morphological degradation. Furthermore, typical measurement tools available after these processes often exhibit significant noise. Due to excessive surface roughness, post-polishing tools cannot be used after these processes. To avoid these characteristics, close monitoring of post-polishing patterns is crucial, including in-plane distortion (IPD), nano-morphology (NT), and post-polishing shape profiles at different stages of silicon wafer production. However, most post-polishing patterns are only available in later stages of production, making feedback processes highly inefficient.

[0005] In some systems, many wafers can be processed after polishing but before problems are detected during the polishing process. Furthermore, individual production lines and polishing machines may have specific characteristics that vary depending on the equipment. Therefore, there is a need for a system for analyzing wafers to quickly and efficiently detect potential problems, reduce material waste, and increase efficiency.

[0006] This [Prior Art] section is intended to introduce to the reader various technical aspects that may relate to various aspects of the present invention, which are described and / or claimed below. It is believed that this discussion helps to provide the reader with background information to facilitate a better understanding of various aspects of the present invention. Therefore, it should be understood and taken in light of this, and not as an endorsement of prior art. [Summary of the Invention]

[0007] In one embodiment, a computer device includes at least one processor (or "processor") communicating with at least one memory device. The processor is programmed to store in the at least one memory device a model for converting shape maps to simulate a portion of an assembly line. The processor is also programmed to receive scan data of a first inspection of a product being assembled. The first inspection is performed at a first inspection station in the assembly line following a first device in the assembly line. The processor is further programmed to generate a shape map from the scan data of the first inspection. Additionally, the processor is programmed to use the shape map as input to execute the model to generate a final shape map of the product. Furthermore, the processor is programmed to compare the final shape map with one or more threshold values. Furthermore, the processor is programmed to determine whether the final shape map exceeds at least one of the one or more threshold values. If the determination is that the final shape map exceeds at least one of the one or more threshold values, the processor is programmed to cause an adjustment to the first device.

[0008] In another embodiment, a method for analyzing an assembly line is performed by a computing device including at least one processor communicating with at least one memory device. The method includes storing in the at least one memory device a model for converting a shape image to simulate a portion of an assembly line. The method also includes receiving scan data of a first inspection of an assembled product. The first inspection is performed at a first inspection station in the assembly line following a first device in the assembly line. The method further includes generating a shape image from the scan data of the first inspection. Additionally, the method includes using the shape image as input to execute the model to generate a final shape image of the product. Furthermore, the method includes comparing the final shape image with one or more threshold values. Furthermore, the method includes determining whether the final shape image exceeds at least one of the one or more threshold values. If the determination is that the final shape image exceeds at least one of the one or more threshold values, the method includes causing an adjustment to the first device.

[0009] Various modifications exist to the features mentioned in the above-described configuration. Similarly, further features may also be incorporated into the above-described configuration. These modifications and additional features may exist individually or in any combination. For example, the various features discussed below with respect to any of the illustrated embodiments may be incorporated individually or in any combination into any of the configurations described above.

Implementation Method

[0028] This application claims priority to U.S. Nonprovisional Patent Application No. 17 / 652,571, filed February 25, 2022, the entire disclosure of which is hereby incorporated by reference.

[0029] The described embodiments relate to systems and methods for analyzing wafer data, and more specifically, to analyzing post-grinding surfaces of wafers to predict post-processing surfaces. More specifically, a computing device executes a wafer surface analysis model to (1) determine the current condition of a wafer; (2) predict a post-processing state of the wafer based on the current condition and the model; and (3) determine whether adjustments to the polishing machine are needed based on the post-processing state of the wafer and one or more predetermined thresholds. Compared to previous procedures, these systems and methods allow for higher accuracy and shorter timeframes for nano-morphology feedback, thereby allowing for the identification and implementation of adjustments that can be used to improve nano-morphology to improve quality control and / or wafer yield with less lag time.

[0030] A computer system, such as a wafer surface analysis computer device and related computer systems, includes a processor and a memory. However, any processor in a computer device mentioned herein may also refer to one or more processors, wherein the processor may be in one computing unit or a plurality of computing units operating in parallel. Similarly, any memory in a computer device mentioned herein may also refer to one or more memory units, wherein the memory may be in one computing unit or a plurality of computing units operating in parallel.

[0031] A processor may comprise any programmable system, including systems using microcontrollers, reduced instruction set circuitry (RISC), application-specific integrated circuitry (ASIC), logic circuitry, and any other circuitry or processor capable of performing the functions described herein. The examples above are merely illustrative and are therefore not intended to limit the definition and / or meaning of the term "processor" in any way.

[0032] The term "database" can refer to a data subject, a relational database management system (RDBMS), or both. As used herein, a database can contain any collection of data, including hierarchical databases, relational databases, flat file databases, object-related databases, object-oriented databases, and any other structured collection of records or data stored in a computer system. The examples above are merely illustrative and are therefore not intended to limit the definition and / or meaning of the term database in any way. Examples of RDBMS include, but are not limited to, Oracle® databases, MySQL, IBM® DB2, Microsoft® SQL Server, Sybase®, and PostgreSQL. However, any database capable of implementing the systems and methods described herein may be used. (Oracle is a registered trademark of Oracle Corporation, Redwood Shores, California; IBM is a registered trademark of International Business Machines Corporation, Armonk, New York; Microsoft is a registered trademark of Microsoft Corporation, Redmond, Washington; and Sybase is a registered trademark of Sybase Corporation, Dublin, California.)

[0033] In one embodiment, a computer program is embodied on a computer-readable medium. In one example, the system runs on a single computer system without being connected to a server computer. In another example embodiment, the system runs in a Windows® environment (Windows is a registered trademark of Microsoft Corporation, Redmond, Washington). In yet another embodiment, the system runs in a host environment and a UNIX® server environment (UNIX is a registered trademark of X / Open Ltd., Reading, Berkshire, United Kingdom). In another embodiment, the system runs in an iOS® environment (iOS is a registered trademark of Cisco Systems, Inc., San Jose, California). In yet another embodiment, the system runs in a Mac OS® environment (Mac OS is a registered trademark of Apple Inc., Cupertino, California). In yet another embodiment, the system runs on Android® OS (Android is a registered trademark of Google Corporation, Inc., Montfort, California). In yet another embodiment, the system runs on Linux® OS (Linux is a registered trademark of Linus Torvalds, Boston, Massachusetts). The application is flexible and designed to operate in a variety of environments without compromising any key functionality. In some embodiments, the system includes multiple components distributed across a plurality of computing devices. One or more components are in the form of computer-executable instructions embodied in a computer-readable medium. The system and program are not limited to the specific embodiments described herein. Furthermore, the components of each system and program may be practiced independently and separately from other components and programs described herein. The components and programs may also be used in combination with other assemblies, packages, and programs.

[0034] Any element or step described in the singular and beginning with the word "a" or "an" should be understood to not exclude a plurality of elements or steps unless such exclusion is explicitly stated. Furthermore, references to "exemplary embodiments" or "an embodiment" of the invention are not intended to be construed as excluding the existence of additional embodiments that also contain the described features.

[0035] The terms "software" and "firmware" are interchangeable and include any computer program stored in memory for execution by a processor, including RAM memory, ROM memory, EPROM memory, EEPROM memory, and non-volatile RAM (NVRAM) memory. The memory types described above are merely examples and therefore do not limit the types of memory that can be used to store a computer program.

[0036] The term "immediate" means at least one of the following: the time of occurrence of the associated event, the time of measurement and collection of predetermined data, the time of data processing, and the time of response of a system to the event and the environment. Such activities and events occur substantially immediately.

[0037] The systems and programs are not limited to the specific embodiments described herein. Furthermore, components of each system and program may be practiced independently and separately from other components and programs described herein. Components and programs may also be used in combination with other assemblies, packages, and programs.

[0038] Figure 1 illustrates a block diagram of a system 100 for processing semiconductor wafers. In the silicon wafer manufacturing process, system 100 begins with a slicing machine 105. In an exemplary embodiment, the slicing machine 105 is a wire saw for cutting silicon material disks.

[0039] After the wafer is sliced ​​by the slicing machine 105, a first measurement device 110 analyzes the wafer, measuring data to generate a wafer profile. At this time, the wafer is unground, unetched, and unpolished. The first measurement device 110 provides measurement data from the ground wafer to a wafer surface analysis (WSA) computer device 115. In some embodiments, the first measurement device 110 uses a capacitive probe or a laser-based distance sensor to measure the wafer. Specifically, the WSA computer device 115 uses the post-slicing shape and GAPI RMS data to generate an in-plane deformation (IPD), nano-topography (NT), and shape distribution map of the silicon wafer. As used herein, GAPI RMS refers to a shape-based matrix, which is an index used to represent the smoothness of a wafer substrate.

[0040] The GAPI RMS can be calculated by the WSA computer device 115. First, the WSA computer device 115 loads raw measurement data, such as from the first measurement device 110. The raw measurement data includes thickness and lower (or front) profile. The WSA computer device 115 converts the raw data into several diameter line scan profiles. The number of diameter scan profiles can be 2, 4, 8 or more. The WSA computer device 115 calculates the least square of the best-fit thickness plane. The WSA computer device 115 calculates the original shape diameter scan profile by adding half the thickness (the thickness of the best-fit plane) to the lower profile. The WSA computer device 115 smooths the original shape diameter scan profile by using a moving average with a defined window size. The WSA computer device 115 uses a one-dimensional polynomial fit to calculate the ideal shape diameter scan profile using each original shape diameter scan profile. The WSA computer device 115 determines that the increment of the shape diameter scan profile is equal to the original shape diameter scan profile minus the ideal shape diameter scan profile.

[0041] The WSA computer device 115 calculates the weighted profile by measuring incremental shape variation and slope change within a defined moving window along the diameter direction. Threshold values ​​for capturing high variation and slope change are also defined. Incremental shape variation can be standard variation, variance, or range. Slope change means, for example, when the left slope multiplied by the right slope is negative. GAPI represents the gap between the original shape and the ideal shape, which is equal to the incremental shape diameter multiplied by the weighted profile. GAPI RMS is the root mean square of GAPI.

[0042] The WSA computer device 115 analyzes the wafer's measurement data to determine the wafer's profile after slicing. If the profile is determined to exceed any quality threshold, the WSA computer device 115 may determine that the slicing machine 105 or other devices need to be adjusted.

[0043] The next device in system 100 is a polisher 120, which can be single-sided or double-sided. Simultaneous double-sided polishing operates on both sides of a wafer, producing a wafer with a highly planarized surface. During polishing, the polisher 120 uses a wafer clamping device to hold the semiconductor wafer. The clamping device typically includes a pair of hydrostatic pads and a pair of grinding wheels. The pads and wheels are oriented relative to each other to hold the wafer between them in a vertical orientation. The hydrostatic pads advantageously create a fluid barrier between their respective pads and the wafer surface to hold the wafer, while the rigid pads do not physically contact the wafer during polishing. This reduces potential damage to the wafer from physical clamping and allows the wafer to move (rotate) tangentially relative to the pad surfaces with less friction. While this polishing process can improve the flatness and / or parallelism of the polished wafer surface, it can lead to a deterioration in the wafer surface morphology. To be clear, the misalignment of the hydrostatic pad and the grinding wheel clamping plane is known to cause this degradation. Polishing after grinding produces a highly reflective mirror-like wafer surface on the ground wafer, but this does not resolve the morphology degradation.

[0044] After the wafer is ground by the grinder 120, a second measurement device 125 analyzes the wafer, measuring data to generate a profile of the ground wafer. At this time, the wafer is unetched and unpolished. The second measurement device 125 provides the measurement data from the ground wafer to a wafer surface analysis (WSA) computer device 115. In some embodiments, the second measurement device 125 uses a capacitive probe or a laser-based distance sensor to measure the wafer. Specifically, the WSA computer device 115 uses the ground shape and GAPI (gap between original shape and ideal shape) RMS (root mean square) data to generate an in-plane deformation (IPD), nano-topography (NT), and shape distribution map of the silicon wafer.

[0045] The WSA computer device 115 analyzes the wafer's measurement data to determine the wafer's profile after polishing. If the profile is determined to exceed any quality threshold, the WSA computer device 115 may determine that the polishing machine 120 or other devices need to be adjusted.

[0046] System 100 may include a plurality of polishers 120, each polisher 120 polishing a wafer, but each wafer may be polished only once. In these embodiments, WSA computer device 115 tracks the polishing results of each of the plurality of polishers 120.

[0047] System 100 includes a plurality of post-polishing devices, such as, but not limited to, an etching device 130 for etching the polished wafer, a surface measuring device 135 for measuring the flatness of the surface of the etched wafer, a polishing device 140 for polishing the etched wafer, and a nano-morphology measuring device 145 for measuring the nano-morphology of the polished wafer. In other embodiments, other devices may be included in system 100.

[0048] The WSA computer device 115 includes a model of one of the devices in system 100, wherein the model is based on measurements of a wafer to simulate etching, polishing, and possibly grinding of the wafer to predict the polished surface of the wafer. The polished surface is similar to the surface measured by the nano-topography measurement device 145. As further described herein, the WSA computer device 115 generates the model based on a plurality of historical data from a plurality of manufactured wafers. The historical data is based on a comparison of the wafer at at least one of the first measurement device 110 (after slicing) or the second measurement device 125 (after grinding) and the wafer at the nano-topography measurement device 145 (after polishing).

[0049] The WSA computer device 115 generates a model for each system 100 it analyzes. For example, a factory may have more than one production line for manufacturing wafers. For each production line, the WSA computer device 115 generates a separate model. In some embodiments, where multiple slicing machines 105 or grinding machines 120 use the same post-grinding process, the WSA computer device 115 may use the same model.

[0050] Figure 2 is a flowchart illustrating an exemplary procedure 200 for evaluating a wafer using system 100 (shown in Figure 1). In an exemplary embodiment, the steps of procedure 200 are executed by WSA computer device 115 (shown in Figure 1).

[0051] Prior to procedure 200, at least one neural network model is established. The neural network model is trained using a plurality of historical images. A first neural network model is trained to receive a post-grinding or post-slicing shape image of a wafer and to determine a post-polished NT image from the input shape image. A second neural network model is trained to receive a post-grinding or post-slicing GAPI RMS image of a wafer and to determine an IPD image of a wafer. Both of these neural network models are trained using a plurality of historical images and a generative adversarial network (GAN).

[0052] The GAN architecture includes a generator model for outputting new plausible synthetic images and a discriminator model for classifying images as real (from the dataset) or fake (generated). The discriminator model is updated directly, while the generator model is updated via the discriminator model. Thus, two models are trained simultaneously in an adversarial process, where the generator attempts to better deceive the discriminator, and the discriminator strives to better identify fake images.

[0053] For the GAN model described herein, the generation of the output image depends on an input, in this case, a source image. The discriminator includes both a source image and a target image, and must determine whether the target is a credible transformation of the source image. The generator is trained via adversarial loss, which encourages the generator to generate credible images in the target domain. The generator is also updated via L1 loss measured between the generated image and the expected output image. This additional loss encourages the generator model to generate credible translations of the source image. The model input can be four-line scan data or eight-line scan data. Further discussion of training the model is described below.

[0054] Wafer processing 205 may include slicing by a slicing machine 105 and / or grinding by a grinding machine 120 (both shown in FIG. 2). After processing 205, at least one of the first measurement device 110 and the second measurement device 125 (both shown in FIG. 1) measures 210 the ground wafer and transmits the current post-processing measurement to the WSA computer device 115. The WSA computer device 115 calculates the GAPI RMS map from the current measurement 215 and calculates the GAPI RMS map from a predefined algorithm.

[0055] The WSA computer device 115 executes 220 the aforementioned neural network model to generate shape maps, such as polished NT maps and / or IPD maps. For the purposes of this invention, the neural network model can convert shape maps into polished NT maps or convert GAPI RMS maps into IPD maps. Next, the WSA computer device 115 calculates 225 predicted wafer properties based on the shape maps. These wafer properties may include, but are not limited to, average IPD, THA1010, and THA2525. THA1010 and THA2525 are nano-topography parameters calculated based on nano-topography maps. THA1010 is calculated by recording peak-to-valley differences within a 10 mm × 10 mm moving window that moves over the entire wafer and then using a specific percentile of this set of recorded values ​​as the THA1010 value. Percentile values ​​can vary and are typically specified by the end consumer. THA2525 is similar to THA1010, except that the window can be a 25 mm × 25 mm square or a circle with a diameter of 25 mm. Wafer properties are predicted to indicate the state of the wafer at the end of processing, such as those measured by the nano-topography measurement device 145.

[0056] The WSA computer device 115 compares the properties of the 230 wafer with one or more predetermined threshold values. In an example embodiment, the predetermined threshold values ​​are requirements for a suitable surface of the polished wafer. In an example embodiment, some of the predetermined threshold values ​​and / or requirements are based on user preferences from one or more users, such as the wafer manufacturer and / or the customer who purchases the wafer.

[0057] If the wafer properties are within tolerance 235, the WSA computer device 115 stores the data and moves to analyze the next wafer. The stored wafer properties can then be used to improve the neural network and / or detect one or more trends. If the wafer properties are not within tolerance 235, the WSA computer device 115 triggers an alarm and potentially adjusts 240 one or more devices, such as, but not limited to, a slicer 105, a grinder 120, an etching device 130, and a polishing device 140. In some embodiments, the WSA computer device 115 directly adjusts 240 of the device(s). In other embodiments, the WSA computer device 115 instructs another device to adjust 240 of the device(s). In yet another embodiment, the WSA computer device 115 instructs a user to adjust 240 of the device(s).

[0058] The WSA computer device 115 determines that the wafer is within tolerance 235, but also determines that one or more of the devices(s) are no longer properly adjusted. In these embodiments, the WSA computer device 115 may determine that the device is out of proper adjustment based on a current trend of one of a plurality of wafer post-processing detections. The WSA computer device 115 may identify the trend and determine that the device will need to be adjusted during a particular use or after a period of time. In these embodiments, the WSA computer device 115 may determine the next planned downtime period for the system 100. If the planned downtime period is before the device is expected to be out of proper adjustment, the WSA computer device 115 may schedule the device adjustment to occur during the planned downtime period. The WSA computer device 115 may determine when the device is expected to produce a wafer that exceeds the tolerance based on one or more predetermined thresholds, the amount of change in the post-processing results of each wafer, and a model.

[0059] The WSA computer device 115 generates a model based on a plurality of historical data, including past post-slicing measurements performed by the first measurement device 110, post-grinding measurements performed by the second measurement device 125, and past post-polishing measurements performed by the nano-topography measurement device 145. In an example embodiment, the WSA computer device 115 generates a model by comparing post-slicing / post-grinding images and post-polishing images of the wafer to determine how the system 100 alters the wafer during wafer processing. In some embodiments, the WSA computer device 115 stores a general model trained on a specific production line (system 100) using historical inspection data from that production line. In other embodiments, the WSA computer device 115 generates the model entirely from historical data of that production line. In some further embodiments, the model is continuously updated based on measurement data from the nano-topography measurement device 145 of the production line while the production line is in operation. This allows the model to most accurately model the current production line (system 100). In other embodiments, the model is updated or calibrated only every six months or other predetermined time intervals. This embodiment is optimal when other devices in system 100 remain unchanged or do not require periodic recalibration. In some embodiments, the model is updated and calibrated for the current state of the production line whenever a device is replaced, calibrated, or otherwise changed.

[0060] Although the system 100 and program 200 are described with respect to a semiconductor wafer manufacturing assembly line, those skilled in the art will understand that the present invention can be used with other assembly lines. In other embodiments, the system 100 will be considered as an assembly line 100 for producing a product. The assembly line includes a first device 105, a first inspection station 110, a computer device 115, a second device 120, a second inspection station 125, and potentially a third device 140 and a third inspection station 145. In other embodiments, the computer device 115 stores a model for simulating a portion of the assembly line 100 in at least one memory device. The computer device 115 receives scan data of a first inspection of one of the assembled products. The first inspection is performed at the first inspection station 110 (or 125) of the assembly line 100, following the first device 105 (or 120) in the assembly line 100. The computer device 115 uses the scan data as input to execute model 220 to produce a final outline and / or attributes of one of the products.

[0061] The computer device 115 compares the final profile 230 with one or more threshold values. The computer device 115 determines whether the final profile 235 exceeds one or more tolerances due to exceeding at least one of the one or more threshold values. If it is determined that the final profile exceeds at least one of the one or more threshold values, the computer device 115 causes adjustment 240 of the first device 105 (or 120).

[0062] The computer device 115 can generate a model simulating a portion of an assembly line 100 based on a plurality of inspection data. The model generates the final outline of a product, simulating the actual outline of the product when it arrives at a second inspection station 125. In some further embodiments, the second inspection station 125 is located after the assembly line 100 is completed. In some embodiments, the plurality of inspection data includes a first plurality of scan data of a plurality of individual products at a first inspection station 110 and a second plurality of scan data of a plurality of individual products at a second inspection station 125. In still some further embodiments, the computer device 115 receives scan data of a second inspection of a product assembled at the second inspection station 125. The computer device 115 compares the second inspection scan data with the final outline. The computer device 115 adjusts the model based on the comparison.

[0063] In other embodiments, computer device 115 generates a model for simulating a portion of assembly line 100. The model generates the final outline and attributes of the product, simulating the actual outline of the product when it arrives at final inspection station 145. The model may receive scan data from a first inspection station 110 after a first processing station 105 and / or from a second inspection station 125 after a second processing station 120. Then, computer device 115 generates the outline of the product based on inputs from both inspection stations 110 and 125.

[0064] If it is determined that the final profile exceeds at least one of one or more threshold values, the computer device 115 analyzes a plurality of previous tests to determine a trend. The computer device 115 predicts, based on the trend, whether a subsequent test of a subsequent product is likely to exceed at least one of one or more threshold values. The computer device 115 adjusts the first device 105 or the second device 120 based on the trend.

[0065] Figure 3 is a simplified block diagram of an exemplary system 300 used to evaluate a wafer according to system 100 (shown in Figure 1) using program 200 (shown in Figure 2). In an exemplary embodiment, system 300 is used to analyze the polished wafer to determine whether it will be within tolerance after polishing. In addition, system 300 includes a real-time data analysis and classification computer system of wafer surface analysis (WSA) computer device 310 (also referred to as a WSA server), which is configured to analyze the wafer and predict future states based on the analysis.

[0066] A measurement device 305 is configured to scan the surface of a wafer to generate a profile of the wafer. More specifically, the measurement device 305 scans the nanometer topography of the wafer and communicates with a WSA computer device 310. The measurement device 305 is connected to the WSA computer device 310 via various wired or wireless interfaces, including but not limited to a network (such as a local area network (LAN) or a wide area network (WAN)), dial-in connection, cable modem, internet connection, wireless, and dedicated high-speed integrated services digital network (ISDN) line. The measurement device 305 receives data about the surface of a wafer and reports the data to the WSA computer device 310. In other embodiments, the measurement device 305 communicates with one or more user terminal systems 325, and the user terminal systems 325 route measurement data to the WSA computer device 310 in real time or near real time. In some embodiments, a first measurement device 305 measures one side of the wafer, and a second measurement device 305 measures the other side of the wafer. In exemplary embodiments, the measurement device 305 is similar to the first measurement device 110 (shown in FIG. 1), the second measurement device 125 (shown in FIG. 1), and the nano-topography measurement device 145 (shown in FIG. 1).

[0067] As described in more detail above, the WSA server 310 is programmed to analyze the wafer to predict the nano-morphology of the wafer surface after polishing, allowing the system 300 to respond to changes that would cause the wafer to rapidly exceed tolerances. The WSA server 310 is programmed to determine the current state of a wafer; (2) predict a post-processing state of the wafer based on the current state and a model; and (3) determine whether adjustments to the wafer processing apparatus are needed based on the wafer post-processing state and one or more predetermined thresholds. In an example embodiment, the WSA server 310 is similar to the wafer surface analysis computer device 115 (shown in FIG. 1).

[0068] The user terminal system 325 is a computer that includes a web browser or a software application that enables the user terminal system 325 to communicate with the WSA server 310 via the Internet, a local area network (LAN), or a wide area network (WAN). In some embodiments, the user terminal system 325 is communicatively coupled to the Internet through a variety of interfaces, including but not limited to at least one of a network (such as the Internet, a LAN, a WAN, or an Integrated Services Digital Network (ISDN)), a dial-up connection, a digital subscriber line (DSL), a cellular telephone connection, a satellite connection, and a cable modem. The user terminal system 325 may be any device capable of accessing a network (such as the Internet), including but not limited to a desktop computer, a laptop computer, a digital assistant (PDA), a cellular telephone, a smartphone, a tablet computer, a tablet phone, or other web-based connectable devices.

[0069] A database server 315 is communicatively coupled to a database 320 storing data. In one embodiment, database 320 is a database containing historical data and models. In some embodiments, database 320 is stored remotely from WSA server 310. In some embodiments, database 320 is distributed. In an example embodiment, database 320 can be accessed via client system 325 by logging into WSA server 310.

[0070] Figure 4 illustrates an exemplary configuration of the user terminal system 325 (shown in Figure 3). The user computer device 402 is operated by a user 401. The user computer device 402 may include, but is not limited to, a first measurement device 110, a second measurement device 125, a wafer surface analysis computer device 115, a nano-topography measurement device 145 (all shown in Figure 1), a measurement device 305, a WSA computer device 310, and the user terminal system 325 (all shown in Figure 3). The user computer device 402 includes a processor 405 for executing instructions. In some embodiments, the executable instructions are stored in a memory region 410. The processor 405 may include one or more processing units (e.g., in a multi-core configuration). The memory region 410 is any means that allows storage and retrieval of information such as executable instructions and / or variable data. The memory region 410 may include one or more computer-readable media.

[0071] The user computer device 402 also includes at least one media output component 415 for presenting information to the user 401. The media output component 415 is any component capable of conveying information to the user 401. In some embodiments, the media output component 415 includes an output adapter (not shown), such as a video adapter and / or an audio adapter. An output adapter is operatively coupled to the processor 405 and operatively coupled to an output device, such as a display device (e.g., a cathode ray tube (CRT), liquid crystal display (LCD), light-emitting diode (LED) display, or "e-ink" display) or an audio output device (e.g., a speaker or headphones). In some embodiments, the media output component 415 is configured to present a graphical user interface (e.g., a web browser and / or a client application) to the user 401. A graphical user interface may include, for example, an interface for viewing the results of analysis of one or more wafers. In some embodiments, the user computer device 402 includes an input device 420 for receiving input from a user 401. The user 401 may use the input device 420 to select a wafer to view its analysis, but is not limited thereto. The input device 420 may include, for example, a keyboard, an indicator device, a mouse, a stylus, a touch-sensitive panel (e.g., a touchpad or a touchscreen), a gyroscope, an accelerometer, a position detector, a biometric input device, and / or an audio input device. A single component such as a touchscreen may serve as both an output device and an input device 420 of the media output component 415.

[0072] The user computer device 402 may also include a communication interface 425, which is communicatively coupled to a remote device such as the WSA server 310 (shown in FIG3). The communication interface 425 may include, for example, a wired or wireless network adapter and / or a wireless data transceiver for use with a mobile telecommunications network.

[0073] For example, computer-readable instructions for providing a user interface to user 401 via media output component 415 and, where appropriate, receiving and processing input from input device 420, are stored in memory area 410. Among other possibilities, a user interface may also include a web browser and / or a client application. The web browser enables a user, such as user 401, to display and interact with media and other information typically embedded in a webpage or website from WSA server 310. A client application allows user 401 to interact with, for example, WSA server 310. For example, instructions may be stored from a cloud service, and the output of the execution of instructions may be sent to media output component 415.

[0074] The processor 405 executes computer-executable instructions for carrying out the present invention. In some embodiments, the processor 405 is transformed into a special-purpose microprocessor by executing computer-executable instructions or by being otherwise programmed.

[0075] Figure 5 illustrates an exemplary configuration of the server system 310 shown in Figure 3. The server computer device 501 may include, but is not limited to, a WSA computer device 115 (shown in Figure 1), a database server 315, and a WSA server 310 (both shown in Figure 3). The server computer device 501 also includes a processor 505 for executing instructions. Instructions may be stored in a memory region 510. The processor 505 may include one or more processing units (e.g., in a multi-core configuration).

[0076] The processor 505 is operatively coupled to a communication interface 515, enabling the server computer device 501 to communicate with a remote device such as another server computer device 501, another WSA server 310, or a client system 325 (shown in FIG. 3). For example, the communication interface 515 may receive requests from the client system 325 via the Internet, as illustrated in FIG. 3.

[0077] The processor 505 may also be operatively coupled to a storage device 534. The storage device 534 is any computer operating hardware suitable for storing and / or retrieving data (such as, but not limited to, data associated with database 320 (shown in FIG. 3)). In some embodiments, the storage device 534 is integrated into a server computer device 501. For example, the server computer device 501 may include one or more hard drives as storage devices 534. In other embodiments, the storage device 534 is external to the server computer device 501 and is accessible by a plurality of server computer devices 501. For example, the storage device 534 may include a storage area network (SAN), a network attached storage (NAS) system, and / or multiple storage units, such as hard drives and / or solid-state drives configured as a redundant array of low-cost disks (RAID).

[0078] The processor 505 may be operatively coupled to the storage device 534 via a storage interface 520. The storage interface 520 may include, for example, an Advanced Technology Attachment (ATA) adapter, a Serial ATA (SATA) adapter, a Small Computer System Interface (SCSI) adapter, a RAID controller, a SAN adapter, a network adapter, and / or any other components that provide the processor 505 with access to the storage device 534.

[0079] Processor 505 executes computer-executable instructions for carrying out the present invention. In some embodiments, processor 505 is transformed into a special-purpose microprocessor by executing computer-executable instructions or by being otherwise programmed. For example, processor 505 is programmed to have instructions such as those illustrated in FIG2.

[0080] Figure 6 is a diagram illustrating an exemplary line scan procedure 600 executed by a measurement device 305 (shown in Figure 3). In an exemplary embodiment, procedure 600 is executed by a first measurement device 110, a second measurement device 125, and a nano-topography measurement device 145 (all shown in Figure 1) and procedure 200 (shown in Figure 2), which are part of system 100.

[0081] According to the line scan procedure 600, the wafer W is supported by one or more support pins 603 in contact with a first surface 605A of the wafer. As illustrated by a comparison between a shape of the wafer in a weightless state (indicated by component symbol 607) and a shape of the wafer in a supported state (indicated by component symbol 609), the shape of the supported wafer 609 is deflected according to gravity and the mass of the wafer W. The measuring device 305 includes a first electrostatic capacitive sensor 621A for measuring a plurality of distances (e.g., "distance B") between the first sensor 621A and a first surface 605A (e.g., the front surface) along a diameter of the supported wafer 609. Similarly, the measurement device 305 includes a second capacitive sensor 621B for measuring a plurality of distances (e.g., "distance F") between the second sensor 621B and a second surface 605B (e.g., a back surface) along a diameter of the supported wafer 609. The acquired data includes a line scan dataset corresponding to the diameter. The line scan dataset includes a plurality of distances measured by the first sensor 621A along the diameter of the supported wafer 609 and a plurality of distances measured by the second sensor 621B along the diameter of the supported wafer 609. The line scan dataset indicates the wafer profile along the diameter.

[0082] Figures 7A and 7B further illustrate an illustrative line scan procedure 600 (shown in Figure 6). Figures 7A and 7B illustrate a line scan procedure 600 performed by a measurement device 305 to obtain a plurality of line scan datasets, each indicating a wafer profile along a specific diameter. As illustrated in Figure 7A, a first line scan is performed along a first diameter of the wafer (indicated by arrow 701). Specifically, a first sensor 621A moves in a plane above a first surface 605A in a first direction along the first diameter of the wafer. The first sensor 621A measures the distance between the first sensor 621A and the first surface 605A of the wafer at predefined intervals (i.e., pitch R, measurement frequency). The predefined intervals are illustrated in Figure 7A as markings on the surface of the wafer W. For example, the first sensor 621A may measure distances along the first diameter of the wafer at intervals of 1 mm or 2 mm. The second sensor 621B is similarly moved in a plane below the second surface 605B in a first direction to measure the distance between the second sensor 621B and the second surface 605B along the first diameter of the wafer. The first diameter of the wafer can be defined to vary depending on a reference point. For example, in the illustrated program, the first diameter is represented by a notch N located on the periphery of the wafer.

[0083] As illustrated in FIG. 7B, after the first line scan 701 is completed, the wafer W is rotated (indicated by arrow 709). Specifically, a rotating stage 705 positioned below the support pin 603 is raised to lift the wafer W to a position above the support pin 603 (indicated by component symbol 707). While the wafer is supported in the raised position 707, the rotating stage rotates. Thus, the wafer rotates by a certain degree (θ). The rotating stage 705 is lowered and the rotated wafer is repositioned on the support pin 603. The position of the support pin 603 relative to the second surface of the wafer is indicated by a hidden line in FIG. 7A and FIG. 7B. Subsequently, a line scan along one of the second diameters of the wafer is performed (indicated by arrow 715). According to the illustrated procedure, the first and second sensors 621A and 621B move in planes corresponding to the first and second surfaces 605A and 605B, respectively, along a second direction (e.g., opposite to the first direction) along one of the second diameters of the wafer. As described above in conjunction with the first line scan 701, the first and second sensors 621A and 621B measure the distances between the sensors 621A and 621B and the first and second surfaces 605A and 605B of the wafer at predefined intervals along the second diameter of the wafer. Rotation 709 and line scan operations 701 and 715 are repeated to obtain each of a plurality of line scan datasets.

[0084] The measurement device 305 appropriately uses a self-mass compensation algorithm to determine the wafer shape 607 in a weightless state. The self-mass compensation determines the wafer shape based on a line scan dataset, wafer density, an elastic constant, wafer diameter, and the position of the support pin 603. In one embodiment, the measurement device 305 measures one or more wafer parameters based on the wafer shape. The wafer parameters may include one or more of the following: warpage, bending, TTV (total thickness variation), and / or GBIR (global back surface ideal range).

[0085] Referring to FIG. 8A, warpage and bending are determined generally relative to a reference plane. The reference plane is defined based on the contact point between the support pin 603 and the wafer surface 605A. Specifically, warpage is defined as the absolute value of the difference between the maximum and minimum deviations of the intermediate region from the reference plane. The intermediate region is a trajectory of points equidistant from the wafer's front surface 605B and back surface 605A. Bending is defined as the amount of deviation from the reference plane at the wafer center. Referring to FIG. 8B, GBIR and TTV reflect the linear thickness variation of the wafer and can be calculated based on the difference between a maximum and a minimum distance from the wafer's back surface to the reference plane. For example, the measurement device 305 can obtain four line scan data sets as illustrated in FIG. 9A or eight line scan data sets as illustrated in FIG. 9B. Each line scan data set indicates a diameter profile of the wafer.

[0086] Referring again to the system 100 illustrated in FIG1, data obtained by measuring devices 110, 125, and 145 for measuring the nanomorphology of a wafer, such as that ground by the polisher 120, is transmitted to the WSA computer device 115. For example, a line scan dataset and / or a determined wafer shape may be transmitted to the WSA computer device 115. The WSA computer device 115 receives the scan data and executes computer-executable instructions for performing a plurality of operations for processing the received scan data, as described herein. Specifically, the WSA computer device 115 predicts a polished nanomorphology of the wafer based on the received scan data. In some embodiments, the WSA computer device 115 determines a polishing parameter based on the predicted nanomorphology of the wafer. The operation of the polisher 120 is adjusted accordingly.

[0087] The WSA computer device 115 can access a feedback program for processing received scan data. The received scan data may include a line scan dataset and / or a determined wafer shape of the polished wafer. Specifically, the WSA computer device 115 predicts a nano-morphology of the polished wafer based on received warp data. The wafer nano-morphology is predicted rather than actually measured because the wafer has not yet undergone polishing when the first measuring device 110 or the second measuring device 125 measures the wafer. The WSA computer device 115 determines one or more polishing parameters based on the predicted nano-morphology of the wafer. In one embodiment, the WSA computer device 115 determines a shift parameter. The shift parameter indicates a magnitude and a direction for moving the pair of grinding wheels to reduce nano-morphology degradation caused by wheel misalignment. In another embodiment, the WSA computer device 115 additionally or alternatively determines a tilt parameter. The tilt parameter indicates an angle used to position the pair of grinding wheels relative to a wafer to reduce nanomorphic degradation caused by wheel misalignment.

[0088] The operation of the grinder 120 or other stations is adjusted based on determined parameters. For example, in the case of the grinder 120, the grinding wheel can be adjusted as specified by determined displacement and / or tilt parameters. In one embodiment, the grinding wheel is adjusted based on determined displacement and / or tilt parameters and a previously defined compensation amount. In one embodiment, the grinder 120 is configured to receive determined grinding parameters, and one or more components of the grinder 120 are adjusted based on the determined grinding parameters. In another embodiment, the determined grinding parameters are provided to an operator, and the operator configures the grinder 120 to adjust one or more components of the grinder 120 based on the determined grinding parameters.

[0089] Figure 10A illustrates the use of a trained neural network model to convert a polished shape image into a predicted polished NT image. Figure 10B illustrates the use of a trained neural network model to convert a GAPI RMS image into a predicted IPD image. A GAN AI model 1005 (which may be a neural network or other artificial intelligence or machine learning-based model) receives an input image 1010 and outputs a predicted output image 1015. The input image 1010 may contain the shape image shown in Figure 10A or the GAPI RMS image shown in Figure 10B.

[0090] The GAN AI model 1005 is trained on large datasets to correlate the input data 1010 with the output image 1015. In the first example shown in Figure 10A, post-polishing (or post-slicing) line data (such as 4-line or 8-line scans) is obtained by a first measurement device 110 or a second measurement device 125 (both shown in Figure 1). The line data is used to create a shape map. The shape map is used as one of the input images 1010 for the model 1005. The model 1005 then outputs a predicted post-polishing nano-topography (NT) image as an output image 1015. In some embodiments, the trained model 1005 provides a correlation between the post-polishing 4-line or 8-line scan data 1010 and the NT image 1015, where R² is approximately 80%.

[0091] In the second example shown in FIG10B, a GAPI RMS map is obtained by either a first measurement device 110 or a second measurement device 125 (both shown in FIG1). The GAPI RMS map is used as one of the input images 1010 of model 1005. Then, model 1005 outputs a predicted shape-based in-plane deformation (IPD) map as an output image 1015. In some embodiments, the trained model 1005 provides one of the correlations between the GAPI RMS map 1010 and the IPD map 1015, where R² is approximately 90%.

[0092] Once both the NT and IPD charts are available, the WSA computer device 310 can calculate different parameters, such as, but not limited to, THA1010, THA2525, average IPD, etc. The WSA computer device 310 can use these parameters to optimize the grinding, slicing and polishing processes during the manufacturing of silicon wafers.

[0093] Figure 11A illustrates images of wafer shape. The first image is an input image 1105, specifically, a data set image after smooth polishing. The second image is a live image 1110, which is a measured wafer after actual polishing. Live image 1110 can be measured by nano-topography measurement device 145 (shown in Figure 1). The third image is a predicted NT image 1115.

[0094] Figure 11B illustrates an exemplary graph comparing the current image 1110 and the predicted NT map 1115 (both shown in Figure 11A). In this example, TH2525 is calculated for both the current image 1110 and the predicted NT map 1115. The graph in Figure 11B plots the correlation between the current image 1110 and the predicted NT map 1115 based on the calculated TH2525. The correlation plot shows an R-squared value of approximately 0.788.

[0095] Figure 12A illustrates images of wafer shape. The first image is an input image 1205, specifically, a data set image after filtering and polishing. The second image is a live image 1210, which is a measured wafer after actual polishing. Live image 1210 can be measured by nano-topography measurement device 145 (shown in Figure 1). The third image is a predicted NT image 1215.

[0096] Figure 12B illustrates an exemplary graph comparing the current image 1210 and the predicted NT map 1215 (both shown in Figure 12A). In this example, TH2525 is calculated for both the current image 1210 and the predicted NT map 1215. The graph in Figure 12B plots the correlation between the current image 1210 and the predicted NT map 1215 based on the calculated TH2525. The correlation plot shows an R-squared value of approximately 0.829.

[0097] Figure 13A illustrates images of the wafer shape. The first image is an input image 1305, specifically a GAPI RMS image. The second image is a live image 1310, which is an actual polished and measured wafer. The live image 1310 can be measured by a nano-topography measurement device 145 (shown in Figure 1). The third image is a predicted IPD image 1315.

[0098] Figure 13B illustrates an exemplary graph comparing the current image 1310 and the predicted IPD map 1315 (both shown in Figure 13A). In this example, TH2525 is calculated for both the current image 1310 and the predicted IPD map 1315. The graph in Figure 13B plots the correlation between the current image 1310 and the predicted IPD map 1315 based on the calculated IPD. The correlation plot shows an R-squared value of approximately 0.930.

[0099] A computer device (such as a wafer surface analysis computer device 115 (shown in FIG. 1)) includes at least one processor 505 (both shown in FIG. 5) communicating with at least one memory device 510. The WSA computer device 115 is programmed to store in at least one memory device 510 a model for converting shape maps to simulate a portion of an assembly line 100 (shown in FIG. 1). The WSA computer device 115 receives scan data of a first inspection of one of the assembled products. The first inspection is performed at a first inspection station (also referred to as a first measuring device 110, which may be a first measuring device 110 or a second measuring device 125 (both shown in FIG. 1)). The first inspection station is located in the assembly line 100, after one of the first devices 105 or 120 (both shown in FIG. 1) in the assembly line 100.

[0100] The WSA computer device 115 also generates a shape drawing from the scanned data of the first detection, and uses the shape drawing as an input to execute a model to generate a final shape drawing of the product. The WSA computer device 115 compares the final shape drawing with one or more threshold values, and determines whether the final shape drawing exceeds at least one of the one or more threshold values. If it is determined that the final shape drawing exceeds at least one of the one or more threshold values, the WSA computer device 115 causes an adjustment to the first device.

[0101] The WSA computer device 115 can also calculate one or more product attributes from the final shape drawing. The WSA computer device 115 compares one or more product attributes with one or more threshold values. If one or more product attributes exceed one or more threshold values, the WSA computer device 115 causes an adjustment to the first device.

[0102] The shape image is appropriately one of a post-polishing shape image and a GAPI RMS (root mean square) image. Thus, the final shape image is one of a post-polished nanomorphology image and an in-plane deformation (IPD) image. The model is a generative adversarial network (GAN) artificial intelligence model trained with historical images of partially and fully processed products. The model transforms an input shape image into a simulation of the final version of the product's shape image.

[0103] The shape map is a first shape map, and the final shape map is a first final shape map. In these embodiments, the WSA computer device 115 generates a second shape map from the self-scanning data. The second shape map is generated via a method different from that of the first shape map. The WSA computer device 115 uses the second shape map as an input to execute a model to generate a second final shape map of the product. The WSA computer device 115 calculates one or more product attributes from the first final shape map and the second final shape map. The WSA computer device 115 compares one or more product attributes with one or more threshold values. If one or more product attributes exceed one or more threshold values, the WSA computer device 115 causes an adjustment of the first device. In these embodiments, the first shape map is a post-grinding shape map, the first final shape map is a post-polished nanomorphology map, the second shape map is a GAPI RMS (root mean square) map, and the second final shape map is an in-plane deformation (IPD) map.

[0104] The scan data is either four-line scan data or eight-line scan data of the product. The product is a semiconductor wafer as described above, and the first device is either a polishing machine or a wafer cutter. The first inspection station includes a nano-morphology measurement device.

[0105] The WSA computer device 115 generates one or more adjustments to the first device based on a comparison of the final shape drawing with one or more threshold values ​​and the model. The WSA computer device 115 transmits one or more adjustments to a user and at least one of the first devices.

[0106] If it is determined that the final shape diagram exceeds at least one of one or more threshold values, the WSA computer device 115 analyzes a plurality of previous tests to determine a trend. Then, the WSA computer device 115 predicts, based on the trend, whether a subsequent test of a subsequent product is likely to exceed at least one of one or more threshold values. Additionally, the WSA computer device 115 adjusts the first device based on the trend.

[0107] The technical solution implemented by the system to solve the technical problem may include at least one of the following: (i) improved analysis of the wafer surface; (ii) reduced material loss due to faults or misalignment; (iii) increased speed of wafer analysis; (iv) increased accuracy of wafer analysis; (v) reduced unnecessary adjustments to the polishing machine; (vi) reduced false alarms and false negatives; and (vii) updated analysis for individual production line calibrations.

[0108] The computer-implemented method may include additional, fewer, or alternative actions, including those discussed elsewhere herein. The method may be implemented via one or more local or remote processors, transceivers, servers, and / or sensors (such as processors, transceivers, servers, and / or sensors installed in or associated with smart infrastructure or remote servers) and / or via computer-executable instructions stored on one or more non-transitory computer-readable media.

[0109] In addition, a computer system may include additional, fewer, or alternative functionalities, including those discussed elsewhere herein. A computer system may include or be implemented via computer-executable instructions stored on or on one or more non-transitory computer-readable media.

[0110] Supervised or unsupervised machine learning can be used to train a processor or processing element, and the machine learning program can employ a neural network, which can be a convolutional neural network, a deep learning neural network, a reinforced or enhanced learning module or program, or a combination learning module or program that learns in two or more domains or regions of interest. Machine learning can involve identifying and recognizing patterns in existing data to facilitate predictions of subsequent data. Models can be generated based on exemplary inputs to make effective and reliable predictions for novel inputs.

[0111] Additionally or alternatively, the machine learning program can be trained by inputting sample datasets or specific data, such as images, object statistics and information, historical estimates, and / or actual repair costs. The machine learning program can utilize deep learning algorithms, which can focus primarily on pattern recognition and can be trained after processing multiple instances. The machine learning program may include Bayesian programming (BPL), speech recognition and synthesis, image or object recognition, optical character recognition, and / or natural language processing (individually or in combination). The machine learning program may also include natural language processing, semantic analysis, automated reasoning, and / or machine learning.

[0112] Supervised and unsupervised machine learning techniques can be used. In supervised machine learning, a processing element may include exemplary inputs and their associated outputs, and may attempt to discover general rules that map inputs to outputs, such that when subsequent novel inputs are provided, the processing element can accurately predict the correct output based on the discovered rules. In unsupervised machine learning, the processing element may need to find its own structure in unlabeled exemplary inputs. In one embodiment, machine learning techniques can be used to extract data about the nanomorphology of a wafer surface to predict future states.

[0113] Based on such analysis, the processing element can learn how to identify characteristics and patterns that may then be applied to the analysis of image data, model data, and / or other data. For example, the processing element can learn to identify trends prior to a grinder dealignment based on a comparison of post-grinding and post-polishing measurements. The processing element can also learn how to identify trends that may not be easily understood, such as trends prior to a grinder dealignment, based on the collected scan data.

[0114] The methods and systems can be implemented using computer programming or engineering techniques that include computer software, firmware, hardware, or any combination or subset thereof. As disclosed above, at least one technical problem with prior art systems is the need for a system that analyzes data in a cost-effective and reliable manner to predict nanoscale morphology. The systems and methods described herein address this technical problem. Furthermore, at least one of the technical solutions implemented by this system to overcome the technical problem may include: (i) improved analysis of wafer surfaces; (ii) reduced material loss attributable to faults or misalignment; (iii) increased speed of wafer analysis; (iv) increased accuracy of wafer analysis; and (v) updated analysis for individual production line calibrations.

[0115] The described method and system can be implemented using computer programming or engineering techniques comprising any combination or subset thereof, including computer software, firmware, hardware, or the like, wherein the technical effect can be achieved by performing at least one of the following steps: (a) storing a model for simulating a portion of an assembly line in at least one memory device; (b) receiving scan data of a first inspection of an assembled product, wherein the first inspection is located at a first inspection station in the assembly line following a first device in the assembly line; (c) using the scan data as input to execute the model to generate a final profile of the product; (d) comparing the final profile with one or more threshold values; (e) determining whether the final profile exceeds at least one of the one or more threshold values; (f) if it is determined that the final profile exceeds at least one of the one or more threshold values, causing an adjustment to the first device; (g) generating a model for simulating a portion of an assembly line based on a plurality of inspection data of the assembly line, wherein the assembly line includes a second inspection station following a second device in the assembly line, and wherein the model is generated The final profile of the product, which simulates an actual profile of the product when it arrives at the second inspection station, wherein the second inspection station is located after the assembly line is completed, wherein the plurality of inspection data includes a plurality of first scan data of a plurality of individual products at the first inspection station and a plurality of second scan data of a plurality of individual products at the second inspection station; h) receiving scan data of a second inspection of a product assembled at the second inspection station; i) comparing the scan data of the second inspection with the final profile; j) adjusting the model based on the comparison; k) generating one or more adjustments to the first device based on a comparison of the final profile with one or more threshold values ​​and the model; l) transmitting one or more adjustments to at least one of the first devices to a user; and m) if it is determined that the final profile exceeds at least one of one or more threshold values, then performing at least one of the following steps: i) analyzing a plurality of previous inspections to determine a trend; ii) predicting based on the trend whether a subsequent inspection of a subsequent product is likely to exceed at least one of one or more threshold values; and iii) adjusting the first device based on the trend.

[0116] The method may be implemented via one or more local or remote processors, transceivers, servers and / or sensors (such as processors, transceivers, servers and / or sensors installed in a vehicle or mobile device or associated with smart infrastructure or remote servers) and / or via computer-executable instructions stored on one or more non-transitory computer-readable media. Additionally, the computer system discussed herein may include additional, fewer or alternative functionalities, including those discussed elsewhere herein. The computer system discussed herein may include or be implemented via computer-executable instructions stored on one or more non-transitory computer-readable media.

[0117] As used herein, the term "non-transitory computer-readable media" is intended to mean any tangible computer-based device implemented in any way or by any technique for short-term and long-term storage of information (such as computer-readable instructions, data structures, program modules and submodules, or other data in any device). Therefore, the methods described herein can be encoded as executable instructions embodied in a tangible non-transitory computer-readable medium, including but not limited to a storage device and / or a memory device. When executed by a processor, these instructions cause the processor to perform at least a portion of the methods described herein. Furthermore, as used herein, the term "non-transitory computer-readable media" includes all tangible computer-readable media, including but not limited to non-transitory computer storage devices (including but not limited to volatile and non-volatile media) and removable and non-removable media (such as firmware, physical and virtual storage), CD-ROMs, DVDs, and any other digital source (such as a network or the Internet), as well as digital components yet to be developed, with the sole exception of a transient propagation signal.

[0118] This written description uses examples to illustrate various implementation schemes (including the best mode) and also enables any person skilled in the art to practice various implementation schemes, including making and using any device or system and performing any incorporated method. The patentable scope of this invention is defined by the claims of the invention and may include other examples that may occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that are no different from the literal language of the claims, or if such other examples contain equivalent structural elements that are not substantially different from the literal language of the claims.

[0119] When introducing elements of the present invention or its embodiments(s), the articles "a," "an," "the," and "said" are intended to mean the presence of one or more elements. The terms "comprising," "including," "containing," and "having" are intended to be inclusive and mean that additional elements may be present in addition to those listed. The use of terms indicating a particular orientation (e.g., "top," "bottom," "side," etc.) is for ease of description and does not require any particular orientation of the described item.

[0120] Since various changes can be made to the above-described structure and method without departing from the scope of the present invention, all matters contained in the above description and shown in the accompanying drawings should be interpreted as illustrative rather than limiting. [Simplified Explanation of the Diagram]

[0010] Figure 1 illustrates a block diagram of a system for processing semiconductor wafers according to an embodiment.

[0011] Figure 2 is a flowchart illustrating one of the exemplary procedures for evaluating a wafer using the system shown in Figure 1.

[0012] Figure 3 is a simplified block diagram of an exemplary system used to evaluate a wafer according to the system shown in Figure 1 using the procedure shown in Figure 2.

[0013] Figure 4 illustrates an exemplary configuration of one of the user terminal computer devices shown in Figure 3.

[0014] Figure 5 illustrates an exemplary configuration of the server system shown in Figure 3.

[0015] Figure 6 is a diagram illustrating an example line scanning procedure performed by a measuring device.

[0016] Figures 7A and 7B are further illustrations of the exemplary line scan procedure shown in Figure 6.

[0017] Figures 8A and 8B are side views of a wafer.

[0018] Figures 9A and 9B are top side views of a wafer, which illustrate the scan lines obtained for the wafer.

[0019] Figure 10A illustrates the use of a trained neural network model to convert a polished shape map into a predicted polished NT map.

[0020] Figure 10B illustrates the use of a trained neural network model to convert a GAPI RMS graph into a predicted IPD graph.

[0021] Figure 11A shows an image of the wafer shape.

[0022] Figure 11B shows an example chart comparing the live image with the predicted NT map shown in Figure 11A.

[0023] Figure 12A shows an image of the wafer shape.

[0024] Figure 12B shows an example chart comparing the live image with the predicted NT map shown in Figure 12A.

[0025] Figure 13A shows an image of the wafer shape.

[0026] Figure 13B shows an example chart comparing the live image with the predicted IPD plot shown in Figure 13A.

[0027] In several views of the drawing, the corresponding component symbol indicates the corresponding part.

Claims

1. A computer device comprising at least one processor communicating with at least one memory device, wherein the at least one processor is programmed to: store in the at least one memory device a model for converting a shape image to simulate a portion of an assembly line, wherein the model is a generative adversarial network (GAN) artificial intelligence model; receive scan data of a first inspection of an assembled product, wherein the first inspection is performed at a first inspection station in the assembly line following a first device in the assembly line, wherein the first device is a grinder; generate a shape image from the scan data of the first inspection; execute the model using the shape image as an input to generate a final shape image of the product; compare the final shape image with one or more threshold values; determine whether the final shape image exceeds at least one of the one or more threshold values; and if the determination that the final shape image exceeds at least one of the one or more threshold values ​​is made, cause the grinder to be adjusted.

2. The computer device of claim 1, wherein the at least one processor is further programmed to: calculate one or more product attributes from the final shape drawing; compare the one or more product attributes with the one or more threshold values; and if the one or more product attributes exceed the one or more threshold values, cause an adjustment to the first device.

3. The computer device of claim 1, wherein the shape image is a ground shape image, and wherein the final shape image is a polished nanomorphological image.

4. The computer device of claim 1, wherein the shape diagram is a GAPI RMS (root mean square) diagram, and wherein the final shape diagram is an in-plane deformation (IPD) diagram.

5. The computer device as requested in claim 1, wherein the model converts an input shape drawing into a simulation of the shape drawing of a final version of the product.

6. The computer device of claim 1, wherein the shape drawing is a first shape drawing, wherein the final shape drawing is a first final shape drawing, and wherein the at least one processor is further programmed to: generate a second shape drawing from the scanned data, wherein the second shape drawing is generated by a method different from the first shape drawing; and use the second shape drawing as an input to execute the model to generate a second final shape drawing of the product.

7. The computer device of claim 6, wherein the at least one processor is further programmed to: calculate one or more product attributes from the first final shape drawing and the second final shape drawing; compare the one or more product attributes with the one or more threshold values; and if the one or more product attributes exceed the one or more threshold values, cause an adjustment to the first device.

8. The computer device of claim 6, wherein the first shape image is a polished shape image, wherein the first final shape image is a polished nano-morphology image, wherein the second shape image is a GAPI RMS (root mean square) image, and wherein the second final shape image is an in-plane deformation (IPD) image.

9. The computer device as requested in item 1, wherein the scan data is one of the four-line scan data or eight-line scan data of the product.

10. The computer device as claimed in claim 1, wherein the product is a semiconductor wafer.

11. The computer device of claim 10, wherein the first device is a grinder or a wafer cutter, and wherein the first inspection station includes a nano-morphology measurement device.

12. The computer device of claim 1, wherein the at least one processor is further programmed to: generate one or more adjustments to the first device based on the comparison of the final shape drawing with the one or more threshold values ​​and the model; and transmit the one or more adjustments to a user and at least one of the first devices.

13. The computer device of claim 1, wherein if the determination that the final shape drawing exceeds at least one of the one or more threshold values, the at least one processor is further programmed to: analyze a plurality of previous tests to determine a trend; predict, based on the trend, whether a subsequent test of a subsequent product is likely to exceed at least one of the one or more threshold values; and adjust the first device based on the trend.

14. The computer device of claim 13, wherein the at least one processor is further programmed to: determine a planned future downtime period; and schedule an adjustment for the first device for the planned future downtime period.

15. A method for analyzing an assembly line, the method being implemented by a computing device including at least one processor communicating with at least one memory device, the method comprising: The at least one memory device stores a model for simulating a portion of an assembly line, wherein the model is a generative adversarial network (GAN) artificial intelligence model; the at least one memory device stores a shape map for converting a shape map to simulate a portion of an assembly line model; receiving scan data of a first inspection of an assembled product, wherein the first inspection is performed at a first inspection station in the assembly line after a first device, wherein the first device is a grinder; generating a shape map from the scan data of the first inspection; using the shape map as an input to execute the model to generate a final shape map of the product; comparing the final shape map with one or more threshold values; determining whether the final shape map exceeds at least one of the one or more threshold values; and if the determination that the final shape map exceeds at least one of the one or more threshold values ​​causes adjustment of the grinder.

16. The method of claim 15, further comprising: Calculate one or more product attributes from the final shape diagram; compare the one or more product attributes with one or more threshold values; If one or more product attributes exceed one or more threshold values, the first device shall be adjusted.

17. The method of claim 15, wherein the shape map is one of a post-polishing shape map or a GAPI RMS (root mean square) map, and wherein the final shape map is one of an in-plane deformation (IPD) map or a post-polished nanomorphology map.

18. The method of claim 15, wherein the shape drawing is a first shape drawing, wherein the final shape drawing is a first final shape drawing, and wherein the method further comprises: A second shape image is generated from the scanned data, wherein the second shape image is generated by a method different from that of the first shape image; and the second shape image is used as an input to execute the model to generate a second final shape image of the product.

19. The method of claim 18, further comprising: Calculate one or more product attributes from the first final shape drawing and the second final shape drawing; compare the one or more product attributes with one or more threshold values; and if the one or more product attributes exceed the one or more threshold values, cause adjustment of the first device.

20. The method of claim 18, wherein the first shape map is a post-grinding shape map, wherein the first final shape map is a post-polished nanomorphology map, wherein the second shape map is a GAPI RMS (root mean square) map, and wherein the second final shape map is an in-plane deformation (IPD) map.

Images