Defect detection methods and devices for wafers

Abstract

This invention provides a method and apparatus for wafer defect detection, belonging to the field of semiconductor manufacturing technology. The wafer defect detection method includes: acquiring defect data from the surface of each wafer, the defect data including defect type and defect location coordinates; performing cluster analysis on the defect location coordinates of wafers in the same batch using a spatial clustering algorithm to determine the defect distribution pattern and defect distribution density of the batch of wafers, wherein the wafers in the same batch use the same manufacturing process parameters; calculating a risk score for the batch of wafers based on the defect distribution pattern, defect distribution density, and the proportion of abnormal wafers in the batch; comparing the risk score of the batch of wafers with a preset risk threshold; if the risk score of the batch of wafers is greater than the preset risk threshold, the batch of wafers is determined to be abnormal wafers. This invention can detect batch defects in wafers.

Description

Technical Field

[0001] This invention relates to the field of semiconductor manufacturing technology, and in particular to a method and apparatus for detecting defects in wafers. Background Technology

[0002] With the continuous advancement of semiconductor manufacturing technology, defect control on wafer surfaces has become particularly important. In actual production, wafer defect distribution is affected by a variety of factors, such as front-end process fluctuations, material quality variations, and equipment maintenance. These influences may lead to specific defect distribution characteristics within the same batch of wafers. However, traditional ADC (Automatic Defect Classification) models typically focus only on the defect characteristics of a single wafer, making it prone to missing batch defects and resulting in a large number of defective products being shipped out. Summary of the Invention

[0003] This invention provides a method and apparatus for detecting defects in wafers, which can detect batch defects in wafers.

[0004] To achieve the above objectives, the technical solution adopted in the embodiments of the present invention is as follows:

[0005] A method for detecting defects in a wafer, comprising:

[0006] Obtain defect data for the surface of each wafer, including the type of defect and the coordinates of the defect location;

[0007] Spatial clustering algorithm is used to perform cluster analysis on the defect location coordinates of wafers in the same batch to determine the defect distribution pattern and defect distribution density of the wafers in the same batch, wherein the wafers in the same batch use the same production process parameters;

[0008] The risk score of the batch of wafers is calculated based on the defect distribution pattern, defect distribution density, and the proportion of abnormal wafers in the batch.

[0009] The risk score of the batch of wafers is compared with a preset risk threshold. If the risk score of the batch of wafers is greater than the preset risk threshold, the batch of wafers is identified as abnormal wafers.

[0010] In some embodiments, acquiring defect data for each wafer surface includes:

[0011] Defect data on the surface of each wafer is collected using wafer surface particle inspection equipment;

[0012] The collected defect data is processed to eliminate noise and errors in the data collection process.

[0013] In some embodiments, after the batch of wafers is determined to be defective, the method further includes:

[0014] The manufacturing process parameters of this batch of wafers are matched with the manufacturing process parameters of the first wafer in the historical database;

[0015] The production process parameters of this batch of wafers are determined to be abnormal based on the degree of matching between the production process parameters of this batch of wafers and the production process parameters of the first wafer, wherein the first wafer is the wafer that is determined to be abnormal.

[0016] In some embodiments, determining whether the production process parameters of the batch of wafers are abnormal based on the matching degree between the production process parameters of the batch of wafers and the production process parameters of the first wafer includes:

[0017] If the matching degree between the production process parameters of this batch of wafers and the production process parameters of the first wafer is greater than or equal to the preset matching degree, it is determined that the production process parameters of this batch of wafers are abnormal.

[0018] If the matching degree between the production process parameters of this batch of wafers and the production process parameters of the first wafer is less than the preset matching degree, it is determined that the production process parameters of this batch of wafers are not abnormal.

[0019] In some embodiments, after the batch of wafers is determined to be defective, the method further includes:

[0020] The batch of wafers is intercepted, and a risk report for the batch is generated. The risk report includes the defect mode, production process parameters, and corresponding corrective measures for the batch of wafers.

[0021] This invention also provides a wafer defect detection device, comprising:

[0022] The acquisition module is used to acquire defect data on the surface of each wafer, the defect data including the type of defect and the coordinates of the defect location;

[0023] The clustering analysis module is used to perform clustering analysis on the defect location coordinates of wafers in the same batch using a spatial clustering algorithm, to determine the defect distribution pattern and defect distribution density of the wafers in the same batch, wherein the wafers in the same batch use the same production process parameters;

[0024] The calculation module is used to calculate the risk score of the batch of wafers based on the defect distribution pattern, defect distribution density, and the proportion of abnormal wafers in the batch.

[0025] The judgment module is used to compare the risk score of the batch of wafers with a preset risk threshold. If the risk score of the batch of wafers is greater than the preset risk threshold, the batch of wafers is judged as abnormal wafers.

[0026] In some embodiments, if the batch of wafers is determined to be defective, the apparatus further includes:

[0027] The matching module is used to match the manufacturing process parameters of this batch of wafers with the manufacturing process parameters of the first wafer in the historical database;

[0028] The determination module is also used to determine whether the production process parameters of the batch of wafers are abnormal based on the matching degree between the production process parameters of the batch of wafers and the production process parameters of the first wafer, wherein the first wafer is the wafer that is determined to be abnormal.

[0029] This invention also provides an electronic device, including: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the wafer defect detection method as described above.

[0030] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the wafer defect detection method described above.

[0031] This invention also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the wafer defect detection method as described above.

[0032] The beneficial effects of this invention are:

[0033] In this embodiment, defect data of each wafer surface is acquired, and spatial clustering algorithms are used to perform cluster analysis on the defect location coordinates of wafers in the same batch to determine the defect distribution pattern and defect density of the batch. Based on the defect distribution pattern, defect density, and the proportion of abnormal wafers in the batch, a risk score is calculated for the batch. The risk score of the batch is compared with a preset risk threshold to determine the abnormal wafers. This embodiment can achieve batch-level defect risk identification, thereby identifying potential process parameter problems or equipment anomalies; by performing risk assessment and shipment interception at the batch level, it effectively prevents the occurrence of batch quality accidents and avoids the large-scale outflow of defective wafers. Attached Figure Description

[0034] Figure 1 A schematic flowchart illustrating the wafer defect detection method according to an embodiment of the present invention;

[0035] Figure 2 This diagram illustrates the defect distribution according to an embodiment of the present invention.

[0036] Figure 3A schematic diagram showing the structure of a wafer defect detection device according to an embodiment of the present invention;

[0037] Figure 4 This is a schematic diagram showing the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0039] This invention provides a method and apparatus for detecting defects in wafers, which can detect batch defects in wafers.

[0040] This invention provides a method for detecting defects in a wafer, such as... Figure 1 As shown, it includes:

[0041] Step 101: Obtain defect data for the surface of each wafer, the defect data including the type of defect and the coordinates of the defect location;

[0042] Specifically, a wafer surface particle inspection device can be used to collect defect data on the surface of each wafer; and the collected defect data can be processed to eliminate noise and errors in the data collection, thereby improving the accuracy of defect detection.

[0043] Step 102: Use spatial clustering algorithm to perform cluster analysis on the defect location coordinates of wafers in the same batch to determine the defect distribution pattern and defect distribution density of the wafers in the same batch. The wafers in the same batch use the same production process parameters.

[0044] In this embodiment, spatial clustering algorithms (such as DBSCAN or K-Means) can be used to perform cluster analysis on the defect location coordinates of wafers in the same batch, identifying specific distribution patterns of defects at the batch level. Figure 2 As shown in the figure, the left side of the figure is a schematic diagram of the defect distribution of a wafer, and the right side of the figure is a schematic diagram of the distribution of defects after superposition of wafers in the same batch. The significant spatial features of defects at the batch level can be extracted by spatial clustering algorithm.

[0045] Step 103: Calculate the risk score of the batch of wafers based on the defect distribution pattern, defect distribution density, and the proportion of abnormal wafers in the batch;

[0046] In this embodiment, defect identification model can be trained using defect sample data. The defect identification model then calculates the risk score of the batch of wafers based on defect distribution patterns, defect density, and the proportion of abnormal wafers in the batch. Specifically, an ADC (Automatic Defect Classification) model can be used in advance to identify abnormal wafers within the batch.

[0047] To improve detection accuracy, multiple defect identification models can be used. These models can be trained independently, and the weights for each model can be set according to the actual situation. The detection results from multiple defect identification models are then weighted and fused to obtain the final risk score. These multiple defect identification models can be random forest models, decision tree models, deep learning neural network-based models, etc.

[0048] Step 104: Compare the risk score of the batch of wafers with the preset risk threshold. If the risk score of the batch of wafers is greater than the preset risk threshold, the batch of wafers is identified as abnormal wafers.

[0049] In this embodiment, defect data of each wafer surface is acquired, and spatial clustering algorithms are used to perform cluster analysis on the defect location coordinates of wafers in the same batch to determine the defect distribution pattern and defect density of the batch. Based on the defect distribution pattern, defect density, and the proportion of abnormal wafers in the batch, a risk score is calculated for the batch. The risk score of the batch is compared with a preset risk threshold to determine the abnormal wafers. This embodiment can achieve batch-level defect risk identification, thereby identifying potential process parameter problems or equipment anomalies; by performing risk assessment and shipment interception at the batch level, it effectively prevents the occurrence of batch quality accidents and avoids the large-scale outflow of defective wafers.

[0050] In this embodiment, potential process problems or equipment malfunctions can be identified based on the batch wafer determination results. If a batch of wafers is determined to be an abnormal wafer, it indicates that there are potential process problems or equipment malfunctions in the corresponding production process parameters (such as crystal growth rate, temperature, pressure, etc.).

[0051] To improve the accuracy of the judgment, historical data can be used to perform correlation analysis on the production process parameters to determine whether there are any abnormalities in the production process parameters corresponding to this batch of wafers. In some embodiments, after the batch of wafers is determined to be abnormal wafers, the method further includes:

[0052] The manufacturing process parameters of this batch of wafers are matched with the manufacturing process parameters of the first wafer in the historical database;

[0053] The production process parameters of this batch of wafers are determined to be abnormal based on the degree of matching between the production process parameters of this batch of wafers and the production process parameters of the first wafer, wherein the first wafer is the wafer that is determined to be abnormal.

[0054] In some embodiments, determining whether the production process parameters of the batch of wafers are abnormal based on the matching degree between the production process parameters of the batch of wafers and the production process parameters of the first wafer includes:

[0055] If the matching degree between the production process parameters of this batch of wafers and the production process parameters of the first wafer is greater than or equal to the preset matching degree, it is determined that the production process parameters of this batch of wafers are abnormal.

[0056] If the matching degree between the production process parameters of this batch of wafers and the production process parameters of the first wafer is less than the preset matching degree, it is determined that the production process parameters of this batch of wafers are not abnormal.

[0057] In some embodiments, after the batch of wafers is determined to be defective, the method further includes:

[0058] The batch of wafers is intercepted, and a risk report for the batch is generated. The risk report includes the defect mode, production process parameters, and corresponding corrective measures for the batch of wafers.

[0059] In this embodiment, abnormal wafers can be intercepted in a timely manner, and detailed risk reports and improvement suggestions can be provided, thereby effectively preventing the outflow of batch defective products. By conducting risk assessment and shipment interception at the batch level, batch quality accidents can be effectively prevented, and large-scale outflow of defective wafers can be avoided.

[0060] This embodiment employs a combination of cluster analysis, morphological analysis, and machine learning algorithms to comprehensively analyze defect distribution patterns from multiple dimensions and provide accurate risk assessment scores, thereby significantly improving the accuracy of shipping decisions. The technical solution in this embodiment can automatically identify various complex defect patterns and perform in-depth analysis in conjunction with production process parameters, thus improving sensitivity to process fluctuations and equipment problems.

[0061] This invention also provides a wafer defect detection device, such as... Figure 3 As shown, it includes:

[0062] The acquisition module 21 is used to acquire defect data on the surface of each wafer, the defect data including the type of defect and the coordinates of the defect location;

[0063] Cluster analysis module 22 is used to perform cluster analysis on the defect location coordinates of wafers in the same batch using a spatial clustering algorithm to determine the defect distribution pattern and defect distribution density of the wafers in the same batch, wherein the wafers in the same batch use the same production process parameters;

[0064] Calculation module 23 is used to calculate the risk score of the batch of wafers based on the defect distribution pattern, defect distribution density and the proportion of abnormal wafers in the batch;

[0065] The determination module 24 is used to compare the risk score of the batch of wafers with a preset risk threshold. If the risk score of the batch of wafers is greater than the preset risk threshold, the batch of wafers is determined to be abnormal wafers.

[0066] In this embodiment, defect data of each wafer surface is acquired, and spatial clustering algorithms are used to perform cluster analysis on the defect location coordinates of wafers in the same batch to determine the defect distribution pattern and defect density of the batch. Based on the defect distribution pattern, defect density, and the proportion of abnormal wafers in the batch, a risk score is calculated for the batch. The risk score of the batch is compared with a preset risk threshold to determine the abnormal wafers. This embodiment can achieve batch-level defect risk identification, thereby identifying potential process parameter problems or equipment anomalies; by performing risk assessment and shipment interception at the batch level, it effectively prevents the occurrence of batch quality accidents and avoids the large-scale outflow of defective wafers.

[0067] In some embodiments, the acquisition module 21 is specifically used to collect defect data of the surface of each wafer using a wafer surface particle detection device; and to process the collected defect data to eliminate noise in the defect data and errors in data acquisition.

[0068] In some embodiments, if the batch of wafers is determined to be defective, the apparatus further includes:

[0069] The matching module is used to match the manufacturing process parameters of this batch of wafers with the manufacturing process parameters of the first wafer in the historical database;

[0070] The determination module is also used to determine whether the production process parameters of the batch of wafers are abnormal based on the matching degree between the production process parameters of the batch of wafers and the production process parameters of the first wafer, wherein the first wafer is the wafer that is determined to be abnormal.

[0071] In some embodiments, the determination module is specifically used to determine that the production process parameters of the batch of wafers are abnormal if the matching degree between the production process parameters of the batch of wafers and the production process parameters of the first wafer is greater than or equal to a preset matching degree; and to determine that the production process parameters of the batch of wafers are not abnormal if the matching degree between the production process parameters of the batch of wafers and the production process parameters of the first wafer is less than a preset matching degree.

[0072] In some embodiments, the apparatus further includes:

[0073] The interception module is used to intercept the batch of wafers and generate a risk report for the batch of wafers. The risk report includes the defect mode, production process parameters and corresponding corrective measures for the batch of wafers.

[0074] Please refer to Figure 4 The present invention also provides an electronic device 30, including a processor 31, a memory 32, and a computer program stored in the memory 32 and executable on the processor 31. When the computer program is executed by the processor 31, it implements the various processes of the above-described wafer defect detection method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0075] This invention also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the various processes of the above-described wafer defect detection method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage, or any other non-transmission medium that can be used to store information accessible to the terminal device under test. As defined in this article, computer-readable storage media do not include transient media, such as modulated data signals and carrier waves.

[0076] This application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the above-described... Figure 1 The various processes of the method embodiments shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0077] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0078] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0079] In the various method embodiments of this disclosure, the sequence numbers of each step are not intended to limit the order of the steps. For those skilled in the art, any changes in the order of the steps are within the scope of protection of this disclosure without any creative effort.

[0080] It should be noted that the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, since the embodiments are basically similar to the product embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the descriptions of the product embodiments.

[0081] The above description represents the preferred embodiments of this disclosure. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles described herein, and these improvements and modifications should also be considered within the scope of protection of this disclosure.

Claims

1. A method for detecting defects in a wafer, characterized in that, include: Obtain defect data for the surface of each wafer, including the type of defect and the coordinates of the defect location; Spatial clustering algorithm is used to perform cluster analysis on the defect location coordinates of wafers in the same batch to determine the defect distribution pattern and defect distribution density of the wafers in the same batch, wherein the wafers in the same batch use the same production process parameters; Based on the defect distribution pattern, defect distribution density, and proportion of abnormal wafers in the batch, the risk score of the batch of wafers is calculated, including: training a defect identification model using defect sample data, and using the defect identification model to calculate the risk score of the batch of wafers based on the defect distribution pattern, the defect distribution density, and the proportion of abnormal wafers in the batch, wherein abnormal wafers in the batch are identified in advance using an automatic defect classification model; The risk score of the batch of wafers is compared with a preset risk threshold. If the risk score of the batch of wafers is greater than the preset risk threshold, the batch of wafers is identified as abnormal wafers.

2. The wafer defect detection method according to claim 1, characterized in that, The acquisition of defect data on the surface of each wafer includes: Defect data on the surface of each wafer is collected using wafer surface particle inspection equipment; The collected defect data is processed to eliminate noise and errors in the data collection process.

3. The wafer defect detection method according to claim 1, characterized in that, After determining that the batch of wafers is defective, the method further includes: The manufacturing process parameters of this batch of wafers are matched with the manufacturing process parameters of the first wafer in the historical database; The production process parameters of this batch of wafers are determined to be abnormal based on the degree of matching between the production process parameters of this batch of wafers and the production process parameters of the first wafer, wherein the first wafer is the wafer that is determined to be abnormal.

4. The wafer defect detection method according to claim 3, characterized in that, The step of determining whether the production process parameters of this batch of wafers are abnormal based on the matching degree between the production process parameters of this batch of wafers and the production process parameters of the first wafer includes: If the matching degree between the production process parameters of this batch of wafers and the production process parameters of the first wafer is greater than or equal to the preset matching degree, it is determined that the production process parameters of this batch of wafers are abnormal. If the matching degree between the production process parameters of this batch of wafers and the production process parameters of the first wafer is less than the preset matching degree, it is determined that the production process parameters of this batch of wafers are not abnormal.

5. The wafer defect detection method according to claim 1, characterized in that, After determining that the batch of wafers is defective, the method further includes: The batch of wafers is intercepted, and a risk report for the batch is generated. The risk report includes the defect mode, production process parameters, and corresponding corrective measures for the batch of wafers.

6. A wafer defect detection device, characterized in that, include: The acquisition module is used to acquire defect data on the surface of each wafer, the defect data including the type of defect and the coordinates of the defect location; The clustering analysis module is used to perform clustering analysis on the defect location coordinates of wafers in the same batch using a spatial clustering algorithm, to determine the defect distribution pattern and defect distribution density of the wafers in the same batch, wherein the wafers in the same batch use the same production process parameters; The calculation module is used to calculate the risk score of the batch of wafers based on the defect distribution pattern, defect distribution density, and the proportion of abnormal wafers in the batch. The calculation module includes: training a defect identification model using defect sample data, and using the defect identification model to calculate the risk score of the batch of wafers based on the defect distribution pattern, the defect distribution density, and the proportion of abnormal wafers in the batch. The abnormal wafers in the batch are identified in advance using an automatic defect classification model. The judgment module is used to compare the risk score of the batch of wafers with a preset risk threshold. If the risk score of the batch of wafers is greater than the preset risk threshold, the batch of wafers is judged as abnormal wafers.

7. The wafer defect detection device according to claim 6, characterized in that, If the batch of wafers is determined to be defective, the device further includes: The matching module is used to match the manufacturing process parameters of this batch of wafers with the manufacturing process parameters of the first wafer in the historical database; The determination module is also used to determine whether the production process parameters of the batch of wafers are abnormal based on the matching degree between the production process parameters of the batch of wafers and the production process parameters of the first wafer, wherein the first wafer is the wafer that is determined to be abnormal.

8. An electronic device, characterized in that, include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the wafer defect detection method as described in any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the wafer defect detection method as described in any one of claims 1 to 5.

10. A computer program product, characterized in that, It includes computer instructions that, when executed by a processor, implement the steps of the wafer defect detection method as described in any one of claims 1 to 5.

Images