Adaptive Regulation Method and Device for the Brightness of a Wafer Detection Light Source

Abstract

The present invention relates to the technical field of light source control, and discloses an adaptive regulation method and device for the brightness of a wafer detection light source. The present invention preliminarily irradiates a wafer with a preset annular light source, collects initial image data, performs digital simulation according to the initial detection data to generate a wafer detection feedback model, analyzes the light source irradiation requirements based on the detection feedback model to generate a gradient execution plan, configures the light source parameters in sequence according to the gradient plan, performs multiple rounds of detection on the wafer and collects data, feeds the detection data back to the model for parameter adjustment, analyzes the extended light source detection requirements by the adjusted model to generate an extended detection plan, and performs final detection. This method realizes efficient and accurate detection of wafer surface defects through automatic adjustment of the light source brightness and configuration, improves the detection accuracy and efficiency, adapts to the detection requirements of different wafers, and solves the problem in the prior art that the light source for detection is not comprehensive enough, resulting in undetected defects.

Description

Technical Field

[0001] The present invention relates to the technical field of light source control, and particularly to an adaptive regulation method and device for the brightness of a wafer detection light source. Background Art

[0002] As a core material in semiconductor manufacturing, the surface quality of a wafer directly affects the performance and reliability of chips. There may be various defects on the wafer surface, including microcracks, scratches, contaminants, etc. These defects are often difficult to detect by traditional detection means. The light source is one of the most critical elements in wafer surface detection. Different types of light sources (such as annular light sources, laser light sources, polarized light sources, etc.) will produce different reflection characteristics when irradiating the wafer surface, thereby revealing different defect information. Parameters such as light source brightness, angle, and distribution need to be adjusted according to the actual state of the wafer to achieve the best detection effect.

[0003] In the actual wafer detection process, the adjustment of the light source brightness is usually based on experience, which may lead to some potential defects not being detected or the image being overexposed due to excessive reflection. The traditional method cannot automatically adjust the light source brightness according to the real-time situation of the wafer surface reflection, and it is difficult to meet the detection requirements for different types of defects. Summary of the Invention

[0004] The purpose of the present invention is to provide an adaptive regulation method and device for the brightness of a wafer detection light source, aiming to solve the problem that the light source used for detection in the prior art is not comprehensive enough, resulting in undetected defects.

[0005] The present invention is implemented as follows. In the first aspect, the present invention provides an adaptive regulation method for the brightness of a wafer detection light source, including:

[0006] Performing initial light source irradiation on the wafer to be detected in a surrounding state by a pre-set annular light source, and collecting image data of the wafer to be detected under the initial light source irradiation in the surrounding state to obtain initial detection data of the wafer to be detected;

[0007] Performing digital simulation on the wafer to be detected according to the initial detection data of the wafer to be detected to obtain a wafer detection feedback model, and analyzing a gradient scheme for subsequent light source irradiation requirements for the annular light source based on the wafer detection feedback model to obtain a light source irradiation gradient execution scheme;

[0008] Performing light source parameter configuration on the annular light source in sequence according to the light source irradiation gradient execution scheme, so that the annular light source sequentially applies detection light source irradiation to the wafer to be detected, thereby obtaining gradient detection data of the wafer to be detected under each round of detection light source irradiation;

[0009] Substitute the gradient detection data of the wafer to be detected under each round of detection light sources into the wafer detection feedback model to adjust the model parameters of the wafer detection feedback model;

[0010] According to the wafer detection feedback model after model parameter adjustment, perform an analysis of the extended light source detection requirements to obtain the extended light source detection scheme for the wafer to be detected, and detect the wafer to be detected according to the extended light source detection scheme to obtain extended detection data and substitute it into the wafer detection feedback model.

[0011] In a second aspect, the present invention provides an adaptive regulation device for the brightness of a wafer detection light source, which is used to implement the adaptive regulation method for the brightness of a wafer detection light source according to any one of the first aspects, including:

[0012] An initial detection module, configured to irradiate the wafer to be detected with an initial light source in a surrounding state through a pre-set annular light source, and collect image data of the wafer to be detected under the initial light source irradiation in the surrounding state to obtain initial detection data of the wafer to be detected;

[0013] A scheme analysis module, configured to perform digital simulation on the wafer to be detected according to the initial detection data of the wafer to be detected to obtain the wafer detection feedback model, and perform a gradient scheme analysis on the subsequent light source irradiation requirements of the annular light source based on the wafer detection feedback model to obtain a light source irradiation gradient execution scheme;

[0014] A gradient detection module, configured to sequentially configure light source parameters for the annular light source according to the light source irradiation gradient execution scheme, so that the annular light source sequentially irradiates the wafer to be detected with a detection light source, thereby obtaining gradient detection data of the wafer to be detected under each round of detection light source irradiation;

[0015] A data feedback module, configured to substitute the gradient detection data of the wafer to be detected under each round of detection light sources into the wafer detection feedback model to adjust the model parameters of the wafer detection feedback model;

[0016] An extended detection module, configured to perform an analysis of the extended light source detection requirements according to the wafer detection feedback model after model parameter adjustment to obtain the extended light source detection scheme for the wafer to be detected, and detect the wafer to be detected according to the extended light source detection scheme to obtain extended detection data and substitute it into the wafer detection feedback model.

[0017] The present invention provides an adaptive regulation method for the brightness of a wafer detection light source, which has the following beneficial effects:

[0018] The present invention preliminarily irradiates a wafer with a preset annular light source, collects initial image data, performs digital simulation based on the initial detection data to generate a wafer detection feedback model, analyzes the light source irradiation requirements based on the detection feedback model to generate a gradient execution plan, sequentially configures the light source parameters according to the gradient plan, performs multiple rounds of detection on the wafer and collects data, feeds the detection data back to the model for parameter adjustment, analyzes the extended light source detection requirements of the adjusted model to generate an extended detection plan, and performs a final detection. This method realizes efficient and accurate detection of wafer surface defects by automatically adjusting the light source brightness and configuration, improves the detection accuracy and efficiency, adapts to the detection requirements of different wafers, and solves the problem that the light source used for detection in the prior art is not comprehensive enough, resulting in undetected defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a schematic diagram of the steps of an adaptive regulation method for the brightness of a wafer detection light source provided by an embodiment of the present invention;

[0020] Figure 2 is a schematic diagram of the structure of an adaptive regulation device for the brightness of a wafer detection light source provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0022] The implementation of the present invention will be described in detail below with reference to specific embodiments.

[0023] Referring to Figure 1 and Figure 2 shown, a preferred embodiment of the present invention is provided.

[0024] In a first aspect, the present invention provides an adaptive regulation method for the brightness of a wafer detection light source, including:

[0025] S1: Initially irradiate the wafer to be detected in a surrounding state with a pre-set annular light source, and collect the image data of the wafer to be detected under the initial light source irradiation in the surrounding state, so as to obtain the initial detection data of the wafer to be detected;

[0026] S2: Perform digital simulation on the wafer to be detected according to the initial detection data of the wafer to be detected, so as to obtain the wafer detection feedback model, and perform gradient plan analysis on the subsequent light source irradiation requirements of the annular light source based on the wafer detection feedback model, so as to obtain a light source irradiation gradient execution plan;

[0027] S3: Configure the light source parameters of the annular light source in sequence according to the light source irradiation gradient execution plan, so that the annular light source irradiates the wafer to be detected with the detection light source in sequence, thereby obtaining the gradient detection data of the wafer to be detected under each round of detection light source irradiation;

[0028] S4: Substitute the gradient detection data of the wafer to be detected under each round of detection light source into the wafer detection feedback model to adjust the model parameters of the wafer detection feedback model;

[0029] S5: Analyze the extended light source detection requirements according to the wafer detection feedback model after the model parameters are adjusted to obtain the extended light source detection plan for the wafer to be detected, and detect the wafer to be detected according to the extended light source detection plan to obtain the extended detection data and substitute it into the wafer detection feedback model.

[0030] Specifically, in step S1 of the embodiment provided by the present invention, an annular light source is pre-installed and set. This kind of light source usually surrounds the wafer to form a uniform illumination environment. The brightness, angle, position, etc. of the annular light source can be adjusted according to requirements to ensure that the entire surface of the wafer can be covered. Place the wafer to be detected within the light source irradiation range to ensure that the surface of the wafer can be evenly irradiated by the annular light source. When the annular light source irradiates the wafer, the surrounding irradiation method is adopted, that is, the light source is evenly distributed along the circumference of the wafer to ensure that the light intensity at each angle is basically the same.

[0031] It can be understood that the configuration of the annular light source can provide uniform illumination, avoiding the shadow and uneven irradiation problems that may be caused by traditional light sources, thereby improving the quality during image acquisition and ensuring the comprehensiveness of image data. The annular light source can ensure uniform irradiation of the wafer surface at all angles, reducing the omission or misjudgment of defects caused by insufficient local illumination. Compared with traditional point light sources, the annular light source can irradiate the wafer surface from multiple angles, helping to improve the brightness uniformity of the preliminary image and reducing the impact on detection.

[0032] More specifically, a high-resolution camera or optical detection device is used to ensure that minute structures and defects on the wafer surface can be precisely captured. Under the illumination of an annular light source, image data of the wafer surface is collected to obtain detailed image information of various regions of the wafer. These image data usually include features such as the surface texture, defects, and blemishes of the wafer. The collected image data is transmitted to a processing system for subsequent image analysis and processing. Due to the uniformity of the light source and the sufficient illumination obtained on the wafer surface, high-quality and high-contrast images can be obtained during the image acquisition process, thereby improving the detection accuracy of wafer defects. The design of the annular light source ensures the illumination of every corner of the wafer surface, avoiding detection blind spots caused by dead angles of illumination and ensuring that image data of all regions on the wafer surface is effectively collected.

[0033] More specifically, the collected image data is stored as an original image data file, usually in a format such as an image file (e.g., TIFF, JPEG, PNG, etc.) or an image data set (e.g., matrix data), etc. These image data will serve as the basic data for subsequent detection and analysis. Subsequently, steps such as image processing and defect recognition will be carried out. According to the collected image data, the image quality is evaluated to check for problems such as blurring and noise to determine whether it is necessary to adjust the light source parameters or re-collect the data. Through the image data collection at this stage, basic data is provided for subsequent defect detection and light source optimization. Subsequent steps will further optimize the light source illumination and detection methods based on these initial data. The initially collected data can not only be directly used for subsequent defect analysis but also provides strong support for establishing a model of the wafer surface characteristics.

[0034] It can be understood that through the initial illumination of the annular light source and image data collection, the technical effect of the entire step is as follows: Through the uniform illumination of the annular light source, the lighting conditions during image acquisition are ensured to be uniform, minimizing the influence of shadows and uneven illumination on the image to the greatest extent, thereby improving the quality and reliability of the detected image. The annular light source ensures that every region of the wafer can be fully illuminated, thus avoiding possible illumination blind spots of traditional light sources. The collection of the initial image data is the basis for all subsequent light source regulation and defect detection, ensuring the accuracy and efficiency of subsequent steps.

[0035] Specifically, in step S2 of the embodiment provided by the present invention, the image data collected by irradiating with the preliminary annular light source is used as the input for the digital simulation program to analyze. At this time, the image data may contain information such as defects, textures, and material non-uniformities on the wafer surface. Using advanced simulation software or algorithms (such as finite element analysis, optical simulation, etc.), based on the input initial detection data, a model of the wafer surface is generated, creating a virtual wafer surface model. Based on the wafer surface model, the image responses under different light source irradiation conditions are simulated to obtain a wafer detection feedback model. This model shows the response characteristics of the wafer under different lighting conditions, including factors such as the visibility, brightness, and contrast of defects. The virtual model generated through digital simulation can accurately reflect the true physical characteristics of the wafer, making subsequent light source adjustment and defect detection more precise. Simulating the detection feedback under different light source conditions helps to evaluate which areas of defects are difficult to identify under the existing lighting conditions, thereby providing a basis for subsequent light source adjustment. The wafer detection feedback model provides a theoretical basis for formulating subsequent light source control schemes, can effectively optimize light source parameters, and avoid unnecessary light waste.

[0036] More specifically, based on the generated wafer detection feedback model, the irradiation requirements for different regions of the wafer surface are analyzed. For example, some regions may require stronger illumination due to the surface structure or the nature of the defects, while other regions may only need weaker illumination to avoid overexposure or over-illumination. According to the regional requirements feedback by the model, a gradient scheme for light source irradiation is formulated. This gradient scheme will specify in detail the parameters such as the light source intensity and irradiation angle required for each region. Specifically, it includes: the required illumination intensity may be different for different regions and needs to be optimized by adjusting the light source brightness, and the irradiation angles for different regions can be fine-tuned according to the different types of defects. For example, some defects are more obvious under oblique illumination. By simulating the effects of different gradient schemes on the wafer and evaluating the visibility and detection effects of wafer defects under each scheme, the optimal light source irradiation gradient execution scheme is finally determined.

[0037] It can be understood that through the precise analysis and gradient adjustment of the lighting requirements for different regions of the wafer, the problems of over-irradiation or uneven illumination caused by global uniform light source irradiation can be avoided, ensuring that each region receives the most suitable illumination. Some small or weak defects are more easily detected under specific lighting conditions. By adjusting the gradient light source irradiation scheme, the detection sensitivity of these tiny defects can be effectively improved. By flexibly adjusting the light source irradiation intensity and angle, overexposure in some regions or insufficient illumination in other regions can be avoided, maximizing the accuracy of defect detection.

[0038] More specifically, based on the previous analysis of the light source gradient scheme, a specific light source irradiation gradient execution plan is formed. The plan should list in detail the parameters such as the light source intensity, angle, irradiation time, etc. required for each area, and provide implementation details. The gradient execution plan is applied in the actual detection environment, and its effect is verified through experiments. If it is found that there are still undetected defects in some areas, it may be necessary to further adjust the light source irradiation plan. After several rounds of adjustment and optimization, the final gradient execution plan is confirmed to ensure that defects in each area can be accurately detected while avoiding false alarms and missed alarms. Through the execution of precise gradient light source schemes, the inspection of wafer surfaces can be completed quickly and efficiently, and it can adapt to the surface characteristics and defect types of different wafers. By optimizing the light source irradiation method, the detection accuracy of different defect types and different areas has been significantly improved, ensuring that all defects (regardless of size or type) can be effectively captured.

[0039] It can be understood that through the analysis and adjustment of the gradient light source scheme, each wafer area can be properly illuminated according to actual needs, avoiding the problem of insufficient or excessive illumination caused by unified light source illumination in traditional methods. Digital simulation and feedback model optimization under different lighting conditions enable tiny and complex defects to be clearly presented under appropriate lighting conditions, thereby improving the accuracy of detection. This method can dynamically adjust the light source parameters according to actual detection needs, adapt to the detection requirements of different types of wafers and defects, and has strong flexibility and adaptability. Through preliminary model simulation and gradient scheme analysis, unnecessary detection steps are reduced, ultimately improving the efficiency and accuracy of the entire detection process.

[0040] Specifically, in step S3 of the embodiment provided by the present invention, according to the determined gradient light source illumination scheme, the illumination parameters of the light source are gradually adjusted, mainly including: light source intensity (brightness): adjusting the brightness of the light source according to the needs of different areas to ensure that the wafer surface in different areas is most appropriately illuminated; illumination angle: adjusting the angle between the light source and the wafer surface to ensure the illumination effect of different areas, especially the effect of revealing surface defects; illumination time: adjusting the duration of light source illumination according to the required exposure time to ensure that each area is adequately illuminated without overexposure or underexposure.

[0041] More specifically, the annular light source is adjusted successively according to a set gradient scheme and irradiates the wafer surface in turn. During each round of light source irradiation, the parameters of the light source change according to the gradient scheme to ensure that different irradiation conditions are obtained for each area. After each round of light source irradiation, a detection device (such as an optical imaging system or a camera) is used to capture the light signal reflected or transmitted by the wafer surface, and image data or other detection data of the wafer under different irradiation conditions are obtained. These data will reflect the response of the wafer surface under different light source irradiations, including defect information, surface non-uniformity, reflectivity, etc. By gradually adjusting the light source parameters and optimizing according to the requirements of each area, it can ensure that the wafer surface of each area is irradiated and detected under the best conditions, so as to obtain more accurate detection data. Through multiple irradiations under different light source conditions, different defect types and manifestations on the wafer surface can be covered, thereby increasing the comprehensiveness of defect detection. By precisely adjusting the intensity, angle, and time of the light source, the detection requirements of different wafers and different defect types can be adapted, thus realizing a personalized customized detection process.

[0042] More specifically, after each light source irradiation ends, the detection system (such as a CCD camera or an optical sensor) will collect in real time the light signal reflected or transmitted by the wafer surface. These signals will be converted into image data or other forms of feedback data. The collected image or light signal data will be preliminarily processed and calibrated to remove noise and enhance key information such as the contrast and brightness of the image, ensuring that defects can be clearly visible. The data after each round of irradiation will be recorded and stored for subsequent analysis and comparison. The parameters of each irradiation (such as light source intensity, angle, time) will be stored together with the corresponding detection data to form a complete gradient detection data set.

[0043] More specifically, through data collection under multiple gradient irradiation schemes, multi-dimensional detection data can be obtained, including information such as reflection, transmission, and contrast under different lighting conditions. These data can provide a comprehensive reference for subsequent analysis. By gradually adjusting the light source parameters, it can ensure that the key information on the wafer surface can be extracted to the greatest extent in each round of irradiation, improving the quality of defect identification. The data under different light source irradiations can help identify different types of defects, such as micro-cracks, surface contamination, non-uniform regions, etc., and can more accurately classify and locate the defects on the wafer surface.

[0044] More specifically, by comparing the data collected under different light source irradiation conditions, analyze which irradiation schemes make the defects on the wafer surface more obvious and which areas may have missed or misdetected defects. According to the results of data analysis, further adjust the light source irradiation gradient, improve the distribution of light source intensity, angle or time, and optimize the detection effect. Continuously improve the detection process through experiments and data feedback to achieve the optimal detection result. Use the data collected under each round of gradient light source irradiation, combined with defect recognition algorithms (such as image processing, machine learning, etc.) to identify and locate the defects, and further extract the defect characteristics on the wafer surface.

[0045] More specifically, through the comparison and analysis of data under different light source conditions, it can help accurately identify different types of defects, especially those tiny or complex defects that are not easily found under conventional light sources. Through the feedback of gradient light source irradiation data, self-optimization and dynamic adjustment can be achieved, enabling the light source configuration to more precisely adapt to different wafer surface characteristics and defect types, improving the overall detection ability. Through successive gradient irradiation and multiple data comparisons, the occurrence of missed and misdetected defects can be effectively reduced, and the reliability and accuracy of detection can be improved.

[0046] It can be understood that through multiple rounds of irradiation and data collection under different light source conditions, the entire wafer surface can be comprehensively covered without missing any potential defect areas, ensuring that all defects can be detected. The annular light source gradually adjusts the light source parameters according to the gradient execution plan, precisely controls the light source irradiation, avoids unnecessary overexposure or under-irradiation problems, and improves the accuracy of wafer defect detection. Through repeated light source adjustment and data feedback, the detection process is continuously optimized, the detection efficiency is improved, and the optimal detection effect is ensured. Based on the gradient data under different light source irradiation conditions, various defects can be identified more clearly and precisely, especially the detection of tiny or complex defects.

[0047] Specifically, in step S4 of the embodiment provided by the present invention, from the previous step, by successively adjusting the light source parameters and performing irradiation, the wafer surface detection data under different light source conditions (such as reflectivity, transmission image, optical image, etc.) are obtained. Necessary preprocessing is performed on the obtained gradient detection data, including noise removal, image enhancement (such as contrast adjustment, smoothing), standardization, etc. This process ensures that the data input into the model has high quality and consistency. The processed gradient detection data is input into the wafer detection feedback model as the input features of the model. At this time, the gradient data is not only the original information of each round of detection, but also includes information related to the environmental conditions and detection parameters under each round of light source irradiation. The preprocessed gradient detection data ensures the quality of the model input data, thereby improving the effect of subsequent model training and adjustment. By substituting the data under multiple rounds of light source irradiation into the feedback model, multi-dimensional and multi-angle information is provided, which helps to more comprehensively characterize the defect characteristics of the wafer.

[0048] More specifically, the wafer inspection feedback model is usually initialized based on some preliminary model parameters (such as thresholds, weights, biases, etc.) to form an initial inspection state. This process can be based on historical data or preliminary assumptions. Using the input gradient inspection data for model prediction, the defect probability or predicted value of the defect type for each region is obtained. By comparing the model prediction results with the actual inspection results (if there is ground truth data), the error is calculated (such as the deviation between the predicted defect position and the actual defect position, false detection rate, missed detection rate, etc.). Based on the error value, the model parameters are adjusted through the backpropagation algorithm (in deep learning models) or other optimization algorithms (such as gradient descent, genetic algorithms, etc.). The update process usually includes adjusting model parameters such as weights, biases, and thresholds to reduce the prediction error.

[0049] More specifically, under multi-round light source conditions, the model will continuously learn and self-adjust. Through repeated iterative optimization, the recognition accuracy of the model for wafer surface defects is gradually improved. The adjusted model needs to be verified with new data to confirm that the adjusted parameters can significantly improve the defect detection accuracy. If it is found that there are still errors, continue to iteratively adjust the model parameters until an ideal detection effect is obtained. By substituting the actual gradient inspection data and combining error backpropagation, the model can adaptively optimize its own parameters. With each round of adjustment, the detection ability of the model will continuously improve. Through fine parameter adjustment, the model can more accurately identify defects under different lighting conditions and gradually improve the defect recognition ability in complex scenarios. With the continuous input of gradient data, the model can continuously adapt to changing factors such as different types of wafers, different defect types, and different light source conditions, enabling the detection system to have stronger dynamic adaptability.

[0050] More specifically, after each model adjustment, the new detection results can be used as data feedback again for a second round or even multiple rounds of learning. The input of the feedback data in each round can further optimize the model, making the model more accurate. Through techniques such as cross-validation, it is ensured that the generalization ability of the model is not affected by overfitting. This process helps to improve the robustness of the model under different wafers and different light source conditions. After multiple rounds of iteration and optimization, the final model will be comprehensively evaluated based on multi-dimensional data (including data under different light source irradiation conditions) to examine its performance in the real production environment, such as the defect detection rate, the missed detection rate, and the false detection rate, etc. Through repeated iteration and parameter adjustment, the recognition accuracy of the model will be continuously improved, and finally, high-precision defect detection can be achieved in a complex process environment. Through multi-round gradient data feedback, the model can adapt to different process changes, handle different types and sizes of wafer defects, enabling it to maintain good stability and adaptability in a changing production environment. As the model accuracy improves, the detection system can identify defects on the wafer in a shorter time, reducing the detection time and the risk of misjudgment in production, thereby improving the overall production efficiency.

[0051] It can be understood that by inputting the gradient detection data under each round of light source irradiation into the feedback model and adjusting the model parameters, the recognition accuracy of wafer defects can be effectively improved. Especially in complex situations with large changes in light conditions, the feedback model has the ability of self-learning and optimization by continuously absorbing gradient data and adjusting parameters, and can adapt to new process requirements or environmental changes. Through gradient data and parameter adjustment, the model can not only identify conventional defects but also handle complex and tiny defects, improving the comprehensiveness and accuracy of detection. The optimized model can efficiently identify defects in real time on the production line, reducing missed detections and false detections, and improving the overall production quality and efficiency. In summary, substituting the gradient detection data into the wafer detection feedback model and adjusting the model parameters can improve the accuracy and efficiency of defect detection, optimize the detection process, and achieve dynamic adaptability, ultimately improving the accuracy of wafer surface defect detection and production efficiency.

[0052] Specifically, in step S5 of the embodiment provided by the present invention, based on the wafer detection feedback model after parameter adjustment, the detection effect of the existing light source conditions on the wafer surface defects is analyzed, which includes the evaluation of indicators such as the defect detection accuracy, the missed detection rate, and the false detection rate under different light source conditions. By modeling the optical characteristics of the wafer (such as reflectivity, transmittance, glossiness, etc.), it is determined which light source parameters (such as wavelength, light intensity, angle, etc.) have a greater impact on the recognition of wafer defects. This step helps to identify the deficiencies of the current light source configuration and determine the light source characteristics that need to be extended.

[0053] More specifically, based on multiple dimensions such as defect type, wafer material, and surface treatment process, the demand analysis of the extended light source is carried out to clarify the types of light sources to be added and their corresponding parameters. For example, it may be necessary to add light sources with specific wavelengths, different illumination angles, or a light source configuration for multi-band joint detection. Finally, a complete detection scheme that can cover different light source conditions is designed. Through the demand analysis, the detection bottlenecks under the current light source conditions can be comprehensively understood, and a clear direction can be provided for the subsequent scheme design. According to the different characteristics of different defect types and wafer materials, appropriate light source parameters are determined, and an extended light source detection scheme with high adaptability is designed.

[0054] More specifically, based on the results of the demand analysis, light sources with different wavelengths, intensities, and incident angles are selected for combination. These light sources include various types such as ultraviolet light, infrared light, and white light. Which specific light sources to choose needs to be combined with the wafer material, defect type, and production process requirements. According to the size and shape of the wafer, the layout of the light sources is designed to ensure that the light sources can evenly illuminate the wafer surface. Usually, the distribution method of the light sources (such as annular, radial, etc.) and the change of the illumination angle are considered to capture the detailed information of different regions on the wafer surface. According to the selected light source configuration, corresponding detectors (such as photodiodes, CCD sensors, etc.) are designed to capture the light signals reflected from the wafer surface. The number and position of the detectors should match the light sources to obtain the best detection results. In the extended light source scheme, it may be necessary to realize the synchronous or alternating operation of multiple light sources to ensure that each light source can comprehensively detect the defects on the wafer surface at different time periods and different positions. At this time, it is necessary to coordinate the working frequency and synchronization mechanism of the light sources to avoid interference.

[0055] More specifically, by designing a variety of different types of light sources and layout schemes, the visibility of the defects on the wafer surface can be improved. In particular, defects that are not easily detected under conventional light sources (such as microcracks, surface scratches, etc.) can be more accurately identified. By precisely designing the light source layout, the full coverage of each region on the wafer surface is ensured, reducing the problem of missed detection caused by uneven light source coverage.

[0056] More specifically, according to the extended light source detection scheme, different light sources are activated to detect the wafer round by round or synchronously. During each round of detection, the wavelength, intensity, and incident angle of the light source are adjusted according to the designed light source parameters. During each round of detection, a detector is used to collect the optical signal data reflected from the wafer surface. These data usually include information such as light intensity, reflection image, and transmission image. The collected data is preprocessed, including denoising, normalization, contrast adjustment, etc., to ensure the data quality. The extended data of each round of detection is stored in the database and the corresponding light source conditions (such as light source type, wavelength, incident angle, etc.) are marked. By using the extended light source, multi-dimensional optical detection data (such as reflection and transmission data under different light sources) are obtained, providing rich information for subsequent defect identification. The collected extended data can effectively supplement the defect features that may be missed under the conventional light source, improving the comprehensive identification ability of the entire detection system.

[0057] More specifically, the multi-dimensional detection data obtained from the extended light source detection is input into the adjusted wafer detection feedback model. At this time, the model will receive the extended data including information such as light source type, wavelength, and incident angle. The model performs defect identification and classification based on the extended detection data and outputs the defect information of each detection area. These results may include defect type, defect location, defect size, etc. According to the defect identification results fed back by the extended detection data, the model can perform further self-optimization and adjustment. For example, if the detection results under a certain light source condition are not ideal, the model can adjust the relevant parameters according to the feedback to improve the accuracy of the next round of detection. By substituting the extended light source data into the model, it can help the model better understand the defect characteristics under different light source conditions, thereby improving the accuracy and comprehensiveness of defect identification. The model can continuously adjust and optimize itself through feedback learning, adapt to various light source configurations, and improve the robustness and stability in different production environments.

[0058] It can be understood that through the extended light source detection scheme, the model can comprehensively collect the defect data on the wafer surface, including the tiny defects that are difficult to detect under different light source conditions, thus significantly improving the detection accuracy. The combination of the extended light source detection scheme and the model feedback mechanism enables the detection system to flexibly adapt to different types of wafers, different defects, and different production environments. Through multiple light source configurations and data feedback, the system can more comprehensively identify various types of defects, especially the defects that are difficult to find under the conventional light source, such as surface microcracks and transparency changes. In summary, by analyzing the extended light source detection requirements, designing the extended light source detection scheme and combining it with the wafer detection feedback model, the accuracy, comprehensiveness, and adaptability of wafer detection can be greatly improved, optimizing the detection efficiency of the production line and reducing the phenomena of missed detection and misdetection.

[0059] The present invention provides an adaptive regulation method for the brightness of a wafer detection light source, which has the following beneficial effects:

[0060] The present invention preliminarily irradiates a wafer through a preset annular light source, collects initial image data, performs digital simulation based on the initial detection data to generate a wafer detection feedback model, analyzes the light source irradiation requirements based on the detection feedback model to generate a gradient execution plan, configures the light source parameters in sequence according to the gradient plan, performs multiple rounds of detection on the wafer and collects data, feeds the detection data back to the model for parameter adjustment, analyzes the extended light source detection requirements of the adjusted model to generate an extended detection plan, and performs a final detection. This method realizes efficient and accurate detection of wafer surface defects through automatic adjustment of the light source brightness and configuration, improves the detection accuracy and efficiency, adapts to the detection requirements of different wafers, and solves the problem that the light source used for detection in the prior art is not comprehensive enough, resulting in undetected defects.

[0061] Preferably, the step of performing initial light source irradiation on the wafer to be detected in a surrounding state through a preset annular light source and collecting image data of the wafer to be detected under the initial light source irradiation in the surrounding state to obtain the initial detection data of the wafer to be detected includes:

[0062] S11: Configure the initial brightness parameters and initial orientation parameters for each light source unit in the preset annular light source, so that each light source unit in the annular light source is in an initial irradiation state, and each light source unit in the initial irradiation state performs initial light source irradiation on the wafer to be detected in a surrounding state;

[0063] S12: Configure the parameters of the camera positions and camera modes for a preset number of camera modules, so that each camera module collects image data of the wafer to be detected, and obtains detection images of the wafer to be detected at each camera position by the camera module in the camera mode. All the detection images together form the initial detection data of the wafer to be detected.

[0064] Specifically, according to the characteristics of the wafer to be detected (such as material, surface reflection characteristics, etc.), adjust the initial brightness parameters of each light source unit in the annular light source. This can be achieved by adjusting the output power of each light source unit to ensure that the brightness of the light source can illuminate the surface of the wafer without causing overexposure. Adjust the irradiation angle of each light source unit so that the light source uniformly irradiates the wafer surface from different angles, avoiding shadows and dead corners caused by the irradiation of a single-angle light source, thereby improving the visibility of defects. Configure each light source unit to be in the initial irradiation state to ensure that the light source can uniformly and continuously irradiate the wafer, forming a surrounding initial light source irradiation condition. By precisely setting the brightness and orientation of the light source unit, it is possible to ensure uniform irradiation of each area on the wafer surface, minimizing the missed detection problems caused by shadows and non-uniform irradiation. By adjusting the brightness and angle of the light source, the irradiation method can be flexibly adjusted according to different wafer materials and surface optical characteristics, enhancing the effectiveness of defect recognition.

[0065] More specifically, determine the installation position of the camera module to ensure that the wafer can be comprehensively photographed from multiple angles. According to the layout of the annular light source, set camera modules at different positions (for example: inside and outside the annular light source, different shooting angles, etc.) to ensure full coverage of the wafer surface. Set the working mode of each camera module according to the detection requirements, usually including: resolution, focusing mode, exposure time, image acquisition rate, etc. Different working modes can help capture defects of different sizes and characteristics, enhancing the diversity and comprehensiveness of the data. Under the configuration of different camera modules, ensure that they synchronously or alternately collect image data on the wafer surface at different angles and in different modes. At this time, the working parameters of all camera modules should be coordinated uniformly to avoid mutual interference. By reasonably arranging the positions of the camera modules, ensure that images are collected from multiple perspectives to comprehensively reflect the surface condition of the wafer. Through precise setting of the camera mode parameters, ensure that each camera module obtains clear and high-quality image data with appropriate exposure, resolution, and focus, providing a more reliable image basis for subsequent analysis.

[0066] More specifically, according to the set camera positions and modes, multiple camera modules will simultaneously or sequentially collect images of the wafer surface. Each camera module will obtain image data at the corresponding position and in a specific mode. The collected image data will undergo necessary preprocessing operations such as denoising, image enhancement, and brightness equalization to ensure that the images are clear and the details are distinguishable. The detection image data from different camera modules will be combined to form complete initial detection data. This initial detection data includes multi-angle and multi-view image information of the wafer surface under different angles and different light source irradiations, comprehensively reflecting the state of the wafer surface. By precisely configuring the parameters of the camera modules, it is ensured that each camera module can obtain clear and high-resolution images, thereby improving the accuracy of defect recognition. Through the cooperation of multiple camera modules, it is guaranteed that the image data covers all areas of the wafer surface, providing rich information for subsequent defect analysis.

[0067] More specifically, the image data obtained from different positions and under different light source irradiations are summarized to form preliminary detection data. This data will be used as the input for subsequent defect detection, defect classification, and model optimization. The initial detection data is preliminarily analyzed to identify possible surface defects and defective areas. This information can provide a reference for subsequent defect diagnosis and repair processes. By summarizing multi-angle and multi-mode image data, the initial detection data contains comprehensive information about the wafer surface, providing a more valuable basis for subsequent analysis. The high quality and comprehensiveness of the initial detection data enable subsequent defect recognition models to more accurately identify and classify minor defects on the wafer surface.

[0068] It can be understood that by setting the annular light source, it is ensured that the wafer surface is evenly and omnidirectionally irradiated, reducing the problem of missed detection caused by uneven light source irradiation. The collaborative work of multiple camera modules can comprehensively cover the wafer surface, not only avoiding dead corners but also improving the accuracy of defect recognition through different modes. The multi-dimensional image data collected can provide more information for subsequent defect analysis, ensuring that the system can adapt to different types of wafers and defects. Due to the high quality and all-roundness of the initial detection data, subsequent defect detection systems can use this data for more accurate defect analysis and judgment, thereby improving the overall detection efficiency and accuracy.

[0069] Preferably, the steps of performing digital simulation on the wafer to be detected according to the initial detection data of the wafer to be detected to obtain the wafer detection feedback model, and based on the wafer detection feedback model, analyzing the gradient scheme of the subsequent light source irradiation requirements for the annular light source to obtain the light source irradiation gradient execution scheme include:

[0070] S21: Analyze the initial detection data of the wafer to be detected to obtain the wafer basic information and wafer detection information of the wafer to be detected; wherein, the wafer basic information is used to describe the wafer specifications and wafer shape of the wafer to be detected, and the wafer detection information is used to describe the detection conditions presented on the wafer surface of the wafer to be detected.

[0071] S22: Perform digital simulation on the wafer to be detected according to the wafer basic information of the wafer to be detected to obtain a wafer detection feedback model for digital twin simulation feedback of the wafer to be detected; wherein, the wafer detection feedback model includes a wafer substrate simulation part and a wafer surface simulation part.

[0072] S23: Substitute the wafer detection information into the wafer detection feedback model to adjust the model parameters of the wafer surface simulation part of the wafer detection feedback model according to the wafer detection information, so as to perform digital simulation feedback on the wafer surface detection conditions of the wafer to be detected through the wafer surface simulation part after model parameter adjustment.

[0073] S24: Analyze the wafer quality at each specific position on the wafer surface simulation part of the wafer detection feedback model to obtain the detection quality characteristic distribution of the wafer detection feedback model, and extract and label the defect characteristics of the wafer detection feedback model according to the detection quality characteristic distribution to obtain a defect annotation set on the wafer detection feedback model; wherein, the defect annotation set is used to perform digital feedback on the defects on the wafer to be detected on the wafer detection feedback model.

[0074] S25: Analyze the light source detection effect at each specific position on the wafer surface simulation part of the wafer detection feedback model based on the initial light source irradiation to obtain the light source detection defect type adaptation range corresponding to the detection quality characteristic distribution of the wafer detection feedback model.

[0075] S26: Perform difference analysis on the light source detection defect type adaptation range according to the preset standard of the defect type to be detected to obtain several subsequent light source detection defect type adaptation ranges to be executed, and perform working parameter analysis and execution gradient arrangement on the annular light source according to the several subsequent light source detection defect type adaptation ranges to be executed to obtain the light source irradiation gradient execution scheme of the annular light source corresponding to the several subsequent light source detection defect type adaptation ranges to be executed.

[0076] Specifically, it includes geometric features such as the specifications and shapes of wafers (e.g., diameter, thickness, curvature, etc.). These data are used to establish a digital model of the wafer to ensure that the simulation is consistent with the shape and size of the actual physical wafer. It involves the detection conditions shown on the wafer surface (e.g., defect types, defect distribution, surface roughness, etc.). These information are used to describe the current state of the wafer surface and provide a reference for subsequent simulations and feedback adjustments. By accurately analyzing the initial data, it ensures that the basic information for subsequent simulations fully reflects the characteristics and current state of the actual wafer, providing a reliable basis for subsequent operations. Combining the geometric information of the wafer with the detection conditions ensures that both the physical characteristics of the wafer and its surface defects are considered during the simulation process.

[0077] More specifically, through digital simulation technology (based on the basic information of the wafer), a digital twin model of the wafer to be detected is established to generate a wafer detection feedback model for detection feedback. This model includes two main parts: the wafer substrate simulation part simulates the basic physical structure of the wafer, including the material properties, thickness, etc. of the wafer. The wafer surface simulation part simulates the topography, defects and other characteristics of the wafer surface according to the initial detection data. Through digital twin technology, it can accurately reproduce the physical state and surface defects of the wafer, providing a precise virtual platform for subsequent light source and defect analysis. The simulated model can provide real-time feedback on the changes in the wafer surface, thus providing data support for the optimization of the light source irradiation strategy.

[0078] More specifically, substitute the actually collected wafer detection information into the feedback model, especially the wafer surface simulation part. By adjusting the simulation parameters (such as the distribution, depth, etc. of surface defects) to more accurately reflect the surface condition of the wafer. By adjusting the model parameters in real time, it can make accurate simulation feedback according to the actual wafer surface state (such as defect type, distribution, etc.), improving the accuracy of the simulation results. The adjusted model is closer to the actual wafer detection situation, providing more practical data for subsequent light source irradiation optimization and defect detection.

[0079] More specifically, through the surface simulation part of the simulation feedback model, quality analysis is carried out for each specific position of the wafer to judge the detection conditions of each position. According to the results of the wafer quality analysis, defect characteristics are extracted and marked to form a defect marking set. This marking set reflects the specific positions, types and severity levels of the surface defects of the wafer. By analyzing the simulation data and defect marking, it can accurately identify the problem areas on the wafer surface, providing guidance for subsequent light source irradiation strategies and defect repair. It can not only qualitatively judge the defect types, but also quantitatively analyze the severity of the defects, facilitating subsequent processing.

[0080] More specifically, based on the initial light source irradiation conditions, the light source effect analysis is carried out on the wafer surface simulation part in the feedback model to determine the influence of different light source irradiations on the wafer surface defects. Combining the light source detection effect, it is analyzed which types of defects can be detected under different light source irradiation conditions and which defects are not easily discovered under the existing light source conditions. Through the adaptation analysis of the light source and defect types, the optimal light source configuration can be selected for each defect type, thereby maximizing the detection efficiency. By analyzing the adaptability of the light source to different defects, it is possible to guide the optimization of subsequent light source irradiation parameters to improve the defect detection rate.

[0081] More specifically, based on the preset defect type standard, the difference analysis of the adaptation range of the light source detection defect types is carried out to identify which light source irradiation conditions are suitable for a certain defect type and which are not. According to the analysis results, the gradient scheme of the light source irradiation requirements is determined, and the corresponding light source irradiation gradient execution scheme is arranged for each defect type adaptation range. By implementing the gradient scheme, the most suitable light source irradiation method can be adopted for different defect types to improve the utilization efficiency of the light source. The gradient analysis ensures that each defect type can obtain the best light source irradiation, improving the intelligence and accuracy of the detection. Through the gradient execution of the light source, unnecessary light source waste is avoided, while the detection efficiency is improved and the potential impact of overexposure on the wafer surface is reduced.

[0082] It can be understood that through digital simulation and defect type adaptation analysis, accurate light source configuration for different defect types can be achieved, thereby maximizing the detection accuracy. The whole process reduces manual intervention through digital twin simulation, real-time adjustment and the design of the gradient execution scheme, improving the automation and intelligence level of the detection process. Through multi-angle and multi-mode simulation feedback and optimization analysis, it can be ensured that all potential defects on the wafer surface can be accurately detected under different light source irradiation conditions. Based on the gradient analysis of the light source requirements, the efficient utilization of the light source is ensured, reducing unnecessary resource waste. Generally speaking, this process makes the light source irradiation configuration more accurate and intelligent through the combination of digital simulation and feedback control, significantly improving the effect and efficiency of wafer defect detection.

[0083] Preferably, the step of analyzing the light source detection effect at each specific position on the wafer surface simulation part of the wafer detection feedback model based on the initial light source irradiation to obtain the adaptation range of the light source detection defect types corresponding to the detection quality feature distribution of the wafer detection feedback model includes:

[0084] S251: Divide the positioning grid coordinate system of the wafer surface simulation part of the wafer detection feedback model to obtain a positioning grid coordinate system for dividing the wafer surface simulation part into several positioning grids with positioning coordinates;

[0085] S252: performing grid decomposition processing on the initial light source illumination based on the positioning grid coordinate system to obtain a light source illumination parameter distribution corresponding to the detection quality feature distribution;

[0086] S253: performing adaptability analysis of detection effects on several preset wafer defect detection types according to the light source illumination parameter distribution, so as to obtain the adaptability of the detection effects of the light source illumination parameter distribution corresponding to various wafer defect detection types;

[0087] S254: performing a combined analysis on the detection effect adaptability of the light source illumination parameter distribution corresponding to various wafer defect detection types to obtain an adaptability range of the light source detection defect type corresponding to the detection quality feature distribution of the wafer detection feedback model.

[0088] Specifically, the wafer surface simulation part of the wafer detection feedback model is divided to create a positioning grid coordinate system, which divides the wafer surface into several grid areas with positioning coordinates. Each grid area represents a specific position on the wafer surface, which is convenient for the subsequent analysis and evaluation of the light source illumination effect. Through this grid division, each position in the model can be accurately associated with the actual detection effect. By finely dividing the grid coordinate system, the light source detection effect of each grid position can be evaluated separately, thereby improving the accuracy of positioning and analysis. This grid division can help to systematically organize the detection data and provide a basis for the subsequent light source illumination parameter distribution analysis.

[0089] More specifically, based on the above positioning grid coordinate system, the initial light source illumination conditions (including light source intensity, illumination angle, illumination range, etc.) are decomposed into grids, which means that each grid area will have an independent light source illumination parameter allocation. Through this decomposition, you can set different light source illumination conditions for each grid area separately to obtain a complete light source illumination parameter distribution map, in which the light source illumination conditions at each grid position have clear values. The decomposition of light source illumination ensures that each grid area can obtain accurate light source illumination according to the needs of its specific location, which improves the flexibility and accuracy of detection. Different areas may require light source illumination of different intensities. The decomposition process can ensure that the light source illumination of each area is optimized in a targeted manner.

[0090] More specifically, according to the light source irradiation parameter distribution of each grid area, an adaptive analysis is carried out on a preset number of wafer defect detection types. Specifically, for each defect type (e.g., surface scratches, cracks, bubbles, etc.), its detection effect under different light source irradiation conditions is evaluated. This step is to analyze whether the light source irradiation can effectively highlight or detect these defects by comparing the light source irradiation parameters with the response model of each defect. Analyzing the detection effects of different types of defects under specific light source irradiation conditions helps to determine the most suitable light source configuration for a certain defect type. By performing an adaptive analysis on the detection effects of each defect, the adaptability of different light source irradiation conditions to different defect types can be quantified, thus providing data support for light source configuration.

[0091] More specifically, a combined analysis is carried out on the detection effect fitness for each wafer defect type. By combining the detection effects of each grid area under different light source irradiations, the overall detection quality characteristic distribution can be obtained, and then the suitable defect types under each light source irradiation condition can be determined. The result of the combined analysis is the "light source detection defect type adaptation range", that is, under specific light source conditions, which defect types can be effectively detected and which may be missed or inadequately detected. Through the combined analysis, the interaction effects of multiple light source conditions and defect types can be comprehensively considered, and an optimal light source configuration scheme can be given. The combined analysis can help determine the light source irradiation range most suitable for various defects and optimize the overall detection scheme.

[0092] More specifically, the result obtained through the combined analysis can determine the light source detection defect type adaptation range corresponding to the detection quality characteristic distribution of the wafer detection feedback model. This adaptation range indicates the wafer defect types that can be effectively detected under specific light source irradiation conditions. This adaptation range provides a basis for the subsequent light source irradiation execution plan, enabling more accurate defect detection. The analysis of the light source adaptation range ensures that each defect type can be effectively detected under specific light source irradiation, avoiding missed detections caused by improper light source configuration. By optimizing the light source adaptation range, the efficient utilization of light source irradiation resources can be achieved, not only improving the detection accuracy but also reducing energy consumption.

[0093] It can be understood that the entire process from light source irradiation analysis to the determination of the defect type adaptation range combines the following technical effects: Through detailed grid division and light source parameter decomposition, precise light source adjustment for different wafer regions and defect types is achieved. Through the fitness analysis of each defect, it is ensured that different types of defects can obtain the best detection effects, avoiding missed detections and misdetections. The light source adaptation range after combined analysis can provide clear guidance for subsequent detections, ensuring the high efficiency of light source configuration and the reliability of detection quality. Through the precise light source irradiation gradient execution plan, the detection efficiency is improved and the energy consumption is reduced.

[0094] Preferably, the step of sequentially configuring the light source parameters of the annular light source according to the light source irradiation gradient execution scheme, so that the annular light source sequentially applies the detection light source irradiation to the wafer to be detected, and thereby obtaining the gradient detection data of the wafer to be detected under each round of detection light source irradiation includes:

[0095] S31: Sequentially configure the gradient brightness parameter and the gradient orientation parameter for each light source unit in the annular light source according to the light source irradiation gradient execution scheme, so that each light source unit in the annular light source is in a gradient irradiation state, and each light source unit in the gradient irradiation state performs gradient light source irradiation on the wafer to be detected in a surrounding state;

[0096] S32: Configure the parameters of the imaging position and the imaging mode for a plurality of pre-set imaging modules according to the light source irradiation gradient execution scheme, so that each imaging module collects image data of the wafer to be detected, and the detection images obtained by the imaging modules in the imaging mode at each imaging position of the wafer to be detected are obtained. Each of the detection images jointly constitutes the gradient detection data of the wafer to be detected.

[0097] Specifically, according to the light source irradiation gradient execution scheme, the gradient brightness parameter and the gradient orientation parameter are sequentially configured for each light source unit in the annular light source. The brightness of each light source unit changes gradually, and different brightness light source irradiations can be applied at different positions, so that the brightness of the irradiation of each light source unit on the wafer surface forms a gradient state. By adjusting the irradiation direction of the light source, it is ensured that the light rays of each light source unit face different angles, forming a gradient irradiation angle, thereby providing a surrounding light source irradiation mode. By adjusting the gradient of the brightness and the orientation, the uniform irradiation of the annular light source on the wafer surface can be realized, while avoiding the errors caused by too strong or too weak irradiation, ensuring the balance of the light source irradiation. Through the adjustment of the gradient orientation, the wafer to be detected can be irradiated at multiple angles, enhancing the detection ability for different regions on the wafer surface, especially for wafers with complex geometric shapes or special defects.

[0098] More specifically, according to the light source illumination gradient execution plan, the camera positions and camera modes of a number of pre-set camera modules are configured: the positioning of the camera modules is adjusted according to the position of the wafer to be detected and the illumination area of the annular light source. The camera modules should collect images at multiple angles and positions to ensure full coverage of the surface of the wafer to be detected. The working modes of the camera modules (such as exposure time, focusing, imaging mode, etc.) are adjusted according to different light source illumination states to optimize the image quality under different light source gradients. Each camera module collects image data of the wafer to be detected according to its camera position and mode, and obtains the detection images of the wafer at each camera position. All these images together constitute the gradient detection data of the wafer to be detected.

[0099] More specifically, by configuring multiple camera modules and adjusting their positions, image data of the wafer to be detected can be obtained from different perspectives, avoiding blind spots that may be caused by a single angle, thus ensuring comprehensive detection coverage. By configuring the camera mode according to different light source gradients, parameters such as exposure time and focusing can be adjusted according to the lighting conditions to ensure that images under different light source illuminations can maintain high quality. Especially in low-brightness or high-brightness areas, multiple camera modules combined with the change of the light source illumination gradient can capture the details of the wafer surface under different lighting conditions, especially the defect information at different brightnesses and angles, improving the accuracy and sensitivity of detection.

[0100] More specifically, the detection images obtained by each camera module together constitute the gradient detection data of the wafer to be detected. These images contain the surface information of the wafer under different light source illumination conditions and can be used to analyze the quality status of the wafer. After these images are post-processed (such as image stitching, feature extraction, etc.), they can be further used in analysis processes such as defect identification, defect localization, and defect classification. The formation of the gradient detection data is based on image data under multi-angle and multi-brightness conditions, thus ensuring that all defects on the wafer surface can be discovered and recorded. By integrating image data from multiple perspectives and different light source illumination states, higher-dimensional wafer defect information can be obtained, providing more basis for subsequent defect analysis and determination. Through the synthesized gradient detection data, different types of wafer defects, such as micro-scratches, bubbles, cracks, etc., can be efficiently identified, especially in the detection of complex surfaces or micro-defects, improving the detection accuracy.

[0101] It can be understood that by configuring the brightness and orientation gradient of each light source unit in the annular light source, a multi-angle and gradient illumination mode can be achieved, which is crucial for the detection of complex wafer surfaces and different types of defects. The position and mode configuration of the camera module ensure that high-quality image data can be collected from all areas of the wafer surface, avoiding missed detections caused by a single perspective. The obtained gradient detection data, through multiple camera modules obtaining images from different angles and different illumination states, can comprehensively reflect the state of the wafer surface, improving the accuracy and reliability of defect recognition. Through the precise cooperation of the light source illumination gradient and image acquisition, fine defects on the wafer surface can be effectively detected, especially in areas with low contrast, thereby optimizing the sensitivity and accuracy of defect detection.

[0102] Preferably, the step of substituting the gradient detection data of the wafer to be detected under each round of detection light sources into the wafer detection feedback model to adjust the model parameters of the wafer detection feedback model includes:

[0103] S41: Substitute the gradient detection data of the wafer to be detected under each round of detection light sources into the wafer surface simulation part of the wafer detection feedback model, and let the wafer surface simulation part of the wafer detection feedback model perform data allocation processing on the gradient detection data under each round of detection light sources, so that the gradient detection data has a corresponding relationship with the specific positions of each part of the wafer surface simulation part;

[0104] S42: Analyze the gradient detection data according to the range of light source detection defect types corresponding to the gradient detection data to obtain the defect detection results feedback by the gradient detection data, and substitute the defect detection results feedback by the gradient detection data into the specific positions of each part of the wafer surface simulation part according to the corresponding relationship between the gradient detection data and the specific positions of each part of the wafer surface simulation part;

[0105] S43: Adjust the model parameters of the specific positions of each part of the wafer surface simulation part according to the defect detection results feedback by the gradient detection data, and perform a comprehensive weight analysis on the model parameters adjusted for the defect detection results feedback by the gradient detection data corresponding to each round of the specific positions of each part of the wafer surface simulation part, so as to finally determine the model parameters of the specific positions of each part of the wafer surface simulation part.

[0106] Specifically, substitute the gradient detection data obtained from the wafer to be detected under different rounds of detection light sources into the wafer surface simulation part of the wafer detection feedback model. The wafer surface simulation part is responsible for simulating the surface characteristics of the wafer according to the model. The goal of this step is to ensure that the detection data can be accurately corresponding to the specific positions in the wafer surface simulation part. That is, according to the specific positions of each data point in the gradient detection data, match it with the corresponding position in the simulation part to ensure the accuracy of data allocation. By corresponding the gradient detection data with the specific positions of the wafer surface simulation part, the relationship between each data point and the corresponding position in the simulation model can be ensured, avoiding the situation of data offset or incorrect correspondence, and improving the accuracy of the model. This step can ensure that the detection data of each point on the wafer surface has been accurately processed, which is crucial for subsequent defect analysis and model adjustment.

[0107] More specifically, according to the range of defect types adapted to the light source detection corresponding to the gradient detection data, perform data parsing. This step aims to identify the defect types (such as cracks, bubbles, scratches, etc.) reflected by each gradient detection data point. According to the parsing results of each data point, obtain the defect detection results at this position, and correspond these defect detection results with the specific positions of the wafer surface simulation part one by one. For example, if a scratch is detected at a certain position, the defect detection result corresponding to this position will be fed back to this position in the wafer surface simulation model. By parsing the gradient detection data and feeding back defect information, accurate judgments can be made for the specific defects at each position, which is crucial for the positioning and analysis of defects. Since the gradient detection data is obtained under different light source irradiations, it can more comprehensively feedback the defect information on the wafer surface under different conditions, avoiding the missed detection that may be caused by a single light source. This parsing and feedback mechanism can capture the minute defects or subtle changes on the wafer surface, improving the sensitivity and accuracy of defect detection.

[0108] More specifically, according to the defect detection results at each position, adjust the model parameters of the wafer surface simulation part. Specifically, if a defect is detected at a certain position, the parameters at this position of the model will be adjusted accordingly. For the defect detection results fed back by each round of gradient detection data, comprehensively analyze its influence on different positions of the wafer surface simulation part. This involves weighting the defect feedback at each position, and finally determining the optimal model parameters at each position. By adjusting the parameters of the wafer surface simulation part in real time, the model can self-adjust according to the actual defect feedback, thereby improving the adaptability and accuracy of the model. This adjustment can ensure that the model can make accurate adjustments when facing different types and positions of defects, avoiding the accuracy loss caused by large-scale adjustments. By performing weighted analysis on the defect detection results at each position, the interference of single data can be avoided, and the feedback effects of each data point can be comprehensively considered, thereby ensuring the accuracy and reliability of model parameter adjustment.

[0109] More specifically, through the aforementioned adjustment and weight analysis, the model parameters at each position of the wafer surface simulation part are finally determined. These parameters reflect the state of each point on the wafer surface under specific light source conditions, including defect information and wafer surface features. Through multiple rounds of gradient data feedback and model parameter adjustment, the finally obtained model has high accuracy, can better adapt to the actual detection requirements. The precise model parameters enable the defect detection system to more efficiently identify and locate various defects on the wafer surface, improving the reliability and efficiency of the detection process.

[0110] It can be understood that through the precise analysis of gradient detection data, various types of defects on the wafer surface can be identified and fed back. The model is adjusted according to the real-time defect feedback to ensure that the simulation parameters at each detection position are more accurate, enhancing the adaptability of the model. With the support of multi-round detection data under different light source conditions, the wafer defects can be comprehensively and finely identified, improving the robustness and precision of the detection system. The comprehensive weight analysis ensures that the adjustment of model parameters is more refined, avoiding unnecessary over-adjustment, and finally obtaining an optimized wafer surface simulation result, improving the overall detection effect.

[0111] Preferably, the steps of analyzing the extended light source detection requirements according to the wafer detection feedback model after model parameter adjustment to obtain the extended light source detection scheme for the wafer to be detected, and detecting the wafer to be detected according to the extended light source detection scheme to obtain extended detection data and substituting them into the wafer detection feedback model include:

[0112] S51: Obtain the performance information of the pre-set extended light source module; wherein, the extended light source module includes a laser light source module and a polarized light source module;

[0113] S52: Perform fixed-point analysis of potential defects on the wafer detection feedback model after model parameter adjustment to obtain the potential defect detection points of the wafer detection feedback model;

[0114] S53: Analyze the extended light source detection requirements for the potential defect detection points according to the performance information of the extended light source module to obtain the extended light source detection schemes for each of the potential defect detection points of the wafer to be detected;

[0115] S54: Configure the parameters of the extended light source module according to the extended light source detection scheme, so that the extended light source module performs extended light source application processing on the wafer to be detected in a specified form, and collect images of the potential defect detection points of the wafer to be detected under the extended light source application processing in a specified form through a pre-set camera module to obtain extended detection data;

[0116] S55: Substitute the expanded detection data into the specific position corresponding to the potential defect detection point in the wafer detection feedback model, and let the wafer detection feedback model perform real-time analysis on the expanded detection data to adjust the model parameters of the wafer detection feedback model, so as to digitally feedback the actual situation of the wafer to be detected.

[0117] Specifically, obtain the performance information of the pre-set expanded light source module. The expanded light source module includes a laser light source module and a polarized light source module. The laser light source module is usually used for focusing and positioning minute defects on the wafer surface, such as cracks, minute scratches, etc. The polarized light source module is used to detect the reflection characteristics of the wafer surface, which can reveal the internal stress, texture and some relatively hidden defects of the material. By obtaining the performance information of the light source module, targeted applications of different types of light sources can be carried out to ensure that the characteristics of each light source can be most matched with the detection target (defects on the wafer surface), improving the effectiveness of subsequent detection. The combination of different light source modules enables the system to perform all-round detection of the wafer under different optical conditions, better revealing potential defects.

[0118] More specifically, perform fixed-point analysis of potential defects on the wafer detection feedback model whose model parameters have been adjusted to identify potential defect detection points, which refer to the positions on the wafer surface where defects or flaws may exist. Through the feedback model, these potential defect areas can be identified, and these areas often require further refined detection. Through fixed-point analysis, possible defect points can be identified from the overall scan, providing a clear direction for subsequent more in-depth detection. By optimizing the selection of detection points, non-discriminatory detection of the entire wafer surface can be avoided, saving time and resources and focusing on areas with more potential defects.

[0119] More specifically, according to the performance information of the expanded light source module, conduct an analysis of the expanded light source detection requirements for potential defect detection points and formulate an expanded light source detection plan for each detection point. This plan determines which light source (laser or polarized light) to use and how to apply the light source (such as the angle and intensity of the light source) according to the nature of the detection point and the problems to be solved (such as cracks, stress, reflection characteristics, etc.). This kind of analysis can select a suitable light source for precise irradiation and imaging for different potential defect positions, avoiding the use of redundant light sources and at the same time improving the accuracy of defect identification. The customized light source usage plan can adopt different detection strategies for different types of defects (such as surface scratches, minute cracks, stress points, etc.), improving the comprehensiveness and accuracy of detection.

[0120] More specifically, according to the extended light source detection scheme, the parameters of the extended light source module are configured to ensure that it can apply light sources to the wafer according to the set requirements. For example, a laser light source can irradiate the wafer surface at a specific angle, and a polarized light source can select different polarization angles. The wafer with the extended light source applied is subjected to image acquisition through a preset camera module. After the camera module obtains the image data, it is used for further analysis. Especially around the potential defect detection points, according to the specific extended light source requirements, adjusting the parameters of the light source module can ensure the best light source irradiation method for each potential defect point, thereby improving the sensitivity and accuracy of detection. The cooperation of the camera module ensures that the images collected through the extended light source can have sufficient clarity and details, providing reliable data support for subsequent image analysis and defect location.

[0121] More specifically, the extended detection data (i.e., the image data obtained through the extended light source module and the camera module) is substituted into the wafer detection feedback model. These data will correspond to the specific positions of the potential defect detection points. The model will perform further on-site analysis of the wafer surface based on these data. On the basis of the analysis, the model will adjust the parameters again according to the new data, so as to perform digital feedback on the actual situation of the wafer to be detected. Through on-site analysis and parameter adjustment, the wafer detection feedback model can self-optimize after each round of detection, continuously improving the ability to identify wafer defects. The digital feedback enables the detection personnel to obtain the defect information of the wafer in real time, so as to make decisions and corrections faster, improving the efficiency and quality of the production process.

[0122] It can be understood that by obtaining the performance information of the extended light source module and formulating a light source scheme that meets the requirements of potential defect detection, different defects can be detected under the best conditions. Through the on-site analysis of potential defects on the wafer surface, the area where defects may exist can be quickly and accurately located, providing a precise target for subsequent in-depth detection. Customizing the extended light source detection scheme for each potential defect point ensures efficient detection under the most suitable light source conditions. After the extended light source is applied, high-quality images are obtained through the camera module, and then analyzed and real-time feedback is performed through the wafer detection feedback model, continuously adjusting the model parameters to improve the detection accuracy.

[0123] Refer to Figure 2 As shown, in a second aspect, the present invention provides an adaptive regulation device for the brightness of a wafer detection light source, which is used to implement the adaptive regulation method for the brightness of a wafer detection light source described in any one of the first aspects, and includes:

[0124] An initial detection module, configured to perform initial light source irradiation on a wafer to be detected in a surrounding state by a pre-set annular light source, and collect image data of the wafer to be detected under the initial light source irradiation in the surrounding state, so as to obtain initial detection data of the wafer to be detected;

[0125] A scheme analysis module, configured to perform digital simulation on the wafer to be detected according to the initial detection data of the wafer to be detected, so as to obtain the wafer detection feedback model, and perform gradient scheme analysis on subsequent light source irradiation requirements of the annular light source based on the wafer detection feedback model, so as to obtain a light source irradiation gradient execution scheme;

[0126] A gradient detection module, configured to sequentially configure light source parameters for the annular light source according to the light source irradiation gradient execution scheme, so that the annular light source sequentially applies detection light source irradiation to the wafer to be detected, thereby obtaining gradient detection data of the wafer to be detected under each round of detection light source irradiation;

[0127] A data feedback module, configured to substitute the gradient detection data of the wafer to be detected under each round of detection light source into the wafer detection feedback model to adjust model parameters of the wafer detection feedback model;

[0128] An extended detection module, configured to perform extended light source detection requirement analysis according to the wafer detection feedback model after model parameter adjustment, so as to obtain an extended light source detection scheme for the wafer to be detected, and perform detection on the wafer to be detected according to the extended light source detection scheme, obtain extended detection data and substitute it into the wafer detection feedback model.

[0129] In this embodiment, for the specific implementation of each module in the above device embodiment, please refer to that described in the above method embodiment, and details are not described herein again.

[0130] The above are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for adaptively controlling the brightness of a wafer inspection light source, characterized in that: include: Using a pre-set annular light source to illuminate the wafer to be inspected in a surrounding state with an initial light source, and collecting image data of the wafer to be inspected under the illumination of the initial light source in the surrounding state, so as to obtain initial inspection data of the wafer to be inspected; Digitally simulating the wafer to be inspected according to the initial inspection data of the wafer to be inspected to obtain a wafer inspection feedback model, and performing a gradient scheme analysis of subsequent light source illumination requirements on the annular light source based on the wafer inspection feedback model to obtain a light source illumination gradient execution scheme; According to the light source illumination gradient execution scheme, the light source parameters of the annular light source are sequentially configured, so that the annular light source sequentially applies the detection light source illumination to the wafer to be inspected, thereby obtaining the gradient detection data of the wafer to be inspected under each round of detection light source illumination; Substituting the gradient detection data of the wafer to be inspected under each round of detection light source into the wafer detection feedback model to adjust the model parameters of the wafer detection feedback model; Performing an extended light source detection demand analysis according to the wafer detection feedback model after the model parameters are adjusted to obtain an extended light source detection scheme for the wafer to be detected, and detecting the wafer to be detected according to the extended light source detection scheme to obtain extended detection data and substitute it into the wafer detection feedback model; The steps of digitally simulating the wafer to be inspected according to the initial inspection data of the wafer to be inspected to obtain the wafer inspection feedback model, and performing a gradient scheme analysis of subsequent light source illumination requirements on the ring light source based on the wafer inspection feedback model to obtain a light source illumination gradient execution scheme include: Parsing the wafer basic information and wafer detection information of the initial detection data of the wafer to be detected to obtain the wafer basic information and wafer detection information of the wafer to be detected; wherein the wafer basic information is used to describe the wafer specifications and wafer shape of the wafer to be detected, and the wafer detection information is used to describe the detection status displayed on the wafer surface of the wafer to be detected; Digitally simulating the wafer to be detected according to the wafer basic information of the wafer to be detected to obtain a wafer detection feedback model for performing digital twin simulation feedback on the wafer to be detected; wherein the wafer detection feedback model includes a wafer substrate simulation part and a wafer surface simulation part; Substituting the wafer detection information into the wafer detection feedback model, so as to adjust the model parameters of the wafer surface simulation part of the wafer detection feedback model according to the wafer detection information, thereby performing digital simulation feedback on the wafer surface detection status of the wafer to be detected through the wafer surface simulation part after the model parameter adjustment; Analyzing the wafer quality at each specific location on the wafer surface simulation part of the wafer detection feedback model to obtain the detection quality characteristic distribution of the wafer detection feedback model; Based on the initial light source irradiation, the light source detection effect is analyzed at each specific position on the wafer surface simulation part of the wafer detection feedback model, so as to obtain the light source detection defect type adaptation range corresponding to the detection quality characteristic distribution of the wafer detection feedback model; Performing a difference analysis on the adaptability range of the light source defect detection type according to the preset defect type standard to be detected, so as to obtain the adaptability range of several types of light source defect detection types to be executed subsequently, and performing working parameter analysis and execution gradient arrangement of the ring light source irradiation requirements according to the adaptability range of several types of light source defect detection types to be executed subsequently, so as to obtain the light source irradiation gradient execution scheme of the ring light source corresponding to the adaptability range of several types of light source defect detection types to be executed subsequently; The steps of analyzing the light source detection effect of each specific position on the wafer surface simulation part of the wafer detection feedback model based on the initial light source irradiation to obtain the light source detection defect type adaptation range corresponding to the detection quality feature distribution of the wafer detection feedback model include: Dividing the wafer surface simulation part of the wafer detection feedback model into a positioning grid coordinate system to obtain a positioning grid coordinate system for dividing the wafer surface simulation part into a plurality of positioning grids having positioning coordinates; Performing grid decomposition processing on the initial light source illumination based on the positioning grid coordinate system to obtain a light source illumination parameter distribution corresponding to the detection quality feature distribution; Performing adaptability analysis on detection effects of several preset wafer defect detection types according to the light source illumination parameter distribution to obtain the adaptability of detection effects of the light source illumination parameter distribution corresponding to various wafer defect detection types; The adaptability of the detection effects of the light source illumination parameter distribution corresponding to various wafer defect detection types is combined and analyzed to obtain the adaptability range of the light source detection defect types corresponding to the detection quality feature distribution of the wafer detection feedback model.

2. The method for adaptively controlling the brightness of a wafer inspection light source according to claim 1, characterized in that: The steps of irradiating the wafer to be inspected with an initial light source in a surrounding state by a pre-set annular light source, and collecting image data of the wafer to be inspected under the irradiation of the initial light source in the surrounding state to obtain initial inspection data of the wafer to be inspected include: The initial brightness parameters and initial orientation parameters of each light source unit in the pre-set annular light source are configured so that each light source unit in the annular light source is in an initial irradiation state, and each light source unit in the initial irradiation state performs initial light source irradiation in a surrounding state on the wafer to be inspected; The parameters of the camera position and the camera mode are configured for several pre-set camera modules so that each of the camera modules can collect image data of the wafer to be inspected, so as to obtain a detection image of the wafer to be inspected at each of the camera positions obtained by the camera modules in the camera mode, and each of the detection images together constitutes the initial detection data of the wafer to be inspected.

3. The method for adaptively controlling the brightness of a wafer inspection light source according to claim 1, characterized in that: The steps of sequentially configuring the light source parameters of the annular light source according to the light source illumination gradient execution scheme so that the annular light source sequentially applies the detection light source illumination to the wafer to be inspected, thereby obtaining the gradient detection data of the wafer to be inspected under each round of detection light source illumination include: According to the light source illumination gradient execution scheme, the gradient brightness parameters and the gradient orientation parameters of each light source unit in the annular light source are sequentially configured, so that each light source unit in the annular light source is in a gradient illumination state, and each light source unit in the gradient illumination state performs gradient light source illumination in a surrounding state on the wafer to be inspected; According to the light source illumination gradient execution scheme, the parameters of the camera position and the camera mode are configured for several pre-set camera modules, so that each of the camera modules collects image data of the wafer to be inspected, so as to obtain a detection image of the wafer to be inspected at each of the camera positions obtained by the camera module in the camera mode, and each of the detection images together constitutes the gradient detection data of the wafer to be inspected.

4. The method for adaptively controlling the brightness of a wafer inspection light source according to claim 1, characterized in that: Substituting the gradient detection data of the wafer to be inspected under each round of detection light source into the wafer inspection feedback model to adjust the model parameters of the wafer inspection feedback model includes: Substituting the gradient detection data of the wafer to be inspected under each round of detection light source into the wafer surface simulation part of the wafer detection feedback model, and allowing the wafer surface simulation part of the wafer detection feedback model to perform data allocation processing on the gradient detection data under each round of detection light source, so that the gradient detection data is in a corresponding relationship with the specific positions of each location of the wafer surface simulation part; The gradient detection data is parsed according to the light source detection defect type adaptation range corresponding to the gradient detection data to obtain the defect detection result fed back by the gradient detection data, and according to the correspondence between the gradient detection data and the specific positions of the wafer surface simulation part, the defect detection result fed back by the gradient detection data is substituted into the specific positions of the wafer surface simulation part; The model parameters of each specific position of the wafer surface simulation part are adjusted according to the defect detection results fed back by the gradient detection data, and a comprehensive weight analysis is performed on the model parameters adjusted by the defect detection results fed back by the gradient detection data in each round at each specific position of the wafer surface simulation part, so as to finally determine the model parameters of each specific position of the wafer surface simulation part.

5. The method for adaptively controlling the brightness of a wafer inspection light source according to claim 1, characterized in that: The steps of performing an extended light source detection demand analysis according to the wafer detection feedback model after the model parameters are adjusted to obtain an extended light source detection scheme for the wafer to be detected, and detecting the wafer to be detected according to the extended light source detection scheme to obtain extended detection data and substitute it into the wafer detection feedback model include: Acquire performance information of a preset extended light source module; wherein the extended light source module includes a laser light source module and a polarized light source module; Performing a fixed-point analysis of potential defects on the wafer inspection feedback model after the model parameters have been adjusted to obtain a potential defect detection point of the wafer inspection feedback model; Performing an extended light source detection demand analysis on the potential defect detection points according to the performance information of the extended light source module to obtain an extended light source detection solution for each of the potential defect detection points of the wafer to be detected; According to the extended light source detection scheme, the extended light source module is configured with parameters so that the extended light source module applies a specified form of extended light source to the wafer to be detected, and an image of a potential defect detection point of the wafer to be detected that is subjected to the specified form of extended light source processing is captured through a preset camera module to obtain extended detection data; The extended detection data is substituted into the specific position of the potential defect detection point corresponding to the wafer detection feedback model, and the wafer detection feedback model is made to perform real-time analysis on the extended detection data so as to adjust the model parameters of the wafer detection feedback model, thereby providing digital feedback on the actual condition of the wafer to be inspected.

6. An adaptive control device for wafer inspection light source brightness, characterized in that: A method for adaptively controlling the brightness of a wafer inspection light source according to any one of claims 1 to 5, comprising: An initial detection module is used to irradiate the wafer to be detected with an initial light source in a surrounding state through a pre-set annular light source, and collect image data of the wafer to be detected under the irradiation of the initial light source in the surrounding state, so as to obtain initial detection data of the wafer to be detected; A scheme analysis module, used for digitally simulating the wafer to be inspected according to the initial inspection data of the wafer to be inspected to obtain the wafer inspection feedback model, and performing a gradient scheme analysis of the subsequent light source illumination requirements on the annular light source based on the wafer inspection feedback model to obtain a light source illumination gradient execution scheme; A gradient detection module, used to sequentially configure light source parameters of the annular light source according to the light source illumination gradient execution scheme, so that the annular light source sequentially applies detection light source illumination to the wafer to be inspected, thereby obtaining gradient detection data of the wafer to be inspected under each round of detection light source illumination; A data feedback module, used for substituting the gradient detection data of the wafer to be detected under each round of detection light source into the wafer detection feedback model, so as to adjust the model parameters of the wafer detection feedback model; The extended detection module is used to perform an extended light source detection demand analysis based on the wafer detection feedback model after model parameter adjustment to obtain an extended light source detection solution for the wafer to be detected, and to detect the wafer to be detected according to the extended light source detection solution to obtain extended detection data and substitute it into the wafer detection feedback model.

Images