UV light source accurate regulation and control method for wafer defect detection and related equipment

Abstract

The invention relates to the technical field of light source regulation and control, and discloses a UV light source accurate regulation and control method for wafer defect detection and related equipment, and the method comprises the following steps: determining initial detection parameters of wafer defect detection; obtaining a wafer surface image of the target wafer according to the initial detection parameters; identifying defect information of the wafer surface image; evaluating a detection effect value of the initial detection parameter according to the defect information; and if the detection effect value is lower than the preset detection threshold value, generating a UV light source regulation and control strategy according to the defect information. Through the implementation of the scheme of the invention, a closed-loop feedback mechanism is established by obtaining the initial detection parameters and evaluating the detection effect value, the situation that the detection effect is not ideal is found in time, the UV light source parameters are adjusted according to the situation, it is ensured that defect detection is always kept in the optimal state, and the accuracy of wafer defect detection is improved.

Description

Technical Field

[0001] The present application relates to the field of light source control technology, and in particular to a method for accurately controlling a UV light source for wafer defect detection and related equipment. Background Art

[0002] With the rapid development of integrated circuit technology and the continuous reduction of process technology, defect detection in the wafer manufacturing process has become increasingly important and challenging. As a key link in semiconductor manufacturing, wafer defect detection directly affects product yield and quality. Traditional wafer defect detection mainly relies on manual visual inspection and automatic optical inspection equipment with fixed parameters. These methods often have problems such as missed detection and false detection when facing fine defects, and it is difficult to meet the precision requirements of modern semiconductor manufacturing.

[0003] UV (ultraviolet) light source is an important optical component in wafer defect detection. Its performance and parameter settings have a decisive impact on the detection effect. However, the industry currently generally adopts an empirical fixed parameter setting method, lacking a dynamic and precise control mechanism for the UV light source. This static detection method cannot adapt to the characteristic differences of different types of wafers, and it is difficult to cope with new defect characteristics caused by process changes, resulting in limited detection accuracy and reliability. Summary of the invention

[0004] The present application provides a method for precisely controlling a UV light source for wafer defect detection and related equipment, which can at least solve the problem of low detection accuracy caused by using a UV light source with fixed parameters to detect different types of wafers in the related art.

[0005] In a first aspect, the present application provides a method for precisely controlling a UV light source for wafer defect detection, the method comprising: Determine initial inspection parameters for wafer defect inspection; Acquire a wafer surface image of the target wafer according to the initial detection parameters; Identifying defect information of the wafer surface image; Evaluate the detection effect value of the initial detection parameter according to the defect information; If the detection effect value is lower than a preset detection threshold, a UV light source control strategy is generated according to the defect information.

[0006] Optionally, in a first implementation of the first aspect of the present application, The step of identifying defect information of the wafer surface image comprises: Preprocessing the wafer surface image; Extracting defect features from pre-processed wafer surface images; Identify the corresponding defect type according to the defect characteristics; Defect information is marked on the wafer surface image according to the defect type.

[0007] Optionally, in a second implementation of the first aspect of the present application, the step of evaluating the detection effect value of the initial detection parameter according to the defect information includes: Generate a defect statistics report based on the defect information; Determine the detection rate, false detection rate and missed detection rate of the wafer defect detection according to the defect statistical report; The detection effect value is determined by converting the false detection rate and the missed detection rate into a penalty factor and performing exponential penalty on the detection rate.

[0008] Optionally, in a third implementation of the first aspect of the present application, the step of generating a UV light source control strategy according to the defect information includes: Extracting characteristic parameters of the defect information; Determine light source requirement data corresponding to the defect feature according to the feature parameter; A UV light source control strategy corresponding to the light source demand data is generated through an adaptive optimization algorithm.

[0009] Optionally, in a fourth implementation of the first aspect of the present application, the method further includes: Detect the actual output parameters of the UV light source through the light sensing sensor; Determining a first deviation value between the actual output parameter and the initial detection parameter; The UV light source control strategy is determined according to the deviation type and deviation degree corresponding to the first deviation value.

[0010] Optionally, in a fifth implementation of the first aspect of the present application, the method further includes: Detecting environmental parameters and material parameters of the target wafer by using a multi-dimensional sensor; Determine a reference value for wafer defect detection according to the environmental parameter and the material parameter; Determining a second deviation value between the reference value and the initial detection parameter; The UV light source control strategy is determined according to the second deviation value.

[0011] Optionally, in a sixth implementation of the first aspect of the present application, the method further includes: Determining the dielectric response characteristics of the target wafer under UV light irradiation based on the Jonscher general power law model; Analyze the correlation between the dielectric response characteristics and the defect type based on the Dissado-Hill model; Establishing a mapping model between wafer defect characteristics and UV light source parameters according to the association relationship; The UV light source control strategy is optimized and iterated based on the mapping model until the detection effect value reaches a preset detection threshold.

[0012] A second aspect of the present application provides a UV light source precision control device for wafer defect detection, the UV light source precision control device for wafer defect detection comprising: A determination module, used to determine initial detection parameters for wafer defect detection; An acquisition module, used for acquiring a wafer surface image of a target wafer according to the initial detection parameters; An identification module, used for identifying defect information of the wafer surface image; An evaluation module, used for evaluating the detection effect value of the initial detection parameter according to the defect information; A generation module is used to generate a UV light source control strategy according to the defect information if the detection effect value is lower than a preset detection threshold.

[0013] A third aspect of an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the processor is used to execute a computer program stored in the memory, and when the processor executes the computer program, it implements each step of the method for precisely controlling a UV light source for wafer defect detection provided in the first aspect of the embodiment of the present application.

[0014] The fourth aspect of the embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, each step of the method for precisely controlling the UV light source for wafer defect detection provided in the first aspect of the embodiment of the present application is implemented.

[0015] In summary, according to the UV light source precise control method and related equipment for wafer defect detection provided by the present application, the initial detection parameters for wafer defect detection are determined; the wafer surface image of the target wafer is obtained according to the initial detection parameters; the defect information of the wafer surface image is identified; the detection effect value of the initial detection parameter is evaluated according to the defect information; if the detection effect value is lower than the preset detection threshold, a UV light source control strategy is generated according to the defect information. Through the implementation of the present application, a closed-loop feedback mechanism is established by obtaining the initial detection parameters and evaluating the detection effect value, so as to timely discover the situation where the detection effect is not ideal, and adjust the UV light source parameters accordingly to ensure that the defect detection is always kept in the best state and improve the accuracy of wafer defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1A schematic diagram of a process flow of a UV light source precision control method for wafer defect detection provided in an embodiment of the present application; Figure 2 A schematic diagram of dielectric response test data of a non-defective area in wafer defect detection is provided for an embodiment of the present application; Figure 3 A schematic diagram of dielectric response test data of surface contamination areas in wafer defect detection is provided for an embodiment of the present application; Figure 4 A schematic diagram of a program module of a UV light source precision control device for wafer defect detection provided in an embodiment of the present application; Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, features, and advantages of the invention of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0018] In order to solve the problem of low detection accuracy caused by using a UV light source with fixed parameters to detect different types of wafers in the related art, the embodiment of the present application provides a method for accurately controlling a UV light source for wafer defect detection, such as Figure 1 The flowchart of the UV light source precise control method for wafer defect detection provided in this embodiment is as follows. The UV light source precise control method for wafer defect detection includes the following steps: Step 110: Determine initial detection parameters for wafer defect detection.

[0019] Specifically, in this embodiment, determining the initial detection parameters for wafer defect detection is the first step in the entire detection process. The initial detection parameters include the wavelength, intensity, exposure time, spot size, etc. of the UV light source. These parameters directly affect the sensitivity and accuracy of the detection system. By analyzing historical data and previous test results, it can help determine which parameter settings are most effective, conduct experimental calibration on multiple samples, and determine the detection effects under different parameter settings. Wafers of different materials may respond differently to UV light sources, so it is necessary to adjust the parameters according to the material characteristics. For example, for silicon wafers, the light source intensity is set to 500mW / cm²; for gallium arsenide wafers, the light source intensity is set to 300mW / cm². The technical specifications and capabilities of the equipment will also affect the selection of parameters, such as the maximum intensity of the light source and the adjustable wavelength range. Therefore, in the process of selecting the initial detection parameters, the influencing factors such as historical data, wafer materials, and equipment capabilities should be fully considered to ensure the effectiveness of the initial detection parameters finally determined when the wafer defect detection begins.

[0020] Step 120 : Acquire a wafer surface image of the target wafer according to the initial detection parameters.

[0021] Specifically, in this embodiment, the wavelength, intensity, exposure time and spot size of the UV light source are set according to the initial detection parameters. During the image acquisition process, the UV light source is adjusted according to the detection parameters to ensure that the light source is evenly irradiated on the wafer surface, the camera is calibrated to ensure the clarity and accuracy of the image, and the wafer surface is captured multiple times to ensure that each area is fully covered. After the image acquisition is completed, the image needs to be preprocessed to improve the visibility of the defective area, use the edge detection algorithm to highlight the defective edges that may exist in the image, and generate a preprocessed image.

[0022] Step 130: Identify defect information of the wafer surface image.

[0023] Specifically, in this embodiment, the shape corresponding to the defect in the wafer surface image is determined by the defect edge identified by the edge detection algorithm, and the SVM classifier is used to identify different types of defects. For example, the SVM classifier is trained to identify scratches and point defects, and the defects are divided into types such as scratches, point defects and particles according to the shape and size of the defects. For example, the length of the scratch is greater than 100μm, and the diameter of the point defect is less than 50μm. Then, an image annotation tool (such as LabelImg) is used to annotate the detected defects on the image, and the annotation information includes the location, type and size of the defect. The detected defect information is stored in the defect database, and the defect information is managed using the data management system. When defining unknown defects later, the defect characteristics of the unknown defects can be used to query in the defect database.

[0024] In an optional implementation of the present embodiment, the step of identifying defect information of a wafer surface image includes: preprocessing the wafer surface image; extracting defect features from the preprocessed wafer surface image; identifying corresponding defect types based on the defect features; and marking defect information on the wafer surface image based on the defect type.

[0025] Specifically, in this embodiment, in the preprocessing stage, a series of processing is required for the acquired wafer surface image to improve the image quality and highlight the defect features. This includes using Gaussian filtering to remove image noise, enhancing image contrast through histogram equalization, and using edge detection algorithms to highlight edge information in the image. For example, for a wafer image containing a scratch defect, a Gaussian filter with a parameter of σ=1.0 can be used for noise reduction, and then the contrast between the scratch area and the background can be made more obvious through histogram equalization. After completing the preprocessing, defect features are extracted from the optimized image, including shape features, texture features, and color features. By calculating the shape features such as the area, perimeter, and circularity of the defect area, combined with the texture features extracted by the gray level co-occurrence matrix (GLCM), and the color distribution features reflected by the color histogram, the feature information of the defect can be fully described. For example, for a point defect, its shape regularity can be judged by calculating its circularity (4π·area / perimeter²), and its texture features can be analyzed by GLCM to determine its surface characteristics. With complete feature information, defect types can be identified, such as support vector machines (SVM) or deep learning networks for classification. Through training with a large amount of labeled data, the classifier can learn the characteristic patterns of different types of defects, thereby accurately identifying new defect samples. For example, an SVM classifier with an RBF kernel function can be used to train 3,000 defect images of different types in the training set, and then use 1,000 verification images to evaluate the classification performance, ultimately achieving a classification accuracy of more than 90%. Finally, the identified defect information is annotated on the wafer surface image, including automatic annotation of the defect location, type and size information, and combined with manual verification to ensure the accuracy of the annotation. The annotation information can be stored in JSON format, including the coordinate position, type classification and size data of the defect. For example, for a scratch defect located at coordinates (100, 200), a label box can be drawn on the image and its information can be stored in the format of {"position": [100, 200], "type": "scratch", "size": 50}. These annotation information are finally stored in the database for subsequent query and analysis.

[0026] Step 140: Evaluate the detection effect value of the initial detection parameters according to the defect information.

[0027] Specifically, in this embodiment, after identifying and classifying the defect information of the wafer surface image, it is necessary to evaluate the detection effect value of the initial detection parameters, and the evaluation annotations include but are not limited to the detection rate, the false detection rate and the missed detection rate, wherein the number of detected defects, the number of falsely reported defects, the number of missed detection defects and the total number of actual defects are counted, and the detection rate is determined according to the ratio of the number of detected defects to the actual number of defects, the false detection rate is determined according to the ratio of the number of falsely reported defects to the actual number of defects without defects, and the missed detection rate is determined according to the ratio of the number of missed detection defects to the actual number of defects. According to the calculated indicators, the detection effect value of the initial detection parameters is comprehensively evaluated according to the detection rate, false detection rate and missed detection rate.

[0028] In an optional implementation of the present embodiment, the step of evaluating the detection effect value of the initial detection parameters based on the defect information includes: generating a defect statistical report based on the defect information; determining the detection rate, false detection rate and missed detection rate of the wafer defect detection based on the defect statistical report; and determining the detection effect value by converting the false detection rate and missed detection rate into a penalty factor to exponentially penalize the detection rate.

[0029] Specifically, in this embodiment, in the wafer defect detection system, it is first necessary to generate a detailed statistical report based on the acquired defect information. This statistical report contains key information such as the number, type, and distribution location of defects. By systematically organizing and analyzing these data, a complete defect statistical result can be obtained. For example, in the detection of a batch of 100 wafers, the system detected 90 real defects, 5 false detection defects, and missed 10 actual defects. These raw data are organized into a structured statistical report, including information such as the number distribution of each type of defect, the spatial distribution characteristics of the defect, and the severity of the defect. Based on the generated defect statistical report, three key indicators need to be calculated next: detection rate, false detection rate, and missed detection rate. The detection rate represents the ratio of the number of defects correctly detected to the total number of defects that actually exist, the false detection rate reflects the ratio of the number of defects that are incorrectly identified as defects to the total number of actual defect-free areas, and the missed detection rate represents the ratio of the actual number of defects that cannot be detected to the total number of defects that actually exist. In the above example, the detection rate is 90 / 100=0.9, which means that 90% of the actual defects are correctly detected; the false detection rate is 5 / 200=0.025, which means that 5 of the 200 defect-free areas are mistakenly identified as defects; the missed detection rate is 10 / 100=0.1, which means that 10% of the actual defects are not detected. In order to obtain more representative detection effect values, it is necessary to convert the false detection rate FPR and the missed detection rate FNR into penalty factors, and use an exponential function to increase the penalty effect. The penalty factor calculation formula is as follows: , When the false positive rate and missed detection rate are small, the penalty factor changes relatively little; when the false positive rate and missed detection rate increase, the penalty factor increases rapidly. The final detection effect value is calculated by the following formula: , Where DR is the detection rate and PF is the penalty factor. Substituting the above values ​​into the formula, we can get: OS = , this detection effect value comprehensively considers the influence of the detection rate, false detection rate and missed detection rate, and can more comprehensively reflect the performance of the detection system. The closer the detection effect value is to 1, the better the performance of the detection system. In practical applications, when the detection effect value is lower than the preset threshold, such as setting the threshold to 0.95, it is necessary to adjust and optimize the parameters of the detection system to improve the detection performance. In this way, quantitative evaluation and continuous optimization of the performance of the detection system can be achieved. In the actual wafer production line, this evaluation method can provide clear guidance for the tuning of the detection system. For example, when it is found that the detection effect value is 0.79, which is lower than the preset threshold of 0.95, the penalty factor can be analyzed to find that the main problem lies in the high missed detection rate (0.1), which indicates that the main direction of system optimization is to improve the sensitivity of detection to reduce missed detection. At the same time, the low false detection rate (0.025) indicates that the system has good specificity, which should be maintained during the optimization process. Through this quantitative evaluation method, the optimization process of the detection system can be more targeted and efficient.

[0030] Step 150: If the detection effect value is lower than the preset detection threshold, a UV light source control strategy is generated according to the defect information.

[0031] Specifically, in this embodiment, if the detection effect value is lower than the preset detection threshold, it is necessary to generate a UV light source control strategy based on the defect information to optimize the detection effect. The control strategy includes adjusting parameters such as the wavelength, intensity, exposure time and spot size of the light source. The preset detection threshold is to set the threshold of the detection effect value based on historical data and experimental results. The calculated detection effect value is compared with the preset threshold to determine whether it is necessary to generate a control strategy. The reasons for the poor detection effect are analyzed based on the defect information, such as the defect position deviating from the center of the spot, insufficient light source intensity, etc. A control strategy is generated based on the analysis results to adjust the light source wavelength, intensity, exposure time and spot size. The effectiveness of the control strategy is verified through simulation experiments to ensure that the adjusted parameters can improve the detection effect.

[0032] In an optional implementation of the present embodiment, the step of generating a UV light source control strategy based on defect information includes: extracting characteristic parameters of the defect information; determining light source demand data corresponding to the defect characteristics based on the characteristic parameters; and generating a UV light source control strategy corresponding to the light source demand data through an adaptive optimization algorithm.

[0033] Specifically, in this embodiment, in the wafer defect detection system, extracting characteristic parameters from the acquired defect information is a key link in achieving precise light source control. First, it is necessary to comprehensively analyze the defect information and extract key parameters including shape characteristics, size characteristics and position characteristics of the defect. Specifically, the shape characteristics include the contour curvature and edge sharpness of the defect; the size characteristics include the area, perimeter, maximum diameter, etc. of the defect; and the position characteristics include the spatial distribution position and distribution density of the defect on the wafer. For example, for a point defect with an area of ​​200 square microns, a contour curvature of 0.85, and an edge sharpness of 0.92, these characteristic parameters will directly affect the formulation of subsequent light source control strategies. According to the extracted characteristic parameters, the corresponding light source demand data needs to be determined. This process requires the establishment of a mapping relationship between the characteristic parameters and the light source parameters to convert the physical characteristics of the defect into specific light source requirements. The light source demand data mainly includes wavelength requirements, intensity requirements, and irradiation angle requirements. For example, for the above-mentioned point defects, according to their characteristic parameters, it can be determined that a UV light source with a wavelength of 365nm is required, the light intensity requirement is 500mW / cm², and the optimal irradiation angle is 75 degrees. The establishment of this mapping relationship needs to consider multiple factors such as the difficulty of defect detection, the optical properties of the material, and the hardware limitations of the detection system. After obtaining the light source demand data, the final UV light source control strategy is generated through an adaptive optimization algorithm. Here, the particle swarm optimization algorithm (PSO) is combined with an adaptive weight adjustment mechanism to achieve global optimization of light source parameters. The algorithm uses parameters such as the wavelength, intensity, and irradiation angle of the light source as optimization variables, and iteratively optimizes with the detection effect as the objective function. During the optimization process, the algorithm dynamically adjusts the parameter weights according to the results of each iteration, so that the optimization process can converge to the optimal solution faster. For example, in a certain optimization, the optimal light source control strategy was obtained after 50 iterations: the wavelength was adjusted to 362nm, the light intensity was set to 520mW / cm², and the irradiation angle was fine-tuned to 73 degrees. This set of parameters is optimized compared to the initial setting values ​​and can better meet the needs of defect detection. The whole process forms a closed-loop optimization system, from the extraction of characteristic parameters, to the determination of light source demand data, and then to the generation of the final control strategy. In this way, adaptive light source control based on defect characteristics is realized, which significantly improves the accuracy and efficiency of defect detection. In an actual wafer production line, this adaptive control method can effectively deal with defects of different types and characteristics, ensuring that the detection system always maintains the best detection state.

[0034] In an optional implementation of the present embodiment, the method also includes: detecting the actual output parameters of the UV light source through a light sensing sensor; determining a first deviation value between the actual output parameters and the initial detection parameters; and determining the UV light source control strategy based on the deviation type and degree of deviation corresponding to the first deviation value.

[0035] Specifically, in this embodiment, in the wafer detection system, since the UV light source may age and other problems after long-term use, it is necessary to monitor the actual output parameters of the light source in real time through a light sensor. The light sensor can accurately capture the key parameters of the UV light source such as wavelength, intensity and spot uniformity through high-precision photoelectric conversion elements. After obtaining the actual output parameters, the system compares them with the pre-set initial detection parameters and calculates the first deviation value. This deviation value contains information in multiple dimensions, mainly reflected in wavelength deviation, intensity deviation and uniformity deviation. For example, the initial setting parameters of a UV light source are: wavelength 365nm, intensity 500mW / cm², and uniformity deviation is less than 3%. The actual output parameters detected by the sensor are: wavelength 368nm, intensity 460mW / cm², and uniformity deviation 4.5%. By calculation, it can be obtained that the wavelength deviation is +3nm, the intensity deviation is -40mW / cm², and the uniformity deviation exceeds the standard by 1.5%. According to the calculated first deviation value, the system needs to further analyze the type and degree of deviation, so as to formulate corresponding control strategies. Deviation types are mainly divided into three categories: wavelength drift, intensity attenuation, and uniformity degradation. For different types of deviations, the control strategy will also be different. In the above example, there is an obvious intensity attenuation phenomenon (attenuation of 8%), which is usually caused by the aging of the light source; the wavelength drift (+0.8%) is relatively small, which may be caused by temperature changes; and the uniformity degradation (exceeding the standard by 50%) needs to be paid special attention. Based on these deviation analyses, the system will generate corresponding UV light source control strategies. For the intensity attenuation problem, it can be compensated by increasing the input power to increase the driving current of the light source to 110% of the original value; for wavelength drift, the operating temperature can be reduced by 2°C by fine-tuning the temperature control system of the light source; and for the uniformity problem, it is necessary to adjust the position parameters of the collimator and homogenizer in the optical path system. These control strategies will be automatically executed by the system, and the adjustment effect will be monitored in real time. In practical applications, this control method based on deviation analysis can effectively solve the problems caused by the aging of UV light sources. For example, after the UV light source on a production line was used for 6 months, the method detected that the light intensity had decayed by 12%. The system automatically increased the light source driving current to restore the output intensity to the initial level, ensuring the stability of the detection system. At the same time, the system will also record these deviation data and control history, establish the light source aging curve, and provide a basis for predictive maintenance. When the deviation value of a certain parameter continues to increase and exceeds the adjustable range, the system will promptly issue an early warning to replace the light source, thereby avoiding a significant decline in detection quality. Through this real-time monitoring and automatic control method, not only can the output deviation of the UV light source be discovered and corrected in a timely manner, but the life cycle of the light source can also be predicted, providing a scientific basis for equipment maintenance, and ultimately ensuring the long-term stable operation of the wafer inspection system.

[0036] It should be noted that in order to protect the reliability of the light source while compensating for the attenuation of the light source, when increasing the current, gradually adjust and monitor the temperature and light output of the light source to ensure that the current is always within the safe range and avoid a one-time large increase in the current; and / or set a current upper limit in the system to ensure that it does not exceed this safe range even when it is necessary to compensate for the light intensity; and / or monitor the operating temperature of the LED in real time and link it with the current regulation. When the temperature exceeds the preset safety threshold, the current is automatically reduced or additional heat dissipation measures are enabled.

[0037] In an optional implementation of the present embodiment, the method also includes: detecting environmental parameters and material parameters of the target wafer through a multidimensional sensor; determining a baseline value for wafer defect detection based on the environmental parameters and material parameters; determining a second deviation value between the baseline value and the initial detection parameter; and determining a UV light source control strategy based on the second deviation value.

[0038] Specifically, in this embodiment, in the wafer defect detection system, the multidimensional sensor network collects environmental parameters and wafer material parameters in real time through temperature sensors, humidity sensors, air pressure sensors, and material property sensors arranged in the detection environment. These sensors can accurately capture environmental factors such as temperature changes (accuracy ±0.1°C), relative humidity (accuracy ±1%), and atmospheric pressure (accuracy ±0.1kPa) in the detection environment, and can also obtain material property parameters such as the refractive index, reflectivity, and dielectric constant of the wafer. For example, in a certain detection environment, the temperature sensor detects that the ambient temperature is 23.5°C, the humidity sensor shows that the relative humidity is 45%, and the air pressure sensor shows that the atmospheric pressure is 101.3kPa, while the material property sensor measures the refractive index of the wafer to be 3.42 and the reflectivity to be 0.35. Based on the acquired environmental parameters and material parameters, the system calculates the reference value of wafer defect detection through the established physical model. This reference value includes parameters in multiple dimensions such as the wavelength reference, intensity reference, and illumination angle reference of the light source. In the calculation process, it is necessary to consider the influence of environmental factors on the propagation characteristics of light and the influence of material parameters on the interaction between light and the wafer surface. Specifically, temperature changes affect the wavelength stability of the light source, humidity changes affect the scattering characteristics of light, and the optical properties of the material directly determine the interaction between light and the wafer surface. , Strength benchmark and illumination angle reference The calculation formulas are: , , , in, is the initial wavelength, is the influence coefficient of temperature on wavelength, is the reference temperature, is the initial strength, is the influence coefficient of humidity on strength, is the influence coefficient of air pressure on strength, is the reference humidity, is the reference air pressure, is the initial irradiation angle, is the refractive index of the wafer material.

[0039] In the above example, the calculated reference values ​​are: wavelength reference 367nm, intensity reference 485mW / cm², and irradiation angle reference 72 degrees. The calculated reference values ​​are compared with the initial detection parameters preset by the system to obtain the second deviation value. This deviation value reflects the deviation of the detection parameters due to environmental and material factors. For example, the initial detection parameters are set as: wavelength 365nm, intensity 500mW / cm², and irradiation angle 75 degrees. After calculation, the wavelength deviation is +2nm, the intensity deviation is -15mW / cm², and the angle deviation is -3 degrees. These deviation data clearly show the degree of adjustment required for the UV light source. According to the calculated second deviation value, the system generates the corresponding UV light source control strategy. The formulation of the control strategy needs to comprehensively consider the changing trends of environmental parameters and material parameters, as well as the degree of influence of these changes on the detection effect. For the above example, the system will generate the following control strategy: adjust the wavelength of the light source to 367nm to adapt to the influence of temperature changes; reduce the light intensity to 485mW / cm² to match the reflective characteristics of the material; and adjust the irradiation angle to 72 degrees to obtain the best detection effect. In practical applications, this method based on multi-dimensional sensing and real-time control can effectively cope with the impact of environmental and material changes. For example, on a semiconductor production line, when the ambient temperature rises from 20°C to 25°C, the system automatically adjusts the UV light source parameters to keep the detection effect stable; when replacing wafers with different doping concentrations, the system can automatically optimize the detection parameters according to the changes in material parameters to ensure the accuracy of the detection. At the same time, the system will also record the correlation data between environmental parameters, material parameters and detection effects, establish a parameter influence model, and provide data support for subsequent optimization of detection parameters.

[0040] In an optional implementation of the present embodiment, the method also includes: determining the dielectric response characteristics of the target wafer under UV light source irradiation based on the Jonscher general power law model; analyzing the correlation between the dielectric response characteristics and the defect type based on the Dissado-Hill model; establishing a mapping model between wafer defect characteristics and UV light source parameters based on the correlation; and optimizing and iterating the UV light source control strategy based on the mapping model until the detection effect value reaches a preset detection threshold.

[0041] Specifically, in this embodiment, during the wafer defect detection process, it is first necessary to build a dielectric response characteristic analysis system based on the Jonscher general power law model. The system stimulates the dielectric response of the material by irradiating the wafer surface with a UV light source, and uses a high-precision capacitive sensor array to collect dielectric response data on the wafer surface. For silicon wafers, when the UV light source frequency varies in the range of 200-400nm, the dielectric response of the material follows the Jonscher general power law model. By measuring the real and imaginary parts of the dielectric constant at different frequencies, the complete dielectric loss characteristic curve of the wafer material can be obtained. The Jonscher general power law model is expressed by the following formula: , in, is the dielectric loss, is the low frequency dielectric constant, are high-frequency dielectric constants, which reflect the dielectric properties of the material in static electric fields and rapidly changing electric fields, respectively. is the excitation frequency of the UV light source. The excitation frequency determines the frequency range of the system response. is the relaxation time constant, the time scale of the dielectric relaxation process, n is the power exponent, which describes the rate at which the dielectric loss changes with frequency, and j is the imaginary unit. For different types of defects, the value of n may be different, thus providing a basis for defect identification. For example, during the inspection process, if it is found that the dielectric loss in a certain frequency range is significantly higher than that in the defect-free area, and the value obtained by fitting is If the value is large, it may indicate that there are large structural defects in the area, such as cracks or deep scratches. The dielectric response characteristics refer to the electrical polarization characteristics of the material under the action of an external electric field, including the change law of parameters such as dielectric constant and dielectric loss with the frequency of the external electric field. In wafer inspection, when the UV light source irradiates the wafer surface, the photon energy will excite the material to produce electron-hole pairs, causing the local charge distribution to change, thereby causing changes in dielectric properties. First, obtain standard dielectric response data in a defect-free area. When the UV light source irradiates at a specific frequency, measure the dielectric constant and dielectric loss on the wafer surface to obtain a baseline dielectric spectrum. This baseline dielectric spectrum reflects the normal dielectric response characteristics under a complete lattice structure. Secondly, measure dielectric response data in areas with defects. Different types of defects will change the local electronic structure and energy level distribution, thereby affecting the dielectric response. For example, for surface contamination, the introduction of new surface states will change the interface charge distribution, resulting in a change in the dielectric constant. The measured data is then substituted into the Dissado-Hill model equation: , in, is the complex permittivity, describing the overall dielectric response of the material, is the dielectric relaxation strength, reflecting the degree of polarization, is the characteristic relaxation time, which characterizes the time scale of the polarization process, a is the short-term program parameter, which describes the correlation within the local structural unit, and b is the long-term program parameter, which describes the correlation between different structural units. By comparing the difference in dielectric response between defect-free areas and areas with different types of defects, the corresponding relationship between defect characteristics and dielectric response parameters is established. For example, when there are micro scratches on the surface of the wafer, its dielectric loss curve will have a characteristic peak in a specific frequency range, while particle contamination may cause abnormal changes in the curve at other frequency points. Figure 2 , Figure 3 The figures show the dielectric response test data of the defect-free area and the dielectric response test data of the surface contaminated area in wafer defect detection. After obtaining sufficient experimental data, a machine learning algorithm is used to establish the mapping relationship between wafer defect characteristics and UV light source parameters. Specifically, the defect type, size, depth and other characteristics are used as input variables, and the wavelength, intensity, irradiation angle and other parameters of the UV light source are used as output variables. The optimal parameter mapping model is obtained through neural network training. Taking micro-scratch detection as an example, when the scratch depth is detected to be on the order of 100nm, the model will automatically adjust the UV light source wavelength to about 280nm and set the irradiation angle within the range of 15-20 degrees to obtain the best detection effect. Based on the established mapping model, an iterative optimization algorithm is designed to dynamically adjust the UV light source parameters. The algorithm first performs defect detection based on the initial detection parameters, and evaluates the detection effect by calculating indicators such as detection rate, false detection rate and missed detection rate. If the detection effect value is lower than the preset threshold, the UV light source is adjusted according to the optimal parameters predicted by the mapping model. In actual applications, assuming that the preset detection threshold is 95%, when the effect value of a certain detection is only 90%, the optimization algorithm will predict a better combination of UV light source parameters based on the current detection results and historical data, and verify the effect in the next round of detection, and repeat this process until the preset threshold is reached. Throughout the process, the real-time monitoring system continuously collects changes in environmental parameters and material parameters, and inputs these factors into the model as correction items to ensure stable detection results under different working conditions. This closed-loop control mechanism enables the detection system to adapt to different types of wafer materials and diverse defect characteristics, greatly improving the accuracy and reliability of detection.

[0042] It should be noted that the present application uses UV LED to detect UV light sources. Considering that UV LEDs usually have a specific wavelength range and are limited by materials and processes in manufacturing, it is difficult to achieve a wide range of continuously adjustable wavelengths on a device. In practical applications, a multi-wavelength UV LED array can be used or a multi-band detection method can be achieved by combining multiple LEDs with different wavelengths. In the actual detection process, the control system can be used to orderly switch LEDs of different wavelengths to irradiate and measure the wafer surface multiple times. After each irradiation, the dielectric response data at the corresponding wavelength is collected by a high-precision capacitive sensor array. For example, first use a UV LED with a wavelength of 280nm for irradiation to obtain a set of dielectric response data; then switch to a UV LED with a wavelength of 310nm to obtain another set of data. In this way, after measuring multiple wavelengths, a complete set of multi-band dielectric response data can be obtained. These data will be input into an analysis system based on the Jonscher general power law model and the Dissado-Hill model. By analyzing the dielectric response characteristics at different wavelengths, the characteristic responses of different defect types can be further analyzed. Assuming that a certain defect exhibits a significant dielectric loss peak at a wavelength of 280nm, but has no obvious features at a wavelength of 310nm, by comparing the differences between the two sets of data, the defect type can be identified more accurately.

[0043] According to the UV light source precise control method for wafer defect detection provided by the present application, the initial detection parameters for wafer defect detection are determined; the wafer surface image of the target wafer is obtained according to the initial detection parameters; the defect information of the wafer surface image is identified; the detection effect value of the initial detection parameters is evaluated according to the defect information; if the detection effect value is lower than the preset detection threshold, a UV light source control strategy is generated according to the defect information. Through the implementation of the present application, a closed-loop feedback mechanism is established by obtaining the initial detection parameters and evaluating the detection effect value, so as to timely discover the situation where the detection effect is not ideal, and adjust the UV light source parameters accordingly to ensure that the defect detection is always kept in the best state and improve the accuracy of wafer defect detection.

[0044] Figure 4 The present application provides a UV light source precision control device for wafer defect detection, which can be used to implement the UV light source precision control method for wafer defect detection in the above-mentioned embodiment. Figure 4 As shown, the UV light source precision control device for wafer defect detection mainly includes: A determination module 10, used to determine initial detection parameters for wafer defect detection; An acquisition module 20, used for acquiring a wafer surface image of a target wafer according to initial detection parameters; An identification module 30, used to identify defect information of a wafer surface image; An evaluation module 40, used to evaluate the detection effect value of the initial detection parameters according to the defect information; The generating module 50 is used to generate a UV light source control strategy according to the defect information if the detection effect value is lower than a preset detection threshold.

[0045] In an optional embodiment of the present application, the identification module is specifically used to: preprocess the wafer surface image; extract defect features from the preprocessed wafer surface image; identify the corresponding defect type according to the defect features; and mark the defect information on the wafer surface image according to the defect type.

[0046] In an optional embodiment of the present application, the evaluation module is specifically used to: generate a defect statistical report based on defect information; determine the detection rate, false detection rate and missed detection rate of wafer defect detection based on the defect statistical report; and perform exponential penalty on the detection rate by converting the false detection rate and missed detection rate into a penalty factor to determine the detection effect value.

[0047] In an optional implementation of the present application, the generation module is specifically used to: extract characteristic parameters of defect information; determine light source demand data corresponding to the defect characteristics based on the characteristic parameters; and generate a UV light source control strategy corresponding to the light source demand data through an adaptive optimization algorithm.

[0048] In an optional embodiment of the present application, the UV light source precision control device for wafer defect detection further includes: a detection module. The detection module is used to: detect the actual output parameter of the UV light source through a light sensing sensor. The determination module is also used to: determine a first deviation value between the actual output parameter and the initial detection parameter; and determine the UV light source control strategy according to the deviation type and deviation degree corresponding to the first deviation value.

[0049] In an optional embodiment of the present application, the detection module is further used to: detect environmental parameters and material parameters of the target wafer through a multi-dimensional sensor. The determination module is further used to: determine a reference value for wafer defect detection based on the environmental parameters and material parameters; determine a second deviation value between the reference value and the initial detection parameter; and determine a UV light source control strategy based on the second deviation value.

[0050] In an optional embodiment of the present application, the UV light source precision control device for wafer defect detection also includes: an analysis module and an adjustment module. The determination module is also used to: determine the dielectric response characteristics of the target wafer under UV light source irradiation based on the Jonscher general power law model. The analysis module is used to: analyze the correlation between the dielectric response characteristics and the defect type based on the Dissado-Hill model. The adjustment module is used to: establish a mapping model between wafer defect characteristics and UV light source parameters based on the correlation relationship; optimize and iterate the UV light source control strategy based on the mapping model until the detection effect value reaches the preset detection threshold.

[0051] According to the UV light source precision control device for wafer defect detection provided by the present application, the initial detection parameters of wafer defect detection are determined; the wafer surface image of the target wafer is obtained according to the initial detection parameters; the defect information of the wafer surface image is identified; the detection effect value of the initial detection parameters is evaluated according to the defect information; if the detection effect value is lower than the preset detection threshold, a UV light source control strategy is generated according to the defect information. Through the implementation of the present application, a closed-loop feedback mechanism is established by obtaining the initial detection parameters and evaluating the detection effect value, so as to timely discover the situation where the detection effect is not ideal, and adjust the UV light source parameters accordingly to ensure that the defect detection is always kept in the best state and improve the accuracy of wafer defect detection.

[0052] According to the application plan provided Figure 5 An electronic device provided in an embodiment of the present application. The electronic device can be used to implement the UV light source precise control method for wafer defect detection in the aforementioned embodiment, mainly comprising: The memory 501, the processor 502, and the computer program 503 stored in the memory 501 and executable on the processor 502, the memory 501 and the processor 502 are connected by communication. When the processor 502 executes the computer program 503, the UV light source precise control method for wafer defect detection in the aforementioned embodiment is implemented. The number of processors can be one or more.

[0053] The memory 501 may be a high-speed random access memory (RAM) memory, or a non-volatile memory (non-volatile memory), such as a disk memory. The memory 501 is used to store executable program codes, and the processor 502 is coupled to the memory 501 .

[0054] Furthermore, the present application also provides a computer-readable storage medium, which may be provided in the electronic device in the above embodiments. Figure 5 Memory in the illustrated embodiment.

[0055] The computer readable storage medium stores a computer program, and when the program is executed by the processor, the UV light source precise control method for wafer defect detection in the aforementioned embodiment is implemented. Furthermore, the computer storable medium can also be a U disk, a mobile hard disk, a read-only memory (ROM), a RAM, a magnetic disk or an optical disk, and other media that can store program codes.

[0056] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0057] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0058] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for accurately controlling a UV light source for wafer defect detection, characterized in that: include: Determine initial inspection parameters for wafer defect inspection; Acquire a wafer surface image of the target wafer according to the initial detection parameters; Identifying defect information of the wafer surface image; Evaluate the detection effect value of the initial detection parameter according to the defect information; If the detection effect value is lower than a preset detection threshold, a UV light source control strategy is generated according to the defect information.

2. The UV light source precise control method for wafer defect detection according to claim 1, characterized in that: The step of identifying defect information of the wafer surface image comprises: Preprocessing the wafer surface image; Extracting defect features from pre-processed wafer surface images; Identify the corresponding defect type according to the defect characteristics; Defect information is marked on the wafer surface image according to the defect type.

3. The UV light source precise control method for wafer defect detection according to claim 2, characterized in that: The step of evaluating the detection effect value of the initial detection parameter according to the defect information comprises: Generate a defect statistics report based on the defect information; Determine the detection rate, false detection rate and missed detection rate of the wafer defect detection according to the defect statistical report; The detection effect value is determined by converting the false detection rate and the missed detection rate into a penalty factor and performing exponential penalty on the detection rate.

4. The UV light source precise control method for wafer defect detection according to claim 2, characterized in that: The step of generating a UV light source control strategy according to the defect information includes: Extracting characteristic parameters of the defect information; Determine light source requirement data corresponding to the defect feature according to the feature parameter; A UV light source control strategy corresponding to the light source demand data is generated through an adaptive optimization algorithm.

5. The UV light source precise control method for wafer defect detection according to claim 1, characterized in that: The method further comprises: Detect the actual output parameters of the UV light source through the light sensing sensor; Determining a first deviation value between the actual output parameter and the initial detection parameter; The UV light source control strategy is determined according to the deviation type and deviation degree corresponding to the first deviation value.

6. The UV light source precise control method for wafer defect detection according to claim 1, characterized in that: The method further comprises: Detecting environmental parameters and material parameters of the target wafer by using a multi-dimensional sensor; Determine a reference value for wafer defect detection according to the environmental parameter and the material parameter; Determining a second deviation value between the reference value and the initial detection parameter; The UV light source control strategy is determined according to the second deviation value.

7. The UV light source precise control method for wafer defect detection according to claim 2, characterized in that: The method further comprises: Determining the dielectric response characteristics of the target wafer under UV light irradiation based on the Jonscher general power law model; Analyze the correlation between the dielectric response characteristics and the defect type based on the Dissado-Hill model; Establishing a mapping model between wafer defect characteristics and UV light source parameters according to the association relationship; The UV light source control strategy is optimized and iterated based on the mapping model until the detection effect value reaches a preset detection threshold.

8. A UV light source precision control device for wafer defect detection, characterized in that: The UV light source precise control device for wafer defect detection comprises: A determination module, used to determine initial detection parameters for wafer defect detection; An acquisition module, used for acquiring a wafer surface image of a target wafer according to the initial detection parameters; An identification module, used for identifying defect information of the wafer surface image; An evaluation module, used for evaluating the detection effect value of the initial detection parameter according to the defect information; A generation module is used to generate a UV light source control strategy according to the defect information if the detection effect value is lower than a preset detection threshold.

9. An electronic device, characterized in that: The device comprises a memory and a processor, wherein: The processor is used to execute the computer program stored in the memory; When the processor executes the computer program, the steps in the method for precisely controlling the UV light source for wafer defect detection described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method for precisely controlling a UV light source for wafer defect detection described in any one of claims 1 to 7 are implemented.

Images