Cleaning method and control system of semiconductor wafer cleaning system

Abstract

The invention discloses a cleaning method and a control system of a semiconductor wafer cleaning system in the technical field of information, and the control method of the semiconductor wafer cleaning system comprises the following steps: obtaining a wafer surface image, and processing the wafer surface image by adopting an image segmentation algorithm to obtain a wafer surface image; identifying a polluted area and a non-polluted area in the wafer surface image, and judging the pollution degree and the pollution type of the wafer surface according to the area, the form and the gray scale characteristics of the polluted area; cleaning process data of each batch of wafers is recorded, the cleaning process data comprises a cleaning formula, cleaning parameters, cleaning time, cleaning agent dosage, pollution removal rate and surface damage conditions, a big data analysis technology is applied, optimal cleaning processes of different types of wafers are mined, the cleaning formula database is dynamically updated and optimized, and the optimal cleaning process is updated and optimized. Therefore, the cleaning efficiency and the yield are improved.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a cleaning method and a control system for a semiconductor wafer cleaning system. Background Art

[0002] Semiconductor wafer cleaning is a key step in the semiconductor manufacturing process, and its cleaning quality directly affects the yield of subsequent processes and the performance of devices. However, as the feature size of integrated circuits continues to shrink and the surface structure of wafers becomes increasingly complex, higher requirements are placed on the cleaning process.

[0003] Traditional cleaning methods are difficult to completely remove various pollutants on the surface of the wafer, such as particles, organic matter, metal ions, etc., and the cleaning effect is easily affected by human factors, and the stability and consistency are poor. At the same time, the degree and type of surface contamination of wafers of different batches and models vary greatly. It is difficult to achieve the optimal cleaning effect using fixed cleaning formulas and parameters. Excessive cleaning will damage the surface structure of the wafer, while insufficient cleaning will not meet the requirements of subsequent processes, resulting in device performance degradation or even failure. Therefore, there is an urgent need for an intelligent wafer cleaning control system that can monitor the surface status of the wafer and the cleaning environment parameters in real time, adaptively adjust the cleaning process, and maximize the protection of the wafer while ensuring thorough cleaning, improve cleaning efficiency and yield, and reduce energy consumption and costs. This is of great significance for the research and development and application of advanced process technologies. Summary of the invention

[0004] The present invention provides a cleaning method for a semiconductor wafer cleaning system, the method comprising the following steps:

[0005] Step S101, acquiring a wafer surface image, processing the wafer surface image using an image segmentation algorithm, identifying a contaminated area and a non-contaminated area in the wafer surface image, and determining the contamination degree and contamination type of the wafer surface according to the area, morphology and grayscale characteristics of the contaminated area;

[0006] Step S102, selecting an optimal cleaning formula from a preset cleaning formula database according to the judgment results of the contamination degree and the contamination type, and dynamically adjusting the cleaning time, cleaning agent concentration and cleaning temperature parameters in the optimal cleaning formula according to the structural complexity of the wafer surface, wherein the structural complexity includes line width, aspect ratio and pattern density, to obtain a dynamically adjusted cleaning formula;

[0007] Step S103, during the wafer cleaning process, the ambient temperature, humidity and pressure parameters in the cleaning equipment are collected in real time through sensors, and the ambient temperature, humidity and pressure parameters are compared with a preset optimal range, which is determined based on historical cleaning data and wafer material characteristics. If the deviation of the comparison result exceeds a preset threshold, an alarm is triggered, and the process parameters of the cleaning equipment are automatically adjusted to maintain the stability of the cleaning environment;

[0008] Step S104, after the cleaning is completed, the surface of the wafer is inspected again by machine vision, the inspection image after cleaning is compared with the image before cleaning, the pollution removal rate is calculated, and the pollution removal rate is compared with the preset cleaning qualification standard. If the cleaning qualification standard is not met, return to step S102 and perform cleaning again until the cleaning qualification standard is met;

[0009] Step S105, after the cleaning reaches the qualified standard, the surface of the wafer is tested by an atomic force microscope to obtain the roughness and defect density parameters of the wafer surface, and the roughness and defect density parameters are compared with the preset wafer surface quality standards to determine whether the cleaning process causes damage to the surface structure of the wafer. If the surface structure is damaged, the damage type and degree are recorded, and the parameters of the cleaning formula are adjusted to reduce similar damage;

[0010] Step S106, recording the cleaning process data of each batch of wafers, wherein the cleaning process data includes cleaning formula, cleaning parameters, cleaning time, cleaning agent dosage, contamination removal rate and surface damage, applying big data analysis technology to mine the optimal cleaning process for different types of wafers, and dynamically updating and optimizing the cleaning formula database to improve cleaning efficiency and yield;

[0011] Step S107, based on the wafer production plan, feedback information from the equipment management system, historical cleaning effect data and energy consumption data, predict and optimize the energy consumption and material consumption of the cleaning equipment, apply an intelligent scheduling algorithm based on multi-objective optimization, comprehensively consider cleaning effect, energy consumption, material consumption and equipment utilization factors, reasonably arrange cleaning tasks, minimize cleaning costs, take into account production efficiency and delivery time, and realize intelligent management and control of the cleaning process.

[0012] The present invention provides a semiconductor wafer cleaning system and a control system, which mainly include:

[0013] Wafer surface contamination detection module, used to identify contaminated areas and determine the degree and type of contamination;

[0014] A cleaning recipe optimization module is used to select the optimal cleaning recipe and dynamically adjust parameters according to the wafer structure;

[0015] The cleaning process monitoring module is used to monitor the cleaning environment parameters in real time and automatically adjust them to maintain stability;

[0016] The cleaning effect evaluation module is used to detect the wafer surface after cleaning and determine whether it meets the cleaning standards;

[0017] Data analysis and optimization module, used to record cleaning data, analyze optimal processes and update the cleaning formula database;

[0018] Intelligent scheduling and control module is used to optimize the energy and material consumption of cleaning equipment and reasonably arrange cleaning tasks.

[0019] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0020] The present invention discloses a cleaning method for a semiconductor wafer cleaning system. The method identifies the contamination of the wafer surface through machine vision and image segmentation algorithms, automatically selects the optimal cleaning formula according to the contamination characteristics, and dynamically adjusts the cleaning parameters in combination with the complexity of the wafer structure. During the cleaning process, the environmental parameters are monitored in real time and automatically adjusted to maintain stability. After cleaning, the test is repeated, and the cleaning is repeated if it does not meet the standard. The surface morphology is detected by atomic force microscopy to evaluate the impact of cleaning on the wafer structure. The cleaning data is recorded and big data analysis is applied to continuously optimize the cleaning process. The present invention also combines production plans and historical data to optimize energy consumption and material consumption and intelligently schedule cleaning tasks. Through the above method, the intelligent and refined control of the wafer cleaning process is realized, the cleaning efficiency and yield are improved, the cost is reduced, and the production efficiency is taken into account while ensuring the cleaning quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 The figure is a flow chart of the cleaning method of the semiconductor wafer cleaning system of the present invention.

[0022] Figure 2 It is a structural schematic diagram of the control system of the semiconductor wafer cleaning system of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0024] like Figure 1-2 The semiconductor wafer cleaning system and control system of this embodiment may specifically include:

[0025] Step S101, obtaining a wafer surface image, processing the wafer surface image using an image segmentation algorithm, identifying contaminated areas and non-contaminated areas in the wafer surface image; and judging the contamination degree and contamination type of the wafer surface according to the area, shape and grayscale characteristics of the contaminated area.

[0026] Step S101 also includes the following steps:

[0027] a. Obtain a high-definition image of the wafer surface, and use an image preprocessing algorithm to denoise and enhance the image to improve the image quality. b. According to the characteristics of the wafer surface, use an image segmentation algorithm to divide the image into different areas to distinguish between contaminated areas and non-contaminated areas. c. Extract the characteristic parameters of the area, morphology and grayscale of the contaminated area to construct a contamination feature vector. d. Input the contamination feature vector into a pre-trained contamination degree classification model to determine the contamination degree of the wafer surface and obtain the contamination degree level. e. Input the contamination feature vector into a pre-trained contamination type classification model to determine the contamination type of the wafer surface and obtain the specific contamination type. f. According to the contamination degree level and contamination type, obtain the corresponding cleaning liquid formula and cleaning parameters from the cleaning process database. g. Input the cleaning liquid formula and cleaning parameters into the cleaning equipment control module to automatically configure the process parameters of the cleaning equipment. h. Start the cleaning equipment and clean the wafer according to the configured process parameters. After cleaning is completed, obtain the wafer surface image again, repeat step be, and determine the contamination degree and contamination type after cleaning. If the cleaning requirements are not met, return to step f and adjust the cleaning process until the cleaning is qualified.

[0028] Exemplarily, to obtain a high-definition image of the wafer surface, a high-resolution industrial camera, such as a camera with more than 10 million pixels, can be used with a specific light source, such as coaxial light or dark field lighting, to obtain a clear wafer surface image. Choosing a suitable lighting method can highlight the defects on the wafer surface, for example, dark field lighting can highlight fine scratches and particles. Assume that an industrial camera with a resolution of 2048x2048 pixels is used with a coaxial light source to obtain a high-definition image of the wafer surface. The image preprocessing algorithm is to remove image noise and enhance image features. Commonly used denoising algorithms include median filtering and Gaussian filtering. Taking median filtering as an example, it can effectively remove salt and pepper noise while retaining image edge information. Assuming that there are some random bright and dark noise points in the image, these noise points can be effectively removed by replacing each pixel value with the median of the 9 pixels around it through a 3x3 median filter. The image enhancement algorithm can use histogram equalization to enhance the contrast of the image and make the contaminated area more obvious. Assuming that the grayscale range of the original image is narrow, the grayscale range can be expanded to 0-255 through histogram equalization to make the image clearer. The goal of the image segmentation algorithm is to divide the image into different regions. Commonly used image segmentation algorithms include threshold segmentation, edge detection, and region growing. Assuming that the contaminated area on the surface of the wafer presents a darker grayscale value, the threshold segmentation algorithm can be used to divide the pixels with grayscale values ​​below a certain threshold into the contaminated area, and the pixels above the threshold into the non-contaminated area. Assuming that the threshold is determined to be 100 by analyzing the grayscale histogram of the image, then the pixels with grayscale values ​​below 100 are considered to be contaminated areas. Extract the characteristic parameters of the area, morphology, and grayscale of the contaminated area to construct a contamination feature vector. For example, the proportion of the area of ​​the contaminated area to the entire wafer area, the morphological features such as the perimeter and circularity of the contaminated area, and the grayscale features such as the average grayscale value and grayscale variance of the contaminated area can be calculated. Assuming that the area of ​​a contaminated area is 100 pixels, the perimeter is 40 pixels, and the average grayscale value is 50, a feature vector can be constructed

[0029] [01,40,50], where 01 represents the proportion of the contaminated area. The contamination degree classification model can be trained using a machine learning algorithm such as a support vector machine (SVM) or a neural network. Assuming that a large number of wafer surface images are collected and the corresponding contamination degree levels (e.g., slight, moderate, severe) are labeled, these data can be used to train an SVM classification model. The extracted contamination feature vector is input into the trained SVM model to obtain the contamination degree level. For example, the feature vector [01,40,50] is input, and the model outputs "slight contamination". The contamination type classification model can also be trained using a similar method. Assuming that wafer image data of different types of contamination are collected, such as particle contamination, organic contamination, metal contamination, etc., and these data are labeled. These data can be used to train a neural network classification model. The extracted contamination feature vector is input into the trained neural network model to obtain the contamination type. For example, the feature vector [01,40,50] is input, and the model outputs "particle contamination". The cleaning process database stores the cleaning solution formulas and cleaning parameters corresponding to different pollution types and pollution degrees. For example, for slight particle contamination, a diluted ammonia solution can be used for cleaning, with a cleaning time of 5 minutes and a cleaning temperature of 60°C. For severe organic contamination, a more concentrated organic solvent can be used for cleaning, with a cleaning time of 10 minutes and a cleaning temperature of 80°C. Assuming that the obtained contamination level is "slight" and the contamination type is "particle contamination", the corresponding cleaning solution formula obtained from the database is "10% ammonia solution" and the cleaning parameters are "cleaning time 5 minutes, cleaning temperature 60°C". The cleaning equipment control module automatically configures the cleaning equipment according to the obtained cleaning solution formula and cleaning parameters. For example, the control module controls the valve to open, injects 10% ammonia solution into the cleaning tank, controls the heater to raise the cleaning tank temperature to 60°C, and sets the cleaning time to 5 minutes. After the cleaning is completed, the wafer surface image is obtained again, and the previous steps are repeated to determine the degree of contamination and the type of contamination after cleaning. Assuming that the analysis result of the wafer surface image after cleaning shows that the contamination level is "no contamination", the cleaning is considered qualified. If contamination still exists after cleaning, it is necessary to adjust the cleaning process parameters, such as increasing the cleaning solution concentration, extending the cleaning time or increasing the cleaning temperature, and perform cleaning again until the cleaning requirements are met. Assuming that the contamination level after cleaning is "slight", the cleaning time can be extended to 10 minutes and cleaning can be performed again.

[0030] Step S102, selecting an optimal cleaning formula from a preset cleaning formula database based on the judgment results of the contamination degree and the contamination type; dynamically adjusting the cleaning time, cleaning agent concentration and cleaning temperature parameters in the optimal cleaning formula based on the structural complexity of the wafer surface, wherein the structural complexity includes line width, aspect ratio and graphic density, to obtain a dynamically adjusted cleaning formula.

[0031] Acquire contamination degree data and contamination type data of the wafer surface; select an optimal cleaning formula from a preset cleaning formula database according to the contamination degree data and contamination type data; acquire the structural complexity of the wafer surface, wherein the structural complexity includes line width, aspect ratio and pattern density; dynamically adjust the cleaning time, cleaning agent concentration and cleaning temperature parameters in the optimal cleaning formula according to the structural complexity to obtain a dynamically adjusted cleaning formula; acquire the surface data of the wafer after cleaning; determine whether the surface data of the wafer after cleaning reaches a preset threshold; if not, trigger a cleaning formula optimization process.

[0032] Exemplarily, the sensor module can monitor the degree of contamination and type of contamination on the wafer surface in real time in a variety of ways. For example, an optical sensor, such as a spectroscopic reflectometer, can be used to determine the type and concentration of contaminants by analyzing the wavelength and intensity of light reflected from the wafer surface. Assuming that the wafer surface is contaminated by organic matter, the reflection spectrum will have an absorption peak within a specific wavelength range. By analyzing the intensity of the absorption peak, the concentration of organic contamination can be determined. Electrochemical sensors can also be used to determine the type and concentration of contaminants by measuring the change in electrochemical signals when the wafer surface is in contact with a specific solution. Assuming that the wafer surface is contaminated by metal ions, a specific electrochemical reaction will occur when it is in contact with a specific solution, thereby changing the electrochemical signal. By analyzing the change in the electrochemical signal, the type and concentration of the metal ions can be determined. The acquired contamination degree data can be quantitative, such as the contaminant concentration value, or qualitative, such as light contamination, moderate contamination, and heavy contamination. The contamination type data can be a specific contaminant name, such as particulate matter, organic matter, metal ions, etc. The preset cleaning formula database stores cleaning formulas for different types and degrees of contamination. For example, for particulate contamination, ultrasonic cleaning with a specific cleaning agent formula can be used; for organic contamination, an organic solvent cleaning formula can be used; for metal ion contamination, a specific chemical reagent cleaning formula can be used. Each formula contains parameters such as the type, concentration, cleaning time, and cleaning temperature of the cleaning agent. Assuming that mild particulate contamination is detected on the wafer surface, an ultrasonic cleaning formula for mild particulate contamination in the database can be selected. Machine vision technology can obtain images of the wafer surface through a high-resolution camera, and then analyze the structural complexity of the wafer surface through an image processing algorithm. For example, the lines and graphics on the wafer surface can be identified through an edge detection algorithm, and parameters such as line width and aspect ratio can be measured. Assuming that there are dense lines and graphics on the wafer surface, the line width is 10 nanometers, and the aspect ratio is 5, it can be judged that the structural complexity of the wafer surface is high. According to the structural complexity of the wafer surface, the parameters in the cleaning formula need to be dynamically adjusted. For example, if the structural complexity of the wafer surface is high, the cleaning time needs to be appropriately extended to ensure that the cleaning solution can fully penetrate into the tiny gaps and completely remove the contaminants. At the same time, the concentration of the cleaning agent may need to be reduced to avoid damage to the fine structure. Assuming that the structure of the wafer surface is very complex, the cleaning time can be extended from 5 minutes to 10 minutes, and the cleaning agent concentration can be reduced from 10% to 5%. The cleaning temperature also needs to be adjusted according to the specific situation. For example, for some temperature-sensitive materials, the cleaning temperature needs to be controlled in a lower range. The actuator module controls the cleaning equipment to perform cleaning operations according to the dynamically adjusted cleaning formula. For example, the control module can control the valve switch to adjust the flow and concentration of the cleaning solution; control the heater to adjust the temperature of the cleaning solution; control the robotic arm to place the wafer into the cleaning tank and control the cleaning time.During the cleaning process, the sensor monitors the temperature, pressure, flow rate and other parameters of the cleaning liquid in real time. For example, the temperature sensor can measure the temperature of the cleaning liquid in real time and transmit the data to the control system. If the temperature of the cleaning liquid is lower than the preset value, the control system will automatically control the heater to increase the temperature of the cleaning liquid. Similarly, the pressure sensor and flow sensor can also monitor the pressure and flow rate of the cleaning liquid in real time and adjust them automatically as needed. After the cleaning is completed, the sensor module is used again to detect the degree and type of contamination on the surface of the wafer, and compare it with the contamination data before cleaning to determine whether the cleaning effect meets the standard. Assuming that the degree of contamination before cleaning is heavy contamination and the degree of contamination after cleaning is light contamination, it can be considered that the cleaning effect meets the standard. If the cleaning effect does not meet the standard, the non-standard data will be fed back to the intelligent control system. The intelligent control system can use machine learning algorithms, such as reinforcement learning algorithms, to automatically adjust the parameters in the cleaning formula, such as cleaning time, cleaning agent concentration and cleaning temperature, based on the non-standard data and historical cleaning data. Assuming that there is still some organic contamination after cleaning, the intelligent control system can appropriately increase the concentration of the organic solvent or extend the cleaning time based on historical data. The optimized cleaning formula will be stored in the cleaning formula database as a reference for subsequent cleaning operations. By continuously accumulating and improving the cleaning formula library, cleaning efficiency and quality can be improved, and resource consumption in the cleaning process can be reduced. For example, by optimizing the cleaning formula, the cleaning time can be shortened and the concentration of the cleaning agent can be reduced, thereby saving energy and reducing waste liquid emissions.

[0033] Step S103, during the wafer cleaning process, the ambient temperature, humidity and pressure parameters in the cleaning equipment are collected in real time through sensors, and the ambient temperature, humidity and pressure parameters are compared with a preset optimal range, which is determined based on historical cleaning data and wafer material characteristics; if the deviation of the comparison result exceeds a preset threshold, an alarm is triggered, and the process parameters of the cleaning equipment are automatically adjusted to maintain the stability of the cleaning environment.

[0034] Acquire the ambient temperature, humidity and pressure parameters in the wafer cleaning equipment collected in real time by the sensor module; obtain the optimal environmental parameter range that matches the current wafer material characteristics from the historical cleaning database; compare the ambient temperature, humidity and pressure parameters collected in real time with the optimal environmental parameter range to obtain a deviation value; if the deviation value exceeds a preset threshold, trigger an alarm, and determine the cleaning equipment process parameters that need to be adjusted and the adjustment range; adjust the corresponding process parameters of the cleaning equipment according to the process parameter adjustment instruction to obtain an adjustment result; if the deviation value still exceeds the preset threshold after multiple consecutive adjustments, it is determined that there is a cleaning equipment failure and the equipment self-test program is triggered.

[0035] For example, in the wafer cleaning process, the control of ambient temperature, humidity and pressure is crucial. For example, if the ambient temperature is too high, the volatilization rate of the cleaning fluid may be accelerated, thereby affecting the cleaning effect. Assume that historical data shows that for a certain wafer material, the optimal cleaning ambient temperature should be controlled between 23°C and 25°C. The ambient temperature monitored in real time by the sensor module is 27°C, which exceeds the set optimal range. At this time, the central processor calculates that the temperature deviation is 2°C and determines that this deviation exceeds the allowed threshold of 1°C. The central processor immediately triggers an alarm and determines that the ambient temperature needs to be lowered based on the direction and size of the deviation. The specific operation may be to increase the cooling intensity of the air conditioner or adjust the ventilation system of the workshop to lower the ambient temperature. After receiving the adjustment instruction, the actuator module adjusts the corresponding equipment parameters, such as setting the air conditioner temperature to 23°C. After the adjustment is completed, the actuator module feeds back the adjustment result to the central processor, and the central processor continues to monitor the ambient temperature to ensure that it is stable within the optimal range. In continuous monitoring, if it is found that the environmental parameters cannot be stabilized within the preset threshold after multiple adjustments, the central processor will consider that there may be equipment failure. At this time, the self-check program will be triggered to check the temperature control module, sensors, etc. of the cleaning equipment. If the self-check program finds that the air-conditioning system is short of refrigerant, the central processor will obtain the operating instructions for replenishing the refrigerant from the knowledge base and execute the self-repair program to replenish the refrigerant to ensure the normal operation of the air-conditioning system. In addition, all environmental parameter data and equipment adjustment data will be recorded and added to the historical cleaning database. These data will be used to analyze and optimize the subsequent cleaning process. For example, if data analysis finds that cooling is frequently required within a certain period of time, it may be recommended to improve the overall heat dissipation design of the workshop, thereby reducing dependence on air conditioning and improving energy efficiency and cleaning efficiency. Such continuous optimization can significantly improve the quality and efficiency of wafer cleaning and ensure that the wafer cleaning process is more stable and reliable.

[0036] Step S104, after cleaning is completed, the wafer surface is inspected again by machine vision, the inspection image after cleaning is compared with the image before cleaning, and the contamination removal rate is calculated; the contamination removal rate is compared with the preset cleaning qualification standard. If the cleaning qualification standard is not met, return to step S102 and re-execute cleaning until the cleaning qualification standard is met.

[0037] Acquire a wafer surface image, the image containing wafer surface contamination degree information; analyze and process the image to obtain contamination parameters characterizing the wafer surface contamination degree; determine the cleaning solution formula and cleaning process parameters required for this cleaning from a preset cleaning solution formula library according to the contamination parameters; adopt a multi-stage cleaning strategy to clean the wafer, the multi-stage cleaning includes at least a first-stage cleaning and a second-stage cleaning, and the first-stage cleaning and the second-stage cleaning use different cleaning solutions and cleaning process parameters; during the wafer cleaning process, acquire real-time monitoring data characterizing the cleaning process, the monitoring data including cleaning solution temperature, cleaning solution concentration and cleaning solution flow rate; determine whether the cleaning solution formula and cleaning process parameters need to be adjusted according to the real-time monitoring data, and if adjustment is required, dynamically adjust the cleaning solution formula and cleaning process parameters; after the wafer cleaning is completed, acquire a wafer surface image after cleaning, compare and analyze the image after cleaning with the image before cleaning, and obtain a contamination removal rate; determine whether the contamination removal rate reaches a preset threshold, and if not, return to re-execute the cleaning until the contamination removal rate reaches the preset threshold.

[0038] For example, the application of machine vision technology is crucial in the wafer manufacturing process. For example, by capturing images of the wafer surface with a high-resolution camera, tiny contaminants on the surface, such as dust or chemical residues, can be accurately identified. These images are analyzed by image processing algorithms to assess the degree of contamination on the wafer. Based on this information, the chemical formula of the cleaning solution can be accurately adjusted, such as increasing the proportion of a specific solvent to remove specific types of contaminants in a targeted manner. It is common practice to adopt a multi-stage cleaning strategy during the cleaning process. For example, a milder cleaning solution is initially used to remove large-area contamination, and then a stronger cleaning solution is used for local treatment of stubborn contamination. This staged approach can effectively improve cleaning efficiency while reducing potential damage to wafer materials. Real-time monitoring of cleaning solution parameters such as temperature, concentration and flow rate is key to ensuring cleaning results. For example, if the sensor detects that the temperature of the cleaning solution is lower than the set value, the intelligent control system will automatically heat the cleaning solution to maintain the cleaning effect. Similarly, if the concentration is low, the system will automatically add more cleaning agent. After cleaning is completed, machine vision technology is used again to check the wafer surface. By comparing the images before and after cleaning, the contamination removal rate can be calculated. For example, through image analysis software, changes in the wafer surface before and after cleaning, such as the degree of reduction of contaminants, can be identified, thereby calculating the contamination removal rate. If the contamination removal rate does not meet the preset standard, the system will automatically repeat the cleaning process until a satisfactory cleaning effect is achieved. This highly automated and precisely controlled cleaning process not only improves production efficiency, but also ensures the quality and reliability of wafers, thus playing a vital role in the semiconductor manufacturing industry.

[0039] Step S105, after the cleaning reaches the qualified standard, the surface of the wafer is morphologically detected by an atomic force microscope to obtain the roughness and defect density parameters of the wafer surface; the roughness and defect density parameters are compared with the preset wafer surface quality standards to determine whether the cleaning process causes damage to the surface structure of the wafer; if it is detected that the surface structure is damaged, the damage type and degree are recorded, and the parameters of the cleaning formula are adjusted to reduce similar damage.

[0040] Acquire a preset wafer surface quality standard, wherein the preset wafer surface quality standard includes a target roughness and a target defect density. Acquire real-time monitoring data of a sensor module, wherein the monitoring data includes the degree of contamination of the wafer surface, the temperature of the cleaning solution, the concentration of the cleaning solution, and the flow rate of the cleaning solution. Determine the formula of the cleaning solution and the cleaning process parameters according to the monitoring data. Use a multi-stage cleaning strategy to clean the wafer, wherein the multi-stage cleaning strategy includes using different cleaning solutions and cleaning methods at different stages. Use a machine learning algorithm to optimize the cleaning process according to the monitoring data and historical cleaning data to obtain adjusted cleaning process parameters. Perform the wafer cleaning again according to the adjusted cleaning process parameters. Use an atomic force microscope to perform morphological detection on the surface of the cleaned wafer to obtain the roughness and defect density parameters of the wafer surface. Compare the obtained roughness and defect density parameters with the preset wafer surface quality standard to determine whether the cleaning process causes damage to the wafer surface structure. If it is determined that the wafer surface structure is damaged, record the damage type and damage degree. According to the damage type and damage degree, the formula parameters of the cleaning solution are adjusted to obtain a new cleaning solution formula. According to the new cleaning solution formula, the wafer is cleaned again. The surface of the cleaned wafer is again tested by atomic force microscopy to obtain new roughness and new defect density parameters. The new roughness and new defect density parameters are compared with the preset wafer surface quality standard to determine whether the new cleaning solution formula effectively reduces the damage.

[0041] For example, real-time monitoring of the degree of contamination on the wafer surface and the parameters of the cleaning solution, such as temperature, concentration, flow rate, etc., through the sensor module is a key step to ensure the cleaning effect. For example, the use of a high-precision temperature sensor can monitor the temperature of the cleaning solution in real time and keep it within the range of 50±2°C to ensure that the chemical activity of the cleaning solution is optimal. The concentration sensor is used to monitor the concentration of active oxygen in the cleaning solution and maintain it at 0±1mol / L to ensure sufficient oxidation capacity to remove pollutants. The flow rate sensor monitors the flow rate of the cleaning solution and maintains it at 5±2L / min to ensure that the cleaning solution evenly covers the wafer surface. According to the monitoring results, the intelligent control system automatically adjusts the formula of the cleaning solution and the cleaning process parameters. For example, if the temperature sensor shows that the temperature is too low, the system will automatically heat it to the set range; if the concentration is too low, the system will automatically replenish the active oxygen component. This intelligent adjustment mechanism is based on a preset algorithm model and can quickly respond to parameter changes to ensure that the cleaning process is always in the optimal state. A multi-stage cleaning strategy is adopted, and different cleaning solutions and cleaning methods are used at different stages. For example, in the first stage, alkaline cleaning solution is used to remove organic pollutants, in the second stage, acidic cleaning solution is used to remove metal ions, and in the third stage, deionized water is used for rinsing. The time and temperature of each stage are strictly controlled, such as the temperature of the first stage is controlled at 60°C for 10 minutes; the temperature of the second stage is controlled at 40°C for 8 minutes; the temperature of the third stage is controlled at room temperature for 5 minutes. The cleaning process is optimized using machine learning algorithms, and the control parameters are adjusted by continuously accumulating cleaning data. For example, the system records the temperature, concentration, flow rate and corresponding pollution removal rate of each cleaning, and uses these data to train the machine learning model. The model analyzes the data and finds that the pollution removal rate is the highest at 55°C, and the system sets this temperature as the optimal temperature. After cleaning, an atomic force microscope is used to detect the morphology of the wafer surface to obtain the roughness and defect density parameters of the wafer surface. For example, the atomic force microscope scanning results show that the roughness of the wafer surface after cleaning is 5nm and the defect density is 1×10^6 / cm 2 These parameters are compared with the preset wafer surface quality standards, which are roughness not exceeding 1nm and defect density not exceeding 2×10^6 / cm 2. According to the comparison results, determine whether the cleaning process causes damage to the surface structure of the wafer. If the surface structure is damaged, record the type and degree of damage. For example, if microcracks are detected on the surface, record the length and depth of the cracks, such as a crack length of 10μm and a depth of 2μm. According to the type and degree of damage, adjust the parameters of the cleaning formula to reduce the occurrence of similar damage. For example, if there are many microcracks, it may be caused by the strong acidity of the cleaning solution. The system will adjust and reduce the concentration of the acidic cleaning solution, such as from 2mol / L to 5mol / L. The wafer is cleaned again with the adjusted cleaning formula. The adjusted wafer surface is repeatedly inspected using an atomic force microscope to confirm whether the new cleaning parameters effectively reduce the damage. For example, the adjusted cleaned wafer is inspected again, and the crack length is reduced to 5μm and the depth is reduced to 1μm, indicating that the adjustment is effective. This multi-parameter monitoring and intelligent adjustment mechanism can significantly improve the cleaning effect and reduce damage to the wafer surface. Through real-time monitoring and intelligent control, the cleaning process is always in the optimal state, which improves the yield rate of the wafer. The high-precision detection of atomic force microscopes provides a reliable basis for the evaluation of cleaning effects, ensuring that the surface quality of wafers meets production requirements. The application of machine learning algorithms continuously optimizes the cleaning process, improving cleaning efficiency and wafer quality. This comprehensive cleaning strategy not only improves the cleaning effect, but also continuously optimizes the cleaning process through data-driven methods, reducing resource waste and environmental pollution, and has important technical and economic significance.

[0042] Step S106, recording the cleaning process data of each batch of wafers, wherein the cleaning process data includes cleaning formula, cleaning parameters, cleaning time, cleaning agent dosage, contamination removal rate and surface damage; applying big data analysis technology to explore the optimal cleaning process for different types of wafers, and dynamically updating and optimizing the cleaning formula database to improve cleaning efficiency and yield.

[0043] The sensor module is used to monitor the wafer surface contamination level and cleaning fluid parameters in real time, including temperature, concentration and flow rate. The central processing unit is used to analyze and process the monitoring data to obtain the cleaning process data of each batch of wafers, including cleaning formula, cleaning parameters, cleaning time, cleaning agent dosage, contamination removal rate and surface damage. The cleaning process is optimized based on a machine learning algorithm, and the control parameters are adjusted through the continuously accumulated cleaning data.

[0044] Exemplarily, the degree of contamination on the surface of the wafer and the parameters of the cleaning solution, such as temperature, concentration, flow rate, etc., are monitored in real time by the sensor module. For example, the sensor module may include an optical sensor and an electrochemical sensor. The optical sensor detects the degree of surface contamination by changes in the intensity of reflected light, while the electrochemical sensor monitors the concentration of the cleaning solution by measuring changes in the conductivity of the cleaning solution. Assume that a monitoring result shows that the temperature of the cleaning solution is 60°C, the concentration is 5%, the flow rate is 2 liters / minute, and the degree of contamination on the surface of the wafer is moderate. According to the monitoring results, the intelligent control system automatically adjusts the formula of the cleaning solution and the cleaning process parameters. For example, if the system finds that excessive temperature may cause damage to the surface of the wafer, it will automatically reduce the temperature to 55°C and increase the concentration of the cleaning solution to 6% according to the degree of contamination to enhance the cleaning effect. The intelligent control system usually adjusts parameters based on preset algorithms and thresholds to ensure the optimization of the cleaning effect. The central processor is used to analyze and process the collected data to obtain the cleaning process data of each batch of wafers, including cleaning formula, cleaning parameters, cleaning time, cleaning agent dosage, contamination removal rate and surface damage. For example, the cleaning process data of a batch of wafers shows that the cleaning formula is a mixture of type A cleaning agent and type B additive, the cleaning time is 30 minutes, the amount of cleaning agent is 10 liters, the pollution removal rate reaches 95%, but the surface damage rate is 2%. Through the multi-dimensional analysis of the central processor, these data can reveal potential problems in the cleaning process, such as excessive cleaning time may lead to increased surface damage. The human-computer interaction interface displays various parameters and states of the cleaning process in real time, and provides functions such as parameter setting and fault alarm. For example, the operator can see the current temperature, concentration and flow rate of the cleaning solution, as well as the degree of contamination on the wafer surface through the interface. If the system detects that the temperature of the cleaning solution is abnormally high, the interface will immediately display a fault alarm to prompt the operator to intervene. The human-computer interaction interface is designed to be user-friendly, which is convenient for operators to quickly understand and respond, and improve production efficiency. The cleaning process is optimized using machine learning algorithms, and the control parameters are adjusted by continuously accumulating cleaning data. For example, the system analyzes historical data and finds that when the cleaning solution concentration is 6%, the pollution removal rate is the highest and the surface damage rate is the lowest, so this parameter will be set to the optimal value. The application of machine learning algorithms makes the cleaning process more intelligent, and can dynamically adjust parameters according to actual conditions to improve the cleaning effect. Automatically adjust cleaning parameters according to the degree of wafer contamination to reduce the waste of cleaning fluid. For example, if the sensor detects that the surface of the wafer is lightly contaminated, the system will automatically reduce the concentration and amount of cleaning fluid to avoid excessive cleaning, which saves costs and protects the surface of the wafer. This dynamic adjustment mechanism not only improves resource utilization, but also reduces environmental pollution. Use big data analysis technology to explore the optimal cleaning process for different types of wafers. For example, by analyzing a large amount of cleaning data, the system finds that a certain type of wafer has the best cleaning effect when using a specific cleaning formula and process parameters, and will store the solution in the database for subsequent production reference.The application of big data analysis technology makes the optimization of cleaning process no longer rely on experience, but based on scientific data analysis, which improves the reliability and consistency of the process. The cleaning formula database is optimized by dynamic updating to improve the cleaning efficiency and yield. For example, the system will evaluate the cleaning effect after each cleaning. If it is found that the new cleaning formula is more effective, the database will be updated to ensure that the cleaning formula in the database is always in the optimal state. The dynamic update mechanism ensures the continuous improvement of the cleaning process and improves production efficiency and product quality. The system also has self-diagnosis and self-repair functions, which can timely detect and solve system failures and improve the reliability and stability of the system. For example, the system regularly checks the working status of each module through the built-in diagnostic program. If a sensor failure is found, it will automatically switch to the backup sensor and prompt the maintenance personnel to repair it. The application of self-diagnosis and self-repair functions greatly reduces the impact of system failures on production and improves the operating efficiency of the system. Through the comprehensive application of the above series of technologies and measures, the wafer cleaning process has achieved a high degree of automation and intelligence, which not only improves the cleaning effect and product quality, but also reduces production costs and environmental pollution, bringing significant economic and social benefits to the enterprise.

[0045] Step S107, predict and optimize the energy consumption and material consumption of the cleaning equipment based on the wafer production plan, feedback information from the equipment management system, historical cleaning effect data and energy consumption data; apply an intelligent scheduling algorithm based on multi-objective optimization, comprehensively consider cleaning effect, energy consumption, material consumption and equipment utilization factors, reasonably arrange cleaning tasks, minimize cleaning costs, take into account production efficiency and delivery time, and realize intelligent management and control of the cleaning process.

[0046] Obtain data from wafer production planning and equipment management systems, as well as historical cleaning effect data and energy consumption data. Based on the data, use machine learning algorithms to predict the energy consumption and material consumption of cleaning equipment. Based on the prediction results, apply a multi-objective optimization algorithm to construct a function with the goal of minimizing cleaning costs, which combines cleaning effects, predicted energy and material consumption, equipment utilization, production efficiency, and delivery time. Solve the multi-objective optimization problem based on the objective function and constraints to obtain a preliminary scheduling plan for the cleaning task. Obtain the wafer surface contamination degree and cleaning fluid parameters monitored in real time by the sensor module, including temperature, concentration, and flow rate data. According to the wafer surface contamination degree, dynamically adjust the cleaning fluid concentration and flow rate to optimize the cleaning intensity and resource usage. After determining the final cleaning parameters, adjust the cleaning fluid formula and cleaning process parameters to generate a final cleaning task scheduling plan. Send the cleaning task scheduling plan to the actuator module to automatically execute the cleaning process. After the cleaning process is completed, collect the cleaning effect data, actual energy consumption data, and material consumption data, and store them in the historical database for subsequent prediction and optimization.

[0047] For example, in the wafer cleaning process, it is first necessary to obtain feedback information from the wafer production plan and equipment management system, which can help predict the energy consumption and material consumption of the cleaning equipment. For example, if the production plan shows that a large number of high-precision wafers will be processed in the next week, the system can predict that the energy consumption of the cleaning equipment will increase during this period because a higher standard cleaning process is required. Next, by applying machine learning algorithms, the system can analyze historical data and current equipment status to predict energy consumption and material consumption under different cleaning formulas and parameters. For example, the machine learning model may find that the use of a certain cleaning agent formula can significantly reduce energy consumption while maintaining the cleaning effect. Using a multi-objective optimization algorithm, the system comprehensively considers the cleaning effect, predicted energy consumption and material consumption, equipment utilization, production efficiency and delivery time, and constructs an objective function that minimizes the cleaning cost. In actual operation, this may mean that the system needs to find a balance between reducing energy consumption and ensuring cleaning quality. For example, by adjusting the flow rate and temperature of the cleaning fluid, the cleaning process can be optimized so that the use of energy and materials is minimized without sacrificing the cleanliness of the wafer surface. During the cleaning process, the sensor module monitors the degree of contamination on the wafer surface and the parameters of the cleaning solution, such as temperature, concentration, flow rate, etc., in real time. According to the degree of contamination of the wafer, the intelligent control system automatically adjusts the formula and flow rate of the cleaning solution. For example, for wafers with a higher degree of contamination, the system may increase the concentration of the cleaning solution and increase the flow rate to enhance the cleaning effect; while for wafers with a lower degree of contamination, these parameters can be reduced to save resources and reduce potential damage to the wafer. Finally, based on the real-time monitoring data and the results of the optimization algorithm, the system generates the final cleaning task scheduling plan and automatically executes the cleaning process through the actuator module. After the cleaning is completed, the system collects cleaning effect data, actual energy consumption data, and material consumption data, and stores these data in the historical database. These data will be used for future predictions and optimizations to help further reduce cleaning costs, improve cleaning efficiency and wafer production quality. In this way, the entire cleaning process is efficient and automated, ensuring high efficiency and high quality of wafer cleaning, while also optimizing the use of resources and reducing production costs.

[0048] The above only lists some preferred embodiments of the present invention, but the present invention is not limited thereto, and many improvements and changes can be made. As long as the improvements and changes are made on the basis of the basic principles of the present invention, they should be regarded as falling within the protection scope of the present invention.

Claims

1. A cleaning method for a semiconductor wafer cleaning system, characterized in that: The method comprises the following steps: Step S101, acquiring a wafer surface image, processing the wafer surface image using an image segmentation algorithm, identifying a contaminated area and a non-contaminated area in the wafer surface image, and determining the contamination degree and contamination type of the wafer surface according to the area, morphology and grayscale characteristics of the contaminated area; Step S102, selecting an optimal cleaning formula from a preset cleaning formula database according to the judgment results of the contamination degree and the contamination type, and dynamically adjusting the cleaning time, cleaning agent concentration and cleaning temperature parameters in the optimal cleaning formula according to the structural complexity of the wafer surface, wherein the structural complexity includes line width, aspect ratio and pattern density, to obtain a dynamically adjusted cleaning formula; Step S103, during the wafer cleaning process, the ambient temperature, humidity and pressure parameters in the cleaning equipment are collected in real time through sensors, and the ambient temperature, humidity and pressure parameters are compared with a preset optimal range, which is determined based on historical cleaning data and wafer material characteristics. If the deviation of the comparison result exceeds a preset threshold, an alarm is triggered, and the process parameters of the cleaning equipment are automatically adjusted to maintain the stability of the cleaning environment; Step S104, after the cleaning is completed, the surface of the wafer is inspected again by machine vision, the inspection image after cleaning is compared with the image before cleaning, the pollution removal rate is calculated, and the pollution removal rate is compared with the preset cleaning qualification standard. If the cleaning qualification standard is not met, return to step S102 and perform cleaning again until the cleaning qualification standard is met; Step S105, after the cleaning reaches the qualified standard, the surface of the wafer is tested by an atomic force microscope to obtain the roughness and defect density parameters of the wafer surface, and the roughness and defect density parameters are compared with the preset wafer surface quality standards to determine whether the cleaning process causes damage to the surface structure of the wafer. If the surface structure is damaged, the damage type and degree are recorded, and the parameters of the cleaning formula are adjusted to reduce similar damage; Step S106, recording the cleaning process data of each batch of wafers, wherein the cleaning process data includes cleaning formula, cleaning parameters, cleaning time, cleaning agent dosage, contamination removal rate and surface damage, applying big data analysis technology to mine the optimal cleaning process for different types of wafers, and dynamically updating and optimizing the cleaning formula database to improve cleaning efficiency and yield; Step S107, based on the wafer production plan, feedback information from the equipment management system, historical cleaning effect data and energy consumption data, predict and optimize the energy consumption and material consumption of the cleaning equipment, apply an intelligent scheduling algorithm based on multi-objective optimization, comprehensively consider cleaning effect, energy consumption, material consumption and equipment utilization factors, reasonably arrange cleaning tasks, minimize cleaning costs, take into account production efficiency and delivery time, and realize intelligent management and control of the cleaning process.

2. The cleaning method of the semiconductor wafer cleaning system according to claim 1, characterized in that: The step S101 also includes the following steps: a. Obtain high-definition images of the wafer surface, and use image preprocessing algorithms to denoise and enhance the images to improve image quality; b. Based on the characteristics of the wafer surface, the image is divided into different areas using an image segmentation algorithm to distinguish between contaminated areas and non-contaminated areas; c. Extract the characteristic parameters of the area, shape and grayscale of the polluted area and construct the pollution feature vector; d. Input the pollution feature vector into the pre-trained pollution degree classification model to determine the pollution degree of the wafer surface and obtain the pollution degree level; e. Input the pollution feature vector into the pre-trained pollution type classification model to determine the pollution type on the wafer surface and obtain the specific pollution type; f. Obtain the corresponding cleaning solution formula and cleaning parameters from the cleaning process database according to the pollution level and pollution type; g. Input the cleaning liquid formula and cleaning parameters into the cleaning equipment control module to automatically configure the process parameters of the cleaning equipment; h. Start the cleaning equipment and clean the wafer according to the configured process parameters; After cleaning is completed, the wafer surface image is acquired again, and step be is repeated to determine the degree and type of contamination after cleaning. If the cleaning requirements are not met, return to step f and adjust the cleaning process until the cleaning is qualified.

3. The cleaning method of the semiconductor wafer cleaning system according to claim 1, characterized in that: The step S102 also includes: Obtaining contamination degree data and contamination type data on the wafer surface; Selecting an optimal cleaning formula from a preset cleaning formula database according to the contamination degree data and the contamination type data; Acquiring the structural complexity of the wafer surface, wherein the structural complexity includes line width, aspect ratio and pattern density; According to the complexity of the structure, dynamically adjusting the cleaning time, cleaning agent concentration and cleaning temperature parameters in the optimal cleaning formula to obtain a dynamically adjusted cleaning formula; Obtaining wafer surface data after cleaning; Determining whether the surface data of the cleaned wafer reaches a preset threshold; If it is not reached, the cleaning recipe optimization process is triggered.

4. The cleaning method of a semiconductor wafer cleaning system according to claim 1, characterized in that: The step S103 also includes: Obtain the ambient temperature, humidity and pressure parameters in the wafer cleaning equipment collected in real time by the sensor module; Obtain the optimal environmental parameter range that matches the current wafer material characteristics from the historical cleaning database; Compare the real-time collected environmental temperature, humidity and pressure parameters with the optimal environmental parameter range to obtain a deviation value; If the deviation value exceeds the preset threshold, an alarm is triggered, and the process parameters of the cleaning equipment that need to be adjusted and the adjustment range are determined; According to the process parameter adjustment instruction, the corresponding process parameters of the cleaning equipment are adjusted to obtain the adjustment result; If the deviation value still exceeds the preset threshold after multiple consecutive adjustments, it is determined that there is a cleaning equipment failure and the equipment self-check program is triggered.

5. The cleaning method of a semiconductor wafer cleaning system according to claim 1, characterized in that: The step S104 also includes: Acquire a wafer surface image, wherein the image contains information on the degree of contamination on the wafer surface; Analyzing and processing the image to obtain a contamination parameter representing the degree of contamination on the wafer surface; According to the contamination parameters, the cleaning solution formula and cleaning process parameters required for this cleaning are determined from a preset cleaning solution formula library; The wafer is cleaned by adopting a multi-stage cleaning strategy, wherein the multi-stage cleaning includes at least a first-stage cleaning and a second-stage cleaning, and the first-stage cleaning and the second-stage cleaning use different cleaning solutions and cleaning process parameters; During the wafer cleaning process, obtaining real-time monitoring data characterizing the cleaning process, wherein the monitoring data includes cleaning solution temperature, cleaning solution concentration, and cleaning solution flow rate; According to the real-time monitoring data, it is determined whether the cleaning solution formula and cleaning process parameters need to be adjusted, and if so, the cleaning solution formula and cleaning process parameters are dynamically adjusted; After the wafer is cleaned, an image of the wafer surface after cleaning is obtained, and the image after cleaning is compared and analyzed with the image before cleaning to obtain a contamination removal rate; It is determined whether the pollution removal rate reaches a preset threshold value. If not, the cleaning process is returned and the cleaning process is repeated until the pollution removal rate reaches the preset threshold value.

6. The cleaning method of a semiconductor wafer cleaning system according to claim 1, characterized in that: The step S105 also includes: Obtaining a preset wafer surface quality standard, wherein the preset wafer surface quality standard includes a target roughness and a target defect density; Acquiring real-time monitoring data of the sensor module, the monitoring data including the degree of contamination of the wafer surface, the temperature of the cleaning solution, the concentration of the cleaning solution and the flow rate of the cleaning solution; Determining the formula of the cleaning solution and cleaning process parameters according to the monitoring data; The wafer is cleaned using a multi-stage cleaning strategy, wherein the multi-stage cleaning strategy includes using different cleaning solutions and cleaning methods at different stages; According to the monitoring data and historical cleaning data, a machine learning algorithm is used to optimize the cleaning process to obtain adjusted cleaning process parameters; According to the adjusted cleaning process parameters, the wafer is cleaned again; Using an atomic force microscope to perform morphology detection on the surface of the cleaned wafer to obtain roughness and defect density parameters of the wafer surface; Comparing the obtained roughness and defect density parameters with the preset wafer surface quality standard to determine whether the cleaning process causes damage to the wafer surface structure; If it is determined that the surface structure of the wafer is damaged, recording the damage type and damage degree; According to the damage type and damage degree, adjusting the formula parameters of the cleaning solution to obtain a new cleaning solution formula; According to the new cleaning solution formula, the wafer is cleaned again; The cleaned wafer surface is again tested using an atomic force microscope to obtain new roughness and new defect density parameters; The new roughness and the new defect density parameters are compared with the preset wafer surface quality standard to determine whether the new cleaning solution formula effectively reduces the damage.

7. A control system for a semiconductor wafer cleaning system, characterized in that: The control system adopts the cleaning method of the semiconductor wafer cleaning system according to any one of claims 1 to 6 to control operation, and the control system comprises: Wafer surface contamination detection module, used to identify contaminated areas and determine the degree and type of contamination; A cleaning recipe optimization module is used to select the optimal cleaning recipe and dynamically adjust parameters according to the wafer structure; The cleaning process monitoring module is used to monitor the cleaning environment parameters in real time and automatically adjust them to maintain stability; The cleaning effect evaluation module is used to detect the wafer surface after cleaning and determine whether it meets the cleaning standards; Data analysis and optimization module, used to record cleaning data, analyze optimal processes and update the cleaning formula database; Intelligent scheduling and control module is used to optimize the energy and material consumption of cleaning equipment and reasonably arrange cleaning tasks.

Images