Wafer cleaning equipment multi-cavity chemical liquid intelligent circulation control method

Abstract

The present application relates to the field of information technology, in particular to a kind of wafer cleaning equipment multi-cavity chemical liquid intelligent circulation control method of semiconductor wafer cleaning technology, comprising: the optimized parameter calculated is sent to the control unit of corresponding cleaning cavity, the actual working flow of the cavity circulating pump and the actual working state of filter device are adjusted, the dynamic optimization of the chemical liquid circulation use process of the cavity is carried out, so that the quality of chemical liquid recovers to the process requirement range;For the cleaning process requirement of different wafer products, the threshold range of the quality parameter of chemical liquid of each cleaning cavity is established in advance, when wafer cleaning equipment switches product model, according to product model, the corresponding chemical liquid quality control threshold of each cavity is automatically matched, and the dynamic adjustment of chemical liquid circulation mode and parameter in cavity is realized.

Description

Technical Field

[0001] The present invention relates to the field of information technology, specifically to semiconductor wafer cleaning technology, and more particularly to a multi-cavity liquid intelligent circulation control method for wafer cleaning equipment. Background Art

[0002] During semiconductor wafer manufacturing, wafers need to be cleaned. The recycling of chemical solutions across multiple cleaning chambers presents interrelated technical challenges. First, chemical quality parameters such as concentration, temperature, and pH in each chamber can gradually deviate from process requirements over time, impacting cleaning performance. Second, different wafer products have varying chemical quality requirements, necessitating dynamic adjustment of chemical circulation parameters within each chamber. Furthermore, optimizing scheduling to improve overall efficiency and chemical utilization when multiple chambers are working together poses a significant challenge. These interrelated issues require a comprehensive solution. By installing sensors in each chamber to monitor chemical quality in real time and incorporating intelligent control algorithms to dynamically adjust the circulation pump flow rate and filtration parameters, chemical quality can be maintained within process requirements. Furthermore, by establishing a correlation model between chemical solution usage time and quality degradation based on historical data, the optimal replacement cycle can be predicted to reduce waste. Furthermore, a central controller monitors the operating status of each chamber in real time, automatically selecting the appropriate chamber based on wafer cleaning progress and process requirements, and invoking the corresponding chemical circulation control strategy, enabling continuous cleaning of multiple products and optimizing resource utilization. Summary of the Invention

[0003] The present invention provides a multi-chamber liquid intelligent circulation control method for wafer cleaning equipment, the method comprising the following steps:

[0004] Step S1: Acquire real-time data on the circulation of the medicinal solution in multiple cleaning chambers, specifically including parameters of the concentration, temperature, and pH of the medicinal solution in each chamber, using concentration sensors, temperature sensors, and pH sensors installed at key locations in the circulation pipeline of each chamber to collect the data, and record the usage time of the medicinal solution in each chamber;

[0005] Step S2: Input the acquired real-time data of the chemical liquid quality parameters of each cavity into the intelligent control algorithm model. The algorithm model determines whether the current chemical liquid quality of each cavity meets the preset wafer cleaning process requirements. If so, continue to acquire real-time data. If not, calculate the optimized chemical liquid circulation pump flow rate and filter device working state parameters of the cavity based on the deviation degree between the chemical liquid quality parameters and the preset process requirements through the intelligent control algorithm.

[0006] Step S3: Send the calculated optimization parameters to the control unit of the corresponding cleaning chamber, adjust the actual working flow of the circulation pump of the chamber and the actual working state of the filter device, and dynamically optimize the liquid recycling process of the chamber to restore the liquid quality to within the process requirements;

[0007] Step S4: Obtain the operating parameters of each cleaning chamber and the corresponding chemical solution usage time data during the actual operation of the wafer cleaning equipment, establish a correlation model between the chemical solution usage time of each chamber and the chemical solution quality attenuation through a machine learning algorithm, dynamically predict the optimal chemical solution replacement cycle for each chamber, guide the regular replacement of the chemical solution, and reduce chemical solution waste;

[0008] Step S5: Obtain the liquid circulation process parameters of each cleaning chamber and the corresponding cleaning effect test results during the actual operation of the wafer cleaning equipment. Use a data mining algorithm to extract the inherent correlation between the liquid quality, circulation parameters and cleaning effect of each chamber from historical big data, form a knowledge base for optimizing the liquid circulation control strategy by chamber, and guide the dynamic optimization of the intelligent control algorithm of each chamber.

[0009] Step S6: Pre-establish a threshold range for the chemical liquid quality parameters of each cleaning chamber based on the cleaning process requirements of different wafer products. When the wafer cleaning equipment switches product models, the chemical liquid quality control threshold corresponding to each chamber is automatically matched according to the product model, thereby achieving dynamic adjustment of the chemical liquid circulation mode and parameters of each chamber;

[0010] Step S7: Acquire real-time operating status data of the wafer cleaning equipment, specifically including the wafer cleaning progress and liquid circulation parameters of each cleaning chamber. The operating status of each chamber is monitored in real time by the central controller. When the wafer cleaning of a chamber is completed, it immediately switches to the next pre-configured idle chamber. Based on the process requirements of the wafer to be cleaned, the corresponding liquid circulation control strategy is retrieved from the knowledge base, and the liquid circulation parameters of the new chamber are preset to achieve continuous multi-chamber cleaning of different wafer products.

[0011] Step S8: Based on the optimized intelligent control algorithm and the sub-chamber knowledge base, the liquid circulation process of multiple cleaning chambers is monitored and dynamically adjusted in real time. When the liquid quality parameters of a certain chamber deviate from the preset threshold, the optimization control algorithm of the chamber is triggered, and the new liquid circulation pump flow and filter device parameters are calculated. The adjustment is performed through the control unit of the chamber. At the same time, the liquid usage time and cleaning efficiency of each chamber are comprehensively analyzed, and the scheduling strategy of multi-chamber collaborative cleaning is dynamically optimized to improve the overall efficiency of wafer cleaning and liquid utilization.

[0012] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0013] The present invention discloses a method for intelligent circulation control of multi-chamber liquid medicine in wafer cleaning equipment. The method collects liquid medicine quality parameters in real time by installing sensors on the circulation pipeline of each cleaning chamber, and inputs them into an intelligent control algorithm to determine whether the process requirements are met. If not, the optimized circulation pump flow and filter device parameters are calculated and adjusted. At the same time, a machine learning algorithm is used to establish a correlation model between the use time of liquid medicine and quality attenuation, and the optimal replacement cycle is dynamically predicted. Through data mining, the correlation rules between liquid medicine quality, circulation parameters and cleaning effect are extracted from historical data to form a knowledge base of sub-chamber optimization control strategies. Liquid medicine quality thresholds are preset for different products to achieve dynamic adjustment. The operating status of each chamber is monitored in real time to achieve continuous multi-chamber cleaning. The usage of each chamber is comprehensively analyzed to optimize the multi-chamber collaborative cleaning scheduling strategy. The present invention realizes the intelligent dynamic optimization control of multi-chamber liquid medicine circulation in the wafer cleaning process, improves cleaning efficiency and liquid medicine utilization, and reduces production costs. DETAILED DESCRIPTION

[0014] To further understand the content of the present invention, the present invention is described in detail with reference to the embodiments. The present application is further described in detail with reference to the embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention.

[0015] In this embodiment, a multi-chamber liquid intelligent circulation control method for wafer cleaning equipment may specifically include:

[0016] Step S1, obtain real-time data of the circulation process of the medicinal solution in multiple cleaning cavities, specifically including the parameters of the medicinal solution concentration, temperature and pH of each cavity, and use concentration sensors, temperature sensors and pH sensors installed at key positions of the circulation pipeline of each cavity to collect the data, and record the usage time of the medicinal solution in each cavity.

[0017] Step S1 includes: obtaining real-time data collected by concentration sensors, temperature sensors and pH sensors installed at key positions of the circulation pipelines of each cleaning cavity; judging whether the real-time concentration of the liquid medicine in each cleaning cavity meets the preset range based on the data collected by the concentration sensor; if it is lower than the preset range, controlling the dosing device to add liquid medicine to the cleaning cavity until the concentration reaches the preset range; judging whether the real-time temperature of the liquid medicine in each cleaning cavity meets the preset range based on the data collected by the temperature sensor; if it is lower than the preset range, controlling the heating device to heat the liquid medicine in the cleaning cavity until the temperature reaches the preset range; judging whether the real-time temperature of the liquid medicine in each cleaning cavity meets the preset range based on the data collected by the pH sensor whether the real-time pH value of the cleaning liquid meets the preset range; if it exceeds the preset range, the acid-adding or alkali-adding device is controlled to add acid or alkali into the cleaning cavity until the pH value reaches the preset range; the real-time concentration, the real-time temperature and the real-time pH value data of the liquid in each cleaning cavity are summarized to obtain the comprehensive quality parameters of the liquid in each cleaning cavity; the start time and the end time of use of the liquid in each cleaning cavity are recorded, and the use time of the liquid in each cleaning cavity is calculated; the comprehensive quality parameters of the liquid in each cleaning cavity and the use time are correlated with each other, and a liquid quality prediction model is established using a support vector machine algorithm; based on the liquid quality prediction model, the optimal replacement time of the liquid in each cleaning cavity is predicted.

[0018] Specifically, concentration sensors, temperature sensors, and pH sensors are installed at key locations in the cleaning chamber's circulation piping to collect real-time data on the concentration, temperature, and pH of the chemical solution. When the concentration sensor detects that the chemical solution concentration is below the lower limit of the preset range by 10%, the dosing device is controlled to add chemical solution to the cleaning chamber at a rate of 20 ml / s until the concentration reaches 12% of the preset range. When the temperature sensor detects that the chemical solution temperature is below the lower limit of the preset range by 40°C, the heating device is controlled to heat the chemical solution in the cleaning chamber at a rate of 1°C / min until the temperature reaches 45°C, which is within the preset range. When the pH sensor detects that the chemical solution's pH exceeds the preset range of 5-5, the acid dosing device is controlled to add hydrochloric acid solution with a concentration of 1 mol / L to the cleaning chamber at a rate of 1 ml / s, or the alkali dosing device is controlled to add sodium hydroxide solution with a concentration of 1 mol / L to the cleaning chamber at a rate of 1 ml / s until the pH reaches 0, which is within the preset range. The real-time concentration, temperature, and pH data of the chemical solution in each cleaning chamber are weighted averaged to obtain the comprehensive chemical solution quality parameters. The start and end times of each cleaning chamber's liquid use were recorded to calculate the liquid's usage duration. A support vector machine algorithm was used to develop a liquid quality prediction model, using the liquid's comprehensive quality parameters and usage duration as inputs and the need for liquid replacement as output. Analyzing historical data, it was determined that when the liquid's usage duration exceeded 48 hours and its comprehensive quality parameters fell below 85, it was predicted that the liquid needed replacement, thus ensuring quality stability during the liquid's recycling process.

[0019] In step S2, the acquired real-time data on the chemical quality parameters of each chamber is input into an intelligent control algorithm model. The algorithm model then determines whether the current chemical quality of each chamber meets the preset wafer cleaning process requirements. If so, real-time data acquisition continues. If not, the intelligent control algorithm calculates the optimized chemical circulation pump flow rate and filtration device operating parameters for that chamber based on the degree of deviation between the chemical quality parameters and the preset process requirements.

[0020] Step S2 includes: obtaining real-time data of the quality parameters of the drug solution in each cavity, wherein the drug solution quality parameters include pH value, temperature and concentration; using the drug solution quality parameters as input of the intelligent control algorithm model; obtaining a pre-established wafer cleaning process quality requirement standard; judging whether the drug solution quality parameters meet the wafer cleaning process quality requirement standard; if the drug solution quality parameters meet the wafer cleaning process quality requirement standard, returning to continue to obtain the real-time data of the drug solution quality parameters; if the drug solution quality parameters do not meet the wafer cleaning process quality requirement standard, determining the degree of deviation between the drug solution quality parameters and the wafer cleaning process quality requirement standard , and determine the target value for optimization and adjustment; use a machine learning algorithm to establish a mapping relationship model between the quality parameters of the medicinal liquid and the flow rate of the medicinal liquid circulation pump and the working status parameters of the filter device; input the deviation degree of the medicinal liquid quality parameters into the mapping relationship model to obtain the optimized flow rate of the medicinal liquid circulation pump and the working status parameters of the filter device; according to the optimized flow rate of the medicinal liquid circulation pump, control the flow rate of the medicinal liquid circulation pump to adjust; according to the optimized working status parameters of the filter device, adjust the backwashing frequency and backwashing time of the filter device; after executing the optimization control, return to continue to obtain the real-time data of the medicinal liquid quality parameters, and perform cyclic judgment and optimization control.

[0021] Specifically, during the wafer cleaning process, pH meters, temperature sensors, and concentration meters are installed in each chamber to collect real-time quality parameters of the chemical solution, such as pH, temperature, and concentration. These parameters serve as inputs to an intelligent control algorithm model and are compared against pre-established wafer cleaning process quality standards to determine whether the chemical solution meets these standards. If parameters deviate from the standard values, a support vector machine algorithm is used to establish a mapping relationship between the chemical solution quality parameters and the chemical solution circulation pump flow rate and filter unit operating status parameters, based on the degree of deviation. For example, if the pH value is lower than 5, the model calculates that the chemical solution circulation pump flow rate needs to be increased by 10%, the filter unit backwash frequency needs to be increased to twice per hour, and the backwash time needs to be extended to 40 seconds. Based on these optimized parameters, the control system automatically adjusts the chemical solution circulation pump flow rate and filter unit operating status, and continuously monitors changes in chemical solution quality parameters, forming a closed-loop control system. This approach enables real-time monitoring and dynamic optimization of chemical solution quality, ensuring the stability and consistency of the wafer cleaning process and improving product yield.

[0022] In step S3, the calculated optimization parameters are sent to the control unit of the corresponding cleaning chamber, the actual working flow of the circulation pump of the chamber and the actual working state of the filter device are adjusted, and the recycling process of the liquid medicine in the chamber is dynamically optimized to restore the quality of the liquid medicine to within the process requirements.

[0023] Step S3 includes: obtaining real-time data on the quality parameters of the medicinal liquid, the working flow of the circulation pump and the working status of the filtering device during the circulation of the medicinal liquid, and inputting the real-time data into the machine learning model; if the machine learning model determines that the current quality of the medicinal liquid does not meet the preset process requirements, a reinforcement learning algorithm is used to obtain a control strategy for optimizing the working flow of the circulation pump and the working status of the filtering device; according to the control strategy, the actual working flow of the circulation pump and the actual working status of the filtering device are dynamically adjusted to achieve optimized control of the medicinal liquid circulation process.

[0024] Specifically, based on the optimized parameters, the control strategy for the cleaning chamber control unit can be determined as follows: when the drug liquid quality parameters are below the threshold of 85%, the circulating pump's operating flow rate is adjusted to 120 L / min, and the filtration accuracy of the filter device is adjusted to 22 μm; when the drug liquid quality parameters are above the threshold of 85%, the circulating pump's operating flow rate is maintained at 100 L / min, and the filtration accuracy of the filter device is maintained at 45 μm. During the drug liquid circulation process, the pH value, conductivity, turbidity, and other quality parameters of the drug liquid are obtained every 5 minutes. The real-time operating flow rate of the circulating pump and the actual operating status of the filter device are also recorded. This real-time data is input into a machine learning model based on a long short-term memory network (LSTM) for analysis. By training on historical data, the machine learning model establishes a nonlinear relationship between the drug liquid quality parameters and the circulating pump's operating flow rate and the operating status of the filter device. Based on the input real-time data, it can determine whether the current drug liquid quality meets the process requirements. If the liquid medicine quality parameters fall below a threshold, the DeepQNetwork (DQN) reinforcement learning algorithm simulates different combinations of circulating pump flow rates and filter device operating states in a simulation environment. Using a reward function (such as the magnitude of improvement in the liquid medicine quality parameters), the algorithm learns strategies for optimizing the circulating pump flow rate and filter device operating states. The optimal strategy might be to increase the circulating pump flow rate to 140 L / min and adjust the filter device's filtration accuracy to 1 μm. Based on the optimization strategy output by the machine learning model, the PLC control system dynamically issues instructions to adjust the actual circulating pump flow rate to 140 L / min and the actual filtration accuracy of the filter device to 1 μm, optimizing control of the liquid medicine recycling process. During the dynamic optimization process, if the drug liquid quality parameters obtained three times in a row are restored to above the threshold of 85%, the dynamic optimization process is judged to be over, and the circulation pump and filter device are restored to normal working state; if the drug liquid quality parameters still fail to recover to above the threshold after three rounds of optimization and adjustment, the latest drug liquid quality parameters, circulation pump working flow and filter device working state data are input into the machine learning model for the next round of analysis and optimization. Through the exploration mechanism of the DQN algorithm, new optimization strategies are tried, such as further increasing the circulation pump working flow to 160L / min and adjusting the filtration accuracy of the filter device to 0.5μm. The above process is repeated continuously. Through the continuous learning optimization of the machine learning model, the circulation pump working flow and the filter device working state are dynamically adjusted until the drug liquid quality is stable within the process requirements, and the dynamic optimization of the drug liquid recycling process is completed.

[0025] Step S4, obtaining the working parameters of each cleaning chamber and the corresponding liquid usage time data during the actual operation of the wafer cleaning equipment, and establishing a correlation model between the liquid usage time of each chamber and the liquid quality attenuation through a machine learning algorithm, dynamically predicting the optimal liquid replacement cycle of each chamber, guiding the regular replacement of the liquid, and reducing liquid waste.

[0026] Step S4 includes: obtaining the operating parameters of each cleaning chamber during the operation of the wafer cleaning equipment to obtain an operating parameter data set; preprocessing the operating parameter data set to obtain a preprocessed data set; using a support vector machine algorithm to construct a correlation model between the use time of the chamber liquid and the attenuation of the liquid quality to obtain model parameters; if the predicted liquid quality is lower than a preset threshold, it is determined that the cavity needs to replace the liquid; based on the cavity that needs to replace the liquid, combined with historical liquid replacement cycle data, the optimal liquid replacement cycle of each cavity is determined by a clustering algorithm.

[0027] Specifically, during wafer cleaning equipment operation, sensors collect real-time operating parameters such as temperature, pressure, and flow rate from each cleaning chamber at a frequency of once per minute to form an operating parameter dataset. Simultaneously, the start-up and replacement time of the corresponding chemical solution in each cleaning chamber are recorded to form a chemical solution duration dataset. Data cleaning is performed on the operating parameter and chemical solution duration datasets to remove outliers and missing values, and key features such as mean temperature and peak pressure are extracted. The data are then normalized to the range of 0 to 1 using the maximum and minimum normalization method to obtain the preprocessed dataset. Using this preprocessed dataset, a support vector machine algorithm with a Gaussian kernel function is selected to construct a correlation model between chamber chemical solution duration and chemical solution mass decay. The model's penalty coefficient C and kernel parameter γ are optimized through grid search, and the model is trained using a 5-fold cross-validation method to obtain the optimal model parameters. During wafer cleaning equipment operation, real-time operating parameters for each cleaning chamber are collected every 10 minutes and input into the correlation model to predict chemical solution mass decay for each chamber. If the predicted drug mass decay value falls below a preset threshold of 8, the chamber is deemed to require drug replacement. For chambers requiring drug replacement, historical drug replacement cycle data is collected. A K-means clustering algorithm is used to categorize replacement cycles into long, medium, and short categories. The mean of each category is taken as the optimal drug replacement cycle for the chamber, for example, a short cycle of 7 days, a medium cycle of 14 days, and a long cycle of 30 days. Based on the optimal replacement cycle, a regular drug replacement schedule is generated for each chamber to guide staff in regularly replacing drugs and reduce drug waste caused by premature replacement.

[0028] Step S5: Obtain the chemical circulation process parameters and corresponding cleaning performance test results for each cleaning chamber during actual operation of the wafer cleaning equipment. Using a data mining algorithm, extract the inherent correlation between chemical quality, circulation parameters, and cleaning performance in each chamber from historical big data. This creates a knowledge base for optimizing chemical circulation control strategies for each chamber, guiding the dynamic optimization of each chamber's intelligent control algorithm.

[0029] Step S5 includes: obtaining the liquid circulation parameters and corresponding cleaning effect detection results of each cleaning chamber during the operation of the wafer cleaning equipment, wherein the liquid circulation parameters include liquid concentration, temperature, flow rate and circulation time, and the cleaning effect detection results include the number of residual particles and organic matter residues on the wafer surface; preprocessing the liquid circulation parameters and cleaning effect detection results to obtain a historical data set suitable for data mining, wherein the preprocessing includes eliminating abnormal data, filling missing values ​​and standardizing the data; using an association rule mining algorithm to mine the inherent association rules between the liquid quality parameters, circulation parameters and cleaning effects of each chamber from the historical data set to obtain an association rule set, wherein the association rules in the association rule set are in the form of "if the liquid concentration is within the range A, the temperature is within the range B, and the circulation time is C, then the wafer The number of residual particles on the surface is less than D"; the association rule set is evaluated, and rules with confidence and support below preset thresholds are eliminated to obtain an optimized association rule set; the optimized association rule set is stored in a knowledge base to form an optimized control strategy for liquid circulation parameters of each chamber; during the operation of the wafer cleaning equipment, the intelligent control algorithm of each cleaning chamber obtains the current liquid circulation parameters and queries the optimized control strategy in the knowledge base; if a matching optimized control strategy is found, the intelligent control algorithm dynamically adjusts the liquid circulation parameters according to the strategy; if no matching optimized control strategy is found, the intelligent control algorithm maintains the current liquid circulation parameters unchanged and adds the current parameters and cleaning results to the historical data set for use in a subsequent data mining process to continuously optimize the control strategy of the knowledge base.

[0030] Specifically, during the operation of the wafer cleaning equipment, the chemical circulation parameters of each cleaning chamber are obtained in real time, such as the chemical concentration within the range of 20-30%, the temperature within the range of 50-60°C, the flow rate of 2-3L / min, the cycle time of 10-15min, etc. At the same time, the corresponding cleaning effect test results are obtained, such as the number of residual particles on the wafer surface is less than 10 / cm 2 , organic matter residue is less than 5ng / cm 2 The acquired historical data was preprocessed, abnormal data was eliminated using the 3σ criterion, missing values ​​were filled using the nearest neighbor interpolation method, and the data were normalized using the Z-score standardization method to form a data set suitable for the April association rule mining algorithm. By setting the minimum support to 10% and the minimum confidence to 80%, a pattern such as "If the concentration of the drug solution is within the range of 25-28%, the temperature is within the range of 55-58°C, and the cycle time is 12-13 minutes, the number of residual particles on the wafer surface is less than 5 / cm 2The high-quality association rules are stored in the knowledge base to form an optimized control strategy. The intelligent control algorithm obtains the current parameters of 27% solution concentration, 56°C temperature, and 11 minutes in real time, searches the knowledge base and matches the above-mentioned optimized control strategy. It dynamically adjusts the cycle time to 15 minutes to further reduce the number of residual particles on the wafer surface. For the current parameters of 31% solution concentration, 62°C temperature, and 16 minutes, there is no matching optimized control strategy in the knowledge base. The control algorithm maintains the current parameters unchanged and adds the parameters and the corresponding cleaning effect test results to the historical data set. In the subsequent data mining iteration process, the control strategy of the knowledge base is continuously optimized and enriched.

[0031] In step S6, based on the cleaning process requirements of different wafer products, the threshold range of the chemical liquid quality parameters of each cleaning chamber is pre-established. When the wafer cleaning equipment switches the product model, the chemical liquid quality control threshold corresponding to each chamber is automatically matched according to the product model, so as to realize the dynamic adjustment of the chemical liquid circulation mode and parameters of each chamber.

[0032] Step S6 includes: obtaining the product model information of the wafer to be processed by the equipment, and obtaining the cleaning process information corresponding to the current product model according to the pre-established product model and cleaning process database; extracting the standard value of the quality parameter of each cleaning chamber liquid corresponding to the current product model from the cleaning process information, and determining the threshold interval of the quality parameter of each cleaning chamber liquid in combination with the preset quality parameter floating range; through real-time monitoring of the current value of the quality parameter of each cleaning chamber liquid, judging whether the current value of the liquid quality parameter is within the threshold interval, and if it exceeds the corresponding threshold interval, generating a liquid quality parameter adjustment signal; obtaining the corresponding cleaning chamber liquid circulation mode adjustment instruction according to the liquid quality parameter adjustment signal, and executing the liquid circulation mode adjustment instruction. The control unit generates an adjustment instruction to obtain a new state of the medicine liquid circulation mode of the corresponding cleaning cavity; based on the new state of the medicine liquid circulation mode, obtains the target value of the medicine liquid circulation parameter of the corresponding cleaning cavity, and obtains the adjustment value of the medicine liquid circulation parameter by adjusting the operating state of the medicine liquid circulation system component; determines whether the deviation between the adjustment value of the medicine liquid circulation parameter and the target value of the medicine liquid circulation parameter is within a preset range; if the deviation exceeds the preset range, generates a medicine liquid circulation parameter fine-tuning instruction, and fine-tunes the operating state of the medicine liquid circulation system component according to the fine-tuning instruction; determines whether the medicine liquid quality parameter meets the preset quality standard by collecting the medicine liquid quality parameter sensor data; if not, returns to the step of real-time monitoring of the current value of the medicine liquid quality parameter of each cleaning cavity, and executes the cycle until the medicine liquid quality parameter meets the standard.

[0033] Specifically, assuming that the wafer product model to be processed by the current equipment is A123, the system has pre-established a product model and cleaning process database, which can be accessed through a query interface. The system queries the database, inputs A123, and the database returns the corresponding cleaning process information, such as information that cleaning chamber 1 needs to use a 5% hydrofluoric acid solution, cleaning chamber 2 needs to use a 10% ammonia solution, and cleaning chamber 3 needs to use pure water. The standard values ​​of the quality parameters of each cleaning chamber liquid corresponding to the A123 model are extracted from the cleaning process information. For example, the standard value of the hydrofluoric acid concentration of cleaning chamber 1 is set to 5%, and the standard value of the ammonia solution concentration of cleaning chamber 2 is set to 10%. Combined with the preset quality parameter floating range of ±2%, the hydrofluoric acid concentration threshold range of cleaning chamber 1 is 8% to 2%, and the ammonia solution concentration threshold range of cleaning chamber 2 is 8% to 12%. Assume that at a certain moment, the system, through real-time sensor monitoring, detects that the current hydrofluoric acid concentration in cleaning chamber 1 is 7%, and the current ammonia solution concentration in cleaning chamber 2 is 11%. Because 7% is lower than 8%, the hydrofluoric acid concentration in cleaning chamber 1 is below the threshold range, and the system generates a liquid medicine quality parameter adjustment signal. Based on the liquid medicine quality parameter adjustment signal, the system queries a preset adjustment rule database. For example, if the hydrofluoric acid concentration is below the lower threshold, it corresponds to the increased concentration mode. The system then obtains an instruction for cleaning chamber 1 to execute the increased concentration mode. Upon executing this instruction, cleaning chamber 1 enters the increased concentration mode. After cleaning chamber 1 enters the increased concentration mode, the system queries the preset liquid medicine circulation parameter database and determines that, for example, the opening of the hydrofluoric acid supply valve needs to be increased by 20% and the speed of the circulation pump needs to be increased by 100 rpm. These values ​​are used as the target values ​​for the liquid medicine circulation parameters. The control system adjusts the hydrofluoric acid supply valve and the circulation pump, actually increasing the valve opening by 19% and the circulation pump speed by 95 rpm, thus obtaining the liquid medicine circulation parameter adjustment values. The calculated deviations are |20%-19%| = 1% for valve opening and |100-95%| = 5 rpm for circulating pump speed. Assuming the preset deviation ranges are no more than 2% for valve opening and 10 rpm for circulating pump speed, the deviations are both within the preset ranges and no fine-tuning is required. At this point, the system collects liquid concentration data through sensors. Assuming the collected hydrofluoric acid concentration is 9%, still below the standard value of 5%, the system returns to the previous step and continues the cycle. At some point, the collected hydrofluoric acid concentration reaches 0.5%, meeting the preset quality standard. The current cycle ends and the cleaning process for the next product model begins.

[0034] Step S7: Real-time operational status data for the wafer cleaning equipment is acquired, specifically including the wafer cleaning progress and chemical circulation parameters for each cleaning chamber. The central controller monitors the operational status of each chamber in real time. Once a wafer in a chamber is cleaned, the system immediately switches to the next pre-configured, idle chamber. Based on the process requirements of the wafers being cleaned, the system retrieves the corresponding chemical circulation control strategy from the knowledge base and presets the chemical circulation parameters for the new chamber, enabling continuous multi-chamber cleaning of different wafer products.

[0035] Step S7 includes: obtaining real-time operating status data of each cavity of the wafer cleaning equipment, the real-time operating status data including wafer cleaning progress and liquid medicine circulation parameters; transmitting the real-time operating status data to the central controller; the central controller determines whether the wafer cleaning of each cavity is completed based on the received real-time operating status data; if a cavity is cleaned, an idle cavity is selected from the pre-configured idle cavity list as the next target cavity to be switched; obtaining process requirement information of the wafer to be cleaned; retrieving a matching liquid medicine circulation control strategy from a pre-built knowledge base according to the process requirement information; if a matching liquid medicine circulation control strategy is found, the liquid medicine circulation parameters in the strategy are used as preset parameters; if no matching liquid medicine circulation control strategy is found, a new set of liquid medicine circulation parameters are generated as preset parameters according to the process requirement information; The liquid medicine circulation parameters of the target cavity are set to the preset parameters, and the liquid medicine circulation system of the cavity is started to pre-treat the internal environment of the target cavity; after the pre-treatment of the target cavity is completed, the conveying system of the wafer cleaning equipment is switched to the target cavity, the wafer to be cleaned is transferred to the target cavity, and the cleaning process is started; the central controller collects the operating status data of the target cavity in real time, and the operating status data includes cleaning progress, liquid medicine temperature, liquid medicine flow rate and liquid medicine concentration; the collected operating status data is compared with the preset parameters; if the operating status data deviates from the preset parameters beyond the allowable range, an alarm is triggered, and the liquid medicine circulation parameters of the target cavity are adjusted according to the degree of deviation; when the wafer cleaning of the target cavity is completed, the cleaned wafer is transferred out of the cavity, and the cavity is marked as idle.

[0036] Specifically, the central controller acquires the cleaning progress and chemical circulation parameters of each chamber, such as temperature, flow rate, and concentration, every second and transmits them via the TCP / IP protocol. When the cleaning progress of a chamber reaches 100%, the controller selects the chamber with the longest idle time from a list of five idle chambers as the target chamber. Based on process requirements such as wafer material and contaminant type, the controller searches a knowledge base containing 100 strategies. If no exact match is found, a decision tree algorithm is used to generate chemical parameters such as temperature, flow rate, concentration, and time. The controller then sends these parameters to the target chamber and activates the chemical circulation system to pre-condition the chamber for two minutes, controlling the temperature at 50±1°C and the flow rate at 10±5 m / s. After pre-conditioning is complete, the conveyor system transfers the wafers into the chamber while simultaneously monitoring the existing chamber. During the cleaning process, if the actual parameters deviate from the preset values ​​by more than 5%, an alarm is triggered and real-time adjustments are made using the PID algorithm. After cleaning is complete, the wafers are removed and the chamber status is updated to idle. If there are more wafers to be cleaned, the above steps are repeated; otherwise, the cleaning process ends.

[0037] In step S8, the liquid circulation process of multiple cleaning chambers is monitored and dynamically adjusted in real time based on the optimized intelligent control algorithm and chamber knowledge base. When the liquid quality parameters of a particular chamber deviate from the preset threshold, the optimized control algorithm for that chamber is triggered, and the new liquid circulation pump flow rate and filtration device parameters are calculated. These adjustments are then executed through the control unit of that chamber. Simultaneously, a comprehensive analysis of the liquid usage time and cleaning efficiency of each chamber is performed, dynamically optimizing the scheduling strategy for multi-chamber collaborative cleaning to improve the overall efficiency of wafer cleaning and liquid utilization.

[0038] Step S8 includes: acquiring real-time liquid circulation data of multiple cleaning chambers, the real-time liquid circulation data including liquid quality parameters, circulation pump flow, and filter device parameters; transmitting the real-time liquid circulation data to an intelligent control system; the intelligent control system determining whether the liquid quality parameters of each chamber deviate from a preset threshold value based on a preset sub-chamber knowledge base; if the liquid quality parameters deviate from the preset threshold value, triggering an optimization control algorithm for the corresponding chamber; the optimization control algorithm calculating an optimized liquid circulation pump flow rate and filter device parameters using a machine learning method based on the degree of deviation of the liquid quality parameters and historical data; transmitting the optimized liquid circulation pump flow rate and filter device parameters to a control unit of the corresponding chamber; after receiving the optimized liquid circulation pump flow rate and filter device parameters, the control unit dynamically adjusts the liquid circulation pump flow rate and the operating parameters of the filter device, and the intelligent control system dynamically generates an optimal scheduling strategy for multi-chamber collaborative cleaning; the optimal scheduling strategy includes reasonably allocating cleaning tasks and liquid usage time for each chamber to improve the overall efficiency of wafer cleaning and liquid utilization.

[0039] Specifically, the intelligent control system acquires real-time liquid circulation data from multiple cleaning chambers every 5 seconds. This data includes quality parameters such as liquid pH, conductivity, and temperature, as well as parameters such as the circulation pump flow rate and the pressure differential and flow rate of the filter. After transmitting this data to the intelligent control system, the system compares it with the standard thresholds for each parameter in a pre-set knowledge base for each chamber. For example, if the standard pH range is 0-0, an actual pH value of 5 is considered a deviation. In the event of a pH deviation, the system triggers the optimization control algorithm for that chamber. Based on the deviation level of 5 and the correlation between pH, liquid pump flow rate, and filter parameters in historical data, the system uses a support vector machine algorithm to calculate the optimal parameter combination that can restore the pH value to 8 within 5 minutes: adjusting the liquid pump flow rate from 2 L / min to 5 L / min and shortening the filter backwash cycle from 60 seconds to 45 seconds. The optimized parameters are then transmitted to the control unit of the corresponding chamber. Upon receiving the optimized parameters, the control unit immediately adjusts the liquid pump flow rate to 5 L / min and the filter backwash cycle to 45 seconds. At the same time, the intelligent control system continuously monitors the duration of the liquid medicine usage and cleaning efficiency data for the cavity. Through data mining algorithm analysis, it was found that after the liquid medicine usage exceeds 2 hours, the cleaning efficiency begins to decline, and the rate of decline is 10% / hour. Based on the analysis results, the intelligent control system dynamically generates a collaborative cleaning scheduling strategy, shortening the cleaning task of the cavity by 5 hours, controlling the liquid medicine usage time to within 5 hours, and simultaneously scheduling adjacent idle cavities to share the remaining cleaning tasks. Analysis shows that the overall cleaning time can be reduced by 5%, and the liquid medicine usage can be saved by 10%. After the scheduling strategy is issued to each cavity control unit, the operating hours and liquid medicine usage of multiple cavities are coordinated to maximize cleaning efficiency and liquid medicine utilization while ensuring the cleaning effect.

[0040] The above is only a preferred embodiment of the present invention. It should be pointed out that ordinary technicians in this technical field can make several improvements and supplements without departing from the principles of the present invention. These improvements and supplements should also be regarded as the scope of protection of the present invention.

Claims

1. A multi-chamber liquid intelligent circulation control method for wafer cleaning equipment, characterized in that: The method comprises the following steps: Step S1: Acquire real-time data on the circulation of the medicinal solution in multiple cleaning chambers, specifically including parameters of the concentration, temperature, and pH of the medicinal solution in each chamber, using concentration sensors, temperature sensors, and pH sensors installed at key locations in the circulation pipeline of each chamber to collect the data, and record the usage time of the medicinal solution in each chamber; The step S1 comprises: Acquire real-time data collected from concentration sensors, temperature sensors, and pH sensors installed at key locations in the circulation pipelines of each cleaning chamber; Based on the data collected by the concentration sensor, it is determined whether the real-time concentration of the liquid medicine in each cleaning chamber meets the preset range. If the concentration is lower than the preset range, the dosing device is controlled to add liquid medicine into the cleaning chamber until the concentration reaches the preset range. Based on the data collected by the temperature sensor, it is determined whether the real-time temperature of the liquid medicine in each cleaning cavity meets the preset range. If the temperature is lower than the preset range, the heating device is controlled to heat the liquid medicine in the cleaning cavity until the temperature reaches the preset range. Based on the data collected by the pH sensor, it is determined whether the real-time pH value of the liquid in each cleaning chamber meets the preset range. If it exceeds the preset range, the acid or alkali adding device is controlled to add acid or alkali solution into the cleaning chamber until the pH value reaches the preset range. Summarizing the real-time concentration, real-time temperature, and real-time pH data of the liquid medicine in each cleaning cavity to obtain comprehensive quality parameters of the liquid medicine in each cleaning cavity; Record the start and end time of use of each cleaning cavity liquid, and calculate the use time of each cleaning cavity liquid; Performing correlation analysis on the comprehensive quality parameters and the usage time of each cleaning cavity liquid, and establishing a liquid quality prediction model using a support vector machine algorithm; Predicting the optimal replacement time of the liquid medicine in each cleaning cavity according to the liquid medicine quality prediction model; Step S2: Input the acquired real-time data of the chemical liquid quality parameters of each cavity into the intelligent control algorithm model. The algorithm model determines whether the current chemical liquid quality of each cavity meets the preset wafer cleaning process requirements. If so, continue to acquire real-time data. If not, calculate the optimized chemical liquid circulation pump flow rate and filter device working state parameters of the cavity based on the deviation degree between the chemical liquid quality parameters and the preset process requirements through the intelligent control algorithm. Step S3: Send the calculated optimization parameters to the control unit of the corresponding cleaning chamber, adjust the actual working flow of the circulation pump of the chamber and the actual working state of the filter device, and dynamically optimize the liquid recycling process of the chamber to restore the liquid quality to within the process requirements; Step S4: Obtain the operating parameters of each cleaning chamber and the corresponding chemical solution usage time data during the actual operation of the wafer cleaning equipment, establish a correlation model between the chemical solution usage time of each chamber and the chemical solution quality attenuation through a machine learning algorithm, dynamically predict the optimal chemical solution replacement cycle for each chamber, guide the regular replacement of the chemical solution, and reduce chemical solution waste; Step S5: Obtain the liquid circulation process parameters of each cleaning chamber and the corresponding cleaning effect test results during the actual operation of the wafer cleaning equipment. Use a data mining algorithm to extract the inherent correlation between the liquid quality, circulation parameters and cleaning effect of each chamber from historical big data, form a knowledge base for optimizing the liquid circulation control strategy by chamber, and guide the dynamic optimization of the intelligent control algorithm of each chamber. The step S5 comprises: Obtaining the chemical liquid circulation parameters and corresponding cleaning effect test results of each cleaning chamber during the operation of the wafer cleaning equipment, wherein the chemical liquid circulation parameters include chemical liquid concentration, temperature, flow rate and circulation time, and the cleaning effect test results include the number of residual particles and organic matter residues on the wafer surface; Preprocessing the liquid circulation parameters and cleaning effect test results to obtain a historical data set suitable for data mining, wherein the preprocessing includes removing abnormal data, filling missing values, and standardizing the data; An association rule mining algorithm is used to mine the inherent association rules between the quality parameters and circulation parameters of each cavity liquid and the cleaning effect from the historical data set to obtain an association rule set; Evaluating the association rule set, eliminating rules whose confidence and support are lower than preset thresholds, and obtaining an optimized association rule set; Storing the optimized association rule set in a knowledge base to form an optimized control strategy for the liquid circulation parameters of the sub-cavities; During the operation of the wafer cleaning equipment, the intelligent control algorithm of each cleaning chamber obtains the current liquid circulation parameters and queries the optimization control strategy in the knowledge base; If a matching optimization control strategy is found, the intelligent control algorithm dynamically adjusts the liquid medicine circulation parameters according to the strategy; If no matching optimized control strategy is found, the intelligent control algorithm maintains the current liquid circulation parameters unchanged and adds the current parameters and cleaning results to the historical data set for subsequent data mining to continuously optimize the control strategy of the knowledge base; Step S6: Pre-establish a threshold range for the chemical liquid quality parameters of each cleaning chamber based on the cleaning process requirements of different wafer products. When the wafer cleaning equipment switches product models, the chemical liquid quality control threshold corresponding to each chamber is automatically matched according to the product model, thereby achieving dynamic adjustment of the chemical liquid circulation mode and parameters of each chamber; Described step S6 comprises: Obtain the product model information of the wafer to be processed by the equipment, and obtain the cleaning process information corresponding to the current product model based on the pre-established product model and cleaning process database; Extracting the standard value of each cleaning chamber liquid quality parameter corresponding to the current product model from the cleaning process information, and determining the threshold range of each cleaning chamber liquid quality parameter in combination with the preset quality parameter floating range; By real-time monitoring of the current value of the quality parameter of the liquid medicine of each cleaning cavity, it is determined whether the current value of the liquid medicine quality parameter is within the threshold range, and if it exceeds the corresponding threshold range, a liquid medicine quality parameter adjustment signal is generated; According to the liquid medicine quality parameter adjustment signal, a corresponding cleaning cavity liquid medicine circulation mode adjustment instruction is obtained, and a new state of the cleaning cavity liquid medicine circulation mode is obtained by executing the liquid medicine circulation mode adjustment instruction; Based on the new state of the liquid medicine circulation mode, a target value of a liquid medicine circulation parameter corresponding to the cleaning chamber is obtained, and an adjusted value of the liquid medicine circulation parameter is obtained by adjusting the operating state of the liquid medicine circulation system components; determining whether a deviation between the adjusted value of the liquid medicine circulation parameter and the target value of the liquid medicine circulation parameter is within a preset range; if the deviation exceeds the preset range, generating a liquid medicine circulation parameter fine-tuning instruction, and fine-tuning the operating state of the liquid medicine circulation system components according to the fine-tuning instruction; By collecting the liquid medicine quality parameter sensor data, it is determined whether the liquid medicine quality parameter meets the preset quality standard. If not, the process returns to the step of real-time monitoring the current value of the liquid medicine quality parameter of each cleaning chamber, and the process is repeated until the liquid medicine quality parameter meets the standard. Step S7: Acquire real-time operating status data of the wafer cleaning equipment, specifically including the wafer cleaning progress and liquid circulation parameters of each cleaning chamber. The operating status of each chamber is monitored in real time by the central controller. When the wafer cleaning of a chamber is completed, it immediately switches to the next pre-configured idle chamber. Based on the process requirements of the wafer to be cleaned, the corresponding liquid circulation control strategy is retrieved from the knowledge base, and the liquid circulation parameters of the new chamber are preset to achieve continuous multi-chamber cleaning of different wafer products. Step S8: Based on the optimized intelligent control algorithm and the sub-chamber knowledge base, the liquid circulation process of multiple cleaning chambers is monitored and dynamically adjusted in real time. When the liquid quality parameters of a certain chamber deviate from the preset threshold, the optimization control algorithm of the chamber is triggered, and the new liquid circulation pump flow and filter device parameters are calculated. The adjustment is performed through the control unit of the chamber. At the same time, the liquid usage time and cleaning efficiency of each chamber are comprehensively analyzed, and the scheduling strategy of multi-chamber collaborative cleaning is dynamically optimized to improve the overall efficiency of wafer cleaning and liquid utilization.

2. The method for intelligent circulation control of multi-chamber chemical liquid in wafer cleaning equipment according to claim 1, characterized in that: Described step S2 comprises: Acquire real-time data on the quality parameters of the drug solution in each cavity, including pH value, temperature and concentration; Using the liquid medicine quality parameters as input to an intelligent control algorithm model; Obtain pre-established wafer cleaning process quality requirements; Determining whether the quality parameters of the chemical solution meet the quality requirements of the wafer cleaning process; If the quality parameters of the chemical solution meet the quality requirements of the wafer cleaning process, returning to continue to obtain real-time data of the quality parameters of the chemical solution; If the quality parameters of the chemical solution do not meet the quality requirements of the wafer cleaning process, determining the degree of deviation between the quality parameters of the chemical solution and the quality requirements of the wafer cleaning process, and determining a target value for optimization adjustment; A machine learning algorithm is used to establish a mapping relationship model between the quality parameters of the liquid medicine and the flow rate of the liquid medicine circulation pump and the working state parameters of the filter device; Inputting the degree of deviation of the liquid medicine quality parameter into the mapping relationship model to obtain optimized liquid medicine circulation pump flow rate and filter device working state parameters; According to the optimized flow rate of the liquid medicine circulation pump, controlling the liquid medicine circulation pump to adjust the flow rate; Adjusting the backwash frequency and backwash time of the filter device according to the optimized working state parameters of the filter device; After executing the optimization control, the system returns to continue acquiring the real-time data of the quality parameters of the liquid medicine, and performs cyclic judgment and optimization control.

3. A multi-chamber liquid intelligent circulation control method for wafer cleaning equipment according to any one of claims 1-2, characterized in that: Described step S7 comprises: Acquire real-time operating status data of each chamber of the wafer cleaning equipment, wherein the real-time operating status data includes wafer cleaning progress and liquid circulation parameters; Transmitting the real-time operating status data to a central controller; The central controller determines whether the wafer cleaning of each cavity is completed based on the received real-time operation status data; If a cavity is cleaned, an idle cavity is selected from the pre-configured idle cavity list as the next target cavity to be switched; Obtain process requirement information for wafers to be cleaned; Retrieving a matching liquid medicine circulation control strategy from a pre-built knowledge base according to the process requirement information; If a matching liquid medicine circulation control strategy is found, the liquid medicine circulation parameters in the strategy are used as preset parameters; If no matching liquid medicine circulation control strategy is found, a new set of liquid medicine circulation parameters is generated as preset parameters according to the process requirement information; Setting the liquid medicine circulation parameters of the target cavity to the preset parameters, and starting the liquid medicine circulation system of the cavity to pre-treat the internal environment of the target cavity; After the pretreatment of the target chamber is completed, the conveying system of the wafer cleaning equipment is switched to the target chamber, the wafer to be cleaned is transferred into the target chamber, and the cleaning process is started; The central controller collects the operating status data of the target cavity in real time, wherein the operating status data includes cleaning progress, liquid medicine temperature, liquid medicine flow rate and liquid medicine concentration; Comparing the collected operating status data with the preset parameters; If the operating status data deviates from the preset parameters beyond the allowable range, an alarm is triggered, and the liquid circulation parameters of the target cavity are adjusted according to the degree of deviation; When the wafers in the target cavity are cleaned, the cleaned wafers are transferred out of the cavity, and the cavity is marked as idle.

4. A multi-chamber liquid intelligent circulation control method for wafer cleaning equipment according to any one of claims 1-2, characterized in that: Described step S8 comprises: Acquiring real-time liquid circulation data of multiple cleaning chambers, wherein the real-time liquid circulation data includes liquid quality parameters, circulation pump flow rate, and filter device parameters; Transmitting the real-time drug liquid circulation data to an intelligent control system; The intelligent control system determines whether the quality parameter of the liquid medicine in each cavity deviates from a preset threshold value based on a preset cavity knowledge base; If the liquid medicine quality parameter deviates from the preset threshold, the optimization control algorithm of the corresponding cavity is triggered; The optimization control algorithm calculates the optimized liquid medicine circulation pump flow rate and filter device parameters using a machine learning method based on the deviation degree of the liquid medicine quality parameters and historical data; Transmitting the optimized liquid medicine circulation pump flow rate and filter device parameters to the control unit of the corresponding cavity; After receiving the optimized flow rate of the liquid medicine circulation pump and the filter device parameters, the control unit dynamically adjusts the flow rate of the liquid medicine circulation pump and the working parameters of the filter device, and the intelligent control system dynamically generates an optimal scheduling strategy for multi-cavity collaborative cleaning; The optimal scheduling strategy includes reasonably allocating the cleaning tasks and chemical solution usage time of each cavity, thereby improving the overall efficiency of wafer cleaning and chemical solution utilization.