Method for cleaning organic glue residue on carrier surface

Abstract

The present application provides a method for cleaning organic glue residues on the surface of a carrier board, which includes the following steps: using an online monitoring device for the surface cleanliness of the carrier board to collect surface cleanliness data during the cleaning process in real time, analyzing the cleanliness change trend in real time through an algorithm, dynamically adjusting the soaking, shaking and rinsing treatment parameters and circulation path, adaptively optimizing the cleaning scheme, and predicting the cleaning endpoint; deploying a colloidal particle agglomeration degree analyzer in the water tank to monitor the agglomeration state data of the colloidal particles in real time, analyzing the correlation between the agglomeration state and water quality parameters through an algorithm model, dynamically adjusting the pH value and ionic strength of ultrapure water, optimizing the water quality environment, and inhibiting the redeposition of colloidal particles.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a method for cleaning organic glue residues on a carrier surface. Background Art

[0002] The existing MicroLED display panel transfer solution involves applying a layer of anisotropic conductive adhesive (ACF) material (containing Au conductive particles) to the entire surface of the substrate, then transferring the LEDs in bulk to the surface of the ACF. Finally, a sheet of quartz glass is pressed against the ACF to break the Au particles, establishing electrical continuity between the LED electrodes and the substrate's CuPad. In this process, the carrier used to transfer the LEDs in bulk to the ACF is also called a temporary carrier. The problem of organic adhesive residue remaining during repeated use after cleaning of the temporary carrier is a significant issue that needs to be addressed.

[0003] The carrier cleaning process within the cleanroom presents multiple interconnected technical challenges, forming a complex system. First, the optimization of stripping solution immersion and ultrasonic oscillation parameters requires consideration of the carrier material characteristics and residue levels, requiring algorithmic model training to determine the optimal solution. Second, the control of the tank overflow and spray system is closely linked to the carrier layout, requiring iterative algorithm optimization to achieve optimal cleaning results. Furthermore, surface tension gradient analysis and the application of the Marangoni effect directly impact residue removal efficiency and require synergy with the water flow layout. Furthermore, the real-time cleanliness monitoring system dynamically adjusts parameters at each step through algorithmic analysis, interoperating with the cleanroom control system. Furthermore, the analysis of the degree of colloidal agglomeration and the optimization of water quality parameters influence each other, requiring algorithmic fusion analysis for mutually reinforcing optimization. Finally, the assessment of particle removal capability and the analysis of residual stress on the carrier surface mutually constrain each other, requiring an algorithmic approach to find the optimal balance. These issues constitute a network of interconnected technical challenges that require comprehensive consideration and solution through algorithmic optimization. Summary of the Invention

[0004] The purpose of the present invention is to solve the above defects and provide a method for cleaning organic glue residues on the carrier surface, which realizes efficient cleaning of organic glue residues on the carrier surface, effectively controls the environmental cleanliness during the cleaning process, prevents the redeposition of glue particles, and improves the cleaning quality and efficiency.

[0005] The object of the present invention is achieved in the following ways:

[0006] A method for cleaning organic adhesive residue on a carrier surface comprises the following steps:

[0007] Obtain data on the residual organic adhesive on the substrate surface and the material's dimensional characteristics. Through algorithm model selection and parameter setting, determine the stripping solution immersion sequence and duration combination, and obtain a multi-step immersion treatment plan. The immersion process is carried out in a dust-free area that meets the cleanliness level requirements, using air filtration devices and anti-static measures to ensure environmental cleanliness.

[0008] Based on the size and material property data of the carrier, the ultrasonic oscillation frequency and duration parameters are obtained through algorithm model training and evaluation. The carriers are staggered in the horizontal direction and rotated in the vertical direction to form an oscillating arrangement. The oscillation process strictly controls the temperature and humidity conditions in the dust-free area.

[0009] Based on the carrier surface area and residual glue data, an algorithm model is iteratively optimized to obtain a combination of ultrapure water overflow and spray parameters, including flow rate, pressure, and angle. The carrier is placed in a water tank at an angle and vertically spaced in multiple layers to form a water flow arrangement. The rinsing process is evaluated in real time through dust particle monitoring and surface cleanliness verification.

[0010] An online monitoring device for the surface cleanliness of the substrate is used to collect surface cleanliness data during the cleaning process in real time. An algorithm is used to analyze the cleanliness change trend in real time, dynamically adjust the soaking, shaking and rinsing treatment parameters and circulation paths, adaptively optimize the cleaning plan, and predict the cleaning endpoint.

[0011] A colloidal particle agglomeration degree analyzer is deployed in the water tank to monitor the agglomeration state data of the colloidal particles in real time, analyze the correlation between the agglomeration state and water quality parameters through an algorithm model, dynamically adjust the pH value and ionic strength of the ultrapure water, optimize the water quality environment, and inhibit the redeposition of colloidal particles;

[0012] A particle removal capacity evaluation device is used to evaluate the removal efficiency of each particle size segment for particles of different sizes. The relationship between the removal efficiency, filtration accuracy and water flow rate is analyzed through an algorithm, the technical parameters of the filtration device are dynamically adjusted, and the horizontal arrangement spacing and staggered arrangement are optimized to form a particle removal process that is suitable for the degree of agglomeration of the colloid particles.

[0013] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0014] The present invention discloses a method for cleaning organic glue residues on the surface of a carrier board. In order to solve the problems of cleanliness control and re-deposition of glue particles during the cleaning process of organic glue residues on the surface of the carrier board, an algorithm model is used to determine a multi-step treatment scheme including soaking, shaking and rinsing by obtaining the data of the organic glue residue amount and material size characteristics on the surface of the carrier board. In a dust-free area, the surface cleanliness data and the state of agglomeration of glue particles during the cleaning process are monitored in real time, and the treatment parameters and water quality environment are adjusted dynamically. The removal efficiency of particles of different sizes is evaluated by a particle removal capacity evaluation device, and the parameters of the filter device and the arrangement of the carrier board are optimized. The present invention realizes the efficient cleaning of organic glue residues on the surface of the carrier board, effectively controls the environmental cleanliness during the cleaning process, prevents the re-deposition of glue particles, and improves the cleaning quality and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The figure is a flow chart of the method for cleaning organic glue residue on the surface of a carrier board according to the present invention.

[0016] Figure 2 Schematic diagram of the method for cleaning organic glue residue on the surface of a carrier board according to the present invention.

[0017] Figure 3 FIG. 4 is another schematic diagram of the method for cleaning organic adhesive residue on the surface of a carrier board according to the present invention. DETAILED DESCRIPTION

[0018] The following will describe the technical solutions in the embodiments of the present invention in detail with reference to the accompanying drawings. The described embodiments are only a part of the embodiments of the present invention.

[0019] like Figure 1-3 The method for cleaning organic glue residue on the carrier surface of this embodiment may specifically include:

[0020] S101. Obtain data on the residual amount of organic glue and material dimensional characteristics on the carrier surface, determine the stripping solution immersion sequence and duration combination through algorithm model selection and parameter setting, and obtain a multi-step immersion treatment plan. The immersion process is carried out in a dust-free area that meets the cleanliness level requirements, and an air filter device and anti-static measures are used to ensure environmental cleanliness.

[0021] S101 specifically also includes the following steps: Step 1, obtaining the data on the amount of organic glue residue on the surface of the carrier board and the material size characteristic data as the input of the algorithm model. Step 2, based on the material size characteristics of the carrier board surface, using the decision tree algorithm model, through parameter setting, determine the optimal stripping liquid immersion sequence and duration combination. Step 3, soaking the carrier board in different stripping liquids in a dust-free area that meets the cleanliness requirements according to the determined immersion sequence and duration. Step 3, during the immersion process, using an air filter device to continuously filter the air in the dust-free area to remove particles and dust in the air. Step 5, during the immersion process, adopt anti-static measures, including the use of anti-static floors, anti-static clothing, anti-static gloves, etc., to prevent static electricity from damaging the carrier board surface. Step 6, after the immersion is completed, obtain the data on the amount of organic glue residue on the surface of the carrier board, and determine whether the residue is lower than the preset threshold. If so, the immersion process is completed. If not, return to step 2, adjust the immersion sequence and duration, and continue the immersion process. In step 7, the data of multiple batches of substrate immersion treatment are input into the algorithm model for training. Through parameter optimization, the accuracy of the model in predicting the immersion sequence and duration combination is continuously improved, thus realizing the intelligentization of the substrate immersion treatment process.

[0022] Specifically, data on the amount of organic glue residue on the surface of the carrier board and material size characteristic data are obtained; based on the material size characteristic data, a decision tree algorithm model is used to determine the optimal stripping liquid immersion sequence and duration combination through parameter setting; the carrier board is immersed in different stripping liquids in a dust-free area that meets the cleanliness requirements according to the immersion sequence and duration; wherein, during the immersion process, an air filter device is used to continuously filter the air in the dust-free area to remove particles and dust in the air; at the same time, anti-static measures are adopted, including the use of anti-static floors, anti-static clothing, and anti-static gloves, to prevent static electricity from damaging the carrier board surface; after the immersion is completed, data on the amount of organic glue residue on the surface of the carrier board is obtained, and it is determined whether the residue is lower than a preset threshold; if so, the immersion process is completed; if not, the process returns to the step of determining the immersion sequence and duration combination, adjusts the immersion sequence and duration, and continues the immersion process; multiple batches of carrier board immersion process data are input into the decision tree algorithm model for training, and the accuracy of the model in predicting the immersion sequence and duration combination is continuously improved through parameter optimization.

[0023] First, the data on the amount of organic glue residue on the surface of the carrier board is obtained through high-precision surface residue detection instruments such as X-ray fluorescence spectrometers. At the same time, a three-dimensional scanner is used to obtain the material and size characteristic data of the carrier board, and these data are input into the intelligent optimization model based on the decision tree algorithm. The model automatically calculates the optimal stripping solution immersion sequence and duration combination by analyzing the characteristic parameters of the carrier board such as material, size, residue, etc., and using algorithms such as information gain ratio and Gini index, such as soaking in isopropyl alcohol for 10 minutes, then soaking in acetone for 5 minutes, and finally soaking in deionized water for 2 minutes. The carrier board is immersed in different stripping solutions in a Class 1000 dust-free workshop in turn according to the best solution determined by the model. At the same time, the workshop is equipped with a high-efficiency air filtration system to filter particles with a diameter of ≥5μm in the air to ensure that the number of suspended particles is ≤1000 / m 3 In addition, anti-static floor, gloves, work clothes, etc. are used to make the static potential of the workshop ≤100V to avoid static damage. After the soaking is completed, the residual amount is tested again. If the residual amount is ≤1μg / cm 2 If the sample is deemed qualified, the optimization model returns to adjust the soaking solution until it passes. Multiple batches of soaking data, such as the type of soaking solution, concentration, duration, temperature, and residual volume, are fed back to the algorithm model for deep learning. Model parameters are continuously adjusted through methods such as gradient descent to improve prediction accuracy, ultimately achieving full intelligent processing of the substrate soaking process.

[0024] S102. Based on the size and material property data of the carrier, the ultrasonic oscillation frequency and duration parameters are obtained through algorithm model training and evaluation. The carriers are staggered in the horizontal direction and rotated in the vertical direction to form an oscillation arrangement. The oscillation process strictly controls the temperature and humidity conditions in the dust-free area.

[0025] The carrier's dimensions and material properties are obtained as input parameters for the algorithm model. Using a machine learning algorithm, support vector machines or neural networks are used to train and evaluate the input parameters to determine the optimal ultrasonic oscillation frequency and duration parameters. Based on the carrier's dimensions, the horizontal staggered arrangement is determined, and computer vision algorithms are used to determine whether the arrangement is reasonable. Based on the material properties, the vertical rotation angle is determined, and the rotation effect is evaluated using a simulation algorithm. Horizontal staggering and vertical rotation are combined to form the optimal oscillation arrangement, which is continuously optimized through iterations using an optimization algorithm. Within the dust-free area, temperature and humidity sensors are used to collect environmental data in real time, and temperature and humidity parameters are adjusted using a PID control algorithm to ensure that oscillation requirements are met. By integrating parameters such as oscillation frequency, duration, arrangement, and environmental conditions, simulation and experimental verification are conducted to determine the final ultrasonic oscillation process parameters, which are used to guide actual production.

[0026] Specifically, the size and material property data of the carrier are obtained as input parameters of the algorithm model; the input parameters are trained and evaluated by a machine learning algorithm to obtain the optimal ultrasonic oscillation frequency and duration parameters; according to the size of the carrier, whether the staggered arrangement in the horizontal direction is reasonable is judged by a computer vision algorithm; according to the material properties, the effect of the rotation angle in the vertical direction is evaluated by a simulation algorithm; the horizontal staggered arrangement and the vertical rotation angle are combined to form an oscillation arrangement; the oscillation arrangement is iteratively optimized by an optimization algorithm to obtain the optimal oscillation arrangement; the environmental data in the dust-free area is obtained; according to the environmental data, the temperature and humidity parameters are adjusted by a PID control algorithm, and the adjusted temperature and humidity parameters are output; the ultrasonic oscillation frequency, duration, optimal oscillation arrangement and adjusted temperature and humidity parameters are comprehensively considered, and the final ultrasonic oscillation process parameters are obtained through simulation and experimental verification.

[0027] Dimensional data such as the length, width, and thickness of the carrier plates, as well as material characteristics such as density, hardness, and elastic modulus, were obtained and fed into a support vector machine (SVM) algorithm. Training on 100 historical data samples revealed the optimal hyperparameters for the model: an oscillation frequency range of 20-50kHz and a duration range of 10-30 seconds. Based on the length and width of the carrier plates, a computer vision edge detection algorithm determined that a staggered arrangement of two rows and three columns horizontally, with a spacing of 10mm between the carrier plates, was most effective. Based on the material's hardness and elastic modulus, finite element simulations determined that a 30° vertical rotation was optimal. Using a genetic optimization algorithm, 100 iterations of optimization were performed on the horizontal staggered arrangement and vertical rotation angles to determine the optimal oscillation arrangement. Within the cleanroom, temperature and humidity sensors collected real-time data, maintaining the temperature at 25±2°C and the humidity at 50%±5%. A PID control algorithm was used to adjust the air conditioning and humidifier's operating conditions in real time. Based on the above parameters, simulations were performed in simulation software and laboratory verification. Ultimately, the optimal ultrasonic vibration process parameters were determined to be: a frequency of 40kHz, a duration of 20 seconds, horizontal staggered carriers, 30° vertical rotation, a temperature of 25°C, and a humidity of 50%. Applying this process to mass production has achieved an organic adhesive removal rate of over 95% on carriers.

[0028] S103. Based on the surface area and residual glue amount data of the carrier plate, an algorithm model is iteratively optimized to obtain a combination of ultrapure water overflow and spray parameters, including flow rate, pressure, and angle. The carrier plate is placed in a water tank at an angle and vertically spaced in multiple layers to form a water flow arrangement. The rinsing process is evaluated in real time through dust particle monitoring and surface cleanliness verification.

[0029] The system obtains data on the carrier's surface area and residual adhesive content. Based on a pre-set algorithm model, iterative optimization is performed to determine the optimal combination of ultrapure water overflow and spray parameters, including flow rate, pressure, and angle. The carrier is positioned in a water tank using an inclined configuration and multiple vertically spaced layers. Based on the determined combination of ultrapure water overflow and spray parameters, an optimal water flow pattern is established. During the rinsing process, a dust particle monitoring device installed within the water tank acquires real-time dust particle concentration data. Simultaneously, a surface cleanliness detection device monitors the carrier's surface cleanliness in real time, generating surface cleanliness data. These dust particle concentration and surface cleanliness data are input into a pre-set cleaning performance evaluation model, which uses the model to perform real-time evaluation of the current cleaning performance. If the evaluation result does not meet the pre-set cleaning performance threshold, the ultrapure water overflow and spray parameter combination is adjusted to re-establish the water flow pattern, and rinsing continues until the evaluation result meets the threshold. If the evaluation result meets the pre-set cleaning performance threshold, rinsing is stopped, the carrier is removed from the water tank, and the carrier cleaning process is complete.

[0030] Specifically, the surface area and residual glue amount data of the carrier are obtained; based on the surface area and residual glue amount data of the carrier, a combination of ultrapure water overflow and spray parameters is determined through a preset iterative optimization algorithm model, and the ultrapure water overflow and spray parameter combination includes flow rate, pressure and angle; the carrier is placed in a water tank in an inclined manner and vertically spaced in multiple layers, and a water flow arrangement is formed according to the ultrapure water overflow and spray parameter combination; during the flushing process, the dust particle concentration data in the water tank is obtained in real time through a dust particle monitoring device set in the water tank; at the same time, a surface cleanliness detection device is used to detect the carrier The cleanliness of the surface is detected in real time to obtain surface cleanliness data; the dust particle concentration data and the surface cleanliness data are input into a preset cleaning effect evaluation model, and the current cleaning effect is evaluated in real time through the calculation of the cleaning effect evaluation model; if the cleaning effect evaluation result does not reach the preset cleaning effect threshold, the ultrapure water overflow and spray parameter combination is adjusted, the water flow arrangement is reformed, and flushing is continued; if the cleaning effect evaluation result reaches the preset cleaning effect threshold, flushing is stopped, the carrier is taken out of the water tank, and the cleaning process of the carrier is completed.

[0031] First, optical measuring instruments were used to obtain surface area data for the carrier, accurate to the nearest 0.1 square centimeter. Then, chemical analysis instruments were used to measure the amount of adhesive remaining on the carrier surface, accurate to the nearest 1 microgram. These surface area and residual adhesive data were input into a pre-defined mathematical model based on fluid mechanics and cleaning dynamics theory. Finite element analysis and numerical simulations determined the optimal ultrapure water flow rate range to be 5-0 liters / minute, the spray pressure range to be 80-100 Pa, and the spray angle range to be 30-45 degrees. In an ultrasonic water tank, the carrier was tilted at a 15-degree angle and arranged vertically in three layers, with a spacing of 10 cm between the layers. Based on the optimized parameter combination, the ultrapure water flow rate was set to 8 liters / minute, the spray pressure to 90 Pa, and the spray angle to 37 degrees, achieving the optimal water flow arrangement. A laser particle counter was installed in the water tank to monitor the concentration of dust particles in the water in real time, capable of detecting particles as small as 1 micron in size. Simultaneously, an optical surface inspection instrument was used to scan the carrier surface cleanliness in real time, with a resolution of 5 microns. Dust particle concentration and surface cleanliness data are fed into a pre-set fuzzy logic evaluation model, which calculates a comprehensive cleaning performance score using membership functions and an evaluation rule base. If the cleaning performance score falls below 85, a parameter adjustment program is triggered. Using genetic algorithms and neural networks, combined with previous cleaning data, the ultrapure water overflow and spray parameter combinations are re-optimized, generating a new water flow arrangement and continuing the rinsing process. If the cleaning performance score reaches 85 or above, rinsing is terminated, and a robotic arm removes the carrier from the tank and moves it to the next step. The entire process is automatically controlled by a computer, requiring no human intervention, ensuring stable and reliable cleaning results.

[0032] S104. Use an online monitoring device for the surface cleanliness of the carrier plate to collect surface cleanliness data during the cleaning process in real time, analyze the cleanliness change trend in real time through an algorithm, dynamically adjust the soaking, shaking and rinsing processing parameters and circulation path, adaptively optimize the cleaning plan, and predict the cleaning endpoint.

[0033] The cleanliness data of the carrier surface is obtained and input into a pre-built cleanliness change trend analysis model to obtain the current cleanliness change trend; based on the cleanliness change trend obtained by analysis, it is determined whether the current cleaning process parameters need to be adjusted. If adjustment is required, the cleaning process parameters such as immersion time, oscillation frequency, and flushing pressure are dynamically adjusted; based on the adjusted cleaning process parameters, the next cleaning cycle path is determined, and the cleaning equipment is controlled to perform cleaning operations according to the determined cycle path; after each cleaning cycle, the cleanliness data of the carrier surface is re-acquired and input into the cleanliness change trend analysis model to adaptively optimize the cleaning plan; by comparing the cleanliness change trends after multiple cleaning cycles, the long short-term memory neural network algorithm is used to predict the cleaning time required to achieve the target cleanliness and obtain the cleaning endpoint; if the difference between the predicted cleaning endpoint and the current cleaning time is less than a preset threshold, it is determined that the cleaning is about to end, and the cleaning end preparation program is started; based on the cleaning endpoint prediction result, the remaining cleaning cycle paths and cleaning process parameters are dynamically adjusted to ensure that the cleaning operation is completed at the predicted endpoint time.

[0034] Specifically, cleanliness data of the carrier surface is obtained, and the cleanliness data is input into a pre-built cleanliness change trend analysis model to obtain the current cleanliness change trend; based on the cleanliness change trend, it is determined whether the current cleaning process parameters need to be adjusted, and if adjustment is required, at least one cleaning process parameter among the immersion time, oscillation frequency and flushing pressure is dynamically adjusted; based on the adjusted cleaning process parameters, the next cleaning cycle path is determined, and the cleaning equipment is controlled to perform cleaning operations according to the cleaning cycle path; after each cleaning cycle, the cleanliness data of the carrier surface is re-acquired and input into the cleanliness change trend analysis model to adaptively optimize the cleaning scheme; by comparing the cleanliness change trends after multiple cleaning cycles, the long short-term memory neural network algorithm is used to predict the cleaning time required to reach the target cleanliness and obtain the cleaning endpoint; if the difference between the cleaning endpoint and the current cleaning time is less than a preset threshold, it is determined that the cleaning is about to end, and the cleaning end preparation program is started; based on the cleaning endpoint prediction result, the remaining cleaning cycle paths and cleaning process parameters are dynamically adjusted.

[0035] During the cleaning process, a high-precision optical camera captures cleanliness data from the substrate surface. This data is fed into a cleanliness trend analysis model based on a support vector machine algorithm. The model calculates the current cleanliness rate of change to be 8% / min. Based on a preset cleanliness rate threshold of 5% / min, the cleaning process parameters are determined to require adjustment: the soak time is increased from 10 minutes to 15 minutes, the oscillation frequency is increased from 50Hz to 60Hz, and the rinse pressure is increased from 2MPa to 25MPa. Based on these adjusted cleaning process parameters, the cleaning cycle is optimized, controlling the cleaning equipment to follow a "soak-oscillate-rinse-soak" cycle. After each cleaning cycle, the substrate surface cleanliness data is re-acquired and fed into the cleanliness trend analysis model. A gradient descent algorithm is then used to adaptively optimize the cleaning schedule. By comparing the cleanliness trends after five cleaning cycles, a long-short-term memory neural network algorithm is used to predict that the cleaning time required to achieve the target cleanliness level of 999% is 30 minutes. If the difference between the predicted cleaning endpoint and the current cleaning time is less than 2 minutes, the cleaning process is considered to be nearing completion, and cleaning preparation procedures such as cleaning fluid recovery and substrate drying are initiated. Based on the cleaning endpoint prediction results, the remaining cleaning cycles and cleaning parameters for each cycle are dynamically adjusted. For example, the soaking time of the last two cycles can be shortened to 5 minutes, the oscillation frequency can be reduced to 45Hz, and the flushing pressure can be reduced to 15MPa. This ensures that the cleaning process is completed at the predicted endpoint, improving cleaning efficiency and cleanliness stability.

[0036] S105. Deploy a colloid agglomeration degree analyzer in the water tank to monitor the agglomeration state data of the colloid particles in real time, analyze the correlation between the agglomeration state and water quality parameters through an algorithm model, dynamically adjust the pH value and ionic strength of the ultrapure water, optimize the water quality environment, and inhibit the re-deposition of colloid particles.

[0037] A dedicated colloid aggregation analyzer is deployed in the water tank. Using high-precision sensors, it monitors the aggregation state of colloid particles in the water in real time. Data from the analyzer is processed using a pre-established algorithm model that analyzes the relationship between colloid aggregation and the water quality parameters of pH and ionic strength. Based on the algorithm's analysis, the control system automatically adjusts the pH and ionic strength in the water tank to optimize water quality. After optimization, the water quality is re-monitored using the same analyzer to confirm the effectiveness of the adjustments. If the adjusted water quality does not meet expectations, the algorithm reanalyzes the data and adjusts the control parameters until optimal water quality is achieved. Throughout this process, the system continuously monitors colloid redeposition to ensure optimal water quality over the long term. This dynamic adjustment mechanism not only improves the quality of ultrapure water but also effectively prevents colloid redeposition, ensuring stable system operation and continuously optimized water quality.

[0038] Specifically, a special colloid agglomeration degree analyzer deployed in the water tank obtains the agglomeration state data of the colloids in the water through a high-precision sensor. Based on the data, a pre-established algorithm model is used to process the data, and the algorithm model is used to analyze the relationship between the colloid agglomeration state and the water quality parameters. The pH value and ion strength in the water tank are automatically adjusted according to the analysis results of the algorithm model by the control system to optimize the water quality. The optimized water quality is monitored again by the same analyzer to determine the effect of the water quality adjustment. If the adjusted water quality does not achieve the expected effect, the algorithm model will re-analyze the data and adjust the control parameters until the optimal water quality state is reached. Throughout the process, the system continuously monitors the redeposition of colloids. Through this dynamic adjustment mechanism, the quality of ultrapure water is improved, the redeposition of colloids is effectively prevented, and the stable operation of the system and the continuous optimization of water quality are guaranteed.

[0039] A dedicated colloid aggregation analyzer, equipped with high-precision sensors, is deployed in the water treatment system to monitor the aggregation state of colloid particles in the water in real time. For example, the sensor collects data every minute with an accuracy of 0.1 micron. Once the analyzer collects data, it is fed into a pre-established algorithm model for processing. This model, based on the support vector machine (SVM) algorithm, accurately analyzes the complex relationship between colloid aggregation and water quality parameters, such as how pH changes within a range of 5 to 5 and ionic strength adjustments from 0.1 to 1 mol / L affect colloid stability. Based on the model's analysis results, the control system automatically adjusts the pH and ionic strength in the water tank. For example, if the model predicts decreased colloid stability, the system might adjust the pH to 8 and increase the ionic strength to 0.5 mol / L to optimize water quality. After optimization, the water quality is again monitored by the analyzer to confirm that the adjustments meet the expected results. If the adjusted water quality doesn't meet expectations, the algorithm will reanalyze and adjust control parameters based on new data, such as further increasing the ionic strength to 0.8 mol / L, until optimal water quality is achieved. Throughout the entire process, the system continuously monitors the redeposition of colloid particles, ensuring optimal water quality over the long term through periodic data analysis. This not only improves the quality of ultrapure water but also effectively prevents redeposition of colloid particles, ensuring stable system operation and continuous optimization of water quality.

[0040] By obtaining real-time monitoring data from the high-precision sensor of the colloid agglomeration degree analyzer, a pre-established algorithm model is used to analyze the relationship between the colloid agglomeration state and the pH value and ionic strength of the water quality parameters. The water quality is adjusted according to the analysis results. If the adjusted water quality does not achieve the expected effect, the algorithm model re-analyzes the data and adjusts the control parameters until the optimal water quality is achieved.

[0041] Real-time monitoring data of the colloid agglomeration state is obtained through high-precision sensors, and the monitoring data is transmitted to the data processing module. The data processing module pre-processes the received monitoring data, extracts key characteristic parameters, and inputs the processed data into the pre-built model. The pre-built model analyzes the relationship between the colloid agglomeration state and the water quality parameters based on the input characteristic parameters to obtain a water quality adjustment strategy. The water quality adjustment strategy is transmitted to the water quality control module, and the water quality control module adjusts the water quality parameters through the control equipment according to the adjustment strategy. After the adjustment is completed, the high-precision sensor continues to monitor the colloid agglomeration state in real time and transmits the monitoring data to the data processing module. The data processing module compares and analyzes the colloid agglomeration state data before and after the adjustment to determine whether the water quality adjustment effect meets expectations. If it does not meet expectations, the analysis results are fed back to the pre-built model. The pre-built model retrains and optimizes the model parameters based on the feedback analysis results and generates a new water quality adjustment strategy.

[0042] Specifically, in this water treatment system, a high-precision sensor collects data on the aggregation status of colloid particles once per second, with an accuracy of up to 1 micron. The sensor transmits real-time monitoring data via industrial Ethernet to a data processing module. The data processing module uses a Kalman filter algorithm to denoise and smooth the raw data, extracting 10 key characteristic parameters, such as the average particle size and the number of aggregates. The processed characteristic parameter data is input into a pre-built model based on the support vector machine (SVM) algorithm. This model analyzes the input characteristic parameters to establish a nonlinear relationship between the colloid aggregation status and five water quality parameters, such as pH and ionic strength, to determine the probability of colloid redeposition under the current water quality. If the redeposition probability exceeds 5%, the model generates a water quality adjustment strategy, such as adjusting the pH from 0 to 5 or the ionic strength from 1 mol / L to 3 mol / L. This adjustment strategy is transmitted via a digital signal to the water quality control module. Based on the strategy instructions, the control module adjusts the water quality parameters within 30 seconds by adjusting the flow rates of the acid and alkali liquids and the amount of flocculant added. After the adjustment is completed, the sensor continues to collect data on the state of colloid agglomeration at a frequency of once per second. The data processing module compares and analyzes the data within 1 minute before and after the adjustment, and calculates the rate of change of the probability of colloid redeposition. If the rate of change does not reach the preset 80%, the analysis results are fed back to the pre-built model. The model uses optimization algorithms such as the gradient descent method to retrain the model parameters based on the feedback data and generate a new water quality adjustment strategy, such as further adjusting the ion strength to 5 mol / L. The water quality adjustment and effect evaluation are performed in this cycle until the probability of redeposition is reduced to below 1%, achieving the optimal water quality state. Through this intelligent control system, precise regulation of water quality and effective suppression of colloid redeposition can be achieved, ensuring the stable and efficient operation of the ultrapure water treatment process.

[0043] S106. Use a particle removal capacity evaluation device to evaluate the removal efficiency of each particle size segment for particles of different sizes, analyze the relationship between the removal efficiency and the filtration accuracy and water flow rate through an algorithm, dynamically adjust the technical parameters of the filtration device, and optimize the horizontal arrangement spacing and staggered arrangement to form a particle removal process that is suitable for the degree of agglomeration of the colloid particles.

[0044] An evaluation device is used to collect data on the removal efficiency of particles of different sizes. Algorithmic analysis reveals the correlation between removal efficiency, filtration accuracy, and water flow rate. Based on this data, the technical parameters of the filtration device are dynamically adjusted to improve filtration efficiency. After obtaining these adjusted parameters, the horizontal spacing and staggered arrangement are optimized to accommodate the degree of colloidal particle agglomeration. This optimization results in a new particle removal process that effectively improves removal efficiency. Based on the effectiveness of the new process, the evaluation device is used again to conduct effectiveness tests. The test results are analyzed using an algorithm to determine whether further adjustments to the technical parameters or optimization of the arrangement are necessary. If the test results are satisfactory, the process is standardized and applied to particle removal processes in practical applications.

[0045] Specifically, the removal efficiency data of different particle sizes are obtained, and the data are collected by an evaluation device. Based on the data, an algorithm is used to analyze the correlation between the removal efficiency, the filtration accuracy and the water flow rate. The technical parameters of the filtration device are dynamically adjusted based on the analysis results of the algorithm. The adjusted technical parameters are obtained to optimize the horizontal layout spacing and the staggered arrangement. A new particle removal process is formed, which effectively improves the removal efficiency through optimized technical parameters and layout. An evaluation device is used to test the effect of the implementation of the new process, and the test results are analyzed by an algorithm to determine whether it is necessary to further adjust the technical parameters or optimize the layout. If the test results are satisfactory, the process is standardized and used for the particle removal process in actual applications.

[0046] When implementing a new particle removal process, a high-precision evaluation device is first used to collect removal efficiency data for different particle sizes. Using machine learning algorithms, such as support vector machines (SVMs) or decision trees, the correlation between removal efficiency and filtration fineness (1 to 10 microns) and water flow rate (5 to 3 meters per second) is analyzed. Based on the algorithmic analysis, the technical parameters of the filtration device are dynamically adjusted, such as increasing the density of the filter layer or changing the pore size of the filter material, to improve filtration efficiency. Following these adjustments, the horizontal spacing (adjusted to 5 to 20 cm) and the staggered arrangement (using a 45-degree stagger) are optimized to accommodate the degree of colloidal particle agglomeration, thereby reducing clogging during the filtration process. This optimization results in a new particle removal process. This process is then retested using the evaluation device, and the collected data is analyzed using a deep learning algorithm to ensure that the removal efficiency meets the target (an improvement of at least 30%). If the test results show that both the removal efficiency and water quality meet the established standards, the process is standardized and applied to actual water treatment processes to achieve efficient and stable particle removal.

[0047] It will be apparent to those skilled in the art that the present application is not limited to the details of the exemplary embodiments described above and that the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the present application is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A method for cleaning organic glue residue on the surface of a carrier board, characterized in that: The method comprises the following steps: S101: Obtain data on the residual organic adhesive on the substrate surface and the material dimensional characteristics. By selecting an algorithm model and setting parameters, determine the stripping solution immersion sequence and duration combination, and obtain a multi-step immersion treatment plan. The immersion process is carried out in a dust-free area that meets the cleanliness level requirements. Air filtration devices and anti-static measures are used to ensure environmental cleanliness. In step S102, based on the size and material characteristics of the carriers, the algorithm model is trained and evaluated to obtain the ultrasonic oscillation frequency and duration parameters. The carriers are then staggered horizontally and rotated vertically to form an oscillation arrangement. The temperature and humidity conditions in the dust-free zone are strictly controlled during the oscillation process. In step S103, based on the carrier surface area and residual adhesive data, an algorithm model is iteratively optimized to determine the ultrapure water overflow and spray parameter combination, including flow rate, pressure, and angle. The carrier is then placed in the water tank at an angle and vertically spaced in multiple layers to form a water flow arrangement. During the rinsing process, dust particle monitoring and surface cleanliness verification are performed to evaluate the cleaning effect in real time. S104, using an online monitoring device for the surface cleanliness of the substrate to collect real-time surface cleanliness data during the cleaning process, and using an algorithm to analyze the cleanliness trend in real time, dynamically adjust the soaking, shaking, and rinsing process parameters and circulation paths, adaptively optimize the cleaning plan, and predict the cleaning endpoint; S105: A colloidal particle aggregation analyzer is deployed in the water tank to monitor the colloidal particle aggregation state data in real time. The correlation between the aggregation state and water quality parameters is analyzed through an algorithm model. The pH value and ionic strength of the ultrapure water are dynamically adjusted to optimize the water quality environment and inhibit the redeposition of colloidal particles. S106, using a particle removal capacity evaluation device to evaluate the removal efficiency of each particle size segment for particles of different sizes, through an algorithm to analyze the relationship between the removal efficiency and the filtration accuracy and water flow rate, dynamically adjust the technical parameters of the filtration device, and optimize the horizontal arrangement spacing and staggered arrangement to form a particle removal process that is suitable for the degree of colloid agglomeration.

2. The method for cleaning organic glue residue on the carrier surface according to claim 1, characterized in that: The S101 further includes: Step 1: Obtain the data of organic adhesive residue on the substrate surface and material dimensional characteristics as input to the algorithm model; Step 2: Based on the surface material and dimensional characteristics of the substrate, a decision tree algorithm model is used to determine the optimal stripping solution immersion sequence and duration combination through parameter settings; Step 3: Immerse the substrate in different stripping solutions in a dust-free area that meets cleanliness requirements, following a predetermined soaking order and duration. Step 4: During the soaking process, an air filter is used to continuously filter the air in the dust-free area to remove particles and dust in the air; Step 5: During the soaking process, take anti-static measures to prevent static electricity from damaging the surface of the carrier board. Step 6: After the immersion is completed, the data of the residual amount of organic glue on the surface of the carrier is obtained to determine whether the residual amount is lower than the preset threshold. If so, the immersion process is completed. If not, return to step 2, adjust the immersion order and duration, and continue the immersion process; In step 7, the data of multiple batches of substrate immersion treatment are input into the algorithm model for training. Through parameter optimization, the accuracy of the model in predicting the immersion sequence and duration combination is continuously improved, thus realizing the intelligentization of the substrate immersion treatment process.

3. The method for cleaning organic glue residue on the carrier surface according to claim 1, characterized in that: The S102 further includes: Obtain the size and material property data of the carrier board as input parameters of the algorithm model; Using machine learning algorithms, support vector machines or neural networks, the input parameters are trained and evaluated to obtain the optimal ultrasonic oscillation frequency and duration parameters; Determine the horizontal staggered arrangement based on the carrier board size, and use computer vision algorithms to determine whether the arrangement is reasonable; According to the material characteristics, the rotation angle in the vertical direction is determined, and the rotation effect is evaluated through simulation algorithms; Combine horizontal staggering and vertical rotation to form the best oscillation layout, and continuously iterate and optimize the layout through optimization algorithms; In the dust-free area, temperature and humidity sensors are used to collect environmental data in real time, and the temperature and humidity parameters are adjusted through the PID control algorithm to ensure that the vibration requirements are met; By integrating the oscillation frequency, duration, layout and environmental condition parameters, through simulation and experimental verification, the final ultrasonic oscillation process parameters are obtained to guide actual production.

4. The method for cleaning organic glue residue on the carrier surface according to claim 1, characterized in that: The S103 further includes: Obtain the carrier surface area and residual glue data, and then, based on the preset algorithm model, obtain the ultrapure water overflow and spray parameter combination, including flow rate, pressure, and angle, through iterative optimization. The carrier plate is placed in the water tank in an inclined manner and spaced vertically in multiple layers, and the optimal water flow arrangement is formed according to the determined ultrapure water overflow and spray parameters. During the flushing process, the dust particle concentration data in the water tank is obtained in real time through the dust particle monitoring device installed in the water tank; At the same time, a surface cleanliness detection device is used to detect the cleanliness of the carrier surface in real time to obtain surface cleanliness data; Input dust particle concentration data and surface cleanliness data into the preset cleaning effect evaluation model, and evaluate the current cleaning effect in real time through model calculation; If the evaluation result does not meet the preset cleaning effect threshold, the ultrapure water overflow and spray parameter combination is adjusted to re-form the water flow arrangement and continue flushing until the evaluation result meets the threshold requirement; If the evaluation result reaches a preset cleaning effect threshold, the rinsing is stopped, the carrier is removed from the water tank, and the carrier cleaning process is completed.

5. The method for cleaning organic glue residue on the carrier surface according to claim 1, characterized in that: The S104 further includes: Obtain the cleanliness data of the carrier surface, input the cleanliness data into a pre-built cleanliness change trend analysis model, and obtain the current cleanliness change trend; Based on the analyzed cleanliness change trend, determine whether the current cleaning process parameters need to be adjusted. If adjustment is required, dynamically adjust at least one cleaning process parameter of the immersion time, the oscillation frequency, and the flushing pressure. Determine the next cleaning cycle path based on the adjusted cleaning processing parameters, and control the cleaning equipment to perform cleaning operations according to the determined cycle path; After each cleaning cycle, the cleanliness data of the substrate surface is retrieved and input into the cleanliness trend analysis model to adaptively optimize the cleaning plan. By comparing the cleanliness trend after multiple cleaning cycles and using the long short-term memory neural network algorithm, the cleaning time required to reach the target cleanliness is predicted and the cleaning endpoint is obtained. If the difference between the predicted cleaning endpoint and the current cleaning time is less than a preset threshold, it is determined that the cleaning is about to end and the cleaning end preparation program is started; Based on the cleaning endpoint prediction results, the remaining cleaning cycle paths and cleaning processing parameters are dynamically adjusted to ensure that the cleaning operation is completed at the predicted endpoint moment.

6. The method for cleaning organic glue residue on the carrier surface according to claim 1, characterized in that: The S105 further includes: A dedicated colloidal particle aggregation analyzer is deployed in the water tank. This device can monitor the aggregation state of colloidal particles in the water in real time through high-precision sensors. After acquiring the data from the analyzer, it is processed by a pre-established algorithm model, which can analyze the relationship between the state of colloidal agglomeration and the pH value and ionic strength of water quality parameters; Based on the analysis results of the algorithm model, the pH value and ionic strength in the water tank are automatically adjusted through the control system to optimize the water quality; The optimized water quality will be monitored again using the same analyzer to confirm whether the effect of the water quality adjustment is as expected; If the adjusted water quality does not meet the expected results, the algorithm model will reanalyze the data and adjust the control parameters until the optimal water quality is achieved; During the entire process, the system will continuously monitor the redeposition of colloid particles to ensure that the water quality remains at the optimal state for a long time; This dynamic adjustment mechanism not only improves the quality of ultrapure water, but also effectively prevents the redeposition of colloid particles, ensuring the stable operation of the system and the continuous optimization of water quality; It also includes: obtaining real-time monitoring data from the high-precision sensor of the colloid agglomeration degree analyzer, using a pre-established algorithm model to analyze the relationship between the colloid agglomeration state and the pH value and ionic strength of the water quality parameters, and adjusting the water quality according to the analysis results. If the adjusted water quality does not achieve the expected effect, the algorithm model will re-analyze the data and adjust the control parameters until the optimal water quality state is obtained.

7. The method for cleaning organic glue residue on the carrier surface according to claim 6, characterized in that: Also includes: The real-time monitoring data of the agglomeration state of the colloid particles is obtained through high-precision sensors and transmitted to the data processing module; The data processing module pre-processes the received monitoring data, extracts key characteristic parameters, and inputs the processed data into the pre-built model; The pre-built model analyzes the relationship between the colloid agglomeration state and water quality parameters based on the input characteristic parameters, and obtains the water quality adjustment strategy; The water quality adjustment strategy is transmitted to the water quality control module, and the water quality control module adjusts the water quality parameters through the control equipment according to the adjustment strategy; After the adjustment is completed, the high-precision sensor continues to monitor the agglomeration state of the colloid particles in real time and transmits the monitoring data to the data processing module; The data processing module compares and analyzes the data on the agglomeration status of the colloid particles before and after the adjustment to determine whether the water quality adjustment effect meets the expectations; If expectations are not met, the analysis results are fed back into the pre-built model; The pre-built model retrains and optimizes model parameters based on the feedback analysis results and generates new water quality adjustment strategies.

8. The method for cleaning organic glue residue on the carrier surface according to claim 1, characterized in that: The S106 further includes: An evaluation device was used to collect data on the removal efficiency of particles of different sizes, and the correlation between the removal efficiency, filtration accuracy, and water flow rate was obtained through algorithm analysis. Based on these data, the technical parameters of the filtration device are dynamically adjusted to improve filtration efficiency; Obtain the adjusted parameters and optimize the horizontal spacing and staggered arrangement to adapt to the degree of agglomeration of the particles; Through this optimization, a new particle removal process is formed, which can effectively improve the removal efficiency; Based on the implementation effect of the new process, the evaluation device is used again to test the effect. The test results are analyzed by algorithms to determine whether further adjustments to technical parameters or optimization of layout are needed. If the test results are satisfactory, the process will be standardized and used for particle removal in actual applications.

Images