Intelligent cleaning control method and system for reducing occurrence rate of silicon powder pollution and storage medium

Abstract

The invention discloses an intelligent cleaning control method and system for reducing the occurrence rate of silicon powder dirt and a storage medium, and relates to the technical field of silicon wafer cleaning. The method comprises the following steps: presetting an image acquisition interval, controlling a visual sensing array to capture a cleaning tank image by taking the acquisition interval as a constraint, and obtaining a water surface and internal image sequence; analyzing dirt composition based on the surface image sequence to obtain dirt time sequence data; according to the internal image sequence grading foul degree, obtaining foul degree time sequence data; pre-constructing a cooperative control model, synchronizing the data to the model for analysis, and outputting cooperative optimization parameters; and updating the operation parameters of the cleaning control module by taking the optimization parameters as constraints. The technical problems that an existing cleaning technology is poor in adaptability and the silicon powder pollution occurrence rate is high when the silicon powder content is high are solved, and the technical effects of reducing the silicon powder pollution occurrence rate and improving the cleaning technology efficiency are achieved by combining control analysis of the cooperative control model and dynamically adjusting the cleaning control parameters.

Description

Technical Field

[0001] The present invention relates to the technical field of silicon wafer cleaning, and in particular to an intelligent cleaning control method, system and storage medium for reducing the occurrence rate of silicon powder contamination. Background Art

[0002] In the silicon wafer manufacturing process, the cleaning process is an important link to ensure the surface quality of silicon wafers, which directly affects the stability and yield of subsequent processes. However, existing cleaning methods mainly rely on a combination of chemicals and pure water to remove surface pollutants through mechanical cleaning methods with fixed parameters. This method shows great limitations when faced with complex and changeable pollution situations. When there is a lot of silicon powder or organic pollutants attached to the surface of the silicon wafer, the water in the cleaning tank gradually accumulates pollutants as the use time increases, resulting in increased turbidity in the cleaning tank water. Traditional methods cannot dynamically adjust the cleaning parameters, which can easily lead to problems such as decreased cleaning efficiency and increased incidence of contaminated wafers. Summary of the invention

[0003] The present application provides an intelligent cleaning control method, system and storage medium for reducing the incidence of silicon powder contamination, which solves the technical problems that the existing cleaning process has poor adaptability and a high incidence of silicon powder contamination when the silicon powder content is high.

[0004] In view of the above problems, the present application provides an intelligent cleaning control method, system and storage medium for reducing the incidence of silicon powder contamination.

[0005] In a first aspect of the present application, an intelligent cleaning control method for reducing the incidence of silicon powder contamination is provided, the method comprising:

[0006] An image acquisition interval is preset, and the image acquisition interval is used as a constraint to control the visual sensor array to capture images of the cleaning tank to obtain water image information, wherein the water image information includes a water surface image sequence and a water interior image sequence; dirt composition analysis is performed based on the water surface image sequence to obtain dirt time series data; turbidity classification of the cleaning tank is performed according to the water interior image sequence to obtain turbidity time series data; a collaborative control model is pre-constructed; control analysis is performed by synchronizing the dirt time series data and the turbidity time series data to the collaborative control model, and collaborative optimization parameters are output; and operating parameters of a cleaning control module are updated with the collaborative optimization parameters as a constraint.

[0007] The second aspect of the present application provides an intelligent cleaning control system for reducing the incidence of silicon powder pollution, the system comprising:

[0008] Image capture component: preset image acquisition interval, and use the image acquisition interval as a constraint to control the visual sensor array to capture images of the cleaning tank, and obtain water body image information, wherein the water body image information includes a water body surface image sequence and a water body internal image sequence; dirt composition analysis component: perform dirt composition analysis based on the water body surface image sequence to obtain dirt time series data; turbidity grading component: perform turbidity grading on the cleaning tank according to the water body internal image sequence to obtain turbidity time series data; model pre-construction component: pre-construct a collaborative control model; control analysis component: perform control analysis by synchronizing the dirt time series data and turbidity time series data to the collaborative control model, and output collaborative optimization parameters; operation parameter update component: use the collaborative optimization parameters as a constraint to update the operation parameters of the cleaning control module.

[0009] The third aspect of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the intelligent cleaning control method for reducing the incidence of silicon powder contamination provided in the present application.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] First, the image acquisition interval is preset, and the image acquisition interval is used as a constraint to control the visual sensor array to capture the image of the cleaning tank to obtain water image information, wherein the water image information includes a water surface image sequence and a water internal image sequence. Next, the dirt composition analysis is performed based on the water surface image sequence to obtain the dirt time series data, and the turbidity of the cleaning tank is graded according to the water internal image sequence to obtain the turbidity time series data. Further, a collaborative control model is pre-constructed, and then the dirt time series data and the turbidity time series data are synchronized to the collaborative control model for control analysis, and the collaborative optimization parameters are output. Finally, the operating parameters of the cleaning control module are updated with the collaborative optimization parameters as constraints. The technical problems of poor adaptability of the existing cleaning process and high incidence of silicon powder pollution when the silicon powder content is high are solved. By combining the control analysis of the collaborative control model, the cleaning control parameters are dynamically adjusted to achieve the technical effect of reducing the incidence of silicon powder pollution and improving the efficiency of the cleaning process. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1A schematic flow chart of an intelligent cleaning control method for reducing the incidence of silicon powder contamination provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the structure of an intelligent cleaning control system for reducing the incidence of silicon powder contamination provided in an embodiment of the present application.

[0015] Explanation of reference numerals: image capturing component 11 , dirt composition analyzing component 12 , dirt turbidity classification component 13 , model pre-building component 14 , control analyzing component 15 , operation parameter updating component 16 . DETAILED DESCRIPTION

[0016] The present application solves the technical problems that the existing cleaning process has poor adaptability and the incidence of silicon powder contamination is high when the silicon powder content is high, by providing an intelligent cleaning control method, system and storage medium for reducing the incidence of silicon powder contamination.

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0018] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0019] Embodiment 1, as Figure 1 As shown, the present application provides an intelligent cleaning control method for reducing the incidence of silicon powder pollution, wherein the method includes:

[0020] An image acquisition interval is preset, and the image acquisition interval is used as a constraint to control the visual sensor array to capture images of the cleaning tank to obtain water body image information, wherein the water body image information includes a water body surface image sequence and a water body interior image sequence.

[0021] In one embodiment, the system terminal first sets a fixed image acquisition time interval, which is used to control the frequency of image acquisition. Through this preset time interval, the visual sensor array in the cleaning system can continuously capture images of the cleaning tank according to the specified cycle. The collected image information is mainly divided into two parts: one part is the image sequence of the water surface, which is used to analyze the type, distribution and quantity of pollutants on the water surface; the other part is the image sequence inside the water body, which is used to monitor the changes in water turbidity. This dual-level image information acquisition provides comprehensive data support for subsequent pollutant analysis and turbidity classification, which helps to achieve precise control and dynamic adjustment of the cleaning process.

[0022] The dirt composition analysis is performed based on the water body surface image sequence to obtain dirt time series data.

[0023] In one embodiment, the system terminal uses a water surface image sequence to perform a detailed analysis of pollutants on the water surface in the cleaning tank. Through the pre-built pollutant ratio recognition model, the composition information of pollutants, such as organic matter, silicon powder clusters, bubbles, etc., as well as the number and coverage area of ​​these pollutants, are extracted from the image to generate time series data of pollutants. These time series data provide an important basis for the subsequent optimization and dynamic adjustment of cleaning parameters.

[0024] Furthermore, the method of performing a pollution composition analysis based on the water body surface image sequence to obtain pollution time series data includes:

[0025] Interactively obtain multiple sample pollution image sets of multiple sample water pollution; perform pollution area ratio directional annotation on the multiple sample pollution image sets to obtain multiple sample annotated image sets; use the multiple sample pollution image sets and the multiple sample annotated image sets as training data to perform directional training of a standard pollution recognition model to obtain multiple pollution proportion recognition branches; connect the multiple pollution proportion recognition branches in parallel to obtain a pollution proportion recognition model; synchronize the water body surface image sequence to the pollution proportion recognition model to perform pollution composition analysis to obtain pollution time series data.

[0026] Preferably, the system terminal first obtains a set of images of multiple sample water pollutants in an interactive manner, and these images represent typical scenes of pollutants on the surface of different water bodies, for example, a combination of organic matter, silicon powder groups and bubbles. Subsequently, these images are annotated, and the specific annotation content includes the distribution of the area ratio of various pollutants on the surface of the water body. For example, a sample image may be annotated with organic matter accounting for 0.5%, silicon powder groups accounting for 2.5%, and bubbles accounting for 1%. During the labeling process, the total coverage area of ​​pollutants (represented by the sum of the coverage areas of organic matter, silica powder, and other debris, S, T, and U, respectively) will also be quantified into the following levels: Level 1 is (S+T+U)≤1% (total coverage area of ​​pollutants is less than or equal to 1%), Level 2 is (S+T+U)≤2% (total coverage area of ​​pollutants is less than or equal to 2%); Level 3 is (S+T+U)≤3% (total coverage area of ​​pollutants is less than or equal to 3%); Level 4 is (S+T+U)≤4% (total coverage area of ​​pollutants is less than or equal to 4%); Level 5 is (S+T+U)>4% (total coverage area of ​​pollutants is greater than 4%). After the labeling is completed, multiple sample pollution image sets and multiple sample annotated image sets are used to train the standard pollution recognition model. During the training process, the convolutional neural network (CNN) is used as the core algorithm to gradually extract the spatial characteristics of pollutants through the image processing layer. Before training begins, multiple sample image sets are normalized to standardize pixel values ​​to a uniform range, such as [0,1], to improve the convergence speed and stability of the model. Multiple sample annotated image sets are then input as labels into multiple pollutant proportion recognition branches, each of which is responsible for a pollutant category and the corresponding coverage area ratio. In the unstarved branch, multiple convolutional layers are used to extract the corresponding sample pollutant image set, and the pooling layer is combined to perform feature dimension reduction, gradually compress the spatial information of the image data and enhance the expression of important features. Afterwards, the extracted features are classified and regressed through the fully connected layer to achieve the prediction of the pollutant ratio. In the training process of these branches, the mean square error (MSE) is used as the optimization target of the regression task to predict the specific proportion of the pollutant coverage area. In order to improve the generalization ability of these branches, data enhancement techniques such as image rotation, flipping, and noise addition are introduced in the training process to enable these branches to adapt to different pollutant morphological changes. In the training stage, the Adam optimizer is used to adjust the parameters of the branches, and the learning rate decay strategy is set to ensure the stability and efficiency of the training process. After training, multiple pollutant proportion recognition branches are obtained, corresponding to the proportion analysis capabilities of organic matter, silicon powder clusters, bubbles and other pollutants. Then, these recognition branches are integrated in parallel to form a complete pollutant proportion recognition model. This model can receive a sequence of water surface images and analyze the types of pollutants in the image and their surface area proportion.For example, through the analysis of multiple internal branches, it can be identified that organic matter accounts for 0.8% (S=0.8%), silicon powder accounts for 1.2% (T=1.2%), and other debris accounts for 1% (U=1%) of the water surface pollutants at a certain moment, and the quantitative level is level 3 through the preset total coverage area evaluation strategy. Finally, the analysis results are arranged in chronological order to generate pollutant time series data, which provides a basis for subsequent cleaning parameter optimization and dynamic adjustment.

[0027] The turbidity of the cleaning tank is graded according to the image sequence inside the water body to obtain turbidity time series data.

[0028] In one embodiment, the turbidity of the water in the cleaning tank is analyzed by a water level analysis model using a sequence of images inside the water body, and is managed in a graded manner. Specifically, the system terminal first extracts the grayscale value information of the image inside the water body, and the grayscale value reflects the transparency and pollution degree of the water body. Combined with the grayscale value interval (for example: grayscale value 240-248 is the highest level N, indicating that the water body is clear; grayscale value 0-128 is the lowest level R, indicating that the water body is severely turbid), the turbidity of the water body is divided into five levels. The grayscale value of each image is mapped to the corresponding level after calculation by the model. As time goes by, the system terminal analyzes the water body image at each time point, records the turbidity changes in different time periods, and generates turbidity time series data. These time series data can reflect the dynamic changes of water pollution over time, and provide key support for the optimization and adjustment of subsequent cleaning parameters.

[0029] Furthermore, the turbidity of the cleaning tank is graded according to the internal image sequence of the water body to obtain turbidity time series data, and the method includes:

[0030] A water body grade analysis model is pre-constructed, wherein the water body grade analysis model includes a cascaded grayscale analysis model and a water body grade judgment module; a first water body internal image corresponding to a first time series is extracted from the water body internal image sequence; the first water body internal image is synchronized to the grayscale analysis model of the water body grade analysis model for analysis to obtain a first water body turbidity; the first water body turbidity is synchronized to the water body grade judgment module of the water body grade analysis model for analysis to obtain a first water body grade; and so on, the turbidity of the cleaning tank is graded by synchronizing the water body internal image sequence to the water body grade analysis model to obtain the turbidity time series data.

[0031] Optionally, during the cleaning control process, the system terminal first pre-builds a water body grade analysis model. The model consists of two core parts: a grayscale analysis model and a water body grade judgment module, which are jointly analyzed in a cascade manner. The grayscale analysis model is trained based on sample data and is responsible for extracting and analyzing the grayscale value information of the internal image of the water body, while the water body grade judgment module determines the specific grade of the water body based on the grayscale value. After the water body grade analysis model is determined, the system terminal extracts the image corresponding to the first time point from the internal image sequence of the water body as the first internal water body image. The image captures the turbidity state of the water body in the cleaning tank at that moment. Subsequently, the first internal water body image is input into the grayscale analysis model, and the grayscale value of the image is calculated pixel by pixel. The average grayscale value can reflect the transparency and pollution degree of the water body. For example, a higher grayscale value indicates that the water body is clear, while a lower grayscale value indicates that the water body is seriously turbid. The result of the analysis is output as the turbidity of the first water body. Afterwards, the turbidity of the first water body is synchronized to the water body grade judgment module, and the module grades the turbidity according to a preset gray value grade interval. For example, the grayscale value in the interval (240,248] corresponds to the water level N (clear). The grayscale value in the interval (128,192] corresponds to the water level Q (slightly polluted). The grayscale value in the interval [0,128] corresponds to the water level R (severely polluted). The module determines the first water level according to the grayscale value interval and records the level information. Repeat the above process, analyze each time series image in the internal image sequence of the water body, extract its turbidity one by one and classify it, arrange the classification results in chronological order, and generate complete turbidity time series data. Finally, the turbidity time series data reflects the pollution change trend of the water in the cleaning tank during the entire cleaning cycle, providing a basis for the subsequent adjustment of cleaning parameters (such as ultrasonic power and jet volume). Through this process, real-time monitoring and dynamic classification of water turbidity can be achieved, ensuring the stability and accuracy of the cleaning effect, and providing data support for reducing energy consumption and improving cleaning efficiency.

[0032] Furthermore, a water body grade analysis model is pre-built, and the method includes:

[0033] Interactively obtain multiple sample water body turbidity images and multiple sample water body turbidity; use the multiple sample water body turbidity images and multiple sample water body turbidity as training data to complete the construction of the grayscale analysis model; interactively obtain multiple water body turbidity intervals of multiple water body grades; store the multiple water body grades and multiple water body turbidity intervals based on the knowledge graph to complete the construction of the water body grade judgment module; and complete the construction of the water body grade analysis model by cascading the grayscale analysis model and the water body grade judgment module.

[0034] Optionally, in the process of building a water body grade analysis model, the system terminal interactively obtains multiple sample water body turbidity images and corresponding sample water body turbidity. These images represent different degrees of water body pollution, and the turbidity is calculated by grayscale value. For example, the grayscale value of an image is 200, reflecting a medium pollution state. Subsequently, the collected sample water body turbidity images and their corresponding sample turbidity are used as training data and input into the grayscale analysis model based on the convolutional neural network. The model learns the grayscale distribution characteristics of the image through the same training method as mentioned above, and gradually optimizes the parameters to achieve accurate extraction of the grayscale value of the input image and prediction of the turbidity. Afterwards, through data statistics or industry standards, multiple levels of water bodies and their corresponding grayscale value intervals are interactively defined, and these intervals are used as water body turbidity intervals. For example, the gray value of level N (clear) is ∈(240,248], the gray value of level O (slightly polluted) is ∈(224,240], the gray value of level P (moderately polluted) is ∈(192,224], the gray value of level Q (heavily polluted) is ∈(128,192], and the gray value of level R (severely polluted) is ∈[0,128]. Then, the knowledge graph technology is used to associate and store the above multiple water body levels with the corresponding water body turbidity intervals. For example, the knowledge graph node can contain the following information: Node 1: Level N → Water body turbidity interval (240,248], Node 2 :Level O→Water turbidity interval (224,240]. Through the association relationship of the knowledge graph, a water body level judgment module is constructed, which enables the corresponding water body level to be quickly judged according to the input turbidity value. Then, the grayscale analysis model is cascaded and integrated with the water body level judgment module to construct a water body level analysis model. The input water body turbidity image is first extracted by the grayscale analysis model in the water body level analysis model to extract the grayscale value and predict the turbidity, and then the predicted turbidity is synchronized to the water body level judgment module, and the water body level is determined according to the water body turbidity interval, providing key support for cleaning control.

[0035] Pre-built collaborative control models.

[0036] In one embodiment, pre-constructing a collaborative control model is a key step to achieve precise dynamic adjustment during the cleaning process. Specifically, the collaborative control model integrates multiple data sources (such as dirt time series data and turbidity time series data) to achieve collaborative optimization and regulation of cleaning tank operating parameters (such as jet volume and ultrasonic power). During the construction process, a large amount of sample data needs to be collected first, including multiple groups of different pollutant proportion arrays and corresponding jet volume adjustment values, as well as multiple sample water body levels and ultrasonic power parameter association data. After cleaning, classification and standardization, these data are used as input for model training. Subsequently, regression analysis and other methods are used to construct the gas volume adjustment branch and the power adjustment branch. The two branches are integrated in parallel to ensure that the model can simultaneously handle the optimization requirements of the jet volume and ultrasonic power. In the design of the model, a hierarchical structure is adopted to input the dirt time series data into the jet volume adjustment branch for calculating the optimal jet volume; at the same time, the turbidity time series data is input into the power adjustment branch for optimizing the ultrasonic power output. The collaborative control logic of the model dynamically analyzes the relationship between these data and comprehensively evaluates the optimal cleaning parameter combination. Finally, the collaborative control model outputs a set of collaborative optimization parameters (including jet volume and ultrasonic power) to provide decision support for the cleaning control module. Through such a pre-built process, the collaborative control model can effectively cope with different pollution conditions and achieve the best balance between cleaning efficiency and energy consumption.

[0037] Further, the collaborative control model is pre-built, and the method includes:

[0038] Interactively obtain multiple sample dirt percentage arrays and multiple sample gas volume adjustment values; perform multi-source regression analysis on the multiple sample dirt percentage arrays and the multiple sample gas volume adjustment values ​​to obtain a gas volume adjustment function; construct a gas volume adjustment branch based on the gas volume adjustment function; interactively obtain multiple sample power parameters and multiple groups of sample water body levels; use a table structure to associate and store the multiple sample power parameters and the multiple groups of sample water body levels to complete the construction of the power adjustment branch; connect the gas volume adjustment branch and the power adjustment branch in parallel to complete the construction of the collaborative control model.

[0039] Optionally, in the process of building a collaborative control model, the system terminal obtains multiple sample dirt ratio arrays and corresponding sample gas volume adjustment values ​​in an interactive manner. These data record the distribution of pollutants under different cleaning conditions (the ratio array includes the area ratio of organic matter, silicon powder group and other debris, such as S+T+U) and the jet volume value required to ensure the cleaning effect. Subsequently, the relationship between the sample dirt ratio array (for example, level one: S+T+U≤1%) and the gas volume adjustment value (for example, jet volume 5%) is modeled using a multi-source regression analysis method. A gas volume adjustment function is generated by the least squares method or other regression algorithms, which can dynamically predict the optimal jet volume value according to the input pollutant ratio. For example, when (S+T+U)≤3%, the predicted jet volume value is 10%. The generated gas volume adjustment function is then encapsulated to construct a gas volume adjustment branch. This branch can receive dirt time series data in real time and use the gas volume adjustment function to calculate the optimal jet volume required in the current cleaning tank. For example, the input dirt ratio is 2.5%, and the gas volume adjustment branch outputs a jet volume of 10%. Afterwards, multiple sample power parameters (such as ultrasonic power: 80%, 90%, 100%) and corresponding sample water levels (such as N, O, P, Q, R) are obtained interactively. These data reflect the adaptation of different cleaning intensities to water bodies with different turbidity levels. For example, for samples with a water grayscale value of (224, 240], the recorded power is 90%. Then, a table structure is used to store the correspondence between power parameters and water body levels. For example, level N (clear): grayscale value (240, 248], power 100%, level Q (heavily polluted): grayscale value (128, 192], power 80%. Through this storage method, the power adjustment branch can quickly query and call the corresponding power parameters. Then, based on the stored association, a power adjustment branch is designed. This branch can receive turbidity time series data and dynamically adjust the ultrasonic power output according to the current water body level. For example, if the input grayscale value is 200, the power adjustment branch outputs power 90%. Finally, the air volume regulation branch and the power regulation branch are integrated through a parallel structure to form a collaborative control model. The air volume regulation branch optimizes the jet volume according to the pollutant ratio array, while the power regulation branch optimizes the ultrasonic power according to the water body level. The two operate independently but output in coordination. After the model is built, its accuracy and reliability are verified through test data, and the air volume regulation function and power parameter storage rules are further optimized to ensure the efficiency and accuracy of the model in actual cleaning operations. Through this process, the collaborative control model can dynamically receive and analyze the dirt time series data and the turbidity time series data, and output the optimal jet volume and power parameters, providing real-time control capabilities for the cleaning control module.

[0040] The pollution time series data and the turbidity time series data are synchronized to the collaborative control model to perform control analysis and output collaborative optimization parameters.

[0041] In one embodiment, during the cleaning control process, the system terminal synchronously inputs the real-time generated dirt time series data and turbidity time series data into the collaborative control model. The collaborative control model comprehensively analyzes these two types of data to identify the correlation between pollutants and water turbidity, and calculates the optimal cleaning parameters suitable for the current cleaning state as collaborative optimization parameters based on the built-in adjustment logic and optimization rules, including the optimal jet volume and ultrasonic power. These parameters are directly transmitted to the cleaning control module for dynamically adjusting the operating state of the cleaning equipment, thereby achieving efficient pollutant removal and energy consumption optimization. Through this process, it is possible to respond to water changes in real time under complex cleaning conditions and maintain the stability and accuracy of the cleaning effect.

[0042] Furthermore, by synchronizing the dirt time series data and the turbidity time series data to the collaborative control model for control analysis and outputting collaborative optimization parameters, the method includes:

[0043] The pollution time series data is synchronized to the air volume regulation branch of the collaborative control model to solve the jet volume and obtain multiple alternative optimization parameters; the multiple alternative optimization parameters are serialized, and the maximum value is extracted according to the sorting result to obtain the jet volume optimization parameter; the turbidity time series data is serialized, and the maximum value is extracted according to the sorting result to obtain the turbidity extreme value; the turbidity extreme value is synchronized to the power regulation branch of the collaborative control model to solve the power optimization and output the ultrasonic optimization power; the jet volume optimization parameter and the ultrasonic optimization power constitute the collaborative optimization parameter.

[0044] Optionally, the system terminal first synchronizes the pollutant time series data to the gas volume regulation branch of the collaborative control model. The gas volume regulation branch uses the gas volume regulation function to calculate the jet volume at different time points according to the type of pollutants (such as bubbles, organic matter, silicon powder agglomerates, etc.), coverage area (such as S+T+US+T+U), and dynamic changes in pollutants, and generates multiple alternative optimization parameters. These alternative parameters are then serialized, and the maximum value is extracted according to the sorting results to obtain the jet volume optimization parameters to ensure the rapid removal of floating pollutants on the surface of the water body. At the same time, the turbidity time series data is serialized and analyzed. For example, the grayscale value at time t1 is 200, corresponding to the turbidity level of P; the grayscale value at time t2 is 180, corresponding to the turbidity level of Q. The maximum grayscale is extracted from these time series data as the turbidity extreme value. Subsequently, the extracted turbidity extreme value is synchronized to the power regulation branch of the collaborative control model. The power adjustment branch calculates the optimal ultrasonic power according to the association rules between the turbidity level and the ultrasonic power (such as 90% power for P level and 80% power for Q level). The adjusted ultrasonic power can effectively decompose the silicon powder particles and other stubborn dirt deposited at the bottom of the water body, improving the cleanliness of the water body. The jet volume optimization parameters and ultrasonic optimization power together constitute the collaborative optimization parameters, which act on the jet control unit and ultrasonic power control unit of the cleaning system respectively. For example, 10.8% of the jet volume is used to quickly remove floating dirt on the surface of the water body, and 90% of the ultrasonic power is used to deal with particles deposited at the bottom of the water body, ensuring the efficiency and accuracy of the entire cleaning process. Through this collaborative optimization process, the system terminal can comprehensively consider the pollution conditions on the surface and inside of the water body, dynamically adjust the cleaning parameters, and achieve comprehensive removal of dirt on the surface of the water body and fine particles at the bottom, while optimizing energy consumption and cleaning effects.

[0045] The operating parameters of the cleaning control module are updated with the collaborative optimization parameters as constraints.

[0046] In one embodiment, the collaborative optimization parameters (including jet volume optimization parameters and ultrasonic optimization power) generated by the collaborative control model are used as constraints to dynamically adjust the operating parameters of the cleaning control module to achieve accurate and efficient cleaning operations. During the cleaning process, the jet control unit and ultrasonic power control unit in the cleaning control module work together to ensure that the entire cleaning system can adapt to different pollution conditions by adjusting the operating parameters in real time, achieving efficient removal of floating dirt on the surface of the water body and sediment particles at the bottom, while maximizing energy consumption and cleaning effects.

[0047] Furthermore, taking the collaborative optimization parameters as constraints, the operation parameters of the cleaning control module are updated, and the method includes:

[0048] The jet volume optimization parameters are sent to the jet control unit of the cleaning control module; the ultrasonic optimization power is sent to the power control unit of the cleaning control module; when the jet volume of the jet control unit is dynamically adjusted with the jet volume optimization parameters as a constraint, the ultrasonic power of the power control unit is dynamically adjusted with the ultrasonic optimization power as a constraint.

[0049] Optionally, during the cleaning control process, the collaborative control model calculates the optimized parameter of the jet volume (for example, the jet volume is 10.8%), which is first sent to the jet control unit of the cleaning control module. The jet control unit dynamically adjusts the nozzle opening and the outlet pressure according to the parameter to keep the jet volume at the optimized value of 10.8% to quickly remove floating pollutants (such as bubbles, organic matter, and silicon powder clumps) on the surface of the water body. At the same time, the ultrasonic optimization power (for example, the power is 90%) generated by the collaborative control model is sent to the power control unit. After receiving the parameter, the power control unit adjusts the output power of the ultrasonic generator so that the ultrasonic emission intensity reaches the optimized value of 90%. This adjustment is aimed at fine particle pollutants (such as silicon powder particles) deposited at the bottom of the cleaning tank, and the particles are efficiently decomposed and removed through optimized ultrasonic energy. During operation, the jet control unit and the power control unit use the collaborative optimization parameters as constraints to maintain synchronous dynamic adjustment. When the jet control unit performs jet volume adjustment (such as fine-tuning the jet volume to between 10.5% and 11% based on real-time feedback), the power control unit will simultaneously respond to the ultrasonic power (such as adjusting the power output to between 89% and 91%) to ensure the synergy between the two and avoid the impact of a single parameter change on the cleaning effect. The cleaning system monitors the jet effect and ultrasonic cleaning effect in real time through sensors, and feeds the monitoring data back to the collaborative control model. The model further optimizes the parameter settings of the jet volume and ultrasonic power based on the latest dirt time series data and turbidity time series data to ensure that the entire cleaning process is always efficient and stable. Through this process, the cleaning control module can quickly remove floating dirt on the surface of the water body and thoroughly remove bottom sediment particles under the synergy of jet volume optimization parameters and ultrasonic optimization power, achieving comprehensive and efficient cleaning operations while effectively controlling energy consumption.

[0050] Further, the method comprises:

[0051] A cleaning control update window is preset; when the duration of the image capture of the cleaning tank by the visual sensor array with the image acquisition interval as a constraint reaches the cleaning control update window, the water body image information is updated; and the collaborative control model cyclically updates the operating parameters of the cleaning control module with the cleaning control update window as a constraint.

[0052] Preferably, the system terminal pre-sets a cleaning control update window according to the pollution characteristics of the cleaning tank and the performance requirements of the cleaning system. For example, setting the update window to 10 minutes means that a comprehensive cleaning parameter update is performed every 10 minutes. This window is a periodic constraint condition for the cleaning control module to adjust the operating parameters. During the cleaning operation, the visual sensor array monitors the cleaning tank in real time according to a preset image acquisition interval (for example, an image is acquired every 30 seconds). When the cumulative image acquisition time reaches the cleaning control update window (such as 10 minutes), a comprehensive update of the water body image information is triggered, including image sequences on the surface and inside of the water body. These updated image information are used to recalculate the dirt time series data and turbidity time series data to ensure that the analysis results reflect the latest cleaning status in real time. After receiving the updated dirt time series data and turbidity time series data, the collaborative control model uses the cleaning control update window as a periodic trigger condition to perform a new round of parameter optimization calculations. The model dynamically adjusts the output of the gas volume regulation branch and the power regulation branch based on the latest data. For example, the dirt coverage area is reduced from 3% to 1.5%, and the optimized parameters of the jet volume output by the gas volume regulation branch are adjusted from 10.8% to 7%. The gray value of the water body increases from 200 to 230, and the ultrasonic optimization power output by the power regulation branch is adjusted from 90% to 100%. The new optimization parameters calculated by the collaborative control model are sent to the jet control unit and the power control unit of the cleaning control module. These units dynamically adjust the operating status of the cleaning tank based on the new optimization parameters to adapt to the latest cleaning needs. The cleaning control update window is continuously cycled at a preset period. When the next round of update window begins, the system terminal collects a new round of water body image information again, and optimizes the operating parameters through the collaborative control model. This periodic cycle ensures that the cleaning system can always maintain efficient cleaning effects and energy utilization according to the dynamic changes of the actual pollution situation. Through this process, the intelligent operation parameter update based on time constraints is realized, and the cleaning operation is optimized in a periodic and dynamic manner, so that it can adapt to complex and changeable pollution conditions and always maintain efficient operation.

[0053] In summary, the embodiments of the present application have at least the following technical effects:

[0054] First, the image acquisition interval is preset, and the image acquisition interval is used as a constraint to control the visual sensor array to capture the image of the cleaning tank to obtain water image information, wherein the water image information includes a water surface image sequence and a water internal image sequence. Next, the dirt composition analysis is performed based on the water surface image sequence to obtain the dirt time series data, and the turbidity of the cleaning tank is graded according to the water internal image sequence to obtain the turbidity time series data. Further, a collaborative control model is pre-constructed, and then the dirt time series data and the turbidity time series data are synchronized to the collaborative control model for control analysis, and the collaborative optimization parameters are output. Finally, the operating parameters of the cleaning control module are updated with the collaborative optimization parameters as constraints. The technical problems of poor adaptability of the existing cleaning process and high incidence of silicon powder pollution when the silicon powder content is high are solved. By combining the control analysis of the collaborative control model, the cleaning control parameters are dynamically adjusted to achieve the technical effect of reducing the incidence of silicon powder pollution and improving the efficiency of the cleaning process.

[0055] Embodiment 2, based on the same inventive concept as the intelligent cleaning control method for reducing the incidence of silicon powder pollution in the previous embodiment, Figure 2 As shown, the present application provides an intelligent cleaning control system for reducing the incidence of silicon powder pollution, wherein the system includes:

[0056] Image capture component 11: preset image acquisition interval, and use the image acquisition interval as a constraint to control the visual sensor array to capture images of the cleaning tank, and obtain water body image information, wherein the water body image information includes a water body surface image sequence and a water body internal image sequence; dirt composition analysis component 12: based on the water body surface image sequence, dirt composition analysis is performed to obtain dirt time series data; turbidity grading component 13: turbidity grading of the cleaning tank is performed according to the water body internal image sequence to obtain turbidity time series data; model pre-construction component 14: pre-construct a collaborative control model; control analysis component 15: by synchronizing the dirt time series data and the turbidity time series data to the collaborative control model, control analysis is performed, and collaborative optimization parameters are output; operation parameter update component 16: using the collaborative optimization parameters as constraints, operation parameters of the cleaning control module are updated.

[0057] Furthermore, the dirt composition analysis component 12 is used to perform the following method:

[0058] Interactively obtain multiple sample pollution image sets of multiple sample water pollution; perform pollution area ratio directional annotation on the multiple sample pollution image sets to obtain multiple sample annotated image sets; use the multiple sample pollution image sets and the multiple sample annotated image sets as training data to perform directional training of a standard pollution recognition model to obtain multiple pollution proportion recognition branches; connect the multiple pollution proportion recognition branches in parallel to obtain a pollution proportion recognition model; synchronize the water body surface image sequence to the pollution proportion recognition model to perform pollution composition analysis to obtain pollution time series data.

[0059] Furthermore, the turbidity classification component 13 is used to perform the following method:

[0060] A water body grade analysis model is pre-constructed, wherein the water body grade analysis model includes a cascaded grayscale analysis model and a water body grade judgment module; a first water body internal image corresponding to a first time series is extracted from the water body internal image sequence; the first water body internal image is synchronized to the grayscale analysis model of the water body grade analysis model for analysis to obtain a first water body turbidity; the first water body turbidity is synchronized to the water body grade judgment module of the water body grade analysis model for analysis to obtain a first water body grade; and so on, the turbidity of the cleaning tank is graded by synchronizing the water body internal image sequence to the water body grade analysis model to obtain the turbidity time series data.

[0061] Furthermore, the turbidity classification component 13 is used to perform the following method:

[0062] Interactively obtain multiple sample water body turbidity images and multiple sample water body turbidity; use the multiple sample water body turbidity images and multiple sample water body turbidity as training data to complete the construction of the grayscale analysis model; interactively obtain multiple water body turbidity intervals of multiple water body grades; store the multiple water body grades and multiple water body turbidity intervals based on the knowledge graph to complete the construction of the water body grade judgment module; and complete the construction of the water body grade analysis model by cascading the grayscale analysis model and the water body grade judgment module.

[0063] Furthermore, the model pre-construction component 14 is used to perform the following method:

[0064] Interactively obtain multiple sample dirt percentage arrays and multiple sample gas volume adjustment values; perform multi-source regression analysis on the multiple sample dirt percentage arrays and the multiple sample gas volume adjustment values ​​to obtain a gas volume adjustment function; construct a gas volume adjustment branch based on the gas volume adjustment function; interactively obtain multiple sample power parameters and multiple groups of sample water body levels; use a table structure to associate and store the multiple sample power parameters and the multiple groups of sample water body levels to complete the construction of the power adjustment branch; connect the gas volume adjustment branch and the power adjustment branch in parallel to complete the construction of the collaborative control model.

[0065] Furthermore, the control analysis component 15 is used to execute the following method:

[0066] The pollution time series data is synchronized to the air volume regulation branch of the collaborative control model to solve the jet volume and obtain multiple alternative optimization parameters; the multiple alternative optimization parameters are serialized, and the maximum value is extracted according to the sorting result to obtain the jet volume optimization parameter; the turbidity time series data is serialized, and the maximum value is extracted according to the sorting result to obtain the turbidity extreme value; the turbidity extreme value is synchronized to the power regulation branch of the collaborative control model to solve the power optimization and output the ultrasonic optimization power; the jet volume optimization parameter and the ultrasonic optimization power constitute the collaborative optimization parameter.

[0067] Furthermore, the operating parameter updating component 16 is used to execute the following method:

[0068] The jet volume optimization parameters are sent to the jet control unit of the cleaning control module; the ultrasonic optimization power is sent to the power control unit of the cleaning control module; when the jet volume of the jet control unit is dynamically adjusted with the jet volume optimization parameters as a constraint, the ultrasonic power of the power control unit is dynamically adjusted with the ultrasonic optimization power as a constraint.

[0069] Furthermore, the operating parameter updating component 16 is used to execute the following method:

[0070] A cleaning control update window is preset; when the duration of the image capture of the cleaning tank by the visual sensor array with the image acquisition interval as a constraint reaches the cleaning control update window, the water body image information is updated; and the collaborative control model cyclically updates the operating parameters of the cleaning control module with the cleaning control update window as a constraint.

[0071] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0072] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0073] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An intelligent cleaning control method for reducing the incidence of silicon powder pollution, characterized in that: The method comprises: Preset an image acquisition interval, and use the image acquisition interval as a constraint to control the visual sensor array to capture images of the cleaning tank to obtain water body image information, wherein the water body image information includes a water body surface image sequence and a water body internal image sequence; Performing a dirt composition analysis based on the water body surface image sequence to obtain dirt time series data; Classifying the turbidity of the cleaning tank according to the internal image sequence of the water body to obtain turbidity time series data; Pre-built collaborative control models; The pollution time series data and the turbidity time series data are synchronized to the collaborative control model to perform control analysis and output collaborative optimization parameters; The operating parameters of the cleaning control module are updated with the collaborative optimization parameters as constraints.

2. The intelligent cleaning control method for reducing the incidence of silicon powder pollution according to claim 1, characterized in that: Based on the water body surface image sequence, a dirt composition analysis is performed to obtain dirt time series data, and the method includes: Interactively obtain multiple sample pollution image sets of multiple sample water pollution; Performing directional marking of the dirt area ratio on the multiple sample dirt image sets to obtain multiple sample marked image sets; Using the plurality of sample dirt image sets and the plurality of sample annotated image sets as training data, performing directional training of a standard dirt recognition model to obtain a plurality of dirt proportion recognition branches; Connecting the plurality of dirt proportion recognition branches in parallel to obtain a dirt proportion recognition model; The water body surface image sequence is synchronized to the dirt proportion identification model to perform dirt composition analysis and obtain dirt time series data.

3. The intelligent cleaning control method for reducing the incidence of silicon powder pollution according to claim 2, characterized in that: The turbidity of the cleaning tank is graded according to the internal image sequence of the water body to obtain turbidity time series data, and the method includes: Pre-constructing a water body grade analysis model, wherein the water body grade analysis model includes a cascaded grayscale analysis model and a water body grade judgment module; Extracting a first water body interior image corresponding to a first time sequence from the water body interior image sequence; Synchronizing the first water body internal image to the grayscale analysis model of the water body grade analysis model to obtain the turbidity of the first water body; Synchronizing the first water body turbidity to the water body grade judgment module of the water body grade analysis model for analysis to obtain a first water body grade; By analogy, the turbidity of the cleaning tank is graded by synchronizing the image sequence inside the water body to the water body grade analysis model to obtain the turbidity time series data.

4. The intelligent cleaning control method for reducing the incidence of silicon powder pollution according to claim 3, characterized in that: A water body grade analysis model is pre-constructed, the method comprising: Interactively obtain multiple sample water pollution images and multiple sample water pollution levels; Using the plurality of sample water pollution images and the plurality of sample water pollution levels as training data, completing the construction of the grayscale analysis model; Interactively obtain multiple water turbidity intervals of multiple water levels; The plurality of water body grades and the plurality of water body turbidity intervals are stored in association with each other based on the knowledge graph, thereby completing the construction of the water body grade judgment module; The construction of the water body grade analysis model is completed by cascading the grayscale analysis model and the water body grade judgment module.

5. The intelligent cleaning control method for reducing the incidence of silicon powder pollution according to claim 4, characterized in that: Pre-building a collaborative control model, the method comprising: Interactively obtain multiple sample dirt percentage arrays and multiple sample gas volume adjustment values; Performing multi-source regression analysis on the plurality of sample dirt percentage arrays and the plurality of sample gas volume adjustment values ​​to obtain a gas volume adjustment function; Constructing a gas volume regulation branch based on the gas volume regulation function; Interactively obtain multiple sample power parameters and multiple groups of sample water body grades; A table structure is used to associate and store the plurality of sample power parameters and the plurality of groups of sample water body grades, so as to complete the construction of the power regulation branch; The gas volume regulating branch and the power regulating branch are connected in parallel to complete the construction of the collaborative control model.

6. The intelligent cleaning control method for reducing the incidence of silicon powder pollution according to claim 5, characterized in that: The method includes: synchronizing the pollution time series data and the turbidity time series data to the collaborative control model for control analysis and outputting collaborative optimization parameters. The pollutant time series data is synchronized to the air volume adjustment branch of the collaborative control model to solve the air injection volume, thereby obtaining a plurality of candidate optimization parameters; Serializing the plurality of candidate optimization parameters, and extracting maximum values ​​according to the sorting results to obtain the jet flow optimization parameters; Serializing the pollution degree time series data, and extracting the maximum value according to the sorting result to obtain the pollution degree extreme value; Synchronizing the extreme value of the pollution degree to the power regulation branch of the cooperative control model to perform power optimization and solve, and outputting ultrasonic optimized power; The jet volume optimization parameter and the ultrasonic wave optimization power constitute the coordinated optimization parameter.

7. The intelligent cleaning control method for reducing the incidence of silicon powder pollution according to claim 6, characterized in that: Taking the collaborative optimization parameters as constraints, updating the operating parameters of the cleaning control module, the method includes: Sending the jet volume optimization parameter to the jet control unit of the cleaning control module; sending the ultrasonic optimized power to a power control unit of the cleaning control module; When the jet volume of the jet control unit is dynamically adjusted with the jet volume optimization parameter as a constraint, the ultrasonic power of the power control unit is dynamically adjusted with the ultrasonic optimization power as a constraint.

8. The intelligent cleaning control method for reducing the incidence of silicon powder pollution according to claim 1, characterized in that: The method comprises: Preset cleaning control update window; When the duration of the image capture of the cleaning tank by the visual sensor array with the image acquisition interval as a constraint reaches the cleaning control update window, the water body image information is updated; The collaborative control model cyclically updates the operating parameters of the cleaning control module based on the cleaning control update window as a constraint.

9. An intelligent cleaning control system for reducing the incidence of silicon powder pollution, characterized in that: The intelligent cleaning control method for reducing the incidence of silicon powder pollution according to any one of claims 1 to 8 is used to implement the system comprising: Image capture component: preset an image acquisition interval, and use the image acquisition interval as a constraint to control the visual sensor array to capture images of the cleaning tank to obtain water body image information, wherein the water body image information includes a water body surface image sequence and a water body internal image sequence; A dirt composition analysis component: performs dirt composition analysis based on the water body surface image sequence to obtain dirt time series data; Turbidity classification component: classifies the turbidity of the cleaning tank according to the internal image sequence of the water body to obtain turbidity time series data; Model pre-built components: pre-built collaborative control model; Control analysis component: synchronizing the dirt time series data and the turbidity time series data to the collaborative control model to perform control analysis and output collaborative optimization parameters; Operation parameter updating component: updating the operation parameters of the cleaning control module based on the collaborative optimization parameters as constraints.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, an intelligent cleaning control method for reducing the occurrence rate of silicon powder contamination as described in any one of claims 1 to 8 is implemented.

Images