An adaptive parameter adjustment method for a paint production plant

Abstract

The application provides a self-adaptive parameter adjustment method of a paint production device, and relates to the technical field of parameter control. The method comprises the following steps: obtaining a stirring part of the paint production device, and setting a particle sensor in a paint mixing cavity. Particle sensing data, including size, density and distribution, are collected. Particle attribute, stirring mode and material information are obtained. Stirring part damage is evaluated, and a particle damage index is obtained. A stirring control module is connected, and self-adaptive identification control parameters are outputted to minimize the damage index. The stirring part is controlled according to the control parameters. The application can solve the technical problems of low stirring efficiency, frequent particle damage, further influence on the quality and performance of the paint, and production efficiency caused by the inability of real-time monitoring and self-adaptive adjustment of the stirring process in the prior art. The application realizes automatic optimization of the stirring process, reduces particle damage, improves production efficiency, reduces manual intervention, and improves the intelligent level of production.

Description

Technical Field

[0001] This application relates to the field of parameter control technology, and in particular to an adaptive parameter adjustment method for coating production equipment. Background Technology

[0002] In the coating production process, the quality and performance of coatings are affected by various factors, such as the quality and ratio of raw materials and the production process. To ensure coating quality and performance, precise parameter adjustment of coating production equipment is necessary. However, traditional methods for adjusting coating production equipment parameters often rely on human experience, which introduces subjectivity and uncertainty, and cannot adapt to changes in the production process in real time. Therefore, researching an adaptive parameter adjustment method for coating production equipment has significant practical implications.

[0003] Currently, existing paint production equipment often lacks a sophisticated parameter adjustment mechanism during the mixing process.

[0004] In summary, existing technologies suffer from low mixing efficiency and frequent particle damage due to the inability to monitor and adaptively adjust the mixing process in real time, which further affects the quality and performance of coatings and production efficiency. Summary of the Invention

[0005] The purpose of this application is to provide an adaptive parameter adjustment method for coating production equipment, in order to solve the technical problems of low stirring efficiency, frequent particle damage, and further impact on coating quality and performance, as well as production efficiency, caused by the inability to monitor and adaptively adjust the stirring process in real time in the existing technology.

[0006] In view of the above problems, this application provides an adaptive parameter adjustment method for coating production equipment.

[0007] This application provides an adaptive parameter adjustment method for a coating production equipment. The method includes: acquiring a stirring component of the coating production equipment, the stirring component acting on a coating mixing chamber; setting a particle sensor, wherein the particle sensor is located in the coating mixing chamber; acquiring a particle sensing dataset based on the particle sensor, including particle size, particle density, and particle distribution; acquiring particle attribute information at the feed inlet, as well as stirring mode information and surface material information of the stirring component; performing a damage assessment on the stirring component based on the particle sensing dataset, the particle attribute information, the stirring mode information, and the surface material information, obtaining a particle damage index; connecting to a stirring control module, adaptively identifying the control parameters of the stirring control module with minimizing the particle damage index as the adaptive target, outputting stirring adjustment parameters, and controlling the stirring component to stir according to the stirring adjustment parameters.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: By acquiring the agitator of the coating production equipment, which acts on the coating mixing chamber; setting a particle sensor in the coating mixing chamber; collecting sensor data to obtain a particle sensing dataset, including particle size, particle density, and particle distribution; acquiring particle attribute information from the feed inlet, as well as the agitator's agitation method and surface material information; assessing the damage of the agitator based on the particle sensing dataset, particle attribute information, agitation method information, and surface material information to obtain a particle damage index; connecting to a stirring control module, adaptively identifying the control parameters of the stirring control module with minimizing the particle damage index as the adaptive target, outputting stirring adjustment parameters, and controlling the agitator to stir according to the stirring adjustment parameters, this effectively solves the technical problem of low stirring efficiency and frequent particle damage caused by the inability to monitor and adaptively adjust the stirring process in real time in existing technologies, which further affects the quality and performance of coatings and production efficiency. This achieves automatic optimization of the stirring process, reduces particle damage, improves production efficiency, reduces manual intervention, and improves the level of intelligent production.

[0009] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0011] Figure 1 This is a flowchart illustrating an adaptive parameter adjustment method for a coating production equipment according to this application. Figure 2 This is a schematic diagram of the damage assessment process in an adaptive parameter adjustment method for a coating production equipment according to this application. Detailed Implementation

[0012] This application provides an adaptive parameter adjustment method for coating production equipment, which solves the technical problems of low stirring efficiency and frequent particle damage caused by the inability to monitor and adaptively adjust the stirring process in real time in the prior art, which further affects the quality and performance of coatings and production efficiency. It realizes automatic optimization of the stirring process, reduces particle damage, improves production efficiency, reduces manual intervention, and improves the level of intelligent production.

[0013] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0014] Example 1 Please see the appendix Figure 1 This application provides an adaptive parameter adjustment method for coating production equipment, wherein the method specifically includes the following steps: S1: Obtain the agitator of the coating production equipment, wherein the agitator acts on the coating mixing chamber.

[0015] Specifically, the equipment's agitator components include an agitator shaft, driven by a motor, capable of rotation and reciprocating up and down. An agitator beam, mounted perpendicularly to one end of the agitator shaft, is extended and retractable by a power mechanism. An agitator section, located at the end of the agitator beam, has a trapezoidal longitudinal section; its long side connects to the agitator beam, and its short side mates with a through-hole in the coating mixing chamber. A discharge channel, located within the agitator section, communicates with the agitator shaft and agitator beam, forming a passageway for materials to pass through.

[0016] S2: A particle sensor is provided, wherein the particle sensor is disposed in the coating mixing chamber.

[0017] Specifically, select a suitable particle sensor based on the size of the paint mixing chamber, the characteristics of the paint, and the production environment. Particle sensors can be laser particle counters, microwave sensors, ultrasonic sensors, or other types, capable of measuring parameters such as particle distribution, size, concentration, and velocity. Choose a suitable location within the paint mixing chamber to install the particle sensor. This location should represent the overall mixing situation within the chamber, typically near the agitator, but avoiding direct interference from the agitator. Secure the particle sensor to the mixing chamber using a bracket, clamp, or other fixing device. Ensure the sensor is firmly fixed and will not move due to vibrations during agitation. After installation, calibrate the particle sensor to ensure the accuracy of its measurement data. Calibration can be performed according to the sensor manufacturer's guidelines and may require the use of standard particle samples. Configure the sensor to acquire particle data in real time.

[0018] S3: Collect sensing data based on the particle sensor to obtain a particle sensing dataset, including particle size, particle density, and particle distribution.

[0019] Specifically, ensure the particle sensor is correctly installed and calibrated. Configure the sensor to collect specific types of particle data, such as particle size, particle density, and particle distribution. During coating mixing, activate the particle sensor to begin real-time data acquisition. The sensor monitors the particle state within the mixing chamber and converts it into electrical signals. The data collected by the sensor is recorded in a dataset. This dataset includes the size, shape, density of each particle, and their distribution within the mixing chamber. The acquired raw data undergoes preprocessing, including data cleaning, outlier removal, data transformation (e.g., conversion from analog to digital signals), and data compression. Statistical methods or machine learning algorithms are used to analyze the particle dataset to identify particle characteristics and trends.

[0020] S4: Obtain particle attribute information from the feed inlet, as well as the stirring method information and surface material information of the stirring component.

[0021] Specifically, samples are taken from the feed inlet and analyzed using particle size analyzers, densitometers, and microscopes to obtain properties such as particle size, shape, density, and chemical composition. Online sensors, such as particle size sensors and concentration sensors, are installed at the feed inlet to monitor particle properties in real time and record process parameters such as stirring speed, stirring time, and stirring path. These parameters are typically determined during equipment commissioning and can be adjusted according to production needs. Simulation tests are conducted to evaluate the impact of different stirring methods, such as clockwise / counterclockwise stirring, intermittent stirring, and continuous stirring, on the coating mixing effect to determine the optimal stirring method. Big data analysis is used to examine the manufacturing material specifications of the stirring components, understanding their composition, hardness, wear resistance, and other characteristics. The surface treatment methods of the stirring components, such as coating type and polishing degree, are recorded; this information affects the contact effect and wear resistance between the stirring components and the coating raw materials. A data management system, such as ERP or MES, is used to integrate particle property information, stirring method information, and surface material information for easy querying and analysis.

[0022] S5: Based on the particle sensing dataset, the particle attribute information, the stirring method information, and the surface material information, perform a damage assessment on the stirring component to obtain particle damage indices.

[0023] Specifically, based on the material properties of the mixing component and its mechanical behavior during mixing, a physical or mathematical model of the component's damage is established. This model should be able to predict the wear and damage of the mixing component under specific operating conditions. Particle sensing datasets are used to analyze particle behavior during mixing, such as particle breakage, deformation, or agglomeration. This data is combined with particle attribute information to assess the potential damage to particles during mixing. Statistical analysis and data mining techniques are used to identify the relationship between particle damage and mixing component damage. This includes using correlation analysis, regression analysis, or machine learning algorithms to establish damage indices. One or more particle damage indices are calculated; these indices can be quantitative values ​​representing the degree of influence of mixing component damage on particle damage.

[0024] S6: Connect to the stirring control module, adaptively identify the control parameters of the stirring control module with minimizing the particle damage index as the adaptive target, output stirring adjustment parameters, and control the stirring component to stir according to the stirring adjustment parameters.

[0025] Specifically, this involves ensuring that particle sensor data is transmitted to the stirring control module in real time. This connection is established through hardware links and software communication protocol settings. An adaptive control model is built using particle damage indicators as feedback. This model predicts and adjusts stirring parameters based on the particle sensor dataset and particle attribute information. Real-time data analysis identifies key control parameters affecting particle damage, such as stirring speed, stirring time, and stirring path. Minimizing the particle damage indicator is set as the objective of the adaptive control. This objective guides the adjustment of control system parameters to optimize the stirring process. The parameters of the stirring control module are automatically adjusted using PID control, fuzzy logic control, or machine learning algorithms. The parameters of the stirring control module are adjusted based on the adaptive control model and recommendations. These parameters directly affect the operating status of the stirred components. The control system monitors the particle damage indicator in real time and automatically adjusts the stirring parameters according to changes in the indicator, ensuring that the stirring process is always in an optimal state.

[0026] Furthermore, such as Figure 2 As shown, step S5 of this application further includes: Based on the particle attribute information, particle hardness attribute information is identified; using the particle hardness attribute information and the particle sensing dataset as input variables, the stirring method information and the surface material information as quantitative inputs, and the particle damage identification information as the response output information, a particle damage assessment model is trained to obtain particle damage indicators; and the stirring component is damaged based on the particle damage assessment model.

[0027] Specifically, relevant features, such as particle size, shape, and density, are extracted from the particle sensing dataset. Based on particle attribute information, the hardness attribute of the particles is identified and quantified. Agitation method information, such as agitation speed, agitation time, and agitation path, as well as surface material information, such as the hardness of the agitated component and coating type, are collected. Labeling standards for particle damage indicators are defined based on historical data. For example, damage levels can be defined based on particle breakage rate and deformation degree. Appropriate machine learning or deep learning models are selected to train the particle damage assessment model, including support vector machines, random forests, and neural networks. The particle hardness attribute information and particle sensing dataset are used as input variables, agitation method information and surface material information are used as quantitative inputs, and particle damage labeling information is used as the response output to train the particle damage assessment model. Model performance is optimized by adjusting model parameters and architecture until the model can accurately predict particle damage indicators. Independent test sets are used to verify the model's accuracy, generalization ability, and robustness. Model performance is evaluated using methods such as cross-validation, confusion matrix, and ROC curves. The trained particle damage assessment model is applied to the actual production process to perform real-time damage assessment of the agitated component. Based on the model's output, adjust the mixing parameters or take maintenance measures to reduce particle damage and wear on the mixing components.

[0028] Furthermore, this application also includes: Collect the time-hardness change curve of particles dissolved in liquid medium; optimize the particle damage assessment model based on the time-hardness change curve to obtain the optimized particle damage assessment model; record the particle stirring time, input the particle stirring time into the optimized particle damage assessment model, and output the optimized particle damage index.

[0029] Specifically, the hardness of the particles is measured periodically using a hardness testing instrument. Particle hardness data at different time points are recorded to establish a time-series hardness variation curve. The collected time-series hardness data is cleaned and preprocessed to remove outliers and noise. The time-series hardness variation curve is used as new training data and input into the particle damage assessment model. The model is retrained or fine-tuned using the new data to optimize its performance and accuracy. The stirring time for each batch of particles is recorded. The stirring time data is input into the optimized particle damage assessment model. Based on the optimized model, a particle damage index is output, which considers the time-series hardness variation of particles in the liquid medium. These indices are used to assess the degree of particle damage during stirring, and stirring parameters or other measures are taken accordingly to reduce damage.

[0030] Furthermore, this application also includes: A feed record queue is generated based on the feed inlet, wherein the feed record queue is connected to the particle damage assessment model; a timer is set, wherein the timer is configured with a preset stirring duration based on each feed item in the feed record queue, wherein each feed item corresponds to a preset stirring duration, which is used to call the particle damage assessment model for damage assessment within the preset stirring duration; the real-time stirring duration of each feed item is recorded, and the real-time stirring duration is compared with the preset stirring duration to update the feed record queue.

[0031] Specifically, a data structure, such as a queue, is created to record all feed items at the inlet. Each feed item should include information such as feed time, particle type, and particle attributes. The feed record queue is connected to a particle damage assessment model to ensure that the model can receive feed information and perform damage assessment accordingly. A preset mixing duration is configured for each feed item, based on particle type and attributes, and the expected mixing effect. A timer is used to periodically call the particle damage assessment model to perform damage assessment within the preset mixing duration. During mixing, the mixing duration of each feed item is recorded in real time, through a mixing control module or additional sensors. The real-time mixing duration is compared with the preset mixing duration to assess whether the mixing process is proceeding as planned. If the real-time mixing duration exceeds or falls short of the preset duration, it indicates a problem with the mixing process, requiring further investigation and adjustment. The feed record queue is updated based on the real-time mixing duration and damage assessment results. Updates include adjusting the preset mixing duration, recording anomalies, and marking batches requiring special attention.

[0032] Furthermore, this application also includes: Based on the real-time updated feed record queue, multiple particle types for stirring are obtained; multiple particle damage indices are obtained for each of the multiple particle types for stirring, the multiple particle damage indices are fitted, and a particle damage fitting index is output; with minimizing the particle damage fitting index as the adaptive objective, stirring adjustment parameters are output.

[0033] Specifically, information on multiple particle types is extracted from a real-time updated feed log queue. Each particle type possesses different physical and chemical properties, such as hardness, shape, and density. For each particle type, a particle damage assessment model is used to calculate particle damage indices. These indices reflect the degree of damage to different particle types during the mixing process. Statistical or machine learning methods are used to fit multiple particle damage indices. The goal of this fitting is to find an index that comprehensively reflects the damage degree of all particle types—the particle damage fitting index. This particle damage fitting index can serve as a comprehensive indicator to evaluate the overall performance of the current mixing process. This index can be used for monitoring purposes or as input to an adaptive control system. Minimizing the particle damage fitting index is the objective of the adaptive control system. By adjusting mixing parameters, such as mixing speed, mixing time, and mixing path, optimal mixing conditions are found to reduce particle damage. Based on the particle damage fitting index, the adaptive control system outputs mixing adjustment parameters. These parameters are used to control the operation of the mixing components to achieve optimal mixing effect and minimal particle damage.

[0034] Furthermore, step S6 of this application also includes: The control parameters of the stirring control module include stirring duration, stirring rate, and stirring radius; an objective function is established with minimizing the particle damage index as the adaptive objective; the stirring duration, stirring rate, and stirring radius are used as a set of control parameters, and adaptive iterative optimization is performed according to the objective function until the optimization converges, and the optimization result is output, which includes the stirring adjustment parameters obtained by optimization.

[0035] Specifically, an objective function is defined to minimize the particle damage index. This objective function may be a composite function combining multiple particle damage indices, or a weighted average function that weights the damage indices for different particle types. The control parameters to be optimized are determined, including stirring time, stirring rate, and stirring radius. These parameters directly affect particle behavior and the degree of damage during stirring. Optimization algorithms, such as gradient descent, genetic algorithms, and particle swarm optimization, are used to adaptively iteratively optimize the control parameters. In each iteration, the optimization algorithm adjusts the values ​​of the control parameters based on feedback from the objective function. The iteration process continues until a predetermined convergence criterion is reached, such as the objective function value no longer decreasing significantly, or the change being less than a certain threshold. The convergence criterion ensures the stability and reliability of the optimization results. Once the optimization converges, the optimized stirring adjustment parameters are output. These parameters are the optimal control parameters for the stirring control module, minimizing the particle damage index.

[0036] Furthermore, this application also includes: The coating mixing chamber is subjected to particle deposition detection, and the particle deposition detection result is obtained; if the particle deposition detection result returns 1, a stirring depth adjustment command is obtained, and the depth adjustment module receives the stirring depth adjustment command and controls the stirring component to perform deep stirring.

[0037] Specifically, appropriate sensors or detection equipment are used to detect particle deposition in the coating mixing chamber. Detection equipment includes laser sensors, ultrasonic sensors, or other devices capable of detecting particle deposition. The detection result is a binary signal, for example, 1 indicates particle deposition detected, and 0 indicates no particle deposition detected. Particle deposition detection results are obtained periodically or continuously from the detection equipment. If the particle deposition detection result returns 1, it indicates that particle deposition has been detected and action is required. If the detection result is 0, the particles in the mixing chamber are mixing normally and no special treatment is needed. When particle deposition is detected, a stirring depth adjustment command is generated. The depth adjustment module receives the stirring depth adjustment command from the control system. According to the received command, the depth adjustment module controls the agitator to adjust its stirring depth. Deep stirring is to break up particle deposition and ensure uniform particle distribution in the mixing chamber.

[0038] Furthermore, this application also includes: Obtain the sensing range of the particle sensor; set up a continuous particle sensor according to the sensing range, wherein the continuous particle sensor is vertically and continuously arranged from top to bottom in the coating mixing chamber, and there is a vertical distance between every two particle sensors; obtain the continuous particle sensing dataset of the continuous particle sensor; perform particle deposition detection based on the continuous particle sensing dataset, and obtain the particle deposition detection result.

[0039] Specifically, the effective detection range of the particle sensors is determined, i.e., the range of particle size and density that the sensors can accurately detect. Based on the sensing range, multiple particle sensors are vertically and continuously installed from top to bottom within the coating mixing chamber. The position of each sensor should ensure that it covers the entire mixing chamber, and a certain vertical distance is maintained between sensors to avoid overlap. The continuous particle sensors are activated to begin real-time particle data acquisition. Each sensor continuously collects parameters such as particle distribution, size, and density. Using the continuous particle sensing dataset, the distribution of particles within the mixing chamber is analyzed. Analysis of the continuous data can detect signs of particle deposition, such as particle accumulation at the bottom or sidewalls of the mixing chamber. Based on the analysis results, it is determined whether particle deposition has occurred. If particle deposition is detected, a particle deposition detection result is generated, which is a binary signal, such as 1 indicating detected particle deposition and 0 indicating no detected particle deposition.

[0040] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0041] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. An adaptive parameter adjustment method for paint production equipment, characterized in that, The method includes: Obtain a stirring component from a paint production equipment, wherein the stirring component acts on the paint mixing chamber; A particle sensor is provided, wherein the particle sensor is disposed in the coating mixing chamber; The particle sensor is used to collect sensing data to obtain a particle sensing dataset, including particle size, particle density, and particle distribution. Obtain particle attribute information from the feed inlet, as well as the stirring method information and surface material information of the stirring component; The particle damage index is obtained by performing a damage assessment on the stirring component based on the particle sensing dataset, the particle attribute information, the stirring method information, and the surface material information. Connect to the stirring control module, and adaptively identify the control parameters of the stirring control module with the goal of minimizing the particle damage index, output stirring adjustment parameters, and control the stirring component to stir according to the stirring adjustment parameters; The method for assessing damage to the stirring component based on the particle sensing dataset, the particle attribute information, the stirring method information, and the surface material information includes: Based on the particle attribute information, identify the particle hardness attribute information; Using the particle hardness attribute information and the particle sensing dataset as input variables, the stirring method information and the surface material information as quantitative inputs, and the particle damage identification information as response output information, a particle damage assessment model is trained to obtain particle damage indices. The damage to the agitator is assessed according to the particle damage assessment model. Collect time-hardness variation curves of particles dissolved in liquid media; The particle damage assessment model is optimized by feedback based on the time-hardness change curve to obtain the optimized particle damage assessment model. Record the particle stirring time, input the particle stirring time into the optimized particle damage assessment model, and output the optimized particle damage index. A feed record queue is generated based on the feed inlet, wherein the feed record queue is connected to the particle damage assessment model; A timer is set up, which is configured with a preset stirring duration according to each feed item in the feed record queue. Each feed item corresponds to a preset stirring duration, which is used to call the particle damage assessment model to perform damage assessment within the preset stirring duration. Record the real-time mixing time of each feed item, compare the real-time mixing time with the preset mixing time, and update the feed record queue. The method includes adaptively identifying the control parameters of the stirring control module with minimizing the particle damage index as the adaptive objective, and outputting stirring adjustment parameters. The control parameters of the stirring control module include stirring duration, stirring rate, and stirring radius; An objective function is established with minimizing the particle damage index as the adaptive objective; The stirring time, stirring rate, and stirring radius are used as a set of control parameters. Adaptive iterative optimization is performed according to the objective function until the optimization converges, and the optimization result is output. The optimization result includes the stirring adjustment parameters obtained by optimization.

2. The adaptive parameter adjustment method for a coating production equipment as described in claim 1, characterized in that, The method further includes: Based on the real-time updated feed record queue, obtain multiple types of stirred particles; Multiple particle damage indices are obtained based on the multiple types of stirred particles, the multiple particle damage indices are fitted, and the particle damage fitting index is output. The stirring adjustment parameters are output with the goal of minimizing the particle damage fitting index.

3. The adaptive parameter adjustment method for a coating production equipment as described in claim 1, characterized in that, The stirring component includes a depth adjustment module, comprising: The coating mixing chamber was subjected to particle deposition detection to obtain the particle deposition detection results; If the particle deposition detection result returns 1, a stirring depth adjustment command is obtained. The depth adjustment module receives the stirring depth adjustment command and controls the stirring component to perform deep stirring.

4. The adaptive parameter adjustment method for a coating production equipment as described in claim 3, characterized in that, The methods include: Obtain the sensing range of the particle sensor; A continuous particle sensor is set according to the sensing range, wherein the continuous particle sensor is vertically and continuously arranged from top to bottom in the paint mixing chamber, and there is a vertical distance between every two particle sensors; Obtain the continuous particle sensing dataset of the continuous particle sensor; Particle deposition detection is performed based on the continuous particle sensing dataset to obtain particle deposition detection results.

Images