Electrostatic agent accurate metering and coating system based on automatic control

Abstract

The invention relates to the technical field of industrial automatic control, and discloses an electrostatic agent accurate metering and coating system based on automatic control, which comprises a data acquisition and monitoring module used for acquiring parameters such as electrostatic agent flow, liquid spraying pressure, material flow velocity and environmental disturbance; the data processing and dynamic modeling module is used for establishing a dynamic model of electrostatic agent flow and coating uniformity according to the parameters acquired by the data acquisition and monitoring module and outputting a system state predicted value; and the sliding mode control module is connected with the data processing and dynamic modeling module and is used for controlling the flow error. According to the invention, real-time monitoring of the coating concentration and uniformity is realized through the coating uniformity monitoring and exception handling module, and the influence of external disturbance and equipment errors on the coating uniformity can be effectively inhibited in combination with dynamic adjustment of the sliding mode control module on the electrostatic agent spraying flow, so that the accuracy and consistency of the coating are remarkably improved, and the production efficiency is improved. And the high-quality coating process requirements are met.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial automation control, and in particular to an electrostatic agent precise metering and coating system based on automation control. Background Art

[0002] Coating technology has been widely used in many industrial fields, especially in the fields of automobile manufacturing, aerospace and electronic product coating. The uniformity and quality of the coating directly affect the performance and service life of the product. In order to ensure the functionality and decorative requirements of the coating, electrostatic spraying technology has gradually become the mainstream of the industry due to its efficient material utilization and coating consistency. This technology evenly distributes the coating material on the target surface through precise control of the electrostatic agent and the spray flow rate, thus forming a high-quality coating.

[0003] Existing electrostatic spray systems generally use fixed parameter settings or simple proportional control methods to adjust the spray flow rate and coating concentration. These systems usually rely on traditional open-loop or single feedback control methods to achieve coating uniformity by manually adjusting parameters such as spray pressure, valve opening and coating distance. However, these methods have poor adaptability to environmental disturbances and nonlinear behavior of the system, which can easily lead to unstable coating concentration, thus affecting product quality.

[0004] In the prior art, although some systems attempt to improve coating uniformity by adding monitoring modules or improving control algorithms, they still have difficulty coping with coating quality control issues in complex environments due to the lack of real-time dynamic modeling capabilities and the accuracy of closed-loop control. For example, when external disturbances or process parameters change, traditional control systems cannot respond quickly and dynamically adjust the spray parameters, resulting in coating concentration deviations exceeding the allowable range. Therefore, the prior art urgently needs an automated control system that can monitor coating concentration and uniformity in real time, and dynamically adjust the spray flow and pressure according to the concentration error, so as to further improve the coating quality and system adaptability. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides an electrostatic agent precise metering and coating system based on automated control. The prior art is unable to monitor the coating uniformity in real time under complex environments and dynamically adjust the spray flow and pressure according to the concentration error.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an electrostatic agent precise metering and coating system based on automatic control, comprising: Data acquisition and monitoring module, used to collect parameters such as electrostatic agent flow, spray pressure, material flow rate and environmental disturbance; A data processing and dynamic modeling module, used to establish a dynamic model of electrostatic agent flow and coating uniformity according to the parameters collected by the data collection and monitoring module, and output a system state prediction value; A sliding mode control module, connected to the data processing and dynamic modeling module, for calculating a dynamic control signal of the electrostatic agent flow rate based on the flow rate error; An actuator and feedback control module is connected to the sliding mode control module, and is used to receive control signals and dynamically adjust the electrostatic agent spray flow rate and pressure, and feed back the adjustment results to the data acquisition and monitoring module; The coating uniformity monitoring and exception handling module is used to monitor the coating concentration and uniformity in real time, trigger the adjustment signal according to the concentration error, and optimize the spray flow rate.

[0007] Preferably, the data processing and dynamic modeling module includes a Kalman filter and an extended state observer, which are used to filter out random noise in the collected data and dynamically estimate disturbances in the electrostatic agent flow.

[0008] Preferably, the sliding mode control module realizes the generation of the control signal through the following steps: The error of the electrostatic agent spray flow rate is calculated, and the difference between the target flow rate and the actual flow rate is used as the control input; generating a sliding surface according to the flow error, wherein the sliding surface is calculated by the flow error and its integral; The equivalent control law and the approaching control law are combined to generate the dynamic control signal of the electrostatic agent spray flow rate.

[0009] Preferably, the actuator and feedback control module includes: A valve actuator, used for adjusting the opening of the electrostatic agent valve according to the control signal output by the sliding mode control module; Spray pressure regulator, used to dynamically optimize spray pressure; The feedback sensor is used to monitor the real-time flow rate and concentration of the spray liquid and feed the monitoring data back to the data acquisition and monitoring module.

[0010] Preferably, the coating uniformity monitoring and exception handling module is used to calculate the coating concentration in real time, monitor the coating uniformity through the ratio of material flow rate to spray flow rate, and trigger automatic adjustment of the reference flow value or control parameter when the concentration error exceeds the set threshold.

[0011] Preferably, the coating uniformity monitoring and abnormality handling module includes a concentration calculation unit and an abnormality detection unit, the concentration calculation unit is used to calculate the coating concentration based on the spray flow rate and the material flow rate, and the abnormality detection unit is used to monitor the concentration error and trigger an alarm signal or adjust parameters.

[0012] Preferably, the data acquisition and monitoring module includes: Electrostatic agent flow sensor, used to measure the spray flow rate; Pressure sensor, used to collect the spray pressure and its dynamic changes; Flow rate sensor, used to collect material conveying flow rate; Environmental disturbance sensors are used to monitor the effects of environmental vibration and temperature on electrostatic agents.

[0013] Preferably, the model established by the dynamic modeling module includes: The electrostatic agent flow model expresses the flow rate as a function of the injection pressure, valve opening and system resistance; Coating uniformity model that expresses coating concentration as the ratio of spray flow rate to material flow rate.

[0014] Preferably, the sliding mode control module is used to optimize the dynamic response speed of the flow error by adjusting the gain parameters in the sliding mode surface, and to achieve rapid error convergence through approach control.

[0015] Preferably, a closed-loop control circuit is formed between the coating uniformity monitoring and exception handling module and the sliding mode control module, and the concentration error triggers real-time adjustment of control parameters to achieve dynamic optimization of coating concentration.

[0016] The present invention provides an electrostatic agent precise metering and coating system based on automatic control, which has the following beneficial effects: 1. The present invention realizes real-time monitoring of coating concentration and uniformity through the coating uniformity monitoring and exception handling module, and combines the sliding mode control module to dynamically adjust the electrostatic agent spray flow rate, which can effectively suppress the influence of external disturbances and equipment errors on coating uniformity, significantly improve the accuracy and consistency of the coating, and meet the requirements of high-quality coating process.

[0017] 2. The sliding mode control module of the present invention realizes the rapid convergence and dynamic response optimization of the electrostatic agent flow error by combining the equivalent control law and the approaching control law. At the same time, the module has the robustness to parameter changes and external interference, can operate stably under complex environmental conditions, and improves the system adaptability.

[0018] 3. The coating uniformity monitoring and abnormality handling module of the present invention combines the concentration calculation unit and the abnormality detection unit to calculate the coating concentration in real time and detect abnormal conditions. When the concentration error exceeds the set threshold, the module will trigger an alarm in time or automatically adjust the spray parameters to avoid coating defects and ensure the stability and reliability of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Please see attached Figure 1 The embodiment of the present invention provides an electrostatic agent precise metering and coating system based on automatic control, including: Data acquisition and monitoring module: For the data acquisition and monitoring module, its main function is to provide real-time dynamic data for the entire electrostatic agent precise metering and coating system, ensuring that the subsequent dynamic modeling and control logic are based on high-quality input data. This module is the basis for the operation of the entire system, involving high-precision acquisition of key parameters such as electrostatic agent flow, spray pressure, material flow rate, etc., while monitoring the impact of environmental disturbances (such as vibration, temperature, etc.) on system performance, and providing necessary input data for the dynamic modeling module. In addition, the data collected by this module is also directly used for closed-loop feedback to form the core data flow throughout the entire control system. The following is a detailed description of the data acquisition and monitoring module.

[0022] In this embodiment, the data acquisition and monitoring module is composed of the following parts: Electrostatic agent flow sensor; Pressure sensor; Material flow rate sensor; Vibration sensor; Temperature sensor.

[0023] In this embodiment, the electrostatic agent flow sensor is used to collect the real-time spray flow rate of the electrostatic agent. .

[0024] · The flow sensor is installed on the spray pipeline to monitor the mass flow of the electrostatic agent through the spray pipeline in real time. · The data acquisition frequency is set to 10ms to capture rapid flow changes in dynamic environments. · The signal output by the flow sensor is converted from analog to digital and then transmitted to the data processing and dynamic modeling module in digital form.

[0025] In this embodiment, the liquid spray pressure sensor is used to collect the liquid spray pressure. and its rate of change .

[0026] The pressure sensor is installed at the connection between the injection pump and the injection pipeline to monitor the pressure output by the pump.

[0027] The real-time pressure signal is output through the sensor to capture the pressure fluctuations caused by the dynamic changes of the system during the injection process.

[0028] To more accurately capture the dynamic characteristics, the system's time derivative of pressure Discretization calculation is performed, the formula is as follows:

[0029] in is the sampling time interval.

[0030] In this embodiment, the material flow rate sensor is used to collect the conveying speed of the coating material. .

[0031] The flow rate sensor is installed in the material conveying pipeline to monitor the volume flow rate of the material.

[0032] The sensor's measurement results will be compared with the electrostatic agent flow rate Combined for calculating coating concentration , the calculation formula is:

[0033] in is the electrostatic agent flow rate, is the material flow rate.

[0034] In this embodiment, the vibration sensor is used to monitor the dynamic disturbance in the system operation. .

[0035] Vibration sensors are installed in the spray pipeline and key nodes of the equipment to capture external disturbances caused by vibration.

[0036] Vibration signals can affect the measurement accuracy of flow and pressure, so the system uses vibration data for dynamic modeling. Interference compensation calculation in blocks.

[0037] In this embodiment, the temperature sensor is used to monitor the effect of the ambient temperature on the physical properties of the electrostatic agent.

[0038] Temperature sensors are installed around the spray system to collect ambient temperature in real time.

[0039] The temperature data will be used to correct the fluid viscosity parameters of the electrostatic agent , and further improve the accuracy of dynamic modeling.

[0040] In this embodiment, the core function of the data acquisition and monitoring module is to collect and transmit all dynamic parameters in real time, providing basic data for dynamic modeling: All collected parameters The data will be transmitted to the dynamic modeling module via industrial communication protocols such as Modbus or EtherCAT.

[0041] The data acquisition frequency matches the response frequency of the control system to ensure the high dynamic response capability of the system.

[0042] In this embodiment, the key formulas involved in the data acquisition and monitoring module are as follows: 1. Electrostatic agent flow equation:

[0043] in, It is the real-time injection flow rate; and are pressure and pressure change rate, respectively, calculated by the pressure sensor; is the valve opening.

[0044] Discretization formula of pressure change rate:

[0045] Coating concentration formula:

[0046] in, Measured by flow sensor; Measured by flow rate sensor.

[0047] Module Data Flow flow ,pressure , flow rate ,vibration and temperature The data is transmitted to the data processing and dynamic modeling module through industrial communication protocols.

[0048] The output of the data acquisition module provides an accurate input data basis for subsequent dynamic modeling and sliding mode control, ensuring the accuracy and stability of the entire system under dynamic changes. Through the above detailed description, the composition, functions and key technical principles of the data acquisition and monitoring module are fully revealed, providing a technical basis for the system's high-precision measurement and coating control.

[0049] The above detailed description fully reveals the composition, functions and key technical principles of the data acquisition and monitoring module, providing a technical basis for the high-precision measurement and coating control of the system. Data processing and dynamic modeling module: First of all, the data processing and dynamic modeling module plays a core supporting role in the system. By cleaning and converting the original data and modeling the multi-dimensional dynamic characteristics, it realizes the accurate characterization and prediction of the state of the target object. This module needs to ensure the integrity and quality of the input data, and at the same time, through appropriate dynamic modeling algorithms, capture the complex patterns of data changes over time, and provide reliable support for subsequent decision-making and optimization. In practice, it is necessary to consider the diversity, timing and potential nonlinear relationships of the data to ensure that the module can flexibly adapt to the needs of multiple scenarios and has a certain degree of robustness.

[0050] In this embodiment, the technology implementation of the data processing module is as follows: Data cleaning and preprocessing In view of the diversity and incompleteness of the original data, the data is first cleaned and preprocessed, including missing value filling, outlier detection and processing, and data type conversion. In the process of missing value filling, a comprehensive method based on interpolation algorithm and feature correlation of adjacent time points is adopted to ensure the accuracy of the filling results. The outlier detection part combines statistical methods (such as the 3σ criterion) and machine learning anomaly detection algorithms (such as isolation forests) for joint analysis to ensure that outliers can be efficiently identified. Data type conversion is based on the requirements of the target modeling algorithm. Discrete variables are processed by one-hot encoding, and continuous variables are normalized or standardized to reduce the impact of data of different scales on model results.

[0051] Data feature extraction and dimensionality reduction The extraction of data features is an important basis for modeling. Through principal component analysis (PCA) and feature importance analysis, key features that can explain the trend of major data changes are retained, while redundant or noise features are eliminated. In addition, statistical feature extraction methods based on time window sliding (such as mean, variance, skewness, kurtosis) and frequency domain feature extraction (such as fast Fourier transform) are combined to further enrich the feature dimension.

[0052] Time Series Modeling Preparation Considering the temporal nature of time series data, a set of dynamic feature extraction strategies is developed for this module, including: Lagged feature generation: Generate time-lagged variables to capture the impact of historical states on the current state.

[0053] Time interval characteristics: By calculating the characteristics of intervals at different time points, the weight of the time factor in modeling is analyzed.

[0054] Trend and seasonality decomposition: Use additive models to decompose the trend and periodicity of time series, so that subsequent modeling can be optimized for different components.

[0055] In this embodiment, the technical implementation of the dynamic modeling module is as follows: Model selection and training The dynamic modeling module adopts a multi-level modeling strategy to select appropriate modeling algorithms for different data characteristics, including: For linear time series data, the traditional autoregressive moving average model (ARIMA) is used to obtain trend and periodicity information.

[0056] For nonlinear data, a long short-term memory network (LSTM) based on deep learning is used for modeling. LSTM can effectively capture the dependencies and change patterns of long time series through its memory gating mechanism.

[0057] In order to improve the flexibility and robustness of modeling, the idea of ​​ensemble learning (such as random forest and gradient boosting tree) is also combined to further optimize the prediction accuracy through model fusion.

[0058] Dynamic model update mechanism The dynamic nature of the model is the core concept of this module. To ensure that the model adapts to real-time changes in data, a real-time training update strategy based on sliding windows is proposed: The data within the sliding window is used for incremental training, enabling the model to capture the latest dynamic changes.

[0059] The prediction accuracy of the model is evaluated regularly, and when the model performance deteriorates, a retraining mechanism is triggered.

[0060] Model interpretation and visualization To facilitate understanding of model output results, the dynamic modeling module also integrates model interpretation tools, including SHAP value analysis and feature importance ranking, to help users intuitively understand the contribution of each feature to model prediction. The visualization part provides time series prediction curves, comparison charts of actual values ​​and predicted values, and model error distribution charts.

[0061] Time Series Modeling Formula: The basic form of the ARIMA model is as follows:

[0062] in, Indicates time point The target variable, and denote the autoregressive and moving average parameters, respectively. is the white noise term.

[0063] LSTM modeling formula: In the LSTM model, the update formula for the hidden layer state is as follows:

[0064]

[0065]

[0066]

[0067] The above formula describes the core mechanism of the forget gate, input gate, and output gate in the LSTM unit, where represents the Sigmoid function, Represents element-wise product.

[0068] Sliding mode control module: The sliding mode control module is an important part of the control system for dealing with nonlinear, strong coupling and external interference problems. Its core idea is to transform the nonlinear dynamic behavior of the system into linear behavior on the sliding surface by constructing the sliding surface to achieve fast and stable tracking control. This module needs to consider both the robustness and practicality of the sliding mode control. Especially in practical engineering, it is necessary to suppress chattering through appropriate optimization while ensuring the balance between control accuracy and system response performance.

[0069] In this embodiment, the technology of the sliding mode control module is implemented as follows: 1. Sliding surface The core of sliding mode control is the sliding surface, which determines the dynamic characteristics of the system motion. In this embodiment, the sliding surface adopts a linear sliding surface, and the specific form is as follows:

[0070] in, To control the error, is the expected value, is the current state of the system, is a parameter used to adjust the dynamic response characteristics of the system. , which can make the system have fast response and good robustness.

[0071] 2. Control Law The sliding mode control law aims to ensure that the system state can quickly approach and remain on the sliding surface. The control law consists of two parts: the approach control term and the equivalent control term: Approach control item: guides the system state to quickly approach the sliding surface. The specific form is:

[0072] in, To approach the speed control parameters, is a symbolic function used to guide the system state to approach the sliding surface.

[0073] Equivalent control term: Maintaining the system motion on the sliding surface, the dynamic model of the system is used to calculate:

[0074] in, and Denoting the known partial dynamics and control gains of the system respectively, the overall control law is:

[0075] 3. Anti-vibration measures In order to reduce the impact of high-frequency chattering in sliding mode control, this embodiment introduces a saturation function to replace the sign.

[0076] The approach control term in the control law is modified as follows:

[0077] Among them, sat is the saturation function, is the boundary layer thickness parameter used to smooth the control input and reduce buffeting.

[0078] 4. Dynamic adjustment of sliding mode control module In view of the possible parameter uncertainty and external disturbance changes during the operation of the system, this embodiment provides an adaptive adjustment mechanism. Specifically, the control parameters are dynamically adjusted according to the actual state of the system and the changes in the sliding surface. and boundary layer thickness , ensuring the stability and robustness of the control system under different working conditions.

[0079] 5. Module implementation process The implementation process of the sliding mode control module includes the following steps: According to the system model and control objectives, the sliding surface .

[0080] Based on the sliding surface, calculate the approach term and equivalent controls .

[0081] Synthetic Control Law , and apply the control quantity to the system.

[0082] Monitor the system status in real time and dynamically adjust the control parameters according to the changes in the sliding surface.

[0083] Actuator and feedback control module: The actuator and feedback control module is the core part of the closed-loop control of the system. It is responsible for converting the control instructions calculated by the controller into specific execution actions, and monitoring and adjusting the execution status through a real-time feedback mechanism. This module needs to ensure the dynamic response performance of the actuator, and at the same time achieve precise state adjustment through the feedback loop to deal with the uncertainty and external interference problems in the nonlinear system. In the process, it is necessary to focus on the dynamic characteristics of the actuator, the hysteresis of signal transmission, and the stability and robustness of the feedback control to ensure that the overall performance of the system reaches the expected goal.

[0084] In this embodiment, the technical implementation of the actuator and feedback control module is as follows: Actuators and drives In this embodiment, the actuator uses a high-precision servo mechanism, which includes the following key parts: Execution unit: The servo motor is the core execution unit. It uses a high-precision position sensor to achieve precise adjustment of the angle or position, and combines it with a power amplifier circuit to improve the driving force output capability.

[0085] Driving circuit: Pulse width modulation (PWM) signal driving method is adopted to ensure the smoothness of signal transmission and the linear response of execution action, and reduce vibration and noise during the control process.

[0086] Dynamic characteristics optimization: The inertia and hysteresis problems of the actuator are optimized through a closed-loop speed control circuit to improve the response speed and stability of the execution action.

[0087] Feedback control loop Feedback control is the basis for dynamic adjustment of the actuator. This embodiment implements a multi-level control loop based on state feedback: Position feedback control: The position state is obtained in real time through a high-precision position sensor (such as an optical encoder or potentiometer) installed on the actuator, and compared with the target value. The error signal is calculated to correct the control output.

[0088] Speed ​​feedback control: In response to dynamic execution requirements, a speed sensor feedback loop is added to adjust the speed of the servo motor in real time to ensure the dynamic response capability of the actuator.

[0089] Current feedback control: The current sensing module monitors the operating current of the servo motor to protect the motor from overload or abnormal operating conditions, while optimizing the power usage efficiency of the actuator.

[0090] Feedback signal processing and filtering In feedback control, the real-time and accuracy of the signal are crucial to the control effect. In this embodiment, the feedback signal processing adopts the following method: Filtering: For the high-frequency noise that may exist in the sensor output signal, a low-pass filter is used to remove interference to ensure the stability of the feedback signal.

[0091] Signal calibration: Online calibration of sensor deviations to eliminate measurement errors that may occur during long-term operation.

[0092] Feedback Control Algorithm This embodiment uses the PID control algorithm as the core of feedback control, and achieves the closed-loop stability of the system through multi-level adjustment of position, speed and acceleration: Proportional control (P): quickly respond to error changes and improve the dynamic performance of the system.

[0093] Integral control (I): Eliminate system steady-state errors and enhance control accuracy.

[0094] Differential control (D): Adjust the error change rate to suppress system oscillation and improve control stability.

[0095] The adjustment of PID parameters is achieved by combining offline optimization with online adaptation to ensure the robustness and flexibility of the control system under different working conditions.

[0096] Actuator nonlinearity compensation In view of the nonlinear characteristics of the actuator in actual operation (such as friction, dead zone effect, etc.), this embodiment proposes a nonlinear compensation strategy: The nonlinear characteristic curve is obtained through experimental measurement, and compensation items are introduced into the control algorithm to reduce the impact of nonlinearity on control accuracy.

[0097] To address the friction problem, a dynamic friction model is used for real-time compensation to improve the low-speed running stability of the actuator.

[0098] Robustness and Fault Detection Mechanisms In order to ensure the stable operation of the actuator and feedback control module in a complex environment, this embodiment provides a fault detection and protection mechanism: Fault detection: By monitoring the changing pattern of the feedback signal, determine whether there is a fault such as actuator failure or sensor abnormality, and prompt the user through an alarm or automatically switch to safe mode.

[0099] Enhanced robustness: The system's adaptability under a wide range of operating conditions is enhanced through the parameter adaptation mechanism of the control algorithm and the limiting protection of the control output.

[0100] Module Integration and Verification The actuator and feedback control module were finally integrated into a complete control system, and its performance was verified through simulation and experiments. Under dynamic loads and complex working environments, the test results showed that the module can quickly respond to control instructions, achieve high-precision position and speed control, and show strong suppression capabilities against external interference.

[0101] Coating uniformity monitoring and abnormality handling module: The coating uniformity monitoring and exception handling module is a key link in the coating process. It is mainly responsible for real-time monitoring of the uniformity and quality of the coating thickness, and for early warning and handling when an abnormality occurs. The module collects coating parameter data in real time through sensors, and combines algorithm analysis to evaluate the uniformity of the coating. For abnormal situations, the module can automatically identify the type of abnormality and take corresponding treatment measures to ensure the stability of the coating quality and the controllability of the process. In practical applications, the module needs to have high-precision monitoring capabilities, fast-response exception handling capabilities, and strong environmental adaptability.

[0102] In this embodiment, the technology of the coating uniformity monitoring and abnormality handling module is implemented as follows: Coating parameter collection The basis of coating uniformity monitoring is the real-time collection of coating related parameters. In this embodiment, the following equipment and methods are used: Thickness sensor: Non-contact laser thickness gauge and ultrasonic thickness gauge are selected to measure the thickness distribution of the coating in real time, covering the entire coating surface.

[0103] Visual inspection equipment: monitors the uniformity of coating surface color, texture and gloss through high-resolution industrial cameras combined with image processing algorithms.

[0104] Sampling strategy: Use multi-point distributed sampling to ensure that the sampling points are evenly distributed, cover key process areas, and improve the comprehensiveness and reliability of monitoring.

[0105] Uniformity Assessment Algorithm The collected coating parameters are analyzed by the uniformity evaluation algorithm to determine whether the coating quality meets the requirements: Statistical analysis: Calculate the mean, variance and range of coating thickness to assess overall uniformity; Spatial distribution analysis: Use heat map or 3D distribution map to analyze the spatial variation trend of coating thickness and intuitively reflect the local uneven areas; Standard Deviation Comparison: Compare the measured coating parameters with the reference standards required by the process to determine whether there is a significant deviation. The uniformity assessment results are output in numerical and visual form to provide a basis for subsequent processing.

[0106] Anomaly detection and identification In response to uneven coating or other abnormal problems, this module has designed a multi-level anomaly detection mechanism: Rule threshold detection: By setting upper and lower thresholds, coating thickness that exceeds the normal range can be quickly detected.

[0107] Pattern recognition: Based on machine learning classification algorithms, the model is trained to identify different types of coating defects (such as local thickness, uneven texture or blistering, etc.).

[0108] Trend monitoring: Through time series analysis of coating parameters, the trend of coating thickness changes over time can be identified, and potential anomalies can be warned in advance.

[0109] Exception handling strategy When an exception occurs, the module can respond quickly and execute the following processing strategies: Real-time warning: Notify operators of specific abnormality types and locations through sound and light alarms or interface prompts; Automatic adjustment: According to the abnormality type, the coating equipment is linked to adjust the parameters. For example, the coating supply is increased in the area with insufficient spraying amount, and the spraying amount is reduced in the area with excessive thickness; Shutdown processing: For serious abnormalities (such as equipment failure causing large-area coating failure), the system automatically triggers the shutdown procedure and records the abnormal information for analysis.

[0110] Data Recording and Traceability In this module, all monitoring data and abnormal records are stored for subsequent quality analysis and process optimization: Data storage: The monitoring data is stored by time and region for easy query and analysis; Abnormal report: Automatically generate abnormal report, including abnormal time, location, type and treatment measures, etc., to provide basis for problem tracing; Historical trend analysis: By analyzing historical data, we can optimize process parameters and reduce the probability of abnormalities.

[0111] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the invention, and the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. The electrostatic agent precise metering and coating system based on automatic control is characterized by: include: Data acquisition and monitoring module, used to collect parameters such as electrostatic agent flow, spray pressure, material flow rate and environmental disturbance; A data processing and dynamic modeling module, used to establish a dynamic model of electrostatic agent flow and coating uniformity according to the parameters collected by the data collection and monitoring module, and output a system state prediction value; A sliding mode control module, connected to the data processing and dynamic modeling module, for calculating a dynamic control signal of the electrostatic agent flow rate based on the flow rate error; An actuator and feedback control module is connected to the sliding mode control module, and is used to receive control signals and dynamically adjust the electrostatic agent spray flow rate and pressure, and feed back the adjustment results to the data acquisition and monitoring module; The coating uniformity monitoring and exception handling module is used to monitor the coating concentration and uniformity in real time and trigger the adjustment signal according to the concentration error.

2. The electrostatic agent precise metering and coating system based on automatic control according to claim 1 is characterized in that: The data processing and dynamic modeling module includes a Kalman filter and an extended state observer, which are used to filter out random noise in the collected data and dynamically estimate the disturbance in the electrostatic agent flow.

3. The electrostatic agent precise metering and coating system based on automatic control according to claim 1 is characterized in that: The sliding mode control module realizes the generation of the control signal through the following steps: The error of the electrostatic agent spray flow rate is calculated, and the difference between the target flow rate and the actual flow rate is used as the control input; generating a sliding surface according to the flow error, wherein the sliding surface is calculated by the flow error and its integral; The equivalent control law and the approaching control law are combined to generate the dynamic control signal of the electrostatic agent spray flow rate.

4. The electrostatic agent precise metering and coating system based on automatic control according to claim 1 is characterized in that: The actuator and feedback control module includes: A valve actuator, used for adjusting the opening of the electrostatic agent valve according to the control signal output by the sliding mode control module; Spray pressure regulator, used to dynamically optimize spray pressure; The feedback sensor is used to monitor the real-time flow rate and concentration of the spray liquid and feed the monitoring data back to the data acquisition and monitoring module.

5. The electrostatic agent precise metering and coating system based on automatic control according to claim 1 is characterized in that: The coating uniformity monitoring and exception handling module is used to calculate the coating concentration in real time, monitor the coating uniformity through the ratio of material flow rate to spray flow rate, and trigger automatic adjustment of the reference flow value or control parameters when the concentration error exceeds the set threshold.

6. The electrostatic agent precise metering and coating system based on automatic control according to claim 1 is characterized in that: The coating uniformity monitoring and abnormality handling module includes a concentration calculation unit and an abnormality detection unit. The concentration calculation unit is used to calculate the coating concentration based on the spray flow rate and the material flow rate. The abnormality detection unit is used to monitor the concentration error and trigger an alarm signal or adjust parameters.

7. The electrostatic agent precise metering and coating system based on automatic control according to claim 1 is characterized in that: The data acquisition and monitoring module includes: Electrostatic agent flow sensor, used to measure the spray flow rate; Pressure sensor, used to collect the spray pressure and its dynamic changes; Flow rate sensor, used to collect material conveying flow rate; Environmental disturbance sensors are used to monitor the effects of environmental vibration and temperature on electrostatic agents.

8. The electrostatic agent precise metering and coating system based on automatic control according to claim 1 is characterized in that: The model established by the dynamic modeling module includes: The electrostatic agent flow model expresses the flow rate as a function of the injection pressure, valve opening and system resistance; Coating uniformity model that expresses coating concentration as the ratio of spray flow rate to material flow rate.

9. The electrostatic agent precise metering and coating system based on automatic control according to claim 1 is characterized in that: The sliding mode control module is used to optimize the dynamic response speed of the flow error by adjusting the gain parameters in the sliding mode surface, and to achieve rapid error convergence through approach control.

10. The electrostatic agent precise metering and coating system based on automatic control according to claim 1, characterized in that: A closed-loop control circuit is formed between the coating uniformity monitoring and abnormality handling module and the sliding mode control module, and the concentration error triggers the real-time adjustment of the control parameters to achieve dynamic optimization of the coating concentration.

Images