Production line spraying treatment system based on Internet of Things

Abstract

The invention discloses a production line spraying processing system based on Internet of Things, which comprises a state identification module, a dynamic airflow compensation analysis module and a spraying cabin airflow control module, and is characterized in that the state identification module is used for monitoring and judging whether a spraying cabin is in an ideal working state in real time; the dynamic airflow compensation analysis module is used for calculating the airflow requirement of a dead angle area in real time according to a three-dimensional model of a sprayed part, and the spraying cabin airflow control module is used for dynamically adjusting parameters of a vortex generator according to a monitoring analysis result so as to optimize airflow distribution and a paint mist adhesion effect. The state recognition module, the dynamic airflow compensation analysis module and the spraying cabin airflow control module are electrically connected with one another, intelligent management of the spraying process is achieved, the paint mist deposition efficiency and the coating uniformity are remarkably improved, and the over-spraying and dissipation phenomena are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial automation, and particularly to a production line spraying processing system based on the Internet of Things. Background Art

[0002] In the spraying process of complex parts by traditional industrial spraying systems, there are generally problems such as uneven distribution of paint mist, serious overspray and dispersion, and poor coverage in dead corners. Most of the existing technologies adopt fixed airflow control schemes, and realize airflow guidance by presetting the parameters of eddy current generators, but lack the real-time response ability to dynamic spraying conditions. Especially when processing special-shaped three-dimensional parts, the traditional system cannot accurately identify the airflow stability and paint mist sedimentation characteristics, resulting in the following technical bottlenecks:

[0003] (1) Uncontrollable airflow disturbance: When the proportion of turbulent energy in the cabin is too high, the diffusion path of paint mist is disordered, resulting in fluctuations in coating thickness. The existing wind speed monitoring means can only obtain local scalar data and lack the real-time analysis ability of three-dimensional flow field vectors;

[0004] (2) Lagging dead corner compensation: Depending on manual experience to preset the airflow compensation scheme, it is difficult to adapt to the geometric feature changes of multi-variety parts. The corner areas of complex curved surfaces are prone to form paint film defects due to insufficient airflow wrapping;

[0005] (3) Insufficient energy efficiency optimization: The global airflow control strategy is disconnected from the local compensation requirements, resulting in long-term high-load operation of eddy current generators and significant energy waste.

[0006] In addition, most of the existing Internet of Things spraying systems focus on equipment networking monitoring and fail to achieve closed-loop optimization of the airflow-paint mist coupling model, which restricts the synchronous improvement of spraying quality and environmental protection indicators. Summary of the Invention

[0007] The purpose of the present invention is to provide a production line spraying processing system based on the Internet of Things to solve the problems raised in the above background art.

[0008] To solve the above technical problems, the present invention provides the following technical solution: A production line spraying processing system based on the Internet of Things includes a state recognition module, a dynamic airflow compensation analysis module, and a spraying cabin airflow control module. The state recognition module is used to monitor and judge in real time whether the spraying cabin is in an ideal working state. The dynamic airflow compensation analysis module is used to calculate the airflow requirements of the dead corner area in real time according to the three-dimensional model of the sprayed part. The spraying cabin airflow control module is used to dynamically adjust the parameters of the eddy current generator according to the monitoring and analysis results to optimize the airflow distribution and paint mist adhesion effect. The state recognition module, the dynamic airflow compensation analysis module, and the spraying cabin airflow control module are electrically connected to each other.

[0009] According to the above technical solution, the state recognition module includes a paint mist concentration monitoring module, an air flow state monitoring module, a feature extraction module, and a judgment module. The paint mist concentration monitoring module is used to monitor the concentration of paint mist. The air flow state monitoring module is used to monitor the air flow state in the cabin. The feature extraction module is electrically connected to the paint mist concentration monitoring module and the air flow state monitoring module. The feature extraction module is used to extract features preset to reflect the current state of the spraying cabin according to the monitoring data of the paint mist concentration module and the air flow state monitoring module. The judgment module is electrically connected to the feature extraction module. The judgment module is used to identify and judge the working state of the spraying cabin according to the extracted state features.

[0010] According to the above technical solution, the dynamic air flow compensation analysis module includes a three-dimensional model acquisition module, a model processing module, a boundary calibration module, and an air flow demand prediction module. The three-dimensional model acquisition module is used to acquire the three-dimensional model of the spraying part. The model processing module is used to remove the microscopic structure with a curvature radius less than 2 mm in the three-dimensional model of the part through a geometric simplification algorithm. The boundary calibration module is used to determine the coordinate system and boundary conditions of the three-dimensional model. The air flow demand prediction module is used to simulate the spraying area and predict and calculate the air flow demand in the dead corner area.

[0011] According to the above technical solution, the air flow control of the spraying cabin includes a signal receiving module, a rotation speed control module, and a blade angle offset module. The signal receiving module is used to receive the recognition and analysis results of the state recognition module and the dynamic air flow compensation analysis module. Both the rotation speed control module and the blade angle offset module are electrically connected to the signal receiving module. The rotation speed control module is used to control the rotation speed of the eddy current generator according to the received recognition and analysis results. The blade angle offset module is used to control the blade offset angle of the eddy current generator according to the received recognition and analysis results.

[0012] An operation method of an Internet of Things-based production line spraying processing system according to any one of the preceding claims 2-4. This method mainly includes the following steps:

[0013] Step S1: Collect air flow data and paint mist concentration data during the spraying process through the paint mist concentration monitoring module and the air flow state monitoring module;

[0014] Step S2: Preprocess the data. Based on the preprocessed data, use the feature extraction module to extract the air flow stability index and the paint mist distribution uniformity feature, and then judge whether the feature index meets the preset standard, so as to identify whether the spraying cabin is in an ideal working state;

[0015] Step S3: When the spraying chamber is in an ideal working state, an electrical signal triggers the start of dynamic airflow compensation analysis. Based on the three-dimensional model of the part, the airflow requirements in the dead corner area are calculated in real time. After the calculation results are output, it proceeds to Step S4; when the spraying chamber is in a non-ideal working state, the electrical signal triggers the airflow control module of the spraying chamber to globally control the intensity and direction of the vortex generator, and then Steps S1 - S2 are re-run;

[0016] Step S4: Based on the calculation results, the intensity and direction of the vortex generator are dynamically adjusted to ensure that the paint mist can evenly adhere to the surface of the part, reducing overspray and dispersion.

[0017] According to the above technical solution, Step S1 further includes:

[0018] Step S1-1: At least 8 groups of laser scattering particle sensors are evenly arranged circumferentially on the inner wall of the spraying chamber. Their installation positions are at a height of 1 / 3 of the maximum working height of the spraying robot arm from the bottom of the chamber, and the distance between adjacent sensors is ≤0.8 m;

[0019] Step S1-2: A three-dimensional ultrasonic anemometer is arranged in the central area at the top of the chamber to form a three-dimensional monitoring network;

[0020] Step S1-3: The paint mist concentration monitoring module obtains the readings of the laser scattering particle sensors at a sampling frequency of 200 Hz, and the airflow state monitoring module obtains the data of the three-dimensional ultrasonic anemometer.

[0021] According to the above technical solution, the method for the feature extraction module to extract the airflow stability index and the paint mist distribution uniformity feature in Step S2 is specifically as follows:

[0022] Step S2-1: Time domain features and frequency domain features are generated by the feature extraction module, where the time domain features include:

[0023] Coefficient of variation of paint mist concentration

[0024] Synthetic velocity of airflow vector

[0025] Proportion of turbulent energy

[0026] The frequency domain features include:

[0027] Perform FFT transformation on the airflow velocity components to extract the main peak frequency of the power spectral density (PSD) in the 0.1 - 10 Hz frequency band;

[0028] Hurst index of the paint mist concentration signal, used to analyze the long-range correlation of the paint mist concentration time series;

[0029] Step S2-2: The following judgment logic is executed by the judgment module

[0030] Input feature vector:

[0031]

[0032] Comprehensive score calculation:

[0033]

[0034] Among them, S is the comprehensive score of the system working state, and S ∈ (0, 1), w1, w2, and w3 are all weight coefficients, and α and β are adjustment parameters;

[0035] State determination rule:

[0036] Set the judgment standard thresholds S0 and H0;

[0037] When the comprehensive score S ≤ S0 and the Hurst index is greater than or equal to H0, the judgment module judges it as the ideal working state;

[0038] When the comprehensive score S > S0 and the Hurst index is less than H0, the judgment module judges it as the non-ideal working state.

[0039] According to the above technical solution, the specific method for calculating the air flow demand in the dead angle area in step S3 is as follows:

[0040] Step S3-1: Preprocess the model, where the preprocessing includes simplifying the geometric shape and removing unnecessary details to improve the calculation efficiency;

[0041] Step S3-2: Determine the coordinate system and boundary conditions of the model to lay the foundation for subsequent calculations;

[0042] Step S3-3: Import the three-dimensional model of the sprayed part into the computational fluid dynamics (CFD) simulation platform, and discretize the model surface and the surrounding space through unstructured tetrahedral meshes;

[0043] Step S3-4: Set the initial simulation conditions based on the real-time monitoring data;

[0044] Step S3-5: Perform transient flow field simulation calculations and solve the following equations simultaneously:

[0045]

[0046] Among them: ρ is the air density, μ is the dynamic viscosity, C is the paint mist concentration; D is the diffusion coefficient;

[0047] Step S3-6: Extract the paint mist deposition efficiency and air flow demand intensity parameters, where:

[0048] Paint mist deposition efficiency: Calculate each grid cell on the part surface The area with a marking η < 60% is the dead corner for air flow compensation;

[0049] Air flow demand intensity: Based on the area A of the dead corner region and the current paint mist concentration gradient Calculate the required compensation air flow velocity: where k is the experimentally calibrated coefficient.

[0050] According to the above technical solution, when the spraying cabin is in a non-ideal working state in step S3, the specific method for the electrical signal to trigger the air flow control module of the spraying cabin and globally control the intensity and direction of the eddy current generator is:

[0051] Based on the characteristic parameters output by the state recognition module, dynamically generate a global control strategy:

[0052] When the air flow stability index is lower than the preset threshold, synchronously increase the reference rotational speed of all eddy current generators and increase the adsorption intensity of the negative pressure system in the cabin to enhance the overall air flow stability;

[0053] When the uniformity index of the paint mist concentration exceeds the standard, adjust the blade angle of the eddy current generator to the preset safe offset range, and at the same time reduce the moving speed of the spraying robotic arm to reduce the escape of paint mist.

[0054] According to the above technical solution, the specific method for dynamically adjusting the intensity and direction of the eddy current generator in step S4 is:

[0055] Step S4-1: For the corner area, increase the rotational speed of the eddy current generator at the corresponding position to The blade offset angle θ = 15° - 25°;

[0056] For the flat area, reduce the rotational speed to N = N0 × 0.8, and the blade angle θ = -5°;

[0057] Step S4-2: Adjust the parameters based on the real-time paint mist deposition efficiency η:

[0058] ΔN = K p ·(η target - η) + K i ·∫(η target - η)dt

[0059] where η target = 85%, K p = 20 rpm / %, when |ΔN| > 300 rpm, trigger the safety limit;

[0060] Step S4-3: When the overlap rate of the coverage areas of two adjacent generators is greater than 30%, reduce their rotational speeds by 10% and offset the blades by 8° in the reverse direction; when the interval gap is greater than 50 mm, increase the rotational speed of the generator at the middle position by 15%.

[0061] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: In the present invention, through the integration of state recognition, dynamic air flow compensation analysis, and air flow control modules, the intelligent management of the spraying process is realized, significantly improving the paint mist deposition efficiency and coating uniformity, and reducing overspray and dispersion phenomena. Especially for complex three-dimensional parts, the system can adjust the air flow parameters in real time according to the geometric features of the parts, ensuring full coverage of dead corners, while optimizing the operating efficiency of the eddy current generator, achieving the dual goals of energy conservation, emission reduction, and high-efficiency production. In addition, the present invention also enhances the adaptability and flexibility of the system, providing strong support for the intelligent upgrade of the spraying process. Brief Description of the Drawings

[0062] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used in conjunction with the embodiments of the present invention to explain the present invention, but do not constitute a limitation to the present invention.

[0063] In the drawings:

[0064] Figure 1 is a schematic diagram of the system module composition of the present invention. Detailed Embodiments

[0065] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0066] Please refer to Figure 1, the present invention provides a technical solution: an IoT-based production line spraying treatment system, including a status recognition module, a dynamic airflow compensation analysis module, and a spraying cabin airflow control module. The status recognition module is used to monitor and judge in real time whether the spraying cabin is in an ideal working state. The dynamic airflow compensation analysis module is used to calculate the airflow demand in the dead corner area in real time according to the three-dimensional model of the sprayed part. The spraying cabin airflow control module is used to dynamically adjust the parameters of the eddy current generator according to the monitoring and analysis results to optimize the airflow distribution and paint mist adhesion effect. The status recognition module, the dynamic airflow compensation analysis module, and the spraying cabin airflow control module are electrically connected to each other; by integrating the status recognition, dynamic airflow compensation analysis, and airflow control modules, the intelligent management of the spraying process is realized, significantly improving the paint mist deposition efficiency and coating uniformity, and reducing overspray and dissipation phenomena. Especially for complex three-dimensional parts, the system can adjust the airflow parameters in real time according to the geometric characteristics of the parts, ensuring full coverage of the dead corner area, while optimizing the operating efficiency of the eddy current generator, achieving the dual goals of energy conservation, emission reduction, and high-efficiency production. In addition, the present invention also enhances the adaptability and flexibility of the system, providing strong support for the intelligent upgrade of the spraying process.

[0067] The status recognition module includes a paint mist concentration monitoring module, an airflow status monitoring module, a feature extraction module, and a judgment module. The paint mist concentration monitoring module is used to monitor the concentration of the paint mist. The airflow status monitoring module is used to monitor the airflow status in the cabin. The feature extraction module is electrically connected to the paint mist concentration monitoring module and the airflow status monitoring module. The feature extraction module is used to extract preset features reflecting the current state of the spraying cabin according to the monitoring data of the paint mist concentration module and the airflow status monitoring module. The judgment module is electrically connected to the feature extraction module. The judgment module is used to identify and judge the working state of the spraying cabin according to the extracted state features.

[0068] The dynamic airflow compensation analysis module includes a three-dimensional model acquisition module, a model processing module, a boundary calibration module, and an airflow demand prediction module. The three-dimensional model acquisition module is used to acquire the three-dimensional model of the sprayed part. The model processing module is used to remove the microscopic structure with a curvature radius less than 2 mm in the three-dimensional model of the part through a geometric simplification algorithm. The boundary calibration module is used to determine the coordinate system and boundary conditions of the three-dimensional model. The airflow demand prediction module is used to simulate the spraying area and predict and calculate the airflow demand in the dead corner area.

[0069] The spraying cabin airflow control includes a signal receiving module, a rotation speed control module, and a blade angle offset module. The signal receiving module is used to receive the recognition and analysis results of the status recognition module and the dynamic airflow compensation analysis module. The rotation speed control module and the blade angle offset module are both electrically connected to the signal receiving module. The rotation speed control module is used to control the rotation speed of the eddy current generator according to the received recognition and analysis results. The blade angle offset module is used to control the blade offset angle of the eddy current generator according to the received recognition and analysis results.

[0070] A method for operating an Internet of Things-based production line spraying treatment system according to any one of the preceding claims 2-4, the method mainly comprising the following steps:

[0071] Step S1: Collect air flow data and paint mist concentration data during the spraying process through a paint mist concentration monitoring module and an air flow state monitoring module;

[0072] Step S2: Preprocess the data, where the preprocessing includes data cleaning, data normalization, etc., to remove outliers and convert data with different dimensions to the same scale. Based on the preprocessed data, use a feature extraction module to extract the air flow stability index and the paint mist distribution uniformity feature, and then determine whether the feature index meets the preset standard to identify whether the spraying chamber is in an ideal working state;

[0073] Step S3: When the spraying chamber is in an ideal working state, an electrical signal triggers the start of dynamic air flow compensation analysis. Based on the three-dimensional model of the part, calculate the air flow demand in the dead corner area in real time. After outputting the calculation result, transfer to Step S4; when the spraying chamber is in a non-ideal working state, an electrical signal triggers the air flow control module of the spraying chamber to globally control the intensity and direction of the eddy current generator, and then re-run Steps S1-S2;

[0074] Step S4: Dynamically adjust the intensity and direction of the eddy current generator based on the calculation result to ensure that the paint mist can be evenly attached to the surface of the part, reducing overspray and dispersion.

[0075] Step S1 further includes:

[0076] Step S1-1: Uniformly arrange at least 8 groups of laser scattering particle sensors circumferentially on the inner wall of the spraying chamber. The installation position is at a height of 1 / 3 of the maximum working height of the spraying robotic arm from the bottom of the chamber, and the distance between adjacent sensors ≤ 0.8 m; by limiting the sensor spacing and installation height, ensure the effective monitoring of the paint mist settlement path and overcome the edge blind area problem caused by traditional uniform arrangement;

[0077] Step S1-2: Arrange a three-dimensional ultrasonic anemometer in the central area at the top of the chamber to form a three-dimensional monitoring network;

[0078] Step S1-3: The paint mist concentration monitoring module obtains the readings of the laser scattering particle sensors at a sampling frequency of 200 Hz, and the air flow state monitoring module obtains the data of the three-dimensional ultrasonic anemometer.

[0079] The method for using the feature extraction module in Step S2 to extract the air flow stability index and the paint mist distribution uniformity feature is specifically as follows:

[0080] Step S2-1: Generate time-domain features and frequency-domain features through the feature extraction module. The time-domain features include:

[0081] Coefficient of variation of paint mist concentration By statistically calculating the ratio of the standard deviation to the average value of the paint mist concentration in each area of the spraying cabin, the fluctuation degree of the concentration distribution is quantified. Exemplarily, if the average concentration in the cabin is 1000 ppm and the standard deviation is 150 ppm, the coefficient of variation is 15%;

[0082] Synthetic velocity of airflow vector

[0083] Proportion of turbulent energy Perform spectral analysis on the airflow velocity signal, calculate the proportion of the energy of the high-frequency turbulent component greater than 5 Hz in the total energy, and characterize the airflow disorder degree. Exemplarily, according to the ventilation fan performance test standard GB / T1236-2017, when E_turb>25%, it is determined that the airflow is unstable. Therefore, when the proportion of high-frequency turbulence in the total energy is 30%, it indicates that the airflow stability is poor;

[0084] The frequency-domain features include:

[0085] Perform FFT transformation on the airflow velocity component, and extract the main peak frequency of the power spectral density (PSD) in the 0.1-10 Hz frequency band;

[0086] Hurst index of the paint mist concentration signal, which is used to analyze the long-range correlation of the paint mist concentration time series. The closer the index is to 1, the more persistent the concentration change trend; the closer it is to 0, the easier the trend is to reverse;

[0087] Step S2-2: The judgment module executes the following judgment logic:

[0088] Input feature vector:

[0089]

[0090] Comprehensive score calculation:

[0091]

[0092] Where S is the comprehensive score of the system working state, and S∈(0,1), w1, w2, and w3 are all weight coefficients, and α and β are adjustment parameters;

[0093] State determination rule:

[0094] Set the judgment standard thresholds S0 and H0;

[0095] When the comprehensive score S≤S0 and the Hurst index is greater than or equal to H0, the judgment module determines it as the ideal working state;

[0096] When the comprehensive score S > S0 and the Hurst index is less than H0, the judgment module determines it as a non-ideal working state;

[0097] By adopting the dual-threshold joint decision-making judgment, the misjudgment rate is greatly reduced compared with the traditional single-index scheme. The nonlinear effect is compressed by the tanh function to avoid the interference of extreme values.

[0098] The specific method for calculating the air flow demand in the dead corner area in real time in step S3 is as follows:

[0099] Step S3-1: Preprocess the model, where the preprocessing includes simplifying the geometric shape and removing unnecessary details to improve the calculation efficiency;

[0100] Step S3-2: Determine the coordinate system and boundary conditions of the model to lay the foundation for subsequent calculations;

[0101] Step S3-3: Import the three-dimensional model of the sprayed part into the computational fluid dynamics (CFD) simulation platform, and discretize the model surface and the surrounding space through unstructured tetrahedral meshes;

[0102] Step S3-4: Set the initial conditions of the simulation based on the real-time monitoring data;

[0103] Step S3-5: Perform transient flow field simulation calculations and simultaneously solve the following formula:

[0104]

[0105] Among them: ρ is the air density, μ is the dynamic viscosity, C is the paint mist concentration; D is the diffusion coefficient;

[0106] Step S3-6: Extract the paint mist deposition efficiency and air flow demand intensity parameters, where:

[0107] Paint mist deposition efficiency: Calculate each grid unit on the part surface Mark the area with η < 60% as the air flow compensation dead corner;

[0108] Air flow demand intensity: According to the dead corner area A and the current paint mist concentration gradient Calculate the required compensation air flow velocity: Among them, k is the experimental calibration coefficient.

[0109] When the spraying cabin is in a non-ideal working state in step S3, the specific method for the electrical signal to trigger the air flow control module of the spraying cabin to globally control the intensity and direction of the eddy current generator is as follows:

[0110] Based on the characteristic parameters output by the state recognition module, dynamically generate a global control strategy:

[0111] When the airflow stability index is lower than the preset threshold, synchronously increase the reference speed of all vortex generators and increase the adsorption intensity of the negative pressure system inside the cabin to enhance the overall stability of the airflow;

[0112] When the uniformity index of the paint mist concentration distribution exceeds the standard, adjust the blade angle of the vortex generator to the preset safe offset range, and at the same time reduce the moving speed of the spraying robotic arm to reduce the escape of paint mist.

[0113] The specific method for dynamically adjusting the intensity and direction of the vortex generator in step S4 is as follows:

[0114] Step S4-1: For the corner area, increase the rotation speed of the vortex generator at the corresponding position to The blade offset angle θ = 15° - 25°; thus, the airflow can be effectively guided to wrap the ridge line;

[0115] For the flat area, reduce the rotation speed to N = N0 × 0.8, and the blade angle θ = -5°; to achieve the effect of suppressing the rebound of paint mist;

[0116] Step S4-2: Adjust the parameters based on the real-time paint mist deposition efficiency η:

[0117] ΔN = K p ·(η target - η) + K i ·∫(η target - η)dt

[0118] where η target = 85%, K p = 20 rpm / %, when |ΔN| > 300 rpm, trigger the safety limit;

[0119] Step S4-3: When the overlap rate of the coverage areas of two adjacent generators is greater than 30%, reduce the rotation speed of both by 10% and reverse-bias the blades by 8° to eliminate the interfering vortices; when the interval gap is greater than 50 mm, increase the rotation speed of the generator in the middle position by 15% to effectively fill the airflow blank area;

[0120] By locally and specifically adjusting the intensity and direction of the vortex generator, uniform adhesion of the paint mist on the surface of the part is achieved. At the same time, through this refined control method, not only is the overspray and paint mist escape phenomenon significantly reduced, but also the spraying quality and the aesthetics of the finished product are further improved. And the local adjustment strategy can also be flexibly adjusted according to the specific shape and spraying requirements of different parts, thus realizing personalized and customized spraying solutions.

[0121] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0122] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An IoT-based production line spraying processing system, characterized in that: The spray processing system of the production line includes a state recognition module, a dynamic air flow compensation analysis module, and a spray cabin air flow control module. The state recognition module is used to monitor and judge in real time whether the spray cabin is in an ideal working state. The dynamic air flow compensation analysis module is used to calculate the air flow demand in the dead corner area in real time according to the three-dimensional model of the sprayed part. The spray cabin air flow control module is used to dynamically adjust the parameters of the eddy current generator according to the monitoring and analysis results to optimize the air flow distribution and paint mist adhesion effect. The state recognition module, the dynamic air flow compensation analysis module, and the spray cabin air flow control module are electrically connected to each other.

2. The spraying processing system for a production line based on the Internet of Things according to claim 1, wherein: The state recognition module includes a paint mist concentration monitoring module, an air flow state monitoring module, a feature extraction module, and a judgment module. The paint mist concentration monitoring module is used to monitor the concentration of the paint mist. The air flow state monitoring module is used to monitor the air flow state in the cabin. The feature extraction module is electrically connected to the paint mist concentration monitoring module and the air flow state monitoring module. The feature extraction module is used to extract the features preset to reflect the current state of the spray cabin according to the monitoring data of the paint mist concentration module and the air flow state monitoring module. The judgment module is electrically connected to the feature extraction module. The judgment module is used to identify and judge the working state of the spray cabin according to the extracted state features.

3. The spraying treatment system for a production line based on the Internet of Things according to claim 1, wherein: The dynamic air flow compensation analysis module includes a three-dimensional model acquisition module, a model processing module, a boundary calibration module, and an air flow demand prediction module. The three-dimensional model acquisition module is used to acquire the three-dimensional model of the sprayed part. The model processing module is used to remove the microstructures with a curvature radius less than 2 mm in the three-dimensional model of the part through a geometric simplification algorithm. The boundary calibration module is used to determine the coordinate system and boundary conditions of the three-dimensional model. The air flow demand prediction module is used to simulate the spraying area and predict and calculate the air flow demand in the dead corner area.

4. The spraying processing system for a production line based on the Internet of Things according to claim 1, characterized in that: The spray cabin air flow control includes a signal receiving module, a rotation speed control module, and a blade angle offset module. The signal receiving module is used to receive the recognition and analysis results of the state recognition module and the dynamic air flow compensation analysis module. The rotation speed control module and the blade angle offset module are both electrically connected to the signal receiving module. The rotation speed control module is used to control the rotation speed of the eddy current generator according to the received recognition and analysis results. The blade angle offset module is used to control the blade offset angle of the eddy current generator according to the received recognition and analysis results.

5. A method for operating an IoT-based production line spraying processing system according to any one of the preceding claims 2-4, characterized in that: This method mainly includes the following steps: Step S1: Collect the air flow data and paint mist concentration data during the spraying process through the paint mist concentration monitoring module and the air flow state monitoring module; Step S2: Preprocess the data. Based on the preprocessed data, use the feature extraction module to extract the air flow stability index and the paint mist distribution uniformity feature, and then judge whether the feature index meets the preset standard, so as to identify whether the spray cabin is in an ideal working state; Step S3: When the spraying chamber is in an ideal working state, an electrical signal triggers the start of dynamic airflow compensation analysis. Based on the 3D model of the part, the airflow requirements in the dead corner area are calculated in real time. After the calculation results are output, it proceeds to Step S4; when the spraying chamber is in a non-ideal working state, the electrical signal triggers the airflow control module of the spraying chamber to globally control the intensity and direction of the eddy current generator, and then Steps S1 - S2 are re-run; Step S4: Based on the calculation results, dynamically adjust the intensity and direction of the eddy current generator to ensure that the paint mist can evenly adhere to the surface of the part, reducing overspray and dispersion.

6. The operating method of a production line spraying treatment system based on the Internet of Things according to claim 5, characterized in that: The said Step S1 further includes: Step S1-1: At least 8 groups of laser scattering particle sensors are evenly arranged circumferentially on the inner wall of the spraying chamber. Their installation positions are at a height of 1 / 3 of the maximum working height of the spraying robotic arm from the bottom of the chamber, and the distance between adjacent sensors ≤ 0.8m; Step S1-2: A three-dimensional ultrasonic anemometer is arranged in the central area at the top of the chamber to form a three-dimensional monitoring network; Step S1-3: The paint mist concentration monitoring module obtains the readings of the laser scattering particle sensors at a sampling frequency of 200Hz, and the airflow state monitoring module obtains the data of the three-dimensional ultrasonic anemometer.

7. The operating method of an IoT-based production line spraying processing system according to claim 5, characterized in that: The method of using the feature extraction module to extract the airflow stability index and the paint mist distribution uniformity feature in the said Step S2 is specifically as follows: Step S2-1: Generate time-domain features and frequency-domain features through the feature extraction module, where the time-domain features include: Coefficient of variation of paint mist concentration Airflow vector synthesis velocity Turbulent energy proportion The frequency-domain features include: Perform FFT transformation on the airflow velocity components to extract the main peak frequency of the power spectral density (PSD) in the frequency band of 0.1 - 10Hz; The Hurst index of the paint mist concentration signal, which is used to analyze the long-range correlation of the paint mist concentration time series; Step S2-2: The judgment module executes the following judgment logic: Input feature vector: Comprehensive score calculation: Where S is the comprehensive score of the system working state, and S ∈ (0,1), w1, w2, and w3 are all weight coefficients, and α and β are adjustment parameters; State determination rule: Set the judgment standard thresholds S0 and H0; When the comprehensive score S ≤ S0 and the Hurst index is greater than or equal to H0, the judgment module determines it as an ideal working state; When the comprehensive score S > S0 and the Hurst index is less than H0, the judgment module determines it as a non-ideal working state.

8. The operating method of an IoT-based production line spraying treatment system according to claim 5, characterized in that: The specific method of calculating the airflow requirements in the dead corner area in the said Step S3 is as follows: Step S3-1: Preprocess the model, where the preprocessing includes simplifying the geometric shape and removing unnecessary details to improve the calculation efficiency; Step S3-2: Determine the coordinate system and boundary conditions of the model to lay the foundation for subsequent calculations; Step S3-3: Import the 3D model of the sprayed part into the computational fluid dynamics (CFD) simulation platform, and discretize the model surface and the surrounding space through unstructured tetrahedral meshes; Step S3-4: Set the simulation initial conditions based on the real-time monitoring data; Step S3-5: Perform transient flow field simulation calculations and simultaneously solve the following formula: Where: ρ is the air density, μ is the dynamic viscosity, C is the paint mist concentration; D is the diffusion coefficient; Step S3-6: Extract the paint mist deposition efficiency and airflow requirement intensity parameters, where: Paint mist deposition efficiency: Calculate for each grid cell on the surface of the part Mark the area with η < 60% as the dead corner for air flow compensation; Airflow demand intensity: Based on the dead zone area A and the current paint mist concentration gradient Calculate the required compensation airflow velocity: where k is the experimentally calibrated coefficient.

9. The operating method of a production line spraying treatment system based on the Internet of Things according to claim 5, characterized in that: In step S3, when the spraying chamber is in a non-ideal working state, the electrical signal triggers the air flow control module of the spraying chamber, and the specific method for globally controlling the intensity and direction of the vortex generator is as follows: Based on the characteristic parameters output by the state recognition module, a global control strategy is dynamically generated: When the air flow stability index is lower than the preset threshold, synchronously increase the reference speed of all vortex generators and increase the adsorption intensity of the negative pressure system in the chamber to enhance the overall stability of the air flow; When the uniformity index of the paint mist concentration distribution exceeds the standard, adjust the blade angle of the vortex generator to the preset safe offset range, and at the same time reduce the moving speed of the spraying robotic arm to reduce the escape of paint mist.

10. The operating method of a production line spraying processing system based on the Internet of Things according to claim 5, characterized in that: The specific method for dynamically adjusting the intensity and direction of the vortex generator in step S4 is as follows: Step S4-1: For the corner area, increase the rotational speed of the corresponding vortex generator to The blade offset angle θ = 15° - 25°; For the planar area, reduce the speed to N = N0 × 0.8, and the blade angle θ = -5°; Step S4-2: Adjust the parameters based on the real-time paint mist deposition efficiency η: ΔN = K p ·(η target - η) + K i ·∫η target - η)dt where η target = 85%, K p = 20 rpm / %, when |ΔN| > 300 rpm, the safety limit is triggered; Step S4-3: When the overlap rate of the coverage areas of two adjacent generators is greater than 30%, reduce the speeds of the two by 10% and reverse-bias the blades by 8°; when the interval gap is greater than 50 mm, increase the speed of the generator at the middle position by 15%.

Images