A kind of axle housing cast steel piece paint spraying device and method

Abstract

The application discloses a kind of axle housing cast steel piece coating spraying device and method, including multi-source state perception module, the multi-source state perception module is connected with digital twin and process decision module communication;The digital twin and process decision module are respectively connected with inner cavity flow field and electric field coupling control module, outer surface trajectory and flow closed-loop control module communication;The inner cavity flow field and electric field coupling control module are used in the inner cavity of the axle housing cast steel piece spraying process, according to the real-time three-dimensional topological change of inner cavity, dynamic adjustment inner cavity spraying atomized airflow field parameter and electrostatic field parameter, to inhibit deep cavity spraying Faraday cage effect, the present application relates to axle housing manufacturing technical field.The present application solves the problem that complex inner cavity of axle housing cast steel piece is easily to produce electrostatic shielding dead angle, surface state is not even, leading to poor adhesion of coating, and traditional lag detection cannot realize wet film real-time closed-loop correction, leading to low problem of spraying quality and efficiency.

Description

Technical Field

[0001] This invention relates to the field of bridge housing manufacturing technology, and in particular to a coating spraying device and method for cast steel bridge housing components. Background Technology

[0002] The axle housing is a core load-bearing component of a commercial vehicle chassis, typically manufactured using cast steel processes. To improve its corrosion resistance and service life, its complex internal and external surfaces require coating after casting. Currently, the industry widely employs conventional robotic automated coating systems for this task.

[0003] However, existing bridge housing spraying technologies have the following significant drawbacks: First, the bridge housing cavity is deep, with varied cross-sections and high curvature. Conventional electrostatic spraying is prone to generating the Faraday cage effect when penetrating deep into the cavity, leading to severe electrostatic shielding and resulting in thinner coatings or even missed areas in the deep cavity. Simultaneously, high-pressure paint mist easily forms eddy currents and rebounds within the sealed deep cavity, causing paint waste. Second, the surface of cast steel parts is porous and highly susceptible to moisture absorption. Furthermore, uneven cooling rates lead to uneven surface temperature and moisture content distribution. Existing systems lack pre-spraying state awareness and feedforward compensation mechanisms, making direct spraying highly susceptible to decreased coating adhesion, blistering, or peeling. Finally, existing systems largely rely on post-treatment dry film thickness measurement, failing to perform real-time closed-loop correction during the wet film stage. If runs or insufficient thickness are detected, rework requires grinding. Moreover, the spraying of internal and external cavities is mostly an independent, sequential operation, lacking global collaborative scheduling among multiple actuators, resulting in long production cycles and low equipment utilization.

[0004] Therefore, there is an urgent need for an intelligent spraying device and method that can overcome deep cavity electrostatic shielding, adapt to changes in surface state, and have real-time closed-loop control of wet film. Summary of the Invention

[0005] To address the problems of electrostatic shielding dead zones, uneven surface conditions leading to poor coating adhesion, and the inability of traditional hysteresis detection to achieve real-time closed-loop correction of wet film in the complex internal cavity of bridge housing cast steel parts, the present invention aims to provide a coating spraying device and method for bridge housing cast steel parts.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a coating spraying device for bridge housing cast steel parts, including a multi-source state sensing module, wherein the multi-source state sensing module is communicatively connected to a digital twin and process decision module, and is used to collect the surface three-dimensional topology data and surface physical state data of the bridge housing cast steel parts in real time and transmit them to the digital twin and process decision module. The digital twin and process decision module is communicatively connected to the internal cavity flow field and electric field coupling control module and the external surface trajectory and flow closed-loop control module, respectively. The digital twin and process decision module is used to construct a dynamic digital twin model based on the received multi-source heterogeneous data, and calculate and generate a global spraying process parameter set and collaborative control commands, which are then sent to the internal cavity flow field and electric field coupling control module and the external surface trajectory and flow closed-loop control module. The internal cavity flow field and electric field coupling control module is used to dynamically adjust the atomized airflow field parameters and electrostatic field parameters of the internal cavity spraying according to the real-time three-dimensional topological changes of the internal cavity during the internal cavity spraying process of the bridge housing cast steel part, so as to suppress the Faraday cage effect of deep cavity spraying. The outer surface trajectory and flow closed-loop control module is used to dynamically correct the outer surface spraying motion trajectory vector and paint flow parameters based on the real-time collected wet film state feedback data during the spraying process of the outer surface of the bridge housing cast steel component.

[0007] Preferably, the digital twin and process decision module includes a surface state feedforward submodule, which is used to map the surface physical state data to the dynamic digital twin model, identify abnormal surface state areas, and generate feedforward correction coefficients for the spraying parameters for the abnormal areas. The surface physical state data includes the surface temperature distribution field and the surface dielectric constant distribution field; the feedforward correction coefficient is used to dynamically adjust the coating atomization pressure and electrostatic voltage in the corresponding area when spraying onto the abnormal area, so as to compensate for the influence of surface moisture or temperature on the coating adhesion.

[0008] Preferably, in the internal cavity flow field and electric field coupling control module, the control logic for dynamically adjusting the atomized airflow field parameters and electrostatic field parameters of the internal cavity spraying includes: Based on the dynamic digital twin model, the equivalent diameter and rate of curvature change of the inner cavity cross section at the current spraying position are extracted; An airflow electrostatic coupling suppression model is constructed. When it is determined that the equivalent diameter of the inner cavity cross section decreases or the rate of curvature change increases, a control command is output to reduce the electrostatic field voltage and increase the swirling intensity of the atomized airflow field. Meanwhile, based on the rate of change of the internal cavity volume, a compensation command for the difference between the intake flow rate and the negative pressure suction flow rate is dynamically output to maintain the micro-negative pressure laminar flow state in the internal cavity.

[0009] Preferably, the outer surface trajectory and flow closed-loop control module includes a wet film feature inversion submodule and a trajectory and flow dynamic correction submodule; The wet film feature inversion submodule is used to collect the multispectral reflectance features of the wet film after spraying, and input them into the preset wet film thickness inversion neural network model to output the actual wet film thickness of the current area. The trajectory and flow dynamic correction submodule is used to calculate the deviation between the actual wet film thickness and the target thickness, and based on the deviation, to generate the velocity correction vector and flow correction scalar of the next spraying trajectory point in real time through a model predictive control algorithm.

[0010] Preferably, it also includes a multi-executor collaborative scheduling module, which is communicatively connected to the digital twin and process decision module. When the inner cavity spraying and the outer surface spraying are performed in parallel or alternately, the module performs spatiotemporal envelope collision detection based on the dynamic digital twin model and uses a heuristic search algorithm to perform global cycle optimization on the inner and outer cavity spraying task sequence to minimize non-spraying waiting time.

[0011] A method for coating cast steel bridge housings includes the following steps: S1, Multi-source state perception and twin initialization: Collect initial surface three-dimensional topological data and surface physical state data of bridge shell cast steel parts to construct an initial digital twin model; S2, Inner cavity flow field and electric field coupled spraying: During the inner cavity spraying process, the topological features of the inner cavity are extracted in real time, and the atomized airflow field and electrostatic field parameters are dynamically adjusted through the airflow-electrostatic coupling suppression model, while maintaining the inner cavity micro-negative pressure laminar flow state simultaneously; S3, closed-loop spraying and wet film inversion on the outer surface: during the outer surface spraying process, the multispectral reflectance characteristics of the wet film are collected in real time, and the actual wet film thickness is obtained through the wet film thickness inversion neural network model; S4, Dynamic Trajectory and Flow Correction: Based on the deviation between the actual wet film thickness and the target thickness, the motion trajectory and flow parameters of subsequent spraying are corrected in real time to complete closed-loop control.

[0012] Preferably, after step S1 and before step S2, a surface state feedforward control step is further included: The surface temperature distribution field and the surface dielectric constant distribution field are mapped to the initial digital twin model to calculate the latent heat of evaporation of water in each region; When spraying into areas with excessive moisture or low temperature, the feedforward correction coefficient is automatically activated to increase the atomization pressure in that area to increase the kinetic energy of the coating and reduce the electrostatic voltage to prevent electrostatic repulsion of coating particles on the wet surface.

[0013] Preferably, in step S2, the specific solution method for the airflow electrostatic coupling suppression model is as follows: Set the electrostatic field voltage as The swirl intensity of the atomized gas flow field is The equivalent diameter of the inner cavity cross section is The rate of change of curvature is ; The control commands are dynamically output using the following relation: and ; Among them, the function and Positively correlated with Negative correlation; function and It is negatively correlated with A positive correlation is shown; this ensures that in narrow or high-curvature regions, the effect is reduced. and increase .

[0014] Preferably, in step S4, the specific algorithm for real-time correction of the motion trajectory and flow parameters of subsequent spraying is as follows: Set the actual wet film thickness of the current trajectory point as The target thickness is Thickness deviation ; like By using a model predictive control algorithm, a scalar value for the paint flow rate is added at the next trajectory point. and reduce the movement speed vector ; like If the flow rate exceeds the preset anti-sagging threshold, an instruction to reduce the paint flow rate will be immediately output. And increase the atomizing air pressure to refine the paint particles.

[0015] Preferably, during the execution of steps S2 and S3, a multi-executor cooperative scheduling step is also performed: Map the set of internal cavity spraying tasks and the set of external surface spraying tasks to a unified time-space coordinate system; With the dual optimization objectives of minimizing total spraying time and avoiding spatiotemporal envelope interference, a non-dominated sorting genetic algorithm is used to solve for the Pareto optimal solution set. An execution sequence is selected from the Pareto optimal solution set and then distributed for collaborative execution.

[0016] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: 1. This invention constructs an airflow electrostatic coupling suppression model and dynamically adjusts the electrostatic field voltage and the swirling intensity of the atomized airflow field according to the equivalent diameter and curvature change rate of the inner cavity cross section. This effectively breaks the Faraday cage electrostatic shielding effect in the deep cavity and narrow curved area of ​​the bridge shell. At the same time, combined with micro-negative pressure laminar flow state control, it completely eliminates the dead corner of the inner cavity spraying, significantly improves the uniformity and adhesion of the inner cavity coating, and prevents the overflow pollution of paint aerosol. 2. This invention achieves non-contact real-time thickness measurement of coatings in wet film state by collecting the multispectral reflectance characteristics of wet film and inputting them into a wet film thickness inversion neural network model. Combined with the model prediction control algorithm, the velocity vector and flow scalar of the subsequent trajectory are dynamically corrected, effectively eliminating defects such as coating sagging and thinning, and significantly reducing rework rate and coating waste. 3. This invention acquires the surface temperature distribution field and surface dielectric constant distribution field in real time through a multi-source state sensing module, accurately identifies high moisture or low temperature abnormal areas on the surface of cast steel parts, and automatically generates correction coefficients through the surface state feedforward submodule. When spraying to abnormal areas, the atomization pressure and electrostatic voltage are dynamically adjusted, compensating for the negative impact of surface physical state on coating adhesion from the source, and effectively avoiding quality hazards such as coating blistering and peeling. 4. This invention maps the internal cavity and external surface spraying tasks to a unified time and space coordinate system through a multi-executor collaborative scheduling module, and uses a non-dominated sorting genetic algorithm to solve the Pareto optimal solution set, realizing global cycle optimization and anti-collision interference verification of multiple spraying executors. Under the premise of ensuring spraying quality, it minimizes non-spraying waiting time and significantly improves the overall production efficiency and equipment utilization of bridge housing cast steel parts. 5. This invention constructs and updates a dynamic digital twin model of the bridge housing cast steel parts in real time, deeply integrating multi-source heterogeneous sensing data with the spraying process decision, realizing a leap from experience-dependent blind spraying to data-driven intelligent precision spraying. This enables the system to adapt to bridge housing workpieces of different batches, different casting tolerances and surface conditions, improving the flexible manufacturing capability and process stability of the spraying system. Attached Figure Description

[0017] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments: Figure 1 This is a system schematic diagram of the device of the present invention; Figure 2 This is a schematic diagram of the spraying method of the present invention. Detailed Implementation

[0018] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification.

[0019] Please see Figures 1 to 2It should be understood that the structures, proportions, sizes, etc., illustrated in the accompanying drawings are merely for illustrative purposes to aid those skilled in the art and to facilitate understanding and reading. They are not intended to limit the scope of the invention and therefore have no substantial technical significance. Any modifications to the structure, changes in proportions, or adjustments to size, without affecting the effectiveness and purpose of the invention, should still fall within the scope of the technical content disclosed in this invention. Furthermore, the terms such as "upper," "lower," "left," "right," "middle," and "one" used in this specification are merely for clarity and not intended to limit the scope of the invention. Changes or adjustments to their relative relationships, without substantially altering the technical content, should also be considered within the scope of the invention's implementation.

[0020] This invention provides a technical solution: a coating spraying device for bridge housing cast steel parts. The device consists of a multi-source state perception module, a digital twin and process decision module, an internal cavity flow field and electric field coupling control module, an external surface trajectory and flow closed-loop control module, and a multi-actuator collaborative scheduling module. The modules form a top-down linkage relationship according to the data interaction hierarchy, and the whole system relies on the digital twin data link to achieve full-process collaborative control.

[0021] The multi-source state sensing module is connected to the digital twin and process decision module and serves as the data input terminal of this device. The multi-source state sensing module is responsible for real-time acquisition of the surface three-dimensional topological data of the bridge shell cast steel parts, as well as surface physical state data including surface temperature distribution field and dielectric constant distribution field, and uniformly transmitting all multi-source heterogeneous acquisition data to the digital twin and process decision module.

[0022] The digital twin and process decision module integrates a surface state feedforward submodule. This submodule receives surface physical state data transmitted from the multi-source state sensing module and maps various physical field data onto the dynamic digital twin model constructed by the device. Based on the model, it identifies abnormal areas on the workpiece surface and generates corresponding spraying parameter feedforward correction coefficients for those areas. These correction coefficients participate in the parameter adjustment logic of subsequent control modules to compensate for the adverse effects of workpiece surface moisture and temperature fluctuations on coating adhesion. The digital twin and process decision module builds the dynamic digital twin model based on the full-volume acquired data. Through model calculation, it obtains a global spraying process parameter set and collaborative control commands, which are then distributed to the internal cavity flow field and electric field coupling control module and the external surface trajectory and flow closed-loop control module, respectively. Simultaneously, the digital twin and process decision module communicates with the multi-executor collaborative scheduling module, outputting spatiotemporal data of the internal and external cavity spraying tasks to the multi-executor collaborative scheduling module.

[0023] The internal cavity flow field and electric field coupling control module receives control parameters and instructions from the digital twin and process decision modules. The control module extracts the equivalent diameter and curvature change rate parameters of the internal cavity cross section based on the dynamic digital twin model. It realizes the dynamic linkage adjustment of the atomized airflow field parameters and electrostatic field voltage parameters through the preset airflow-electrostatic coupling suppression model. When the equivalent diameter of the internal cavity cross section decreases and the curvature change rate increases, the electrostatic voltage is reduced and the swirling intensity of the atomized airflow is increased to suppress the deep cavity Faraday cage effect. Furthermore, based on the real-time change of the internal cavity volume, the difference between the inlet flow rate and the negative pressure suction flow rate is dynamically adjusted to continuously maintain the internal cavity micro-negative pressure laminar flow state.

[0024] The outer surface trajectory and flow closed-loop control module includes two built-in units: a wet film feature inversion submodule and a trajectory and flow dynamic correction submodule. The wet film feature inversion submodule collects the multispectral reflectance characteristics of the wet film after spraying the workpiece, imports the collected data into a preset wet film thickness inversion neural network model, and calculates and outputs the actual wet film thickness. The wet film thickness data is transmitted to the trajectory and flow dynamic correction submodule, which compares the deviation between the actual wet film thickness and the target thickness, and uses a model predictive control algorithm to generate a motion velocity correction vector and a paint flow correction scalar for the next spraying point, thereby realizing closed-loop dynamic correction of the outer surface spraying trajectory and paint flow.

[0025] The multi-actuator collaborative scheduling module and the digital twin and process decision module establish a data interaction link to receive two types of spraying task information, namely inner cavity and outer surface, from the digital twin and process decision module. The multi-actuator collaborative scheduling module conducts spatiotemporal envelope surface collision detection of the spraying actuator based on the dynamic digital twin model, and uses a heuristic search algorithm to optimize the timing of the inner and outer cavity spraying tasks. The optimization goal is to reduce the non-spraying waiting time of the device. The optimized scheduling logic synchronously constrains the start and stop timing of the inner cavity flow field and electric field coupling control module and the outer surface trajectory and flow closed loop control module.

[0026] During the spraying operation, each control module transmits real-time data on changes in the internal cavity topology and feedback data on the detection of wet film on the external surface back to the digital twin and process decision module, continuously updating the parameters of the dynamic digital twin model and forming a closed-loop iterative logic for the entire device.

[0027] A method for coating cast steel bridge housings includes the following steps: S1, Multi-source state perception and twin initialization: Collect initial surface three-dimensional topological data and surface physical state data of bridge shell cast steel parts to construct an initial digital twin model; S2, Inner cavity flow field and electric field coupled spraying: During the inner cavity spraying process, the topological features of the inner cavity are extracted in real time, and the atomized airflow field and electrostatic field parameters are dynamically adjusted through the airflow-electrostatic coupling suppression model, while maintaining the inner cavity micro-negative pressure laminar flow state simultaneously; S3, closed-loop spraying and wet film inversion on the outer surface: during the outer surface spraying process, the multispectral reflectance characteristics of the wet film are collected in real time, and the actual wet film thickness is obtained through the wet film thickness inversion neural network model; S4, Dynamic Trajectory and Flow Correction: Based on the deviation between the actual wet film thickness and the target thickness, the motion trajectory and flow parameters of subsequent spraying are corrected in real time to complete closed-loop control.

[0028] After step S1 and before step S2, a surface state feedforward control step is also included: The surface temperature distribution field and the surface dielectric constant distribution field are mapped to the initial digital twin model to calculate the latent heat of evaporation of water in each region; When spraying into areas with excessive moisture or low temperature, the feedforward correction coefficient is automatically activated to increase the atomization pressure in that area to increase the kinetic energy of the coating and reduce the electrostatic voltage to prevent electrostatic repulsion of coating particles on the wet surface.

[0029] In step S2, the specific solution method for the airflow electrostatic coupling suppression model is as follows: Set the electrostatic field voltage as The swirl intensity of the atomized gas flow field is The equivalent diameter of the inner cavity cross section is The rate of change of curvature is ; The control commands are dynamically output using the following relation: and ; Among them, the function and Positively correlated with Negative correlation; function and It is negatively correlated with A positive correlation is shown; this ensures that in narrow or high-curvature regions, the effect is reduced. and increase .

[0030] In step S4, the specific algorithm for real-time correction of the motion trajectory and flow rate parameters of subsequent spraying is as follows: Set the actual wet film thickness of the current trajectory point as The target thickness is Thickness deviation ; like By using a model predictive control algorithm, a scalar value for the paint flow rate is added at the next trajectory point. and reduce the movement speed vector ; like If the flow rate exceeds the preset anti-sagging threshold, an instruction to reduce the paint flow rate will be immediately output. And increase the atomizing air pressure to refine the paint particles.

[0031] During the execution of steps S2 and S3, a multi-executor cooperative scheduling step is also performed: Map the set of internal cavity spraying tasks and the set of external surface spraying tasks to a unified time-space coordinate system; With the dual optimization objectives of minimizing total spraying time and avoiding spatiotemporal envelope interference, a non-dominated sorting genetic algorithm is used to solve for the Pareto optimal solution set. An execution sequence is selected from the Pareto optimal solution set and then distributed for collaborative execution.

[0032] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A coating spraying device for cast steel bridge housings, comprising a multi-source state sensing module, characterized in that: The multi-source state perception module is communicatively connected to the digital twin and process decision module, and is used to collect the surface three-dimensional topology data and surface physical state data of the bridge shell cast steel parts in real time and transmit them to the digital twin and process decision module. The digital twin and process decision module is communicatively connected to the internal cavity flow field and electric field coupling control module and the external surface trajectory and flow closed-loop control module, respectively. The digital twin and process decision module is used to construct a dynamic digital twin model based on the received multi-source heterogeneous data, and calculate and generate a global spraying process parameter set and collaborative control instructions, which are then sent to the internal cavity flow field and electric field coupling control module and the external surface trajectory and flow closed-loop control module. The internal cavity flow field and electric field coupling control module is used to dynamically adjust the atomized airflow field parameters and electrostatic field parameters of the internal cavity spraying according to the real-time three-dimensional topological changes of the internal cavity during the internal cavity spraying process of the bridge housing cast steel part, so as to suppress the Faraday cage effect of deep cavity spraying. The outer surface trajectory and flow closed-loop control module is used to dynamically correct the outer surface spraying motion trajectory vector and paint flow parameters based on the real-time collected wet film state feedback data during the spraying process of the outer surface of the bridge housing cast steel component.

2. The coating spraying device for bridge housing cast steel parts according to claim 1, characterized in that: The digital twin and process decision module includes a surface state feedforward submodule, which is used to map the surface physical state data to the dynamic digital twin model, identify abnormal surface state areas, and generate feedforward correction coefficients for the spraying parameters for the abnormal areas. The surface physical state data includes the surface temperature distribution field and the surface dielectric constant distribution field; the feedforward correction coefficient is used to dynamically adjust the coating atomization pressure and electrostatic voltage in the corresponding area when spraying onto the abnormal area, so as to compensate for the influence of surface moisture or temperature on the coating adhesion.

3. The coating spraying device for bridge housing cast steel parts according to claim 1, characterized in that: In the internal cavity flow field and electric field coupling control module, the control logic for dynamically adjusting the atomized airflow field parameters and electrostatic field parameters of the internal cavity spraying includes: Based on the dynamic digital twin model, the equivalent diameter and rate of curvature change of the inner cavity cross section at the current spraying position are extracted; An airflow electrostatic coupling suppression model is constructed. When it is determined that the equivalent diameter of the inner cavity cross section decreases or the rate of curvature change increases, a control command is output to reduce the electrostatic field voltage and increase the swirling intensity of the atomized airflow field. Meanwhile, based on the rate of change of the internal cavity volume, a compensation command for the difference between the intake flow rate and the negative pressure suction flow rate is dynamically output to maintain the micro-negative pressure laminar flow state in the internal cavity.

4. The coating spraying device for bridge housing cast steel parts according to claim 1, characterized in that: The outer surface trajectory and flow closed-loop control module includes a wet film feature inversion submodule and a trajectory and flow dynamic correction submodule; The wet film feature inversion submodule is used to collect the multispectral reflectance features of the wet film after spraying, and input them into the preset wet film thickness inversion neural network model to output the actual wet film thickness of the current area. The trajectory and flow dynamic correction submodule is used to calculate the deviation between the actual wet film thickness and the target thickness, and based on the deviation, to generate the velocity correction vector and flow correction scalar of the next spraying trajectory point in real time through a model predictive control algorithm.

5. The coating spraying device for bridge housing cast steel parts according to claim 1, characterized in that: It also includes a multi-executor collaborative scheduling module, which is communicatively connected to the digital twin and process decision module. When the internal cavity spraying and the external surface spraying are performed in parallel or alternately, the module performs spatiotemporal envelope collision detection based on the dynamic digital twin model and uses a heuristic search algorithm to perform global cycle optimization on the internal and external cavity spraying task sequence to minimize non-spraying waiting time.

6. A method for spraying coating on cast steel bridge housings, characterized in that, The bridge housing cast steel coating spraying device according to any one of claims 1-5 includes the following steps: S1, Multi-source state perception and twin initialization: Collect initial surface three-dimensional topological data and surface physical state data of bridge shell cast steel parts to construct an initial digital twin model; S2, Inner cavity flow field and electric field coupled spraying: During the inner cavity spraying process, the topological features of the inner cavity are extracted in real time, and the atomized airflow field and electrostatic field parameters are dynamically adjusted through the airflow-electrostatic coupling suppression model, while maintaining the inner cavity micro-negative pressure laminar flow state simultaneously; S3, closed-loop spraying and wet film inversion on the outer surface: during the outer surface spraying process, the multispectral reflectance characteristics of the wet film are collected in real time, and the actual wet film thickness is obtained through the wet film thickness inversion neural network model; S4, Dynamic Trajectory and Flow Correction: Based on the deviation between the actual wet film thickness and the target thickness, the motion trajectory and flow parameters of subsequent spraying are corrected in real time to complete closed-loop control.

7. The method for coating cast steel bridge housings according to claim 6, characterized in that: After step S1 and before step S2, a surface state feedforward control step is also included: The surface temperature distribution field and the surface dielectric constant distribution field are mapped to the initial digital twin model to calculate the latent heat of evaporation of water in each region; When spraying into areas with excessive moisture or low temperature, the feedforward correction coefficient is automatically activated to increase the atomization pressure in that area to increase the kinetic energy of the coating and reduce the electrostatic voltage to prevent electrostatic repulsion of coating particles on the wet surface.

8. A method for coating cast steel bridge housings according to claim 6, characterized in that: In step S2, the specific solution method for the airflow electrostatic coupling suppression model is as follows: Set the electrostatic field voltage as The swirl intensity of the atomized gas flow field is The equivalent diameter of the inner cavity cross section is The rate of change of curvature is ; The control commands are dynamically output using the following relation: and ; Among them, the function and Positively correlated with Negative correlation; function and It is negatively correlated with A positive correlation is shown; this ensures that in narrow or high-curvature regions, the effect is reduced. and increase .

9. A method for coating cast steel bridge housings according to claim 6, characterized in that: In step S4, the specific algorithm for real-time correction of the motion trajectory and flow rate parameters of subsequent spraying is as follows: Set the actual wet film thickness of the current trajectory point as The target thickness is Thickness deviation ; like By using a model predictive control algorithm, a scalar value for the paint flow rate is added at the next trajectory point. and reduce the movement speed vector ; like If the flow rate exceeds the preset anti-sagging threshold, an instruction to reduce the paint flow rate will be immediately output. And increase the atomizing air pressure to refine the paint particles.

10. A method for coating cast steel bridge housings according to claim 6, characterized in that: During the execution of steps S2 and S3, a multi-executor cooperative scheduling step is also performed: Map the set of internal cavity spraying tasks and the set of external surface spraying tasks to a unified time-space coordinate system; With the dual optimization objectives of minimizing total spraying time and avoiding spatiotemporal envelope interference, a non-dominated sorting genetic algorithm is used to solve for the Pareto optimal solution set. An execution sequence is selected from the Pareto optimal solution set and then distributed for collaborative execution.

Images