Multi-parameter regulation and control method and system for vacuum insulated panel heat insulation layer spraying robot

Abstract

The invention provides a multi-parameter regulation and control method and system for a vacuum insulation panel heat insulation layer spraying robot, relates to the technical field of multi-parameter regulation and control, and effectively solves the problems of uneven spraying thickness and poor space consistency by dynamically sensing and regulating and controlling the interference relation and track offset influence among multiple nozzles in the spraying process. Fine adjustment of parameters of the spray heads can be achieved, all the spray heads can maintain the ideal spraying state under different working conditions, and therefore the overall spraying precision and stability are improved. By introducing a multi-parameter combined regulation and control mechanism, spraying defects caused by factors such as attitude deviation and coupling interference can be remarkably reduced, and the rework rate and material waste are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-parameter control, and more specifically, to a multi-parameter control method and system for a vacuum insulation panel insulation layer spraying robot. Background Art

[0002] With the continuous improvement of building energy-saving standards and the widespread application of new insulation materials, vacuum insulation panels have become one of the core materials of high-performance insulation systems due to their excellent thermal resistance and good structural compatibility. In the actual preparation process, in order to ensure the sealing, durability and thermal stability of the VIP edges and surfaces in subsequent use, it is often necessary to spray a uniform insulation layer with a certain thickness control accuracy on its surface or edge area. At present, industrial spraying robots have been widely used in this type of precision spraying operations, with advantages such as high degree of automation and good repeatability. However, due to the complex size and shape of vacuum insulation panels and large changes in curvature in the corner areas, the nozzle array has a coupled disturbance effect during the multi-angle and multi-path operation process, and the spraying thickness is prone to being locally thin or too thick, which in turn affects the overall performance of the insulation panel. At the same time, existing spraying control methods are mostly based on a single parameter control model, which is difficult to cope with the multi-dimensional precision feedback requirements under dynamic working conditions, and it is also difficult to achieve closed-loop regulation of the spraying quality.

[0003] In the existing technology, although some literature has proposed methods for spray path correction based on robot posture feedback, or the use of neural networks to predict and correct the spray thickness, there are still key technical deficiencies: First, the actual coupling relationship between nozzles is often not systematically modeled, resulting in the interference effect of adjacent nozzles being difficult to effectively quantify, thereby forming non-uniform coating accumulation or gaps in complex surface areas; Second, in the dynamic spraying process, the nozzle operation trajectory is affected by factors such as the dynamic response lag of the robot arm and material adhesion rebound, and the actual spraying trajectory often produces errors compared with the theoretical path. However, most current control models only perform static compensation and lack continuous modeling and regulation of dynamic disturbance factors; Third, most existing spray control systems are based on fixed parameter table control, lack an adaptive update mechanism, and cannot be combined with coating detection results for feedback correction, resulting in insufficient system control accuracy and difficulty in achieving simultaneous optimization of spray thickness and uniformity.

[0004] Therefore, there is an urgent need for an intelligent spraying control method that can integrate nozzle array relationship modeling, trajectory disturbance modeling and multi-parameter feedback control. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention is proposed. The present invention provides a multi-parameter control method and system for a vacuum insulation panel insulation layer spraying robot.

[0006] According to one aspect of the present invention, a multi-parameter control method for a vacuum insulation panel insulation layer spraying robot is provided, which includes: modeling the spatial layout of the robot nozzle array, and generating a nozzle array correlation matrix for representing the coupling influence between adjacent nozzles based on historical spraying data; collecting the nozzle trajectory in real time during the spraying process, calculating the offset vector based on the posture error, and constructing a trajectory disturbance influence factor matrix; constructing a three-parameter joint fine-tuning matrix based on the correlation matrix and the disturbance matrix; dynamically adjusting the current nozzle according to the nozzle number based on the parameter correction amount output by the joint fine-tuning matrix to achieve synchronous control of the spraying thickness and spatial uniformity; updating the nozzle disturbance influence matrix based on the obtained actual coating thickness difference and uniformity deviation, and transmitting it back to the joint fine-tuning matrix to complete the next round of control.

[0007] Furthermore, the modeling of the spatial layout of the robotic nozzle array includes: forming a spatial arrangement parameter group by calibrating the relative position coordinates, pitch angle and array spacing of the robotic nozzle array under a standard spraying task.

[0008] Furthermore, the construction of the nozzle array association matrix includes: performing statistical analysis on the overlapping segments of the trajectories of adjacent nozzles in the historical data set, combining the spraying thickness deviation value, determining the interference weight of each nozzle on its adjacent nozzle, and extracting it as a coupling weight vector; taking the spatial arrangement parameter group and the coupling weight vector as input, normalizing and fusing the spatial distance of each pair of nozzle numbers with the historical interference intensity, and generating a nozzle array association matrix for representing the coupling relationship.

[0009] Furthermore, the offset vector calculated based on the posture error includes: calculating the posture error term ΔQ of the nozzle in the six-degree-of-freedom space based on the current posture parameter group Q of the nozzle recorded by the spray controller and the target posture parameter group Q0 set by the task; and extracting the actual spray axis offset vector V of each nozzle by projecting the linear offset part in the posture error term ΔQ to the spray axis direction as a physical quantity characterizing the actual deviation trend of the spray beam.

[0010] Furthermore, the three parameters include paint mixing parameters, spraying speed and nozzle moving speed.

[0011] Furthermore, the construction of the joint fine-tuning matrix includes: taking the nozzle number as the axis, extracting the nozzle coupling degree and offset trend from the correlation matrix and the disturbance influence factor matrix respectively, and constructing the disturbance state tensor T; each dimension of the disturbance state tensor T corresponds to the interference direction between the nozzles, the spraying displacement trend and the physical position index; setting the basic spraying parameter group P0 = {α0, β0, γ0}, corresponding to the default paint mixing parameters, spraying speed, and nozzle movement speed respectively; constructing the nozzle parameter adjustment offset group ΔP = Δα, Δβ, Δγ} according to the interference direction and disturbance offset direction of each nozzle in the disturbance state tensor T; taking the nozzle number as the index, combining the basic parameter group P0 and the offset group ΔP to generate a three-parameter joint fine-tuning matrix M, wherein each row is the three-parameter adjustment result corresponding to the nozzle.

[0012] Furthermore, the dynamic adjustment of the current nozzle includes: extracting the parameter correction group corresponding to each nozzle based on the nozzle number index joint fine-tuning matrix M, which respectively corresponds to the paint mixing parameters, spraying speed and nozzle movement speed setting values ​​of the current nozzle; and regulating the paint mixing parameters, spraying speed and nozzle movement speed according to the parameter group instructions.

[0013] Furthermore, the actual coating thickness difference and uniformity deviation include: collecting thickness measurement data in the completed spraying area, and extracting the thickness difference and local uniformity deviation of the corresponding area of ​​each nozzle by comparing it with a preset target thickness template; combining the thickness difference and local uniformity deviation of each nozzle to construct a deviation vector.

[0014] Furthermore, the updating of the nozzle disturbance influence matrix includes: inputting the deviation vector into the trajectory disturbance influence factor matrix, and performing exponential correction on the nozzle corresponding item in the disturbance matrix.

[0015] According to another aspect of the present invention, a multi-parameter control system for a vacuum insulation panel insulation layer spraying robot is provided, comprising: an array modeling module for modeling the spatial layout of the robot's spray head array and generating a spray head array correlation matrix for representing the coupling effect between adjacent spray heads based on historical spraying data;

[0016] The trajectory acquisition module is used to collect the nozzle trajectory in real time during the spraying process, calculate the offset vector based on the posture error, and construct the trajectory disturbance influence factor matrix;

[0017] The fine-tuning matrix module is used to construct a three-parameter joint fine-tuning matrix based on the correlation matrix and the perturbation matrix;

[0018] The synchronous control module is used to dynamically adjust the current nozzle according to the nozzle number based on the parameter correction amount output by the joint fine-tuning matrix, thereby achieving synchronous control of the spray thickness and spatial uniformity;

[0019] The error feedback module is used to update the nozzle disturbance influence matrix based on the actual coating thickness difference and uniformity deviation obtained, and return it to the joint fine-tuning matrix to complete the next round of control.

[0020] Compared with the prior art, the multi-parameter control method and system of the vacuum insulation panel insulation layer spraying robot provided by the present invention effectively solves the problems of uneven spraying thickness and poor spatial consistency by dynamically sensing and controlling the interference relationship and trajectory offset influence between multiple nozzles during the spraying process; it can realize fine adjustment of nozzle parameters, so that each nozzle can maintain an ideal spraying state under different working conditions, thereby improving the overall spraying accuracy and stability. By introducing a multi-parameter joint control mechanism, the present invention can significantly reduce spraying defects caused by factors such as posture deviation and coupling interference, and reduce rework rate and material waste. Compared with traditional methods that are difficult to deal with real-time disturbances and local error accumulation during the spraying process, the present invention has stronger adaptability and control robustness, and is particularly suitable for high requirements such as vacuum insulation panel insulation layers. It realizes the simultaneous optimization of spraying thickness and spatial uniformity, and effectively improves the molding quality and production yield of vacuum insulation panel insulation layers. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0022] Figure 1 4 is a system block diagram of a multi-parameter control method for a vacuum insulation panel insulation layer spraying robot according to an embodiment of the present invention.

[0023] Figure 2 This is a flowchart of calculating an offset vector based on a posture error in a multi-parameter control method for a vacuum insulation panel insulation layer spraying robot according to an embodiment of the present invention.

[0024] Figure 3 4 is a structural diagram of a multi-parameter control system for a vacuum insulation panel insulation layer spraying robot according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0026] As mentioned in the background technology above, although some literature has proposed methods for spray path correction based on robot posture feedback, or using neural networks to predict and correct spray thickness, there are still key technical deficiencies: First, the actual coupling relationship between nozzles is often not systematically modeled, resulting in the interference effect of adjacent nozzles being difficult to effectively quantify, thereby forming non-uniform coating accumulation or gaps in complex surface areas; Second, during the dynamic spraying process, the nozzle trajectory is affected by factors such as the dynamic response lag of the robot arm and material adhesion rebound, and the actual spray trajectory often produces errors compared to the theoretical path. However, most current control models only perform static compensation and lack continuous modeling and regulation of dynamic disturbance factors; Third, most existing spray control systems are based on fixed parameter table control, lack an adaptive update mechanism, and cannot be combined with coating detection results for feedback correction, resulting in insufficient system control accuracy and difficulty in achieving simultaneous optimization of spray thickness and uniformity. Therefore, there is an urgent need for an intelligent spray control method that can integrate nozzle array relationship modeling, trajectory disturbance modeling, and multi-parameter feedback control.

[0027] Figure 1 Flowchart of the multi-parameter control method of the vacuum insulation panel insulation layer spraying robot according to an embodiment of the present invention. Figure 1 As shown in the figure, the multi-parameter control method of the vacuum insulation panel insulation layer spraying robot includes: S1: modeling the spatial layout of the robot nozzle array, and generating a nozzle array correlation matrix for representing the coupling influence between adjacent nozzles based on historical spraying data; S2: real-time acquisition of nozzle trajectory during the spraying process, calculation of the offset vector based on the posture error, and construction of the trajectory disturbance influence factor matrix; S3: construction of a three-parameter joint fine-tuning matrix based on the correlation matrix and the disturbance matrix; S4: based on the parameter correction amount output by the joint fine-tuning matrix, the current nozzle is dynamically adjusted according to the nozzle number to achieve synchronous control of the spraying thickness and spatial uniformity; S5: based on the actual coating thickness difference and uniformity deviation obtained, the nozzle disturbance influence matrix is ​​updated, and the result is transmitted back to the joint fine-tuning matrix to complete the next round of control.

[0028] In an embodiment of the present invention, step S1 specifically includes modeling the spatial layout of the robot nozzle array, and generating a nozzle array correlation matrix for representing the coupling effect between adjacent nozzles based on historical spraying data. The correlation matrix is ​​used to quantify the degree of interference of the nozzle on the adjacent spraying trajectory under relative motion.

[0029] Preferably, the spatial layout modeling of the robotic nozzle array includes: forming a spatial arrangement parameter group by calibrating the relative position coordinates, pitch angle and array spacing of the robotic nozzle array under a standard spraying task, and the parameter group provides a spatial distribution basis for nozzle array association modeling.

[0030] First, before modeling the nozzle array, it's necessary to clarify the spray robot structure used in this invention and the basic principles of nozzle arrangement. In conventional spraying operations, nozzles are typically arranged in a linear array or rectangular grid, suitable for achieving uniform coverage over large surfaces. However, these arrangements are often limited to a two-dimensional coordinate system for spatial modeling, lacking consideration for the "spatial offset" caused by pitch angles, nozzle angles, and assembly errors in actual operation. Therefore, to more comprehensively depict the actual spatial arrangement of the nozzles, the present invention uses a spatial configuration parameter set consisting of "three-dimensional spatial coordinates + pitch attitude angle + array spacing" as the modeling basis. The acquisition process of this parameter set relies on a combination of the robot's own motion control system and a laser calibration device. Specifically, the motion control unit first moves the nozzles sequentially to multiple positions on a standard reference trajectory. In conjunction with an external positioning device, the three-dimensional coordinates and attitude angle information of each nozzle during this process are obtained. This generates a multidimensional parameter record containing the nozzle number, X / Y / Z coordinates, pitch angle, yaw angle, and distance to adjacent nozzles. The advantage of this approach is that the modeling not only takes into account where the sprinkler is, but also clearly defines at what angle it faces the target area.

[0031] Next, on the basis of establishing the spatial distribution model of the nozzles, it is necessary to further construct a data model that can reflect the mutual influence relationship between the nozzles. Generally speaking, in the collaborative operation of multiple nozzles, there are inevitable interactions between the nozzles, such as coating area overlap, airflow disturbance, and edge tailing. These effects often manifest as inconsistent spraying thickness, rough edges and other microscopic defects in a short period of time. In order to accurately capture the true manifestations of these mutual influences, the present invention designs a method for generating a nozzle association matrix based on historical spraying task records. Specifically, historical spraying trajectory data and corresponding thickness distribution records are extracted from archived spraying tasks to form a data set, wherein the data set contains data samples of nozzle number, motion trajectory, control parameters and finished product thickness distribution, which are used to derive the degree of mutual interference between nozzles and thickness offset response.

[0032] Preferably, a statistical analysis is performed on the overlapping sections of the trajectories of adjacent nozzles in the historical data set, and the interference weight of each nozzle on its adjacent nozzle is determined in combination with the spraying thickness deviation value, and extracted as a coupling weight vector.

[0033] It should be noted that in order to further refine this interference trend, the present invention proposes a coupling weight vector construction mechanism to quantify the degree of influence of each nozzle on the spraying quality of its adjacent nozzles. In specific operations, first screen out all nozzle pairs (such as nozzle i and nozzle j) with overlapping or intersecting trajectories, and then perform mean and variance statistics on the thickness deviation values ​​of their corresponding areas (that is, the difference between the theoretical thickness and the measured thickness), and then summarize their interference intensity. For example, if nozzle j is operating after nozzle i, its spraying thickness in the overlapping area is generally higher than the standard value, indicating that the exhaust gas or solvent evaporation of nozzle i affects the subsequent nozzles. This type of interference effect is represented in vector form and defined as W ij , which represents the influence of nozzle i on nozzle j. The interference weights between all nozzle pairs will be integrated into a two-dimensional matrix W∈R n×n , where n is the total number of nozzles. It is worth noting that at this stage the present invention adopts an asymmetric matrix expression, namely W ij ≠W ji , in order to truly reflect the directional influence of the spraying order on the disturbance.

[0034] Finally, the spatial configuration parameter group and coupling weight vector constructed above are used as input, and the spatial distances and historical interference intensities of each pair of nozzle numbers are normalized and fused to generate a nozzle array association matrix for representing the coupling relationship.

[0035] As can be seen, this invention systematically establishes a high-dimensional, precision-adjustable printhead array coupling model from four perspectives: printhead spatial modeling, historical data extraction, interference weight derivation, and multi-factor fusion modeling. This model not only reflects the potential impact of the physical arrangement of printheads on spray consistency but also incorporates historical spray performance as a weighting reference, laying a solid data foundation for subsequent dynamic parameter control.

[0036] In this embodiment of the present invention, S2 specifically involves capturing the nozzle trajectory in real time during the spraying process, calculating the offset vector based on the posture error, and constructing a trajectory disturbance influence factor matrix to describe the spray deviation trend caused by the disturbance for each nozzle. Its main purpose is to dynamically detect the degree of deviation between the actual nozzle trajectory and the task-set trajectory during the real-time execution of the spraying task.

[0037] First, during the operation of a spray robot, each nozzle is typically mounted on the end of a multi-degree-of-freedom robotic arm. The nozzle moves along a complex path within the workspace, and its trajectory is affected by various factors, including drive errors, mechanical backlash, and inertial delay. Therefore, a high-frequency sensor acquisition device is required to record the nozzle's spatial position and posture information in real time.

[0038] Preferably, the calculation of the offset vector based on the posture error includes, based on the current posture parameter group Q of the nozzle recorded by the spray controller, combining with the target posture parameter group Q0 set by the task, calculating the posture error term ΔQ of the nozzle in the six-degree-of-freedom space; by projecting the linear offset part of the posture error term ΔQ to the spray axis direction, extracting the actual spray axis offset vector V of each nozzle as a physical quantity characterizing the actual deviation trend of the spray beam.

[0039] Specifically, the current posture parameter group Q of each nozzle contains six dimensions, namely three-dimensional linear position coordinates (x, y, z) and three-dimensional attitude angles (pitch angle, yaw angle, roll angle). The parameters can be obtained through an optical tracking system, an encoder or an IMU (inertial measurement unit). Compared with the conventional process in which only the trajectory path points are pre-planned and recorded offline, the present invention uses a real-time-continuous acquisition strategy to dynamically acquire the actual trajectory points with a millisecond time resolution to ensure data density and timeliness. Furthermore, in order to calculate the deviation between the actual motion state of the nozzle and the set trajectory, it is necessary to provide a target posture parameter group at the same time, that is, the ideal nozzle trajectory predefined in the task. By comparing the current posture Q with the target posture of the task point by point, the error vector ΔQ in the six-degree-of-freedom space can be solved.

[0040] It is known that the spraying behavior performed by the nozzle is essentially a directional distribution process of a beam of material jets (such as a paint atomization flow), and the effect of the spraying is closely related to the axial consistency of the nozzle. Even a small spatial displacement, if the directionality changes, may cause the spraying area to shift, the spraying angle to change, or the thickness to be uneven. Therefore, the present invention only extracts the linear displacement term (Δx, Δy, Δz) part in the ΔQ six-dimensional error and projects it to the current spraying direction axis of the nozzle (usually defined as the center axis of the nozzle, i.e., the Z direction). The projection operation is completed by vector dot product: if the unit direction of the spraying axis is m, the offset vector is V = (Δx, Δy, Δz) × m × m, that is, the projection size of the linear offset in the spraying direction multiplied by the direction unit vector. Through this operation, the three-dimensional spatial offset can be converted into an effective deviation in the spraying axis. This processing method can more realistically reflect the impact of the nozzle deviation on the actual spraying thickness and trajectory path.

[0041] Preferably, V is weighted based on the coupling weights of adjacent nozzles in the nozzle array correlation matrix to generate an interference adjustment vector group U to characterize the changing trend of the single nozzle disturbance transmission to its adjacent area.

[0042] This physical vector V not only provides the direction of the deviation trend (inward or outward), but also reflects the magnitude of the deviation. In practical applications, when the V value is significantly positive or negative, it indicates that the nozzle is currently deviating outside or inside the target spray path, causing a buildup or loss effect on the thickness. Therefore, the construction of the deviation vector V is the core quantity that constitutes the physical representation in disturbance modeling.

[0043] Since the spraying robot usually has a multi-nozzle array structure, there is spatial overlap and influence between the spraying areas of each nozzle. Even if a certain nozzle undergoes a posture disturbance, it will affect the thickness or uniformity of the coverage area of ​​the adjacent nozzle. Therefore, the V vector cannot be viewed in isolation, but its disturbance effect needs to be projected to the adjacent area. To this end, the present invention generates a nozzle array correlation matrix in the first step, and each element of the matrix represents the coupling influence weight of nozzle i on nozzle j. By weighted diffusion of the V value vector of each nozzle, an interference adjustment vector group U can be formed. This processing process reflects the simulation of the disturbance conduction path, that is, the degree of influence of the actual offset of a certain nozzle on its adjacent spraying area. Compared with the traditional direct correction of the V vector, this solution can more accurately capture the disturbance resonance and local amplification phenomenon under array coupling. The establishment of the U vector group not only retains the physical dimension of V, but also reasonably weights the error propagation direction, thereby improving the accuracy of disturbance trend assessment, especially in the high-speed collaborative operation scenario of multiple nozzles.

[0044] Finally, the corresponding disturbance influence factor matrix D is constructed with the nozzle number as the index, and each row corresponds to the disturbance weight distribution of a nozzle.

[0045] S3: Based on the correlation matrix and the disturbance influence factor matrix, and utilizing the disturbance mapping relationship between the interference trend and the offset trend between the nozzles, a three-parameter joint fine-tuning matrix is ​​constructed. The joint fine-tuning matrix is ​​used to dynamically couple and adjust the paint mixing parameters, spraying speed, and nozzle movement speed corresponding to each nozzle.

[0046] Preferably, with the nozzle number as the axis, the nozzle coupling degree and offset trend are extracted from the correlation matrix and the disturbance influence factor matrix respectively to construct the disturbance state tensor T. Each dimension of the disturbance state tensor T corresponds to the interference direction between the nozzles, the spray displacement trend and the physical position index. It can be seen that the nozzle number is essentially the unique identifier of the nozzle and can be mapped one-to-one to the physical position. For a nozzle numbered i, its row in the correlation matrix represents the intensity of interference from all other nozzles to the nozzle. The higher the value, the greater the influence between the nozzles. At the same time, the corresponding row in the disturbance influence factor matrix D represents the spray offset trend of the nozzle in each direction. These two data sources jointly characterize the disturbance characteristics and spatial variation trend of nozzle i. In order to perform data fusion on this type of three-dimensional relationship, the present invention constructs a disturbance state tensor T, which can be understood as a three-dimensional matrix structure under multiple nozzles, and its dimensions correspond to: interference direction (such as the main / auxiliary direction relationship between nozzles), spraying offset trend direction (i.e., physical disturbance vector, such as X / Y / Z axis) and nozzle physical number (used to locate the nozzle in the physical array). By performing tensor synthesis on the interference vector and offset vector of each nozzle i, the i-th layer of tensor T can be formed. This construction method not only retains the spatial topological structure between nozzles, but also effectively integrates their dynamic operation status. Compared with traditional two-dimensional matrix processing, this method uses tensor data structure to enhance feature expression capabilities, which facilitates efficient indexing and calling in subsequent rule lookup and fine-tuning control.

[0047] It can be seen that the present invention combines the above two matrices to extract the disturbance mapping relationship between the interference trend between the nozzles and the spray offset trend, thereby constructing a new joint fine-tuning matrix. This matrix uses the nozzle as the unit, and adjusts the three core control parameters of each nozzle: the paint mixing parameters (such as the ratio of main and auxiliary paints, viscosity adjustment value), the spraying speed (that is, the speed at which the paint leaves the nozzle, affecting the coating thickness), and the nozzle movement speed (that is, the linear speed at which the nozzle moves relative to the workpiece surface), to achieve dynamic adaptive adjustment of the nozzle coupling state. Each row of the matrix corresponds to a nozzle, and each column is an adjustable parameter, ultimately forming a dynamic, time-varying linkage control input, so that the system still maintains spraying uniformity and system stability in the multi-nozzle working mode, solving the coupling imbalance problem existing in traditional independent parameter control.

[0048] It is better to set the basic spraying parameter group P0 = {α0, β0, γ0}, which corresponds to the default paint mixing parameters, spraying speed, and nozzle movement speed respectively; among them, bundling the three parameters into a basic parameter group can avoid the coupling imbalance problem caused by independent adjustment of a single parameter.

[0049] It should be noted that when the spray system is started or a specific cycle is initialized, to ensure that the control system has a unified and stable initial state, the present invention introduces a basic spray parameter group setting strategy. This parameter group is typically set by process engineers based on the spray type, coating properties, and target surface, providing a basic reference frame for the nozzle control module. The parameter group consists of three key indicators: the coating mixing parameter, which represents the mixing ratio or blending concentration of different coating components (such as the base and curing agent); the spray velocity, which is the linear velocity at which the spray material is ejected from the nozzle, directly affecting coverage thickness and adhesion; and the nozzle movement speed, which is the speed at which the nozzle moves along the trajectory, which has a significant impact on film uniformity and surface quality. In conventional systems, engineers may independently adjust a single parameter, such as adjusting the spray velocity to address air flow disturbances or increasing the nozzle movement speed to improve cycle efficiency. However, in a spray environment with dynamically coupled multiple parameters, this single parameter adjustment can disrupt the original control balance. For example, if the nozzle speed is increased without synchronously adjusting the spray velocity, this can lead to fractured spray layers or uneven thickness. Therefore, the present invention proposes bundling these three parameters into a single, integrated set for adjustment, forming a base parameter set that serves as a benchmark for subsequent fine-tuning of the offset. Subsequent offset corrections are no longer targeted at a single parameter, but rather a coordinated correction of the entire set of parameters. This ensures the overall system coupling is balanced and avoids the risk of uncontrolled "one-touch-all" effects. This design not only enhances the stability of the control system but also provides a unified reference for tensor mapping relationships, making parameter mapping more engineering-logical and feasible.

[0050] Furthermore, based on the interference direction and disturbance offset direction of each nozzle in the disturbance state tensor T, a nozzle parameter adjustment offset set ΔP = {Δα, Δβ, Δγ} is constructed. This means that the disturbance and interference trends exhibited by the nozzles in T are matched to a parameter offset mapping table through a lookup rule. ΔP is then assigned to each nozzle as its dynamic adjustment value based on P0. It should be noted that this invention determines the three parameter adjustment values ​​through a lookup table based on preset rules, replacing the traditional control weight method, simplifying the logic and facilitating embedded implementation.

[0051] Traditional control systems usually use the "weighted coefficient multiplied by error" method for fine-tuning, for example, projecting the disturbance vector into an error term, and then using a proportional factor for linear control. However, this method is often highly dependent on the proportional factor, making parameter adjustment difficult, and has low operating efficiency in embedded controllers. The present invention avoids the complexity of floating-point operations and weight coefficient adjustment through a table lookup method, and directly obtains the adjustment amount of the three parameters quickly through a discrete state-offset comparison table, greatly improving the computing efficiency and system response speed, and is particularly suitable for resource-constrained industrial embedded control systems. The table lookup method can also ensure that the adjustment range is limited to the safe operating range, avoiding over-adjustment or critical oscillation, and improving the robustness of the system.

[0052] Preferably, the nozzle number is used as the index, and the basic parameter group P0 and the offset group ΔP are combined to generate a three-parameter joint fine-tuning matrix M. Each row is the three-parameter adjustment result corresponding to the nozzle, that is, the ternary parameter group of each nozzle is represented as M i =P 0i +ΔP i , obtaining the final three-parameter joint fine-tuning matrix M, which serves as the input to the linkage control module. Furthermore, this matrix can not only be refreshed periodically (e.g., before each task round) but can also be reconstructed in real time based on a disturbance trigger mechanism. That is, upon detecting a dramatic change in the disturbance tensor T, the system automatically invokes a table lookup mechanism to reset ΔP and rebuild the joint fine-tuning matrix M. This structure enables the control system to possess high responsiveness, strong dynamics, and coupled stability, effectively supporting the linkage operation of large-scale multi-nozzle systems.

[0053] S4: Based on the parameter correction amount output by the joint fine-tuning matrix, the paint mixing parameters, spraying speed and moving speed corresponding to the current nozzle are dynamically adjusted according to the nozzle number to achieve synchronous control of the spraying thickness and its spatial uniformity.

[0054] The preferred approach is to index the joint fine-tuning matrix M based on the nozzle number to extract the parameter correction group corresponding to each nozzle. These groups correspond to the current nozzle's paint mixing parameters, spray velocity, and nozzle movement speed settings. It should be noted that using the joint fine-tuning matrix M directly as a scheduling reference source to bind the number index to the control parameters avoids the traditional nozzle-parameter mapping table lookup process and improves control efficiency. Furthermore, during this operation, the nozzle number is used as a direct index pointer to quickly access the corresponding row in the joint fine-tuning matrix M, thereby obtaining the three correction values ​​for the current nozzle. This direct number access method skips the traditional intermediate table lookup, eliminating the need to first search for the nozzle ID and then map the control strategy. This significantly reduces the control system's response latency and facilitates parallel execution of control instructions. Furthermore, this mechanism offers excellent scalability. Even if the number of nozzles is subsequently increased, only the number of rows in the joint fine-tuning matrix M needs to be expanded, while the core control logic remains unchanged, avoiding the need to redesign the control path due to system scale changes. The number indexing mechanism can also be implemented in embedded controllers as an array pointer or index address, making the system highly portable and real-time.

[0055] Preferably, according to the mixing ratio instruction of the paint mixing parameters in the parameter group, the opening combination of multiple component valves in the feed unit is controlled to adjust the component mixing ratio of the current nozzle paint; according to the spraying speed instruction of the spraying speed in the parameter group, the internal pressure delivery system or pulse drive frequency of the nozzle is adjusted to output the material flow matching the mixing ratio; according to the moving speed instruction of the nozzle moving speed setting value in the parameter group, the trajectory speed of the nozzle actuator is controlled, and the spraying thickness and coverage uniformity are controlled based on the ratio between it and the spraying speed.

[0056] Exemplarily, the correction value of the spraying speed is provided by the joint fine-tuning matrix M matrix, which is directly used as the input parameter of the pressure-feeding mechanism or pulse driver in the nozzle. There are significant differences in the spraying speed required for different paint types and different mixing ratios. If the spraying speed does not change synchronously after the mixing ratio is adjusted, it may cause the paint to spray thinly, splash or sag, affecting the spraying quality. The spraying speed control can be achieved in the following two ways: if a pressure-feeding system (such as a servo motor driven pump) is used to transport the paint, the pump speed can be adjusted according to the instructions to achieve flow regulation; if a pulse-type nozzle (such as a piezoelectric nozzle) is used, the pulse spraying amount of the paint can be adjusted by adjusting the driving frequency or pulse width. The system performs feedback adjustment based on the feedback, and combines closed-loop correction with real-time sensor feedback (such as a flow meter or pressure gauge) to ensure that the material flow output by each nozzle matches its mixing ratio, achieving the dual purpose of material output consistency and coating thickness control.

[0057] Furthermore, there is a critical speed ratio matching relationship between the movement speed of the nozzle and its spraying speed. If the nozzle moves too slowly and the spraying speed is high, it will cause localized material piling; conversely, moving too fast will result in uneven spraying and exposed bottom. The present invention uses a three-parameter joint fine-tuning mechanism to simultaneously fine-tune the movement speed and the spraying speed, and ensure that their ratio relationship is always maintained in the optimal range. The adjustment of the nozzle movement speed is achieved by controlling the XYZ three-axis motion platform or the multi-joint robotic arm execution system. The speed adjustment amount instruction is given by the joint fine-tuning matrix M. After receiving the instruction, the control system uses it as the target speed adjustment factor of the trajectory planner and recalibrates the speed during the trajectory calculation, so that it can synchronously adjust the speed under the given path while maintaining trajectory stability. It is particularly important to point out that traditional systems often decouple path planning and spraying speed adjustment, while the present invention bundles them in the joint fine-tuning matrix M for joint adjustment, ensuring that the edges and movements are synchronously coupled on all nozzles, and there will be no ghosting, offset, or uneven thickness between the spray patterns.

[0058] In summary, the coordinated application of the joint fine-tuning matrix M and the numbering indexing mechanism enables dynamic linkage control of three parameters for multiple nozzles in the spray system. This not only improves control accuracy and response speed, but also significantly simplifies the control logic and enhances the system's robustness to external disturbances. By replacing the traditional mapping lookup table with a direct indexing mechanism, the controller can update nozzle parameters at a high frequency to adapt to rapidly changing interference environments. Furthermore, by adjusting the three parameters in an integrated manner, the coupling imbalance caused by single-parameter control is avoided, achieving significant results in actual spray thickness control and maintaining spatial uniformity.

[0059] S5: Based on the actual coating thickness difference and uniformity deviation obtained, the nozzle disturbance influence matrix is ​​updated and sent back to the joint fine-tuning matrix to complete the next round of control.

[0060] After completing a round of spraying operation, automatic detection will be started to accurately collect coating thickness and uniformity data for all sprayed areas.

[0061] Preferably, the thickness measurement data of the completed spraying area is collected and compared with the preset target thickness template to extract the thickness difference ΔH of the corresponding area of ​​each nozzle. i and local uniformity deviation ΔU i ; The thickness difference of each nozzle ΔH i Deviation from local uniformity ΔU i The combination is constructed as a bias vector ε i =ΔH i ,ΔU i ] and input it into the trajectory disturbance influence factor matrix, and perform exponential correction on the corresponding items of the nozzle in the disturbance matrix. In the embodiment, the exponential correction can be performed by the exponential attenuation coefficient, which is not limited to the embodiment of the present invention; the construction of this vector not only reflects the macroscopic thickness error of the nozzle spraying result, but also takes into account the local stability problem of the coating, forming a multi-dimensional feedback input. In the traditional spraying system, only ΔH is used. i As a feedback reference value, the complex spatial characteristics of spraying uniformity are ignored. i Features make the system more spatially adaptable.

[0062] The updated disturbance influence matrix is ​​recombined with the original nozzle array association matrix for parameter adjustment, dynamically generating a new round of three-parameter joint fine-tuning matrices. This three-parameter fine-tuning matrix is ​​then fed back for nozzle control and used as input for the next round of spray scheduling, achieving adaptive iteration of the multi-parameter control loop. Unlike conventional fixed-value spray control, the system of the present invention automatically generates a parameter matrix for each spraying task based on feedback from the previous round, forming a closed-loop adaptive control system based on local spraying state, disturbance modeling, parameter correction, and re-spraying feedback. This mechanism significantly reduces the system's reliance on human intervention and provides dynamic adaptability to different materials, environments, and target thickness templates.

[0063] In summary, the multi-parameter control method of the insulation layer spraying robot of the vacuum insulation panel based on the embodiment of the present invention is explained. It effectively solves the problems of uneven spraying thickness and poor spatial consistency by dynamically sensing and controlling the interference relationship and trajectory offset influence between multiple nozzles during the spraying process; it can realize the fine adjustment of nozzle parameters, so that each nozzle can maintain an ideal spraying state under different working conditions, thereby improving the overall spraying accuracy and stability. By introducing a multi-parameter joint control mechanism, the present invention can significantly reduce the spraying defects caused by factors such as posture deviation and coupling interference, and reduce the rework rate and material waste. Compared with the traditional method that is difficult to deal with the problems of real-time disturbance and local error accumulation during the spraying process, the present invention has stronger adaptability and control robustness, and is particularly suitable for high requirements such as the insulation layer of the vacuum insulation panel, and realizes the simultaneous optimization of spraying thickness and spatial uniformity, effectively improving the molding quality and production yield of the insulation layer of the vacuum insulation panel.

[0064] Figure 3 This is a structural diagram of a multi-parameter control system for a vacuum insulation panel insulation layer spraying robot according to an embodiment of the present invention. Figure 3 As shown, in the multi-parameter control system of the vacuum insulation panel insulation layer spraying robot, it includes: an array modeling module, which is used to model the spatial layout of the robot nozzle array and generate a nozzle array correlation matrix for representing the coupling effect between adjacent nozzles based on historical spraying data;

[0065] The trajectory acquisition module is used to collect the nozzle trajectory in real time during the spraying process, calculate the offset vector based on the posture error, and construct the trajectory disturbance influence factor matrix;

[0066] The fine-tuning matrix module is used to construct a three-parameter joint fine-tuning matrix based on the correlation matrix and the perturbation matrix;

[0067] The synchronous control module is used to dynamically adjust the current nozzle according to the nozzle number based on the parameter correction amount output by the joint fine-tuning matrix, thereby achieving synchronous control of the spray thickness and spatial uniformity;

[0068] The error feedback module is used to update the nozzle disturbance influence matrix based on the actual coating thickness difference and uniformity deviation obtained, and return it to the joint fine-tuning matrix to complete the next round of control.

[0069] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned multi-parameter control method of the insulation layer spraying robot of the vacuum insulation panel have been introduced in detail in the description of the multi-parameter control method of the insulation layer spraying robot of the vacuum insulation panel from reference figure to figure above, and therefore, its repeated description will be omitted.

[0070] In summary, the multi-parameter control method for a vacuum insulation panel insulation spraying robot, based on an embodiment of the present invention, is demonstrated. This method uses time-series analysis of high-definition images of a patient's puncture site at different time points within a target monitoring period to determine whether the patient's puncture site has signs of infection. This improves the accuracy and timeliness of infection monitoring, facilitates early detection of infection signs, and enables timely action to reduce the incidence and severity of infection.

Claims

1. A multi-parameter control method for a vacuum insulation panel insulation layer spraying robot, characterized in that: include: Model the spatial layout of the robot nozzle array and generate a nozzle array correlation matrix based on historical spraying data to represent the coupling effect between adjacent nozzles; During the spraying process, the nozzle trajectory is collected in real time, the offset vector is calculated based on the posture error, and the trajectory disturbance influencing factor matrix is ​​constructed; Based on the correlation matrix and the perturbation matrix, a three-parameter joint fine-tuning matrix is ​​constructed; Based on the parameter correction value output by the joint fine-tuning matrix, the current nozzle is dynamically adjusted according to the nozzle number to achieve synchronous control of the spray thickness and spatial uniformity; Based on the actual coating thickness difference and uniformity deviation obtained, the nozzle disturbance influence matrix is ​​updated and fed back to the joint fine-tuning matrix to complete the next round of control.

2. The multi-parameter control method of the vacuum insulation panel insulation layer spraying robot according to claim 1 is characterized in that: The modeling of the spatial layout of the robot nozzle array includes: forming a spatial layout parameter group by calibrating the relative position coordinates, pitch angle and array spacing of the robot nozzle array under a standard spraying task.

3. The multi-parameter control method of the vacuum insulation panel insulation layer spraying robot according to claim 2, characterized in that: The construction of the nozzle array association matrix includes: performing statistical analysis on the overlapping sections of the trajectories of adjacent nozzles in the historical data set, combining the spraying thickness deviation value, determining the interference weight of each nozzle on its adjacent nozzle, and extracting it as a coupling weight vector; taking the spatial arrangement parameter group and the coupling weight vector as input, normalizing and fusing the spatial distance of each pair of nozzle numbers with the historical interference intensity, and generating a nozzle array association matrix for representing the coupling relationship.

4. The multi-parameter control method for a vacuum insulation panel insulation layer spraying robot according to claim 1, characterized in that: Calculating the offset vector based on the posture error includes: Based on the current posture parameter group Q of the nozzle recorded by the spray controller and the target posture parameter group Q0 set by the task, the posture error term ΔQ of the nozzle in the six-degree-of-freedom space is calculated; By projecting the linear offset part of the posture error term ΔQ to the spray axis direction, the actual spray axis offset vector V of each nozzle is extracted as a physical quantity that characterizes the actual deviation trend of the spray beam.

5. The multi-parameter control method of the vacuum insulation panel insulation layer spraying robot according to claim 1 is characterized in that: The three parameters include paint mixing parameters, spraying speed and nozzle moving speed.

6. The multi-parameter control method for a vacuum insulation panel insulation layer spraying robot according to claim 5, characterized in that: The construction of the joint fine-tuning matrix includes: taking the nozzle number as the axis, extracting the nozzle coupling degree and offset trend from the correlation matrix and the disturbance influence factor matrix respectively, and constructing the disturbance state tensor T; each dimension of the disturbance state tensor T corresponds to the interference direction between the nozzles, the spraying displacement trend and the physical position index; setting the basic spraying parameter group P0 = {α0, β0, γ0}, which respectively correspond to the default paint mixing parameters, spraying speed, and nozzle movement speed; constructing the nozzle parameter adjustment offset group ΔP = {Δα, Δβ, Δγ} according to the interference direction and disturbance offset direction of each nozzle in the disturbance state tensor T; taking the nozzle number as the index, combining the basic parameter group P0 and the offset group ΔP to generate a three-parameter joint fine-tuning matrix M, wherein each row is the three-parameter adjustment result corresponding to the nozzle.

7. The multi-parameter control method for a vacuum insulation panel insulation layer spraying robot according to claim 1, characterized in that: The dynamic adjustment of the current nozzle includes: extracting the parameter correction group corresponding to each nozzle based on the nozzle number index joint fine-tuning matrix M, which corresponds to the paint mixing parameters, spraying speed and nozzle movement speed setting values ​​of the current nozzle respectively; and regulating the paint mixing parameters, spraying speed and nozzle movement speed respectively according to the parameter group instructions.

8. The multi-parameter control method for a vacuum insulation panel insulation layer spraying robot according to claim 1, characterized in that: The actual coating thickness difference and uniformity deviation include: collecting thickness measurement data in the completed spraying area, and extracting the thickness difference and local uniformity deviation of the area corresponding to each nozzle by comparing it with a preset target thickness template; combining the thickness difference and local uniformity deviation of each nozzle to construct a deviation vector.

9. The multi-parameter control method for a vacuum insulation panel insulation layer spraying robot according to claim 8, characterized in that: The updating of the nozzle disturbance influence matrix includes: inputting the deviation vector into the trajectory disturbance influence factor matrix, and performing exponential correction on the nozzle corresponding item in the disturbance matrix.

10. A multi-parameter control system for a vacuum insulation panel insulation layer spraying robot, using the method according to any one of claims 1 to 9 to perform multi-parameter control on the vacuum insulation panel insulation layer spraying robot, characterized in that: include: The array modeling module is used to model the spatial layout of the robot nozzle array and generate a nozzle array correlation matrix based on historical spraying data to represent the coupling effect between adjacent nozzles; The trajectory acquisition module is used to collect the nozzle trajectory in real time during the spraying process, calculate the offset vector based on the posture error, and construct the trajectory disturbance influence factor matrix; The fine-tuning matrix module is used to construct a three-parameter joint fine-tuning matrix based on the correlation matrix and the perturbation matrix; The synchronous control module is used to dynamically adjust the current nozzle according to the nozzle number based on the parameter correction amount output by the joint fine-tuning matrix, thereby achieving synchronous control of the spray thickness and spatial uniformity; The error feedback module is used to update the nozzle disturbance influence matrix based on the actual coating thickness difference and uniformity deviation obtained, and return it to the joint fine-tuning matrix to complete the next round of control.

Images