Intelligent spraying construction control method and system based on image processing and medium

Abstract

The invention relates to the technical field of image processing, and discloses an intelligent spraying construction control method and system based on image processing and a medium. The method comprises the following steps: performing image acquisition and defect analysis on an outer wall base layer to generate reference data; performing lattice optimization and path planning based on the reference data; environment parameters are collected, a compensation database is established, and a process regulation matrix is generated; coating quality is monitored in real time, and a data set and an early warning library are generated; the spraying track is optimized, and a control instruction is generated; and evaluating the construction quality to form an evaluation system. Intelligent spraying quality real-time monitoring and self-adaptive adjustment based on image processing are realized, so that the automation level and the quality control precision of outer wall spraying construction are improved.

Description

Technical Field

[0001] This application relates to the field of image processing, and particularly to an intelligent spraying construction control method, system and medium based on image processing. Background Art

[0002] In the field of building exterior wall spraying construction, traditional manual spraying methods have problems such as low efficiency and unstable quality. With the development of automation technology, spraying robots have begun to be applied to exterior wall construction, and automated construction is carried out through preset spraying paths and process parameters. The current intelligent spraying systems have been able to achieve basic automatic spraying functions, including automatically adjusting spraying pressure, controlling spraying distance and speed, etc., and can basically monitor and control the spraying quality.

[0003] However, there are still many deficiencies in the existing intelligent spraying technologies in practical applications. First, there is a lack of accurate assessment and analysis capabilities for the substrate conditions, resulting in a lack of pertinence in setting spraying parameters; second, it is unable to make real-time adjustments according to environmental changes and quality fluctuations during the construction process, resulting in uneven coating quality; third, the quality monitoring means are single, it is difficult to form a complete quality assessment system, and it cannot effectively guide the optimization and adjustment of the construction process. These problems seriously affect the quality and efficiency of intelligent spraying construction. Summary of the Invention

[0004] This application provides an intelligent spraying construction control method, system and medium based on image processing, which is used to realize real-time monitoring and adaptive adjustment of intelligent spraying quality based on image processing, so as to improve the automation level and quality control accuracy of exterior wall spraying construction.

[0005] In a first aspect, the present application provides an intelligent spraying construction control method based on image processing. The intelligent spraying construction control method based on image processing includes: collecting images of the surface of the building exterior wall base layer, locating the hollow area and analyzing the crack distribution of the obtained image data, generating a base layer defect feature map and a surface parameter matrix, and extracting intelligent spraying reference data according to the base layer defect feature map; according to the intelligent spraying reference data and the surface parameter matrix, performing grid preprocessing on the building exterior wall to obtain an initial grid scheme, and optimizing the initial grid scheme in combination with the building elevation features to generate a grid control parameter set and a spraying path planning library; collecting the temperature, humidity and wind force parameters in the construction environment, dynamically detecting the coating characteristics according to the temperature, humidity and wind force parameters, establishing an environmental compensation database in combination with the grid control parameter set, and generating a spraying process regulation matrix; collecting the coating forming data during the spraying process, calculating the coating uniformity index and the coverage parameter according to the coating forming data, and generating a quality monitoring data set and a defect warning parameter library in combination with the spraying process regulation matrix; based on the quality monitoring data set and the environmental compensation database, in combination with the spraying path planning library and the defect warning parameter library, optimizing the spraying trajectory in real time to generate an intelligent compensation control instruction; collecting the surface feature information of the sprayed area, calculating the construction quality index according to the surface feature information and the intelligent compensation control instruction, establishing a construction file including the quality monitoring data set, and forming a quality evaluation system.

[0006] In a second aspect, the present application provides an intelligent spraying construction control system based on image processing. The intelligent spraying construction control system based on image processing includes:

[0007] A collection module for collecting images of the surface of the building exterior wall base layer, locating the hollow area and analyzing the crack distribution of the obtained image data, generating a base layer defect feature map and a surface parameter matrix, and extracting intelligent spraying reference data according to the base layer defect feature map;

[0008] A processing module for performing grid preprocessing on the building exterior wall according to the intelligent spraying reference data and the surface parameter matrix to obtain an initial grid scheme, and optimizing the initial grid scheme in combination with the building elevation features to generate a grid control parameter set and a spraying path planning library;

[0009] A detection module for collecting the temperature, humidity and wind force parameters in the construction environment, dynamically detecting the coating characteristics according to the temperature, humidity and wind force parameters, establishing an environmental compensation database in combination with the grid control parameter set, and generating a spraying process regulation matrix;

[0010] A generation module, configured to collect coating forming data during the spraying process, calculate a coating uniformity index and a coverage parameter according to the coating forming data, and generate a quality monitoring data set and a defect warning parameter library in combination with the spraying process regulation matrix;

[0011] An optimization module, configured to perform real-time optimization on the spraying trajectory based on the quality monitoring data set and the environmental compensation database, in combination with the spraying path planning library and the defect warning parameter library, and generate an intelligent compensation control instruction;

[0012] A calculation module, configured to collect surface feature information of the sprayed completed area, calculate a construction quality index according to the surface feature information and the intelligent compensation control instruction, establish a construction file including the quality monitoring data set, and form a quality assessment system.

[0013] A third aspect of the present application provides a computer-readable storage medium, in which instructions are stored, and when the instructions run on a computer, the computer is enabled to execute the above-mentioned intelligent spraying construction control method based on image processing.

[0014] In the technical solution provided by the present application, by collecting and analyzing images of the surface of the building exterior wall base layer, accurate positioning of the hollow areas and cracks is achieved, and a base layer defect feature map and a surface parameter matrix are generated, providing an accurate basis for subsequent construction; by performing grid preprocessing on the building exterior wall and optimizing in combination with the building elevation features, an accurate grid control parameter set and a spraying path planning library are generated, realizing a reasonable division of the construction area and an optimized planning of the spraying path; collecting and dynamically detecting the temperature, humidity and wind force parameters in the construction environment, establishing an environmental compensation database in combination with the grid control parameter set, and generating a spraying process regulation matrix, effectively solving the influence of environmental factors on the construction quality; by collecting the coating forming data during the spraying process in real time, calculating the coating uniformity index and the coverage parameter, and generating a quality monitoring data set and a defect warning parameter library in combination with the spraying process regulation matrix, realizing real-time monitoring of the spraying quality; based on the quality monitoring data set and the environmental compensation database, performing real-time optimization on the spraying trajectory in combination with the spraying path planning library and the defect warning parameter library, and generating an intelligent compensation control instruction, ensuring the accuracy of the spraying construction; finally, by collecting the surface feature information of the sprayed completed area, calculating the construction quality index according to the surface feature information and the intelligent compensation control instruction, establishing a construction file including the quality monitoring data set, and forming a quality assessment system, realizing the quality traceability and assessment of the whole construction process. Description of the Drawings

[0015] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0016] Figure 1 It is a schematic diagram of an embodiment of the intelligent spraying construction control method based on image processing in the embodiments of the present application;

[0017] Figure 2 It is a schematic diagram of the quality change trend chart in the embodiments of the present application;

[0018] Figure 3 It is a schematic diagram of the measuring point layout on the surface of the intermediate coating in the embodiments of the present application;

[0019] Figure 4 It is a schematic diagram of an embodiment of the intelligent spraying construction control system based on image processing in the embodiments of the present application. Specific Embodiments

[0020] The embodiments of the present application provide an intelligent spraying construction control method, system and medium based on image processing. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and above-mentioned accompanying drawings of the present application are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the term "comprising" or "having" and any deformation thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0021] For ease of understanding, the following describes the specific process of the embodiments of the present application. Please refer to Figure 1 , an embodiment of the intelligent spraying construction control method based on image processing in the embodiments of the present application includes:

[0022] Step S101: Collect images of the surface of the building exterior wall base layer, locate the hollow areas and analyze the crack distribution of the acquired image data, generate a base layer defect feature map and a surface parameter matrix, and extract intelligent spraying reference data according to the base layer defect feature map;

[0023] Step S102: According to the intelligent spraying reference data and the surface parameter matrix, perform grid preprocessing on the building exterior wall to obtain an initial grid plan, and optimize the initial grid plan in combination with the building elevation characteristics to generate a grid control parameter set and a spraying path planning library;

[0024] Step S103: Collect the temperature, humidity, and wind force parameters in the construction environment, dynamically detect the coating characteristics according to the temperature, humidity, and wind force parameters, establish an environmental compensation database in combination with the grid control parameter set, and generate a spraying process regulation matrix;

[0025] Step S104: Collect the coating forming data during the spraying process, calculate the coating uniformity index and coverage parameters according to the coating forming data, and generate a quality monitoring data set and a defect warning parameter library in combination with the spraying process regulation matrix;

[0026] Step S105: Based on the quality monitoring data set and the environmental compensation database, in combination with the spraying path planning library and the defect warning parameter library, perform real-time optimization on the spraying trajectory to generate intelligent compensation control instructions;

[0027] Step S106: Collect the surface feature information of the sprayed completed area, calculate the construction quality index according to the surface feature information and the intelligent compensation control instructions, establish a construction file containing the quality monitoring data set, and form a quality assessment system.

[0028] It can be understood that the execution subject of this application can be an intelligent spraying construction control system based on image processing, or a terminal or a server. Specifically, it is not limited here. This application embodiment is described by taking the server as the execution subject as an example.

[0029] Specifically, when spraying the building exterior wall, a multi-channel high-definition imaging device is used to scan the surface of the exterior wall base layer. During the scanning process, the camera moves along the preset trajectory at a moving speed of 0.5 m / s to collect image data, and the obtained image data is preprocessed to form a standardized digital image. When locating the hollow area of these image data, the internal structure of the wall is detected by infrared thermal imaging technology, and the detection data is subjected to Fourier transform to obtain a spectral feature map. By performing threshold segmentation on the spectral feature map, the temperature abnormal areas are identified, and these areas are the potential hollow positions. Then, the crack distribution analysis is carried out. The edge detection algorithm is used to extract the crack contour, and the length, width, and distribution density of the cracks are calculated. After these processes, a base layer defect feature map containing the hollow area ratio and crack distribution information is generated. At the same time, the surface roughness and flatness are measured to construct a surface parameter matrix.

[0030] Based on the obtained base defect feature map and surface parameter matrix, preprocess the grid division of the building exterior wall. Use the distribution information of the hollow area in the intelligent spraying reference data to set the grid density, perform weighted calculation on the base grid data, and generate the weight value of each partition. These weight values determine the size and shape of the grid division. Areas with higher weights require more detailed grid division processing. Merge the areas according to the standard of 1.5 meters × 1.5 meters to form an initial grid division plan. Subsequently, extract the feature of the building exterior facade, identify structural features such as windows and balconies, and adjust and optimize the grid boundary according to these features. Calculate the area, position, and boundary eigenvalue of each grid area to form a grid control parameter set, and plan the motion trajectory of the spraying robot based on this, and store the sequence of trajectory points in the spraying path planning library.

[0031] During the construction process, collect the temperature, humidity, and wind speed data in the construction environment through sensors, segment these environmental parameters at time intervals to obtain the average environmental parameter value of each time period. Take samples of the paint for testing, analyze the relationship between the environmental parameters and the paint viscosity, and establish an environmental-paint dynamic association database. Integrate these data with the grid control parameter set to finally generate a spraying process regulation matrix. During the spraying operation, obtain the coating forming data through real-time image acquisition, perform partition marking and segmentation processing on these data, and extract color difference and texture features. Calculate the coating uniformity index based on these features to evaluate the coating quality. Obtain the coverage parameters of each partition through statistical analysis, perform correlation analysis on these parameters and the process parameters in the spraying process regulation matrix to generate a quality monitoring data set. Based on the parameter change trend, establish an early warning threshold and construct a defect early warning parameter library.

[0032] In order to optimize the spraying trajectory in real time, sort the coating uniformity index and coverage parameters in the quality monitoring data set by partition to obtain a quality parameter sequence. Extract the compensation coefficient of the current time period from the environmental compensation database and match it with the quality parameter sequence. At the same time, calculate the overlap rate based on the trajectory points in the spraying path planning library to obtain the trajectory compensation parameter. Combine the early warning threshold in the defect early warning parameter library to perform constraint processing on the compensation parameter, and finally generate an intelligent compensation control instruction.

[0033] Perform multi-angle imaging on the sprayed area to obtain surface feature information, compare this information with the compensation data in the intelligent compensation control instruction, and generate a construction quality deviation value. Perform point-by-point measurement on the coating surface with a digital level, filter it with a 2-mm error band after comparing it with the construction quality deviation value to obtain flatness data. Measure the glossiness data by incident measurement at a 60-degree angle and extract the qualified interval value. Combine the data in the weather resistance evaluation matrix to form a construction quality index. Organize the historical data in the quality monitoring data set into a quality change trend chart, establish a partition quality evaluation record, generate a construction file, and finally form a quality evaluation system.

[0034] In the embodiment of the present application, by collecting and analyzing images of the surface of the building exterior wall base layer, precise positioning of the hollow area and cracks is achieved, and a base layer defect feature map and a surface parameter matrix are generated, providing an accurate basis for subsequent construction; by performing grid preprocessing on the building exterior wall and optimizing it in combination with the building elevation features, an accurate grid control parameter set and a spraying path planning library are generated, realizing the reasonable division of the construction area and the optimized planning of the spraying path; collecting and dynamically detecting the temperature, humidity, and wind force parameters in the construction environment, establishing an environmental compensation database in combination with the grid control parameter set, and generating a spraying process regulation matrix, effectively solving the influence of environmental factors on the construction quality; by collecting the coating forming data during the spraying process in real time, calculating the coating uniformity index and coverage parameters, and generating a quality monitoring data set and a defect warning parameter library in combination with the spraying process regulation matrix, realizing real-time monitoring of the spraying quality; based on the quality monitoring data set and the environmental compensation database, combining the spraying path planning library and the defect warning parameter library to optimize the spraying trajectory in real time, generating an intelligent compensation control instruction, ensuring the accuracy of the spraying construction; finally, by collecting the surface feature information of the sprayed area, calculating the construction quality index according to the surface feature information and the intelligent compensation control instruction, establishing a construction file including the quality monitoring data set, and forming a quality evaluation system, realizing the quality traceability and evaluation of the entire construction process.

[0035] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0036] (1) Perform multi-angle scanning on the surface of the building exterior wall base layer with a high-definition camera to obtain the original image data of the exterior wall base layer;

[0037] (2) Perform partition slicing processing on the original image data of the exterior wall base layer according to the size of 1.5 m × 1.5 m to obtain the partition data of the base layer image;

[0038] (3) Perform graying and edge enhancement processing on the partition data of the base layer image to obtain the enhanced base layer image;

[0039] (4) Identify the hollow areas and extract the crack edges from the enhanced base layer image through image segmentation methods to generate a base layer defect feature map;

[0040] (5) Calculate the surface roughness, flatness, and color difference of each partition based on the enhanced base layer image to construct a surface parameter matrix;

[0041] (6) Perform weighted fusion on the hollow area ratio and crack length density in the base layer defect feature map and the data in the surface parameter matrix to generate intelligent spraying reference data.

[0042] Specifically, a high-resolution camera array is used to collect multi-angle images of the exterior wall base layer surface. The camera array consists of three high-definition cameras distributed at an angle of 120 degrees. The resolution of each camera is 4096×3072 pixels. When collecting images, the cameras maintain a fixed distance of 0.8 meters from the wall surface and perform synchronous collection every 0.5 meters. There is a 30% overlap rate between adjacent images. Through multi-angle collection, the unevenness and surface details of the wall surface can be effectively captured to form the original image data of the exterior wall base layer. After the image is obtained, the original image data is divided into multiple sub-regions according to the standard size of 1.5 meters×1.5 meters. The grid cutting algorithm is used in the division process, and feature point matching is performed in the image overlapping area to eliminate image stitching errors. Image fusion is performed on each partition in the overlapping part to ensure the continuity of the partition boundary, and the base layer image partition data is obtained.

[0043] Perform digital image preprocessing on the base layer image partition data, perform grayscale processing to convert the RGB three-channel image into a single-channel grayscale image, reducing the amount of data processing. Then, the adaptive histogram equalization method is used to enhance the image contrast and highlight the edge and texture information in the image. Next, the Gaussian difference operator is used for edge enhancement to improve the clarity and detail performance of the image, and the enhanced base layer image is obtained.

[0044] Defect detection is performed on the enhanced base layer image. The mathematical models for hollow area identification and crack edge extraction are expressed as:

[0045]

[0046] where D(x,y) represents the defect feature value, ω i is the weight coefficient for different types of defects, G(x,y) is the image gradient value, H(x,y) is the local gray mean value, μ x and μ y represent the defect center coordinates, σ x and σ y

[0047] represent the spatial distribution parameters of the defect area, and n is the number of defect types. The defect feature map is calculated through this model.

[0048] In terms of surface parameter calculation, a comprehensive evaluation model is established:

[0049]

[0050] Among them, M(r, p, c) is the comprehensive evaluation value of surface parameters; r is the surface roughness parameter; p is the flatness parameter; c is the color difference parameter; α is the roughness weight coefficient, with a value range of [0, 1]; β is the flatness weight coefficient, with a value range of [0, 1]; γ is the color difference weight coefficient, with a value range of [0, 1]; Z ij is the surface height value of the sampling point at the i-th row and j-th column; is the average height value of all sampling points; m is the number of rows of surface height sampling points; n is the number of columns of surface height sampling points; P k is the value of the k-th flatness measurement point; P k-1 is the value of the (k - 1)-th flatness measurement point; l is the total number of flatness measurement points; L i is the Lab color space component value of the current measurement point (i = 1, 2, 3 correspond to L, a, b respectively); is the reference value of the standard Lab color space component; i is the sampling point row index; j is the sampling point column index; k is the flatness measurement point index.

[0051] For the data in the base defect feature map and the surface parameter matrix, a hierarchical weighted fusion method is used to generate intelligent spraying reference data. The ratio of the hollow area and the crack length density are normalized, and then multi-level fusion is performed with the roughness, flatness, and color difference data in the surface parameter matrix. Corresponding weight coefficients are set for each level, and the final intelligent spraying reference data is obtained through iterative calculation.

[0052] For example, one standard area of 1.5 m × 1.5 m is selected for analysis. In the image acquisition stage, three high-definition cameras collect image data of this area from different angles. After image partition processing, two hollow defects are detected in this area, with areas of 200 square centimeters and 150 square centimeters respectively, and three cracks with a total length of 80 centimeters. The surface roughness measurement shows that there are many unevennesses in this area, and specific surface parameter values are calculated through data processing. These original data are weighted and fused to form the spraying reference parameters for this area.

[0053] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0054] (1) Divide the intelligent spraying reference data according to the distribution of the hollow areas to output the base grid data;

[0055] (2) Weight the basic grid data using the surface parameter matrix to obtain the wall surface partition weight values;

[0056] (3) Binarize the wall surface partition weight values and merge the regions according to the standard of 1.5 m × 1.5 m to generate an initial grid division scheme;

[0057] (4) Scan the structural features of the building exterior wall and extract the position information of windows and balconies, and correct the grid division boundaries in the initial grid division scheme;

[0058] (5) Calculate the area, position, and boundary feature values of each grid division region according to the corrected grid division boundaries to form a grid division control parameter set;

[0059] (6) Plan the motion trajectory points of the spraying robot according to the boundary feature values of each grid division region, and store the trajectory point sequence in the spraying path planning library.

[0060] Specifically, divide the grid density of the hollow area according to the intelligent spraying reference data. The grid density division uses the adaptive grid method, that is, denser grid points are set around the hollow area, and the grid point spacing gradually increases as the distance from the hollow area increases. For example, at the edge of the hollow area, the grid point spacing is set to 5 cm, and the grid spacing increases by 5 cm every 20 cm outward until the maximum grid spacing of 25 cm is reached. This dynamically changing grid density distribution forms the basic grid data. Then, use the surface parameter matrix to perform weighted calculation on the basic grid data. The specific method is to assign different weight coefficients to the three index values of roughness, flatness, and color difference in the surface parameter matrix, and obtain the comprehensive weight value of each grid point through weighted summation. For the grid points within each 1.5 m × 1.5 m area, calculate their average weight value as the wall surface partition weight value of this area.

[0061] Binarize the obtained wall surface partition weight values, set the threshold as the weight mean value, mark the area higher than the threshold as 1, and mark the area lower than the threshold as 0. Then, according to the standard size of 1.5 m × 1.5 m, merge the adjacent same-value regions to generate an initial grid division scheme. Next, perform a scan of the building exterior wall structural features, and use an edge detection algorithm to extract the position information of features such as windows and balconies. For each identified feature, record the four corner coordinates and the boundary contour line. According to this feature information, correct the grid division boundaries in the initial grid division scheme to ensure that the grid division boundaries do not pass through windows or balconies.

[0062] Perform parameter calculation on the corrected grid division boundaries to establish a grid division control parameter calculation model:

[0063]

[0064] Where: F(A,B,C) is the comprehensive eigenvalue of the grid area; t is the total number of grid areas; V i is the area of the i-th grid area; Q i is the position weight of the i-th grid area; s is the number of boundary nodes; E ij is the curvature value of the j-th boundary node in the i-th grid area; R ij is the relative position of the j-th boundary node in the i-th grid area; B k are the coordinates of the four main inflection points of the boundary; B k-1 represents the coordinate value of the (k - 1)-th inflection point; are the characteristic weight coefficients; i is the grid area number; j is the boundary node number; k is the inflection point number.

[0065] According to the calculated grid control parameter set, plan the motion trajectory of the spraying robot. Generate reference trajectory points within each grid area, and the density of the trajectory points is dynamically adjusted according to the area and boundary eigenvalue of the area. For areas with complex boundaries, increase the density of the trajectory points; for regular areas, use a trajectory point distribution with a standard spacing. Finally, arrange all the trajectory points in the order of spatial positions to form a trajectory point sequence and store it in the spraying path planning library.

[0066] For example, during wall construction, there are windows and two hollow defect areas in a standard area. Grid division is performed according to the positions of the hollow defects, and dense grid points with a 5 - centimeter spacing are set in the areas around the hollows, and the grid spacing gradually increases as the distance increases. Then, substitute the surface roughness data (value 0.8), flatness data (value 1.2), and color difference data (value 0.6) of this area into the weight calculation to obtain the area weight value. After binarization processing, merge the grid points with similar weight values into one spraying partition. The identified window position information is used to adjust the partition boundary to ensure that the partition boundary is set along the window contour. Finally, calculate the trajectory point sequence according to the geometric characteristics of the partition to complete the entire partition planning process.

[0067] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0068] (1) Collect temperature, humidity, and wind speed data in the construction environment through sensors to form an environmental parameter sequence;

[0069] (2) Segment the environmental parameter sequence according to the time interval, and calculate the average temperature, humidity, and wind force parameters for each time period;

[0070] (3) Take a sample of the paint for testing, and perform correlation processing on the average temperature, humidity, and wind force parameters with the paint viscosity data to obtain the environmental impact eigenvalue;

[0071] (4)Fuse the environmental impact characteristic values with the grid control parameter set to construct an environmental compensation database;

[0072] (5)Calculate the compensation factor based on the data in the environmental compensation database to obtain the environmental compensation coefficient;

[0073] (6)Convert the environmental compensation coefficient into spraying process parameters and generate a spraying process regulation matrix according to the partition numbers.

[0074] Specifically, temperature sensors, humidity sensors, and wind speed sensors are arranged at the construction site. The measurement accuracy of the temperature sensor is 0.1 °C, and the measurement range is from -30 °C to 70 °C; the measurement accuracy of the humidity sensor is 1% RH, and the measurement range is 0 - 100% RH; the measurement accuracy of the wind speed sensor is 0.1 m / s, and the measurement range is 0 - 30 m / s. These sensors collect data at 10-second intervals. Each data point includes a timestamp, a sensor ID, and a measured value, forming an environmental parameter sequence. The collected environmental parameter sequence is segmented with a 15-minute time window. Statistical analysis is performed on the data within each time window to calculate the average temperature value, the average relative humidity value, and the average wind speed value. At the same time, the fluctuation range of each parameter is recorded, and outliers are removed to ensure the accuracy of the data. The processed data forms the average temperature, humidity, and wind force parameters for each time period.

[0075] Samples of the paint are taken for regular testing, and a rotational viscometer is used to measure the dynamic viscosity value of the paint. The measured viscosity value is correlated with the average temperature, humidity, and wind force parameters of the same time period, and the environmental impact characteristic value is obtained through data fitting. This characteristic value reflects the degree of influence of environmental changes on the paint performance. Then, the environmental impact characteristic value is fused with the grid control parameter set. The grid control parameter set contains the area, location, and boundary characteristic values of each partition. These parameters are combined with the environmental impact characteristic value to construct an environmental compensation database. The database records the compensation parameters required for each partition under different environmental conditions.

[0076] Calculate the compensation factor based on the information in the environmental compensation database. The calculation of the compensation factor takes into account the influence of temperature on the paint viscosity, the influence of humidity on the drying speed, and the influence of wind speed on the deviation of the spraying trajectory to obtain the environmental compensation coefficient.

[0077] For the conversion of spraying process parameters, the following calculation model is established:

[0078]

[0079] Where: T(N,U,W) is the spraying process parameter matrix; n is the number of partitions; X i is the spraying pressure value of the i-th partition; Y iis the spraying distance value for the i-th partition; J i is the spraying speed value for the i-th partition; K ij is the environmental compensation coefficient for the j-th in the i-th partition; S ij is the standard parameter value for the j-th in the i-th partition; W k is the coating performance parameter for the k-th; U k is the environmental impact factor for the k-th; θ1, θ2, θ3 are the process parameter weight coefficients; m is the number of environmental compensation parameters; S is the number of coating performance parameters; i is the partition number; j is the compensation parameter number; k is the performance parameter number;

[0080] For example, the sensor collects that the temperature is 25°C, the relative humidity is 65%, and the wind speed is 2.5 m / s within a certain period. Sampling and testing the coating finds that under these environmental conditions, the coating viscosity increases compared to the standard value. Input this change into the environmental compensation database, and calculate a compensation plan that requires increasing the spraying pressure and reducing the spraying speed. According to the different partition positions, set a larger compensation coefficient for the high partitions that are more affected by the wind speed. Finally, integrate all the parameters to form a process control matrix to guide the robot for precise spraying.

[0081] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0082] (1) Perform real-time image acquisition on the spraying area, obtain the coating forming data, and mark the data according to the partition number;

[0083] (2) Process the coating forming data in segments at a preset sampling time interval, and extract the color difference and texture features of each segment of the coating;

[0084] (3) Calculate the uniformity index of the coating in each area according to the color difference and texture features to form the coating uniformity evaluation data;

[0085] (4) Conduct statistical analysis on the coating uniformity evaluation data to calculate the coverage parameters of the coating in each partition;

[0086] (5) Conduct correlation analysis on the coverage parameters and the process parameters corresponding to the spraying process control matrix to generate a quality monitoring data set;

[0087] (6) Establish a parameter warning threshold according to the parameter change trend in the quality monitoring data set, and construct a defect warning parameter library.

[0088] Specifically, during the spraying process, a high-resolution imaging device is used to collect real-time images of the spraying area. The imaging device includes an RGB camera and an infrared camera. The RGB camera has a resolution of 4096×3072 pixels and is used to collect color information on the coating surface; the infrared camera has a resolution of 1920×1080 pixels and is used to detect the curing state of the coating. The cameras are installed at the end of the spraying robot arm and move synchronously with the spraying action to ensure the continuity of image collection. Each collected image is automatically added with a timestamp and a partition identifier for subsequent data processing. The collected image data is segmented according to a 5-second time window. Within each time window, the color difference features of the coating are extracted, the RGB image is converted to the Lab color space, and the color difference value from the standard color sample is calculated. At the same time, texture analysis is performed on the image, and feature parameters such as contrast, entropy, energy, and correlation are extracted using the gray-level co-occurrence matrix method. To improve the analysis accuracy, multi-scale decomposition is performed on the image, and features are extracted at scales of 1×1, 2×2, and 4×4 respectively, and the final texture feature value is synthesized by a weighted method.

[0089] Based on the extracted color difference and texture features, the uniformity index of the coating is calculated. The color difference value is normalized to obtain a uniformity index between 0 and 1. Then, the surface texture uniformity is calculated using the texture features, including the texture consistency in the local area and the global texture distribution characteristics. By combining these indexes, the coating uniformity evaluation data is formed. Statistical analysis is performed on the coating uniformity evaluation data to calculate the coverage parameters of the coatings in each partition. The coverage parameter reflects the covering degree of the coating on the base layer and is evaluated by analyzing the gray-scale distribution, edge continuity, and texture integrity of the image. Multiple sampling points are set for each partition, the coverage values of the sampling points are calculated, and the coverage distribution map of the entire partition is obtained by interpolation.

[0090] The calculated coverage parameters are correlated with the parameters in the spraying process control matrix. The process parameters include spraying pressure, spraying distance, spraying speed, etc. By establishing the mapping relationship between the parameters, the influence of different process parameter combinations on the coating quality is analyzed. The correlation analysis uses the sliding time window method to calculate the correlation between parameter changes and quality changes in real time and generates a quality monitoring data set. Based on the quality monitoring data set, a parameter warning mechanism is established. By analyzing the distribution characteristics of historical data, the normal fluctuation range of each parameter is calculated. Three-level warning thresholds are set: a prompt warning is issued when the parameter deviates from the mean by 1 standard deviation, a warning warning is issued when it deviates by 2 standard deviations, and a severe warning is issued when it deviates by 3 standard deviations. These thresholds and the corresponding warning rules are stored in the defect warning parameter library.

[0091] For example, during real-time monitoring, the image acquisition system detects slight quality fluctuations in the coating of a certain area. Through analysis, it is found that the color difference value in this area fluctuates within the standard deviation range, but the contrast parameter in the texture features shows an abnormal increase. By querying the process parameters, it is found that the spraying pressure fluctuates slightly at this time. The system immediately activates a first-level warning to prompt adjustment of the spraying pressure parameter. Through timely parameter adjustment, the coating quality quickly returns to the normal level.

[0092] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0093] (1) Sort the coating uniformity index and coverage parameter in the quality monitoring dataset according to the partition number to obtain a quality parameter sequence;

[0094] (2) Extract the environmental compensation coefficient for the current time period from the environmental compensation database and perform data matching with the quality parameter sequence;

[0095] (3) Calculate the spraying overlap rate for each partition according to the trajectory point sequence in the spraying path planning library to obtain a trajectory compensation parameter;

[0096] (4) Extract the warning threshold from the defect warning parameter database and perform boundary constraint processing on the trajectory compensation parameter;

[0097] (5) Perform weighted calculation on the environmental compensation coefficient and the trajectory compensation parameter to form a compensation data stream;

[0098] (6) Calculate the adjusted spraying speed and spraying distance according to the compensation data stream and generate an intelligent compensation control instruction.

[0099] Specifically, during the spraying construction process, the coating uniformity index and coverage parameter are extracted from the quality monitoring dataset. The uniformity index reflects the degree of consistency on the coating surface, and the coverage parameter represents the covering effect of the coating on the substrate. Sort these data in ascending order according to the partition number to generate an ordered quality parameter sequence, and each sequence item includes the partition number, uniformity index value, and coverage value.

[0100] Retrieve the environmental data for the current time period from the environmental compensation database according to the timestamp. The environmental compensation coefficient includes a temperature compensation factor, a humidity compensation factor, and a wind speed compensation factor. Establish a corresponding relationship between these compensation coefficients and the data in each item of the quality parameter sequence to form a parameter-environment mapping table.

[0101] For the calculation of the spraying trajectory overlap rate, the following mathematical model is established:

[0102]

[0103] Where: Z(x, y, z) is the trajectory overlap compensation parameter; g is the number of partitions; U e is the spraying width of the e-th partition; V e is the trajectory spacing of the e-th partition; Y ef is the offset of the f-th trajectory point in the e-th partition; X ef is the standard spacing of the f-th trajectory point in the e-th partition; G d is the d-th trajectory feature parameter; F d is the d-th influencing factor; ξ1, ξ2, ξ3 are the overlap rate weight coefficients; h is the number of trajectory points; s is the number of feature parameters; e is the partition number; f is the trajectory point number; d is the feature number.

[0104] Extract the warning thresholds of each parameter from the defect warning parameter library, including the maximum allowable overlap rate and the minimum necessary overlap rate. Constrain the calculated trajectory compensation parameters according to these thresholds to ensure that the parameter values are within a reasonable range. Weight and fuse the environmental compensation coefficient and the trajectory compensation parameter according to the preset weight. The environmental compensation coefficient mainly affects the spraying pressure and the paint flow rate, and the trajectory compensation parameter mainly affects the spraying distance and the speed. Obtain the complete compensation data stream through weighted calculation.

[0105] Generate specific control instructions according to the compensation data stream. The adjusted spraying speed is the product of the reference speed and the compensation factor, and the spraying distance is fine-tuned according to the overlap rate requirement. These parameters are packaged into control instructions in a standard format and sent to the spraying robot for execution.

[0106] For example, real-time monitoring finds that the coating uniformity index in the 3rd partition shows a downward trend. At the same time, the environmental monitoring data shows that the wind speed in this area is relatively high. Analyzing the trajectory planning, it is found that this area is located at a corner and requires a higher trajectory overlap rate. Considering these factors, the compensation control module calculates an adjustment plan to reduce the spraying speed and shorten the spraying distance. By executing these compensation control instructions, the coating quality in this partition has been effectively improved.

[0107] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0108] (1) Collect multi-angle images of the sprayed area, and process the images to obtain surface feature information;

[0109] (2) Compare and analyze the surface feature information with the compensation data in the intelligent compensation control instruction to generate a construction quality deviation value;

[0110] (3) Calculate the coating flatness, glossiness and weather resistance data according to the construction quality deviation value to form a construction quality index;

[0111] (4) Sort the historical monitoring data in the quality monitoring dataset in chronological order to obtain a quality change trend chart;

[0112] (5) Establish a zonal quality assessment record based on the construction quality indicators and the quality change trend chart, and generate a construction file;

[0113] (6) Conduct statistical analysis on the data in the construction file, and divide it according to the evaluation dimension to form a quality assessment system.

[0114] Specifically, for the area where spraying is completed, a multi-angle image acquisition device is used to obtain surface information. The device includes three high-definition cameras, which take pictures of the wall from 0 degrees, 45 degrees, and 90 degrees respectively. The acquired images are preprocessed, including geometric correction, illumination equalization, and noise elimination. Feature extraction is performed on the processed images, including surface texture, color distribution, and edge features, so as to obtain surface feature information. The obtained surface feature information is compared and analyzed with the compensation data in the intelligent compensation control instruction. The compensation data includes compensation values of process parameters such as spraying pressure, spraying distance, and spraying speed. By comparing the difference between the actual construction effect and the expected effect, the construction quality deviation value is calculated. This deviation value reflects the adjustment effect of various parameters in the actual construction process.

[0115] According to the construction quality deviation value, a digital level is used to measure the flatness of the coating surface. When measuring, 9 measuring points are set in each area of 1.5 m × 1.5 m to form a measuring point grid. The data obtained from each measuring point is compared with the standard plane to calculate the deviation value. At the same time, a glossmeter is used to measure the coating surface at an incident angle of 60 degrees to obtain the surface glossiness data. The weather resistance data is evaluated by analyzing the density and bonding strength of the coating surface. These data together constitute the construction quality indicators. Perform time series analysis on the historical data in the quality monitoring dataset. The data includes all monitoring records from the start of construction to the current moment. Arrange these records in chronological order, and draw a quality change trend chart through data visualization technology. As Figure 2 shown, it is the quality change trend chart in the embodiment of the present application, which shows the change trends of three main quality indicators during the construction process of the exterior wall coating. The flatness index (solid line) remains relatively stable throughout the construction process, with only small fluctuations, which reflects the precise control ability of the intelligent spraying system for the coating thickness; the glossiness index (dashed line) shows large fluctuations but an overall upward trend, which is related to the dynamic changes of environmental factors and the adjustment process of compensation control; the weather resistance index (dash-dotted line) rapidly increases in the initial stage of construction and then tends to be stable, indicating that the coating performance gradually meets the design requirements during the construction process. The horizontal axis represents the construction time (min), and the vertical axis represents the quality index value (dimensionless). The trend chart intuitively shows the change rules of various quality indicators over time.

[0116] Combine construction quality indicators with quality trend charts to establish area quality assessment records. The records for each area include basic information (area number, construction time, construction personnel), quality indicator data (flatness, glossiness, weather resistance), and quality change trends. These records are sorted and archived to form a complete construction file. Finally, multi-dimensional statistical analysis is performed on the data in the construction file. From a technical dimension, analyze the physical performance indicators of the coating; from a process dimension, evaluate the control effect of construction parameters; from an environmental dimension, study the impact of external conditions on construction quality. Through this multi-dimensional analysis, a systematic quality assessment system is formed.

[0117] For example, conduct a quality assessment on a completed area. Obtain the surface images of the area through multi-angle shooting. After image processing, it is found that there are slight surface unevenness in local areas. Querying the intelligent compensation control instructions reveals that the wind speed was relatively high during construction in this area, and the system automatically increased the spraying pressure and decreased the spraying speed. Through measurement, it is found that the flatness index of this area is within the 2mm error range, the glossiness meets the required standard, and the weather resistance index is good. Comparing these data with historical monitoring records, it is found that although there were environmental factor interferences during the construction process, through intelligent compensation control, the construction quality reached the expected standard.

[0118] In a specific embodiment, the process of performing the steps of calculating the flatness, glossiness, and weather resistance data of the coating according to the construction quality deviation value may specifically include the following steps:

[0119] (1) Perform point-by-point measurement on the coating surface with a digital level, compare the measurement data with the construction quality deviation value, and calculate the flatness reference value;

[0120] (2) Perform a 2mm error band filtering process on the flatness reference value to obtain the coating flatness data;

[0121] (3) Use a glossmeter to perform 60-degree angle incidence measurement on the sprayed surface, correct the measurement result with the construction quality deviation value, and calculate the glossiness data;

[0122] (4) Compare the glossiness data with the process standard value and extract the qualified interval value of the glossiness;

[0123] (5) Construct a coating durability assessment matrix according to the construction quality deviation value and extract the weather resistance data from it;

[0124] (6) Perform weighted integration on the coating flatness data, the qualified interval value of the glossiness, and the weather resistance data to form the construction quality indicator.

[0125] Specifically, a digital level is used to measure the coating surface at discrete points. The nine-point method is adopted during the measurement, that is, 9 measuring points are evenly arranged within each standard area of 1.5 m × 1.5 m, forming a 3×3 measurement grid. As Figure 3 shown, it is a schematic diagram of the measuring point arrangement on the coating surface in the embodiment of the present application, showing the 9 measuring point arrangement schemes within the 1.5 m × 1.5 m standard detection area. The dashed lines represent the area bisectors, dividing the entire area into 9 equal small areas; the circles represent the positions of the measuring points; the solid outer frame represents the boundary of the detection area. The measuring points are evenly distributed within the area, ensuring the representativeness of the measurement data. The accuracy of the digital level is 0.1 mm, and the measurement range is ±10 mm. The difference between the elevation data obtained at each measuring point and the reference plane is recorded as the measuring point deviation value. These deviation values are compared and analyzed with the construction quality deviation values, and a preliminary flatness reference value is calculated. The obtained flatness reference value is subjected to a 2-mm error band filtering process. The filtering process uses a band-pass filter to truncate the deviation values greater than 2 mm and smooth the minor fluctuations less than 0.1 mm. Through this filtering method, outliers and noise interferences are eliminated, and more accurate coating flatness data are obtained.

[0126] In the glossiness measurement step, a standard glossiness meter is used to detect the coating surface. The incident angle of the glossiness meter is fixed at 60 degrees because this incident angle is most suitable for measuring the glossiness of exterior wall coatings of buildings and can accurately reflect the microscopic structural characteristics of the coating surface. During the measurement, 5 measuring points are taken within each standard area, and each measuring point is measured 3 times, and the average value is taken as the glossiness reading of that measuring point. These readings are corrected and calculated with the construction quality deviation values to obtain the actual glossiness data. The measured glossiness data is compared with the process standard value. The process standard value is a reference range preset according to the coating type and construction requirements, usually including an upper limit value and a lower limit value. Through comparison and analysis, it is determined whether the measured glossiness falls within the qualified range, and the qualified range value is recorded. This range value reflects the acceptable range of the coating surface glossiness.

[0127] A coating durability evaluation matrix is constructed based on the construction quality deviation values. The evaluation matrix includes multiple evaluation dimensions: the bonding strength between the coating and the substrate, surface density, crack resistance, water resistance, etc. Through the comprehensive analysis of these performance indicators, weather resistance data is extracted from the evaluation matrix, and these data reflect the long-term use performance of the coating. The coating flatness data, the glossiness qualified range value, and the weather resistance data are integrated according to different weights. The flatness data reflects the macroscopic quality of the coating, the glossiness data reflects the apparent quality of the coating, and the weather resistance data reflects the service life of the coating. Through weighted calculation, a comprehensive construction quality index is formed.

[0128] For example, within a certain standard detection area, elevation measurements are first taken at 9 measurement points using a digital level. After processing the measurement data, it is found that the maximum deviation appears at the edge of the area. By comparing with the construction quality deviation values, it is determined that this deviation is related to the environmental factors during construction. After filtering through a 2-mm error band, the flatness data for this area is obtained. Meanwhile, measurements are taken using a glossmeter, and the data from 5 measurement points, after averaging, falls within the qualified range specified by the process standard. Combining the coating durability evaluation results, the comprehensive quality index for this area is finally calculated.

[0129] The above described the intelligent spraying construction control method based on image processing in the embodiments of the present application. Next, the intelligent spraying construction control system based on image processing in the embodiments of the present application will be described. Please refer to Figure 4 , an embodiment of the intelligent spraying construction control system based on image processing in the embodiments of the present application includes:

[0130] An acquisition module 201, configured to collect images of the surface of the building exterior wall base, locate the hollow areas and analyze the crack distribution of the acquired image data, generate a base defect feature map and a surface parameter matrix, and extract intelligent spraying reference data according to the base defect feature map;

[0131] A processing module 202, configured to perform grid preprocessing on the building exterior wall according to the intelligent spraying reference data and the surface parameter matrix, obtain an initial grid scheme, and optimize the initial grid scheme in combination with the building elevation features to generate a grid control parameter set and a spraying path planning library;

[0132] A detection module 203, configured to collect the temperature, humidity, and wind force parameters in the construction environment, dynamically detect the coating properties according to the temperature, humidity, and wind force parameters, establish an environmental compensation database in combination with the grid control parameter set, and generate a spraying process regulation matrix;

[0133] A generation module 204, configured to collect the coating forming data during the spraying process, calculate the coating uniformity index and coverage parameters according to the coating forming data, and generate a quality monitoring data set and a defect warning parameter library in combination with the spraying process regulation matrix;

[0134] An optimization module 205, configured to perform real-time optimization on the spraying trajectory based on the quality monitoring data set and the environmental compensation database, in combination with the spraying path planning library and the defect warning parameter library, to generate an intelligent compensation control instruction;

[0135] A calculation module 206, configured to collect the surface feature information of the sprayed completed area, calculate the construction quality index according to the surface feature information and the intelligent compensation control instruction, establish a construction file including the quality monitoring data set, and form a quality evaluation system.

[0136] Through the collaborative cooperation of the above-mentioned various components, by collecting and analyzing images of the surface of the building exterior wall base layer, the precise positioning of the hollow areas and cracks is achieved, and the base defect feature map and surface parameter matrix are generated, providing an accurate basis for subsequent construction; by performing grid preprocessing on the building exterior wall and optimizing it in combination with the building facade features, an accurate grid control parameter set and spraying path planning library are generated, realizing the reasonable division of the construction area and the optimized planning of the spraying path; by collecting the temperature, humidity and wind force parameters in the construction environment and conducting dynamic detection, establishing an environmental compensation database in combination with the grid control parameter set, and generating a spraying process regulation matrix, effectively solving the influence of environmental factors on the construction quality; by collecting the coating forming data during the spraying process in real time, calculating the coating uniformity index and coverage parameters, and generating a quality monitoring data set and defect warning parameter library in combination with the spraying process regulation matrix, realizing the real-time monitoring of the spraying quality; based on the quality monitoring data set and the environmental compensation database, combining the spraying path planning library and the defect warning parameter library to optimize the spraying trajectory in real time, generating intelligent compensation control instructions, ensuring the accuracy of the spraying construction; finally, by collecting the surface feature information of the sprayed area, calculating the construction quality index according to the surface feature information and the intelligent compensation control instructions, establishing a construction file containing the quality monitoring data set, and forming a quality evaluation system, realizing the quality traceability and evaluation of the whole construction process.

[0137] This application also provides a computer-readable storage medium. The computer-readable storage medium can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a computer, the computer is made to execute the steps of the intelligent spraying construction control method based on image processing.

[0138] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described system, system and unit can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0139] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0140] As described above, the above embodiments are only used to illustrate the technical solution of this application and are not intended to limit it; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of various embodiments of this application.

Claims

1. An intelligent spraying construction control method based on image processing, characterized in that: The intelligent spraying construction control method based on image processing includes: Capture images of the base surface of the building exterior wall, locate hollow areas and analyze crack distribution on the acquired image data, generate a base defect feature map and a surface parameter matrix, and extract intelligent spraying benchmark data based on the base defect feature map; According to the intelligent spraying benchmark data and the surface parameter matrix, the building exterior wall is preprocessed to obtain an initial gridding scheme, and the initial gridding scheme is optimized in combination with the building facade features to generate a gridding control parameter set and a spraying path planning library; Collect temperature, humidity and wind parameters in the construction environment, dynamically detect the coating characteristics according to the temperature, humidity and wind parameters, establish an environmental compensation database in combination with the grid control parameter set, and generate a spraying process control matrix; Collect coating forming data during the spraying process, calculate coating uniformity index and coverage parameter according to the coating forming data, and generate quality monitoring data set and defect warning parameter library in combination with the spraying process control matrix; Based on the quality monitoring data set and the environmental compensation database, combined with the spray path planning library and the defect warning parameter library, the spray trajectory is optimized in real time to generate intelligent compensation control instructions; Collect surface feature information of the sprayed area, calculate construction quality indicators based on the surface feature information and intelligent compensation control instructions, establish a construction file containing the quality monitoring data set, and form a quality assessment system.

2. The intelligent spraying construction control method based on image processing according to claim 1 is characterized in that: The method includes collecting images of the surface of the base layer of the building exterior wall, locating the hollow area and analyzing the crack distribution of the acquired image data, generating a base layer defect feature map and a surface parameter matrix, and extracting intelligent spraying benchmark data according to the base layer defect feature map, including: Use a high-definition camera to scan the surface of the building's exterior wall base at multiple angles to obtain the original image data of the exterior wall base; The original image data of the exterior wall base layer is partitioned and sliced ​​according to a size of 1.5 meters × 1.5 meters to obtain base layer image partition data; graying and edge enhancement processing are performed on the base image partition data to obtain an enhanced base image; Using an image segmentation method, hollow area recognition and crack edge extraction are performed on the enhanced base layer image to generate a base layer defect feature map; Calculate the surface roughness, flatness and color difference value of each partition according to the enhanced base layer image, and construct a surface parameter matrix; The hollow area ratio, crack length density in the base defect characteristic map and the data in the surface parameter matrix are weightedly fused to generate intelligent spraying benchmark data.

3. The intelligent spraying construction control method based on image processing according to claim 1 is characterized in that: According to the intelligent spraying reference data and the surface parameter matrix, the building exterior wall is preprocessed to obtain an initial gridding scheme, and the initial gridding scheme is optimized in combination with the building facade features to generate a gridding control parameter set and a spraying path planning library, including: Divide the intelligent spraying benchmark data into grid density according to the hollow area distribution, and output the base grid data; Performing weighted calculation on the base grid data through the surface parameter matrix to obtain a wall partition weight value; Binarize the wall partition weight values, merge the regions according to the standard of 1.5 meters × 1.5 meters, and generate an initial partitioning scheme; Scanning the structural features of the building's exterior walls and extracting window and balcony location information, and correcting the grid boundaries in the initial grid scheme; The area, position and boundary characteristic value of each grid region are calculated according to the corrected grid boundary to form a grid control parameter set; The motion trajectory points of the spraying robot are planned according to the boundary characteristic values ​​of each grid area, and the trajectory point sequence is stored in the spraying path planning library.

4. The intelligent spraying construction control method based on image processing according to claim 1 is characterized in that: The temperature, humidity and wind parameters in the construction environment are collected, the coating characteristics are dynamically detected according to the temperature, humidity and wind parameters, an environmental compensation database is established in combination with the grid control parameter set, and a spraying process control matrix is ​​generated, including: The temperature, humidity and wind speed data in the construction environment are collected through sensors to form an environmental parameter sequence; The environmental parameter sequence is segmented according to time intervals, and the average temperature, humidity and wind parameters of each time period are calculated; Sampling and testing the paint, correlating the average temperature, humidity and wind force parameters with the paint viscosity data to obtain an environmental impact characteristic value; Performing data fusion on the environmental impact characteristic value and the grid control parameter set to construct an environmental compensation database; Calculate the compensation factor according to the data in the environmental compensation database to obtain the environmental compensation coefficient; The environmental compensation coefficient is converted into a spraying process parameter, and the spraying process control matrix is ​​generated by sorting the parameters according to the partition number.

5. The intelligent spraying construction control method based on image processing according to claim 1 is characterized in that: The coating forming data collected during the spraying process, the coating uniformity index and coverage parameter calculated according to the coating forming data, and the quality monitoring data set and defect warning parameter library generated in combination with the spraying process control matrix include: Collect real-time images of the spraying area, obtain coating forming data, and mark the data according to the partition number; Segmenting the coating forming data according to a preset sampling time interval to extract the color difference and texture features of each coating segment; Calculating the uniformity index of the coating in each area according to the color difference and texture characteristics to form coating uniformity evaluation data; Performing statistical analysis on the coating uniformity evaluation data to calculate the coverage parameters of each partition coating; Correlation analysis is performed on the coverage parameter and the process parameters corresponding to the spraying process control matrix to generate a quality monitoring data set; A parameter warning threshold is established according to the parameter change trend in the quality monitoring data set, and a defect warning parameter library is constructed.

6. The intelligent spraying construction control method based on image processing according to claim 1 is characterized in that: Based on the quality monitoring data set and the environmental compensation database, in combination with the spraying path planning library and the defect warning parameter library, the spraying trajectory is optimized in real time to generate intelligent compensation control instructions, including: Sorting the coating uniformity index and coverage parameter in the quality monitoring data set according to the partition number to obtain a quality parameter sequence; Extracting the environmental compensation coefficient of the current time period from the environmental compensation database and performing data matching with the quality parameter sequence; Calculate the spraying overlap rate of each partition according to the trajectory point sequence in the spraying path planning library to obtain the trajectory compensation parameter; Extracting a warning threshold from the defect warning parameter library and performing boundary constraint processing on the trajectory compensation parameter; Performing weighted calculation on the environment compensation coefficient and the trajectory compensation parameter to form a compensation data stream; The adjusted spraying speed and spraying distance are calculated according to the compensation data stream, and an intelligent compensation control instruction is generated.

7. The intelligent spraying construction control method based on image processing according to claim 1 is characterized in that: The surface feature information of the sprayed area is collected, the construction quality index is calculated according to the surface feature information and the intelligent compensation control instruction, a construction file containing the quality monitoring data set is established, and a quality evaluation system is formed, including: Collect multi-angle images of the sprayed area and process the images to obtain surface feature information; Comparing and analyzing the surface feature information with the compensation data in the intelligent compensation control instruction to generate a construction quality deviation value; Calculating the coating flatness, glossiness and weather resistance data according to the construction quality deviation value to form a construction quality index; Arrange the historical monitoring data in the quality monitoring data set in chronological order to obtain a quality change trend graph; Establish a zoning quality assessment record based on the construction quality indicators and quality change trend chart, and generate a construction file; Conduct statistical analysis on the data in the construction files and form a quality assessment system according to the assessment dimensions.

8. The intelligent spraying construction control method based on image processing according to claim 7 is characterized in that: The coating flatness, glossiness and weather resistance data are calculated according to the construction quality deviation value to form the construction quality index, including: The coating surface is measured at different points by a digital level, the measured data is compared with the construction quality deviation value, and a flatness reference value is calculated; Perform 2 mm error band filtering on the flatness reference value to obtain coating flatness data; The gloss meter is used to measure the sprayed surface at an incident angle of 60 degrees, and the measurement result is corrected with the construction quality deviation value to calculate the gloss data; Comparing the glossiness data with the process standard value to extract the glossiness qualified interval value; constructing a coating durability evaluation matrix according to the construction quality deviation value, and extracting weather resistance data therefrom; The coating flatness data, glossiness qualified interval value and weather resistance data are weighted and integrated to form a construction quality index.

9. An intelligent spraying construction control system based on image processing, used to implement the intelligent spraying construction control method based on image processing as described in any one of claims 1 to 8, characterized in that: The intelligent spraying construction control system based on image processing includes: The acquisition module is used to acquire images of the surface of the base layer of the building's exterior wall, locate the hollow area and analyze the crack distribution of the acquired image data, generate a base layer defect feature map and a surface parameter matrix, and extract intelligent spraying benchmark data based on the base layer defect feature map; A processing module is used to perform grid preprocessing on the building exterior wall according to the intelligent spraying benchmark data and the surface parameter matrix, obtain an initial grid scheme, optimize the initial grid scheme in combination with the building facade features, and generate a grid control parameter set and a spraying path planning library; A detection module is used to collect temperature, humidity and wind parameters in the construction environment, dynamically detect the coating characteristics according to the temperature, humidity and wind parameters, establish an environmental compensation database in combination with the grid control parameter set, and generate a spraying process control matrix; A generation module, used to collect coating forming data during the spraying process, calculate coating uniformity index and coverage parameter according to the coating forming data, and generate a quality monitoring data set and a defect warning parameter library in combination with the spraying process control matrix; An optimization module, for optimizing the spraying trajectory in real time and generating intelligent compensation control instructions based on the quality monitoring data set and the environmental compensation database, in combination with the spraying path planning library and the defect warning parameter library; The calculation module is used to collect surface feature information of the spraying completed area, calculate the construction quality index according to the surface feature information and the intelligent compensation control instruction, establish a construction file containing the quality monitoring data set, and form a quality evaluation system.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the intelligent spraying construction control method based on image processing as described in any one of claims 1 to 8 is implemented.

Images