A method and system for optimizing process parameters of a power transmission tower reinforcement

Abstract

The application provides a power transmission tower reinforcing process parameter optimization method and system, and relates to the technical field of power transmission tower reinforcement. The method comprises the following steps: obtaining image data of a power transmission tower to-be-sprayed base material; obtaining heterogeneity characteristic quantitative information of the to-be-sprayed base material by processing the image data; dividing the surface of the to-be-sprayed base material into multiple heterogeneity regions according to the heterogeneity characteristic quantitative information; determining the spraying reinforcement parameters of each heterogeneity region according to the heterogeneity characteristic quantitative information corresponding to the heterogeneity region; and controlling the spraying equipment to spray and reinforce each heterogeneity region according to the spraying reinforcement parameters. The method of the application aims to solve the problems of poor coating performance and the inability to realize real-time adaptive optimization of the base material caused by the uneven surface of the base material in the prior art, and improves the overall quality and reliability of the reinforcing coating.

Description

Technical Field

[0001] This invention relates to the field of power transmission tower reinforcement technology, and more specifically, to a method and system for optimizing process parameters for power transmission tower reinforcement. Background Technology

[0002] As a crucial component of the national power infrastructure, transmission towers are constantly exposed to harsh outdoor environments, inevitably suffering from wind and rain erosion, ultraviolet radiation, temperature fluctuations, and industrial pollution. These factors threaten the tower structure with corrosion and material fatigue, thus affecting its structural integrity and service life. To ensure the safe and stable operation of the power system, regular reinforcement and anti-corrosion maintenance of transmission towers is essential. Among these, applying anti-corrosion coatings is a core maintenance step. The protective performance of the coating is not determined by a single indicator but is the result of the combined effect of several key process parameters. Coating thickness and coating hardness are two interrelated and mutually restrictive core indicators: insufficient coating thickness cannot form an effective physical barrier layer, making it difficult to resist the intrusion of external corrosive media; while insufficient coating hardness makes it easily scratched or worn by external forces, also losing its protective function.

[0003] To improve the quality and efficiency of transmission tower reinforcement and maintenance, the industry has introduced automated operation and monitoring solutions based on drones. The workflow of this solution typically includes: First, a drone equipped with a high-resolution camera and specialized sensors (such as a binocular camera for 3D reconstruction or a thermal imaging camera that indirectly reflects the coating's curing degree) collects image data of the reinforced tower surface. The collected image data is then transmitted to a backend computing system, where advanced image processing algorithms perform in-depth analysis. Specifically, using 3D reconstruction technology, the system can accurately calculate the actual thickness of the coating at various points on the tower surface; simultaneously, by analyzing the coating's gloss, texture features, or thermodynamic properties, the system can indirectly assess the coating's hardness. To optimize coating performance, a process parameter optimization model is established in the system's backend. The core objective of this model is to simultaneously optimize both coating thickness and hardness by intelligently adjusting the process parameters of the automated spraying equipment, such as the distance between the nozzle and the tower surface, the spraying speed, the spraying pressure, and the coating viscosity.

[0004] However, in practice, it has been found that adjusting a single process parameter does not have a synchronous positive correlation with coating thickness and hardness; in fact, conflicts may exist. For example, deliberately reducing the spraying speed to increase coating thickness may lead to excessive paint buildup at single points, uneven solvent evaporation, and consequently, impaired coating curing, ultimately reducing coating hardness. Conversely, using fast-curing paint and increasing the spraying speed to achieve higher coating hardness may result in insufficient coating thickness in certain areas, failing to provide effective protection. Therefore, existing optimization models need to address these conflicts between multiple objectives, aiming to find a Pareto optimal solution set for engineers to make decisions in actual operations.

[0005] While the aforementioned drone-based automation solutions have made significant progress in improving coating thickness and hardness control, the surface condition of the substrate of transmission towers, as long-term service structures, is far from uniform. In actual maintenance operations, different parts of the tower may exhibit varying degrees of degradation, such as severe corrosion in localized areas, peeling or residue of old coatings, uneven surface roughness, and even slight surface deformation. This heterogeneity of the substrate is an inherent challenge that cannot be completely overcome by optimizing a single spraying parameter. Existing optimization methods based on drone image data processing primarily focus on assessing the thickness and hardness of the new coating after spraying, and partitioning the overall tower structure to accommodate its complex geometric differences. However, these methods often fall short in the detailed assessment and quantification of the substrate surface condition during the pre-spraying preparation stage. For example, while visible light images can identify macroscopic corrosion areas or peeling of old coatings, existing image processing technologies struggle to accurately quantify and characterize parameters crucial to coating performance, such as microscopic surface roughness, the degree of residual adhesion of old coatings, and substrate cleanliness.

[0006] Due to the lack of precise quantitative input regarding the heterogeneity of the substrate before spraying, existing multi-objective optimization models typically assume a homogeneous substrate when calculating spraying parameters, or only make rough adjustments based on experience for a few typical cases. Therefore, even if the model calculates the theoretically optimal coating thickness and hardness, the adhesion, uniformity, and even the final durability of the new coating may not meet expectations on real-world heterogeneous substrates. For example, in severely corroded or highly rough areas, even with sufficient coating thickness, poor adhesion may cause premature peeling, leading to protective failure. In areas with residual old coatings, the interlayer adhesion between the old and new coatings may become a weak point, resulting in coating delamination. This neglect of substrate heterogeneity introduces significant uncertainty into the optimization results in practical applications, affecting maintenance effectiveness.

[0007] Furthermore, critical performance indicators such as coating adhesion typically require on-site sampling inspections using destructive methods like pull-out tests. This method is inefficient, cannot achieve full coverage of all critical areas, and can damage the structure itself. Indirectly assessing adhesion through images currently lacks accurate and reliable models. This results in the system's inability to detect and predict potential coating defects caused by substrate heterogeneity in real time during construction, such as insufficient adhesion, localized sagging, bubbles, or pinholes. Therefore, even if coating performance deviates from targets during later evaluations, the system cannot accurately trace back whether the problem lies with the spraying parameters themselves or with the substrate condition, nor can it proactively adjust parameters during spraying to compensate for the impact of substrate heterogeneity. This means the system can only conduct quality assessments and troubleshooting after the fact, and cannot perform real-time "substrate-adaptive" optimization during construction, severely impacting the stability and reliability of the reinforcement coating under complex and variable substrate conditions. This neglect of substrate heterogeneity ultimately leads to premature local failures in certain critical areas (such as bolted joints, welds, and corrosion spots) despite meeting coating thickness and hardness standards. This is due to poor adhesion or insufficient uniformity, requiring frequent rework or additional maintenance, which significantly increases overall operating costs and risks. Summary of the Invention

[0008] The purpose of this invention is to provide a method and system for optimizing process parameters of power transmission tower reinforcement, which aims to solve the problems of poor coating performance caused by uneven substrate surface and inability to achieve substrate adaptive real-time optimization in the prior art, thereby improving the overall quality and reliability of reinforcement coating.

[0009] In a first aspect, the present invention provides a method for optimizing process parameters of power transmission tower reinforcement, comprising the following steps: Acquire image data of the substrate to be coated on the power transmission tower; By processing the image data, quantitative information on the heterogeneity characteristics of the substrate to be coated is obtained; Based on the quantification information of heterogeneity characteristics, the surface of the substrate to be sprayed is divided into regions to obtain multiple heterogeneous regions; For each heterogeneous region, the spraying reinforcement parameters for that region are determined based on the quantification information of the heterogeneous characteristics corresponding to that region. The spraying reinforcement parameters are used to optimize the coating thickness, coating hardness, and coating adhesion. The spraying equipment is controlled according to the spraying reinforcement parameters to carry out spraying reinforcement on each heterogeneous area.

[0010] The method for optimizing the process parameters of power transmission tower reinforcement provided by this invention accurately quantifies the heterogeneity characteristics of these substrates, and accordingly ensures the adhesion, uniformity and long-term durability of the coating in different substrate areas during the optimization of spraying parameters, while avoiding local protection failure and additional maintenance costs caused by substrate differences.

[0011] Secondly, the present invention provides a system for optimizing process parameters of power transmission tower reinforcement, comprising: The acquisition module is used to acquire image data of the substrate to be coated on the power transmission tower; The image processing module is used to process image data to obtain quantitative information on the heterogeneity characteristics of the substrate to be coated. The segmentation module is used to divide the surface of the substrate to be sprayed into regions based on the quantification information of heterogeneity characteristics, resulting in multiple heterogeneous regions. The determination module is used to determine the spraying reinforcement parameters for each heterogeneous region based on the quantification information of the heterogeneous characteristics corresponding to the heterogeneous region. The spraying reinforcement parameters are used to optimize the coating thickness, coating hardness and coating adhesion. The control module is used to control the spraying equipment to spray and reinforce various heterogeneous areas according to the spraying reinforcement parameters.

[0012] As can be seen from the above, the method for optimizing the process parameters of power transmission tower reinforcement provided by this invention, by introducing a UAV equipped with multifunctional sensors and advanced image processing technology, achieves precise, non-contact quantification of heterogeneous characteristics such as surface corrosion, old coating residue, and surface roughness of the substrate before spraying. This compensates for the shortcomings of existing methods in the fine characterization of substrate conditions, providing accurate and comprehensive input for subsequent optimization. Furthermore, it allows for targeted correction or recalculation of the multi-objective spraying optimization model, generating differentiated spraying parameters applicable to different substrate regions. This enables the spraying process to be intelligently adjusted according to the actual heterogeneity of the substrate, ensuring that the adhesion, uniformity, and long-term durability of the coating on complex and variable substrates all meet expectations, thus overcoming the limitations of existing "one-size-fits-all" spraying methods. Simultaneously, by accurately assessing the heterogeneity of the substrate and optimizing regional parameters before spraying, this solution achieves pre-compensation for the impact of substrate heterogeneity. This forward-looking optimization mechanism significantly reduces localized protective failures caused by substrate differences, coating defects (such as insufficient adhesion and delamination), and reliance on post-inspection and rework, thereby fundamentally improving maintenance quality and reducing overall operating costs and risks.

[0013] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0014] Figure 1 This is a flowchart of a method for optimizing process parameters of power transmission tower reinforcement provided in an embodiment of the present invention.

[0015] Figure 2 This is a schematic diagram of a power transmission tower reinforcement process parameter optimization system provided in an embodiment of the present invention.

[0016] Label Explanation: 100. Acquisition module; 200. Image processing module; 300. Division module; 400. Determination module; 500. Control module. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0018] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0019] Reference Appendix Figure 1 This invention provides a method for optimizing process parameters of power transmission tower reinforcement, comprising the following steps: Acquire image data of the substrate to be coated on the power transmission tower; By processing the image data, the heterogeneity characteristics of the substrate to be coated are quantified; the heterogeneity characteristics quantification information includes corrosion area information, old coating residue information, and surface roughness information. Based on the quantification information of heterogeneity characteristics, the surface of the substrate to be sprayed is divided into regions to obtain multiple heterogeneous regions; For each heterogeneous region, the spraying reinforcement parameters for that region are determined based on the quantification information of the heterogeneous characteristics corresponding to that region. The spraying reinforcement parameters are used to optimize the coating thickness, coating hardness, and coating adhesion. The spraying equipment is controlled according to the spraying reinforcement parameters to carry out spraying reinforcement on each heterogeneous area.

[0020] Image data refers to visual information used to characterize the surface condition of the substrate of the power transmission tower to be coated. It can be acquired in the form of visible light images, multispectral images, 3D point cloud data, or thermal imaging images, such as through acquisition using a drone equipped with a high-resolution camera or LiDAR. Its main purpose is to obtain initial state information of the substrate, providing a data foundation for subsequent heterogeneity analysis. Heterogeneity feature quantification information refers to a numerical and calculable description of the surface non-uniformity of the power transmission tower substrate to be coated. This can be achieved using image processing algorithms, machine learning models, or deep learning networks. For example, pixel-level analysis, texture recognition, or feature extraction of image data is used. Its main purpose is to transform the complex surface condition of the substrate into data that can be processed and analyzed by computers for precise evaluation. Corrosion area information refers to a quantitative description of areas on the substrate surface that have undergone chemical or electrochemical corrosion. This can be achieved using image segmentation techniques, color analysis, or spectral feature recognition. For example, identifying the color, texture, or spectral response of rust in an image is used. Its main purpose is to identify the degree of substrate degradation, providing a basis for subsequent repair and protection. Information on residual old coatings refers to a quantitative description of the parts of the original coating on the substrate surface that have not been completely removed or have peeled off. This can be achieved using edge detection, texture analysis, or deep learning classification. For example, by identifying the boundaries, thickness, or adhesion status of the old coating in an image, it is primarily used to assess the cleanliness of the substrate and avoid adhesion problems between the old and new coatings. Surface roughness information refers to a quantitative description of the degree of microscopic unevenness on the substrate surface. This can be achieved using photometric stereochemistry, laser scanning, or texture analysis. For example, by analyzing light and shadow variations or microscopic texture features in an image, it is primarily used to assess the physical properties of the substrate and their impact on coating leveling and adhesion. Heterogeneous regions refer to local areas with relatively consistent characteristics, defined based on the quantitative information of the heterogeneous features of the substrate surface. This can be achieved using clustering algorithms, image segmentation algorithms, or rule-based region partitioning methods. For example, by grouping regions with similar corrosion levels, residual old coatings, or surface roughness into one category, it is primarily used to achieve fine-grained management of the substrate surface and to customize spraying solutions for different areas. Spraying reinforcement parameters refer to process variables used to control spraying equipment to achieve specific coating performance. These parameters can include the distance between the nozzle and the substrate, the spraying speed, the spraying pressure, the paint viscosity, the number of spraying layers, or the curing temperature. For example, by adjusting the spraying angle and flow rate of the spraying equipment, the main purpose is to accurately control the coating formation process in order to achieve the desired coating performance indicators.

[0021] The working principle of this invention lies in overcoming the limitation of the assumed uniformity of the substrate surface in existing transmission tower reinforcement coatings. It utilizes drones to collect detailed, non-contact image data of the tower substrate before coating. This data is processed by a backend system to accurately quantify the heterogeneous characteristics of the substrate surface, such as corrosion levels, residual old coatings, and surface roughness. Based on these quantifications, the system intelligently divides the tower surface into several regions with similar substrate characteristics. Subsequently, for each specific heterogeneous region, the system dynamically modifies or reconfigures the original multi-objective optimization model for coating thickness and hardness, ensuring it fully considers the influence of substrate heterogeneity in that region. This allows for the calculation of a Pareto-optimal set of coating process parameters suitable for that region, simultaneously optimizing coating thickness, hardness, and key properties such as adhesion and uniformity. Finally, these regionalized, differentiated coating parameters are transmitted to automated coating equipment, guiding it to perform precise adaptive coating operations, thereby ensuring stable, high-quality, and long-term reliability of the coating under complex and variable substrate conditions.

[0022] The core innovation of this application lies in acquiring and accurately quantifying the heterogeneous characteristics of the substrate to be coated on the power transmission tower, and dividing the substrate surface into regions based on this quantified information. This allows for the adaptive determination of coating reinforcement parameters for different heterogeneous regions. In particular, coating adhesion is included as an optimization objective. This solves the problems of poor coating performance caused by uneven substrate surface and the inability to achieve adaptive real-time optimization of the substrate in the prior art, thereby improving the overall quality and reliability of the reinforcement coating.

[0023] Specifically, this method first acquires image data of the power transmission tower substrate to be coated, recording the initial state of the substrate before coating. Then, by processing this image data, the surface inhomogeneity of the substrate is transformed into quantifiable heterogeneity characteristics, including corrosion area information, old coating residue information, and surface roughness information. This quantified information characterizes the substrate condition, which plays a crucial role in coating performance, overcoming the shortcomings of existing technologies in quantifying microscopic heterogeneity. After obtaining the quantified heterogeneity characteristics, this method uses this information to divide the substrate surface into multiple heterogeneous regions. This division is based on the actual heterogeneity of the substrate, ensuring that the heterogeneity characteristics within each region are relatively consistent, while differences exist between different regions, thus laying the foundation for adaptive coating. For each divided heterogeneous region, this method determines specific coating reinforcement parameters based on its quantified heterogeneity characteristics. This step solves the problem of existing optimization models assuming substrate uniformity or relying solely on experience for adjustment. The optimization objectives of the coating reinforcement parameters include not only coating thickness and coating hardness but also, in particular, coating adhesion. By incorporating adhesion into the optimization objective and directly linking it to the quantified information of the substrate's heterogeneity, this method can compensate for adhesion problems caused by poor substrate conditions, thereby enabling proactive parameter adjustments during the spraying process. Finally, the customized spraying reinforcement parameters determined in the preceding steps for each heterogeneous region are applied to the control of the spraying equipment, achieving adaptive spraying of the power transmission tower substrate. This means that the spraying equipment can dynamically adjust the spraying strategy according to the actual conditions of different areas of the substrate, ensuring that the desired coating performance, including the desired thickness, hardness, and crucial adhesion, is achieved in each heterogeneous region.

[0024] Through the above-described solution, this application addresses the problem that the performance of sprayed reinforcement coatings cannot meet expectations due to the surface heterogeneity of transmission tower substrates. By accurately quantifying and regionalizing the substrate heterogeneity and optimizing spraying parameters accordingly, particularly by incorporating coating adhesion into the optimization objective, this method achieves adaptive spraying for complex substrate conditions. This improves the overall quality, uniformity, and durability of the reinforcement coating, reduces the risk of localized failure, and thus enhances maintenance efficiency and reliability.

[0025] In some embodiments, the step of acquiring image data of the power transmission tower substrate to be coated includes: Obtain structural and environmental information of the substrate to be coated on the power transmission tower; Based on structural and environmental information, an image data acquisition path is generated. Image data is acquired along the image data acquisition path to obtain the first image data; The first evaluation result is obtained by evaluating the image data quality and coverage of the first image data; Based on the first evaluation result, the image data acquisition path or acquisition parameters are adjusted, and supplementary acquisition is performed based on the adjusted image data acquisition path or acquisition parameters to obtain the second image data; The first image data and the second image data are fused to obtain the final image data for subsequent processing.

[0026] Specifically, the acquired structural information refers to the geometry, dimensions, topology, material composition, and spatial location and interrelationships of key components (such as beams, braces, bolt connections, welds, etc.) of the transmission tower substrate to be coated. This information can be pre-acquired using technologies such as CAD models, 3D laser scanning, or structured light scanning, and stored in the form of 3D point clouds, mesh models, or parametric models. Its purpose is to provide precise geometric constraints and occlusion analysis for planning the image data acquisition path. Environmental information refers to the external conditions surrounding the transmission tower during image data acquisition, including but not limited to light intensity, light direction, wind speed, wind direction, temperature, humidity, and potential weather conditions such as fog, rain, and snow. This information can be acquired in real-time through on-site sensors or obtained through meteorological forecast data. Its purpose is to assess the potential impact of environmental factors on image data quality and guide the adjustment of acquisition parameters. The image data acquisition path refers to the sequence of trajectories of the equipment used to acquire image data of the transmission tower substrate to be coated in three-dimensional space, including a series of preset or dynamically generated observation points and attitudes. The path generation aims to ensure comprehensive coverage of the target area while avoiding structural obstructions and adverse environmental conditions. The path can be composed of a series of discrete waypoints, flight speed, camera angle, and focal length. "Image data quality" in image data quality and coverage refers to indicators such as the sharpness, brightness, contrast, noise level, distortion, and whether the acquired image contains valid information. For example, it can be quantitatively evaluated using parameters such as image sharpness, signal-to-noise ratio, exposure, and color balance. "Coverage" refers to the complete coverage of all key heterogeneous areas of the transmission tower substrate to be coated by the image data; that is, whether there are areas that were not captured or were incompletely captured. This can be evaluated by comparing the acquired image data with a preset 3D model of the tower or by assessing the completeness of the stitched images. "Adjusting the image data acquisition path" in adjusting the image data acquisition path or parameters refers to modifying the original acquisition path when insufficient image data quality or coverage is found. This may involve adding new observation points, changing the flight altitude or angle, or replanning the scanning trajectory of local areas. "Adjusting acquisition parameters" refers to modifying the operating settings of the image acquisition equipment, such as adjusting exposure time, ISO sensitivity, aperture size, white balance, focal length, or changing image resolution and frame rate, to adapt to current environmental conditions or compensate for image defects. Fusion processing refers to the process of integrating first and second image data acquired multiple times, which may contain overlapping or complementary information. This process aims to eliminate geometric distortions and lighting differences between images, and to perform precise alignment and stitching, thereby generating a seamless, high-resolution, and information-complete unified image dataset. Fusion processing can employ techniques such as feature matching, photometric correction, and multi-view geometric reconstruction to ensure the accuracy and consistency of the final image data.

[0027] In this solution, to optimize the image data acquisition process of the power transmission tower substrate to be coated, the system first acquires the structural and environmental information of the substrate. The structural information provides a precise description of the tower's geometry, key components, and potential obstruction areas, while the environmental information predicts the potential impact of external factors such as lighting and wind on image acquisition. Based on this comprehensive contextual information, the system intelligently generates an image data acquisition path. This path is designed to ensure effective coverage of all key heterogeneous areas while avoiding structural obstructions and adverse environmental conditions, thus laying the foundation for subsequent image data acquisition. Subsequently, preliminary image data acquisition is performed along the generated path to obtain the first image data. During or after acquisition, the system performs real-time or near-real-time evaluation of the image data quality and coverage of the first image data, thus obtaining the first evaluation result. This evaluation mechanism is a key feedback loop in the solution, enabling timely identification of issues such as image blurring, underexposure, and omission of key areas. Based on the first evaluation result, the system can adaptively adjust the image data acquisition path or acquisition parameters. For example, if a blurry area is detected, the system can adjust the camera focus or exposure time; if an area is missed, the system can replan the local path for supplementary scanning. Subsequently, supplementary data is acquired based on the adjusted path or parameters, resulting in second image data. This iterative acquisition and evaluation mechanism ensures that the quality and completeness of image data are progressively optimized even in complex and changing environments. Finally, the first and second image data are fused to obtain the final image data for subsequent processing. This fusion step integrates multiple, quality-assured acquisitions into a comprehensive, high-precision substrate image dataset. In this way, this solution overcomes the limitations of traditional acquisition methods in terms of data quality and completeness in complex environments, providing a reliable data foundation for subsequent accurate quantification of substrate heterogeneity. Furthermore, the complete and high-resolution image data acquired by this solution, as a key input in the optimization method for transmission tower reinforcement process parameters, can significantly improve the accuracy of subsequent processing. Specifically, once image data quality is guaranteed, the accuracy of processing the image data to obtain quantified information on the heterogeneity characteristics of the substrate to be coated (including information on corrosion areas, residual old coatings, and surface roughness) will be significantly improved. Based on more accurate quantified information on heterogeneity characteristics, the surface of the substrate to be coated can be divided into more refined and reasonable regions. This allows for more accurate determination of coating reinforcement parameters for each heterogeneous region, based on its corresponding quantified information, to optimize coating thickness, coating hardness, and coating adhesion. Ultimately, controlling the coating equipment according to these optimized coating reinforcement parameters will more effectively ensure the performance of the coating in different heterogeneous regions, thereby improving the overall reinforcement effect and reliability.

[0028] This solution acquires structural and environmental information about the substrate of the power transmission tower to be coated, and generates an image data acquisition path based on this information. This makes the image data acquisition process targeted and optimized, effectively avoiding the influence of structural obstruction and adverse environmental factors. Furthermore, by evaluating the quality and coverage of the initially acquired image data, and adaptively adjusting the acquisition path or parameters for supplementary acquisition based on the evaluation results, the integrity and high quality of the image data are ensured. Finally, the multi-source image data is fused to obtain comprehensive and high-precision substrate image data. This overcomes the difficulties in ensuring complete, high-resolution, and comprehensive image data acquisition in complex structures and high-altitude operating environments, as well as the problems of missing or blurred images. This provides a reliable data foundation for the accuracy of subsequent substrate heterogeneity quantification, thereby improving the reliability of coating parameter optimization.

[0029] In some embodiments, the step of generating an image data acquisition path based on structural and environmental information includes: Based on the structural information, identify the key heterogeneous areas on the substrate of the power transmission tower that have high requirements for coating performance, and obtain the spatial location information of the key heterogeneous areas. For each key heterogeneous region, based on structural and spatial location information, the structural occlusion status of the key heterogeneous region is analyzed, and the observation angle range and observation distance range that can ensure high visibility of the key heterogeneous region are determined. By combining environmental information, the impact of environmental factors on the image data quality of key heterogeneous areas within the range of observation angle and observation distance is evaluated to obtain a second evaluation result; Based on the observation angle range, observation distance range, and second evaluation results, a set of image data acquisition points is generated for each key heterogeneous region to ensure its high visibility and image data quality. The image data acquisition points are integrated with the overall coverage requirements of the power transmission tower substrate to be coated, and the image data acquisition path is generated by combining the flight constraint information of the coating equipment.

[0030] Key heterogeneous areas refer to specific regions on the substrate of the transmission tower that have high requirements for coating performance, such as corrosion at bolt connections, micro-cracks in welds, and residual adhesion at the edges of peeling old coatings. These can be identified using preset rules, historical data analysis, or image recognition algorithms. Structural obstruction refers to the degree or state of obstruction of specific areas in the complex truss structure of the transmission tower at certain viewing angles due to component intersections, overlaps, or the tower's own geometry. This can be achieved using 3D geometric model analysis, ray tracing algorithms, or visibility mapping. The observation angle range and observation distance range refer to the set of spatial positions of cameras or sensors relative to the key heterogeneous areas that ensure clear and complete capture. These can be determined using a computational model based on the sensor's field of view, resolution requirements, and the geometric features of the target area. The second evaluation result refers to the quantitative assessment of the impact of environmental factors (such as light intensity, light direction, weather conditions, air humidity, etc.) on the image data quality (such as sharpness, contrast, color accuracy, noise level, etc.) of key heterogeneous areas within a specific observation angle and distance range. This assessment can be obtained using environmental sensor data, lighting models, or image quality evaluation algorithms. Image data acquisition points refer to the specific spatial locations where the spraying equipment collects image data, planned to ensure high visibility and image data quality in key heterogeneous areas. These points can be generated using multi-objective optimization algorithms, path planning algorithms, or discrete point sampling strategies. Flight constraint information for the spraying equipment refers to the limitations imposed on its flight capabilities, attitude control, obstacle avoidance capabilities, endurance, load limits, and minimum safe distance when performing image data acquisition tasks. This information can be obtained using technical parameters provided by the equipment manufacturer, actual flight test data, or the constraint rules built into the flight control system.

[0031] Based on the aforementioned technical features, this method achieves its intended function through the following steps. When generating the image data acquisition path, this scheme first identifies key heterogeneous regions with high requirements for coating performance based on the structural information of the transmission tower, and acquires the spatial location information of these regions. This identification process is the foundation of refined acquisition, shifting the focus from overall coverage to local areas crucial to coating performance, thereby avoiding the efficiency problems and data redundancy caused by indiscriminate acquisition. Subsequently, for each identified key heterogeneous region, combining its structural and spatial location information, the structural occlusion status of the region is analyzed, and the observation angle and distance ranges that ensure high visibility are determined. This analysis step overcomes the self-occlusion challenge posed by the complex structure of the transmission tower, ensuring that even hidden or difficult-to-access key regions can be clearly captured by accurately calculating the optimal observation angle and distance, thus guaranteeing the integrity and effectiveness of the image data. Based on this, the scheme further incorporates environmental information, evaluating the impact of environmental factors on the image data quality of key heterogeneous regions within the aforementioned observation angle and distance ranges, to obtain a second evaluation result. This assessment considers unavoidable environmental interference in actual operations. By quantitatively evaluating environmental factors, it can predict and avoid situations that may lead to image quality degradation, ensuring that the final acquired image data meets the accuracy requirements of subsequent processing. Next, based on the observation angle range, observation distance range, and the results of the second assessment, a set of image data acquisition points is generated for each key heterogeneous region to ensure high visibility and image data quality. These acquisition points are optimal locations after comprehensively considering structural occlusion, best observation conditions, and environmental influences, ensuring high-quality image data even under complex conditions and providing solid data support for subsequent heterogeneity feature quantification. Finally, these image data acquisition points generated for key heterogeneous regions are integrated with the overall coverage requirements of the transmission tower substrate to be coated, and combined with the flight constraint information of the coating equipment, to generate the final image data acquisition path. This integration step ensures that while meeting the high-precision acquisition requirements of key areas, the coverage integrity of the entire substrate surface is also considered, and by taking into account the actual flight capabilities and limitations of the coating equipment, an executable, efficient, and safe acquisition path is generated. This solution, combined with a fundamental method for generating image data acquisition paths, achieves intelligent and refined image data acquisition of the substrate to be coated on power transmission towers. While the fundamental method provides comprehensive coverage of the tower, this solution builds upon this by further optimizing key heterogeneous areas with high requirements for coating performance. By identifying these key areas, analyzing their structural obstructions, determining optimal observation conditions, and considering the impact of environmental factors on image quality, acquisition points are ultimately generated that ensure high visibility and high image data quality in these key areas.The integration of these acquisition points with overall coverage requirements and flight constraint information ensures that the final image data acquisition path not only fully covers the tower surface but also guarantees high-quality, high-visibility image data in critical areas requiring the most detailed data. This combination allows the acquired image data to more accurately reflect the heterogeneity characteristics of the substrate, providing a more reliable input for subsequent quantification of heterogeneity characteristics. This, in turn, supports more precise optimization of spraying reinforcement parameters, overcoming the limitations of traditional methods in terms of data quality and completeness under complex structures, and improving the stability and reliability of the reinforcement coating under complex and variable substrate conditions.

[0032] This solution overcomes the self-occlusion problem caused by the complex truss structure of power transmission towers by identifying key heterogeneous areas on the substrate to be coated that have high requirements for coating performance and planning refined image data acquisition paths for these areas. By analyzing the structural occlusion of these key heterogeneous areas and determining the observation angle and distance ranges that ensure high visibility, even heterogeneous features hidden deep within the structure or difficult to observe directly can be clearly and completely captured. By evaluating the impact of environmental information on image data quality, it avoids image quality degradation caused by environmental factors such as insufficient lighting, backlighting, or inclement weather, thus ensuring high-definition and high-availability image data. Finally, by integrating these optimized acquisition points for key areas with the overall coverage requirements of the power transmission tower substrate and the flight constraints of the coating equipment, an image data acquisition path can be generated that satisfies both overall coverage requirements and ensures high visibility and image data quality for key heterogeneous areas. This makes the subsequent quantification of heterogeneous characteristics more accurate, providing more reliable and comprehensive data input for optimizing the coating process parameters for power transmission tower reinforcement, thereby improving the guarantee level of coating performance and the overall quality of maintenance operations.

[0033] In some embodiments, the step of fusing the first image data and the second image data to obtain the final image data for subsequent processing includes: Geometric correction is performed on the first image data and the second image data to obtain the corrected first image data and the corrected second image data; Feature points are extracted from the corrected first image data and the corrected second image data, and a first spatial transformation relationship between the corrected first image data and the corrected second image data is determined based on the feature points; Based on the first spatial transformation relationship, the corrected first image data and the corrected second image data are initially aligned, and the geometric consistency of the initially aligned image data in the overlapping area is evaluated. Based on the geometric consistency evaluation results, the second spatial transformation relationship is obtained by optimizing the first spatial transformation relationship to improve the geometric consistency of the overlapping region. Based on the second spatial transformation relationship, the corrected first image data and the corrected second image data are fused to obtain the final image data for subsequent processing.

[0034] Geometric correction refers to image data processing to eliminate or reduce image distortion caused by camera optical characteristics, shooting angle, or the three-dimensional structure of objects, making the geometric shapes and spatial relationships in the image closer to the real world. It can be achieved using techniques such as distortion correction based on camera calibration parameters, perspective correction, or orthorectification. Feature points refer to unique, repeatable pixels or regions in an image that are robust to changes in lighting and viewing angle. They can be extracted using algorithms such as SIFT (Scale Invariant Feature Transform), SURF (Speed-Up Robust Feature Transform), ORB (Oriented Fast and Rotationally Shortened Feature Transform), or AKAZE. Spatial transformation relationships refer to mathematical models describing the pixel coordinate mapping relationship between two images. They can be represented using affine transformations, perspective transformations, or polynomial transformations, and image alignment is achieved by calculating transformation matrices or parameters. Geometric consistency refers to the degree to which the projected positions of the same physical points in overlapping areas of multiple images precisely match. It can be evaluated using metrics such as image pixel differences, edge alignment errors, structural similarity index (SSIM), or mutual information. Optimizing the first spatial transformation relationship refers to iteratively adjusting or finely refining the initially determined spatial transformation parameters based on the geometric consistency evaluation results to minimize misalignment and inconsistency in overlapping image regions. This can be achieved using algorithms based on Iterative Closest Point (ICP), optical flow, or nonlinear optimization methods based on gradient descent. Fusion processing refers to seamlessly stitching or mixing multiple image data in space to generate a more complete and higher-quality image. This can be achieved using techniques such as weighted average fusion, multi-resolution fusion, Poisson fusion, or graph cut-based stitching.

[0035] This application provides an image data fusion method aimed at overcoming image geometric distortion, scale differences, and parallax caused by changes in viewing angle and distance during image acquisition of complex structures such as power transmission towers, thereby ensuring the spatial consistency and geometric accuracy of the fused image. The method first performs geometric correction on the initially acquired first image data and the supplementarily acquired second image data. This initial processing step is fundamental; it systematically eliminates inherent distortions caused by camera lens characteristics or shooting angles, allowing subsequent image alignment and fusion operations to be performed on a more accurate geometric reference, avoiding the negative impact of original image distortion on overall accuracy. Based on this, feature points are precisely extracted from the corrected first and second image data. These feature points serve as stable references within the image content and are used to calculate the first spatial transformation relationship between the two sets of images. This process utilizes the inherent correspondence of the images themselves to establish a preliminary pixel-level mapping, thus achieving preliminary alignment of the two sets of images. This feature-point-based alignment method, compared to methods relying solely on external pose parameters, is more robust to uncertainties in the actual acquisition environment, providing a reliable starting point for subsequent refined processing. Subsequently, based on the initially determined first spatial transformation relationship, the corrected first image data and the corrected second image data are initially superimposed. Building upon this initial alignment, the system further evaluates the geometric consistency of the two sets of images in the overlapping region. This evaluation is a crucial feedback loop; it identifies and reveals potential residual errors and inaccuracies in the initial alignment by quantifying the degree of misalignment, edge fit, or texture continuity in the overlapping region. It is based on this quantitative evaluation that this method can be specifically optimized. According to the geometric consistency evaluation results, the system iteratively optimizes the first spatial transformation relationship to improve the geometric consistency of the overlapping region, thereby obtaining a more accurate second spatial transformation relationship. This optimization process is the core of this method; it continuously adjusts the transformation parameters to ensure that the corresponding features of the two sets of images in the overlapping region achieve a high degree of consistency, minimizing the impact of perspective distortion, scale differences, and parallax. This refined optimization ensures that detailed features such as members and bolts in complex truss structures maintain accurate spatial correspondences in the fused image, laying a solid foundation for subsequent precise quantitative analysis. Finally, based on the optimized second spatial transformation relationship, the corrected first and second image data are fused to generate the final image data for subsequent processing. This final image data not only has a wider coverage, but more importantly, it is geometrically accurate and spatially consistent, accurately reflecting the surface condition of the power transmission tower substrate to be coated.This refined fusion process effectively addresses the issue of insufficient image data accuracy in complex structures using traditional simple fusion methods. It provides high-quality, reliable input for subsequent steps involving the quantification of heterogeneous features such as corrosion area, old coating peeling edge shape, or micro-roughness. This allows for more accurate substrate information in the subsequent heterogeneous region segmentation and coating reinforcement parameter determination, thereby improving the overall accuracy and effectiveness of power transmission tower reinforcement process parameter optimization and ensuring the reliability of coating performance.

[0036] The method provided in this application effectively eliminates perspective distortion and scale differences generated during image acquisition by performing geometric correction on the initially acquired and supplemented image data. Preliminary image alignment is achieved by extracting feature points from the corrected images and determining the initial spatial transformation relationship. Furthermore, by evaluating the geometric consistency of the initially aligned images in overlapping areas and optimizing the spatial transformation relationship based on the evaluation results, the alignment accuracy and spatial consistency of the images in complex structural regions are improved, overcoming the limitations of traditional simple fusion methods when handling complex geometric features. Finally, by performing fusion processing based on the optimized spatial transformation relationship, geometrically accurate, spatially consistent, and high-resolution unified image data is obtained. This enables subsequent quantitative analysis of heterogeneous characteristics of the transmission tower substrate to be coated, such as the area of ​​corrosion zones, the shape of the old coating peeling edge, or the micro-roughness, based on more accurate image information, thereby reducing measurement errors and providing a reliable data foundation for accurate heterogeneous region segmentation and coating reinforcement parameter determination, thus improving the overall accuracy and reliability of transmission tower reinforcement process parameter optimization.

[0037] In some embodiments, the step of dividing the surface of the substrate to be coated into regions based on heterogeneity characteristic quantification information to obtain multiple heterogeneous regions includes: A1. Based on the quantitative information of heterogeneity characteristics, spatial analysis is performed on the surface of the substrate to be sprayed to identify the spatial distribution pattern and gradient change region of the heterogeneity characteristics on the surface of the substrate to be sprayed. A2. Based on the spatial distribution pattern and gradient change region, determine the first initial heterogeneity region and its boundary; A3. Identify transition regions where the gradient of the change in the quantification information of heterogeneous features between the first initial heterogeneous regions exceeds a preset threshold; A4. Based on the heterogeneous characteristics of the transition region, quantify the information change gradient and generate a smooth transition rule for the spraying parameters of the transition region; A5. Based on the smooth transition rules of the spraying parameters of the first initial heterogeneous region and the transition region, the surface of the substrate to be sprayed is divided into regions to obtain multiple heterogeneous regions; the multiple heterogeneous regions include the first initial heterogeneous region and the transition region.

[0038] Spatial analysis refers to a series of techniques for processing, manipulating, analyzing, and modeling geographic or spatial data to reveal spatial relationships, patterns, and trends within the data. This can be achieved using Geographic Information System (GIS) technology, image processing algorithms, statistical methods, or machine learning models. Spatial distribution patterns refer to the arrangement, aggregation, or dispersion of heterogeneous features on the surface of the substrate to be coated. These can be identified using methods such as cluster analysis, hotspot analysis, density estimation, or spatial autocorrelation analysis. Gradient change regions refer to areas on the surface of the substrate where the rate of change of the quantitative information of heterogeneous features is large; that is, areas where heterogeneous features transition from one state to another. These can be identified using image processing techniques such as edge detection algorithms, difference operations, or local variance analysis. The first initial heterogeneous region refers to a continuous region on the substrate surface with relatively uniform heterogeneous features in the initial segmentation stage. This can be determined using threshold-based segmentation, region growing algorithms, or clustering algorithms. The preset threshold refers to a pre-defined numerical limit used to judge whether the gradient of the quantitative information change of heterogeneous features is significant when identifying transition regions. This threshold can be set based on experience, experimental data, or statistical analysis results. The transition region refers to the area between two or more initial heterogeneous regions where the gradient of the quantified information of heterogeneous features exceeds a preset threshold. It can be identified using methods such as morphological dilation, distance transformation, or gradient-based region expansion. The smooth transition rule for spraying parameters refers to a strategy or function within the transition region that guides the continuous adjustment of process parameters of the spraying equipment (such as spraying speed, spraying pressure, nozzle distance, paint flow rate, etc.) according to the gradient change of the quantified information of heterogeneous features. It can be generated using linear interpolation, nonlinear function fitting, or a lookup table-based gradient strategy.

[0039] This solution, when dividing the surface of the power transmission tower substrate to be coated into regions, first identifies the spatial distribution patterns and gradient change regions of the heterogeneous features on the substrate surface through spatial analysis based on the quantified information of heterogeneous characteristics. This initial step is fundamental to understanding the complexity of the substrate; it goes beyond simple discrete segmentation and delves into the spatial continuity and changing trends of heterogeneous features, especially those regions with drastic heterogeneous changes. Based on this, according to the identified spatial distribution patterns and gradient change regions, a first initial heterogeneous region with relatively uniform heterogeneous characteristics and its boundaries are determined. This ensures that relatively stable heterogeneous regions on the substrate surface can be accurately defined, providing a reliable basis for subsequent targeted determination of coating parameters. Furthermore, this solution identifies transition regions where the gradient of the quantified information of heterogeneous features between the first initial heterogeneous regions exceeds a preset threshold. This step is key to solving the problems of inaccurate region boundary division and unsmooth coating parameter switching in existing technologies. By actively identifying these transition regions with significant heterogeneous changes, this solution avoids coating defects caused by rigid region boundary divisions in traditional methods. Once the transition region is identified, this scheme quantifies the gradient of information change based on the heterogeneity characteristics of the transition region, generating smooth transition rules for the spraying parameters in the transition region. This means that the spraying parameters will no longer be simple jumps, but will be smoothly and gradually adjusted according to the actual changing trend of the substrate's heterogeneity, thereby ensuring the uniformity and continuity of the coating in the transition region. Finally, based on the smooth transition rules for the spraying parameters of the first initial heterogeneous region and the transition region, this scheme divides the surface of the substrate to be sprayed into multiple heterogeneous regions, including the first initial heterogeneous region and the transition region. This comprehensive region division method not only provides clear guidance for spraying parameters for each relatively uniform region, but more importantly, by introducing and processing the transition region, it ensures the continuity and adaptability of the spraying parameters across the entire substrate surface. This enables the spraying equipment to perform highly adaptive spraying operations based on the actual heterogeneity of the substrate. By employing this refined and adaptive regional division, this solution effectively addresses the issues of inaccurate regional boundary delineation and uneven coating in transitional areas caused by the gradual heterogeneity of the power transmission tower substrate. This allows for a significant improvement in coating thickness, hardness, and adhesion when determining coating reinforcement parameters for each heterogeneous region and controlling the spraying equipment for reinforcement. In particular, the uniformity, adhesion, and durability of the coating are ensured in areas of heterogeneity variation, preventing the generation of local defects.

[0040] This solution utilizes spatial analysis of quantified heterogeneity characteristics to identify the spatial distribution patterns and gradient change regions of heterogeneity features on the substrate surface, thereby achieving a refined understanding of the substrate surface heterogeneity. Based on this, the solution can determine a first initial heterogeneous region with relatively uniform heterogeneous characteristics and its boundaries, and identify transition regions where the gradient of quantified heterogeneity feature changes between the first initial heterogeneous regions exceeds a preset threshold. For these transition regions, the solution can generate smooth transition rules for spraying parameters, allowing the spraying parameters to be smoothly and gradually adjusted according to the actual changing trend of substrate heterogeneity. Finally, by integrating the first initial heterogeneous region and the transition region for region division, this solution ensures a smooth transition of spraying parameters between different regions, thereby improving the uniformity, adhesion, and durability of the coating across the entire substrate surface, effectively avoiding localized coating defects caused by inaccurate region boundary division or uneven switching of spraying parameters.

[0041] In some embodiments, the step of dividing the surface of the substrate to be coated into regions based on heterogeneity characteristic quantification information to obtain multiple heterogeneous regions includes: B1. Based on the quantification information of heterogeneity characteristics, the surface of the substrate to be sprayed is initially divided into regions to obtain the second initial heterogeneous region; B2. Obtain the parameter response range information of the spraying equipment and the efficiency target information of the spraying operation; B3. Based on the distribution of the initial heterogeneous regions, the parameter response range information of the spraying equipment, and the efficiency target information of the spraying operation, the third evaluation result is obtained by evaluating the impact of the second initial heterogeneous region division on the spraying operation. B4. Based on the third evaluation results, the second initial heterogeneous regions are merged or refined to obtain multiple heterogeneous regions.

[0042] Initial region segmentation refers to the preliminary segmentation of the substrate surface based on quantitative data of original heterogeneous characteristics. This can be achieved using threshold-based segmentation, cluster-based segmentation, or image morphology-based segmentation. The parameter response range information of the spraying equipment refers to the minimum and maximum values ​​that the adjustable parameters (such as spray flow rate, spray angle, spray distance, and spray temperature) of the spraying equipment can achieve during spraying operations, as well as the time or energy consumption required for parameter switching. This information can be obtained from the equipment's technical manual, performance test reports, or through actual calibration. The efficiency target information for the spraying operation refers to the expected performance indicators during the spraying process, such as total operation time, paint utilization rate, unit area spraying cost, or rework rate. This information can be set by the user according to project requirements or optimized based on historical operation data. The third evaluation result refers to the output obtained after quantitatively analyzing the feasibility, efficiency, and potential impact of the initial region segmentation scheme in actual spraying operations. This may include indicators such as parameter switching frequency, path complexity, potential equipment over-limit risks, or estimated operation time. Merging or refining refers to the operation of adjusting the existing regional boundaries based on the evaluation results. This can be achieved using algorithms such as regional growth, regional shrinkage, regional splitting, or regional fusion.

[0043] This solution addresses the conflict between granular region segmentation and operational efficiency and equipment adaptability in transmission tower reinforcement spraying operations, providing an optimized region segmentation method. This method effectively solves the aforementioned problems by organically combining substrate heterogeneity with the constraints and optimization objectives of the actual spraying operation, forming an adaptive region segmentation closed loop. First, an initial region segmentation is performed on the surface of the substrate to be sprayed based on quantified heterogeneity characteristics, resulting in a second initial heterogeneous region. This step is fundamental to the entire region segmentation process; it utilizes quantified heterogeneity characteristics such as corrosion area information, old coating residue information, and surface roughness information obtained from image data to perform preliminary region segmentation based on the inherent heterogeneity of the material. This preliminary segmentation provides original, fine-grained region information for subsequent optimization, ensuring that subsequent region segmentation is based on a quantitative understanding of the true condition of the substrate. Building upon this, the parameter response range information of the spraying equipment and the efficiency target information of the spraying operation are obtained. This step introduces the constraints and optimization objectives of the actual spraying operation. The parameter response range information of the spraying equipment is crucial to ensuring the feasibility of the spraying scheme and avoiding the generation of parameters that the equipment cannot execute. The efficiency target information for the spraying operation guides the optimization of zoning towards greater efficiency. Obtaining this information provides important decision-making basis for subsequent zoning evaluation and adjustment, ensuring that the final zoning scheme not only considers substrate characteristics but also the feasibility and economy of engineering implementation. Subsequently, based on the distribution of the initial heterogeneous regions, the parameter response range information of the spraying equipment, and the efficiency target information for the spraying operation, the impact of the second initial heterogeneous region division on the spraying operation is evaluated, resulting in a third evaluation result. This step is a critical evaluation stage. It combines the initially obtained zoning with the acquired equipment capabilities and efficiency targets to comprehensively consider the initial zoning scheme. The evaluation content may include: whether the initial zoning will cause spraying parameters to frequently exceed the equipment response range, whether it will cause the spraying path to be overly complex, and whether it will increase unnecessary parameter switching time, thereby reducing efficiency. It is through this evaluation that the system can identify problems in the initial zoning that are mismatched with the actual spraying operation or inefficient, and quantify the impact of these problems, providing clear guidance for subsequent zoning adjustments. Finally, based on the third evaluation results, the second initial heterogeneous regions are merged or refined to obtain multiple heterogeneous regions. This step optimizes and adjusts the initial region division based on the evaluation results. If the evaluation results show that some adjacent initial heterogeneous regions, although having minor differences, have required spraying parameters within the equipment response range and merging them can significantly improve efficiency, then they are merged.Conversely, if the evaluation results show significant heterogeneity differences within an initial region, or if the required spraying parameters are within the equipment's response range but have a critical impact on coating performance, and refinement better meets performance requirements, then refinement is performed. It is precisely this dynamic merging or refinement that results in a heterogeneous region partitioning scheme that effectively reflects the substrate's heterogeneity while fully considering the actual capabilities and operational efficiency of the spraying equipment, thereby achieving a better match between spraying reinforcement process parameters and improving overall operational efficiency. This scheme, as a key step in the optimization method for transmission tower reinforcement process parameters, enables more precise and efficient subsequent steps in determining spraying reinforcement parameters and controlling the spraying equipment for each heterogeneous region through refined management of region partitioning. This optimized region partitioning allows for spraying parameter determination that better aligns with the actual substrate condition, while avoiding equipment performance bottlenecks or inefficiencies caused by unreasonable region partitioning, thus improving the overall adaptability and reliability of the transmission tower reinforcement process.

[0044] This solution addresses the conflict between granular region division and actual spraying efficiency and equipment feasibility in transmission tower reinforcement spraying operations by dynamically optimizing the substrate surface area division based on the capabilities and operational efficiency of the spraying equipment. By evaluating and merging or refining the initial regions, the solution avoids issues such as frequent equipment parameter switching, reduced operational efficiency, and increased control system complexity caused by overly fine region division. Simultaneously, it avoids the problem of insufficient reflection of substrate heterogeneity and weakened regional spraying adaptability due to overly coarse region division. Ultimately, this solution yields a region division scheme that effectively reflects substrate heterogeneity while meeting the actual operational capabilities and efficiency requirements of the spraying equipment, thus ensuring a balance between coating performance and operational efficiency and improving the overall quality and efficiency of transmission tower reinforcement spraying operations.

[0045] In some embodiments, the specific steps in step B4 include: B41. Based on the third assessment results, identify the key heterogeneous regions in the second initial heterogeneous region that have high requirements for coating performance; B42. Based on the type of critical heterogeneous regions and the results of the third assessment, determine the performance assurance priority of critical heterogeneous regions; B43. Combining the third evaluation results, the parameter response range information of the spraying equipment, the efficiency target information of the spraying operation, and the performance assurance priority of the key heterogeneous areas, a comprehensive decision is made on the merging or refinement scheme of the second initial heterogeneous areas to obtain the decision result; B44. Based on the decision results, the second initial heterogeneous region is merged or refined to obtain multiple heterogeneous regions.

[0046] Critical heterogeneous areas refer to localized areas on the surface of power transmission tower substrates that, due to their structural characteristics (e.g., bolted joints, welds, edges, narrow gaps) or degree of deterioration (e.g., severe corrosion pits, deep areas of old coating peeling), have special or higher requirements for key coating performance aspects such as coating adhesion, corrosion resistance, and wear resistance. These areas can be identified using methods such as pattern recognition based on preset rules, expert system knowledge base matching, or region labeling combining image features and structural CAD models. Performance assurance priority refers to the degree or importance to which coating performance (e.g., adhesion, corrosion resistance, hardness, durability, etc.) needs to be prioritized when spraying and reinforcing the surface of power transmission towers for different critical heterogeneous areas. This can be determined using methods such as based on predefined weight matrices, fuzzy logic reasoning, or machine learning models for dynamic calculation according to region type and evaluation results. Comprehensive decision-making refers to the process by which a system or algorithm, when merging or refining the second initial heterogeneous regions, weighs multiple factors, including the third evaluation result (reflecting the impact of the initial division on efficiency and equipment adaptability), the parameter response range information of the spraying equipment, the efficiency target information of the spraying operation, and the performance guarantee priority of key heterogeneous regions, to generate an optimal region division adjustment scheme. This can be achieved using multi-objective optimization algorithms, decision tree models, or rule-based expert systems. The decision result refers to the output of the comprehensive decision-making process, specifically manifested as concrete instructions or schemes for merging or refining the second initial heterogeneous regions. This may include information such as which regions need to be merged, which regions need to be refined, and the boundaries of the new refined regions.

[0047] Based on the aforementioned technical features, this method achieves its intended function and solves the technical problems encountered in the reinforcement coating operation of transmission towers through the following approach. When dividing the surface of the substrate to be coated on the transmission tower into regions, this solution aims to resolve the contradiction between ensuring coating performance in critical heterogeneous areas and the overall efficiency of the coating operation. Its working principle is as follows: First, after obtaining the third evaluation result of the impact of the second initial heterogeneous region division on the coating operation, the system will, based on this evaluation result, conduct in-depth analysis and identify those critical heterogeneous regions in the second initial heterogeneous region that have high requirements for coating performance. This identification process ensures that in subsequent region adjustments, targeted attention can be paid to areas on the transmission tower with higher coating quality requirements, such as bolt connections or severely corroded areas. Subsequently, for these identified critical heterogeneous regions, the system will further determine the performance assurance priority of each critical heterogeneous region based on their specific type and the impact of the initial division reflected in the third evaluation result. By assigning different priorities to different critical regions, the system can avoid a uniform approach, thereby prioritizing the protection of important coating performance requirements under limited resources. Based on this, the core of this solution lies in comprehensive decision-making. This decision-making process organically combines the third evaluation results, the parameter response range information of the spraying equipment, the efficiency target information of the spraying operation, and the performance guarantee priority of the previously determined key heterogeneous areas. By employing multi-objective optimization or intelligent decision-making algorithms, the system can weigh these interrelated factors. For example, while ensuring the coating performance of key areas, it can merge non-key areas as much as possible to improve efficiency, or, within the range allowed by the efficiency target, refine key areas to ensure performance. This fusion and balancing of multi-dimensional information allows the final area merging or refinement scheme to consider both global efficiency and local performance. Finally, based on the results of this comprehensive decision-making, the system performs actual merging or refinement processing on the second initial heterogeneous areas, resulting in multiple final heterogeneous areas. These final heterogeneous areas not only consider the overall efficiency of the spraying operation and the actual capabilities of the spraying equipment, but more importantly, they can specifically guarantee high-quality coating protection for key areas on the transmission towers that have high requirements for coating performance. In this way, the solution achieves a balance between coating performance and operational efficiency in the reinforcement spraying of power transmission towers under complex substrate conditions, avoiding the problem of neglecting the performance of key areas or sacrificing overall efficiency due to excessive refinement.

[0048] This method, through the aforementioned technical solution, effectively resolves the contradiction between ensuring coating performance in critical, heterogeneous areas and maintaining overall spraying efficiency in transmission tower reinforcement coating operations. Specifically, this solution avoids simply merging critical areas with high coating performance requirements into large areas, thus preventing the averaging of their specific needs. This ensures that critical areas such as bolted connections, welds, and severely corroded pits receive precisely matched spraying parameters, significantly improving coating adhesion, corrosion resistance, and long-term protective effects in these critical areas. Simultaneously, through comprehensive decision-making, this solution avoids over-refinement of all local details, effectively controlling the number of areas, reducing frequent switching of spraying parameters, and ensuring overall spraying efficiency. Therefore, this solution, while ensuring coating quality in critical areas of transmission towers, optimizes the spraying process, reduces rework and maintenance costs, and improves the overall reliability and durability of the reinforcement coating.

[0049] In some embodiments, the step of determining the spraying reinforcement parameters for each heterogeneous region based on the quantification information of the heterogeneity characteristics corresponding to the heterogeneous region includes: For each heterogeneous region, the dominant heterogeneous feature type and severity of the feature are identified based on the corrosion area information, old coating residue information, and surface roughness information of the heterogeneous region. Based on the identified dominant heterogeneity feature type and severity, the coating performance assurance priority for the heterogeneous region is determined; the coating performance assurance priority is used to indicate the performance indicators that need to be prioritized among coating thickness, coating hardness, and coating adhesion. Based on the quantitative information of the heterogeneous characteristics of this heterogeneous region and the determined priority of coating performance assurance, the spraying reinforcement parameters for this heterogeneous region are determined by analyzing the influence of spraying parameters on coating thickness, coating hardness and coating adhesion.

[0050] The dominant heterogeneity feature type refers to the category of substrate surface condition that has a dominant impact on coating performance within a specific heterogeneous region. This can be achieved through comprehensive analysis and comparison of corrosion area information, old coating residue information, and surface roughness information. For example, by setting thresholds or using classification algorithms, the main problem type in the current region can be identified. Feature severity refers to the quantification degree or influence intensity exhibited by the dominant heterogeneity feature type. This can be achieved by evaluating specific quantitative indicators such as corrosion depth, old coating adhesion residue rate, and surface roughness index, classifying them into different levels. Coating performance assurance priority refers to determining the performance indicators that need to be prioritized or ensured, and their relative importance, among the three performance indicators of coating thickness, coating hardness, and coating adhesion, based on the dominant heterogeneity feature type and severity. This can be achieved through a pre-set rule base, expert system, or machine learning-based decision model, dynamically allocating weights or rankings of different performance indicators based on the identified dominant feature type and severity. The influence of spraying parameters on coating thickness, coating hardness, and coating adhesion refers to the quantitative relationship or functional model between the operating parameters of the spraying equipment and the final coating performance. This relationship can be established and characterized through experimental data fitting, physical models, simulation, or machine learning models.

[0051] This application effectively addresses the multi-objective conflicts and coating performance imbalances caused by substrate heterogeneity in transmission tower reinforcement coating because it introduces a deeper understanding of substrate heterogeneity and a dynamic priority adjustment mechanism when determining coating reinforcement parameters. First, for each heterogeneous region, the system no longer relies solely on quantitative information of heterogeneity characteristics. Instead, it further identifies the dominant heterogeneity feature type and severity in that region based on corrosion area information, old coating residue information, and surface roughness information. This process transforms abstract quantitative data into concrete problem descriptions, such as clarifying whether the region is primarily affected by corrosion, old coating residue, or surface roughness. This refined identification allows the system to grasp the unique challenges of each region. Based on this, the system dynamically determines the coating performance assurance priority for that heterogeneous region according to the identified dominant heterogeneity feature type and severity. The coating performance assurance priority indicates which performance indicators—coating thickness, coating hardness, and coating adhesion—require priority assurance. For example, in areas identified as corroded, the system can intelligently prioritize coating adhesion, as ensuring strong adhesion is crucial to preventing premature failure. This dynamic priority adjustment mechanism addresses the problem of fixed or difficult-to-dynamically adjust objective weights in traditional multi-objective optimization, avoiding compromises on certain key performance indicators. Ultimately, based on the quantified heterogeneous characteristics of the heterogeneous region and the determined coating performance priority, the system analyzes the influence of spraying parameters on coating thickness, hardness, and adhesion to determine the spraying reinforcement parameters for that region. This step organically combines the actual condition of the substrate, performance priorities, and the influence mechanism of spraying parameters, enabling the determined parameters to address specific problems in that region. For instance, in areas with high adhesion priority, the system can adjust parameters such as spraying pressure and paint viscosity to promote wetting and penetration while considering thickness and hardness. This progressive and interconnected parameter determination logic allows the entire reinforcement process to better adapt to complex and changing substrate conditions, thereby improving the quality and reliability of coating reinforcement within the overall framework of region division and parameter determination.

[0052] This application, for each heterogeneous region, first identifies the dominant heterogeneous feature type and severity based on corrosion area information, old coating residue information, and surface roughness information, thereby grasping the actual condition and main problems of the substrate. Subsequently, based on the identified dominant feature type and severity, the coating performance guarantee priority for that heterogeneous region is dynamically determined, clarifying the performance indicators that need to be prioritized among coating thickness, coating hardness, and coating adhesion. This resolves the potential conflict of performance indicators in multi-objective optimization and avoids the situation where blindly pursuing the optimal of all indicators leads to poor actual results. Finally, based on the quantitative information of heterogeneous features and the determined coating performance guarantee priority, the influence of spraying parameters on coating performance is analyzed to determine spraying reinforcement parameters. This makes the determined parameters more targeted and effective, thereby improving the quality and reliability of coating reinforcement under complex substrate conditions, ensuring that the most critical coating performance is prioritized, while also considering other performance indicators and avoiding the generation of local defects.

[0053] Reference Appendix Figure 2 This invention provides a system for optimizing process parameters of power transmission tower reinforcement, comprising: The acquisition module 100 is used to acquire image data of the substrate to be coated on the power transmission tower; The image processing module 200 is used to process image data to obtain quantitative information on the heterogeneity characteristics of the substrate to be sprayed. The segmentation module 300 is used to segment the surface of the substrate to be sprayed into regions based on the quantification information of heterogeneity characteristics, thereby obtaining multiple heterogeneous regions. The determination module 400 is used to determine the spraying reinforcement parameters for each heterogeneous region based on the quantification information of the heterogeneous characteristics corresponding to the heterogeneous region; the spraying reinforcement parameters are used to optimize the coating thickness, coating hardness and coating adhesion. The control module 500 is used to control the spraying equipment to spray and reinforce various heterogeneous areas according to the spraying reinforcement parameters.

[0054] In this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying any such actual relationship or order between these entities or operations.

[0055] The above description is merely an embodiment of the present invention and is not intended to limit the scope of protection of the present invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for optimizing process parameters of power transmission tower reinforcement, characterized in that, Includes the following steps: Acquire image data of the substrate to be coated on the power transmission tower; By processing the image data, quantitative information on the heterogeneity characteristics of the substrate to be coated is obtained; Based on the quantification information of heterogeneity characteristics, the surface of the substrate to be sprayed is divided into regions to obtain multiple heterogeneous regions; For each heterogeneous region, the spraying reinforcement parameters for that heterogeneous region are determined based on the quantification information of the heterogeneous characteristics corresponding to that region. Spraying reinforcement parameters are used to optimize coating thickness, coating hardness, and coating adhesion; The spraying equipment is controlled according to the spraying reinforcement parameters to carry out spraying reinforcement on each heterogeneous area; The steps for acquiring image data of the power transmission tower substrate to be coated include: Obtain structural and environmental information of the substrate to be coated on the power transmission tower; Based on structural and environmental information, an image data acquisition path is generated. Image data is acquired along the image data acquisition path to obtain the first image data; The first evaluation result is obtained by evaluating the image data quality and coverage of the first image data; Based on the first evaluation result, the image data acquisition path or acquisition parameters are adjusted, and supplementary acquisition is performed based on the adjusted image data acquisition path or acquisition parameters to obtain the second image data; The first image data and the second image data are fused to obtain the final image data for subsequent processing. The steps for generating an image data acquisition path based on structural and environmental information include: Based on the structural information, identify the key heterogeneous areas on the substrate of the power transmission tower that have high requirements for coating performance, and obtain the spatial location information of the key heterogeneous areas. For each key heterogeneous region, based on structural and spatial location information, the structural occlusion status of the key heterogeneous region is analyzed, and the observation angle range and observation distance range that can ensure high visibility of the key heterogeneous region are determined. By combining environmental information, the impact of environmental factors on the image data quality of key heterogeneous areas within the range of observation angle and observation distance is evaluated to obtain a second evaluation result; Based on the observation angle range, observation distance range, and second evaluation results, a set of image data acquisition points is generated for each key heterogeneous region to ensure its high visibility and image data quality. The image data acquisition points are integrated with the overall coverage requirements of the substrate to be coated on the power transmission tower to generate an image data acquisition path. The steps for fusing the first image data and the second image data to obtain the final image data for subsequent processing include: Geometric correction is performed on the first image data and the second image data to obtain the corrected first image data and the corrected second image data; Feature points are extracted from the corrected first image data and the corrected second image data, and a first spatial transformation relationship between the corrected first image data and the corrected second image data is determined based on the feature points; Based on the first spatial transformation relationship, the corrected first image data and the corrected second image data are initially aligned, and the geometric consistency of the initially aligned image data in the overlapping area is evaluated. Based on the geometric consistency evaluation results, the second spatial transformation relationship is obtained by optimizing the first spatial transformation relationship; Based on the second spatial transformation relationship, the corrected first image data and the corrected second image data are fused to obtain the final image data for subsequent processing.

2. The method for optimizing the process parameters of power transmission tower reinforcement according to claim 1, characterized in that, The quantification information of heterogeneity features includes information on corrosion areas, residual old coatings, and surface roughness.

3. The method for optimizing the process parameters of power transmission tower reinforcement according to claim 1, characterized in that, The steps for dividing the surface of the substrate to be coated into multiple heterogeneous regions based on the quantification information of heterogeneity characteristics include: A1. Based on the quantitative information of heterogeneity characteristics, spatial analysis is performed on the surface of the substrate to be sprayed to identify the spatial distribution pattern and gradient change region of the heterogeneity characteristics on the surface of the substrate to be sprayed. A2. Determine the first initial heterogeneous region based on the spatial distribution pattern and gradient change region; A3. Identify transition regions where the gradient of the change in the quantification information of heterogeneous features between the first initial heterogeneous regions exceeds a preset threshold; A4. Based on the heterogeneous characteristics of the transition region, quantify the information change gradient and generate a smooth transition rule for the spraying parameters of the transition region; A5. Based on the smooth transition rules of the spraying parameters of the first initial heterogeneous region and the transition region, the surface of the substrate to be sprayed is divided into regions to obtain multiple heterogeneous regions; the multiple heterogeneous regions include the first initial heterogeneous region and the transition region.

4. The method for optimizing the process parameters of power transmission tower reinforcement according to claim 1, characterized in that, The steps for dividing the surface of the substrate to be coated into multiple heterogeneous regions based on the quantification information of heterogeneity characteristics include: B1. Based on the quantification information of heterogeneity characteristics, the surface of the substrate to be sprayed is initially divided into regions to obtain the second initial heterogeneous region; B2. Obtain the parameter response range information of the spraying equipment and the efficiency target information of the spraying operation; B3. Based on the distribution of the initial heterogeneous regions, the parameter response range information of the spraying equipment, and the efficiency target information of the spraying operation, the third evaluation result is obtained by evaluating the impact of the second initial heterogeneous region division on the spraying operation. B4. Based on the third evaluation results, the second initial heterogeneous regions are merged or refined to obtain multiple heterogeneous regions.

5. The method for optimizing the process parameters of power transmission tower reinforcement according to claim 4, characterized in that, The specific steps in step B4 include: B41. Based on the third assessment results, identify the key heterogeneous regions in the second initial heterogeneous region that have high requirements for coating performance; B42. Based on the type of critical heterogeneous regions and the results of the third assessment, determine the performance assurance priority of critical heterogeneous regions; B43. Combining the third evaluation results, the parameter response range information of the spraying equipment, the efficiency target information of the spraying operation, and the performance assurance priority of the key heterogeneous areas, a comprehensive decision is made on the merging or refinement scheme of the second initial heterogeneous areas to obtain the decision result; B44. Based on the decision results, the second initial heterogeneous region is merged or refined to obtain multiple heterogeneous regions.

6. The method for optimizing the process parameters of power transmission tower reinforcement according to claim 1, characterized in that, For each heterogeneous region, the steps to determine the spray reinforcement parameters for that region based on the quantification information of its corresponding heterogeneous characteristics include: For each heterogeneous region, the dominant heterogeneous feature type and severity of the feature are identified based on the corrosion area information, old coating residue information, and surface roughness information of the heterogeneous region. Based on the identified dominant heterogeneity feature type and severity, the coating performance assurance priority for the heterogeneous region is determined; the coating performance assurance priority is used to indicate the performance indicators that need to be prioritized among coating thickness, coating hardness, and coating adhesion. Based on the quantitative information of the heterogeneous characteristics of this heterogeneous region and the determined priority of coating performance assurance, the spraying reinforcement parameters for this heterogeneous region are determined by analyzing the influence of spraying parameters on coating thickness, coating hardness and coating adhesion.

7. A transmission tower reinforcement process parameter optimization system employing the method for optimizing transmission tower reinforcement process parameters as described in any one of claims 1-6, characterized in that, include: The acquisition module is used to acquire image data of the substrate to be coated on the power transmission tower; The image processing module is used to process image data to obtain quantitative information on the heterogeneity characteristics of the substrate to be coated. The segmentation module is used to divide the surface of the substrate to be sprayed into regions based on the quantification information of heterogeneity characteristics, resulting in multiple heterogeneous regions. The determination module is used to determine the spraying reinforcement parameters for each heterogeneous region based on the quantification information of the heterogeneous characteristics corresponding to the heterogeneous region. Spraying reinforcement parameters are used to optimize coating thickness, coating hardness, and coating adhesion; The control module is used to control the spraying equipment to spray and reinforce various heterogeneous areas according to the spraying reinforcement parameters.

Images