Corrosion risk prediction method and device for coastal photovoltaic equipment steel structural member

Abstract

The invention belongs to the field of photovoltaic technology, and discloses a coastal photovoltaic equipment steel structural member corrosion risk prediction method and device, and the method comprises the steps: obtaining pre-coating multi-dimensional quality detection data and environmental stress parameters, predicting a corrosion risk grade through a model, and predicting a low corrosion risk period. The method can predict the later corrosion risk at the early stage of the installation of the coastal photovoltaic equipment steel structural member, and is beneficial to guarantee the long-term stable operation of the coastal photovoltaic equipment.

Description

Technical Field

[0001] The present application relates to the field of photovoltaic technology, and more specifically, to a method and device for predicting corrosion risk of steel structures of coastal photovoltaic equipment. Background Art

[0002] As an important clean energy infrastructure, the long-term stable operation of coastal photovoltaic equipment is crucial to ensuring the reliability of energy supply. However, the harsh corrosiveness of the marine environment poses a severe challenge to the steel structures of photovoltaic equipment. In order to deal with the corrosion problem, anti-corrosion coatings are usually pre-coated in the early stages of construction of prefabricated steel structures of photovoltaic equipment. However, during the transportation, lifting and installation of steel structures, the pre-coating will inevitably be subject to various mechanical damages, such as scratches and wear. These damages will significantly reduce the anti-corrosion performance of the coating, thereby threatening the long-term safe operation of photovoltaic equipment. Therefore, a comprehensive assessment of the quality of the pre-coating after installation is completed and an accurate prediction of future corrosion risks are crucial to ensure the long-term stable operation of photovoltaic equipment.

[0003] At present, the traditional pre-coating quality inspection method mainly relies on manual visual inspection. This method is not only inefficient, but the inspection results are easily affected by the subjective factors of the inspectors, lacking objectivity and quantitative standards. Therefore, it is difficult to accurately evaluate the true quality status of the pre-coating, and it cannot be used to predict future corrosion risks. In addition, in the early stage of coastal photovoltaic equipment construction, due to the lack of long-term operation data and corrosion data accumulation, the direct application of traditional big data-driven machine learning algorithms for corrosion risk prediction faces the problem of severe data shortage.

[0004] Therefore, in the special early stage of the installation of prefabricated steel structures for coastal photovoltaic equipment, under the extreme conditions of lack of long-term operation data and corrosion data accumulation, how to accurately predict future corrosion risks based only on the limited multi-dimensional quality inspection data of pre-coating obtained in the early stage of installation has become a key technical problem that needs to be solved to ensure the construction quality and long-term stable operation of coastal photovoltaic equipment. Solving this problem has important practical significance and application value for improving the anti-corrosion performance of coastal photovoltaic equipment, reducing operation and maintenance costs, and ensuring energy security.

[0005] In view of the above problems, the existing technology needs to be improved urgently. Summary of the invention

[0006] The purpose of this application is to provide a method and device for predicting the corrosion risk of steel structures of coastal photovoltaic equipment, which can predict the later corrosion risk of steel structures of coastal photovoltaic equipment in the early stage of installation, which is conducive to ensuring the long-term stable operation of coastal photovoltaic equipment.

[0007] First aspect, this application provides a method for predicting the corrosion risk of steel structure components of coastal photovoltaic equipment, which is used to predict the corrosion risk of steel structure components of coastal photovoltaic equipment. The method includes the following steps: A1. Obtain the multi-dimensional quality inspection data of the pre-coating after the installation of the steel structure component and the environmental stress parameters at the location of the coastal photovoltaic equipment; the multi-dimensional quality inspection data of the pre-coating includes coating thickness, coating porosity, and coating adhesion; the environmental stress parameters include salt mist concentration, ultraviolet radiation intensity, and temperature change range; A2. According to the multi-dimensional quality inspection data of the pre-coating and the environmental stress parameters, use the multi-factor coupled environmental stress accelerated aging model to predict the quality status of the pre-coating at different service time points; the quality status includes corrosion depth, ultraviolet degradation degree, and adhesion; A3. According to the quality status of the pre-coating at different service time points, determine the corrosion risk level of the steel structure component at different service time points through the corrosion risk level assessment model; A4. Compare the corrosion risk levels of the steel structure component at different service time points with the preset risk level threshold to predict the low corrosion risk period of the steel structure component.

[0008] By obtaining the multi-dimensional quality inspection data of the pre-coating and the environmental stress parameters, using the model to predict the corrosion risk level, and then predicting the low corrosion risk period, this method can predict the later corrosion risk in the early stage of the installation of the steel structure components of coastal photovoltaic equipment, which is beneficial to ensuring the long-term stable operation of coastal photovoltaic equipment.

[0009] Preferably, step A1 includes: A101. For the surface of the steel structure component, divide multiple detection areas, and based on the corrosion sensitivity criterion, screen out the corrosion-sensitive areas from the multiple detection areas; among them, the corrosion sensitivity criterion includes weld proximity, edge exposure, and water accumulation risk; A102. Obtain the surface image of the corrosion-sensitive area, and use the image processing algorithm to identify the coating defect type and defect area of each defect feature in the surface image; among them, the coating defect types include scratches, cracks, and bubbles; A103. According to the coating defect type and defect area, calculate the coating damage degree of the corrosion-sensitive area, and based on the coating damage degree of the corrosion-sensitive area, determine the coating thickness, coating porosity, and coating adhesion of the steel structure component; A104. Based on the historical environmental monitoring data at the location of the coastal photovoltaic equipment, extract the environmental stress parameters, and combine with the real-time environmental monitoring data to correct the environmental stress parameters to obtain the corrected environmental stress parameters.

[0010] Thus, more effective and accurate acquisition of pre - coating multi - dimensional quality inspection data and environmental stress parameters can be achieved, providing a data basis for subsequent corrosion risk prediction.

[0011] Preferably, step A101 includes: Obtain the three - dimensional point cloud data of the steel structure surface, and based on a preset segmentation algorithm, segment the point cloud data into multiple detection regions; For each detection region, obtain the welding point proximity, edge exposure degree, and water accumulation risk degree; among them, the welding point proximity is obtained by calculating the reciprocal of the distance from the center point of the detection region to the nearest welding point, the edge exposure degree is obtained by calculating the ratio of the boundary length of the detection region to the region area, and the water accumulation risk degree is obtained by simulating the rainfall process and calculating the water accumulation depth of the detection region; Perform a weighted sum of the welding point proximity, edge exposure degree, and water accumulation risk degree of each detection region to obtain a comprehensive corrosion sensitivity score, and sort the comprehensive corrosion sensitivity scores from high to low, and select a preset number of detection regions as corrosion - sensitive regions.

[0012] Thus, through the calculation, sorting, and selection of the comprehensive corrosion sensitivity score, automatic screening and efficient identification of corrosion - sensitive regions are realized, overcoming the problems of low efficiency and strong subjectivity in manually screening corrosion - sensitive regions, ensuring the accuracy and efficiency of identifying corrosion - sensitive regions, and laying a foundation for subsequent pre - coating quality inspection and corrosion risk prediction.

[0013] Preferably, step A103 includes: According to the coating defect types and defect areas of each defect feature identified, count the total defect areas of each coating defect type; Calculate the weighted sum of the total defect areas of each coating defect type to obtain the coating damage degree of the corrosion - sensitive region; Utilize the non - linear relationship model between the coating damage degree and the coating thickness, coating porosity, and coating adhesion, and calculate the coating thickness, coating porosity, and coating adhesion of the corrosion - sensitive region according to the coating damage degree of the corrosion - sensitive region; Determine the coating thickness, coating porosity, and coating adhesion of the steel structure according to the coating thickness, coating porosity, and coating adhesion of the corrosion - sensitive region.

[0014] Preferably, the multi-factor coupled environmental stress accelerated aging model includes a salt spray corrosion model, an ultraviolet degradation model, and a mechanical aging model. Among them, the salt spray corrosion model is based on the electrochemical principle and considers the influence of chloride ion concentration, temperature, and humidity on the corrosion rate. The ultraviolet degradation model is based on the photochemical reaction kinetics and considers the influence of ultraviolet radiation intensity, wavelength, and the light absorption characteristics of the coating material on the degradation rate. The mechanical aging model is based on the creep theory and considers the influence of stress level, temperature, and time on the adhesion attenuation; Step A2 includes: A201. Initialize the parameters of the multi-factor coupled environmental stress accelerated aging model according to the multi-dimensional quality inspection data of the pre-coating; the initialized parameters include coating thickness, porosity, adhesion, chloride ion diffusion coefficient, ultraviolet absorption coefficient, and creep coefficient; A202. Determine the environmental stress input of the multi-factor coupled environmental stress accelerated aging model based on the environmental stress parameters of the location of the coastal photovoltaic equipment; the environmental stress input includes the change curve of salt spray concentration over time, the change curve of ultraviolet radiation intensity over time, and the change curve of temperature over time; A203. Iteratively solve the multi-factor coupled environmental stress accelerated aging model at a preset time step to obtain the quality state of the pre-coating at different service time points; the quality state includes corrosion depth, ultraviolet degradation degree, and adhesion.

[0015] Preferably, the step A3 includes: A301. Obtain the corrosion influencing factor data of the steel structure member; the corrosion influencing factor data includes the quality state of the pre-coating at different service time points and the environmental factor data of the location of the coastal photovoltaic equipment; the environmental factor data includes salt spray concentration, temperature, and humidity; A302. Calculate the corrosion risk score of the steel structure member at different service time points according to the corrosion influencing factor data and the corrosion risk level assessment model, and map the corrosion risk score to the corresponding corrosion risk level.

[0016] Preferably, the corrosion risk level assessment model includes a corrosion risk score model and an environmental factor risk score model; the corrosion risk score model is used to calculate the quality state risk score according to the pre-coating quality state parameters, and the environmental factor risk score model is used to calculate the environmental factor risk score according to the environmental factor parameters; the pre-coating quality state parameters include corrosion depth, ultraviolet degradation degree, and adhesion, and the environmental factor parameters include salt spray concentration, temperature, and humidity; Step A302 includes: Extract the pre-coating quality state parameters according to the quality state of the pre-coating at different service time points, and extract the environmental factor parameters according to the environmental factor data of the location of the coastal photovoltaic equipment; According to the corrosion risk scoring model and the environmental factor risk scoring model, calculate the quality status risk score corresponding to the pre-coated quality status parameters extracted and the environmental factor risk score corresponding to the environmental factor parameters extracted respectively; Perform a fusion calculation on the quality status risk score and the environmental factor risk score to obtain a comprehensive corrosion risk score; Determine the corresponding corrosion risk level according to the comprehensive corrosion risk score.

[0017] Preferably, step A4 includes: A401. Based on the corrosion risk levels of the steel structure components at different service time points, construct a time series corrosion risk level curve; A402. According to the preset risk level threshold, determine the time point when the time series corrosion risk level curve first exceeds the risk level threshold as the initial over-threshold time point; A403. Starting from the initial over-threshold time point, trace back forward to search for the time point when the time series corrosion risk level curve first drops below the risk level threshold as the end point of the low corrosion risk period; A404. Calculate the time difference between the end point of the low corrosion risk period and the time point when the steel structure component is installed and completed to obtain the low corrosion risk period of the steel structure component.

[0018] Preferably, after step A401 and before step A402, the following steps are further included: A401a. For each extreme weather event time point, analyze the extreme weather event type and intensity, and calculate the influence degree of the corresponding extreme weather event on the corrosion risk level; A401b. According to the calculated influence degree of the corrosion risk level, correct the corrosion risk level after the corresponding extreme weather event time point in the time series corrosion risk level curve.

[0019] In a second aspect, the present application provides a corrosion risk prediction device for steel structure components of coastal photovoltaic equipment, which is used to predict the corrosion risk of steel structure components of coastal photovoltaic equipment. The device includes: A data acquisition module, which is used to acquire multi-dimensional quality inspection data of the pre-coating after the steel structure component is installed and the environmental stress parameters at the location of the coastal photovoltaic equipment; the multi-dimensional quality inspection data of the pre-coating includes coating thickness, coating porosity, and coating adhesion; the environmental stress parameters include salt fog concentration, ultraviolet radiation intensity, and temperature change range; An aging prediction module, which is used to predict the quality status of the pre-coating at different service time points according to the multi-dimensional quality inspection data of the pre-coating and the environmental stress parameters, and utilize a multi-factor coupled environmental stress accelerated aging model; the quality status includes corrosion depth, ultraviolet degradation degree, and adhesion; A risk assessment module, configured to determine the corrosion risk level of a steel structure member at different service time points through a corrosion risk level assessment model according to the quality status of a pre - coating at different service time points; A risk warning module, configured to compare the corrosion risk levels of the steel structure member at different service time points with a preset risk level threshold to predict the low - corrosion - risk period of the steel structure member.

[0020] Beneficial effects: A method and device for predicting the corrosion risk of a steel structure member of a coastal photovoltaic device provided by this application can, by obtaining multi - dimensional quality detection data of a pre - coating and environmental stress parameters, use a model to predict the corrosion risk level and then predict the low - corrosion - risk period, be able to predict the later corrosion risk in the early stage of installing the steel structure member of the coastal photovoltaic device, which is beneficial to ensuring the long - term stable operation of the coastal photovoltaic device. Description of the Drawings

[0021] Figure 1 It is a flowchart of the method for predicting the corrosion risk of a steel structure member of a coastal photovoltaic device provided by an embodiment of this application.

[0022] Figure 2 It is a schematic structural diagram of the device for predicting the corrosion risk of a steel structure member of a coastal photovoltaic device provided by an embodiment of this application.

[0023] Reference numeral description: 1. Data acquisition module; 2. Aging prediction module; 3. Risk assessment module; 4. Risk warning module. Detailed Embodiments

[0024] Next, the technical solutions in this application will be clearly and completely described in conjunction with the drawings in this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. The components of this application described and illustrated in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of this application that is required to be protected, but only represents the selected embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of this application.

[0025] It should be noted that: Similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0026] Reference Figure 1, this application proposes a method for predicting the corrosion risk of steel structure components of coastal photovoltaic equipment, which is used to predict the corrosion risk of steel structure components of coastal photovoltaic equipment. The method includes the following steps: A1. Obtain the multi-dimensional quality inspection data of the pre-coating after the installation of the steel structure component and the environmental stress parameters at the location of the coastal photovoltaic equipment; the multi-dimensional quality inspection data of the pre-coating includes coating thickness, coating porosity, and coating adhesion; the environmental stress parameters include salt fog concentration, ultraviolet radiation intensity, and temperature change range; A2. According to the multi-dimensional quality inspection data of the pre-coating and the environmental stress parameters, use the multi-factor coupled environmental stress accelerated aging model to predict the quality status of the pre-coating at different service time points; the quality status includes corrosion depth, ultraviolet degradation degree, and adhesion; A3. According to the quality status of the pre-coating at different service time points, determine the corrosion risk level of the steel structure component at different service time points through the corrosion risk level assessment model; A4. Compare the corrosion risk levels of the steel structure component at different service time points with the preset risk level threshold to predict the low corrosion risk period of the steel structure component.

[0027] Among them, in step A1, the multi-dimensional quality inspection data of the pre-coating and the environmental stress parameters are obtained, providing a data basis for subsequent corrosion risk prediction. The multi-dimensional quality inspection data of the pre-coating includes coating thickness, coating porosity, and coating adhesion, which reflect the initial quality status of the pre-coating. The environmental stress parameters include salt fog concentration, ultraviolet radiation intensity, and temperature change range, which represent the severity of the corrosion environment where the steel structure component is located.

[0028] Among them, in step A2, use the multi-factor coupled environmental stress accelerated aging model, combined with the data obtained in step A1, to predict the quality status of the pre-coating at different service time points. The quality status is specifically manifested as corrosion depth, ultraviolet degradation degree, and adhesion. This step simulates the aging process of the pre-coating under the coupling action of multiple environmental stresses through model calculation, realizing the prediction of the future quality status.

[0029] Among them, in step A3, based on the quality status of the pre-coating at different service time points predicted in step A2, determine the corrosion risk level of the steel structure component at different service time points through the corrosion risk level assessment model. This step quantifies the quality status of the pre-coating into the corrosion risk level, realizing the assessment of the corrosion risk.

[0030] Among them, in step A4, by comparing the corrosion risk levels at different service time points obtained in step A3 with a preset risk level threshold, the low corrosion risk period of the steel structure member is predicted. This step finally outputs the service life of the steel structure member under low corrosion risk, providing a reference for operation and maintenance decisions (for example, the operation and maintenance decisions include periodically performing on-site inspections of the steel structure member at a first inspection frequency during the low corrosion risk period, and periodically performing on-site inspections of the steel structure member at a second inspection frequency after the low corrosion risk period, where the first inspection frequency is lower than the second inspection frequency, thereby reducing the maintenance workload during the low corrosion risk period while ensuring low risk).

[0031] Specifically, this technical solution obtains initial data through step A1, uses a model to predict the future quality state through step A2, evaluates the corrosion risk level through step A3, and predicts the low corrosion risk period through step A4, predicting the future risk from the initial state, thereby solving the technical problem of accurately predicting the corrosion risk at the initial stage of the installation of steel structure members of coastal photovoltaic equipment and providing a reference for operation and maintenance decisions. Each step works together to achieve an effective prediction of the corrosion risk of steel structure members of coastal photovoltaic equipment.

[0032] In some preferred embodiments, step A1 includes: A101. For the surface of the steel structure member, divide multiple detection areas, and based on the corrosion sensitivity criterion, screen out the corrosion-sensitive areas from the multiple detection areas; among them, the corrosion sensitivity criterion includes the weld proximity, edge exposure, and water accumulation risk; A102. Obtain the surface image of the corrosion-sensitive area, and use an image processing algorithm to identify the coating defect type and defect area of each defect feature in the surface image; among them, the coating defect types include scratches, cracks, and bubbles; A103. According to the coating defect type and defect area, calculate the coating damage degree of the corrosion-sensitive area, and based on the coating damage degree of the corrosion-sensitive area, determine the coating thickness, coating porosity, and coating adhesion of the steel structure member; A104. Based on the historical environmental monitoring data of the location of the coastal photovoltaic equipment, extract the environmental stress parameters (that is, the environmental monitoring data contains various environmental stress parameters), and combine with the real-time environmental monitoring data to correct the environmental stress parameters to obtain the corrected environmental stress parameters.

[0033] Among them, for step A101, the detection area can be divided by using a grid division method to evenly divide the surface of the steel structure into multiple rectangular areas, or an irregular area division method can be used. For example, according to the geometric shape and structural characteristics of the steel structure, the surface can be divided into multiple polygonal areas. The welding point proximity of the corrosion sensitivity criterion can be quantified as the reciprocal of the distance from the center point of the detection area to the nearest welding point. The smaller the distance, the higher the welding point proximity and the higher the corrosion sensitivity. The edge exposure can be quantified as the ratio of the boundary length of the detection area to the area of the region. The larger the ratio, the higher the edge exposure and the higher the corrosion sensitivity. The water accumulation risk can be calculated by simulating the rainfall process, such as using finite element simulation or computational fluid dynamics simulation, to calculate the water accumulation depth in the detection area. The greater the water accumulation depth, the higher the water accumulation risk (the calculated water accumulation depth can be directly used as the water accumulation risk, or the water accumulation depth can be converted into the water accumulation risk through a conversion formula. In the conversion formula, the water accumulation risk is proportional to the water accumulation depth), and the higher the corrosion sensitivity. Each corrosion sensitivity criterion can be assigned a weight, and then weighted summation is performed to obtain a comprehensive corrosion sensitivity score. Among them, the corrosion-sensitive area is screened according to the size of the comprehensive corrosion sensitivity score.

[0034] For step A102, the surface image can be obtained by taking pictures with an industrial camera. The image processing algorithm can adopt an image segmentation algorithm, a defect detection algorithm, and a feature extraction algorithm. The image segmentation algorithm is used to segment the coating surface image into different regions, such as a defect region and a non-defect region. The defect detection algorithm is used to detect defect features in the image, such as scratches, cracks, and bubbles. The feature extraction algorithm is used to extract parameters such as the type and area of the defect features.

[0035] Among them, for step A103, the coating damage degree can be defined as the weighted sum of the total defect areas of each coating defect type. The weight can be determined according to the influence degree of different defect types on the corrosion risk. For example, the scratch weight is 0.5, the crack weight is 0.8, and the bubble weight is 0.3. The coating thickness, coating porosity, and coating adhesion of the steel structure can be calculated through a non-linear relationship model between the coating damage degree and the coating thickness, coating porosity, and coating adhesion. The non-linear relationship model between the coating damage degree and the coating thickness, coating porosity, and coating adhesion can be obtained by fitting or training with experimental data, such as using a neural network model or a support vector machine model.

[0036] Among them, for step A104, the historical environmental monitoring data can be obtained from the meteorological department or the environmental monitoring station, and the real-time environmental monitoring data can be collected in real time through environmental sensors installed at the location of the coastal photovoltaic equipment. The correction of the environmental stress parameters can adopt the Kalman filter algorithm or the particle filter algorithm to fuse the historical data and the real-time data to improve the accuracy of the environmental stress parameters.

[0037] Specifically, through step A101, targeted selection of the detection area can be achieved. By screening the corrosion-sensitive areas according to the corrosion sensitivity criterion, the detection resources can be concentrated in the areas with higher corrosion risk, improving the detection efficiency and pertinence. Through step A102, automatic identification and quantification of coating defects can be realized. By using image processing algorithms to automatically identify the types and areas of coating defects, the subjectivity and inefficiency of manual visual inspection can be avoided, and the objectivity and accuracy of the detection results can be improved. Through step A103, quantification of the coating quality inspection data can be realized. According to the defect types and areas, the coating damage degree is calculated, and quantitative indicators such as coating thickness, coating porosity, and coating adhesion are determined, providing a data basis for subsequent corrosion risk prediction. Through step A104, accurate acquisition of environmental stress parameters can be realized. Based on historical data and real-time data, the environmental stress parameters are corrected, improving the accuracy and real-time performance of the environmental stress parameters, and providing accurate environmental input for subsequent corrosion risk prediction. Thus, the technical solution of step A1 can achieve more effective and accurate acquisition of multi-dimensional quality inspection data of the pre-coated layer and environmental stress parameters, providing a data basis for subsequent corrosion risk prediction.

[0038] In some possible implementation manners, step A101 includes: Obtain the three-dimensional point cloud data of the steel structure surface, and based on a preset segmentation algorithm, segment the point cloud data into multiple detection areas; For each detection area, obtain the welding point proximity, edge exposure degree, and water accumulation risk degree; among them, the welding point proximity is obtained by calculating the reciprocal of the distance from the center point of the detection area to the nearest welding point, the edge exposure degree is obtained by calculating the ratio of the boundary length of the detection area to the area of the area, and the water accumulation risk degree is obtained by simulating the rainfall process and calculating the water accumulation depth of the detection area; Perform weighted summation on the welding point proximity, edge exposure degree, and water accumulation risk degree of each detection area to obtain a comprehensive corrosion sensitivity score, and sort the comprehensive corrosion sensitivity scores from high to low, and select a preset number of detection areas as corrosion-sensitive areas.

[0039] Among them, the acquisition of three-dimensional point cloud data can be realized by using a three-dimensional scanner, such as a laser scanner or a structured light scanner, which can quickly collect the three-dimensional geometric information of the steel structure surface. The preset segmentation algorithm can be an algorithm based on region growing or an algorithm based on clustering, such as the K-means algorithm. Through these algorithms, the point cloud data can be divided into multiple spatially continuous regions, and each region is used as a detection area for subsequent corrosion sensitivity analysis of each region.

[0040] Among them, for the calculation of the welding point proximity, specifically, the three-dimensional coordinates of all welding points on the steel structure components can be determined first, and then for each detection area, the distance from its center point to all welding points is calculated, and the reciprocal of the minimum distance is selected as the welding point proximity. For the calculation of the edge exposure degree, specifically, the boundary points of each detection area can be extracted first, then the total length of the boundary points is calculated, and then the area of the detection area is calculated. The ratio of the boundary length to the area of the area is the edge exposure degree. For the calculation of the water accumulation risk degree, specifically, it can be realized by simulating the rainfall process. For example, the computer simulation is used to simulate the flow and accumulation of rainfall on the surface of the steel structure components, and the water accumulation depth of each detection area is calculated. The water accumulation depth can be quantified as the water accumulation risk degree (the calculated water accumulation depth can be directly used as the water accumulation risk degree, or the water accumulation depth can be converted into the water accumulation risk degree through a conversion formula. In the conversion formula, the water accumulation risk degree is proportional to the water accumulation depth). In the process of weighted summation of the welding point proximity, edge exposure degree and water accumulation risk degree of each detection area, the weights can be preset according to the actual situation, and thus the comprehensive corrosion sensitivity score can be obtained.

[0041] Among them, the preset quantity can be an absolute quantity or a proportion of the total number of detection areas. The detection areas of the preset quantity are selected as the corrosion-sensitive areas. For example, the detection areas ranked top 10 or top 20% in the comprehensive corrosion sensitivity score can be selected as the corrosion-sensitive areas, so as to facilitate subsequent key detection and risk assessment.

[0042] Specifically, through the application of the three-dimensional point cloud data acquisition and segmentation algorithm, the surface of the steel structure components is effectively divided into multiple detection areas, realizing the automatic division and refined management of the detection areas. Through the quantitative calculation of the three corrosion sensitivity criteria of the welding point proximity, edge exposure degree and water accumulation risk degree, the objective evaluation of the corrosion sensitivity of each detection area is realized. Thus, the calculation and sorting selection of the comprehensive corrosion sensitivity score realize the automatic screening and efficient identification of the corrosion-sensitive areas, overcome the problems of low efficiency and strong subjectivity in the manual screening of the corrosion-sensitive areas, ensure the accuracy and efficiency of the identification of the corrosion-sensitive areas, and lay a foundation for the subsequent pre-coating quality detection and corrosion risk prediction.

[0043] In some possible implementation manners, step A103 includes: According to the coating defect types and defect areas of the defect characteristics identified, the total defect areas of each coating defect type are statistically calculated; The weighted sum of the total defect areas of each coating defect type is calculated to obtain the coating damage degree of the corrosion-sensitive area; Using the non-linear relationship model between the coating damage degree and the coating thickness, coating porosity and coating adhesion, according to the coating damage degree of the corrosion-sensitive area, the coating thickness, coating porosity and coating adhesion of the corrosion-sensitive area are calculated; Determine the coating thickness, coating porosity, and coating adhesion of steel structural members based on the coating thickness, coating porosity, and coating adhesion in the corrosion-sensitive area.

[0044] Among them, for the calculation of the weighted sum of the total defect areas for each coating defect type, weight coefficients for different coating defect types such as scratches, cracks, and bubbles can be preset. The weight coefficient for scratches can be set to 0.3, the weight coefficient for cracks can be set to 0.7, and the weight coefficient for bubbles can be set to 0.1, but it is not limited to this. Thus, by multiplying the total defect area of each type of coating defect by its corresponding weight coefficient and summing them up, a quantitative value of the coating damage degree in the corrosion-sensitive area is obtained.

[0045] Among them, for the non-linear relationship model between the coating damage degree and the coating thickness, coating porosity, and coating adhesion, it can include three neural network models. The inputs of the three neural network models are all set to the coating damage degree, and the outputs of the three neural network models are the coating thickness, coating porosity, and coating adhesion respectively. By training each neural network model with the pre-collected experimental data, a non-linear mapping relationship between the coating damage degree and the coating thickness, coating porosity, and coating adhesion can be obtained.

[0046] Among them, when determining the coating thickness, coating porosity, and coating adhesion of steel structural members based on the coating thickness, coating porosity, and coating adhesion in the corrosion-sensitive area, the coating thickness, coating porosity, and coating adhesion in the corrosion-sensitive area can be directly used as the coating thickness, coating porosity, and coating adhesion of the steel structural members, or redundant operations can be performed based on the coating thickness, coating porosity, and coating adhesion in the corrosion-sensitive area to obtain the coating thickness, coating porosity, and coating adhesion of the steel structural members.

[0047] Specifically, in step A103, first, the surface image of the corrosion-sensitive area is analyzed to identify various types of coating defects such as scratches, cracks, and bubbles, and the total area of each defect type is quantified. Then, based on a preset weight distribution scheme, for example, a higher weight is assigned to crack defects, a value comprehensively reflecting the degree of coating damage is calculated. Subsequently, this value is input into a pre-trained non-linear relationship model, and the model outputs the predicted values of the coating thickness, coating porosity, and coating adhesion corresponding to this coating damage degree. Finally, these predicted values are used to determine the key parameters characterizing the overall pre-coating quality of the steel structural members. Through the above process, an accurate assessment of the pre-coating quality status of the steel structural members can be achieved.

[0048] Specifically, the multi-factor coupled environmental stress accelerated aging model includes a salt spray corrosion model, an ultraviolet degradation model, and a mechanical aging model. Among them, the salt spray corrosion model is based on the principle of electrochemistry, considering the influence of chloride ion concentration, temperature, and humidity on the corrosion rate. The ultraviolet degradation model is based on the kinetics of photochemical reactions, considering the influence of ultraviolet radiation intensity, wavelength, and the light absorption characteristics of the coating material on the degradation rate. The mechanical aging model is based on the creep theory, considering the influence of stress level, temperature, and time on the adhesion attenuation; Step A2 includes: A201. Initialize the parameters of the multi-factor coupled environmental stress accelerated aging model according to the multi-dimensional quality inspection data of the pre-coating; the initialized parameters include coating thickness, porosity, adhesion, chloride ion diffusion coefficient, ultraviolet absorption coefficient, and creep coefficient; A202. Determine the environmental stress input of the multi-factor coupled environmental stress accelerated aging model based on the environmental stress parameters of the location of the coastal photovoltaic equipment; the environmental stress input includes the variation curve of salt spray concentration with time, the variation curve of ultraviolet radiation intensity with time, and the variation curve of temperature with time; A203. Iteratively solve the multi-factor coupled environmental stress accelerated aging model with a preset time step to obtain the quality state of the pre-coating at different service time points; the quality state includes corrosion depth, ultraviolet degradation degree, and adhesion.

[0049] Among them, the multi-factor coupled environmental stress accelerated aging model consists of three sub-models, realizing the simulation of the aging behavior of the pre-coating under the coupled action of multiple environmental stresses. The salt spray corrosion model, as one of the sub-models, can be constructed using the electrochemical corrosion kinetics equation, where the corrosion rate is associated with parameters such as chloride ion concentration, temperature, and humidity. The chloride ion concentration can be converted from the salt spray concentration, and the temperature and humidity can be directly adopted from the environmental stress parameters (i.e., the environmental stress parameters can also include humidity). The ultraviolet degradation model, as another sub-model, can be constructed based on the principle of photochemical reaction kinetics. The ultraviolet degradation rate can be associated with the ultraviolet radiation intensity, wavelength, and the light absorption coefficient of the coating material. The ultraviolet radiation intensity and wavelength can be obtained from the environmental stress parameters (i.e., the environmental stress parameters can also include the ultraviolet wavelength), and the light absorption coefficient of the coating material is determined by the properties of the pre-coating material itself. The mechanical aging model, as the third sub-model, can be constructed based on the creep theory. The coating adhesion attenuation rate can be associated with the stress level, temperature, and time. The stress level can be obtained from the force analysis of the steel structure component, and the temperature can also be taken from the environmental stress parameters.

[0050] In step A201, the initialization operation of model parameters is the basis for prediction accuracy. Pre-coated multi-dimensional quality inspection data, such as coating thickness, porosity, and adhesion, can be directly used as the set values of model initial parameters. Material parameters of the pre-coating, such as chloride ion diffusion coefficient, ultraviolet absorption coefficient, and creep coefficient, can be obtained through experimental tests or by referring to material manuals, etc.

[0051] In step A202, environmental stress parameters at the location of coastal photovoltaic equipment, such as salt fog concentration, ultraviolet radiation intensity, and temperature, etc., need to be sorted into a curve form that changes over time so that the model can simulate the dynamic changes of environmental stress during the actual service process. These environmental stress parameter curves can be obtained through methods such as historical environmental monitoring data analysis, extrapolation of short-term environmental monitoring data, or typical environmental scenario assumptions.

[0052] In step A203, the model iterative solution process realizes the dynamic prediction of the quality state of the pre-coating. The preset time step can be selected according to the requirements of prediction accuracy and calculation efficiency. For example, it can be selected as 1 day, 1 week, or 1 month. Within each time step, three sub-models are solved separately to obtain the increment of salt fog corrosion depth, the increment of ultraviolet degradation degree, and the adhesion attenuation amount, and these increments are accumulated onto the current quality state of the pre-coating to obtain the predicted value of the quality state at the next time step. Through continuous iteration, the change curve of the quality state of the pre-coating during the entire service period can be obtained.

[0053] Specifically, the multi-factor coupled environmental stress accelerated aging model comprehensively simulates the aging process of the pre-coating of the steel structure parts of coastal photovoltaic equipment under the coupling action of multiple environmental stresses by integrating the salt fog corrosion model, the ultraviolet degradation model, and the mechanical aging model. The salt fog corrosion model considers the effects of salt fog, temperature, and humidity on the corrosion rate. The ultraviolet degradation model considers the effects of ultraviolet radiation intensity, wavelength, and the light absorption characteristics of the coating material on the degradation rate. The mechanical aging model considers the effects of stress, temperature, and time on the adhesion attenuation. Thus, this model can more accurately reflect the aging law of the pre-coating under the actual service environment.

[0054] Step A201 initializes the model parameters using the multi-dimensional quality inspection data of the pre-coating, enabling the model to make predictions based on the measured initial quality state of the pre-coating, eliminating the prediction errors caused by the uncertainty of the initial state, and improving the personalization and accuracy of the prediction. Step A202 determines the environmental stress input of the model based on the environmental stress parameters at the location of the coastal photovoltaic equipment, enabling the model to simulate the aging process under the actual service environment, ensuring the consistency between the prediction results and the actual situation, and improving the reliability of the prediction. Step A203 iteratively solves the model through a preset time step, realizing the dynamic prediction of the quality state of the pre-coating over time. It can not only predict the quality state of the pre-coating at a specific time point but also obtain the trend of the quality state of the pre-coating over time, providing more comprehensive information for corrosion risk assessment and operation and maintenance decisions. Therefore, this application ensures the accuracy and reliability of corrosion risk prediction by clarifying the composition and usage method of the multi-factor coupled environmental stress accelerated aging model.

[0055] In some specific embodiments, the salt spray corrosion model can be constructed by combining Faraday's law and Wagner's corrosion theory. The chloride ion concentration can be calculated from the salt spray deposition rate and solution concentration in the salt spray test standard. The temperature and humidity can be directly obtained from environmental monitoring data. The ultraviolet degradation model can be described by the Langmuir-Hinshelwood kinetic model. The ultraviolet radiation intensity and wavelength can be calculated using the solar spectrum model and geographical location parameters, and the light absorption coefficient of the coating material can be obtained through testing with a UV-visible spectrophotometer. The mechanical aging model can be described by the Findley creep model. The stress level can be obtained through finite element analysis or theoretical calculation, the temperature can be obtained from environmental monitoring data, and the time is the service time. In step A201, the initial coating thickness, porosity, and adhesion can also be obtained through on-site inspection using non-destructive testing equipment such as an ultrasonic thickness gauge, porosity tester, and pull-off adhesion tester. Material parameters such as the chloride ion diffusion coefficient, ultraviolet absorption coefficient, and creep coefficient can also be obtained through indoor accelerated aging tests and material property tests. In step A202, the environmental stress parameter curve can also be predicted by analyzing the historical meteorological data of coastal weather stations and combining with the short-term meteorological monitoring data at the photovoltaic power station site. In step A203, the time step can be set to 1 month, and the iterative solution of the model can be realized by programming using numerical calculation software such as Matlab or Python. Through the above specific embodiments, accurate prediction of the quality state of the pre-coating of the steel structure of coastal photovoltaic equipment can be achieved.

[0056] In some embodiments, in step A203, within each time step, first, according to the variation curve of salt spray concentration with time, temperature, and humidity, the corrosion depth increment of the salt spray corrosion model is calculated. Then, according to the variation curve of ultraviolet radiation intensity with time, wavelength, and the light absorption characteristics of the coating material, the ultraviolet degradation degree increment of the ultraviolet degradation model is calculated. Finally, according to the stress level, the variation curve of temperature with time, and time, the adhesion attenuation of the mechanical aging model is calculated, and these increments are accumulated onto the current quality state of the pre - coating.

[0057] Among them, within the time step, the salt spray corrosion model, the ultraviolet degradation model, and the mechanical aging model are executed in sequence to achieve the coupled calculation of the quality state increment. Specifically, first, the salt spray corrosion model is used to calculate the corrosion depth increment. The input parameters used in the calculation process include the salt spray concentration, temperature, and humidity that vary with time. These parameters act together on the salt spray corrosion model. Based on the electrochemical principle, considering the influence of chloride ion concentration, temperature, and humidity on the corrosion rate, the increment of the corrosion depth within the current time step is obtained. Secondly, the ultraviolet degradation model is used to calculate the ultraviolet degradation degree increment. The input parameters used in the calculation process include the ultraviolet radiation intensity, wavelength, and the light absorption characteristics of the coating material that vary with time. The ultraviolet degradation model is based on the photochemical reaction kinetics, considering the influence of ultraviolet radiation intensity, wavelength, and the light absorption characteristics of the coating material on the degradation rate, and thus calculates the increment of the ultraviolet degradation degree within the current time step. Then, the mechanical aging model is used to calculate the adhesion attenuation. The input parameters used in the calculation process include the stress level, the temperature that varies with time, and time. The mechanical aging model is based on the creep theory, considering the influence of stress level, temperature, and time on the adhesion attenuation, and further obtains the attenuation of the adhesion within the current time step. Finally, at the end of each time step, by accumulating the salt spray corrosion depth increment, the ultraviolet degradation degree increment, and the adhesion attenuation, the quality state of the pre - coating is updated. The quality state includes the corrosion depth, the ultraviolet degradation degree, and the adhesion. Through the above steps, in the iterative solution process of the multi - factor coupled environmental stress accelerated aging model, the coupling method of each sub - model is clear, ensuring the accuracy and reliability of the corrosion risk prediction.

[0058] In some possible implementation manners, step A3 includes: A301. Obtain the corrosion influencing factor data of the steel structure member; the corrosion influencing factor data includes the quality state of the pre - coating at different service time points and the environmental factor data of the location of the coastal photovoltaic equipment; the environmental factor data includes the salt spray concentration, temperature, and humidity; A302. According to the corrosion influencing factor data and the corrosion risk level assessment model, calculate the corrosion risk scores of the steel structure member at different service time points, and map the corrosion risk scores to the corresponding corrosion risk levels.

[0059] Among them, in step A301, the corrosion influence factor data is clearly defined and includes two main components. One part is the quality state of the pre-coated layer at different service time points. This part of the data comes from the prediction results of step A2 and is specifically reflected in the quality information such as the corrosion depth, ultraviolet degradation degree, and adhesion force generated by the pre-coated layer over time. The other part is the environmental factor data of the location of the coastal photovoltaic equipment. This part of the data specifically includes the salt spray concentration, temperature, and humidity. These environmental parameters are the key external conditions affecting the corrosion behavior of steel structural parts.

[0060] Among them, in step A302, the obtained corrosion influence factor data will be used as the input of the corrosion risk level assessment model. The model calculates the corrosion risk scores of the steel structural parts at different service time points, and then the corrosion risk scores are mapped to the corresponding corrosion risk levels, so as to realize the hierarchical assessment of corrosion risk.

[0061] Specifically, in order to evaluate the corrosion risk more comprehensively and accurately, step A3 focuses on two aspects of factors: the evolution of the quality of the pre-coated layer itself and the influence of the external environment. The pre-coated layer quality state data, such as the corrosion depth, reflects the change of the corrosion resistance ability of the coating over time. The ultraviolet degradation degree data reflects the performance decline of the coating material due to ultraviolet irradiation. The adhesion force data quantifies the bonding strength between the coating and the steel structural part. These quality state parameters can dynamically reflect the health status of the pre-coated layer at different service time points. The environmental factor data, such as the salt spray concentration, temperature, and humidity, represents the severity of the corrosion environment where the steel structural parts are located. The salt spray concentration is directly related to the corrosion erosion of chloride ions on the steel, and the temperature and humidity jointly affect the rate of the corrosion reaction. By simultaneously collecting and using the pre-coated layer quality state data and the environmental factor data, the corrosion risk level assessment model can comprehensively analyze the combined effects of internal and external factors on the corrosion risk of steel structural parts, and the corrosion risk assessment results obtained thereby can be closer to the actual situation.

[0062] In some specific implementation manners, the corrosion risk level assessment model includes a corrosion risk score model and an environmental factor risk score model; the corrosion risk score model is used to calculate the quality state risk score according to the pre-coated layer quality state parameters, and the environmental factor risk score model is used to calculate the environmental factor risk score according to the environmental factor parameters; the pre-coated layer quality state parameters include the corrosion depth, ultraviolet degradation degree, and adhesion force, and the environmental factor parameters include the salt spray concentration, temperature, and humidity; Step A302 includes: A302.1. According to the quality state of the pre-coated layer at different service time points, extract the pre-coated layer quality state parameters, and according to the environmental factor data of the location of the coastal photovoltaic equipment, extract the environmental factor parameters; A302.2. Calculate the quality status risk score corresponding to the extracted pre - coating quality status parameters and the environmental factor risk score corresponding to the extracted environmental factor parameters respectively according to the corrosion risk scoring model and the environmental factor risk scoring model; A302.3. Perform a fusion calculation on the quality status risk score and the environmental factor risk score to obtain a comprehensive corrosion risk score; A302.4. Determine the corresponding corrosion risk level according to the comprehensive corrosion risk score.

[0063] Among them, the corrosion risk level assessment model is constructed as a dual - model structure, including a corrosion risk scoring model and an environmental factor risk scoring model. The corrosion risk scoring model is used to quantify the impact of the pre - coating's own quality on the corrosion risk. Its implementation method can be, for example, presetting the scoring criteria and weights for corrosion depth, ultraviolet degradation degree, and adhesion respectively, and obtaining the quality status risk score through weighted summation. The environmental factor risk scoring model is used to quantify the impact of environmental factors on the corrosion risk. Its implementation method can be, for example, establishing a mapping relationship between salt spray concentration, temperature, and humidity and the environmental factor risk score, which can be a non - linear mapping relationship to more accurately reflect the complex impact of environmental factors. In step A302.1, the quality status parameters are extracted from the pre - coating quality status data, and the environmental factor parameters are extracted from the environmental factor data. In step A302.2, the quality status risk score and the environmental factor risk score are calculated, and the corrosion risk scoring model and the environmental factor risk scoring model are used in the calculation process respectively. In step A302.3, a fusion calculation of the quality status risk score and the environmental factor risk score is performed. The fusion calculation method can be weighted average, multiplicative model, or other fusion algorithms to comprehensively consider the combined effects of the quality status and environmental factors. In step A302.4, the comprehensive corrosion risk score is mapped to the corresponding corrosion risk level. The division of the risk level can be a preset level interval, for example, low risk, medium risk, high risk, etc., or a level value, for example, level 1, level 2, level 3, level 4, level 5, etc. Each corrosion risk level corresponds to a comprehensive corrosion risk score range, and the mapping is performed according to this corresponding relationship.

[0064] Specifically, the working principle of the corrosion risk level assessment model is as follows: First, through two independent sub-models, namely the corrosion risk scoring model and the environmental factor risk scoring model, the contributions of the pre-coated layer quality status and environmental factors to the corrosion risk are evaluated respectively. This decoupled evaluation method makes the risk assessment process more refined. Then, through fusion calculation, the scoring results of the two sub-models are combined to obtain the comprehensive corrosion risk score, so as to comprehensively consider the combined effects of the pre-coated layer quality and environmental factors. Finally, the comprehensive corrosion risk score is used to determine the final corrosion risk level, realizing the quantification and grading of the corrosion risk. Thus, the corrosion risk level of steel structure components can be evaluated more accurately, overcoming the problem that the corrosion risk level cannot be effectively quantified in traditional methods.

[0065] In some specific embodiments, the corrosion risk scoring model is designed as a linear weighted model, where the quality status risk score = w1 * corrosion depth score + w2 * ultraviolet degradation degree score + w3 * adhesion score. Here, w1, w2, and w3 are weight coefficients, and the corrosion depth score, ultraviolet degradation degree score, and adhesion score are obtained by mapping the corrosion depth, ultraviolet degradation degree, and adhesion through a preset scoring standard. The environmental factor risk scoring model is designed as a non-linear model. For example, a neural network model is used, with the salt spray concentration, temperature, and humidity as inputs and the environmental factor risk score as the output. The parameters of the neural network model are obtained by training with historical corrosion data. The fusion calculation adopts the weighted average method, and the comprehensive corrosion risk score = α * quality status risk score + (1 - α) * environmental factor risk score, where α is a weight coefficient that can be adjusted according to the actual situation. Through this embodiment, a corrosion risk level assessment model that can effectively and accurately evaluate the corrosion risk level can be constructed.

[0066] In some embodiments, step A4 includes: A401. Based on the corrosion risk levels of the steel structure components at different service time points, construct a time-series corrosion risk level curve; A402. According to the preset risk level threshold, determine the time point when the time-series corrosion risk level curve first exceeds the risk level threshold as the initial over-threshold time point; A403. Starting from the initial over-threshold time point, trace back forward to search for the time point when the time-series corrosion risk level curve first drops below the risk level threshold as the end point of the low corrosion risk period; A404. Calculate the time difference between the end point of the low corrosion risk period and the time point when the steel structure component is installed to complete to obtain the low corrosion risk period of the steel structure component.

[0067] Among them, in step A401, the construction of the time-series corrosion risk level curve can be implemented as follows: taking the service time as the horizontal axis and the corrosion risk level as the vertical axis, marking the corrosion risk level data of the steel structure at each service time point in the coordinate system, and connecting the marked points in chronological order, thereby obtaining the time-series corrosion risk level curve.

[0068] Among them, in step A402, the preset risk level threshold can be set according to engineering experience or relevant standards. For example, the risk level threshold can be set to level 3, representing medium corrosion risk. Determining the initial time point exceeding the threshold can be implemented as follows: starting from the starting point of the time-series corrosion risk level curve, searching along the positive direction of the time axis. When the corresponding corrosion risk level on the curve first exceeds the preset risk level threshold, record this time point as the initial time point exceeding the threshold.

[0069] Among them, in step A403, searching backward to find the end point of the low corrosion risk period can be implemented as follows: taking the initial time point exceeding the threshold as the starting point, searching backward along the negative direction of the time axis on the time-series corrosion risk level curve. When the corresponding corrosion risk level on the curve first drops below the risk level threshold, record this time point as the end point of the low corrosion risk period.

[0070] Among them, in step A404, calculating the low corrosion risk period can be implemented as follows: subtracting the time value corresponding to the completion time point of the installation of the steel structure from the time value corresponding to the end point of the low corrosion risk period to obtain a time difference, and this time difference is the low corrosion risk period of the steel structure. Thus, through the above steps, the low corrosion risk period is quantitatively determined.

[0071] Specifically, this method combines time-series analysis and threshold judgment to effectively predict the low corrosion risk period. Using the time-series corrosion risk level curve can clearly show the trend of the corrosion risk evolving over time, laying a foundation for subsequent threshold judgment and period definition. By presetting the risk level threshold, the acceptable and unacceptable corrosion risk levels can be quantitatively defined, making the prediction of the low corrosion risk period have a clear standard. Using the backward search method to find the end point of the low corrosion risk period can accurately capture the time critical point when the corrosion risk changes from an acceptable level to an unacceptable level, ensuring the accuracy of the prediction of the low corrosion risk period.

[0072] Furthermore, after step A401 and before step A402, the following steps can also be included: A401a. For each extreme weather event time point (i.e., the occurrence time point of each extreme weather event occurring between the installation completion moment of the steel structure and the current moment), analyze the extreme weather event type and intensity, and calculate the influence degree of the corresponding extreme weather event on the corrosion risk level; A401b. Modify the corrosion risk level after the corresponding extreme weather event time point in the time-series corrosion risk level curve according to the calculated influence degree of the corrosion risk level.

[0073] Among them, for the problem that extreme weather events affect the corrosion risk level, step A401a is proposed to analyze the type and intensity of extreme weather events at each extreme weather event time point, and calculate the influence degree of the corresponding extreme weather event on the corrosion risk level. The types of extreme weather events can include, but are not limited to, typhoons, heavy rains, high temperatures, low temperatures, etc. The intensity of extreme weather events can be characterized by quantitative indicators. For example, the intensity of a typhoon can be represented by the wind speed level, the intensity of heavy rain can be represented by the rainfall amount, and the intensity of high and low temperatures can be represented by temperature values. The calculation of the influence degree can be based on a pre-established mapping relationship model between extreme weather events and the corrosion risk level, and this model can be constructed based on historical data statistical analysis, corrosion mechanism research or expert experience. Step A401b is proposed to modify the corrosion risk level after the corresponding extreme weather event time point in the time-series corrosion risk level curve according to the influence degree calculated in step A401a. The modification method can be to directly superimpose the influence degree value on the original corrosion risk level, or to adjust it by means of weighted average, etc. Thus, the time-series corrosion risk level curve can more accurately reflect the sudden impact of extreme weather events on the corrosion risk.

[0074] Specifically, after constructing the time-series corrosion risk level curve and before determining the initial over-threshold time point, an extreme weather event influence assessment and modification step is further added. Through step A401a, for each extreme weather event recorded in the time series, first determine the specific type of the event, such as whether it is a typhoon or heavy rain. Subsequently, evaluate the intensity of the event, such as the wind force level of the typhoon or the rainfall magnitude of the heavy rain. Based on this information, using a preset influence assessment model, quantitatively calculate the specific influence degree value of this extreme weather event on the corrosion risk level of steel structural components, and this influence value may be manifested as the increase amplitude of the risk level. In step A401b, the calculated influence degree is used to modify the time-series corrosion risk level curve. Specifically, in the curve, starting from the time point when the extreme weather event occurs, the corrosion risk levels of subsequent time points are all adjusted upward, and the adjustment amplitude is the influence degree value calculated in step A401a. Through this modification, the time-series corrosion risk level curve can reflect the sudden impact of extreme weather, thereby providing a more practical risk assessment basis for the prediction of the subsequent low corrosion risk period.

[0075] In some specific embodiments, it is assumed that in the time-series corrosion risk level curve, a severe typhoon event occurs at time point T. In step A401a, after analysis, the typhoon is a severe typhoon of level 17, and it is calculated through the mapping relationship model between extreme weather events and corrosion risk levels that this severe typhoon event will cause the corrosion risk level to increase by 2 levels. In step A401b, the corrosion risk level values at time point T and all subsequent time points in the time-series corrosion risk level curve are increased by 2 based on the original values. For example, if the originally predicted corrosion risk level at time point T + 1 is level 3, it becomes level 5 after correction. In this way, the accelerating effect of extreme weather events on corrosion risk is quantified and reflected in the corrosion risk level prediction, making the prediction results of the low corrosion risk period more reliable.

[0076] Reference Figure 2 , this application also provides a corrosion risk prediction device for steel structure components of coastal photovoltaic equipment, which is used to predict the corrosion risk of steel structure components of coastal photovoltaic equipment. The device includes: A data acquisition module 1, which is used to acquire the multi-dimensional quality inspection data of the pre-coating after the installation of the steel structure component and the environmental stress parameters of the location of the coastal photovoltaic equipment; the multi-dimensional quality inspection data of the pre-coating includes coating thickness, coating porosity, and coating adhesion; the environmental stress parameters include salt spray concentration, ultraviolet radiation intensity, and temperature change range (the specific process refers to step A1 in the previous text); An aging prediction module 2, which is used to predict the quality status of the pre-coating at different service time points by using a multi-factor coupled environmental stress accelerated aging model based on the multi-dimensional quality inspection data of the pre-coating and the environmental stress parameters; the quality status includes corrosion depth, ultraviolet degradation degree, and adhesion (the specific process refers to step A2 in the previous text); A risk assessment module 3, which is used to determine the corrosion risk level of the steel structure component at different service time points through a corrosion risk level assessment model based on the quality status of the pre-coating at different service time points (the specific process refers to step A3 in the previous text); A risk warning module 4, which is used to compare the corrosion risk levels of the steel structure component at different service time points with a preset risk level threshold to predict the low corrosion risk period of the steel structure component (the specific process refers to step A4 in the previous text).

[0077] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some communication interfaces. The indirect coupling or communication connection of the devices or units can be in electrical, mechanical or other forms.

[0078] In addition, the units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0079] Furthermore, in each embodiment of this application, the various functional modules can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0080] In this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0081] The above are only the embodiments of this application and are not used to limit the protection scope of this application. For those skilled in the art, this application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included in the protection scope of this application.

Claims

1. A corrosion risk prediction method for steel structure components of coastal photovoltaic equipment, which is used to predict the corrosion risk of steel structure components of coastal photovoltaic equipment, and is characterized in that The method includes the following steps: A1. Obtain the multi-dimensional quality inspection data of the pre-coating after the installation of the steel structure components and the environmental stress parameters at the location of the coastal photovoltaic equipment; the multi-dimensional quality inspection data of the pre-coating includes coating thickness, coating porosity, and coating adhesion; the environmental stress parameters include salt fog concentration, ultraviolet radiation intensity, and temperature change range; A2. According to the multi-dimensional quality inspection data of the pre-coating and the environmental stress parameters, use the multi-factor coupled environmental stress accelerated aging model to predict the quality status of the pre-coating at different service time points; the quality status includes corrosion depth, ultraviolet degradation degree, and adhesion; A3. According to the quality status of the pre-coating at different service time points, determine the corrosion risk level of the steel structure components at different service time points through the corrosion risk level assessment model; A4. Compare the corrosion risk levels of the steel structure components at different service time points with the preset risk level threshold to predict the low corrosion risk period of the steel structure components.

2. The corrosion risk prediction method for the steel structure parts of a coastal photovoltaic device according to claim 1, wherein Step A1 includes: A101. For the surface of the steel structure components, divide multiple detection areas, and based on the corrosion sensitivity criterion, screen out the corrosion-sensitive areas from the multiple detection areas; among them, the corrosion sensitivity criterion includes weld point proximity, edge exposure degree, and water accumulation risk degree; A102. Obtain the surface image of the corrosion-sensitive area, and use the image processing algorithm to identify the coating defect type and defect area of each defect feature in the surface image; among them, the coating defect types include scratches, cracks, and bubbles; A103. According to the coating defect type and defect area, calculate the coating damage degree of the corrosion-sensitive area, and based on the coating damage degree of the corrosion-sensitive area, determine the coating thickness, coating porosity, and coating adhesion of the steel structure components; A104. Based on the historical environmental monitoring data at the location of the coastal photovoltaic equipment, extract the environmental stress parameters, and combine with the real-time environmental monitoring data to correct the environmental stress parameters to obtain the corrected environmental stress parameters.

3. A corrosion risk prediction method for steel structural components of coastal photovoltaic equipment according to claim 2, characterized in that, Step A101 includes: Obtain the three-dimensional point cloud data of the surface of the steel structure components, and based on the preset segmentation algorithm, segment the point cloud data into multiple detection areas; For each detection area, obtain the weld point proximity, edge exposure degree, and water accumulation risk degree; among them, the weld point proximity is obtained by calculating the reciprocal of the distance from the center point of the detection area to the nearest weld point, the edge exposure degree is obtained by calculating the ratio of the boundary length of the detection area to the area of the area, and the water accumulation risk degree is obtained by simulating the rainfall process and calculating the water accumulation depth of the detection area; Perform a weighted sum of the weld point proximity, edge exposure degree, and water accumulation risk degree of each detection area to obtain a comprehensive corrosion sensitivity score, and sort the comprehensive corrosion sensitivity scores from high to low, and select a preset number of detection areas as the corrosion-sensitive areas.

4. A corrosion risk prediction method for steel structural components of coastal photovoltaic equipment according to claim 2, characterized in that, Step A103 includes: According to the coating defect type and defect area of each identified defect feature, count the total defect area of each coating defect type; Calculate the weighted sum of the total defect areas of each coating defect type to obtain the coating damage degree of the corrosion-sensitive area; Using the non - linear relationship model between the coating damage degree and the coating thickness, coating porosity, and coating adhesion, calculate the coating thickness, coating porosity, and coating adhesion of the corrosion - sensitive area according to the coating damage degree of the corrosion - sensitive area; Determine the coating thickness, coating porosity, and coating adhesion of the steel structure member according to the coating thickness, coating porosity, and coating adhesion of the corrosion - sensitive area.

5. A method for predicting the corrosion risk of steel structural components of coastal photovoltaic equipment according to claim 1, characterized in that, The multi - factor coupled environmental stress accelerated aging model includes a salt - spray corrosion model, an ultraviolet degradation model, and a mechanical aging model. Among them, the salt - spray corrosion model is based on the electrochemical principle, considering the influence of chloride ion concentration, temperature, and humidity on the corrosion rate; the ultraviolet degradation model is based on the photochemical reaction kinetics, considering the influence of ultraviolet radiation intensity, wavelength, and the light absorption characteristics of the coating material on the degradation rate; the mechanical aging model is based on the creep theory, considering the influence of stress level, temperature, and time on the adhesion attenuation; Step A2 includes: A201. Initialize the parameters of the multi - factor coupled environmental stress accelerated aging model according to the multi - dimensional quality inspection data of the pre - coating; the initialized parameters include coating thickness, porosity, adhesion, chloride ion diffusion coefficient, ultraviolet absorption coefficient, and creep coefficient; A202. Determine the environmental stress input of the multi - factor coupled environmental stress accelerated aging model based on the environmental stress parameters of the location of the coastal photovoltaic equipment; the environmental stress input includes the variation curve of salt - spray concentration with time, the variation curve of ultraviolet radiation intensity with time, and the variation curve of temperature with time; A203. Iteratively solve the multi - factor coupled environmental stress accelerated aging model with a preset time step to obtain the quality state of the pre - coating at different service time points; the quality state includes corrosion depth, ultraviolet degradation degree, and adhesion.

6. A corrosion risk prediction method for steel structural components of coastal photovoltaic equipment according to claim 1, characterized in that, The said step A3 includes: A301. Obtain the corrosion influence factor data of the steel structure member; the corrosion influence factor data includes the quality state of the pre - coating at different service time points and the environmental factor data of the location of the coastal photovoltaic equipment; the environmental factor data includes salt - spray concentration, temperature, and humidity; A302. Calculate the corrosion risk scores of the steel structure member at different service time points according to the corrosion influence factor data and the corrosion risk level assessment model, and map the corrosion risk scores to the corresponding corrosion risk levels.

7. A method for predicting the corrosion risk of steel structures of coastal photovoltaic equipment according to claim 6, characterized in that, The corrosion risk level assessment model includes a corrosion risk score model and an environmental factor risk score model; the corrosion risk score model is used to calculate the quality state risk score according to the pre - coating quality state parameters, and the environmental factor risk score model is used to calculate the environmental factor risk score according to the environmental factor parameters; The pre - coating quality state parameters include corrosion depth, ultraviolet degradation degree, and adhesion, and the environmental factor parameters include salt - spray concentration, temperature, and humidity; Step A302 includes: Extract the pre - coating quality state parameters according to the quality state of the pre - coating at different service time points, and extract the environmental factor parameters according to the environmental factor data of the location of the coastal photovoltaic equipment; Calculate the quality state risk score corresponding to the extracted pre - coating quality state parameters and the environmental factor risk score corresponding to the extracted environmental factor parameters respectively according to the corrosion risk score model and the environmental factor risk score model; Perform a fusion calculation on the quality status risk score and the environmental factor risk score to obtain a comprehensive corrosion risk score; Determine the corresponding corrosion risk level according to the comprehensive corrosion risk score.

8. A corrosion risk prediction method for steel structural components of coastal photovoltaic equipment according to claim 1, characterized in that, Step A4 includes: A401. Based on the corrosion risk levels of the steel structure components at different service time points, construct a time series corrosion risk level curve; A402. According to the preset risk level threshold, determine the time point when the time series corrosion risk level curve first exceeds the risk level threshold as the initial over-threshold time point; A403. Starting from the initial over-threshold time point, trace back forward to search for the time point when the time series corrosion risk level curve first drops below the risk level threshold as the end point of the low corrosion risk period; A404. Calculate the time difference between the end point of the low corrosion risk period and the time point when the steel structure component is installed to complete to obtain the low corrosion risk period of the steel structure component.

9. A method for predicting the corrosion risk of steel structures of coastal photovoltaic equipment according to claim 8, characterized in that, After step A401 and before step A402, it also includes the step: A401a. For each extreme weather event time point, analyze the extreme weather event type and intensity, and calculate the impact degree of the corresponding extreme weather event on the corrosion risk level; A401b. According to the calculated impact degree of the corrosion risk level, correct the corrosion risk level after the corresponding extreme weather event time point in the time series corrosion risk level curve.

10. A corrosion risk prediction device for steel structure components of coastal photovoltaic equipment, which is used to predict the corrosion risk of steel structure components of coastal photovoltaic equipment, is characterized in that, The device includes: A data acquisition module for acquiring the multi-dimensional quality inspection data of the pre-coating after the steel structure component is installed and the environmental stress parameters at the location of the coastal photovoltaic equipment; the multi-dimensional quality inspection data of the pre-coating includes coating thickness, coating porosity, and coating adhesion; the environmental stress parameters include salt fog concentration, ultraviolet radiation intensity, and temperature change range; An aging prediction module for predicting the quality status of the pre-coating at different service time points by using a multi-factor coupled environmental stress accelerated aging model according to the multi-dimensional quality inspection data of the pre-coating and the environmental stress parameters; the quality status includes corrosion depth, ultraviolet degradation degree, and adhesion; A risk assessment module for determining the corrosion risk level of the steel structure component at different service time points through a corrosion risk level assessment model according to the quality status of the pre-coating at different service time points; A risk warning module for comparing the corrosion risk levels of the steel structure component at different service time points with the preset risk level threshold to predict the low corrosion risk period of the steel structure component.

Images