Coastal region corrosion grade map generation method and related apparatus

Abstract

Provided in the present invention are a coastal region corrosion grade map generation method and apparatus, the method comprising: deploying an intelligent sensor network in a coastal region to be studied, and, by means of the intelligent sensor network, continuously acquiring and preprocessing environmental parameters and corrosion data of metal materials in the region; performing feature extraction on the preprocessed environmental parameters and corrosion data to obtain time series features, and using the time series features and characteristic data of the metal materials in the region to train a pre-established prediction model, so as to obtain a corrosion prediction model; using the corrosion prediction model to acquire a corrosion prediction result of the region, and, by combining same and geospatial data, generating a corrosion grade map of said coastal region at a current time point; and using environmental parameters and corrosion data newly acquired by the intelligent sensor network to update the corrosion prediction model. The present invention acquires data extensively and comprehensively, and simultaneously allows models to be continuously updated over time and environmental changes, thus ensuring the accuracy of corrosion grade maps.

Description

Method for drawing a coastal area corrosion grade map and related device TECHNICAL FIELD

[0001] The present application belongs to the technical field of corrosion grade map drawing, and specifically relates to a method for drawing a coastal area corrosion grade map and a related device. BACKGROUND

[0002] With the rapid development of the global marine economy, the infrastructure construction and maintenance of coastal areas are facing severe corrosion challenges. Accurate assessment and drawing of a corrosion grade map is of great significance for preventive maintenance, material selection and environmental protection. However, existing technical means encounter many limitations in achieving this goal.

[0003] Firstly, due to the limitations of manpower and cost, researchers can only sample and measure in limited areas. The sparsity of data collection directly leads to a serious lack of coverage, and the universal applicability and credibility of research conclusions are greatly discounted. This local data-driven analysis may produce significant cognitive bias due to the neglect of special corrosion phenomena in some key areas, affecting the practicality and accuracy of the final results. Secondly, corrosion is a dynamic process, and its grade fluctuates with changes in the natural environment and the influence of human activities. Most existing data collection modes are one-time static snapshots, which cannot track this dynamic nature, so the decisions made based on past data may have already lagged behind the actual situation. The lag in data updates undoubtedly poses potential risks to institutions that rely on these data for risk management and strategy planning. In addition, the high cost and inefficient work process constitute another challenge. Traditional data acquisition relies on intensive manpower and material resources, especially in remote and complex terrain areas. This process is both time-consuming and costly, severely restricting the possibility of large-scale data collection. Coupled with limited measurement technology and human operational variables, the quality and accuracy of the data obtained are often questioned, affecting the effective planning and implementation of subsequent prevention measures.

[0004] In view of the above challenges, there is an urgent need for an innovative technology that can efficiently, accurately and dynamically draw a coastal area corrosion grade map to overcome the limitations of existing technologies and provide strong technological support for the sustainable development of coastal areas.

[0005] SUMMARY

[0006] In view of this, the purpose of the present application is to propose a coastal area corrosion level mapping method and related device, aiming to fundamentally solve the two core problems in the prior art field, namely the limitation of data coverage and the obstacle of data timely updating. Through the present application, the integrity, accuracy and dynamic adaptability of the corrosion map can be effectively improved, ensuring that the map can fully reflect the corrosion condition of the coastal area, and realizing the continuous updating of the data, thereby overcoming the static nature and inaccuracy of the map information under the traditional mapping method, and providing more reliable and timely information support for corrosion monitoring and protection strategy.

[0007] In order to achieve the above-mentioned purpose, the technical scheme provided by the present application is as follows:

[0008] In the first aspect, the present application provides a mapping method of a coastal area corrosion level map, comprising the following steps:

[0009] Deploying an intelligent sensor network in the coastal area to be studied, and continuously collecting environmental parameters and corrosion data of metal materials in the region through the intelligent sensor network, the intelligent sensor network comprising a plurality of monitoring sites, the monitoring range of the plurality of monitoring sites covering the coastal area to be studied, and each monitoring site pre-processing the collected parameters and data;

[0010] Feature extraction is performed on the pre-processed environmental parameters and corrosion data to obtain time series features, and a pre-established prediction model is trained using the time series features and characteristic data of the metal materials in the region to obtain a corrosion prediction model;

[0011] The corrosion prediction model is used to obtain the corrosion prediction result in the region, and a corrosion level map of the coastal area to be studied at the current time node is drawn in combination with geographic spatial data;

[0012] The corrosion prediction model is updated using newly collected environmental parameters and corrosion data of the intelligent sensor network, so that the corrosion prediction result matches the corrosion trend at the drawing time node.

[0013] Further, the pre-processing process of each monitoring site of the intelligent sensor network comprises:

[0014] Data cleaning, outlier detection, missing data filling and data normalization.

[0015] Further, the corrosion prediction result of the corrosion prediction model includes the corrosion rate, corrosion mode and corrosion trend of the metal materials in the region, and according to the corrosion prediction result, the mapping method further comprises:

[0016] Optimizing the layout of the monitoring sites in the intelligent sensor network according to the corrosion rate, corrosion mode and corrosion trend of the metal materials in the region, wherein the higher the corrosion level of the region, the denser the layout of the monitoring sites.

[0017] Collecting new environmental parameters and corrosion data by the optimized intelligent sensor network to update the corrosion prediction model;

[0018] Performing corrosion trend early warning according to the corrosion prediction result of the new corrosion prediction model.

[0019] Further, the random forest algorithm is used to establish the prediction model, and the training process of the prediction model includes:

[0020] Divide the training set of the trained model into several subsets, select one subset as the validation set and the other subsets as the training set each time, and perform cyclic training and validation on the model;

[0021] The grid search and / or random search method is used to optimize the hyperparameters of the model.

[0022] Further, a corrosion grade map is drawn according to the corrosion prediction result and the geographic space data, including:

[0023] Based on the corrosion prediction result, the corrosion data is spatially interpolated to obtain corrosion data covering the entire area;

[0024] Create several layers, each layer corresponding to a data type, and the data type at least including corrosion intensity, geographical boundary and sensor position, and the corrosion intensity, geographical boundary and sensor position are determined according to the corrosion data, geographic space data and layout of the intelligent sensor network respectively;

[0025] Set the style of different layers, and the style is used to reflect the characteristics of the data type;

[0026] Superimpose each layer to display different characteristic information in the region by using different styles.

[0027] In a second aspect, the present application provides a device for drawing a corrosion grade map of a coastal area, comprising:

[0028] A data acquisition module is used to continuously collect environmental parameters and corrosion data of metal materials in the region through an intelligent sensor network deployed in the coastal area to be studied, the intelligent sensor network includes several monitoring sites, the monitoring range of the several monitoring sites covers the coastal area to be studied, and each monitoring site pre-processes the collected parameters and data;

[0029] A model training module is used to extract features from the pre-processed environmental parameters and corrosion data to obtain time series features, train a pre-established prediction model using the time series features and characteristic data of metal materials in the region, and obtain a corrosion prediction model;

[0030] The mapping module is configured to obtain corrosion prediction results in the region by using the corrosion prediction model, and draw a corrosion level map of the coastal region to be studied at a current time node in combination with geographic space data.

[0031] The model updating module is configured to update the corrosion prediction model by using newly collected environmental parameters and corrosion data of the intelligent sensor network, so that the corrosion prediction results match the corrosion trend at the drawing time node.

[0032] Further, the corrosion prediction results of the corrosion prediction model include the corrosion rate, corrosion mode and corrosion trend of the metal material in the region, and the drawing method further includes:

[0033] According to the corrosion rate, corrosion mode and corrosion trend of the metal material in the region, the layout of the monitoring sites in the intelligent sensor network is optimized, wherein the higher the corrosion level of the region, the denser the layout of the monitoring sites.

[0034] New environmental parameters and corrosion data are collected by using the optimized intelligent sensor network to update the corrosion prediction model.

[0035] According to the corrosion prediction results of the new corrosion prediction model, a corrosion trend warning is performed.

[0036] Further, the corrosion level map is drawn according to the corrosion prediction results and the geographic space data, including:

[0037] Based on the corrosion prediction results, spatial interpolation is performed on the corrosion data to obtain corrosion data covering the entire region.

[0038] A plurality of layers are created, and each layer corresponds to a data type, and the data type at least includes corrosion intensity, geographic boundary and sensor position, and the corrosion intensity, geographic boundary and sensor position are determined according to the corrosion data, geographic space data and layout of the intelligent sensor network respectively.

[0039] Styles of different layers are set, and the styles are used to reflect the characteristics of the data types.

[0040] Each layer is superimposed, and different styles are used to display different characteristic information in the region.

[0041] Correspondingly, the application also provides a computer device, which includes a processor and a memory:

[0042] The memory is configured to store a computer program and send instructions of the computer program to the processor.

[0043] The processor executes the drawing method of the corrosion level map of the coastal region according to the instructions of the computer program.

[0044] Correspondingly, the application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the method for drawing a coastal area corrosion grade map according to the first aspect.

[0045] In conclusion, the application provides a method and device for drawing a coastal area corrosion grade map, which comprises deploying an intelligent sensor network in a coastal area to be studied, and continuously collecting environmental parameters and corrosion data of metal materials in the area through the intelligent sensor network, the intelligent sensor network comprising a plurality of monitoring sites, the monitoring range of the plurality of monitoring sites covering the coastal area to be studied, and each monitoring site pre-processing the collected parameters and data; performing feature extraction on the pre-processed environmental parameters and corrosion data to obtain time series features, training a pre-established prediction model using the time series features and characteristic data of metal materials in the area to obtain a corrosion prediction model; obtaining a corrosion prediction result in the area through the corrosion prediction model, and drawing a corrosion grade map of the coastal area to be studied at a current time node in combination with geographic spatial data; and updating the corrosion prediction model using newly collected environmental parameters and corrosion data of the intelligent sensor network, so as to match the corrosion prediction result with a corrosion trend at the drawing time node. The application can ensure the accuracy of the corrosion grade map by collecting data extensively and comprehensively, and continuously updating the model with time and environmental changes. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0047] Fig. 1 is a flowchart of a method for drawing a coastal area corrosion grade map according to an embodiment of the application;

[0048] Fig. 2 is a schematic diagram of a partial coastal area corrosion grade map according to an embodiment of the application;

[0049] Fig. 3 is a block diagram of a drawing device for a coastal area corrosion grade map according to an embodiment of the application;

[0050] Fig. 4 is a block diagram of a computer device according to an embodiment of the application. DETAILED DESCRIPTION

[0051] In order to make the purposes, characteristics and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the embodiments described below are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0052] Referring to FIG. 1, the present embodiment provides a method for drawing a coastal area corrosion grade map, including the following steps:

[0053] S1: deploying an intelligent sensor network in the coastal area to be studied, and continuously collecting environmental parameters and corrosion data of metal materials in the area through the intelligent sensor network, the intelligent sensor network including a plurality of monitoring sites, the monitoring range of the plurality of monitoring sites covering the coastal area to be studied, and each monitoring site pre-processing the collected parameters and data.

[0054] It should be noted that this step first arranges an intelligent sensor network composed of multiple monitoring sites in the target coastal area. These monitoring sites are widely distributed to ensure that the entire study area is covered. The sensor network not only continuously monitors environmental parameters such as humidity, salt concentration, temperature, etc., but also directly collects real-time corrosion data of metal materials. Each site has data preprocessing capability, i.e., preliminary cleaning and formatting of collected information, to prepare for subsequent analysis.

[0055] S2: feature extraction is performed on the pre-processed environmental parameters and corrosion data to obtain time series features, and a pre-established prediction model is trained using the time series features and characteristic data of the metal materials in the area to obtain a corrosion prediction model.

[0056] It should be noted that after the collected data is pre-processed, time series features are further extracted, which reflect the change law of the corrosion process over time. At the same time, combined with the specific characteristics (such as composition, structure, etc.) of the metal materials in the area, these features are used to train a preliminary constructed prediction model. This model can be based on machine learning or deep learning algorithms and can predict the possibility and degree of future corrosion based on historical data.

[0057] S3: obtaining corrosion prediction results in the area through the corrosion prediction model, and drawing a corrosion grade map of the coastal area to be studied at the current time node in combination with geographic spatial data.

[0058] It is worth noting that the trained corrosion prediction model is used to predict the corrosion situation of the entire coastal area at a certain time point in the future. The prediction results are combined with detailed geospatial data, such as GIS (Geographic Information System) data, to generate a corrosion level map. This map uses different colors or patterns to indicate the severity of corrosion in different areas, providing a visual reference for decision-makers.

[0059] S4: Update the corrosion prediction model with the newly collected environmental parameters and corrosion data from the intelligent sensor network, so that the corrosion prediction results match the corrosion trend at the drawing time node.

[0060] It is worth noting that in order to ensure the timeliness and accuracy of the prediction, this method also includes a dynamic updating mechanism for the model. The intelligent sensor network will continuously collect new environmental parameters and corrosion data, and these latest data will be used to update the original corrosion prediction model, ensuring that the model's prediction results are consistent with the actual corrosion trend, achieving continuous monitoring and adaptive assessment of corrosion conditions.

[0061] This embodiment provides a method for drawing a coastal area corrosion level map. By deploying an intelligent sensor network to continuously monitor environmental factors and metal corrosion conditions, these sensor networks are widely distributed and can autonomously preprocess data. After feature extraction, the collected data is combined with metal properties to optimize the prediction model, which can accurately predict the corrosion level of the area. The prediction results are combined with geographic information to generate a real-time corrosion level map, which visually displays the corrosion distribution and severity. Most importantly, the system can learn and update itself, ensuring that the prediction model remains accurate over time and environmental changes, effectively guiding the planning and implementation of corrosion protection measures. Overall, this solution greatly improves the accuracy and efficiency of corrosion monitoring, providing a scientific and dynamic management tool for protecting coastal infrastructure and environmental resources.

[0062] In some embodiments, the intelligent sensor network is widely deployed with sensors in the coastal area, which can monitor environmental parameters (such as temperature, humidity, salt fog concentration, etc.) and corrosion conditions of metal materials in real time. These data are collected through high-precision and high-reliability sensors to ensure the quality and accuracy of the acquired data.

[0063] The collected data will be uploaded in real time through advanced online monitoring systems and preprocessed using complex data processing algorithms. Preprocessing includes data cleaning, outlier detection, missing data filling, and data normalization to ensure the accuracy and reliability of subsequent analysis. Specific preprocessing steps include:

[0064] 1) Data cleaning: Use Pandas library in Python to clean the raw data, remove invalid data and obvious error data. For example, records with temperature sensor readings beyond the physically reasonable range will be marked and deleted.

[0065] 2) Outlier detection: Use standard deviation-based method and boxplot method to identify outliers. For example, by calculating the standard deviation of each environmental parameter, identify and remove outliers beyond 3 times the standard deviation.

[0066] 3) Missing data filling: Use K-Nearest Neighbors (KNN) algorithm to fill in missing data. KNN algorithm calculates the Euclidean distance between missing data points and other data points, and selects the average value of the nearest K data points for filling.

[0067] In this embodiment, each monitoring site of the intelligent sensor network has edge computing capability, which can preprocess the collected data. The advantage of this is that edge computing reduces the burden of the cloud server, so that the central server can focus on more complex tasks such as model training and advanced analysis, while the edge device handles more basic but immediate data processing work, which can more reasonably allocate computing resources. In addition, intelligent sensors can flexibly adjust the preprocessing strategy according to the field conditions, such as adjusting the sampling rate or using different filtering algorithms according to the current environmental changes to adapt to the data processing needs in different scenarios along the coast.

[0068] In some embodiments, the corrosion prediction result of the corrosion prediction model includes the corrosion rate, corrosion mode and corrosion trend of the metal material in the region, and according to the corrosion prediction result, the method further comprises:

[0069] S21: According to the corrosion rate, corrosion mode and corrosion trend of the metal material in the region, the layout of the monitoring site in the intelligent sensor network is optimized, wherein the higher the corrosion level of the region, the denser the layout of the monitoring site.

[0070] It should be noted that this step determines which regions have higher corrosion risks according to the corrosion rate, corrosion mode and trend information provided by the corrosion prediction model. The density of monitoring sites is increased in regions with higher corrosion levels. This can ensure that more detailed data is obtained in areas most susceptible to corrosion, facilitating timely detection of corrosion problems and evaluation of the effectiveness of protective measures.

[0071] S22: Use the optimized intelligent sensor network to collect new environmental parameters and corrosion data to update the corrosion prediction model.

[0072] It is worth noting that the new data collected after the optimized layout can continuously enrich and calibrate the model. The intelligent sensor network collects environmental parameters (such as humidity, temperature, pH value, etc.) and corrosion data (such as corrosion depth, rate, etc.) according to the optimized layout. These new data are fed back to the corrosion prediction model to adjust the model parameters or algorithm and improve the prediction accuracy.

[0073] S23: According to the corrosion prediction results of the new corrosion prediction model, the corrosion trend warning is carried out.

[0074] It is worth noting that based on the updated corrosion prediction model, the corrosion trend in the future period of time can be analyzed. If the prediction results output by the model show that the corrosion rate in some areas will significantly accelerate or reach the dangerous threshold, the system will automatically trigger a warning signal.

[0075] In some embodiments, the main goal of the established prediction model is to predict the corrosion rate and corrosion mode of metal materials in coastal areas under different environmental conditions. Through comprehensive analysis of environmental parameters (such as temperature, humidity, salt fog concentration, etc.) and metal corrosion data, the model can provide the following key predictions:

[0076] (1) Corrosion rate prediction: predict the corrosion rate of metal materials in a specific period of time to quantify the degree of corrosion.

[0077] (2) Corrosion mode identification: identify the corrosion mode of metal materials under different environmental conditions (such as uniform corrosion, local corrosion, etc.).

[0078] (3) Future corrosion trend prediction: predict the corrosion trend in the future period of time, provide warning information, and help take preventive measures in advance.

[0079] After data preprocessing, in-depth feature extraction is performed on environmental parameters and corrosion data. Feature engineering is a key step in the machine learning process, through which more representative information can be extracted from raw data. Specifically, time series features are generated for environmental parameters such as temperature, humidity, and salt fog concentration, such as past one-week moving average, standard deviation, etc. At the same time, statistical features such as maximum value, minimum value, average value, etc. are extracted. In addition, combined with the physical and chemical characteristics of metal materials, such as the chemical composition of the metal, the surface treatment method, the type of coating, etc., these features can significantly improve the interpretability and prediction accuracy of the model.

[0080] After feature engineering is completed, the random forest algorithm is selected to establish the corrosion prediction model. Random forest algorithm has significant advantages in handling multi-dimensional data and non-linear relationships, specifically using RandomForestRegressor in Scikit-learn library for model training.

[0081] In some embodiments, the steps of training and validating the prediction model are as follows:

[0082] (1) Data set division:

[0083] The collected data set is divided into training set, validation set and test set, with the proportion of 70%, 20% and 10% respectively. The training set is used for model training, the validation set is used for model parameter adjustment and optimization, and the test set is used for evaluating the final performance of the model. Through such division method, the generalization ability and stability of the model on different data sets are ensured.

[0084] (2) Model training and optimization:

[0085] During the model training process, cross-validation technique is used to comprehensively evaluate the model. Cross-validation technique further divides the training set into K subsets, each time selects one subset as the validation set, and the other subsets as the training set, and the training and validation are carried out in a loop, and finally the average value is taken as the evaluation index of the model. In addition, grid search and random search methods are used to optimize the hyperparameters of the model, and the number of trees, maximum depth, minimum sample leaf node number and other parameters of random forest are optimized to ensure the best performance of the model under different parameter combinations.

[0086] In addition, in order to ensure the timeliness and accuracy of the model, online learning and real-time updating are carried out as follows:

[0087] (3) Online learning and real-time updating:

[0088] In order to ensure the timeliness and accuracy of the model, online learning technology is introduced. Online learning technology allows the model to continuously update when real-time data arrives, constantly adjusts the model parameters, and improves the prediction accuracy. For example, incremental learning algorithm is used to enable the model to directly update the parameters without retraining, and improve the adaptability to new data.

[0089] In some embodiments, the corrosion mapping includes the following steps:

[0090] (1) Preparation of data visualization:

[0091] After completing the training and validation of the model, the prediction results are converted into intuitive and easy-to-understand corrosion maps. For this purpose, first prepare the required geospatial data, including the geographical boundaries of coastal areas, sensor locations, terrain data, etc. These geographic data will be combined with the corrosion prediction results to form the basic map data layer.

[0092] (2) Spatial interpolation of corrosion data:

[0093] Two main spatial interpolation methods are used to generate the corrosion intensity distribution map: inverse distance weighting (IDW) and Kriging interpolation.

[0094] 1) Inverse Distance Weighting (IDW):

[0095] IDW is a distance-based interpolation method suitable for areas with dense point data and smooth changes. The principle of this method is to calculate the weight according to the distance between the known measurement points and the points to be predicted, and the closer the distance, the greater the contribution to the predicted value. IDW interpolation is implemented using the GDAL library in Python, with the following steps:

[0096] S31: Determine the positions of known points and points to be predicted.

[0097] S32: Calculate the distance from each known point to the point to be predicted.

[0098] S33: Calculate the weight according to the distance, and use the weight to perform a weighted average of the corrosion data of the known points to obtain the corrosion intensity of the point to be predicted.

[0099] S34: Repeat the above steps to generate the corrosion intensity distribution map of the entire area.

[0100] 2) Kriging Interpolation:

[0101] Kriging interpolation is a statistical-based interpolation method suitable for data with strong spatial correlation. Kriging interpolation not only considers distance, but also considers spatial variability, providing unbiased and optimal prediction results. Kriging interpolation is performed using the PyKrige library, with the following steps:

[0102] S41: Construct a spatial variability function to describe the spatial correlation between known points.

[0103] S42: Calculate the influence of each known point on the points to be predicted based on the spatial variability function.

[0104] S43: Calculate the corrosion intensity of each point to be predicted using spatial correlation and distance.

[0105] S44: Generate a high-precision corrosion prediction map for the entire area.

[0106] (3) Corrosion Map Drawing:

[0107] Use geographic information system (GIS) software (such as ArcGIS) to combine the spatially interpolated corrosion data with geographic boundary data to generate an intuitive corrosion map. The specific steps are as follows:

[0108] 1) Data import and layer management:

[0109] The interpolated corrosion data and geographic boundary data are imported into GIS software to create multiple layers. Each layer represents a data type, such as corrosion intensity, geographic boundary, sensor location, etc.

[0110] 2) Map style setting:

[0111] The style of each layer is set, including color, marker, transparency, etc. For example, use color gradient to represent corrosion intensity, with color changing from blue (low corrosion) to red (high corrosion).

[0112] 3) Superimposed analysis and comprehensive display:

[0113] Superimpose different layers to form a comprehensive display effect. Through superimposed analysis, the spatial distribution of corrosion intensity and high-risk areas can be clearly displayed.

[0114] 4) Interactive function and user interface:

[0115] Add interactive functions to the corrosion map, such as zooming, panning, clicking to view detailed information, etc. Through a user-friendly interface, users can easily browse and analyze corrosion data. The corrosion level map of the coastal area drawn according to the above steps is shown in Figure 2.

[0116] In addition, based on the generated corrosion map, a comprehensive assessment of the corrosion risk of the coastal area is made, and corresponding anticorrosion measures are proposed. As follows:

[0117] 1) Risk classification and regional division:

[0118] According to the corrosion intensity, the area is divided into low-risk, medium-risk and high-risk areas.

[0119] 2) Risk map generation:

[0120] In the corrosion map, use different colors and markers to mark the corrosion risk level of each area, providing intuitive visual reference. For example, low-risk areas are marked in green, medium-risk areas are marked in yellow, and high-risk areas are marked in red.

[0121] 3) Anticorrosion measures:

[0122] According to the corrosion risk assessment results, develop corresponding anticorrosion measures and strategies. For example, in high-risk areas, it is recommended to use corrosion-resistant materials and anticorrosive coatings, and to conduct regular monitoring and maintenance. At the same time, according to the corrosion mode recognition results, take targeted protective measures, such as preventing local corrosion and stress corrosion cracking, etc.

[0123] In combination with the above examples, compared with the prior art, the present application has the following advantages:

[0124] (1) More comprehensive data collection

[0125] By utilizing big data sensing devices, the present application can collect environmental parameters such as humidity, temperature, and salinity concentration in a wider area. These data can more comprehensively reflect the actual environmental conditions in coastal areas than traditional methods, thereby improving the accuracy of research and prediction.

[0126] (2) Real-time data monitoring and dynamic updating

[0127] By combining real-time corrosion monitoring data and environmental data, and using machine learning algorithms, the present application can not only analyze current data but also predict future corrosion trends. This enables the corrosion map to be dynamically updated, reflecting real-time corrosion conditions, which is superior to traditional static and time-lagging data updating methods.

[0128] (3) High-precision corrosion prediction

[0129] Through the complex data analysis capability of machine learning, the present application can consider the influence of multiple factors on corrosion and achieve precise prediction of the corrosion process. This precision improvement is difficult to achieve with traditional methods based on simple statistics or empirical judgment.

[0130] (4) Cost-effectiveness

[0131] Although initial equipment and system setup may require some investment, in the long run, through big data and machine learning optimization of data collection and processing, the frequency and range of manual sampling can be reduced, and the overall cost of maintenance and operation can be reduced.

[0132] (5) Strong data support for decision-making

[0133] With high-precision and real-time updated corrosion maps, the present application can provide stronger data support for equipment maintenance, material selection, and related policy making in coastal areas, enhancing the scientificity and effectiveness of decision-making.

[0134] (6) Easy to expand and highly adaptable

[0135] The method of the present application is applicable to different scales and types of coastal areas, easy to expand to larger geographical ranges and different application scenarios, with good adaptability and broad application prospects.

[0136] Based on the same inventive concept, the present application also provides a device for drawing a coastal area corrosion grade map for implementing the method of drawing a coastal area corrosion grade map as described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in the following device embodiment of the coastal area corrosion grade map drawing device can be referred to the limitations of the coastal area corrosion grade map drawing method in the above text, which will not be repeated here.

[0137] Referring to FIG. 3, the embodiment provides a device for drawing a corrosion grade map of a coastal area, comprising:

[0138] a data collection module, configured to continuously collect environmental parameters and corrosion data of metal materials in the area through an intelligent sensor network deployed in the coastal area to be studied, the intelligent sensor network comprising a plurality of monitoring sites, the monitoring range of the plurality of monitoring sites covering the coastal area to be studied, and each monitoring site pre-processing the collected parameters and data;

[0139] a model training module, configured to perform feature extraction on the pre-processed environmental parameters and corrosion data to obtain time series features, and train a pre-established prediction model using the time series features and characteristic data of metal materials in the area to obtain a corrosion prediction model;

[0140] a map drawing module, configured to obtain corrosion prediction results in the area through the corrosion prediction model, and draw a corrosion grade map of the coastal area to be studied at a current time node in combination with geographic space data;

[0141] a model updating module, configured to update the corrosion prediction model using newly collected environmental parameters and corrosion data of the intelligent sensor network, so that the corrosion prediction results match the corrosion trend at the drawing time node.

[0142] In some embodiments, the corrosion prediction results of the corrosion prediction model include corrosion rates, corrosion modes and corrosion trends of metal materials in the area, and according to the corrosion prediction results, the drawing method further comprises:

[0143] optimizing the layout of the monitoring sites in the intelligent sensor network according to the corrosion rates, corrosion modes and corrosion trends of metal materials in the area, wherein the higher the corrosion grade of an area, the denser the layout of the monitoring sites in the area;

[0144] collecting new environmental parameters and corrosion data using the optimized intelligent sensor network to update the corrosion prediction model;

[0145] conducting corrosion trend early warning according to the corrosion prediction results of the new corrosion prediction model.

[0146] In some embodiments, drawing the corrosion grade map according to the corrosion prediction results and the geographic space data comprises:

[0147] spatially interpolating the corrosion data based on the corrosion prediction results to obtain corrosion data covering the entire area;

[0148] create several layers, each layer corresponds to a data type, the data type at least includes corrosion intensity, geographical boundary and sensor position, the corrosion intensity, the geographical boundary and the sensor position are determined according to corrosion data, geographical space data and the layout of the intelligent sensor network respectively;

[0149] set the style of different layers, the style is used to reflect the characteristics of the data type;

[0150] superimpose each layer, and display different characteristic information in the region by using different styles.

[0151] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0152] Referring to FIG. 4, the embodiment of the application further provides a computer device 4, comprising a memory 402 and a processor 401 and a computer program 403 stored in the memory 402, when the computer program 403 is executed on the processor 401, the drawing method of the coastal area corrosion grade map is realized as described in any one of the above methods.

[0153] The computer device 4 can be a desktop computer, a notebook computer, a palm computer and a cloud server, etc. The computer device 4 can include, but is not limited to, a processor 401 and a memory 402. Those skilled in the art can understand that FIG. 4 is only an example of the computer device 4, and does not constitute a limitation on the computer device 4, and can include more or fewer components than the illustration, or combine certain components, or different components, for example, it can also include input / output devices, network access devices, etc.

[0154] The processor 401 can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0155] The memory 402 can be an internal storage unit of the computer device 4 in some embodiments, for example, a hard disk or a memory of the computer device 4. The memory 402 can also be an external storage device of the computer device 4 in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 402 can include both the internal storage unit and the external storage device of the computer device 4. The memory 402 is used to store an operating system, an application program, a boot loader, data and other programs, for example, program codes of the computer program, etc. The memory 402 can also be used to temporarily store data that has been output or is to be output.

[0156] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is run by a processor to implement the method for drawing a coastal area corrosion grade map according to any one of the above methods.

[0157] In this embodiment, the integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the computer program for instructing the relevant hardware to complete all or part of the processes in the above-described embodiment methods can be stored in a computer readable storage medium. The computer program can be executed by a processor to implement the steps of the above-mentioned various method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the photographing device / terminal equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer readable medium can not be an electrical carrier signal and a telecommunication signal.

[0158] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0159] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solutions. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0160] In the embodiments disclosed in the present application, it should be understood that the disclosed apparatus / terminal equipment and methods can be implemented in other ways. For example, the apparatus / terminal equipment embodiments described above are only schematic, for example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed mutual units can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0161] The above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced by equivalent features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of mapping a coastal area corrosion rating, characterized by, The method comprises the following steps: deploying an intelligent sensor network in a coastal area to be studied, and continuously collecting environmental parameters and corrosion data of metal materials in the area through the intelligent sensor network, the intelligent sensor network comprising a plurality of monitoring sites, the monitoring range of each monitoring site covering the coastal area to be studied, and each monitoring site pre-processing the collected parameters and data; extracting features from the pre-processed environmental parameters and corrosion data to obtain time series features, training a pre-established prediction model using the time series features and characteristic data of metal materials in the area to obtain a corrosion prediction model; obtaining corrosion prediction results in the area through the corrosion prediction model, and drawing a corrosion level map of the coastal area to be studied at the current time node in combination with geographic spatial data; updating the corrosion prediction model using newly collected environmental parameters and corrosion data of the intelligent sensor network to match the corrosion prediction results with the corrosion trend at the drawing time node.

2. The method of claim 1, wherein, The pre-processing process of each monitoring site of the intelligent sensor network comprises: data cleaning, outlier detection, missing data filling, and data normalization.

3. The method of claim 1, wherein, The corrosion prediction results of the corrosion prediction model include the corrosion rate, corrosion mode, and corrosion trend of metal materials in the area, and the drawing method further comprises: optimizing the layout of the monitoring sites in the intelligent sensor network according to the corrosion rate, corrosion mode, and corrosion trend of metal materials in the area, wherein the higher the corrosion level of an area, the denser the layout of the monitoring sites in the area; collecting new environmental parameters and corrosion data using the optimized intelligent sensor network to update the corrosion prediction model; conducting corrosion trend early warning according to the corrosion prediction results of the new corrosion prediction model.

4. The method of claim 1, wherein, The random forest algorithm is used to establish the prediction model, and the training process of the prediction model comprises: dividing the training set of the training model into a plurality of subsets, selecting one subset as a validation set and the other subsets as training sets each time, and cyclically training and validating the model; using the grid search and / or random search method to optimize the hyperparameters of the model.

5. The method of claim 1, wherein, Drawing a corrosion level map according to the corrosion prediction results and the geographic spatial data comprises: spatially interpolating corrosion data based on corrosion prediction results to obtain corrosion data covering the entire area; creating a plurality of layers, each layer corresponding to a data type, the data type at least including corrosion intensity, geographic boundary, and sensor location, the corrosion intensity, geographic boundary, and sensor location being determined according to the corrosion data, geographic spatial data, and layout of the intelligent sensor network respectively; setting the style of different layers, the style being used to reflect the characteristics of the data type; superimposing each layer to display different characteristic information in the area using different styles.

6. A device for drawing a map of a corrosion level in a coastal area, characterized by The method comprises the following steps: The data acquisition module is used for continuously collecting environmental parameters and corrosion data of metal materials in the region through an intelligent sensor network deployed in the coastal region to be studied, the intelligent sensor network comprising a plurality of monitoring sites, the monitoring range of each of the monitoring sites covering the coastal region to be studied, and each of the monitoring sites pre-processing the collected parameters and data; The model training module is used for extracting features from the pre-processed environmental parameters and corrosion data to obtain time series features, training a pre-established prediction model using the time series features and characteristic data of metal materials in the region, and obtaining a corrosion prediction model; The map drawing module is used for obtaining corrosion prediction results in the region through the corrosion prediction model, and drawing a corrosion level map of the coastal region to be studied at a current time node in combination with geographic space data; The model updating module is used for updating the corrosion prediction model using newly collected environmental parameters and corrosion data of the intelligent sensor network, so that the corrosion prediction results match the corrosion trend at the drawing time node.

7. The apparatus for drawing a coastal area corrosion classification map according to claim 6, wherein The corrosion prediction results of the corrosion prediction model include corrosion rates, corrosion modes and corrosion trends of metal materials in the region, and the drawing method further comprises: According to the corrosion rates, corrosion modes and corrosion trends of metal materials in the region, the layout of the monitoring sites in the intelligent sensor network is optimized, wherein the higher the corrosion level of a region, the denser the layout of the monitoring sites; New environmental parameters and corrosion data are collected using the optimized intelligent sensor network to update the corrosion prediction model; According to the corrosion prediction results of the new corrosion prediction model, a corrosion trend warning is given. According to the corrosion prediction results and the geographic space data, a corrosion level map is drawn, comprising:

8. The apparatus for drawing a coastal area corrosion level map according to claim 6, wherein Based on the corrosion prediction results, spatial interpolation is performed on the corrosion data to obtain corrosion data covering the entire region; A plurality of layers are created, each layer corresponding to a data type, the data type at least including corrosion intensity, geographic boundary and sensor position, the corrosion intensity, the geographic boundary and the sensor position being determined according to the corrosion data, the geographic space data and the layout of the intelligent sensor network respectively; Different styles are set for different layers, the styles being used to reflect the characteristics of the data types; Each layer is superimposed, and different styles are used to display different characteristic information in the region. The device comprises a processor and a memory:

9. A computer device, comprising: The memory is used to store a computer program and send instructions of the computer program to the processor; The processor executes the instructions of the computer program to perform the drawing method of the corrosion level map of the coastal region according to any one of claims 1-5. The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the drawing method of the corrosion level map of the coastal region according to any one of claims 1-5.

10. A computer-readable storage medium, characterized in that, ​

Images