A real-time monitoring method, system, terminal and storage medium for marine corrosion

Abstract

The present invention belongs to the technical field of marine corrosion monitoring, and particularly relates to a real-time marine corrosion monitoring method, system, terminal and storage medium, including: obtaining real-time original data based on sensing devices arranged on marine structures, where the original data includes electrochemical data, environmental data, physical state data and corrosion state data; mapping the original data to a high-dimensional space based on a kernel function, and obtaining the enhanced features most relevant to the corrosion state in the original data mapped to the high-dimensional space based on an attention mechanism; establishing an LSTM model based on the time-dependent relationship of the corrosion state, inputting the enhanced features into the LSTM model, and outputting local time series features; performing weighted fusion on the enhanced features and the local time series features to obtain a corrosion state prediction model, inputting the enhanced features and the local time series features, and outputting corrosion rate prediction values, corrosion depth prediction values and corrosion risk score values. It can reflect the changes in the corrosion process in real time and improve the timeliness of decision-making.

Description

Technical Field

[0001] The present invention belongs to the technical field of marine corrosion monitoring, and particularly relates to a method, a system, a terminal and a storage medium for real-time monitoring of marine corrosion. Background Art

[0002] Marine corrosion is the corrosion that components undergo in the marine environment. In the marine environment, seawater itself is a strong corrosive medium. At the same time, waves, tides, and currents generate low-frequency reciprocating stresses and impacts on metal components. In addition, marine microorganisms, attached organisms, and their metabolites all have direct or indirect accelerating effects on the corrosion process. Marine corrosion is mainly local corrosion, that is, corrosion that starts from the surface of the component and occurs in a very small area, such as galvanic corrosion, pitting corrosion, crevice corrosion, etc. Marine corrosion has a significant impact on the safety, stability, and service life of marine structures (such as offshore platforms, ships, submarine pipelines, etc.).

[0003] Existing marine corrosion detection technologies mainly rely on electrochemical methods (such as electrochemical impedance spectroscopy, linear polarization resistance) and basic machine learning models (such as linear regression, BP neural network). Although these methods can detect the presence of corrosion, they often have the following problems.

[0004] Traditional corrosion monitoring methods cannot detect the initial stage of corrosion; it is difficult to effectively process complex, non-linear, and multi-dimensional time series data relying on linear regression and simple neural networks; and electrochemical methods usually require a long time for data collection and processing, and cannot reflect the changes in the corrosion process in real time, affecting the timeliness of maintenance decisions. Summary of the Invention

[0005] In view of the above deficiencies of the prior art, the present invention provides a method, a system, a terminal and a storage medium for real-time monitoring of marine corrosion to solve the above technical problems.

[0006] In a first aspect, the present invention provides a method for real-time monitoring of marine corrosion, including:

[0007] S1, obtaining real-time raw data based on sensing devices deployed on marine structures, where the raw data includes electrochemical data, environmental data, physical state data, and corrosion state data;

[0008] S2, mapping the raw data to a high-dimensional space based on a kernel function, and obtaining the enhanced features most relevant to the corrosion state in the raw data mapped to the high-dimensional space based on an attention mechanism;

[0009] S3, establishing an LSTM model based on the time-dependent relationship of the corrosion state, inputting the enhanced features into the LSTM model, and outputting local time series features;

[0010] S4. Weightedly fuse the enhanced features and local time series features to obtain a corrosion state prediction model. Input the enhanced features and local time series features, and output the predicted corrosion rate value, predicted corrosion depth value, and corrosion risk score value.

[0011] In an optional implementation, in step S2, mapping the original data to a high-dimensional space based on a kernel function includes:

[0012] Preprocess the original data to obtain an original data feature matrix;

[0013] Map the original data feature matrix to a high-dimensional space based on a Gaussian kernel to obtain a kernel matrix reflecting the similarity between the original data feature vectors, calculated as:

[0014]

[0015] where is the original data feature vector at the i-th time step, is the original data feature vector at the j-th time step, represents the Euclidean distance between two feature vectors, is the bandwidth parameter of the kernel function.

[0016] In an optional implementation, obtaining the enhanced features most relevant to the corrosion state in the original data mapped to a high-dimensional space based on an attention mechanism includes:

[0017] Calculate the attention score for each original data feature vector based on the kernel matrix, calculated as:

[0018]

[0019] where, is the attention score of the original data feature vector at the i-th time step, is the weight of the similarity between the original data feature vector at the i-th time step and the original data feature vector at the j-th time step, and T is the total length of the time series;

[0020] Normalize the attention scores based on the softmax function to obtain the weights of the original data feature vectors, calculated as:

[0021]

[0022] where, is the weight of the i-th original data feature vector;

[0023] Perform weighted synthesis on all original data feature vectors to obtain an enhanced feature vector, calculated as:

[0024]

[0025] wherein is the enhanced feature vector;

[0026] An enhanced feature matrix is obtained based on the enhanced feature vector.

[0027] In an alternative embodiment, step S3 specifically includes:

[0028] S3-1, calculating the output of the forget gate to control the enhanced features to be retained or forgotten in the memory unit at the previous time step, calculated as:

[0029]

[0030] wherein is the weight matrix of the forget gate, is the hidden layer state at the previous moment, is the input enhanced feature at the current time step, is the bias term of the forget gate, S is the sigmoid activation function, is the output of the forget gate at the current time step;

[0031] S3-2, calculating the output of the input gate to determine the degree to which the enhanced features at the current time step need to be written into the memory unit, calculated as:

[0032] ,

[0033]

[0034] wherein is the weight matrix of the input gate, is the bias term of the input gate, is the weight matrix for generating candidate values, is the corresponding bias term for generating candidate values, is the new candidate value at the current moment, is the output of the input gate at the current time step;

[0035] S3-3, updating the memory unit state at the current time step based on the memory unit state at the previous time step and the current input candidate memory unit calculated as:

[0036]

[0037] wherein is the memory unit state at the current time step, is the memory unit state at the previous time step;

[0038] S3-4. Calculate the output of the output gate to obtain the hidden layer state at the current time step, which is calculated as:

[0039] ,

[0040]

[0041] where is the weight matrix of the output gate, is the bias term of the output gate, is the output of the output gate at the current time step, is the hidden layer state at the current time step;

[0042] S3-5. Based on the hidden layer states of all time steps, obtain the local time series features.

[0043] In an optional implementation manner, step S4 specifically includes:

[0044] Perform weighted integration on the enhanced feature and the local time series feature, which is calculated as:

[0045]

[0046] where is the weight parameter, is the enhanced feature matrix, is the local time series feature, and F is the fused feature vector;

[0047] Map the fused feature vector to a low-dimensional space based on the fully connected layer, which is calculated as:

[0048]

[0049] where is the weight matrix of the fully connected layer; is the bias of the fully connected layer, is the output of the fully connected layer;

[0050] Based on the output layer, combine the output of the fully connected layer with the weight parameters corresponding to the corrosion rate to obtain the corrosion rate prediction result; combine the output of the fully connected layer with the weight parameters corresponding to the corrosion depth to obtain the corrosion depth prediction result; combine the output of the fully connected layer with the weight parameters corresponding to the corrosion risk score to obtain the corrosion risk score prediction result;

[0051] Integrate the corrosion rate prediction result, the corrosion depth prediction result, and the corrosion risk score prediction result to obtain the prediction matrix output by the output layer.

[0052] In an alternative embodiment, the weight parameters corresponding to the corrosion rate, the weight parameters corresponding to the corrosion depth, and the weight parameters corresponding to the corrosion risk score are all obtained through model training, specifically including:

[0053] The weight parameters include a weight matrix and a bias term, and all weight matrices and bias terms are randomly initialized;

[0054] Based on the forward propagation algorithm, the predicted values of the corrosion rate, the predicted values of the corrosion depth, and the predicted values of the corrosion risk score under the current parameters are calculated;

[0055] Based on the mean square error loss function, the predicted loss values of the corrosion rate, the predicted loss values of the corrosion depth, and the predicted loss values of the corrosion risk score are calculated respectively;

[0056] Based on the backpropagation algorithm, the gradients of the loss value with respect to the weight matrix and the bias term are calculated;

[0057] Based on the stochastic gradient descent method, the weight matrix and the bias term are updated in combination with the calculated gradients.

[0058] In an alternative embodiment, the severity of the corrosion is obtained, and the corrosion risk prediction score value is evaluated for the severity of the corrosion. The severity of the corrosion includes low risk, medium risk, and high risk.

[0059] In a second aspect, the present invention provides a real-time marine corrosion monitoring system. When the system is implemented, it executes the above-mentioned real-time marine corrosion monitoring system, including:

[0060] A data acquisition module that obtains real-time raw data based on the sensing devices deployed on the marine structure. The raw data includes electrochemical data, environmental data, physical state data, and corrosion state data;

[0061] A KAN module that maps the raw data to a high-dimensional space based on a kernel function, and obtains the enhanced features most relevant to the corrosion state in the raw data mapped to the high-dimensional space based on an attention mechanism;

[0062] An LSTM module that establishes an LSTM model based on the time dependence relationship of the corrosion state. The LSTM model inputs the enhanced features and outputs local time series features;

[0063] A comprehensive prediction module that performs weighted fusion on the enhanced features and the local time series features to obtain a corrosion state prediction model. The enhanced features and the local time series features are input, and the predicted values of the corrosion rate, the predicted values of the corrosion depth, and the corrosion risk score values are output.

[0064] In a third aspect, a terminal is provided, including:

[0065] A processor and a memory, wherein,

[0066] The memory is used to store a computer program.

[0067] The processor is used to call and run the computer program from the memory, so that the terminal executes the method of the terminal described above.

[0068] In a fourth aspect, a computer storage medium is provided. Instructions are stored in the computer-readable storage medium. When it runs on a computer, the computer is made to execute the methods described in the above aspects.

[0069] The beneficial effects of the present invention are as follows. The real-time marine corrosion monitoring method, system, terminal and storage medium provided by the present invention obtain various types of raw data through the sensing devices arranged on marine structures, providing a rich information source for comprehensively understanding the condition of marine structures. By using kernel function mapping and attention mechanism, the enhanced features most relevant to the corrosion state are effectively mined, enhancing the data value. The LSTM model established based on the time-dependent relationship of the corrosion state can accurately capture the temporal changes of the features, and the output local time series features are more targeted. The corrosion state prediction model constructed by weighted fusion of enhanced features and local time series features combines the advantages of various features, and can output the corrosion rate, corrosion depth and corrosion risk score value, realizing multi-dimensional accurate prediction of the marine corrosion state, helping to timely grasp the corrosion situation of marine structures, providing a strong basis for taking targeted maintenance measures, improving the safety and service life of marine structures, and at the same time enhancing the accuracy and reliability of real-time marine corrosion monitoring, which has important significance in the field of marine engineering.

[0070] In addition, the design principle of the present invention is reliable and the structure is simple, having a very wide application prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for description in the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0072] Figure 1 is a schematic flowchart of the real-time marine corrosion monitoring method according to an embodiment of the present invention.

[0073] Figure 2 is a schematic block diagram of the real-time marine corrosion monitoring system according to an embodiment of the present invention.

[0074] Figure 3 is Figure 2 a detailed expansion diagram of the KAN module and the LSTM module of

[0075] Figure 4A schematic structural diagram of a terminal provided by an embodiment of the present invention. Detailed implementation manners

[0076] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0077] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the description of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0078] The real-time marine corrosion monitoring method provided by the embodiments of the present invention is executed by a computer device. Correspondingly, the real-time marine corrosion monitoring system runs in the computer device.

[0079] Figure 1 It is a schematic flowchart of the real-time marine corrosion monitoring method according to an embodiment of the present invention. Among them, Figure 1 The execution subject can be a real-time marine corrosion monitoring system. According to different requirements, the order of the steps in this flowchart can be changed, and some can be omitted.

[0080] Such as Figure 1 shown, the method includes:

[0081] S1. Obtain real-time original data based on the sensing devices deployed on the marine structure. The original data includes electrochemical data, environmental data, physical state data, and corrosion state data;

[0082] Multiple types of data cover aspects such as electrochemistry, environment, physical state, and corrosion state, just like drawing a detailed panoramic picture of the health status of the marine structure, which can comprehensively reflect the real state of the marine structure in the complex marine environment. The real-time obtained data ensures the timeliness of information, enables subsequent analysis to timely capture the dynamic changes in the corrosion situation of the marine structure, and provides the possibility for timely discovery of potential corrosion problems.

[0083] S2. Map the original data to a high-dimensional space based on a kernel function, and obtain the enhanced features most relevant to the corrosion state in the original data mapped to the high-dimensional space based on an attention mechanism;

[0084] The kernel function mapping can uncover the hidden non - linear relationships in the original data, making the originally complex and indistinguishable data features become clear and distinguishable in the high - dimensional space. This helps to discover the feature patterns that are not easily detectable in the low - dimensional space but have an important impact on the corrosion state. The attention mechanism automatically focuses on the features most relevant to the corrosion state, reducing the influence of irrelevant or interfering information, enabling the model to grasp the key information more accurately, thereby improving the accuracy and efficiency of the subsequent prediction model and providing more valuable feature inputs for accurately predicting the corrosion state.

[0085] S3. Establish an LSTM model based on the time - dependent relationship of the corrosion state. The LSTM model takes the enhanced features as input and outputs local time - series features.

[0086] The LSTM model can effectively learn the law of the corrosion state changing over time and accurately capture the dependence relationship of features between different time steps. The output local time - series features not only contain the information of the current moment but also the key trends in the historical data, providing a dynamic and forward - looking basis for predicting the future corrosion state, making the prediction results more in line with the evolution of the actual corrosion process, greatly improving the reliability and accuracy of the corrosion state prediction, and helping to formulate reasonable maintenance strategies in advance.

[0087] S4. Perform weighted fusion on the enhanced features and the local time - series features to obtain a corrosion state prediction model. Input the enhanced features and the local time - series features, and output the predicted values of the corrosion rate, the corrosion depth, and the corrosion risk score.

[0088] It can reasonably allocate weights according to the importance of the two types of features, enabling the model to fully absorb the key information in the enhanced features and the temporal dynamic information in the local time - series features. The finally output values of the corrosion rate, the corrosion depth, and the corrosion risk score provide a quantitative and intuitive description of the corrosion condition of the marine structure from different perspectives, helping relevant personnel to comprehensively understand the severity, development speed, and potential risks of corrosion, so as to be able to formulate maintenance plans more accurately, allocate resources reasonably, and effectively ensure the safety, stability, and service life of the marine structure.

[0089] Optionally, as an embodiment of the present invention, in step S1, the sensing devices include electrochemical sensors (such as electrochemical impedance spectroscopy EIS and linear polarization resistance LPR), temperature and humidity sensors, salinity sensors, stress sensors, vibration sensors, etc. The collected original data includes electrochemical data (such as current density, potential change), environmental data (such as temperature, humidity, salinity), physical state data (such as stress, vibration, etc.), and corrosion state data (such as corrosion rate, corrosion depth, etc.).

[0090] Optionally, as an embodiment of the present invention, in step S2, mapping the original data to the high - dimensional space based on the kernel function includes:

[0091] After preprocessing the original data to complete denoising, standardization, and normalization, the original data feature matrix is obtained;

[0092]

[0093] Among them, is the length of the time series; is the dimension of the feature; represents the th time step of the th eigenvalue.

[0094] Based on the Gaussian kernel, the original data feature matrix is mapped to a high-dimensional space to generate an enhanced representation of the features, and a kernel matrix reflecting the similarity between the original data feature vectors is obtained , calculated as:

[0095]

[0096] Among them is the original data feature vector at the i-th time step, is the original data feature vector at the j-th time step, represents the Euclidean distance between two feature vectors, is the bandwidth parameter of the kernel function.

[0097] The kernel matrix is:

[0098]

[0099] Optionally, as an embodiment of the present invention, in step S2, the enhanced features most relevant to the corrosion state in the original data mapped to the high-dimensional space obtained based on the attention mechanism include:

[0100] Calculate the attention score of each original data feature vector based on the kernel matrix, calculated as:

[0101]

[0102] Among them, is the attention score of the original data feature vector at the i-th time step, is the weight of the similarity between the original data feature vector at the i-th time step and the original data feature vector at the j-th time step, and T is the total length of the time series;

[0103] Normalize the attention score through the softmax function to obtain the weight of the original data feature vector, calculated as:

[0104]

[0105] Among them, is the weight of the i-th original data feature vector;

[0106] All the original data feature vectors are weighted and synthesized to obtain a strengthened feature vector, which is calculated as:

[0107]

[0108] where is the strengthened feature vector;

[0109] A strengthened feature matrix is obtained based on the strengthened feature vector :

[0110] .

[0111] Each column in the strengthened feature matrix corresponds to an important dimension of the original feature set. After being strengthened by the attention mechanism, its correlation and weight can better reflect the dynamic characteristics of the corrosion process.

[0112] Optionally, as an embodiment of the present invention, step S3 specifically includes:

[0113] S3-1, calculating the output of the forget gate to control the strengthened features to be retained or forgotten in the memory unit of the previous time step, which is calculated as:

[0114]

[0115] where is the weight matrix of the forget gate, is the hidden layer state of the previous moment, is the input strengthened feature of the current time step, is the bias term of the forget gate, S is the sigmoid activation function, is the output of the forget gate of the current time step and is between 0 and 1;

[0116] S3-2, calculating the output of the input gate to determine the degree to which the strengthened features of the current time step need to be written into the memory unit, which is calculated as:

[0117] ,

[0118]

[0119] where is the weight matrix of the input gate, is the bias term of the input gate, is the weight matrix for generating candidate values, is the corresponding bias term for generating candidate values, is the new candidate value at the current moment, is the output of the input gate at the current time step and is between 0 and 1;

[0120] S3-3, based on the memory cell state of the previous time step and the candidate memory cell of the current input update the memory cell state of the current time step, calculated as:

[0121]

[0122] where, is the memory cell state of the current time step, is the memory cell state of the previous time step;

[0123] S3-4, calculate the output of the output gate to obtain the hidden layer state of the current time step, calculated as:

[0124] ,

[0125]

[0126] where, is the weight matrix of the output gate, is the bias term of the output gate, is the output of the output gate of the current time step and is between 0 and 1, is the hidden layer state of the current time step;

[0127] S3-5, based on the hidden layer states of all time steps, obtain the local time series features .

[0128] Optionally, as an embodiment of the present invention, step S4 specifically includes:

[0129] Perform weighted synthesis on the enhanced feature and the local time series feature, calculated as:

[0130]

[0131] where, is the weight parameter, is the enhanced feature matrix, is the local time series feature, and F is the fused feature vector;

[0132] Map the fused feature vector to a low-dimensional space based on the fully connected layer, calculated as:

[0133]

[0134] where, is the weight matrix of the fully connected layer; is the bias of the fully connected layer, is the output of the fully connected layer;

[0135] Based on the output layer, the weight parameters corresponding to the output of the fully connected layer and the corrosion rate are combined to obtain the corrosion rate prediction result; specifically, the corrosion rate prediction model is:

[0136]

[0137] where, is the corrosion rate, is the corrosion rate weight matrix, is the corrosion rate bias term, and the corrosion rate prediction value can be obtained according to this model .

[0138] The output of the fully connected layer is combined with the weight parameters corresponding to the corrosion depth to obtain the corrosion depth prediction result;

[0139]

[0140] where, is the corrosion depth, is the corrosion depth weight matrix, is the corrosion depth bias term, and the corrosion depth prediction value can be obtained according to this model .

[0141] The output of the fully connected layer is combined with the weight parameters corresponding to the corrosion risk score to obtain the corrosion risk score prediction result;

[0142]

[0143] where, is the corrosion risk score, is the corrosion risk score weight matrix, is the corrosion risk score bias term, and the corrosion risk score prediction value can be obtained according to this model .

[0144] Combining the corrosion rate prediction result, the corrosion depth prediction result and the corrosion risk score prediction result, the prediction matrix output by the output layer is obtained :

[0145] .

[0146] Real-time monitoring and updating is the key dynamic response mechanism of this method and can adapt to environmental changes. New sensor data is received in real time , and after being processed by the data preprocessing module, the latest feature representation is generated through the above method. At the same time, the module updates the predicted value in real time according to these features to ensure that the prediction result can reflect the dynamic changes of the current environment. In addition, by combining historical data and real-time input, the system can adaptively adjust the fusion weight and other key parameters, thereby further enhancing the robustness and accuracy of the prediction.

[0147] Optionally, as an embodiment of the present invention, the weight parameters corresponding to the corrosion rate, the weight parameters corresponding to the corrosion depth, and the weight parameters corresponding to the corrosion risk score are all obtained through model training, specifically including:

[0148] The weight parameters include a weight matrix and a bias term. All weight matrices and bias terms are randomly initialized; they are randomly assigned values within a small range using a normal distribution or a uniform distribution to ensure that the initial parameters have a certain degree of randomness, but are not too large or too small so as not to affect the training effect of the model.

[0149] Based on the forward propagation algorithm, calculate the predicted values of the corrosion rate, the predicted values of the corrosion depth, and the predicted values of the corrosion risk score under the current parameters; pass the training data (including input features and corresponding labels such as the true corrosion rate, corrosion depth, and corrosion risk score) through the forward propagation process of the entire system, that is, obtain data from the data acquisition module, go through preprocessing, the KAN module, the LSTM module, weighted fusion, the fully connected layer, and finally to the output layer, and calculate the predicted values of the corrosion rate, corrosion depth, and corrosion risk score under the current parameters.

[0150] Based on the mean square error loss function, calculate the predicted loss value of the corrosion rate, the predicted loss value of the corrosion depth, and the predicted loss value of the corrosion risk score respectively;

[0151] Based on the backpropagation algorithm, calculate the gradients of the loss value with respect to the weight matrix and the bias term; the backpropagation starts from the output layer and gradually calculates the parameter gradients of each layer according to the chain rule, and propagates the error from the output layer back to the previous layers, thereby obtaining the gradient values of each weight matrix and bias term.

[0152] Based on the stochastic gradient descent method, update the weight matrix and the bias term by combining the calculated gradients:

[0153]

[0154]

[0155] wherein, is the learning rate, which controls the step size of parameter update, the loss value of the predicted value of the corrosion rate.

[0156] Optionally, as an embodiment of the present invention, obtain the severity of corrosion, evaluate the corrosion risk prediction score value for the severity of corrosion, and the severity of corrosion includes low risk, medium risk, and high risk.

[0157] Low risk (0.0 - 0.3): No immediate maintenance is required.

[0158] Medium risk (0.3 - 0.7): Regular monitoring is recommended.

[0159] High risk (0.7 - 1.0): It is recommended to take repair measures as soon as possible. The specific repair measures include detailed inspection of specific areas, repairing or replacing severely corroded components, adding anti - corrosion coatings, or replacing highly corrosion - resistant materials.

[0160] Optionally, as an embodiment of the present invention, draw a curve graph based on corrosion rate data, corrosion depth data, and corrosion risk score, specifically:

[0161] Corrosion rate curve graph, with time on the horizontal axis and rate on the vertical axis, showing the corrosion rate The changing trend over time, marking outliers or rapidly changing areas.

[0162] Corrosion depth change graph, cumulative corrosion depth The growth trend, showing the cumulative depth in a bar graph, and each bar corresponds to a future predicted time step.

[0163] Risk score heat map, using a heat map to show the corrosion risk distribution in different areas, showing the risk level in different areas with a color gradient (from green to red), and highlighting high - risk areas.

[0164] Optionally, as an embodiment of the present invention, sort and organize the prediction results according to corrosion rate, corrosion depth, and risk score. Add time information to clarify the predicted time step and the report generation time. Store the generated report in a database, classified by time and region, for convenient query and analysis of historical records. Users can export the report in common formats (such as PDF, Excel, JSON) for offline use and sharing.

[0165] The system automatically records and stores historical data for long - term trend analysis of the corrosion status.

[0166] In some embodiments, the marine corrosion real - time monitoring system may include multiple functional modules composed of computer program segments. The computer programs of each program segment in the marine corrosion real - time monitoring system can be stored in the memory of a computer device and executed by at least one processor to perform (see Figure 1 description) the functions of marine corrosion real - time monitoring.

[0167] In this embodiment, the real-time marine corrosion monitoring system can be divided into multiple functional modules according to the functions it performs, such as Figure 2 and Figure 3 shown. The functional modules of the system can include: a data acquisition module, a KAN module, an LSTM module, and an integrated prediction module. The module referred to in the present invention means a series of computer program segments that can be executed by at least one processor and can complete fixed functions, and are stored in the memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0168] The data acquisition module obtains real-time raw data based on the sensing devices deployed on the marine structure. The raw data includes electrochemical data, environmental data, physical state data, and corrosion state data;

[0169] The KAN module maps the raw data to a high-dimensional space based on a kernel function, and obtains the enhanced features most relevant to the corrosion state in the raw data mapped to the high-dimensional space based on an attention mechanism;

[0170] The LSTM module establishes an LSTM model based on the time-dependent relationship of the corrosion state. The LSTM model inputs the enhanced features and outputs local time series features;

[0171] The integrated prediction module performs weighted fusion on the enhanced features and the local time series features to obtain a corrosion state prediction model. It inputs the enhanced features and the local time series features and outputs the corrosion rate prediction value, the corrosion depth prediction value, and the corrosion risk score value.

[0172] Figure 3 For Figure 2 the detailed expansion diagrams of the KAN module and the LSTM module, in the detailed expansion process, the above-mentioned real-time marine corrosion monitoring method is implemented.

[0173] Figure 4 This is a schematic structural diagram of a terminal provided by an embodiment of the present invention. This terminal can be used to execute the real-time marine corrosion monitoring method provided by the embodiment of the present invention.

[0174] Among them, the terminal can include: a processor, a memory, and a communication unit. These components communicate through one or more buses. Those skilled in the art can understand that the structure of the server shown in the figure does not constitute a limitation to the present invention. It can be a bus structure, a star structure, and can also include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0175] Among them, the memory can be used to store the execution instructions of the processor. The memory can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disc. When the execution instructions in the memory are executed by the processor, the terminal can execute some or all of the steps in the above method embodiments.

[0176] The processor is the control center of the storage terminal, connecting various parts of the entire electronic terminal through various interfaces and lines. By running or executing software programs and / or modules stored in the memory, and by calling the data stored in the memory, it executes various functions of the electronic terminal and / or processes data. The processor can be composed of an integrated circuit (IC). For example, it can be composed of a single packaged IC, or can be composed of multiple packaged ICs with the same or different functions connected together. For example, the processor can include only a central processing unit (CPU). In the embodiment of the present invention, the CPU can be a single arithmetic core or can include multiple arithmetic cores.

[0177] The communication unit is used to establish a communication channel so that the storage terminal can communicate with other terminals. It receives user data sent by other terminals or sends user data to other terminals.

[0178] The present invention also provides a computer storage medium. Among them, the computer storage medium can store a program, and when the program is executed, it can include some or all of the steps in the embodiments provided by the present invention. The storage medium can be a magnetic disk, an optical disc, a read-only memory (ROM) or a random access memory (RAM), etc.

[0179] Therefore, the technical effects that can be achieved by this embodiment can be referred to the description above and will not be elaborated here.

[0180] Those skilled in the art can clearly understand that the technologies in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solutions in the embodiments of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disc, etc., which are various media that can store program codes, and includes several instructions for causing a computer terminal (which can be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0181] For the same or similar parts among the various embodiments in this specification, reference can be made to each other. In particular, for the terminal embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for the relevant parts, reference can be made to the descriptions in the method embodiments.

[0182] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there can be other division methods. For example, multiple modules 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 couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of systems or modules can be in electrical, mechanical or other forms.

[0183] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules, that is, they can be located in one place, or they can be distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0184] In addition, in each embodiment of the present invention, the functional modules can be integrated in a processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0185] Although the present invention has been described in detail by referring to the accompanying drawings and in conjunction with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, those of ordinary skill in the art can make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions should all be within the scope of the present invention. / Any person skilled in the art within the technical scope disclosed by the present invention can easily conceive of changes or substitutions, which should all be covered by the protection scope of the present invention.

Claims

1. A real-time monitoring method for marine corrosion, characterized in that: include: S1, based on the sensor equipment deployed on the marine structure to obtain real-time raw data, the raw data includes electrochemical data, environmental data, physical state data and corrosion state data; S2, maps the original data to a high-dimensional space based on the kernel function, and obtains the most relevant enhanced features of the corrosion state in the original data mapped to the high-dimensional space based on the attention mechanism; S3, establish an LSTM model based on the time dependency of the corrosion state. The LSTM model inputs the reinforcement features and outputs the local time series features. S4, weighted fusion of the enhanced features and the local time series features to obtain a corrosion state prediction model, input the enhanced features and the local time series features, and output the corrosion rate prediction value, the corrosion depth prediction value and the corrosion risk score value; Step S4 specifically includes: The weighted combination of enhanced features and local time series features is calculated as: in, is the weight parameter, is the reinforcement feature matrix, is the local time series feature, and F is the fused feature vector; Based on the fully connected layer, the fused feature vector is mapped to a low-dimensional space and calculated as: in, is the weight matrix of the fully connected layer; is the bias of the fully connected layer, is the output of the fully connected layer; Based on the output layer, the output of the fully connected layer is combined with the weight parameter corresponding to the corrosion rate to obtain the corrosion rate prediction result; the specific corrosion rate prediction model is: in, is the corrosion rate, is the corrosion rate weight matrix, is the corrosion rate bias term. According to this model, the corrosion rate prediction value can be obtained. ; The output of the fully connected layer is combined with the weight parameter corresponding to the corrosion depth to obtain the corrosion depth prediction result; in, is the corrosion depth, is the erosion depth weight matrix, is the corrosion depth bias term. According to this model, the corrosion depth prediction value can be obtained. ; The output of the fully connected layer is combined with the weight parameter corresponding to the corrosion risk score to obtain the corrosion risk score prediction result; in, is the corrosion risk score, is the corrosion risk score weight matrix, is the corrosion risk score bias term. According to this model, the corrosion risk score prediction value can be obtained. ; The prediction matrix output by the output layer is obtained by integrating the corrosion rate prediction results, the corrosion depth prediction results and the corrosion risk score prediction results; In step S2, mapping the original data to a high-dimensional space based on the kernel function includes: Preprocess the original data to obtain the original data feature matrix; Based on the Gaussian kernel, the original data feature matrix is ​​mapped to a high-dimensional space to obtain a kernel matrix that reflects the similarity between the feature vectors of the original data, which is calculated as: in is the original data feature vector of the i-th time step, is the original data feature vector of the jth time step, represents the Euclidean distance between two eigenvectors, is the bandwidth parameter of the kernel function; In step S2, the enhanced features most relevant to the corrosion state in the original data mapped to the high-dimensional space based on the attention mechanism include: The attention score of each original data feature vector is calculated based on the kernel matrix, which is calculated as: in, is the attention score of the original data feature vector at the i-th time step, is the weight of the similarity between the original data feature vector of the i-th time step and the original data feature vector of the j-th time step, and T is the total length of the time series; The attention score is normalized based on the softmax function to obtain the weight of the original data feature vector, which is calculated as: in, is the weight of the i-th original data feature vector; All original data feature vectors are weighted and integrated to obtain the enhanced feature vector, which is calculated as: in is the reinforcement feature vector; A reinforced feature matrix is ​​obtained based on the reinforced feature vector.

2. The method for real-time monitoring of marine corrosion according to claim 1, characterized in that: Step S3 specifically includes: S3-1, calculate the forget gate output to control the reinforcement features that need to be retained or forgotten in the memory unit of the previous time step, calculated as: . in, is the weight matrix of the forget gate, is the hidden state at the previous moment, is the input reinforcement feature of the current time step, is the bias term of the forget gate, S is the sigmoid activation function, is the output of the forget gate at the current time step; S3-2, calculate the input gate output to determine the extent to which the reinforcement feature of the current time step needs to be written into the memory unit, calculated as: , . in, is the weight matrix of the input gate, is the bias term of the input gate, is the weight matrix used to generate candidate values, is the corresponding bias term used to generate candidate values, is the new candidate value at the current moment, is the output of the input gate at the current time step; S3-3, candidate memory cells based on the memory cell state of the previous time step and the current input Update the memory cell state of the current time step, calculated as: . in, is the memory cell state at the current time step, is the memory cell state at the previous time step; S3-4, calculate the output gate output to obtain the hidden layer state of the current time step, which is calculated as: , . in, is the weight matrix of the output gate, is the bias term of the output gate, is the output of the output gate at the current time step, is the hidden state of the current time step; S3-5, based on the hidden layer states of all time steps, obtain the local time series features.

3. The method for real-time monitoring of marine corrosion according to claim 1, characterized in that: The weight parameters corresponding to the corrosion rate, the weight parameters corresponding to the corrosion depth, and the weight parameters corresponding to the corrosion risk score are all obtained through model training, including: The weight parameters include weight matrices and bias items, and all weight matrices and bias items are randomly initialized; Based on the forward propagation algorithm, the corrosion rate prediction value, corrosion depth prediction value and corrosion risk score prediction value under the current parameters are calculated; Based on the mean square error loss function, the corrosion rate prediction loss value, the corrosion depth prediction loss value, and the corrosion risk score prediction loss value are calculated respectively; Calculate the gradient of the loss value with respect to the weight matrix and bias term based on the back-propagation algorithm; The weight matrix and bias terms are updated based on the stochastic gradient descent method combined with the calculated gradients.

4. The method for real-time monitoring of marine corrosion according to claim 1, characterized in that: The severity of corrosion is obtained and the corrosion risk prediction score is evaluated. The severity of corrosion includes low risk, medium risk and high risk.

5. A real-time monitoring system for marine corrosion, characterized in that: When the system is implemented, the real-time marine corrosion monitoring system according to any one of claims 1 to 4 is implemented, including: Data acquisition module, which acquires real-time raw data based on sensor equipment deployed on marine structures. The raw data includes electrochemical data, environmental data, physical state data and corrosion state data; The KAN module maps the original data to a high-dimensional space based on the kernel function, and obtains the most relevant enhanced features of the corrosion state in the original data mapped to the high-dimensional space based on the attention mechanism; LSTM module, which builds an LSTM model based on the time dependency of the corrosion state. The LSTM model inputs reinforcement features and outputs local time series features. The comprehensive prediction module performs weighted fusion of the enhanced features and local time series features to obtain a corrosion state prediction model, inputs the enhanced features and local time series features, and outputs the corrosion rate prediction value, corrosion depth prediction value and corrosion risk score value.

6. A terminal, characterized in that: include: A memory for storing a real-time marine corrosion monitoring program; A processor is used to implement the steps of the real-time marine corrosion monitoring method as described in any one of claims 1 to 4 when executing the real-time marine corrosion monitoring program.

7. A computer-readable storage medium storing a computer program, characterized in that: The readable storage medium stores a real-time monitoring program for marine corrosion, which, when executed by a processor, implements the steps of the real-time monitoring method for marine corrosion as described in any one of claims 1 to 4.

Images