Earthing storage tank corrosion monitoring method

Abstract

The invention belongs to the technical field of storage tank corrosion monitoring, and discloses an earthing storage tank corrosion monitoring method, which comprises the following steps: constructing a data acquisition framework comprising a central server and a plurality of monitoring clients; constructing a storage tank corrosion rate prediction model in the central server, and performing training and hyper-parameter optimization on the storage tank corrosion rate prediction model based on historical monitoring data to obtain an optimized storage tank corrosion rate prediction model; deploying the optimized storage tank corrosion rate prediction model to each monitoring client for rate prediction to obtain corrosion rate prediction data corresponding to each monitoring client; and sending the corrosion rate prediction data to a central server for storage, and visually displaying the corrosion rate prediction data corresponding to the monitoring clients by using a digital twin technology. According to the technical scheme, the risk of human errors can be reduced, and therefore it is ensured that the monitoring result is accurate and high in reliability.

Description

Technical Field

[0001] The invention belongs to the technical field of storage tank corrosion monitoring, and in particular relates to a method for monitoring corrosion of an earth-covered storage tank. Background Art

[0002] Earth-covered storage tanks are a special type of storage equipment, mainly used to store liquid or gaseous chemicals, especially flammable, explosive and other hazardous substances, such as oil, natural gas and chemicals. During the operation of the tank, corrosion of local components of the tank is inevitable due to the influence of the medium in the tank and the natural environment. As the service life of the tank increases, the degree of corrosion of the tank will gradually become more severe over time until perforation occurs, causing the liquid in the tank to leak, seriously threatening the safe use of the tank. Therefore, it is particularly important to predict the corrosion rate of the tank.

[0003] At present, the main method of monitoring tank corrosion is to use manual regular inspections and random inspections to conduct point-by-point inspections. The monitoring range is small and cannot be systematically monitored, and the accuracy of the monitoring results is low. Summary of the invention

[0004] The purpose of the present invention is to provide a corrosion monitoring method for an earth-covered storage tank to solve the problems existing in the above-mentioned prior art.

[0005] To achieve the above object, the present invention provides a method for monitoring corrosion of an earth-covered storage tank, comprising:

[0006] Build a data collection architecture including a central server and several monitoring clients;

[0007] Constructing a tank corrosion rate prediction model in the central server, wherein the tank corrosion rate prediction model is constructed based on a convolutional neural network and an LSTM network, and includes sequentially connecting a spatial feature extraction module, a spatiotemporal feature extraction module, a feature fusion module, and a fully connected layer;

[0008] The tank corrosion rate prediction model is trained and hyperparameters are optimized based on historical monitoring data to obtain an optimized tank corrosion rate prediction model; the historical monitoring data includes environmental data, tank internal sensor data and acoustic emission signal data;

[0009] Deploy the optimized tank corrosion rate prediction model to each of the monitoring clients to perform rate prediction, and obtain corrosion rate prediction data corresponding to each of the monitoring clients;

[0010] The corrosion rate prediction data are sent to a central server for storage, and the corrosion rate prediction data corresponding to each monitoring client are visualized using digital twin technology.

[0011] Optionally, the environmental data includes soil moisture data, soil temperature data, pH value data and oxidation-reduction potential data.

[0012] Optionally, the internal sensor data of the storage tank includes liquid level sensor data, temperature sensor data and corrosion monitoring sensor data.

[0013] Optionally, the method further includes performing data cleaning, data denoising and standardization on the historical monitoring data to obtain preprocessed historical monitoring data, and performing training and hyperparameter optimization of the tank corrosion rate prediction model based on the preprocessed historical monitoring data.

[0014] Optionally, the tank corrosion rate prediction model is trained and hyperparameters are optimized based on historical monitoring data, specifically including:

[0015] Obtaining several hyperparameter combinations in the tank corrosion rate prediction model;

[0016] Based on the historical monitoring data, the tank corrosion rate prediction model corresponding to each of the hyperparameter combinations is trained, and the tank corrosion rate prediction model corresponding to each of the hyperparameter combinations is verified and evaluated by a cross-validation method, and the evaluation result is used as the evaluation score corresponding to each of the hyperparameter combinations;

[0017] generating a walrus population for the walrus using each of the hyperparameter combinations;

[0018] Based on the evaluation scores corresponding to the hyperparameter combinations and in combination with the walrus optimization algorithm, parameter optimization is performed in the walrus population to obtain the optimal hyperparameter combination;

[0019] An optimized tank corrosion rate prediction model is constructed based on the optimal hyperparameter combination.

[0020] Optionally, performing parameter optimization in the walrus population based on the evaluation scores corresponding to the hyperparameter combinations in combination with a walrus optimization algorithm specifically includes:

[0021] Setting the value range, population size and number of iterations of the hyperparameter combination, and using each of the hyperparameter combinations as a walrus to generate the walrus population in combination with the walrus optimization algorithm;

[0022] Based on the walrus optimization algorithm, each hyperparameter combination in the walrus population is iteratively updated multiple times. In each iterative update process, the evaluation score corresponding to each hyperparameter combination is calculated, and the walrus population is updated based on the evaluation score corresponding to each hyperparameter combination, until the number of iterations reaches a preset value, and the optimal hyperparameter combination is output.

[0023] Optionally, the optimized tank corrosion rate prediction model is deployed to each of the monitoring clients to perform rate prediction, specifically including:

[0024] Input the real-time monitoring data of each monitoring client into the corresponding tank corrosion rate prediction model, extract the spatial features of the real-time monitoring data through the spatial feature extraction module, and extract the temporal features of the real-time monitoring data through the spatiotemporal feature extraction module;

[0025] Taking the spatial feature and the temporal feature as inputs of the feature fusion module to perform feature fusion to obtain a fusion feature;

[0026] The fusion features are input into the fully connected layer to perform rate prediction, and corrosion rate prediction data corresponding to each monitoring client within a preset time period is obtained.

[0027] Optionally, the corrosion rate prediction data corresponding to each monitoring client is visualized using digital twin technology, specifically including:

[0028] The real-time monitoring data and corrosion rate prediction data corresponding to the monitoring client are connected to the digital twin platform.

[0029] In the digital twin platform, the preset three-dimensional tank model is associated with the accessed data to realize the dynamic update of the preset three-dimensional tank model.

[0030] The technical effects of the present invention are:

[0031] The present invention systematizes the monitoring equipment by constructing a data acquisition architecture, achieving a high degree of intelligence and automation. From accurate data collection, efficient processing, in-depth analysis to accurate prediction, there is no need for excessive human intervention, which improves work efficiency and significantly reduces the risk of human error, thereby ensuring the accuracy and high reliability of the monitoring results. The monitoring scheme of the present invention not only takes into account environmental parameters, but also combines the operating data and corrosion monitoring data inside the storage tank, as well as the acoustic emission signal, to achieve comprehensive monitoring of the corrosion condition of the storage tank. The comprehensive monitoring method can more accurately reflect the corrosion condition of the storage tank and improve the reliability of the prediction; finally, the present invention can keenly capture the subtle changes in the corrosion rate of the storage tank through real-time monitoring and advanced neural network prediction technology, thereby warning of potential corrosion risks in advance and taking corresponding maintenance measures. This preventive maintenance strategy can extend the service life of the storage tank, reduce maintenance costs, and improve overall operational benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0034] Figure 1 It is a monitoring flow chart in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] Various exemplary embodiments of the present invention will now be described in detail. This detailed description should not be considered as limiting the present invention, but should be understood as a more detailed description of certain aspects, features, and embodiments of the present invention.

[0036] It should be understood that the terms described in the present invention are only for describing special embodiments and are not intended to limit the present invention. In addition, for the numerical range in the present invention, it should be understood that each intermediate value between the upper and lower limits of the scope is also specifically disclosed. Each smaller range between the intermediate value in any stated value or stated range and any other stated value or intermediate value in the described range is also included in the present invention. The upper and lower limits of these smaller ranges can be independently included or excluded in the scope.

[0037] Unless otherwise indicated, all technical and scientific terms used herein have the same meanings as those of ordinary skill in the art generally understood by the present invention. Although the present invention describes only preferred methods, any method similar or equivalent to that described herein may also be used in the implementation or testing of the present invention. All documents mentioned in this specification are incorporated by reference to disclose and describe the methods related to the documents. In the event of a conflict with any incorporated document, the content of this specification shall prevail.

[0038] It will be apparent to those skilled in the art that various modifications and variations may be made to the specific embodiments of the present invention description without departing from the scope or spirit of the present invention. Other embodiments derived from the present invention description will be apparent to those skilled in the art. The present application description and examples are exemplary only.

[0039] The words “include,” “including,” “have,” “contain,” etc. used in this article are open-ended terms, meaning including but not limited to.

[0040] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0041] Embodiment 1

[0042] like Figure 1As shown, in this embodiment, a method for monitoring corrosion of earth-covered storage tanks is provided, including: constructing a data acquisition architecture including a central server and a plurality of earth-covered storage tank corrosion monitoring clients; constructing a tank corrosion rate prediction model in the central server based on a convolutional neural network and an LSTM network, training the tank corrosion rate prediction model based on historical monitoring data and optimizing hyperparameters to obtain an optimized tank corrosion rate prediction model;

[0043] This embodiment systematizes the monitoring equipment by constructing a data acquisition architecture, achieving a high degree of intelligence and automation. From accurate data collection, efficient processing, in-depth analysis to accurate prediction, there is no need for excessive human intervention, which improves work efficiency and significantly reduces the risk of human error, thereby ensuring the accuracy and high reliability of the monitoring results. The monitoring scheme of this embodiment not only takes into account environmental parameters, but also combines the operating data and corrosion monitoring data inside the storage tank, as well as the acoustic emission signal, to achieve comprehensive monitoring of the corrosion condition of the storage tank. The comprehensive monitoring method can more accurately reflect the corrosion condition of the storage tank and improve the reliability of the prediction; finally, this embodiment can keenly capture the subtle changes in the corrosion rate of the storage tank through real-time monitoring and advanced neural network prediction technology, thereby warning of potential corrosion risks in advance and taking corresponding maintenance measures. This preventive maintenance strategy can extend the service life of the storage tank, reduce maintenance costs, and improve overall operational efficiency.

[0044] The historical monitoring data includes:

[0045] Environmental parameters: Soil moisture sensors, soil temperature sensors, pH sensors, and redox potential sensors are installed around the storage tank to ensure that changes in environmental parameters can be fully captured.

[0046] Internal sensing data of the storage tank: liquid level sensors, temperature sensors and corrosion monitoring sensors (such as resistance probes, electrochemical noise sensors, etc.) are installed inside the storage tank to monitor the operating status and corrosion conditions inside the storage tank in real time.

[0047] Acoustic emission sensor signals, installed outside or inside the tank, are used to capture the acoustic emission signals generated during metal corrosion to analyze the intensity and location of corrosion activity.

[0048] The monitoring scheme provided in this embodiment not only takes environmental parameters into consideration, but also combines the operation data and corrosion monitoring data inside the storage tank, as well as the acoustic emission signal, to achieve comprehensive monitoring of the corrosion condition of the storage tank. The comprehensive monitoring method can more accurately reflect the corrosion condition of the storage tank and improve the reliability of the prediction.

[0049] Deploy the optimized tank corrosion rate prediction model to each of the monitoring clients to perform rate prediction, and obtain corrosion rate prediction data corresponding to each of the monitoring clients;

[0050] The corrosion rate prediction data are sent to a central server for storage, and the corrosion rate prediction data corresponding to each monitoring client are visualized using digital twin technology.

[0051] Construction and training of prediction models:

[0052] A deep learning model integrating CNN and LSTM is constructed. This model combines the spatial feature extraction capability of CNN and the time series modeling capability of LSTM, including an input layer, a CNN module, an LSTM module, a fusion layer, and a prediction layer connected in sequence. The deep learning model integrating CNN and LSTM can capture spatial and temporal features at the same time and achieve high-precision corrosion rate prediction.

[0053] Input layer: receives processed traffic flow data and auxiliary data as input.

[0054] CNN module: used to extract the spatial features of traffic flow;

[0055] LSTM module: used to extract time series features of traffic flow.

[0056] Fusion layer: Fusion the features extracted by CNN and LSTM.

[0057] Prediction layer: Based on the fused features, a fully connected layer (Dense layer) is used for prediction, and the output is used to train the tank corrosion rate prediction model and optimize the hyperparameters:

[0058] Before historical data is input into the model, it is necessary to perform preprocessing to clean, denoise and standardize the collected data to ensure that data of different dimensions can be compared and analyzed in the same model. After preprocessing, it is ready for model training.

[0059] For model training and parameter optimization, firstly, several hyperparameter combinations in the tank corrosion rate prediction model are obtained;

[0060] Based on the historical monitoring data, the tank corrosion rate prediction model corresponding to each of the hyperparameter combinations is trained, and the tank corrosion rate prediction model corresponding to each of the hyperparameter combinations is verified and evaluated by a cross-validation method, and the evaluation result is used as the evaluation score corresponding to each of the hyperparameter combinations;

[0061] generating a walrus population for the walrus using each of the hyperparameter combinations;

[0062] Based on the evaluation scores corresponding to the hyperparameter combinations and in combination with the walrus optimization algorithm, parameter optimization is performed in the walrus population to obtain the optimal hyperparameter combination;

[0063] An optimized tank corrosion rate prediction model is constructed based on the optimal hyperparameter combination.

[0064] It is feasible to perform parameter optimization in the walrus population based on the evaluation scores corresponding to each of the hyperparameter combinations in combination with the walrus optimization algorithm, specifically including:

[0065] Setting the value range, population size and number of iterations of the hyperparameter combination, and using each of the hyperparameter combinations as a walrus to generate the walrus population in combination with the walrus optimization algorithm;

[0066] Based on the walrus optimization algorithm, each hyperparameter combination in the walrus population is iteratively updated multiple times. In each iterative update process, the evaluation score corresponding to each hyperparameter combination is calculated, and the walrus population is updated based on the evaluation score corresponding to each hyperparameter combination, until the number of iterations reaches a preset value, and the optimal hyperparameter combination is output.

[0067] The optimized tank corrosion rate prediction model is deployed to each monitoring client for rate prediction to ensure that each monitoring point can predict the corrosion rate in real time. Specifically:

[0068] Input the real-time monitoring data of each monitoring client into the corresponding tank corrosion rate prediction model, extract the spatial features of the real-time monitoring data through the spatial feature extraction module, and extract the temporal features of the real-time monitoring data through the spatiotemporal feature extraction module;

[0069] Taking the spatial feature and the temporal feature as inputs of the feature fusion module to perform feature fusion to obtain a fusion feature;

[0070] The fusion features are input into the fully connected layer to perform rate prediction, and corrosion rate prediction data corresponding to each monitoring client within a preset time period is obtained.

[0071] It is feasible to use digital twin technology to visualize data, including:

[0072] First, detailed data collection is required for the storage tank and its surrounding environment, including the size, shape, material, surface texture, internal structure and surrounding environmental information such as terrain and buildings; a 3D laser scanner is used to obtain point cloud data of the outer surface of the tank.

[0073] Based on the collected data, a three-dimensional model of the tank is constructed on the digital twin platform.

[0074] The real-time monitoring data and corrosion rate prediction data corresponding to the monitoring client are connected to the digital twin platform, and the preset three-dimensional tank model is associated with the connected data in the digital twin platform. The corresponding parts of the three-dimensional model (such as liquid level height, corrosion area, etc.) are dynamically updated according to the changes in the real-time monitoring data, so as to realize real-time and intuitive display of the corrosion situation of the tank, so that managers can more easily understand and analyze the corrosion situation of the tank.

[0075] This embodiment has significant advantages such as high precision, real-time, comprehensiveness, intelligence, visualization, scalability and preventive maintenance, which can effectively improve the safety and reliability of storage tanks, reduce operating costs, and provide strong guarantees for the sustainable development of enterprises.

[0076] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for monitoring corrosion of earth-covered storage tanks, characterized in that: include: Build a data collection architecture including a central server and several monitoring clients; Constructing a tank corrosion rate prediction model in the central server, wherein the tank corrosion rate prediction model is constructed based on a convolutional neural network and an LSTM network, and includes sequentially connecting a spatial feature extraction module, a spatiotemporal feature extraction module, a feature fusion module, and a fully connected layer; The tank corrosion rate prediction model is trained and hyperparameters are optimized based on historical monitoring data to obtain an optimized tank corrosion rate prediction model; the historical monitoring data includes environmental data, tank internal sensor data and acoustic emission signal data; Deploy the optimized tank corrosion rate prediction model to each of the monitoring clients to perform rate prediction, and obtain corrosion rate prediction data corresponding to each of the monitoring clients; The corrosion rate prediction data are sent to a central server for storage, and the corrosion rate prediction data corresponding to each monitoring client are visualized using digital twin technology.

2. A method for monitoring corrosion of earth-covered storage tanks according to claim 1, characterized in that: The environmental data includes soil moisture data, soil temperature data, pH value data and oxidation-reduction potential data.

3. The method for monitoring corrosion of earth-covered storage tanks according to claim 1, characterized in that: The internal sensing data of the storage tank includes liquid level sensing data, temperature sensing data and corrosion monitoring sensing data.

4. The method for monitoring corrosion of earth-covered storage tanks according to claim 1, characterized in that: The method also includes data cleaning, data denoising and standardization processing of the historical monitoring data to obtain pre-processed historical monitoring data, and training and hyperparameter optimization of the tank corrosion rate prediction model based on the pre-processed historical monitoring data.

5. The method for monitoring corrosion of earth-covered storage tanks according to claim 1, characterized in that: The tank corrosion rate prediction model is trained and hyperparameters are optimized based on historical monitoring data, specifically including: Obtaining several hyperparameter combinations in the tank corrosion rate prediction model; Based on the historical monitoring data, the tank corrosion rate prediction model corresponding to each of the hyperparameter combinations is trained, and the tank corrosion rate prediction model corresponding to each of the hyperparameter combinations is verified and evaluated by a cross-validation method, and the evaluation result is used as the evaluation score corresponding to each of the hyperparameter combinations; generating a walrus population for the walrus using each of the hyperparameter combinations; Based on the evaluation scores corresponding to the hyperparameter combinations and in combination with the walrus optimization algorithm, parameter optimization is performed in the walrus population to obtain the optimal hyperparameter combination; An optimized tank corrosion rate prediction model is constructed based on the optimal hyperparameter combination.

6. A method for monitoring corrosion of earth-covered storage tanks according to claim 5, characterized in that: Based on the evaluation scores corresponding to the hyperparameter combinations and in combination with the walrus optimization algorithm, parameter optimization is performed within the walrus population, specifically including: Setting the value range, population size and number of iterations of the hyperparameter combination, and using each of the hyperparameter combinations as a walrus to generate the walrus population in combination with the walrus optimization algorithm; Based on the walrus optimization algorithm, each hyperparameter combination in the walrus population is iteratively updated multiple times. In each iterative update process, the evaluation score corresponding to each hyperparameter combination is calculated, and the walrus population is updated based on the evaluation score corresponding to each hyperparameter combination, until the number of iterations reaches a preset value, and the optimal hyperparameter combination is output.

7. The method for monitoring corrosion of earth-covered storage tanks according to claim 1, characterized in that: The optimized tank corrosion rate prediction model is deployed to each monitoring client to perform rate prediction, specifically including: Input the real-time monitoring data of each monitoring client into the corresponding tank corrosion rate prediction model, extract the spatial features of the real-time monitoring data through the spatial feature extraction module, and extract the temporal features of the real-time monitoring data through the spatiotemporal feature extraction module; Taking the spatial feature and the temporal feature as inputs of the feature fusion module to perform feature fusion to obtain a fusion feature; The fusion features are input into the fully connected layer to perform rate prediction, and corrosion rate prediction data corresponding to each monitoring client within a preset time period is obtained.

8. The method for monitoring corrosion of earth-covered storage tanks according to claim 1, characterized in that: The digital twin technology is used to visualize the corrosion rate prediction data corresponding to each monitoring client, including: The real-time monitoring data and corrosion rate prediction data corresponding to the monitoring client are connected to the digital twin platform. In the digital twin platform, the preset three-dimensional tank model is associated with the accessed data to realize the dynamic update of the preset three-dimensional tank model.

Images