Pipeline corrosion early warning method, early warning device, electronic equipment and storage medium

Abstract

The invention is suitable for the technical field of artificial intelligence, and provides a pipeline corrosion early warning method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a target point cloud data change value set and a target data set, the target point cloud data change value set comprises a point cloud data change value corresponding to a first preset duration of a target position in the target pipeline before the current moment; inputting the target point cloud data change value set into a point cloud data change value prediction model to obtain a point cloud data change prediction value set; the target point cloud data change value set, the target data set and the point cloud data change prediction value set are input into a pipeline deformation value prediction model, a target deformation prediction value set is obtained, and the target deformation prediction value set comprises target deformation prediction values corresponding to second preset duration after the current moment of each target position; and the target early warning information is determined based on the target deformation predicted value set, so that the efficiency and accuracy of pipeline corrosion early warning are improved.

Description

Technical Field

[0001] This application belongs to the technical field of artificial intelligence, and particularly relates to a pipeline corrosion warning method, a warning device, an electronic device, and a storage medium. Background Art

[0002] With the rapid development of industries such as petroleum, natural gas, and chemical engineering, long-distance transmission pipelines have become an indispensable part. However, due to the harsh working environments these pipelines often face, such as high pressure, high temperature, humidity, or corrosive media, coupled with the erosion of chemical substances in the soil, the problem of pipeline corrosion has become increasingly prominent. Corrosion not only causes the wall thickness of the pipeline to decrease, but may even lead to leakage or fracture, thus triggering environmental pollution, property losses, and even casualties.

[0003] Traditional pipeline corrosion warning methods rely on single detection means, such as electrochemical testing or ultrasonic thickness measurement, etc., and cannot comprehensively capture complex and changeable corrosion phenomena. They are insufficient in terms of the efficiency of processing a large amount of data and are difficult to quickly and accurately identify the corrosion trends in key areas. Moreover, they lack real-time online monitoring capabilities, resulting in a long time delay between problem discovery and measure taking, increasing the risk of accidents and leading to low efficiency and accuracy of pipeline corrosion warning. In addition, in the face of extreme weather conditions or human interferences, etc., their reliability and accuracy will also be severely affected.

[0004] Therefore, how to improve the efficiency and accuracy of pipeline corrosion warning has become an urgent problem to be solved. Summary of the Invention

[0005] Embodiments of this application provide a pipeline corrosion warning method, a warning device, an electronic device, and a storage medium, aiming to improve the efficiency and accuracy of pipeline corrosion warning.

[0006] In a first aspect, an embodiment of the present application provides a pipeline corrosion warning method, and the method includes: obtaining a target point cloud data change value set and a target data set of a target pipeline, where the target point cloud data change value set includes point cloud data change values corresponding to a first preset time period before the current moment at a target position in the target pipeline, the target position is any one or more positions in the target pipeline, and the target data set includes point cloud data and environmental data corresponding to each of the target positions at the current moment; inputting the target point cloud data change value set into a point cloud data change value prediction model in a trained pipeline corrosion warning model to obtain a point cloud data change prediction value set, where the point cloud data change prediction value set includes point cloud data change prediction values corresponding to the first preset time period after the current moment at each of the target positions in the target pipeline; inputting the target point cloud data change value set, the target data set, and the point cloud data change prediction value set into a pipeline deformation value prediction model in the pipeline corrosion warning model to obtain a target deformation prediction value set, where the target deformation prediction value set includes target deformation prediction values corresponding to a second preset time period after the current moment at each of the target positions in the target pipeline, and the second preset time period is an integer multiple of the first preset time period; determining target warning information based on the target deformation prediction value set, where the target warning information is used to warn of abnormal deformation of the target pipeline.

[0007] In a possible implementation manner, the obtaining the target point cloud data change value set of the target pipeline includes: within the first preset time period before the current moment, obtaining a point cloud data set of the target pipeline based on a preset time interval; determining a point cloud data change value set based on the point cloud data set and reference point cloud data; and constructing the target point cloud data change value set based on the point cloud data change values corresponding to each of the target positions in the point cloud data change value set.

[0008] In a possible implementation manner, the method further includes: determining each of the target positions in the target pipeline based on a preset interval distance, or determining each of the target positions in the target pipeline based on the point cloud data change value set and a preset point cloud data change threshold.

[0009] In a possible implementation, the pipeline corrosion warning model includes a first model input module, a second model input module, the point cloud data change value prediction model, the pipeline deformation value prediction model, and a model output module; the point cloud data change value prediction model is a seasonal autoregressive integrated moving average model, and its input is connected to the first model input module; the pipeline deformation value prediction model is a densely connected convolutional neural network model, and its input is connected to the outputs of the first model input module, the second model input module, and the point cloud data change value prediction model; the model output module is connected to the output of the pipeline deformation value prediction model.

[0010] In a possible implementation, the training process of the pipeline corrosion warning model includes: obtaining a set of historical point cloud data change values, a set of historical target data, and a set of historical deformation values of the target pipeline; based on the set of historical point cloud data change values, constructing and training a seasonal autoregressive integrated moving average model to obtain the point cloud data change value prediction model; based on the set of historical point cloud data change values, the set of historical target data, and the set of historical deformation values, constructing and training a densely connected convolutional neural network model to obtain the pipeline deformation value prediction model; constructing the pipeline corrosion warning model based on the point cloud data change value prediction model and the pipeline deformation value prediction model.

[0011] In a possible implementation, determining the target warning information based on the set of target deformation prediction values includes: determining the corrosion location of the target pipeline based on the set of target deformation prediction values and a preset deformation value threshold; determining the target corrosion level of each corrosion location based on the set of target deformation prediction values, the corrosion location, and a first preset mapping relationship, where the first mapping relationship represents the mapping relationship between the deformation value and the corrosion level; determining the target maintenance suggestion based on the target corrosion level and a second preset mapping relationship, where the second mapping relationship represents the mapping relationship between the corrosion level and the maintenance suggestion; determining the target warning information based on the corrosion location, the target corrosion level, and the target maintenance suggestion.

[0012] In a possible implementation, the environmental data includes any one or more of the repair times, the pressure, the temperature, the humidity, and the pH value at each target location in the target pipeline at the current moment.

[0013] Second aspect, an embodiment of the present application provides a pipeline corrosion warning device, and the device includes: a data acquisition module, configured to acquire a set of target point cloud data change values and a set of target data of a target pipeline, the set of target point cloud data change values includes point cloud data change values corresponding to a first preset duration before the current moment at a target position in the target pipeline, the target position is any one or more positions in the target pipeline, and the set of target data includes point cloud data and environmental data corresponding to each of the target positions at the current moment; a first prediction module, configured to input the set of target point cloud data change values into a point cloud data change value prediction model in a trained pipeline corrosion warning model to obtain a set of point cloud data change prediction values, the set of point cloud data change prediction values includes point cloud data change prediction values corresponding to the first preset duration after the current moment at each of the target positions in the target pipeline; a second prediction module, configured to input the set of target point cloud data change values, the set of target data, and the set of point cloud data change prediction values into a pipeline deformation value prediction model in the pipeline corrosion warning model to obtain a set of target deformation prediction values, the set of target deformation prediction values includes target deformation prediction values corresponding to a second preset duration after the current moment at each of the target positions in the target pipeline, and the second preset duration is an integer multiple of the first preset duration; a warning module, configured to determine target warning information based on the set of target deformation prediction values, and the target warning information is used to warn of abnormal deformation of the target pipeline.

[0014] Third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method described in the first aspect or any one of its implementation manners is implemented.

[0015] Fourth aspect, an embodiment of the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect or any one of its implementation manners is implemented.

[0016] Fifth aspect, an embodiment of the present application provides a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any one of its implementation manners are implemented.

[0017] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: When performing pipeline corrosion warning for the target pipeline, the set of target point cloud data change values collected includes the point cloud data change values corresponding to the first preset duration before the current moment at the target position in the target pipeline. The target position is any one or more positions in the target pipeline, rather than collecting and predicting data for each position in the target pipeline, which reduces the computational complexity and improves the efficiency of pipeline corrosion warning. Further, the obtained set of target point cloud data change values is input into the point cloud data change value prediction model in the trained pipeline corrosion warning model to predict the point cloud change values of each target position in the target pipeline, obtaining a set of predicted point cloud data change values. Then, the set of target point cloud data change values, the set of target data, and the set of predicted point cloud data change values are input into the pipeline deformation value prediction model in the pipeline corrosion warning model to obtain a set of target deformation prediction values. Compared with directly predicting the deformation values of each target position in the future preset period based on the deformation values at the current moment and the preset period before the current moment of each target position in the target pipeline, first predicting the point cloud data change values of each target position, and then predicting the deformation values based on the predicted point cloud data change values, the point cloud data at the current moment of each target position, and the environmental data, taking into account the law of point cloud change at each target position and the influence of environmental factors at the current moment, improves the accuracy of pipeline corrosion warning. Moreover, the pipeline deformation value prediction model can not only predict the deformation values of each target position in the target pipeline after a single duration, but can output deformation prediction values corresponding to multiple durations that are integer multiples of the first preset duration, obtaining deformation prediction values for multiple different future periods based on the first preset duration. Furthermore, based on the set of target deformation prediction values corresponding to multiple different future periods, corresponding multiple target warning messages can be determined, which improves the efficiency of pipeline corrosion warning and enhances the user experience.

[0018] It can be understood that a pipeline corrosion warning device, an electronic device, a computer-readable storage medium, and a computer program product provided by the embodiments of the present application have the same beneficial effects as the above pipeline corrosion warning method, and will not be elaborated herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a schematic flowchart of a pipeline corrosion warning method provided by an embodiment of the present application;

[0021] Figure 2 A structural schematic diagram of a pipeline corrosion warning model provided by an embodiment of the present application;

[0022] Figure 3 A structural block diagram of a pipeline corrosion warning device provided by an embodiment of the present application;

[0023] Figure 4 A structural schematic diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0024] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system architectures and technologies are set forth in order to provide a thorough understanding of the embodiments of the present application. However, those skilled in the art should understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from obscuring the description of the present application.

[0025] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0026] It should also be understood that the term "and / or" as used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0027] As used in the specification of the present application and the appended claims, the term "if" can be interpreted as "when" or "once" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if determined" or "if detected [the described condition or event]" can be interpreted as meaning "once determined" or "in response to determining" or "once detected [the described condition or event]" or "in response to detecting [the described condition or event]" depending on the context.

[0028] In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0029] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that a particular feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0030] The research on pipeline corrosion warning stems from the urgent need of the industrial community to improve the safety and reliability of infrastructure. With the rapid development of industries such as oil, gas, and chemicals, long-distance transmission pipelines have become an indispensable part. However, since these pipelines often face harsh working environments, such as high pressure, high temperature, humidity, or corrosive media, coupled with the erosion of chemical substances in the soil, the problem of pipeline corrosion has become increasingly prominent. Corrosion not only causes the wall thickness of the pipeline to decrease, but may even lead to leakage or rupture, thus causing environmental pollution, property losses, and even casualties. Therefore, it is particularly important to establish a set of efficient and accurate pipeline corrosion warning systems. Such systems can monitor the pipeline status in real time, detect potential corrosion risks in advance, provide a scientific basis for preventive maintenance, and ensure the safety and economy of pipeline operation.

[0031] Traditional pipeline corrosion warning systems have shown some limitations in coping with modern industrial challenges. First of all, these systems often rely on a single detection method, such as electrochemical testing or ultrasonic thickness measurement, and cannot comprehensively capture complex and variable corrosion phenomena. Secondly, the lack of real-time online monitoring capabilities results in a long time delay between discovering problems and taking measures, increasing the risk of accidents. Moreover, traditional methods are insufficient in the efficiency of processing a large amount of data and are difficult to quickly and accurately identify the corrosion trends in key areas. In addition, due to the failure to fully utilize digital and intelligent technologies, the reliability and accuracy of traditional systems may be affected in the face of extreme weather conditions or human interferences. Therefore, the development of a new generation of pipeline corrosion warning systems that are more advanced, highly integrated, and have adaptive learning capabilities has become an industry consensus.

[0032] To solve the above technical problems, the present application provides a pipeline corrosion warning method, which obtains a set of target point cloud data change values and a set of target data of a target pipeline. The set of target point cloud data change values includes the point cloud data change values corresponding to a first preset duration before the current moment at a target position in the target pipeline, where the target position is any one or more positions in the target pipeline, and the set of target data includes the point cloud data and environmental data corresponding to each target position at the current moment; input the set of target point cloud data change values into the point cloud data change value prediction model in the trained pipeline corrosion warning model to obtain a set of point cloud data change prediction values, where the set of point cloud data change prediction values includes the point cloud data change prediction values corresponding to a first preset duration after the current moment at each target position in the target pipeline; input the set of target point cloud data change values, the set of target data, and the set of point cloud data change prediction values into the pipeline deformation value prediction model in the pipeline corrosion warning model to obtain a set of target deformation prediction values, where the set of target deformation prediction values includes the target deformation prediction values corresponding to a second preset duration after the current moment at each target position in the target pipeline, and the second preset duration is an integer multiple of the first preset duration; based on the set of target deformation prediction values, determine the target warning information, where the target warning information is used to warn of abnormal deformation of the target pipeline, improving the efficiency and accuracy of pipeline corrosion warning.

[0033] For ease of understanding, the technical solution of the present application will be introduced in detail below with reference to the accompanying drawings.

[0034] Figure 1 FIG. is a schematic flow chart of a pipeline corrosion warning method provided by an embodiment of the present application. For ease of description, only parts related to this embodiment are shown. The method provided by this embodiment includes the following steps:

[0035] S110, obtain a set of target point cloud data change values and a set of target data of the target pipeline. The set of target point cloud data change values includes the point cloud data change values corresponding to a first preset duration before the current moment at a target position in the target pipeline, where the target position is any one or more positions in the target pipeline, and the set of target data includes the point cloud data and environmental data corresponding to each target position at the current moment.

[0036] Specifically, use a Terrestrial Laser Scanning (TLS) device or a drone equipped with a high-precision camera for aerial photography to collect high-density point cloud data along the target pipeline to obtain detailed spatial morphological information of the target pipeline, that is, point cloud data, and deploy various sensors at each target position of the target pipeline to obtain a set of target data of the target pipeline. The deployed sensors include but are not limited to temperature sensors, displacement sensors, pressure sensors, humidity sensors, and PH sensors.

[0037] As an example, corresponding to the sensors deployed on the target pipeline, the environmental data corresponding to each target position in the acquired target data set at the current moment includes any one or more of the repair times, pressure, temperature, humidity, and pH value at each target position in the target pipeline.

[0038] In a possible implementation manner, the steps of obtaining the target point cloud data change value set of the target pipeline may optionally but not limited to include: within the first preset duration before the current moment, obtaining the point cloud data set of the target pipeline based on a preset time interval; determining the point cloud data change value set based on the point cloud data set and the reference point cloud data; and constructing the target point cloud data change value set based on the point cloud data change values corresponding to each target position in the point cloud data change value set.

[0039] Specifically, the reference point cloud data is the point cloud data of the target pipeline when it is not in use or the preset ideal pipeline point cloud data. The point cloud data change value set includes the differences between the point cloud data at different time points corresponding to each position in the target pipeline based on the preset time interval and the reference point cloud data. The point cloud data is in three-dimensional coordinates, and the difference in the point cloud data is the displacement amount in the X, Y, and Z axis directions.

[0040] In a specific implementation, within the first preset duration before the current moment, the point cloud data of the target pipeline is obtained based on a preset time interval, and preprocessing operations such as denoising, registration, and simplification are performed on the obtained point cloud data. Among them, the denoising operation is to remove the noise points in the point cloud data by applying a filtering algorithm. Common filtering algorithms include statistical filtering, median filtering, etc.; if the method of multiple scans is used to obtain the point cloud data of the target pipeline, the point cloud data obtained from each independent scan needs to be registered to form a unified coordinate system; for the overly dense point cloud data, simplification operations such as downsampling are performed to speed up the subsequent processing without sacrificing too much detailed information; the point cloud data after the preprocessing operation is constructed into a point cloud data set.

[0041] As an example, if the first preset duration is 7 days and the preset time interval is 1 day, then the step of obtaining the point cloud data of the target pipeline based on the preset time interval within the first preset duration before the current moment is to obtain the point cloud data of the target pipeline at the same moment every day within 7 days before the current moment.

[0042] In a possible implementation manner, the target position in the target pipeline is determined based on a preset interval distance, or the target position in the target pipeline is determined based on the point cloud data change value set and a preset point cloud data change threshold.

[0043] Specifically, the target position is the position in the target pipeline where pipeline corrosion prediction is carried out. Pipeline corrosion prediction includes prediction of point cloud data change values and prediction of deformation values. Determining the target position in the target pipeline based on a preset interval distance can evenly distribute the positions for pipeline corrosion prediction, ensuring that pipeline corrosion prediction can be realized in all areas where the target pipeline is located and avoiding missing positions that need to be predicted for pipeline corrosion. Determining the target position in the target pipeline based on the set of point cloud data change values and a preset threshold for point cloud data change is to take the positions where the point cloud data has changed significantly or has abnormal changes within the first preset time period in the past as the target positions, which helps to focus on the positions with abnormal changes when predicting the pipeline corrosion situation and not predict the pipeline corrosion situation for positions without abnormal changes, improving the efficiency of pipeline corrosion early warning and saving computing power.

[0044] In a specific implementation, the positions corresponding to the point cloud data change values in the set of point cloud data change values that exceed the preset threshold for point cloud data change are taken as the target positions.

[0045] It should be noted that the first preset time period, preset time interval, preset interval distance, etc. can all be custom-set according to the actual situation, and the present application does not limit this.

[0046] S120, input the set of target point cloud data change values into the point cloud data change value prediction model in the trained pipeline corrosion early warning model to obtain a set of point cloud data change prediction values. The set of point cloud data change prediction values includes the point cloud data change prediction values corresponding to each target position in the target pipeline for the first preset time period after the current moment.

[0047] In a possible implementation manner, as Figure 2 shown, the pipeline corrosion early warning model includes a first model input module, a second model input module, a point cloud data change value prediction model, a pipeline deformation value prediction model, and a model output module. Among them, the point cloud data change value prediction model is a seasonal autoregressive integrated moving average model, and its input is connected to the first model input module. The pipeline deformation value prediction model is a densely connected convolutional neural network model, and its input is connected to the outputs of the first model input module, the second model input module, and the point cloud data change value prediction model. The model output module is connected to the output of the pipeline deformation value prediction model.

[0048] In a possible implementation, the training process of the pipeline corrosion warning model may optionally but not limited to include: obtaining a set of historical point cloud data change values, a set of historical target data, and a set of historical deformation values of the target pipeline; based on the set of historical point cloud data change values, constructing and training a Seasonal Autoregressive Integrated Moving Average (SARIMA) model to obtain a point cloud data change value prediction model; based on the set of historical point cloud data change values, the set of historical target data, and the set of historical deformation values, constructing and training a densely connected convolutional neural network model to obtain a pipeline deformation value prediction model; based on the point cloud data change value prediction model and the pipeline deformation value prediction model, constructing a pipeline corrosion warning model.

[0049] Specifically, the Seasonal Autoregressive Integrated Moving Average (SARIMA) model is a seasonal extension of the Autoregressive Integrated Moving Average Model (ARIMA). The ARIMA model is a combination of Autoregressive (AR) and Moving Average (MA), while the SARIMA model also takes into account the seasonal component. Its parameters include the seasonal autoregressive order, the seasonal moving average order, the non-seasonal autoregressive order, the non-seasonal moving average order, and the differencing order. In this representation, the SARIMA model can handle both non-seasonal and seasonal components in the time series, making the model more suitable for time series data with obvious seasonal changes. The model takes into account the periodic patterns of data changes over time, such as weekly, monthly, quarterly, annual, etc. temporal regularities, uses past data points to predict future values, transforms non-stationary time series into stationary series through differencing, and uses the average of past errors in the time series for prediction to help eliminate random fluctuations.

[0050] As an example, perform preprocessing operations such as handling missing values and outliers on the set of historical point cloud data change values to ensure the integrity of the time series data. Perform seasonal differencing according to the seasonal period of the preprocessed set of historical point cloud data change values to eliminate the non-stationarity caused by seasonal changes. Identify a suitable SARIMA model by observing the time series graph and the Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF) graphs, use maximum likelihood estimation or other methods to estimate the model parameters, check whether the residual series is white noise to ensure the goodness of fit of the model. After completion of the fitting, determine the point cloud data change value prediction model.

[0051] Specifically, the densely connected convolutional neural network model (Densely Connected Convolutional Networks, DenseNet) is a deep convolutional neural network model that aims to enhance feature reuse and gradient flow through dense connection mechanisms, thereby improving the performance and generalization ability of the model, and can solve the problems of gradient disappearance and model degradation in deep networks. This model helps the gradient back propagation by establishing connections between the previous layers and the subsequent layers, and at the same time establishes dense connections between all the previous layers and the subsequent layers, that is, each layer receives the feature maps of all the previous layers as input, and passes its feature maps to all the subsequent layers, which can more effectively utilize feature information and reduce the number of parameters and computational costs.

[0052] As an example, first build a DenseNet model, configure the hyperparameters in the training process, such as learning rate, batch size, and number of training epochs, and select an appropriate learning rate adjustment strategy, such as exponential decay or cosine decay. Based on the preprocessed historical point cloud data change value set, historical target data set, and historical deformation value set, use the data loader for batch loading, use the optimizer (such as Adam, etc.) to train the model, and monitor indicators such as loss value and accuracy during training. Continuously adjust model parameters and hyperparameters such as learning rate to avoid overfitting or underfitting, use learning rate scheduler, weight decay, and regularization techniques to further improve the performance of the model, and determine the pipeline deformation value prediction model.

[0053] Exemplarily, the target point cloud data change value set includes the point cloud data change values ​​corresponding to the same time of each day for each target position in the target pipeline within the 7 days before the current time. The target point cloud data change value set is input into the point cloud data change value prediction model in the trained pipeline corrosion early warning model to obtain the point cloud data change prediction values ​​corresponding to the same time of the target point cloud data change value set on each day within the 7 days after the current time.

[0054] In addition, when training the pipeline corrosion early warning model, the historical point cloud data change value set, historical target data set and historical deformation value set collected for the target pipeline should include the historical data corresponding to each position in the target pipeline as much as possible to improve the richness of the sample data, improve the training effect, and improve the accuracy of the pipeline corrosion early warning model.

[0055] S130. Input the set of target point cloud data change values, the set of target data, and the set of predicted point cloud data change values into the pipeline deformation value prediction model in the pipeline corrosion warning model to obtain a set of target deformation prediction values. The set of target deformation prediction values includes the target deformation prediction values corresponding to the second preset time period after the current time for each target position in the target pipeline, and the second preset time period is an integer multiple of the first preset time period.

[0056] Specifically, the pipeline deformation value prediction model uses the first preset time period for collecting the set of target point cloud data change values as the calculation base, and predicts a set of target deformation prediction values corresponding to multiple integer multiples of the first preset time period, that is, the pipeline deformation value prediction model can predict the set of target deformation prediction values corresponding to multiple future time periods.

[0057] In a specific implementation, input the set of target point cloud data change values, the set of target data, and the set of predicted point cloud data change values into the pipeline deformation value prediction model in the pipeline corrosion warning model to obtain a set of target deformation prediction values corresponding to multiple different second preset time periods after the current time. The second preset time period is an integer multiple of the first preset time period, and different second preset time periods correspond to different multiples.

[0058] As an example, if the first preset time period is 7 days, then input the set of target point cloud data change values, the set of target data, and the set of predicted point cloud data change values into the pipeline deformation value prediction model in the pipeline corrosion warning model, and a set of target deformation prediction values corresponding to 7 days, 14 days, and 21 days after the current time can be obtained.

[0059] S140. Based on the set of target deformation prediction values, determine the target warning information, and the target warning information is used to warn of abnormal deformation of the target pipeline.

[0060] In a possible implementation manner, step S140 may optionally but not limited to include: determining the corrosion position of the target pipeline based on the set of target deformation prediction values and the preset deformation value threshold; determining the target corrosion level of each corrosion position based on the set of target deformation prediction values, the corrosion position, and the first preset mapping relationship, where the first mapping relationship represents the mapping relationship between the deformation value and the corrosion level; determining the target maintenance suggestion based on the target corrosion level and the second preset mapping relationship, where the second mapping relationship represents the mapping relationship between the corrosion level and the maintenance suggestion; and determining the target warning information based on the corrosion position, the target corrosion level, and the target maintenance suggestion.

[0061] In specific implementation, a first mapping relationship and a second mapping relationship are pre-constructed. The target positions corresponding to the target deformation prediction values in the target deformation prediction value set that exceed the preset deformation value threshold are determined as the corrosion positions of the target pipeline. Based on the target deformation prediction values corresponding to each corrosion position and the first mapping relationship, the target corrosion grades of each corrosion position are determined. Based on the target corrosion grades and the second preset mapping relationship, the target maintenance suggestions are determined. Then, based on the corrosion positions, the target corrosion grades, and the target maintenance suggestions, the target warning information is determined.

[0062] As an example, the preset deformation value threshold can be set to 3% of the pipe wall thickness of the target pipeline. When the target deformation prediction value is greater than 3% of the pipe wall thickness of the target pipeline, it is considered that there will be a corrosion situation at the target position corresponding to the target deformation prediction value, and the target position corresponding to the target deformation prediction value is determined as the corrosion position.

[0063] As an example, the corrosion grades of the pipeline include slight corrosion, moderate corrosion, obvious corrosion, and severe corrosion; in the first mapping relationship, a deformation value of 3%-5% of the pipe wall thickness of the target pipeline has a mapping relationship with slight corrosion, a deformation value of 5%-15% of the pipe wall thickness of the target pipeline has a mapping relationship with moderate corrosion, a deformation value of 15%-30% of the pipe wall thickness of the target pipeline has a mapping relationship with obvious corrosion, and a deformation value exceeding 30% of the pipe wall thickness of the target pipeline has a mapping relationship with severe corrosion.

[0064] As an example, in the second mapping relationship, the maintenance suggestions corresponding to slight corrosion include keeping the pipe surface clean and using passivation treatment; the maintenance suggestions corresponding to moderate corrosion include strengthening cleaning and performing local repairs; the maintenance suggestions corresponding to obvious corrosion are comprehensive inspection and replacement of damaged pipelines; the maintenance suggestions corresponding to severe corrosion include emergency replacement and taking preventive measures.

[0065] In addition, on the basis of the above technical solutions, continuous optimization and upgrading are required. Updates and improvements are made in terms of algorithms and hardware, case data is continuously accumulated, machine learning algorithms are optimized, and the accuracy of deformation prediction is improved; the performance of existing sensors is regularly evaluated, and new models are replaced or the density is increased when necessary.

[0066] Furthermore, on the basis of the above technical solutions, a user interface that is easy to operate is further developed. The pipeline health status and key attention sections are intuitively displayed in the form of maps, charts, etc., and a detailed data analysis report is provided to provide a reference basis for maintenance plan arrangement and resource allocation.

[0067] When the technical solution provided by this application is used for pipeline corrosion warning of a target pipeline, the collected set of target point cloud data change values includes the point cloud data change values corresponding to a first preset time period before the current moment at the target position in the target pipeline. The target position is any one or more positions in the target pipeline, rather than collecting and predicting data for each position in the target pipeline, which reduces the computational complexity and improves the efficiency of pipeline corrosion warning. Further, the obtained set of target point cloud data change values is input into the point cloud data change value prediction model in the trained pipeline corrosion warning model to predict the point cloud change values at each target position in the target pipeline, obtaining a set of point cloud data change prediction values. Then, the set of target point cloud data change values, the set of target data, and the set of point cloud data change prediction values are input into the pipeline deformation value prediction model in the pipeline corrosion warning model to obtain a set of target deformation prediction values. Compared with directly predicting the deformation values of each target position in the future preset time period based on the deformation values at the current moment and the preset time period before the current moment at each target position in the target pipeline, first predicting the point cloud change values at each target position and then predicting the deformation values based on the predicted point cloud data change values, the point cloud data at each target position at the current moment, and the environmental data takes into account the law of point cloud change at each target position and the influence of environmental factors at the current moment, improving the accuracy of pipeline corrosion warning. Moreover, the pipeline deformation value prediction model can not only predict the deformation values of each target position in the target pipeline after a single time period, but can output deformation prediction values corresponding to multiple time periods that are integer multiples of the first preset time period, obtaining deformation prediction values for multiple different future time periods based on the first preset time period. Furthermore, based on the set of target deformation prediction values corresponding to multiple different future time periods, corresponding multiple target warning messages can be determined, improving the efficiency of pipeline corrosion warning and enhancing the user experience.

[0068] In summary, the technical solution provided by this application, which uses a pipeline corrosion warning method based on three-dimensional modeling technology, has brought significant changes and improvements to the industrial field. First, by constructing a fine digital twin, a high-fidelity reproduction of the real-world pipeline structure and environment is achieved, making the assessment of corrosion risk more intuitive and accurate. Second, with the help of advanced data analysis algorithms and machine learning techniques, not only can the corrosion-sensitive parts be accurately located, but also the potential fault points that may occur in the future can be predicted, greatly improving the timeliness and pertinence of the warning. Moreover, three-dimensional modeling enables engineers to simulate different operation scenarios in a virtual environment, effectively reducing the number of on-site tests, saving costs and reducing safety risks. In addition, it supports remote monitoring and automated management, greatly improving the operation and maintenance efficiency and reducing the human input. Through this series of comprehensive measures, the technical solution provided by this application can effectively prevent and control the safety hazards caused by pipeline deformation, ensure the long-term stable operation of the pipeline, and at the same time greatly improve the efficiency and quality of operation and management.

[0069] Figure 3 The following is a structural block diagram of a pipeline corrosion warning device provided by an embodiment of the present application. For the convenience of description, only the parts related to the embodiment of the present application are shown. Referring to Figure 3 , the pipeline corrosion warning device 300 may include a data acquisition module 301, a first prediction module 302, a second prediction module 303, and a warning module 304.

[0070] The data acquisition module 301 is used to acquire a set of target point cloud data change values and a set of target data of the target pipeline. The set of target point cloud data change values includes the point cloud data change values corresponding to a first preset time period before the current moment at the target position in the target pipeline. The target position is any one or more positions in the target pipeline. The set of target data includes the point cloud data and environmental data corresponding to each target position at the current moment.

[0071] The first prediction module 302 is used to input the set of target point cloud data change values into the point cloud data change value prediction model in the trained pipeline corrosion warning model to obtain a set of point cloud data change prediction values. The set of point cloud data change prediction values includes the point cloud data change prediction values corresponding to a first preset time period after the current moment at each target position in the target pipeline.

[0072] The second prediction module 303 is used to input the set of target point cloud data change values, the set of target data, and the set of point cloud data change prediction values into the pipeline deformation value prediction model in the pipeline corrosion warning model to obtain a set of target deformation prediction values. The set of target deformation prediction values includes the target deformation prediction values corresponding to a second preset time period after the current moment at each target position in the target pipeline. The second preset time period is an integer multiple of the first preset time period.

[0073] The warning module 304 is used to determine target warning information based on the set of target deformation prediction values. The target warning information is used to warn of abnormal deformation of the target pipeline.

[0074] A pipeline corrosion warning device provided by an embodiment of the present application has the same beneficial effects as the above-mentioned pipeline corrosion warning method.

[0075] It should be noted that the information interaction, execution process, etc. between the above-mentioned device / units, due to being based on the same concept as the method embodiment of the present application, for their specific functions and the technical effects brought, please refer to the method embodiment part specifically, and will not be elaborated here.

[0076] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device 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 a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of the functional units and modules are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0077] Figure 4 FIG. is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 4 shown, the electronic device 4 of this embodiment includes: at least one processor 40 ( Figure 4 only one is shown in the figure), a memory 41, and a computer program 42 stored in the memory 41 and executable on at least one processor 40. When the processor 40 executes the computer program 42, it implements the steps in the above Figure 1 method embodiment, or implements the functions of each module / unit in the above Figure 3 device embodiment.

[0078] The electronic device 4 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The electronic device 4 may include but is not limited to the processor 40 and the memory 41. Those skilled in the art can understand that Figure 4 merely an example of the electronic device 4, which does not constitute a limitation on the electronic device 4, and may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0079] The processor 40 may be a Central Processing Unit (CPU), and the processor 40 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0080] The memory 41 may be an internal storage unit of the electronic device 4 in some embodiments, such as the hard disk or memory of the electronic device 4. The memory 41 may also be an external storage device of the electronic device 4 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., equipped on the electronic device 4. Further, the memory 41 may also include both the internal storage unit and the external storage device of the electronic device 4. The memory 41 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of a computer program. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0081] The embodiments of the present application also provide a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in the above various method embodiments can be implemented.

[0082] When an integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above method embodiments of this application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to an electronic device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc.

[0083] A computer-readable storage medium provided by an embodiment of this application has the same beneficial effects as the above pipeline corrosion warning method.

[0084] An embodiment of this application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments can be implemented.

[0085] A computer program product provided by an embodiment of this application has the same beneficial effects as the above pipeline corrosion warning method.

[0086] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0087] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0088] In the embodiments provided in the present application, it should be understood that the disclosed apparatus / devices and methods can be implemented in other ways. For example, the apparatus / device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the apparatus or unit can be in electrical, mechanical or other forms.

[0089] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0090] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A pipeline corrosion early warning method, characterized in that: The method comprises: Acquire a target point cloud data change value set and a target data set of a target pipeline, wherein the target point cloud data change value set includes a point cloud data change value corresponding to a first preset time length of a target position in the target pipeline before a current moment, the target position is any one or more positions in the target pipeline, and the target data set includes point cloud data and environmental data corresponding to each of the target positions at the current moment; Inputting the target point cloud data change value set into a point cloud data change value prediction model in a trained pipeline corrosion early warning model to obtain a point cloud data change prediction value set, wherein the point cloud data change prediction value set includes the point cloud data change prediction value corresponding to the first preset time length of each target position in the target pipeline after the current moment; Inputting the target point cloud data change value set, the target data set and the point cloud data change prediction value set into the pipeline deformation value prediction model in the pipeline corrosion early warning model to obtain a target deformation prediction value set, wherein the target deformation prediction value set includes target deformation prediction values ​​corresponding to a second preset time length after the current moment for each target position in the target pipeline, wherein the second preset time length is an integer multiple of the first preset time length; Based on the target deformation prediction value set, target warning information is determined, and the target warning information is used to warn of abnormal deformation of the target pipeline.

2. The method according to claim 1, characterized in that The step of obtaining a target point cloud data change value set of a target pipeline includes: Within the first preset time period before the current moment, acquiring a point cloud data set of the target pipeline based on a preset time interval; Determining a point cloud data change value set based on the point cloud data set and the reference point cloud data; The target point cloud data change value set is constructed based on the point cloud data change value corresponding to each of the target positions in the point cloud data change value set.

3. The method according to claim 2, characterized in that The method further comprises: Each of the target positions in the target pipeline is determined based on a preset interval distance, or each of the target positions in the target pipeline is determined based on the point cloud data change value set and a preset point cloud data change threshold.

4. The method according to claim 1, characterized in that The pipeline corrosion early warning model includes a first model input module, a second model input module, the point cloud data change value prediction model, the pipeline deformation value prediction model and a model output module; The point cloud data change value prediction model is a seasonal difference autoregressive moving average model, and its input is connected to the first model input module; The pipeline deformation value prediction model is a densely connected convolutional neural network model, whose input is connected to the first model input module, the second model input module and the output of the point cloud data change value prediction model; The model output module is connected to the output of the pipeline deformation value prediction model.

5. The method according to claim 4, characterized in that The training process of the pipeline corrosion early warning model includes: Acquire a historical point cloud data change value set, a historical target data set, and a historical deformation value set of the target pipeline; Based on the historical point cloud data change value set, a seasonal difference autoregressive moving average model is constructed and trained to obtain the point cloud data change value prediction model; Based on the historical point cloud data change value set, the historical target data set and the historical deformation value set, a densely connected convolutional neural network model is constructed and trained to obtain the pipeline deformation value prediction model; The pipeline corrosion early warning model is constructed based on the point cloud data change value prediction model and the pipeline deformation value prediction model.

6. The method according to claim 1, characterized in that The determining target warning information based on the target deformation prediction value set includes: Determining the corrosion position of the target pipeline based on the target deformation prediction value set and a preset deformation value threshold; Determining a target corrosion level for each of the corrosion locations based on the target deformation prediction value set, the corrosion locations, and a first preset mapping relationship, wherein the first mapping relationship represents a mapping relationship between deformation values ​​and corrosion levels; Determining a target maintenance suggestion based on the target corrosion level and a second preset mapping relationship, wherein the second mapping relationship represents a mapping relationship between the corrosion level and the maintenance suggestion; The target warning information is determined based on the corrosion location, the target corrosion level and the target maintenance suggestion.

7. The method according to any one of claims 1 to 6, characterized in that: The environmental data includes any one or more of the number of maintenance times of each target position in the target pipeline, pressure, temperature, humidity and pH at the current moment.

8. A pipeline corrosion early warning device, characterized in that: The device comprises: A data acquisition module, used to acquire a target point cloud data change value set and a target data set of a target pipeline, wherein the target point cloud data change value set includes a point cloud data change value corresponding to a first preset time length of a target position in the target pipeline before a current moment, the target position is any one or more positions in the target pipeline, and the target data set includes point cloud data and environmental data corresponding to each of the target positions at the current moment; A first prediction module is used to input the target point cloud data change value set into the point cloud data change value prediction model in the trained pipeline corrosion early warning model to obtain a point cloud data change prediction value set, wherein the point cloud data change prediction value set includes the point cloud data change prediction value corresponding to the first preset time length of each target position in the target pipeline after the current moment; A second prediction module is used to input the target point cloud data change value set, the target data set and the point cloud data change prediction value set into the pipeline deformation value prediction model in the pipeline corrosion early warning model to obtain a target deformation prediction value set, wherein the target deformation prediction value set includes target deformation prediction values ​​corresponding to a second preset time length after the current moment for each target position in the target pipeline, and the second preset time length is an integer multiple of the first preset time length; The early warning module is used to determine target early warning information based on the target deformation prediction value set, and the target early warning information is used to warn of abnormal deformation of the target pipeline.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images