Underwater production system pipeline damage position identification method, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a damage position identification method of an underwater production system pipeline, electronic equipment, a storage medium and a program product. The preset noise reduction algorithm is adopted to carry out noise reduction processing on the collected first reflection ultrasonic guided wave signal, noise interference in the signal can be removed, the quality and reliability of the signal can be improved, a more accurate data basis is provided for subsequent damage feature extraction and analysis, and improvement of the accuracy of damage identification is facilitated. The one-dimensional convolutional neural network model can extract at least one of the time domain damage feature and the frequency domain damage feature from the second reflection ultrasonic guided wave signal, the damage position of the pipeline is judged by comprehensively utilizing the multiple features, and the damage position of the pipeline can be reflected more comprehensively. The pipeline is divided into a plurality of pipeline position sections, and the damage probability of each pipeline position section is calculated by using the one-dimensional convolutional neural network model, so that the damage position in the pipeline of the underwater production system can be positioned more accurately.

Description

Technical Field

[0001] The present application relates to the field of marine engineering, and in particular to a method for identifying damage locations of pipelines in underwater production systems, electronic equipment, storage media, and program products. Background Art

[0002] In offshore oil production, underwater production system pipelines are crucial for transporting oil and gas, connecting and supporting equipment, and ensuring the normal operation of deepwater production systems and oil and gas production. However, in complex marine environments, pipelines are susceptible to corrosion, fatigue, and third-party activities, leading to damage and increasing the risk of leaks.

[0003] At present, ultrasonic guided wave detection technology is widely used in the intelligent identification and monitoring of pipeline damage in underwater production systems. Its principle is to use the reflection, refraction and mode conversion of ultrasonic guided waves when they encounter damage in the pipeline, causing changes in propagation characteristics. These changes are analyzed by signal processing algorithms to identify damage. Signal processing algorithms such as Fourier transform analyze the pre-processed signal and extract characteristic parameters related to pipeline damage, thereby realizing the identification and location of pipeline damage.

[0004] However, the propagation characteristics of ultrasonic guided waves in pipelines are affected by many factors. For pipelines with complex structures, ultrasonic guided waves will undergo complex reflections, refractions and mode conversions in these areas, which easily generate interference noise. Traditional signal processing methods have difficulty processing this interference noise, resulting in low accuracy in identifying and locating pipeline damage. Summary of the Invention

[0005] The embodiments of the present application provide a method for identifying the damaged location of an underwater production system pipeline, an electronic device, a storage medium, and a program product, which are used to accurately identify the damaged location of the underwater production system pipeline.

[0006] In a first aspect, an embodiment of the present application provides a method for identifying a damage location of a pipeline in an underwater production system, comprising:

[0007] Receiving a first reflected ultrasonic guided wave signal of any underwater production system pipeline collected by an ultrasonic guided wave detection system;

[0008] Using a preset noise reduction algorithm, the first reflected ultrasonic guided wave signal is subjected to noise reduction processing to obtain a second reflected ultrasonic guided wave signal;

[0009] Divide the underwater production system pipeline into multiple pipeline location segments;

[0010] Inputting the second reflected ultrasonic guided wave signal into a trained one-dimensional convolutional neural network model to perform the following processing: extracting damage features associated with the damage from the second reflected ultrasonic guided wave signal, wherein the damage features include at least one of a time-domain damage feature and a frequency-domain damage feature; calculating a damage probability for each pipeline location segment based on at least one of the time-domain damage feature and the frequency-domain damage feature, and outputting the damage probability for each pipeline location segment;

[0011] The pipeline location section where the damage probability meets the preset conditions is determined as the damage location of the underwater production system pipeline.

[0012] In a possible implementation, the ultrasonic guided wave detection system includes an excitation signal source device and a piezoelectric transducer;

[0013] Accordingly, before receiving the first reflected ultrasonic guided wave signal of any underwater production system pipeline collected by the ultrasonic guided wave detection system, the method includes:

[0014] Establish a cylindrical coordinate system for the cross section of the underwater production system pipeline;

[0015] Based on the cylindrical coordinate system of the cross section of the underwater production system pipeline, the wave equation and dispersion equation of the underwater production system pipeline are established;

[0016] Determine the excitation signal based on the wave equation and dispersion equation;

[0017] Sending an excitation signal to the piezoelectric transducer through an excitation signal source device;

[0018] In response to the excitation signal, the piezoelectric transducer is triggered to transmit an ultrasonic guided wave signal to the underwater production system pipeline to collect the reflected ultrasonic guided wave signal of the underwater production system pipeline.

[0019] In one possible implementation, a preset noise reduction algorithm is used to perform noise reduction processing on the reflected ultrasonic guided wave signal to obtain a noise-reduced reflected ultrasonic guided wave signal, including:

[0020] Inputting the reflected ultrasonic guided wave signal into a first preset algorithm to decompose the reflected ultrasonic guided wave signal, and obtaining an output as n signal components, where n is an integer greater than 1;

[0021] Calculate the permutation entropy of n signal components;

[0022] Select the signal component whose permutation entropy value is less than a preset threshold to obtain the valid signal component;

[0023] Selecting a signal component whose permutation entropy value is greater than or equal to a preset threshold to obtain a noise signal component;

[0024] Perform wavelet decomposition and reconstruction on the noise signal component, and perform wavelet threshold noise reduction to obtain the noise reduction signal component;

[0025] The effective signal component and the noise reduction signal component are combined to obtain the noise-reduced reflected ultrasonic guided wave signal.

[0026] In one possible implementation, before inputting the reflected ultrasonic guided wave signal into the first preset algorithm, the method includes:

[0027] Based on a second preset algorithm, generating a first preset number of first parameters and second parameters within a preset value range;

[0028] Combine the first parameter and the second parameter in pairs and calculate the envelope entropy value of the combination;

[0029] A combination whose envelope entropy value is less than a first preset threshold is selected to establish a first preset algorithm.

[0030] In a possible implementation, the method further includes:

[0031] Establish j one-dimensional convolutional neural network models with different structures, where j is an integer greater than 1;

[0032] Obtain damage dataset;

[0033] Inputting the damage dataset into j one-dimensional convolutional neural network models with different structures, training the j one-dimensional convolutional neural network models with different structures to obtain j trained one-dimensional convolutional neural network models with different structures;

[0034] Obtain the classification accuracy, precision, recall, and F1 value of j trained one-dimensional convolutional neural network models with different structures;

[0035] Based on the classification accuracy, precision, recall rate and F1 value, a one-dimensional convolutional neural network model that meets the preset requirements is selected and determined as the trained one-dimensional convolutional neural network model.

[0036] In one possible implementation, obtaining a damage dataset includes:

[0037] Establish a simulation model of the underwater production system pipeline based on preset underwater production system pipeline parameters and preset damage types;

[0038] A damage dataset is obtained based on a simulation model of a subsea production system pipeline.

[0039] In a second aspect, an embodiment of the present application provides a device for identifying a damaged location of a pipeline in an underwater production system, comprising:

[0040] A receiving module, configured to receive a first reflected ultrasonic guided wave signal of any underwater production system pipeline collected by the ultrasonic guided wave detection system;

[0041] a noise reduction module, configured to perform noise reduction processing on the first reflected ultrasonic guided wave signal using a preset noise reduction algorithm to obtain a second reflected ultrasonic guided wave signal;

[0042] a processing module for dividing a subsea production system pipeline into a plurality of pipeline position segments;

[0043] The processing module is further configured to input the second reflected ultrasonic guided wave signal into a trained one-dimensional convolutional neural network model to perform the following processing: extracting damage features related to the damage from the second reflected ultrasonic guided wave signal, wherein the damage features include at least one of a time domain damage feature and a frequency domain damage feature; and calculating a damage probability for each pipeline location segment based on at least one of the time domain damage feature and the frequency domain damage feature, and outputting the damage probability for each pipeline location segment;

[0044] The determination module is used to determine the pipeline position section whose damage probability meets the preset conditions as the damage position of the underwater production system pipeline.

[0045] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory, a processor;

[0046] Memory stores computer-executable instructions;

[0047] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0048] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementation methods of the first aspect.

[0049] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0050] The damage location identification method, electronic device, storage medium and program product of the underwater production system pipeline provided in the embodiment of the present application adopts a preset noise reduction algorithm to perform noise reduction processing on the collected first reflected ultrasonic guided wave signal, which can remove noise interference in the signal and improve the quality and reliability of the signal, thereby providing a more accurate data basis for subsequent damage feature extraction and analysis, and helping to improve the accuracy of damage identification. The one-dimensional convolutional neural network model can extract at least one of the time domain damage features and frequency domain damage features from the second reflected ultrasonic guided wave signal, and comprehensively utilize multiple features to judge the damage location of the pipeline, which can more comprehensively reflect the damage location of the pipeline. By dividing the pipeline into multiple pipeline position segments and using the one-dimensional convolutional neural network model to calculate the damage probability of each pipeline position segment, the damage location in the underwater production system pipeline can be located more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0052] Figure 1 A schematic diagram of a pipeline scenario of an underwater production system provided in an embodiment of the present application;

[0053] Figure 2a Schematic diagram of the process of the damage location identification method of the underwater production system pipeline provided in the embodiment of the present application Figure 1 ;

[0054] Figure 2b A schematic diagram of the architecture of a one-dimensional convolutional neural network model provided in an embodiment of the present application;

[0055] Figure 3a Flowchart 2 of the method for identifying damage locations of pipelines in an underwater production system provided in an embodiment of the present application;

[0056] Figure 3b A schematic diagram of a group velocity dispersion curve of ultrasonic guided waves in an underwater production system pipeline provided in an embodiment of the present application;

[0057] Figure 3c A schematic diagram of a phase velocity dispersion curve of ultrasonic guided waves in an underwater production system pipeline provided in an embodiment of the present application;

[0058] Figure 3d A schematic diagram of the propagation of ultrasonic guided waves in a pipeline according to an embodiment of the present application;

[0059] Figure 4 A schematic diagram of the structure of a device for identifying damaged locations of pipelines in an underwater production system provided in an embodiment of the present application;

[0060] Figure 5A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0061] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0062] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0063] Figure 1 A schematic diagram of a pipeline of an underwater production system provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the specific application scenarios of this application include underwater production systems and pipelines.

[0064] Subsea production systems are key facilities for deepwater oil and gas development, responsible for transporting oil and gas, connecting and supporting equipment, and playing a vital role in ensuring the normal operation of deepwater production systems and oil and gas production. In deepwater environments, underwater production system pipelines are subjected to long-term high pressure, low temperatures, severe corrosion, and complex currents and wave loads, making them highly susceptible to damage. Furthermore, underwater production system pipelines are complex, with different pipes having varying internal and external diameters and materials.

[0065] At present, ultrasonic guided wave detection technology is widely used in the intelligent identification and monitoring of pipeline damage in underwater production systems. Its principle is to use the reflection, refraction and mode conversion of ultrasonic guided waves when they encounter damage in the pipeline, causing changes in propagation characteristics. These changes are analyzed by signal processing algorithms to identify damage. Signal processing algorithms such as Fourier transform analyze the pre-processed signal and extract characteristic parameters related to pipeline damage, thereby realizing the identification and location of pipeline damage.

[0066] However, the propagation characteristics of ultrasonic guided waves in pipelines are affected by many factors. For pipelines with complex structures, ultrasonic guided waves will undergo complex reflections, refractions and mode conversions in these areas, which easily generate interference noise. Traditional signal processing methods have difficulty processing this interference noise, resulting in low accuracy in identifying and locating pipeline damage.

[0067] To address the aforementioned technical issues, the following technical concept was proposed: The inventors propose a pre-set noise reduction algorithm for ultrasonic guided wave signals reflected from underwater production system pipelines to suppress interference noise in the reflected ultrasonic guided wave signals and increase the effective signal ratio in the reflected ultrasonic guided wave signals. Furthermore, the inventors conceived the possibility of using a deep neural network model to more comprehensively and deeply explore damage features in the noise-reduced reflected ultrasonic guided wave signals, thereby more accurately identifying the location of damage. Furthermore, to more accurately locate damage, the inventors conceived the possibility of fine-tuning the management of underwater production systems to enable more precise damage detection and analysis of different parts of the pipeline.

[0068] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0069] Figure 2a Schematic diagram of the process of the damage location identification method of the underwater production system pipeline provided in the embodiment of the present application Figure 1 ,like Figure 2a As shown, the method is applied to any electronic device, as detailed below:

[0070] S201. Receive a first reflected ultrasonic guided wave signal of any underwater production system pipeline collected by an ultrasonic guided wave detection system.

[0071] Specifically, the ultrasonic guided wave detection system, according to established detection strategies and parameter settings, transmits ultrasonic guided waves into the underwater production system pipelines. As the ultrasonic guided waves propagate through the pipelines, they are reflected when they encounter pipeline damage. The ultrasonic guided wave detection system then uses its own signal receiving device to accurately capture the first reflected ultrasonic guided wave signal reflected from the pipeline.

[0072] S202: Use a preset noise reduction algorithm to perform noise reduction processing on the first reflected ultrasonic guided wave signal to obtain a second reflected ultrasonic guided wave signal.

[0073] Specifically, a preset noise reduction algorithm is used to extract features from the first reflected ultrasonic guided wave signal, identifying the noise components and effective signal features in the first reflected ultrasonic guided wave signal. Then, according to the noise reduction rules set in the preset noise reduction algorithm, the noise components are suppressed or eliminated. During the processing, the algorithm continuously monitors and adjusts the signal in real time to ensure that while removing noise, the effective information in the first reflected ultrasonic guided wave signal is retained to the greatest extent. After a series of calculations and processing steps of the noise reduction algorithm, a relatively pure second reflected ultrasonic guided wave signal is finally output.

[0074] S203: Divide the underwater production system pipeline into multiple pipeline position segments.

[0075] Specifically, based on the actual layout drawings of the underwater production system pipelines, key information such as the pipeline direction, connection method, and surrounding environmental characteristics are carefully sorted out. At the same time, referring to the experience data of similar underwater pipeline inspections and maintenance in the past, a comprehensive consideration is given to the different degrees to which pipelines at different locations are affected by factors such as water flow impact, seawater corrosion, and mechanical stress. Then, based on this information, the underwater production system pipelines are divided according to preset rules. The division criteria can be based on the physical length of the pipeline, such as setting a segment node every specific length (such as 50 meters); it can also be based on the functional area of ​​the pipeline, such as dividing the pipeline section connecting different production equipment into independent location segments; it can also be combined with terrain factors to distinguish pipelines at different seabed depths or landform features. In this way, the originally continuous underwater production system pipelines are systematically divided into multiple pipeline location segments with clear boundaries and characteristics.

[0076] S204. Input the second reflected ultrasonic guided wave signal into a trained one-dimensional convolutional neural network model for the following processing: extract damage features related to the damage from the second reflected ultrasonic guided wave signal, wherein the damage features include at least one of a time domain damage feature and a frequency domain damage feature; calculate the damage probability of each pipeline position segment based on at least one of the time domain damage feature and the frequency domain damage feature, and output the damage probability of each pipeline position segment.

[0077] Among them, the one-dimensional convolutional neural network model is as follows Figure 2b As shown, Figure 2b The schematic diagram of the architecture of the one-dimensional convolutional neural network model provided in the embodiment of the present application includes: an input layer for inputting a second reflected ultrasonic guided wave signal. A convolution layer for extracting damage features related to damage from the second reflected ultrasonic guided wave signal. A pooling layer for reducing the dimension of the damage features and reducing the amount of calculation while maintaining the invariance of the features. A fully connected layer for integrating the damage features and calculating the damage probability of each pipeline location segment. A dropout layer for randomly discarding a portion of neurons to prevent overfitting. An output layer for outputting the damage probability of each pipeline location segment.

[0078] Specifically, when the second reflected ultrasonic guided wave signal is input into the one-dimensional convolutional neural network model, the convolutional layer within the model uses its specific convolution kernel to scan the second reflected ultrasonic guided wave signal point by point. During this process, the convolution kernel is convolved with a local region of the second reflected ultrasonic guided wave signal, capturing local features within the signal. Through the layered screening and refinement of multiple convolutional layers, the one-dimensional convolutional neural network model is able to accurately extract damage-related features from the complex second reflected ultrasonic guided wave signal. These damage features include at least one of time-domain damage features and frequency-domain damage features. For time-domain damage features, the one-dimensional convolutional neural network model can identify information such as arrival time difference of reflected waves, changes in pulse width, and waveform distortion. These features can intuitively reflect signs of pipeline damage in the time dimension. For frequency-domain damage features, the one-dimensional convolutional neural network model uses mathematical techniques such as Fourier transform to convert the time-domain signal into the frequency domain for analysis, extracting features such as amplitude changes of specific frequency components, frequency curve offsets, and abnormal energy distribution in frequency bands.

[0079] After damage signature extraction, the fully connected layer of the one-dimensional convolutional neural network model comprehensively processes at least one of the extracted time-domain and frequency-domain damage signatures. Using a pre-defined algorithm and weight assignment, these damage signatures are compared and matched with the patterns of different damage levels and corresponding probabilities learned during the one-dimensional convolutional neural network training process. Based on this, the model calculates the damage probability for each pipeline segment and outputs the calculated damage probability for each segment.

[0080] Possibly, the one-dimensional convolutional neural network model can identify the damage type of each pipeline location segment based on the damage characteristics, including no damage, crack, corrosion, and fracture.

[0081] S205: Determine the pipeline location segment whose damage probability meets the preset conditions as the damage location of the underwater production system pipeline.

[0082] Specifically, the setting of preset conditions is based on comprehensive consideration of multiple factors. On the one hand, reference is made to the design standards, material properties, and past damage cases and statistical data of similar pipelines in the underwater production system pipelines. For example, a reasonable damage probability threshold is set based on parameters such as the fatigue limit and corrosion rate of the material, combined with the severity of the actual operating environment. For pipelines in some key locations, since they are crucial to the normal operation of the entire underwater production system, the preset damage probability threshold may be relatively low, such as being set to 0.3 (that is, when the damage probability of a certain pipeline location section reaches 30% or above, it is considered that the pipeline location section may be damaged). Optionally, for some minor or non-critical pipeline locations, the threshold can be appropriately increased, such as being set to 0.5.

[0083] For example, critical pipelines might be those connecting the underwater central manifold to the wellhead, or to the offshore pipeline. Damage to these critical pipelines could affect oil and gas collection and transmission, leading to a decrease in system production capacity or even shutdown. Secondary or non-critical pipelines might be used for flushing or sewage treatment. A single pipeline failure won't cause a system shutdown and can be resolved through isolation, switching, or temporary repairs.

[0084] After the damage probability of each pipeline segment is output, the damage probability of each pipeline segment is compared with the preset conditions one by one. For those pipeline segments whose damage probability meets the preset conditions, they are determined to be the damaged locations of the underwater production system pipeline.

[0085] If possible, the pipeline location section with the highest loss probability is selected and determined as the damage location of the underwater production system pipeline.

[0086] In summary, the damage location identification method for underwater production system pipelines provided in the embodiment of the present application, by using a preset noise reduction algorithm to perform noise reduction processing on the collected first reflected ultrasonic guided wave signal, can remove noise interference in the signal and improve the quality and reliability of the signal, thereby providing a more accurate data basis for subsequent damage feature extraction and analysis, and helping to improve the accuracy of damage identification. The one-dimensional convolutional neural network model can extract at least one of the time domain damage features and frequency domain damage features from the second reflected ultrasonic guided wave signal, and comprehensively utilize multiple features to determine the damage location of the pipeline, which can more comprehensively reflect the damage location of the pipeline. By dividing the pipeline into multiple pipeline position segments and using the one-dimensional convolutional neural network model to calculate the damage probability of each pipeline position segment, the damage location in the underwater production system pipeline can be located more accurately.

[0087] Figure 3a Flowchart 2 of the method for identifying the damage location of the underwater production system pipeline provided in the embodiment of the present application, as shown in FIG. Figure 3a As shown, the method is applied to any electronic device, as detailed below:

[0088] S301. Establish j one-dimensional convolutional neural network models with different structures, where j is an integer greater than 1.

[0089] Among them, the one-dimensional convolutional neural network model includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. By adjusting parameters such as the number of convolutional layers and pooling layers, the filter size of the convolutional layer, and the pooling window size, j one-dimensional convolutional neural network models with different structures are established.

[0090] S302: Obtain a damage dataset.

[0091] In some possible implementation manners, a simulation model of the underwater production system pipeline is established based on preset underwater production system pipeline parameters and preset damage types. Based on the simulation model of the underwater production system pipeline, a damage data set is obtained.

[0092] Specifically, the preset underwater production system pipeline parameters include geometric parameters and material parameters, and the preset damage types include no damage, crack, corrosion and fracture. Based on the preset underwater production system pipeline parameters and the preset damage types, the simulation model of the underwater production system pipeline is established. Based on a sine wave function modulated by a Hanning window, a preset period and a preset center frequency, a simulated excitation signal is determined. Based on the simulated excitation signal, a simulated ultrasonic guided wave is excited and transmitted to the simulation model of the underwater production system pipeline. The simulation model of the underwater production system pipeline is subjected to a very fine predefined processing. Simulated reflected ultrasonic guided waves are collected to obtain a loss data set.

[0093] S303, input the damage data set into j one-dimensional convolutional neural network models with different structures, train the j one-dimensional convolutional neural network models with different structures, and obtain j trained one-dimensional convolutional neural network models with different structures.

[0094] Specifically, the damage data set is input into the j one-dimensional convolutional neural network models with different structures. Based on a rectified linear unit (ReLU) activation function and a Softmax output layer activation function, the j one-dimensional convolutional neural network models with different structures are trained to obtain the j trained one-dimensional convolutional neural network models with different structures.

[0095] S304, obtain the classification accuracy, precision, recall and F1 value of the j trained one-dimensional convolutional neural network models with different structures.

[0096] The test data set in the loss data set is input into the j trained one-dimensional convolutional neural network models with different structures. The output results of the one-dimensional convolutional neural network models are compared with the test data set to obtain the classification accuracy, precision, recall and F1 value of the j trained one-dimensional convolutional neural network models with different structures. The F1 value is the harmonic mean of the precision and the recall.

[0097] S305, based on the classification accuracy, precision, recall and F1 value, select a one-dimensional convolutional neural network model that meets preset requirements as a trained one-dimensional convolutional neural network model.

[0098] Specifically, according to the actual needs of the underwater production system pipeline damage detection, preset requirements are determined, such as setting index thresholds according to detection focus, and then comparing and screening each one-dimensional convolutional neural network model index with the preset requirements. If multiple one-dimensional convolutional neural network models meet the requirements, the optimal one is selected according to the importance of each index; if no model meets the requirements, the one-dimensional convolutional neural network model needs to be retrained. Finally, the one-dimensional convolutional neural network model that meets the preset requirements is selected as the trained one-dimensional convolutional neural network model.

[0099] S306, receiving the first reflected ultrasonic guided wave signal of any underwater production system pipeline collected by the ultrasonic guided wave detection system.

[0100] The ultrasonic guided wave detection system includes an excitation signal source device and a piezoelectric transducer.

[0101] In one possible implementation, before receiving the first reflected ultrasonic guided wave signal of any underwater production system pipeline collected by the ultrasonic guided wave detection system, it includes: establishing a cylindrical coordinate system of the underwater production system pipeline cross section. Based on the cylindrical coordinate system of the underwater production system pipeline cross section, the wave equation and the dispersion equation of the underwater production system pipeline are established. Based on the wave equation and the dispersion equation, the excitation signal is determined. The excitation signal source device sends the excitation signal to the piezoelectric transducer. In response to the excitation signal, the piezoelectric transducer is triggered to emit an ultrasonic guided wave signal to the underwater production system pipeline to collect a reflected ultrasonic guided wave signal of the underwater production system pipeline.

[0102] Specifically, the cylindrical coordinate system of the pipeline cross section is established, and the parameters of the inner and outer diameters a and b, density p, elastic modulus E, and Poisson's ratio v of the pipeline are determined. By introducing displacement potential φ and ψ, the motion equation is solved to obtain the wave equation satisfied by the displacement potential variable, as shown in the following formula (1), including:

[0103]

[0104] Where φ is the scalar displacement potential; ψ is the vector displacement potential; c L is the longitudinal wave velocity; c T is the transverse wave velocity; t is time.

[0105] Further, the displacement potential is substituted into the boundary condition to obtain the homogeneous equation group about constants A1, A2, B1, and B2, and the relationship between the wave number k and the frequency ω is solved, that is, the dispersion equation, as shown in the following formula (2), including:

[0106] det[A1A2B1B2]=0 (2)

[0107] Among them, A1 is the first general solution coefficient of the scalar displacement potential; A2 is the second statistical coefficient of the scalar displacement potential; B1 is the first general solution coefficient of the vector displacement potential; B2 is the second general solution coefficient of the vector displacement potential.

[0108] Possibly, the dispersion curve of ultrasonic guided waves in underwater production system pipelines is as follows: Figure 3b and Figure 3c As shown, Figure 3b Schematic diagram of the group velocity dispersion curve of ultrasonic guided waves in the underwater production system pipeline provided by the embodiment of the present application, Figure 3c Schematic diagram of the phase velocity dispersion curve of ultrasonic guided waves in the underwater production system pipeline provided in an embodiment of the present application.

[0109] Based on the wave equation and dispersion equation, the group velocity and phase velocity dispersion curves of ultrasonic guided waves in the underwater production system pipeline are solved. Based on the group velocity and phase velocity dispersion curves, the frequency of the excitation signal is calculated to determine the excitation signal.

[0110] An excitation signal is sent to the piezoelectric transducer through the excitation signal source device. In response to the excitation signal, the piezoelectric transducer is triggered. The piezoelectric transducer is a key device based on the piezoelectric effect. After receiving the excitation signal, the piezoelectric material inside it will undergo electromechanical coupling and convert the electrical signal into mechanical vibration. This mechanical vibration is further emitted to the underwater production system pipeline in the form of ultrasonic guided waves. Ultrasonic guided waves propagate along a specific path in the pipeline. During the propagation process, once the ultrasonic guided waves encounter structural changes, damage, or the end of the pipeline, the ultrasonic guided waves will be reflected, such as Figure 3d As shown, Figure 3d A schematic diagram of the propagation of ultrasonic guided waves in a pipeline is provided in an embodiment of the present application. The ultrasonic guided waves emitted by the piezoelectric transducer propagate toward both ends of the pipeline. When they encounter a loss position in the pipeline, the ultrasonic guided waves will be reflected. At this time, the corresponding signal acquisition device is used to collect the ultrasonic guided wave signals reflected from the pipeline.

[0111] S307: Use a preset noise reduction algorithm to perform noise reduction processing on the first reflected ultrasonic guided wave signal to obtain a second reflected ultrasonic guided wave signal.

[0112] In one possible embodiment, the reflected ultrasonic guided wave signal is input into a first preset algorithm to decompose the reflected ultrasonic guided wave signal, and the output obtained is n signal components, where n is an integer greater than 1. The permutation entropy values ​​of the n signal components are calculated, and the signal components whose permutation entropy values ​​are less than a preset threshold are selected to obtain effective signal components. The signal components whose permutation entropy values ​​are greater than or equal to a preset threshold are selected to obtain noise signal components. The noise signal components are subjected to wavelet decomposition and reconstruction, and wavelet threshold denoising is performed to obtain noise-reduced signal components. The effective signal components and the noise-reduced signal components are merged to obtain the noise-reduced reflected ultrasonic guided wave signal.

[0113] The wavelet threshold denoising is used to indicate that a soft threshold function is used to perform denoising on the noise signal component.

[0114] Exemplarily, the first preset algorithm may be an improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) algorithm, and the signal component is an intrinsic mode function (IMF) component.

[0115] In one possible embodiment, before inputting the reflected ultrasonic guided wave signal into the first preset algorithm, the method includes: generating a first preset number of first and second parameters within a preset value range based on the second preset algorithm; combining the first and second parameters in pairs and calculating envelope entropy values ​​for the combinations; and selecting combinations whose envelope entropy values ​​are less than a first preset threshold to establish the first preset algorithm.

[0116] Exemplarily, the second preset algorithm is a Northern Goshawk Optimization (NGO) algorithm.

[0117] If possible, a combination with the smallest envelope entropy value is selected to establish a first preset algorithm.

[0118] S308. Divide the underwater production system pipeline into multiple pipeline position segments.

[0119] S309. Input the second reflected ultrasonic guided wave signal into the trained one-dimensional convolutional neural network model for the following processing: extract damage features related to the damage from the second reflected ultrasonic guided wave signal, wherein the damage features include at least one of time domain damage features and frequency domain damage features; calculate the damage probability of each pipeline position segment based on at least one of the time domain damage features and the frequency domain damage features, and output the damage probability of each pipeline position segment.

[0120] S310: Determine the pipeline location segment whose damage probability meets the preset conditions as the damage location of the underwater production system pipeline.

[0121] It should be noted that the specific implementation of steps S308 to S310 can refer to the specific implementation of steps S203 to S205, and will not be described in detail here.

[0122] In conclusion, the damage position identification method of the underwater production system pipeline provided by the embodiments of the present application adopts a preset noise reduction algorithm to perform noise reduction processing on the collected first reflected ultrasonic guided wave signal, which can remove noise interference in the signal, improve the quality and reliability of the signal, thereby providing more accurate data basis for subsequent damage feature extraction and analysis, and helping to improve the accuracy of damage identification. The one-dimensional convolutional neural network model can extract at least one of the time domain damage features and the frequency domain damage features from the second reflected ultrasonic guided wave signal, comprehensively utilize multiple features to determine the damage position of the pipeline, and can more comprehensively reflect the damage position of the pipeline. By dividing the pipeline into multiple pipeline position segments and using the one-dimensional convolutional neural network model to calculate the damage probability of each pipeline position segment, the damage position in the underwater production system pipeline can be more accurately located.

[0123] In addition, j one-dimensional convolutional neural network models with different structures are constructed, each model has a unique architecture, and multiple models with different structures can complement each other to reduce the risk of overfitting. The classification accuracy, precision, recall and F1 value of each model are obtained, which reflect the performance of the model from different angles. Based on these multi-dimensional indicators, the model that meets the preset requirements can be more accurately selected. Different types of damage data may have different features and distributions. By constructing multiple models with different structures and training and evaluating them, the model that best suits the specific type of damage data can be found.

[0124] Among them, by presetting the underwater production system pipeline parameters and the preset damage type, the damage of the underwater production system pipeline under various actual operating conditions can be accurately simulated. Using the established simulation model, damage data sets under various different working conditions can be generated systematically, which can greatly reduce the experimental cost and improve the research efficiency.

[0125] Further, a cylindrical coordinate system of the cross section of the underwater production system pipeline is established, which can more closely describe the physical properties of the pipeline according to its geometric shape. The wave equation and the dispersion equation of the underwater production system pipeline are established based on the cylindrical coordinate system, which can deeply understand the propagation law of ultrasonic guided waves in the pipeline from a theoretical level. The excitation signal is determined according to the wave equation and the dispersion equation, which ensures the pertinence and effectiveness of the excitation signal. The excitation signal source device sends the excitation signal to the piezoelectric transducer, and the piezoelectric transducer emits the ultrasonic guided wave signal to collect the reflected ultrasonic guided wave signal, realizing a reliable signal excitation and collection process.

[0126] Furthermore, the reflected ultrasonic guided wave signal is input into the first preset algorithm for decomposition to obtain n signal components. This decomposition method can split the complex reflected ultrasonic guided wave signal into multiple relatively simple components, which helps to analyze the characteristics of the signal more carefully. By calculating the permutation entropy value of the n signal components and selecting the effective signal component and the noise signal component according to the preset threshold, an effective distinction between the signal and the noise is achieved. The noise signal component is subjected to wavelet decomposition and reconstruction, and the wavelet threshold denoising method is used to effectively remove the noise. The effective signal component and the denoised signal component are merged to obtain the denoised reflected ultrasonic guided wave signal, which significantly improves the quality of the signal.

[0127] Furthermore, by generating a first preset number of first and second parameters within a preset numerical range based on a second preset algorithm, a systematic search of the possible parameter space can be performed. This helps find the optimal or more optimal parameter combination to adapt to different underwater production system pipeline inspection scenarios and the characteristics of reflected ultrasonic guided wave signals, thereby improving the adaptability and generalization capabilities of the algorithm. Calculating the envelope entropy values ​​of each pair of first and second parameters and selecting combinations with envelope entropy values ​​less than a first preset threshold to establish the first preset algorithm provides an effective parameter selection criterion. Using a screened parameter combination to establish the first preset algorithm can optimize the algorithm's performance.

[0128] Figure 4 A schematic diagram of the structure of a device for identifying damaged locations of pipelines in an underwater production system provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the damage location identification device 40 for an underwater production system pipeline provided in this embodiment includes: a receiving module 401 , a noise reduction module 402 , a processing module 403 and a determination module 404 .

[0129] The receiving module 401 is configured to receive a first reflected ultrasonic guided wave signal from any underwater production system pipeline collected by the ultrasonic guided wave detection system.

[0130] The noise reduction module 402 is configured to perform noise reduction processing on the first reflected ultrasonic guided wave signal by using a preset noise reduction algorithm to obtain a second reflected ultrasonic guided wave signal.

[0131] The processing module 403 is used to divide the underwater production system pipeline into multiple pipeline position segments.

[0132] The processing module 403 is also used to input the second reflected ultrasonic guided wave signal into the trained one-dimensional convolutional neural network model for the following processing: extracting damage features related to the damage from the second reflected ultrasonic guided wave signal, wherein the damage features include at least one of a time domain damage feature and a frequency domain damage feature; based on at least one of the time domain damage feature and the frequency domain damage feature, calculating the damage probability of each pipeline position segment, and outputting the damage probability of each pipeline position segment.

[0133] The determining module 404 is configured to determine a pipe position segment, in which the damage probability meets the preset condition, as a damage position of the underwater production system pipe.

[0134] In a possible implementation, the ultrasonic guided wave detection system includes an excitation signal source device and a piezoelectric transducer, and the receiving module 401 is specifically configured to:

[0135] establish a cylindrical coordinate system of a cross section of the underwater production system pipe;

[0136] based on the cylindrical coordinate system of the cross section of the underwater production system pipe, establish a wave equation and a dispersion equation of the underwater production system pipe;

[0137] determine the excitation signal based on the wave equation and the dispersion equation;

[0138] send the excitation signal to the piezoelectric transducer through the excitation signal source device;

[0139] in response to the excitation signal, trigger the piezoelectric transducer to emit an ultrasonic guided wave signal to the underwater production system pipe to collect a reflected ultrasonic guided wave signal of the underwater production system pipe.

[0140] In a possible implementation, the noise reduction module 402 is specifically configured to:

[0141] input the reflected ultrasonic guided wave signal into a first preset algorithm to decompose the reflected ultrasonic guided wave signal, and obtain n signal components as output, where n is an integer greater than 1;

[0142] calculate permutation entropy values of the n signal components;

[0143] select a signal component with a permutation entropy value less than a preset threshold value to obtain an effective signal component;

[0144] select a signal component with a permutation entropy value greater than or equal to the preset threshold value to obtain a noise signal component;

[0145] perform wavelet decomposition and reconstruction on the noise signal component, and perform wavelet threshold noise reduction to obtain a noise-reduced signal component;

[0146] merge the effective signal component and the noise-reduced signal component to obtain a noise-reduced reflected ultrasonic guided wave signal.

[0147] In a possible implementation, the noise reduction module 402 is specifically configured to:

[0148] based on a second preset algorithm, generate a first preset number of first parameters and second parameters within a preset numerical range;

[0149] combine the first parameters and the second parameters two by two and calculate envelope entropy values of the combinations;

[0150] A combination whose envelope entropy value is less than a first preset threshold is selected to establish a first preset algorithm.

[0151] In a possible implementation, the processing module 403 is specifically configured to:

[0152] Establish j one-dimensional convolutional neural network models with different structures, where j is an integer greater than 1;

[0153] Obtain damage dataset;

[0154] Inputting the damage dataset into j one-dimensional convolutional neural network models with different structures, training the j one-dimensional convolutional neural network models with different structures to obtain j trained one-dimensional convolutional neural network models with different structures;

[0155] Obtain the classification accuracy, precision, recall, and F1 value of j trained one-dimensional convolutional neural network models with different structures;

[0156] Based on the classification accuracy, precision, recall rate and F1 value, a one-dimensional convolutional neural network model that meets the preset requirements is selected and determined as the trained one-dimensional convolutional neural network model.

[0157] In a possible implementation, the processing module 403 is specifically configured to:

[0158] Establish a simulation model of the underwater production system pipeline based on preset underwater production system pipeline parameters and preset damage types;

[0159] A damage dataset is obtained based on a simulation model of a subsea production system pipeline.

[0160] The device for identifying the damaged position of an underwater production system pipeline provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effects are similar, and are not described in detail in this embodiment.

[0161] Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the electronic device 50 further includes a communication component 503. The processor 501, the memory 502 and the communication component 503 are connected via a bus.

[0162] In a specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that the at least one processor 501 performs the above method.

[0163] The specific implementation process of the processor 501 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0164] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules in the processor.

[0165] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0166] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be classified into address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0167] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0168] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0169] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0170] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in a device as discrete components.

[0171] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0172] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0173] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0174] If the function 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, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0175] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0176] Finally, it should be noted that those skilled in the art will readily identify other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

Claims

1. A method for identifying damage locations of underwater production system pipelines, characterized in that: include: Receiving a first reflected ultrasonic guided wave signal of any underwater production system pipeline collected by an ultrasonic guided wave detection system; Using a preset noise reduction algorithm, performing noise reduction processing on the first reflected ultrasonic guided wave signal to obtain a second reflected ultrasonic guided wave signal; Dividing the underwater production system pipeline into a plurality of pipeline position sections; Inputting the second reflected ultrasonic guided wave signal into a trained one-dimensional convolutional neural network model to perform the following processing: extracting damage features related to the damage from the second reflected ultrasonic guided wave signal, wherein the damage features include at least one of a time-domain damage feature and a frequency-domain damage feature; calculating the damage probability of each pipeline location segment based on at least one of the time-domain damage feature and the frequency-domain damage feature, and outputting the damage probability of each pipeline location segment; The pipeline position segment where the damage probability meets a preset condition is determined as the damage position of the underwater production system pipeline.

2. The method according to claim 1, characterized in that The ultrasonic guided wave detection system includes an excitation signal source device and a piezoelectric transducer; Accordingly, before receiving the first reflected ultrasonic guided wave signal of any underwater production system pipeline collected by the ultrasonic guided wave detection system, the method includes: Establish a cylindrical coordinate system for the cross section of the underwater production system pipeline; Establishing a wave equation and a dispersion equation for the underwater production system pipeline based on a cylindrical coordinate system of a cross section of the underwater production system pipeline; Determining an excitation signal based on the wave equation and the dispersion equation; Sending an excitation signal to the piezoelectric transducer via an excitation signal source device; In response to the excitation signal, the piezoelectric transducer is triggered to transmit an ultrasonic guided wave signal to the underwater production system pipeline to collect the reflected ultrasonic guided wave signal of the underwater production system pipeline.

3. The method according to claim 1, characterized in that The method of performing noise reduction processing on the reflected ultrasonic guided wave signal by using a preset noise reduction algorithm to obtain a noise-reduced reflected ultrasonic guided wave signal includes: Inputting the reflected ultrasonic guided wave signal into a first preset algorithm to decompose the reflected ultrasonic guided wave signal, and obtaining an output as n signal components, where n is an integer greater than 1; Calculate the permutation entropy of n signal components; Select the signal component whose permutation entropy value is less than a preset threshold to obtain a valid signal component; Selecting the signal component whose permutation entropy value is greater than or equal to a preset threshold to obtain the noise signal component; Performing wavelet decomposition and reconstruction on the noise signal component, and performing wavelet threshold noise reduction to obtain a noise reduction signal component; The effective signal component and the noise reduction signal component are combined to obtain a noise-reduced reflected ultrasonic guided wave signal.

4. The method according to claim 3, characterized in that Before inputting the reflected ultrasonic guided wave signal into the first preset algorithm, the method includes: Based on a second preset algorithm, generating a first preset number of first parameters and second parameters within a preset value range; Combining the first parameters and the second parameters in pairs and calculating the envelope entropy value of the combination; A combination whose envelope entropy value is less than a first preset threshold is selected to establish the first preset algorithm.

5. The method according to claim 1, wherein Also includes: Establish j one-dimensional convolutional neural network models with different structures, where j is an integer greater than 1; Obtain damage dataset; Inputting the damage data set into the j one-dimensional convolutional neural network models with different structures, and training the j one-dimensional convolutional neural network models with different structures to obtain j trained one-dimensional convolutional neural network models with different structures; Obtain the classification accuracy, precision, recall, and F1 value of j trained one-dimensional convolutional neural network models with different structures; Based on the classification accuracy, precision, recall rate and F1 value, a one-dimensional convolutional neural network model that meets the preset requirements is selected and determined as the trained one-dimensional convolutional neural network model.

6. The method according to claim 5, characterized in that The obtaining of the damage data set includes: Establish a simulation model of the underwater production system pipeline based on preset underwater production system pipeline parameters and preset damage types; A damage data set is obtained based on the underwater production system pipeline simulation model.

7. A device for identifying damaged locations of pipelines in underwater production systems, characterized in that: include: A receiving module, configured to receive a first reflected ultrasonic guided wave signal of any underwater production system pipeline collected by the ultrasonic guided wave detection system; a noise reduction module, configured to perform noise reduction processing on the first reflected ultrasonic guided wave signal using a preset noise reduction algorithm to obtain a second reflected ultrasonic guided wave signal; a processing module, configured to divide the underwater production system pipeline into a plurality of pipeline position segments; The processing module is further configured to input the second reflected ultrasonic guided wave signal into a trained one-dimensional convolutional neural network model to perform the following processing: extracting damage features related to damage from the second reflected ultrasonic guided wave signal, wherein the damage features include at least one of a time domain damage feature and a frequency domain damage feature; and calculating a damage probability for each pipeline location segment based on at least one of the time domain damage feature and the frequency domain damage feature, and outputting the damage probability for each pipeline location segment; The determination module is used to determine the pipeline position segment where the damage probability meets the preset conditions as the damage position of the underwater production system pipeline.

8. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images