Baseline detection system and method for gathering and transportation pipelines based on multi-technology fusion

Through artificial intelligence data analysis technology combined with global navigation satellite system and ultrasonic detector, the shortcomings of traditional detection methods cannot detect and locate the collection and transportation pipeline problems in a timely manner, and efficient detection and positioning of the pipeline baseline state is achieved, ensuring the pipeline's Safe and stable.

CN118731172BActive Publication Date: 2024-11-22KARAMAY BEST TECH DEV CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411225183.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-11-22
Estimated Expiration
2044-09-03

AI Technical Summary

Technical Problem

The traditional baseline detection method of collecting and transport pipelines cannot comprehensively and promptly discover potential problems in the pipeline, and it is difficult to accurately locate abnormal points, resulting in delays in maintenance measures and further expanding pipeline problems.

Method used

The global navigation satellite system is used to collect detection point position coordinate data of the pipeline baseline, combine the signals collected by ultrasonic detectors, and perform CEEMDAN decomposition, feature extraction and aggregation to identify pipeline cracks and leakages through data analysis algorithms based on artificial intelligence and signal processing. For problems such as point and corrosion, return the position coordinate data of the abnormal point.

Benefits of technology

Timely detection and positioning of the baseline status of the collection and transportation pipelines is realized, ensuring the safety and stability of the pipelines, and reducing maintenance delays and resource consumption.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118731172B_ABST
    Figure CN118731172B_ABST
Patent Text Reader

Abstract

The present application discloses a gathering and transportation pipeline baseline detection system and method based on multi-technology fusion, which collects the position coordinate data of multiple detection points of the gathering and transportation pipeline baseline through the global navigation satellite system, and uses this as the basic data of the detection point for subsequent return of abnormal detection points, then collects the pipeline ultrasonic receiving signal at each detection point through an ultrasonic detector, and introduces a data analysis algorithm based on artificial intelligence and signal processing at the back end to analyze the ultrasonic receiving signal, so as to detect the pipeline baseline status, so as to identify whether there are problems such as pipeline cracks, leakage points and corrosion, and return the position coordinate data of the abnormal point when the pipeline baseline abnormal condition is detected, so as to facilitate the subsequent timely repair of pipeline abnormalities and ensure the safety and stability of the gathering and transportation pipeline baseline.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of intelligent detection, and more specifically, to a gathering and transportation pipeline baseline detection system and method based on multi-technology fusion. Background Art

[0002] As an important infrastructure for the transportation of oil, natural gas and other fluids, the safety and reliability of gathering and transportation pipelines are directly related to the stability of energy supply and environmental protection. With the acceleration of industrialization, the aging, corrosion and damage caused by external factors of pipelines have become increasingly prominent, resulting in frequent leakage and accidents, which have brought serious impacts on the environment and society. Therefore, it is very important to conduct effective safety inspections on the baseline of gathering and transportation pipelines in order to timely discover and deal with safety hazards.

[0003] The main safety hazards of pipelines include cracks, corrosion and leakage, which not only lead to material losses, but also may cause environmental pollution and personal injury. Traditional baseline detection methods for gathering and transportation pipelines, such as visual inspection and conventional mechanical detection methods, often fail to fully and timely detect potential problems in pipelines. In addition, after discovering abnormal problems and safety hazards in pipelines, traditional detection schemes also find it difficult to accurately locate abnormal points, making it difficult to carry out subsequent maintenance measures in a timely manner, thus further expanding the baseline problems of gathering and transportation pipelines.

[0004] Therefore, an optimized baseline detection system for gathering and transportation pipelines is desired. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a gathering and transportation pipeline baseline detection system and method based on multi-technology fusion, which collects the position coordinate data of multiple detection points of the gathering and transportation pipeline baseline through the global navigation satellite system, and uses this as the basic data of the detection point for subsequent return of abnormal detection points, and then collects the pipeline ultrasonic receiving signal at each detection point through an ultrasonic detector, and introduces a data analysis algorithm based on artificial intelligence and signal processing at the back end to analyze the ultrasonic receiving signal, so as to detect the pipeline baseline status, to identify whether there are pipeline cracks, leakage points, corrosion and other problems, and return the position coordinate data of the abnormal point when the pipeline baseline abnormal condition is detected, so as to facilitate the subsequent timely repair of pipeline abnormalities and ensure the safety and stability of the gathering and transportation pipeline baseline.

[0006] According to one aspect of the present application, a gathering and transportation pipeline baseline detection system based on multi-technology fusion is provided, which includes: a gathering and transportation pipeline baseline detection point position coordinate acquisition module, which is used to obtain the position coordinate data of multiple detection points of the detected gathering and transportation pipeline baseline collected by the global navigation satellite system; a pipeline ultrasonic signal receiving module, which is used to obtain the pipeline ultrasonic receiving signal collected by the ultrasonic detector at the kth detection point; a signal decomposition module, which is used to perform CEEMDAN decomposition on the pipeline ultrasonic receiving signal to obtain a sequence of ultrasonic signal IMF components; an ultrasonic signal component waveform semantic feature extraction module, which is used to perform ultrasonic waveform feature extraction on each ultrasonic signal IMF component in the sequence of ultrasonic signal IMF components to obtain a sequence of ultrasonic IMF signal component waveform semantic feature vectors; ultrasonic signal components A waveform semantic selection and enhancement module is used to pass the sequence of ultrasonic IMF signal component waveform semantic feature vectors through a feature reverse attention selection and enhancement module based on the self-supervised cluster center to obtain a sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors; an ultrasonic IMF signal component waveform semantic aggregation module is used to input the sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors into a feature aggregation network based on feature energy local significance gating to obtain ultrasonic IMF signal component waveform aggregation semantic feature vectors; a gathering and transportation pipeline baseline inspection anomaly detection module is used to determine a detection result based on the ultrasonic IMF signal component waveform aggregation semantic feature vector, the detection result is used to indicate whether there is an anomaly at the kth detection point, and determine whether to return the position coordinate data of the kth detection point based on the detection result.

[0007] According to another aspect of the present application, a method for detecting a baseline of a gathering and transportation pipeline based on multi-technology fusion is provided, which includes: obtaining position coordinate data of multiple detection points of the baseline of the gathering and transportation pipeline to be detected collected by a global navigation satellite system; obtaining a pipeline ultrasonic receiving signal collected by an ultrasonic detector at the kth detection point; performing CEEMDAN decomposition on the pipeline ultrasonic receiving signal to obtain a sequence of ultrasonic signal IMF components; performing ultrasonic waveform feature extraction on each ultrasonic signal IMF component in the sequence of ultrasonic signal IMF components to obtain a sequence of ultrasonic IMF signal component waveform semantic feature vectors; passing the sequence of ultrasonic IMF signal component waveform semantic feature vectors through a feature reverse attention selection enhancement module based on the center of a self-supervised cluster to obtain a sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors; inputting the sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors into a feature aggregation network based on feature energy local significance gating to obtain an ultrasonic IMF signal component waveform aggregation semantic feature vector; determining a detection result based on the ultrasonic IMF signal component waveform aggregation semantic feature vector, the detection result being used to indicate whether there is an abnormality at the kth detection point, and determining whether to return the position coordinate data of the kth detection point based on the detection result.

[0008] Compared with the prior art, the present application provides a gathering and transportation pipeline baseline detection system and method based on multi-technology fusion, which collects the position coordinate data of multiple detection points of the gathering and transportation pipeline baseline through the global navigation satellite system, and uses this as the basic data of the detection point for subsequent return of abnormal detection points, then collects the pipeline ultrasonic receiving signal at each detection point through an ultrasonic detector, and introduces a data analysis algorithm based on artificial intelligence and signal processing at the back end to analyze the ultrasonic receiving signal, so as to detect the pipeline baseline status, so as to identify whether there are pipeline cracks, leakage points, corrosion and other problems, and return the position coordinate data of the abnormal point when the pipeline baseline abnormal condition is detected, so as to facilitate the subsequent timely repair of pipeline abnormalities and ensure the safety and stability of the gathering and transportation pipeline baseline. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0010] Figure 1 It is a block diagram of a gathering and transportation pipeline baseline detection system based on multi-technology fusion according to an embodiment of the present application.

[0011] Figure 2 It is a data flow diagram of a gathering and transportation pipeline baseline detection system based on multi-technology fusion according to an embodiment of the present application.

[0012] Figure 3 It is a flow chart of a gathering and transportation pipeline baseline detection method based on multi-technology fusion according to an embodiment of the present application. DETAILED DESCRIPTION

[0013] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0014] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0015] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0016] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0017] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0018] Traditional baseline inspection methods for gathering and transportation pipelines, such as visual inspection and conventional mechanical inspection methods, often fail to fully and timely discover potential problems in pipelines. In addition, after discovering abnormal problems and safety hazards in pipelines, traditional inspection schemes also have difficulty accurately locating abnormal points, making it difficult to carry out subsequent maintenance measures in a timely manner, thereby further expanding the baseline problems of gathering and transportation pipelines. Therefore, an optimized baseline inspection system for gathering and transportation pipelines is desired.

[0019] It should be understood that GNSS is a global navigation satellite system. The advancement of GNSS technology makes it possible to obtain high-precision geographic location information in real time. Obtaining the location coordinates of multiple detection points of the pipeline baseline through GNSS can not only provide the location data of the baseline test points of the gathering and transportation pipeline, but also realize the subsequent spatial positioning of abnormal points in the pipeline. Ultrasonic detection technology is a non-destructive detection method. By emitting ultrasonic waves and receiving their reflected signals in the material, it can detect defects inside the material, such as cracks and voids. In pipeline detection, ultrasonic technology can penetrate the pipeline material and detect defects in the pipeline wall. It can also effectively identify abnormal conditions such as cracks and corrosion on the pipeline surface, which is crucial for early detection of potential problems.

[0020] In the technical solution of the present application, a gathering and transportation pipeline baseline detection system based on multi-technology fusion is proposed. Figure 1 It is a block diagram of a gathering and transportation pipeline baseline detection system based on multi-technology fusion according to an embodiment of the present application. Figure 2 FIG. 1 is a data flow diagram of a baseline detection system for a gathering and transportation pipeline based on multi-technology fusion according to an embodiment of the present application. Figure 1 and Figure 2As shown, according to an embodiment of the present application, a gathering and transportation pipeline baseline detection system 300 based on multi-technology fusion includes: a gathering and transportation pipeline baseline detection point position coordinate acquisition module 310, which is used to obtain the position coordinate data of multiple detection points of the detected gathering and transportation pipeline baseline collected by the global navigation satellite system; a pipeline ultrasonic signal receiving module 320, which is used to obtain the pipeline ultrasonic receiving signal collected by the ultrasonic detector at the kth detection point; a signal decomposition module 330, which is used to perform CEEMDAN decomposition on the pipeline ultrasonic receiving signal to obtain a sequence of ultrasonic signal IMF components; an ultrasonic signal component waveform semantic feature extraction module 340, which is used to perform ultrasonic waveform feature extraction on each ultrasonic signal IMF component in the sequence of ultrasonic signal IMF components to obtain a sequence of ultrasonic IMF signal component waveform semantic feature vectors; an ultrasonic ... signal component waveform semantic feature vectors; an ultrasonic signal decomposition module 330, which is used to perform CEEMDAN decomposition on the pipeline ultrasonic receiving signal to obtain a sequence of ultrasonic signal IMF components; an ultrasonic signal decomposition module 330, which is used to perform CEEMDAN decomposition on the pipeline ultrasonic receiving signal to obtain a sequence of ultrasonic signal IMF components; an ultrasonic signal decomposition module 330, which is used to perform CEEMDAN decomposition on the pipeline ultrasonic receiving signal to obtain A waveform semantic selection and enhancement module 350 is used to pass the sequence of ultrasonic IMF signal component waveform semantic feature vectors through a feature reverse attention selection and enhancement module based on the self-supervised cluster center to obtain a sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors; an ultrasonic IMF signal component waveform semantic aggregation module 360 ​​is used to input the sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors into a feature aggregation network based on feature energy local significance gating to obtain ultrasonic IMF signal component waveform aggregation semantic feature vectors; a gathering and transportation pipeline baseline inspection anomaly detection module 370 is used to determine a detection result based on the ultrasonic IMF signal component waveform aggregation semantic feature vector, the detection result is used to indicate whether there is an anomaly at the kth detection point, and determine whether to return the position coordinate data of the kth detection point based on the detection result.

[0021] In particular, the gathering pipeline baseline detection point position coordinate acquisition module 310 and the pipeline ultrasonic signal receiving module 320 are used to obtain the position coordinate data of multiple detection points of the detected gathering pipeline baseline collected by the global navigation satellite system; and obtain the pipeline ultrasonic receiving signal collected by the ultrasonic detector at the kth detection point. The global navigation satellite system is a satellite constellation that transmits signals to receivers on the earth to determine their position, speed and time. The ultrasonic detector is a device that uses ultrasonic pulses to detect and image objects or materials.

[0022] In particular, the signal decomposition module 330 is used to perform CEEMDAN decomposition on the pipeline ultrasonic receiving signal to obtain a sequence of IMF components of the ultrasonic signal. It should be understood that CEEMDAN is an effective signal denoising technology that can decompose complex ultrasonic receiving signals into multiple intrinsic mode functions (IMFs). These IMF components can better reflect the local characteristics of the ultrasonic receiving signal, thereby eliminating the interference of noise on subsequent analysis. In addition, through signal decomposition, different frequency components in the ultrasonic receiving signal can be separated, which is convenient for analysis of different frequency characteristics. This helps to identify problems and safety hazards such as cracks, corrosion and leakage in pipelines.

[0023] In particular, the ultrasonic signal component waveform semantic feature extraction module 340 is used to extract ultrasonic waveform features from each ultrasonic signal IMF component in the sequence of ultrasonic signal IMF components to obtain a sequence of ultrasonic IMF signal component waveform semantic feature vectors. In a specific example of the present application, each ultrasonic signal IMF component in the sequence of ultrasonic signal IMF components is respectively passed through an ultrasonic waveform feature extractor based on a dilated convolutional neural network model to obtain a sequence of ultrasonic IMF signal component waveform semantic feature vectors. That is, each ultrasonic signal IMF component in the sequence of ultrasonic signal IMF components is respectively subjected to feature mining in an ultrasonic waveform feature extractor based on a dilated convolutional neural network model to extract waveform semantic feature information of each ultrasonic signal IMF component, thereby obtaining a sequence of ultrasonic IMF signal component waveform semantic feature vectors. The ultrasonic IMF signal component waveform semantic feature vector extracted by the dilated convolutional neural network can better represent the essential information of the ultrasonic component signal, which is crucial for subsequent classification and anomaly detection. Compared with the traditional manual feature extraction method, the dilated convolutional neural network can adaptively optimize the feature representation and improve the robustness of the model.

[0024] In particular, the ultrasonic signal component waveform semantic selection and enhancement module 350 is used to pass the sequence of ultrasonic IMF signal component waveform semantic feature vectors through a feature reverse attention selection and enhancement module based on the self-supervised cluster center to obtain a sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors. Considering that in the waveform semantics of multiple ultrasonic IMF signal components, not all signal component waveform features are equally important for anomaly detection. Therefore, in order to improve the expressiveness of ultrasonic waveform semantic features and provide a basis for subsequent pipeline anomaly detection, it is necessary to evaluate the importance of each ultrasonic IMF signal component waveform semantics in order to select features related to subsequent anomaly detection tasks, that is, focus on those features that are more influential on pipeline status detection, thereby reducing the interference of redundant information and improving the detection accuracy of the model. Based on this, in the technical solution of the present application, the sequence of ultrasonic IMF signal component waveform semantic feature vectors is passed through a feature reverse attention selection and enhancement module based on the self-supervised cluster center to obtain a sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors. The feature reverse attention selection and reinforcement module based on the self-supervised cluster center is a feature enhancement mechanism based on self-supervised learning and reverse attention mechanism. The self-supervised learning method allows the model to learn from the data generated by itself without a large amount of labeled data, thereby improving the flexibility and adaptability of the selection of semantic features of ultrasonic IMF signal component waveforms. The reverse attention mechanism can enhance those features that are more critical in the subsequent pipeline anomaly detection tasks, so that the feature vector output in the end has more recognition ability and feature expression ability. This reinforcement not only improves the robustness of the model, but also helps the model better capture the subtle features of pipeline anomalies, which helps to identify the subtle abnormal state of the pipeline. Therefore, through the processing of the feature reverse attention selection and reinforcement module based on the self-supervised cluster center, the model can more accurately capture the useful information in the semantics of each ultrasonic IMF signal component waveform through fine feature engineering and adaptive weight adjustment, while ignoring insignificant noise, thereby achieving better performance in various complex pipeline anomaly detection tasks.

[0025] In an embodiment of the present application, the sequence of ultrasonic IMF signal component waveform semantic feature vectors is subjected to a feature reverse attention selection enhancement module based on a self-supervised cluster center to obtain a sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors, including: performing self-supervised clustering processing based on energy measurement on each ultrasonic IMF signal component waveform semantic feature vector in the sequence of ultrasonic IMF signal component waveform semantic feature vectors to obtain a self-supervised cluster center representation vector; calculating the anti-correlation coefficient between each ultrasonic IMF signal component waveform semantic feature vector in the sequence of ultrasonic IMF signal component waveform semantic feature vectors and the self-supervised cluster center representation vector to obtain a sequence of ultrasonic IMF signal component waveform semantic anti-correlation coefficients; inputting the sequence of ultrasonic IMF signal component waveform semantic anti-correlation coefficients into a Sigmoid activation function to obtain a normalized The invention relates to a method for obtaining a sequence of ultrasonic IMF signal component waveform semantic anti-correlation weight coefficients; using each normalized ultrasonic IMF signal component waveform semantic anti-correlation weight coefficient in the sequence of normalized ultrasonic IMF signal component waveform semantic anti-correlation weight coefficients as a weight, and weighting each ultrasonic IMF signal component waveform semantic feature vector in the sequence of ultrasonic IMF signal component waveform semantic feature vectors to obtain a sequence of ultrasonic IMF signal component waveform semantic anti-enhancement feature vectors; calculating the positional difference between each group of corresponding ultrasonic IMF signal component waveform semantic feature vectors and ultrasonic IMF signal component waveform semantic anti-enhancement feature vectors in the sequence of ultrasonic IMF signal component waveform semantic anti-enhancement feature vectors to obtain a sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors.

[0026] Among them, the process of performing self-supervised clustering processing based on energy measurement on each ultrasonic IMF signal component waveform semantic feature vector in the sequence of ultrasonic IMF signal component waveform semantic feature vectors to obtain a self-supervised cluster center representation vector includes: calculating the maximum value, average value and variance of each ultrasonic IMF signal component waveform semantic feature vector in the sequence of ultrasonic IMF signal component waveform semantic feature vectors to obtain a sequence of ultrasonic IMF signal component waveform semantic maximum values, a sequence of ultrasonic IMF signal component waveform semantic average values ​​and a sequence of ultrasonic IMF signal component waveform semantic variances; respectively calculating the sum of each ultrasonic IMF signal component waveform semantic variance and the bias term in the sequence of ultrasonic IMF signal component waveform semantic variances and then multiplying the sum with a constant 4 to obtain a sequence of energy statistical factors of the first ultrasonic IMF signal component waveform semantic node; and performing self-supervised clustering processing on each ultrasonic IMF signal component waveform semantic feature vector in the sequence of ultrasonic IMF signal component waveform semantic feature vectors. The sequence of waveform semantic variances and the bias term are modulated by a factor of two to obtain a sequence of waveform semantic variances of a factor of two-modulated ultrasonic IMF signal component and a double-modulated regularization term hyperparameter; the square of the difference between the ultrasonic IMF signal component waveform semantic maximum value and the ultrasonic IMF signal component waveform semantic average value corresponding to the sequence of waveform semantic maximum values ​​of the ultrasonic IMF signal component and the sequence of waveform semantic average values ​​of the ultrasonic IMF signal component is calculated, and then the square of the difference is added with the double-modulated regularization term hyperparameter and the corresponding waveform semantic variance of the factor of two-modulated ultrasonic IMF signal component to obtain a sequence of energy statistical factors of waveform semantic nodes of the second ultrasonic IMF signal component; the positional division between the sequence of energy statistical factors of waveform semantic nodes of the first ultrasonic IMF signal component and the sequence of energy statistical factors of waveform semantic nodes of the second ultrasonic IMF signal component is calculated to obtain a sequence of energy measurement coefficients; and the energy statistical factors of waveform semantic nodes of the second ultrasonic IMF signal component are calculated by using After the function normalizes the sequence of energy measurement coefficients, it multiplies the sequence of waveform semantic feature vectors of the ultrasonic IMF signal component by position points to obtain the self-supervised cluster center representation vector.

[0027] More specifically, the process of calculating the anti-correlation coefficient between each ultrasonic IMF signal component waveform semantic feature vector in the sequence of ultrasonic IMF signal component waveform semantic feature vectors and the self-supervised cluster center representation vector to obtain a sequence of ultrasonic IMF signal component waveform semantic anti-correlation coefficients includes: calculating the difference vector between the ultrasonic IMF signal component waveform semantic feature vector and the self-supervised cluster center representation vector to obtain an ultrasonic IMF signal component waveform semantic offset vector; calculating the covariance matrix between the ultrasonic IMF signal component waveform semantic feature vector and the self-supervised cluster center representation vector to obtain an ultrasonic IMF signal component waveform semantic offset covariance matrix; calculating the matrix division between the transposed vector of the ultrasonic IMF signal component waveform semantic offset vector and the ultrasonic IMF signal component waveform semantic offset covariance matrix to obtain an ultrasonic IMF signal component waveform semantic offset degree feature representation vector; calculating the square root of the anti-correlation difference value obtained after the vector multiplication between the ultrasonic IMF signal component waveform semantic offset degree feature representation vector and the ultrasonic IMF signal component waveform semantic offset vector to obtain the ultrasonic IMF signal component waveform semantic anti-correlation coefficient.

[0028] In summary, in the above embodiment, the sequence of the ultrasonic IMF signal component waveform semantic feature vectors is passed through a feature reverse attention selection enhancement module based on a self-supervised cluster center to obtain a sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors, including: the sequence of the ultrasonic IMF signal component waveform semantic feature vectors is passed through the feature reverse attention selection enhancement module based on a self-supervised cluster center with the following feature selection enhancement formula to obtain the sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors; wherein the feature selection enhancement formula is: ;in, is a sequence of waveform semantic feature vectors of the ultrasonic IMF signal components, is the first in the sequence of semantic feature vectors of the ultrasonic IMF signal component waveform The waveform semantic feature vectors of ultrasonic IMF signal components, is the first in the sequence of semantic feature vectors of the ultrasonic IMF signal component waveform The waveform semantic feature vectors of ultrasonic IMF signal components, and Indicates the The mean and variance of the waveform semantic feature vector of ultrasonic IMF signal components, is the bias term, Indicates the The maximum value of the waveform semantic feature vector of ultrasonic IMF signal components, is the energy measurement coefficient, for function, is the number of vectors in the sequence of the waveform semantic feature vectors of the ultrasonic IMF signal component, is the self-supervised cluster center representation vector, For the said The covariance matrix between the waveform semantic feature vectors of ultrasonic IMF signal components and the self-supervised cluster center representation vector, For the said The anti-correlation coefficient corresponding to the semantic feature vector of the ultrasonic IMF signal component waveform is for function, is the first in the sequence of semantic anti-correlation weight coefficients of the normalized ultrasonic IMF signal component waveform Normalized ultrasonic IMF signal component waveform semantic anti-correlation weight coefficient, is the first in the sequence of the semantic anti-correlation weight coefficients of the normalized ultrasonic IMF signal component waveform Normalized ultrasonic IMF signal component waveform semantic anti-correlation weight coefficient, is the sequence of semantic anti-enhancement feature vectors of ultrasonic IMF signal component waveforms, For positional subtraction, is a sequence of semantic feature vectors of the waveform of the enhanced ultrasonic IMF signal component.

[0029] In particular, the ultrasonic IMF signal component waveform semantic aggregation module 360 ​​is used to input the sequence of the enhanced ultrasonic IMF signal component waveform semantic feature vectors into a feature aggregation network based on feature energy local significance gating to obtain ultrasonic IMF signal component waveform aggregation semantic feature vectors. It should be understood that since each enhanced ultrasonic IMF signal component waveform semantic feature vector in the sequence of the enhanced ultrasonic IMF signal component waveform semantic feature vectors respectively contains waveform semantic feature information about each ultrasonic IMF signal component after key feature enhancement expression, in pipeline baseline detection, the waveform semantic feature of a single signal component may not be sufficient to fully describe the state of the ultrasonic signal, and thus cannot reflect the abnormal situation of the pipeline. Based on this, in the technical solution of the present application, the sequence of the enhanced ultrasonic IMF signal component waveform semantic feature vectors is further input into a feature aggregation network based on feature energy local significance gating to obtain ultrasonic IMF signal component waveform aggregation semantic feature vectors. It should be understood that the feature energy local significance gating mechanism can dynamically adjust the weight of the feature so that the model can focus on those ultrasonic IMF signal component waveform features with higher energy and more contribution to abnormality detection. This mechanism can filter out noise and redundant information and improve the effectiveness of features. Therefore, through the processing of the feature aggregation network based on the local significance gating of feature energy, the local energy distribution of each ultrasonic IMF signal component waveform feature can be analyzed in the process of aggregating the waveform features of different ultrasonic IMF signal components, which helps to identify and strengthen those features with significant energy distribution in the local neighborhood, thereby improving the sensitivity of the model to local changes. This analysis of local energy distribution helps to identify key feature changes, which may be related to cracks, leaks or other abnormal conditions in the pipeline. Then, using the gating function and mask module, dynamic adjustment of feature significance can be achieved. This adaptive screening mechanism allows the model to dynamically adjust its focus according to the current input ultrasonic IMF signal component waveform features, thereby more effectively highlighting important signal component waveform features and suppressing unimportant features, which helps the model to more accurately identify and locate abnormal conditions in the pipeline. This is crucial for timely detection of problems such as cracks, leaks and corrosion.

[0030] In an embodiment of the present application, the sequence of the enhanced ultrasonic IMF signal component waveform semantic feature vectors is input into a feature aggregation network based on feature energy local significance gating to obtain ultrasonic IMF signal component waveform aggregation semantic feature vectors, including: based on the maximum value, minimum value, mean value and variance of each enhanced ultrasonic IMF signal component waveform semantic feature vector in the sequence of the enhanced ultrasonic IMF signal component waveform semantic feature vectors, determining the feature energy level coefficients of each enhanced ultrasonic IMF signal component waveform semantic feature vector to obtain a sequence of ultrasonic IMF signal component waveform semantic feature energy level coefficients; determining the scale of the ultrasonic IMF signal component waveform semantic local neighborhood, using the scale of the ultrasonic IMF signal component waveform semantic local neighborhood as the The method comprises the following steps: wherein the local neighborhood mean of each ultrasonic IMF signal component waveform semantic feature energy level coefficient is calculated respectively to obtain a sequence of ultrasonic IMF signal component waveform semantic feature energy level significance descriptors; the sequence of ultrasonic IMF signal component waveform semantic feature energy level significance descriptors is input into a mask module based on a gating function to obtain a sequence of mask-gated probabilistic ultrasonic IMF signal component waveform semantic feature energy level significance descriptors; and the sequence of mask-gated probabilistic ultrasonic IMF signal component waveform semantic feature energy level significance descriptors is used as a sequence of weights to calculate the position-weighted sum of the sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors to obtain the ultrasonic IMF signal component waveform aggregated semantic feature vector.

[0031] Among them, based on the maximum value, minimum value, mean value and variance of each enhanced ultrasonic IMF signal component waveform semantic feature vector in the sequence of the enhanced ultrasonic IMF signal component waveform semantic feature vector, the process of determining the characteristic energy level coefficients of each enhanced ultrasonic IMF signal component waveform semantic feature vector to obtain a sequence of ultrasonic IMF signal component waveform semantic feature energy level coefficients includes: calculating the maximum value, minimum value, mean value and variance of the enhanced ultrasonic IMF signal component waveform semantic feature vector to obtain the ultrasonic IMF signal component waveform semantic maximum value, ultrasonic IMF signal component waveform semantic minimum value, ultrasonic IMF signal component waveform semantic mean value and ultrasonic IMF signal component waveform semantic variance; calculating the sum of the ultrasonic IMF signal component waveform semantic variance and the hyperparameter to obtain the first ultrasonic IMF signal component waveform semantic local energy statistical factor; calculating The difference between the ultrasonic IMF signal component waveform semantic maximum value and the ultrasonic IMF signal component waveform semantic average value is used to obtain the ultrasonic IMF signal component waveform semantic maximum deviation value; the difference between the ultrasonic IMF signal component waveform semantic minimum value and the ultrasonic IMF signal component waveform semantic average value is calculated to obtain the ultrasonic IMF signal component waveform semantic minimum deviation value; the square sum of the ultrasonic IMF signal component waveform semantic maximum deviation value and the ultrasonic IMF signal component waveform semantic minimum deviation value is calculated and then added to the hyperparameter to obtain the second ultrasonic IMF signal component waveform semantic local energy statistical factor; the division between the first ultrasonic IMF signal component waveform semantic local energy statistical factor and the second ultrasonic IMF signal component waveform semantic local energy statistical factor is calculated to obtain the ultrasonic IMF signal component waveform semantic feature energy level coefficient.

[0032] More specifically, the process of inputting the sequence of ultrasonic IMF signal component waveform semantic feature energy level significance descriptors into a mask module based on a gating function to obtain a sequence of masked gated probabilistic ultrasonic IMF signal component waveform semantic feature energy level significance descriptors includes: using the negative number of each ultrasonic IMF signal component waveform semantic feature energy level significance descriptor in the sequence of ultrasonic IMF signal component waveform semantic feature energy level significance descriptors as an exponential power, calculating the exponential function value with the natural constant e as the base to obtain a sequence of ultrasonic IMF signal component waveform semantic feature energy level class support significance descriptors; calculating the positional sum between the sequence of ultrasonic IMF signal component waveform semantic feature energy level class support significance descriptors and the constant 1 to obtain a sequence of linearly modulated ultrasonic IMF signal component waveform semantic feature energy level class support significance descriptors; calculating the linearly modulated ultrasonic IMF signal component waveform semantic feature energy level class support significance descriptors. The invention relates to a method for enhancing the ultrasonic IMF signal component waveform semantic feature energy level of a linear modulated ultrasonic IMF signal component. The method comprises the following steps: obtaining a sequence of gated probabilistic feature energy level significance descriptors of the enhanced ultrasonic IMF signal component waveform semantic feature vector by supporting the inverse of each linear modulated ultrasonic IMF signal component waveform semantic feature energy level class in a sequence of probabilistic feature descriptors; performing masking processing on each gated probabilistic feature energy level significance descriptor in the sequence of gated probabilistic feature energy level significance descriptors to obtain a sequence of masked gated probabilistic ultrasonic IMF signal component waveform semantic feature energy level significance descriptors; wherein the method comprises the following steps: in response to the gated probabilistic feature energy level significance descriptor being greater than a predetermined threshold, taking the original value of the gated probabilistic feature energy level significance descriptor, otherwise setting it to 0.

[0033] In summary, in the above embodiment, the sequence of the enhanced ultrasonic IMF signal component waveform semantic feature vectors is input into the feature aggregation network based on feature energy local significance gating to obtain the ultrasonic IMF signal component waveform aggregate semantic feature vector, including: inputting the sequence of the enhanced ultrasonic IMF signal component waveform semantic feature vectors into the feature aggregation network based on feature energy local significance gating to process with the following feature aggregation formula to obtain the ultrasonic IMF signal component waveform aggregate semantic feature vector; wherein the feature aggregation formula is: ;in, is a sequence of semantic feature vectors of the waveform of the enhanced ultrasonic IMF signal component, is the first in the sequence of the semantic feature vectors of the enhanced ultrasonic IMF signal component waveform The waveform semantic feature vectors of enhanced ultrasonic IMF signal components, For the The mean of the semantic feature vectors of the waveform of the enhanced ultrasonic IMF signal components, For the The variance of the semantic feature vector of the waveform of the enhanced ultrasonic IMF signal component, is a hyperparameter, Indicates the The maximum value of the semantic feature vector of the enhanced ultrasonic IMF signal component waveform, Indicates the The minimum value of the semantic feature vector of the waveform of the enhanced ultrasonic IMF signal component, For the The characteristic energy level coefficients of the semantic feature vectors of the waveform of the enhanced ultrasonic IMF signal component, Indicated by the characteristic energy level coefficient The number of characteristic energy coefficients in the local neighborhood centered at For the The characteristic energy level coefficients of the semantic feature vectors of the waveform of the enhanced ultrasonic IMF signal component, For the The feature energy level significance descriptor of the semantic feature vector of the waveform of the enhanced ultrasonic IMF signal component, For the The gated probabilistic feature energy level significance descriptor of the waveform semantic feature vector of the enhanced ultrasonic IMF signal component is For masking operation, is the predetermined threshold, For the The mask-gated probabilistic feature energy level significance descriptor of the waveform semantic feature vector of the enhanced ultrasonic IMF signal component is For the The semantic feature vector of the waveform of the enhanced ultrasonic IMF signal component corresponds to the semantic feature vector of the waveform of the enhanced ultrasonic IMF signal component. To significantly enhance the number of sequences of semantic feature vectors of the waveform of ultrasonic IMF signal components, Aggregate semantic feature vectors for the ultrasonic IMF signal component waveforms.

[0034] In particular, the gathering and transportation pipeline baseline detection anomaly detection module 370 is used to determine the detection result based on the ultrasonic IMF signal component waveform aggregation semantic feature vector, the detection result is used to indicate whether there is an abnormality at the kth detection point, and whether to return the position coordinate data of the kth detection point based on the detection result. In a specific example of the present application, the ultrasonic IMF signal component waveform aggregation semantic feature vector is passed through a gathering and transportation pipeline baseline state detector based on a classifier to obtain a detection result, and the detection result is used to indicate whether there is an abnormality at the kth detection point. That is, the aggregation information between the semantic features of each ultrasonic IMF signal component waveform is used for classification processing, so as to detect each detection point of the gathering and transportation pipeline baseline, which is conducive to identifying pipeline cracks, leakage points and corrosion problems of the gathering and transportation pipeline baseline. Furthermore, in response to the detection result of whether there is an abnormality at the kth detection point, the position coordinate data of the kth detection point is returned, so as to facilitate the subsequent timely repair of pipeline abnormalities and ensure the safety and stability of the gathering and transportation pipeline baseline.

[0035] Furthermore, the present application takes into account the image semantic features of the IMF component of the ultrasonic received signal of the pipeline ultrasonic reverse attention selection based on the self-supervised cluster center feature reverse attention of the sequence expression of the enhanced ultrasonic IMF signal component waveform semantic feature vector. In this way, after the sequence of the enhanced ultrasonic IMF signal component waveform semantic feature vectors is subjected to feature aggregation based on feature energy local significance gating, the ultrasonic IMF signal component waveform aggregated semantic feature vectors will also cause feature energy local significance gating differences due to the reverse attention weight differences of the image semantic features based on the self-supervised cluster center, resulting in insufficient feature aggregation coverage, thereby causing a lack of interpretability of the outlier class regression and affecting the accuracy of the classification results.

[0036] In a preferred example, the ultrasonic IMF signal component waveform aggregation semantic feature vector is passed through a gathering and transportation pipeline baseline state detector based on a classifier to obtain a detection result, including: optimizing the ultrasonic IMF signal component waveform aggregation semantic feature vector to obtain an optimized ultrasonic IMF signal component waveform aggregation semantic feature vector; passing the optimized ultrasonic IMF signal component waveform aggregation semantic feature vector through a gathering and transportation pipeline baseline state detector based on a classifier to obtain a detection result.

[0037] Specifically, the waveform aggregation semantic feature vector of the ultrasonic IMF signal component is optimized, including the steps of: calculating the autocorrelation matrix of the waveform aggregation semantic feature vector of the ultrasonic IMF signal component, that is: ;in, represents the waveform aggregation semantic feature vector of the ultrasonic IMF signal component, represents the transpose of a vector, represents matrix multiplication, Denotes the autocorrelation matrix.

[0038] The ultrasonic IMF signal component waveform aggregation semantic feature vector is query-multiplied with the autocorrelation matrix to obtain an intermediate feature vector, that is: ;in, represents the waveform aggregation semantic feature vector of the ultrasonic IMF signal component, represents the autocorrelation matrix, represents matrix multiplication, Denotes the intermediate eigenvector.

[0039] Calculate the autocorrelation matrix Row vector and Inner product sum of row vectors distance, to obtain the first weight matrix and the second weight matrix , expressed as: ;in, and The autocorrelation matrix is ​​represented by Row vector and row vector, represents the transpose of a vector, represents matrix multiplication, represents the autocorrelation matrix, represents the first weight matrix, represents the first weight matrix The eigenvalues ​​of the positions, represents the second weight matrix, represents the second weight matrix The eigenvalues ​​of the positions, Represents the calculation vector distance.

[0040] The first weight matrix and the second weight matrix After matrix multiplication, further matrix multiplication is performed with the intermediate feature vector to obtain the optimized ultrasonic IMF signal component waveform aggregation semantic feature vector, that is: ;in, represents the first weight matrix, represents the second weight matrix, represents the intermediate eigenvector, represents matrix multiplication, Represents the optimized ultrasonic IMF signal component waveform aggregation semantic feature vector.

[0041] That is, for the bitwise scattered association response space of the eigenvalues ​​of the waveform aggregation semantic feature vector of the ultrasonic IMF signal component, a deep embedding structure in the high-order association space is obtained through the joint embedding space of the vector inner product embedding space and the vector independent embedding space, and the decomposable association response sub-dimension of the bitwise scattered association response space of the eigenvalues ​​of the waveform aggregation semantic feature vector of the ultrasonic IMF signal component is represented as a set of spatial sub-dimensions to further perform the dependent space mapping of the decomposable association response sub-dimension of the deep embedding structure of the waveform aggregation semantic feature vector of the ultrasonic IMF signal component, so as to improve the interpretability of the solution space of the class regression solution of the waveform aggregation semantic feature vector of the ultrasonic IMF signal component based on the association distribution through the complex dimensional representation of the association response, thereby improving the accuracy of the detection result obtained by the baseline state detector of the gathering and transportation pipeline based on the classifier of the waveform aggregation semantic feature vector of the ultrasonic IMF signal component. In this way, the abnormal condition of the gathering and transportation pipeline baseline can be detected more accurately, which is helpful to timely discover and deal with potential safety hazards, so as to take effective repair measures to prevent the further expansion of the baseline problem of the gathering and transportation pipeline and ensure the safety and stability of the baseline of the gathering and transportation pipeline.

[0042] As described above, the baseline detection system 300 for gathering and transportation pipelines based on multi-technology fusion according to the embodiment of the present application can be implemented in various wireless terminals, such as a server with a baseline detection algorithm for gathering and transportation pipelines based on multi-technology fusion. In a possible implementation, the baseline detection system 300 for gathering and transportation pipelines based on multi-technology fusion according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the baseline detection system 300 for gathering and transportation pipelines based on multi-technology fusion can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the baseline detection system 300 for gathering and transportation pipelines based on multi-technology fusion can also be one of the many hardware modules of the wireless terminal.

[0043] Alternatively, in another example, the gathering and transportation pipeline baseline detection system 300 based on multi-technology fusion and the wireless terminal may also be separate devices, and the gathering and transportation pipeline baseline detection system 300 based on multi-technology fusion may be connected to the wireless terminal via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.

[0044] Furthermore, a gathering and transportation pipeline baseline detection method based on multi-technology fusion is also provided.

[0045] Figure 3 FIG. 1 is a flow chart of a baseline detection method for a gathering and transportation pipeline based on multi-technology fusion according to an embodiment of the present application. Figure 3As shown, according to the multi-technology fusion-based baseline detection method of the gathering and transportation pipeline of the embodiment of the present application, the method comprises the following steps: S1, acquiring the position coordinate data of multiple detection points of the baseline of the gathering and transportation pipeline to be detected collected by the global navigation satellite system; S2, acquiring the pipeline ultrasonic receiving signal collected by the ultrasonic detector at the kth detection point; S3, performing CEEMDAN decomposition on the pipeline ultrasonic receiving signal to obtain a sequence of ultrasonic signal IMF components; S4, performing ultrasonic waveform feature extraction on each ultrasonic signal IMF component in the sequence of ultrasonic signal IMF components to obtain a sequence of ultrasonic IMF signal component waveform semantic feature vectors; S5, combining the ultrasonic I The sequence of MF signal component waveform semantic feature vectors is selected and enhanced by a feature reverse attention enhancement module based on the self-supervised cluster center to obtain a sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors; S6, the sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors is input into a feature aggregation network based on feature energy local significance gating to obtain an ultrasonic IMF signal component waveform aggregated semantic feature vector; S7, based on the ultrasonic IMF signal component waveform aggregated semantic feature vector, a detection result is determined, the detection result is used to indicate whether there is an abnormality at the kth detection point, and based on the detection result, it is determined whether to return the position coordinate data of the kth detection point.

[0046] In summary, according to the embodiment of the present application, the baseline detection method of the gathering and transportation pipeline based on multi-technology fusion is explained, which collects the position coordinate data of multiple detection points of the baseline of the gathering and transportation pipeline through the global navigation satellite system, and uses this as the basic data of the detection point for the subsequent return of abnormal detection points. Then, the pipeline ultrasonic receiving signal is collected at each detection point through the ultrasonic detector, and a data analysis algorithm based on artificial intelligence and signal processing is introduced at the back end to analyze the ultrasonic receiving signal, so as to detect the pipeline baseline state, so as to identify whether there are problems such as pipeline cracks, leaks and corrosion, and return the position coordinate data of the abnormal point when the pipeline baseline abnormal condition is detected, so as to facilitate the subsequent timely repair of pipeline abnormalities and ensure the safety and stability of the baseline of the gathering and transportation pipeline. In one embodiment, the research content of this application includes: 1. Optimization of the baseline detection process of the newly built production capacity gathering and transportation pipeline: (1) Optimization of the detection link: In view of the differences in pipeline materials, laying methods, and transportation media, as well as the characteristics of the small diameter of the gathering and transportation pipeline, the on-site detection links such as macro detection, anti-corrosion layer detection, and pipe body detection are deleted, simplified or weakened to reduce costs and labor intensity.

[0047] (2) Integrity management: Ensure that the inspection process after optimization of technical methods such as pipeline centerline positioning, internal inspection and external inspection meets the requirements of pipeline integrity management and ensures the safe operation of the pipeline.

[0048] Through the above two aspects of research, an efficient and economical baseline detection process is achieved to ensure the safety and integrity of pipeline operations and reduce resource consumption and potential risks.

[0049] 2. Research on the application of pipeline centerline positioning and measurement technology: In order to solve the problem of centerline positioning of newly built gathering and transportation pipelines, it is necessary to improve the efficiency and accuracy of pipeline positioning and measurement, and provide basic geographic information data for the future safe and stable operation of gathering and transportation pipelines. Use global navigation satellite system (GNSS) measurement technology to obtain the precise coordinates, elevation and distance data of the pipeline, process and analyze these collected data through advanced measurement data algorithms, establish a corresponding database, load it into the relevant pipeline detection and evaluation system, predict the location of potential hidden danger points in the pipeline in advance, or in the case of hidden dangers, timely and accurately locate the hidden danger points to ensure the safe and stable operation of the pipeline.

[0050] 3. Research on the application of external detection technology for gathering and transportation pipelines: On the basis of macroscopic detection of the pipe body, the laying environment, anti-corrosion system, cathodic protection system, stray flow interference, direct excavation detection and other technical means, auxiliary magnetic stress, etc. are used to detect and evaluate the safety status of the pipeline. First, the acoustic wave detection method is used to measure the acoustic wave signal reflected by the pipeline surface through the sensor, and the frequency and amplitude changes of the sound are combined to determine whether there are problems with the pipeline, such as cracks, corrosion, etc. Second, the magnetic powder detection method is used to apply iron powder or magnetic powder on the surface of the pipeline, and observe the distribution of the powder after applying the magnetic field, in order to find defects or cracks in the pipeline. Third, the ultrasonic detection technology is used to send and receive acoustic wave signals using an ultrasonic probe outside the pipeline to detect problems such as pipeline wall thickness, leakage points and corrosion. Fourth, leakage monitoring is carried out on the gathering and transportation pipelines that have been built and operated for a period of time to timely discover possible leakage.

[0051] The technical means for external inspection of gathering and transportation pipelines are not static. During the actual inspection process, this project research will adopt appropriate inspection methods based on the actual situation of the pipeline.

[0052] 4. Research on the application of internal detection technology for gathering and transportation pipelines: On the basis of pipe body detection, internal detection technologies and evaluation methods such as pipeline leakage magnetic detection technology, industrial pipeline endoscopic detection system, pipeline geometric deformation detection technology, pipeline centerline IMU detection, and pipeline ultrasonic internal detection technology are selectively used to obtain the relationship between pipeline corrosion conditions, operating parameters and protective measures, providing data basis for the safe and efficient operation of gathering and transportation pipelines.

[0053] Due to the influence of factors such as pipe diameter, material, construction period, and importance, there is no need for overly complex internal inspections of gathering and transportation pipelines. This project combines the actual capacity construction to form an economical, reasonable, feasible and reliable internal inspection technology for gathering and transportation pipelines.

[0054] The technical route is as follows; 1. Preliminary literature and data support: Investigate and collect technical information on oil and gas pipelines and baseline detection at home and abroad, sort out the differences between newly built capacity gathering and transportation pipelines and long-distance pipelines and other pipelines, refine the detection content and study the detection process, and formulate a baseline detection plan for newly built capacity gathering and transportation pipelines.

[0055] 2. Technical implementation route: (1) Project initiation and demand analysis: - Convene the project team and clarify the project goals and expected results.

[0056] - Analyze existing baseline testing processes to identify existing issues and potential areas for improvement.

[0057] (2) Optimization design of detection links: - Review the necessity and effectiveness of each detection link based on the material, laying method, conveying medium and pipe diameter of the pipeline.

[0058] - Determine which testing steps can be deleted, simplified or weakened to reduce costs and labor intensity.

[0059] - Design new inspection processes to ensure key safety points are effectively covered.

[0060] (3) Integrity management plan formulation: - Based on the characteristics of the pipeline, an integrity management plan is formulated to ensure that the inspection process can meet the requirements for safe operation of the pipeline.

[0061] - Includes risk assessments, process simulations and compliance checks.

[0062] (4) Implementation of pipeline centerline positioning measurement: - Use the Global Navigation Satellite System (GNSS) to perform pipeline centerline positioning measurement to obtain the precise coordinates, elevation and distance data of the pipeline.

[0063] - Apply data processing algorithms to analyze measurement data to predict and detect potential leak locations.

[0064] (5) Research on application of external detection technology: - Use technologies such as acoustic detection, magnetic particle detection, and ultrasonic detection to perform external pipeline detection.

[0065] - Analyze the inspection results to evaluate the surface condition and potential defects of the pipeline.

[0066] (6) Research on the application of internal inspection technology: - According to the actual situation of the pipeline, select appropriate internal inspection technology, such as magnetic flux leakage internal inspection, endoscopic inspection, geometric deformation inspection, etc.

[0067] - Analyze the test results to obtain information such as the corrosion condition inside the pipeline and changes in wall thickness.

[0068] (7) Data analysis and optimization adjustment: - Comprehensively analyze the collected data to evaluate the overall condition of the pipeline.

[0069] - Make necessary adjustments and optimizations to the testing process based on the analysis results.

[0070] (8) Results verification and implementation: - Verify the effectiveness of the optimized testing process in actual operations.

[0071] - Train operators to ensure smooth execution of the process.

[0072] - Monitor implementation results and make continuous improvements.

[0073] 3. In view of the inspection process of gathering and transportation pipelines, a feasible inspection method is proposed in combination with the standards; based on the actual new production capacity, a baseline inspection plan for gathering and transportation pipelines is proposed, and baseline inspection is implemented on site.

[0074] The innovations of this application are as follows: 1. Customization of the inspection process for the characteristics of the gathering and transportation pipeline significantly improves the inspection efficiency, reduces unnecessary inspection steps, and thus reduces costs. It fills the gap in the national oil industry in the inspection technology of gathering and transportation pipelines, especially in the inspection of small-diameter pipelines.

[0075] 2. Use GNSS technology for high-precision measurement and combine it with advanced data processing algorithms to accurately locate the potential hazard points.

[0076] 3. Use a variety of external inspection technologies, such as sonic, magnetic particle, and ultrasonic testing, to comprehensively evaluate the surface condition and potential defects of the pipeline.

[0077] 4. Select appropriate internal inspection technology according to the actual situation of the pipeline, such as magnetic flux leakage internal inspection, endoscopy inspection, etc., to obtain detailed conditions inside the pipeline. This technology is applied for the first time in the Xinjiang oil gathering and transportation pipeline industry, especially in achieving accurate assessment of the internal conditions of the pipeline.

[0078] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A baseline detection system for gathering and transportation pipelines based on multi-technology fusion, characterized in that: include: A gathering and transportation pipeline baseline detection point position coordinate acquisition module is used to obtain the position coordinate data of multiple detection points of the detected gathering and transportation pipeline baseline collected by the global navigation satellite system; The pipeline ultrasonic signal receiving module is used to obtain the pipeline ultrasonic receiving signal collected by the ultrasonic detector at the kth detection point; A signal decomposition module, used for performing CEEMDAN decomposition on the pipeline ultrasonic receiving signal to obtain a sequence of IMF components of the ultrasonic signal; An ultrasonic signal component waveform semantic feature extraction module is used to extract ultrasonic waveform features from each ultrasonic signal IMF component in the sequence of ultrasonic signal IMF components to obtain a sequence of ultrasonic IMF signal component waveform semantic feature vectors; An ultrasonic signal component waveform semantic selection and enhancement module, used for passing the sequence of ultrasonic IMF signal component waveform semantic feature vectors through a feature reverse attention selection and enhancement module based on the center of a self-supervised cluster to obtain a sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors; An ultrasonic IMF signal component waveform semantic aggregation module, used for inputting the sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors into a feature aggregation network based on feature energy local significance gating to obtain ultrasonic IMF signal component waveform aggregation semantic feature vectors; A gathering and transportation pipeline baseline inspection anomaly detection module, used to determine a detection result based on the waveform aggregation semantic feature vector of the ultrasonic IMF signal component, the detection result is used to indicate whether there is an anomaly at the kth detection point, and determine whether to return the position coordinate data of the kth detection point based on the detection result; The ultrasonic signal component waveform semantic selection and enhancement module includes: A self-supervised clustering unit is used to perform self-supervised clustering processing based on energy measurement on each ultrasonic IMF signal component waveform semantic feature vector in the sequence of ultrasonic IMF signal component waveform semantic feature vectors to obtain a self-supervised cluster center representation vector; an anti-correlation coefficient calculation unit, used for calculating the anti-correlation coefficient between each ultrasonic IMF signal component waveform semantic feature vector in the sequence of ultrasonic IMF signal component waveform semantic feature vectors and the self-supervised cluster center representation vector to obtain a sequence of ultrasonic IMF signal component waveform semantic anti-correlation coefficients; A normalization unit, used for inputting the sequence of semantic anti-correlation coefficients of the ultrasonic IMF signal component waveform into a Sigmoid activation function to obtain a sequence of normalized semantic anti-correlation weight coefficients of the ultrasonic IMF signal component waveform; An ultrasonic IMF signal component waveform semantic anti-enhancement unit is used to weight each ultrasonic IMF signal component waveform semantic anti-correlation weight coefficient in the sequence of normalized ultrasonic IMF signal component waveform semantic anti-correlation weight coefficients as a weight, and to weight each ultrasonic IMF signal component waveform semantic feature vector in the sequence of ultrasonic IMF signal component waveform semantic feature vectors to obtain a sequence of ultrasonic IMF signal component waveform semantic anti-enhancement feature vectors; An ultrasonic IMF signal component waveform semantic enhancement unit, used for calculating the positional difference between each group of corresponding ultrasonic IMF signal component waveform semantic feature vectors and ultrasonic IMF signal component waveform semantic anti-enhancement feature vectors in the sequence of ultrasonic IMF signal component waveform semantic feature vectors and the sequence of ultrasonic IMF signal component waveform semantic anti-enhancement feature vectors to obtain the sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors; Wherein, the ultrasonic IMF signal component waveform semantic aggregation module includes: A characteristic energy level coefficient calculation unit is used to determine the characteristic energy level coefficients of each enhanced ultrasonic IMF signal component waveform semantic feature vector in the sequence of enhanced ultrasonic IMF signal component waveform semantic feature vectors based on the maximum value, minimum value, mean value and variance of each enhanced ultrasonic IMF signal component waveform semantic feature vector to obtain a sequence of ultrasonic IMF signal component waveform semantic feature energy level coefficients; A local neighborhood mean calculation unit is used to determine the scale of the ultrasonic IMF signal component waveform semantic local neighborhood, use the scale of the ultrasonic IMF signal component waveform semantic local neighborhood as the mean calculation range, and respectively calculate the local neighborhood mean of each ultrasonic IMF signal component waveform semantic feature energy level coefficient to obtain a sequence of ultrasonic IMF signal component waveform semantic feature energy level significance descriptors; A masking unit, used for inputting the sequence of ultrasonic IMF signal component waveform semantic feature energy level significance descriptors into a masking module based on a gating function to obtain a sequence of masked gated probabilistic ultrasonic IMF signal component waveform semantic feature energy level significance descriptors; A waveform semantic aggregation unit is used to calculate the position-weighted sum of the sequence of waveform semantic feature vectors of the enhanced ultrasonic IMF signal component using the sequence of the mask-gated probabilistic ultrasonic IMF signal component waveform semantic feature energy level significance descriptors as a sequence of weights to obtain the ultrasonic IMF signal component waveform aggregation semantic feature vector.

2. The gathering and transportation pipeline baseline detection system based on multi-technology fusion according to claim 1 is characterized in that: The ultrasonic signal component waveform semantic feature extraction module is used to: pass each ultrasonic signal IMF component in the sequence of ultrasonic signal IMF components through an ultrasonic waveform feature extractor based on a hole convolutional neural network model to obtain a sequence of ultrasonic IMF signal component waveform semantic feature vectors.

3. The baseline detection system for gathering and transportation pipelines based on multi-technology fusion according to claim 2 is characterized in that: The self-supervised clustering unit is used to: Calculating the maximum value, average value and variance of each ultrasonic IMF signal component waveform semantic feature vector in the sequence of ultrasonic IMF signal component waveform semantic feature vectors to obtain a sequence of ultrasonic IMF signal component waveform semantic maximum values, a sequence of ultrasonic IMF signal component waveform semantic average values ​​and a sequence of ultrasonic IMF signal component waveform semantic variances; Respectively calculating the sum of each ultrasonic IMF signal component waveform semantic variance and the bias term in the sequence of ultrasonic IMF signal component waveform semantic variances and then multiplying the sum by a constant 4 to obtain a sequence of first ultrasonic IMF signal component waveform semantic node energy statistical factors; Performing double modulation on the sequence of semantic variances of the ultrasonic IMF signal component waveform and the bias term to obtain a sequence of double-modulated semantic variances of the ultrasonic IMF signal component waveform and double-modulated regularization term hyperparameters; Calculate the square of the difference between the ultrasonic IMF signal component waveform semantic maximum value and the ultrasonic IMF signal component waveform semantic average value corresponding to the sequence of the ultrasonic IMF signal component waveform semantic maximum value and the sequence of the ultrasonic IMF signal component waveform semantic average value, and then add them to the double modulation regularization term hyperparameter and the corresponding double modulation ultrasonic IMF signal component waveform semantic variance to obtain a sequence of second ultrasonic IMF signal component waveform semantic node energy statistical factors; Calculating the positional division between the sequence of energy statistical factors of the first ultrasonic IMF signal component waveform semantic node and the sequence of energy statistical factors of the second ultrasonic IMF signal component waveform semantic node to obtain a sequence of energy measurement coefficients; use After the function normalizes the sequence of energy measurement coefficients, it multiplies the sequence of waveform semantic feature vectors of the ultrasonic IMF signal component by position points to obtain the self-supervised cluster center representation vector.

4. The baseline detection system for gathering and transportation pipelines based on multi-technology fusion according to claim 3 is characterized in that: The anti-correlation coefficient calculation unit is used for: Calculating a difference vector between the ultrasonic IMF signal component waveform semantic feature vector and the self-supervised cluster center representation vector to obtain an ultrasonic IMF signal component waveform semantic offset vector; Calculating the covariance matrix between the ultrasonic IMF signal component waveform semantic feature vector and the self-supervised cluster center representation vector to obtain the ultrasonic IMF signal component waveform semantic offset covariance matrix; Calculating the matrix division between the transposed vector of the ultrasonic IMF signal component waveform semantic offset vector and the ultrasonic IMF signal component waveform semantic offset covariance matrix to obtain an ultrasonic IMF signal component waveform semantic offset degree feature representation vector; After calculating the vector multiplication between the ultrasonic IMF signal component waveform semantic deviation feature representation vector and the ultrasonic IMF signal component waveform semantic deviation vector, the square root of the anti-correlation difference value obtained is calculated to obtain the ultrasonic IMF signal component waveform semantic anti-correlation coefficient.

5. The gathering and transportation pipeline baseline detection system based on multi-technology fusion according to claim 4 is characterized in that: The characteristic energy level coefficient calculation unit is used to: Calculating the maximum value, minimum value, average value and variance of the enhanced ultrasonic IMF signal component waveform semantic feature vector to obtain the ultrasonic IMF signal component waveform semantic maximum value, ultrasonic IMF signal component waveform semantic minimum value, ultrasonic IMF signal component waveform semantic average value and ultrasonic IMF signal component waveform semantic variance; Calculate the sum of the ultrasonic IMF signal component waveform semantic variance and the hyperparameter to obtain a first ultrasonic IMF signal component waveform semantic local energy statistical factor; Calculate the difference between the ultrasonic IMF signal component waveform semantic maximum value and the ultrasonic IMF signal component waveform semantic average value to obtain the ultrasonic IMF signal component waveform semantic maximum deviation value; Calculating the difference between the ultrasonic IMF signal component waveform semantic minimum value and the ultrasonic IMF signal component waveform semantic average value to obtain the ultrasonic IMF signal component waveform semantic minimum deviation value; Calculate the square sum of the maximum deviation value of the ultrasonic IMF signal component waveform semantics and the minimum deviation value of the ultrasonic IMF signal component waveform semantics, and then add the sum to the hyperparameter to obtain a second ultrasonic IMF signal component waveform semantics local energy statistical factor; The division between the first ultrasonic IMF signal component waveform semantic local energy statistics factor and the second ultrasonic IMF signal component waveform semantic local energy statistics factor is calculated to obtain the ultrasonic IMF signal component waveform semantic feature energy level coefficient.

6. The baseline detection system for gathering and transportation pipelines based on multi-technology fusion according to claim 5 is characterized in that: The mask unit is used for: Taking the negative number of each ultrasonic IMF signal component waveform semantic feature energy level significance descriptor in the sequence of ultrasonic IMF signal component waveform semantic feature energy level significance descriptors as an exponential power, calculating the exponential function value with the natural constant e as the base to obtain a sequence of ultrasonic IMF signal component waveform semantic feature energy level class support significance descriptors; Calculating the positional sum between the sequence of the ultrasonic IMF signal component waveform semantic feature energy level class support significance descriptor and a constant 1 to obtain a sequence of linear modulated ultrasonic IMF signal component waveform semantic feature energy level class support significance descriptor; Calculating the inverse of each linear modulation ultrasonic IMF signal component waveform semantic feature energy level class support significance descriptor in the sequence of linear modulation ultrasonic IMF signal component waveform semantic feature energy level class support significance descriptors to obtain a sequence of gated probabilistic feature energy level significance descriptors of enhanced ultrasonic IMF signal component waveform semantic feature vectors; Performing masking processing on each gated probabilistic feature energy level significance descriptor in the sequence of gated probabilistic feature energy level significance descriptors to obtain a sequence of masked gated probabilistic ultrasonic IMF signal component waveform semantic feature energy level significance descriptors; Wherein, performing masking processing on each gated probabilistic feature energy level significance descriptor in the sequence of gated probabilistic feature energy level significance descriptors to obtain the sequence of masked gated probabilistic ultrasonic IMF signal component waveform semantic feature energy level significance descriptors comprises: In response to the gated probabilistic feature energy level significance descriptor being greater than a predetermined threshold, the original value of the gated probabilistic feature energy level significance descriptor is taken, otherwise it is set to 0.

7. The gathering and transportation pipeline baseline detection system based on multi-technology fusion according to claim 6 is characterized in that: The gathering and transportation pipeline baseline inspection anomaly detection module is used to: The ultrasonic IMF signal component waveform aggregation semantic feature vector is passed through a gathering pipeline baseline state detector based on a classifier to obtain the detection result, and the detection result is used to indicate whether there is an abnormality at the kth detection point; In response to the detection result of whether there is an abnormality at the kth detection point, the position coordinate data of the kth detection point is returned.

8. A method for baseline detection of a gathering and transportation pipeline based on multi-technology fusion, using the baseline detection system for a gathering and transportation pipeline based on multi-technology fusion according to claim 1, characterized in that: include: Acquire the position coordinate data of multiple detection points of the baseline of the detected gathering and transportation pipeline collected by the global navigation satellite system; Obtaining a pipeline ultrasonic receiving signal collected by the ultrasonic detector at the kth detection point; Performing CEEMDAN decomposition on the pipeline ultrasonic receiving signal to obtain a sequence of IMF components of the ultrasonic signal; Performing ultrasonic waveform feature extraction on each ultrasonic signal IMF component in the sequence of ultrasonic signal IMF components to obtain a sequence of ultrasonic IMF signal component waveform semantic feature vectors; The sequence of semantic feature vectors of the ultrasonic IMF signal component waveform is passed through a feature reverse attention selection enhancement module based on the center of a self-supervised cluster to obtain a sequence of enhanced semantic feature vectors of the ultrasonic IMF signal component waveform; Inputting the sequence of the enhanced ultrasonic IMF signal component waveform semantic feature vectors into a feature aggregation network based on feature energy local significance gating to obtain ultrasonic IMF signal component waveform aggregation semantic feature vectors; Based on the waveform aggregation semantic feature vector of the ultrasonic IMF signal component, a detection result is determined, the detection result is used to indicate whether there is an abnormality at the kth detection point, and based on the detection result, it is determined whether to return the position coordinate data of the kth detection point.

Citation Information

Cited By

  • Defect identification and positioning method

    CN120807633A