Pipeline defect development state prediction method and device, and storage medium

Abstract

This application discloses a method, apparatus, and storage medium for predicting the development state of pipeline defects, relating to the field of pipeline prediction technology, and aims to solve the problems of strong data dependence, insufficient generalization, and insufficient reliability in current pipeline defect development state prediction schemes. The pipeline defect development state prediction method includes: acquiring multi-source prior knowledge and historical pipeline inspection data related to pipeline defect development; quantifying and characterizing the multi-source prior knowledge to obtain quantified multi-source prior knowledge; constructing a pipeline defect development state prediction model based on the quantified multi-source prior knowledge and historical pipeline inspection data; and determining the pipeline defect development state of the target pipeline through the pipeline defect development state prediction model.

Description

Technical Field

[0001] This application relates to the field of pipeline prediction technology, and in particular to methods, devices and storage media for predicting the development status of pipeline defects. Background Technology

[0002] As a critical infrastructure for energy transmission, the safe and stable operation of pipelines is directly related to the security of energy supply and the safety of production operations. The dynamic evolution of pipeline defects is the main cause of pipeline failure, and accurate prediction of the development trend of pipeline defects is an important prerequisite for the safe operation and maintenance of pipelines throughout their entire life cycle.

[0003] Current pipeline defect development prediction schemes mainly rely on in-line inspection (ILI) data. However, these schemes are highly dependent on inspection data, resulting in insufficient prediction accuracy in scenarios with limited data. Furthermore, they struggle to characterize the uncertainties in pipeline defect evolution, exhibiting poor model generalization and reliability, and ultimately failing to meet the practical needs of pipeline safety operation and maintenance. Summary of the Invention

[0004] The purpose of this application is to provide a method, device and storage medium for predicting the development state of pipeline defects, which aims to solve the problems of strong data dependence, insufficient generalization and reliability in the current pipeline defect development state prediction scheme. This application can improve the prediction accuracy and uncertainty characterization ability by integrating multi-source prior knowledge, so as to meet the needs of pipeline safe operation and maintenance.

[0005] To achieve the above objectives, this application adopts the following technical solution: In a first aspect, this application provides a method for predicting the development state of pipeline defects, including: acquiring multi-source prior knowledge and historical pipeline inspection data related to pipeline defect development; quantifying and characterizing the multi-source prior knowledge to obtain quantified multi-source prior knowledge; constructing a pipeline defect development state prediction model based on the quantified multi-source prior knowledge and historical pipeline inspection data; and determining the pipeline defect development state of the target pipeline through the pipeline defect development state prediction model.

[0006] The above technical solution brings at least the following beneficial effects: This application breaks the dependence of traditional solutions on massive historical pipeline inspection data by integrating and quantifying multi-source prior knowledge, and can still guarantee prediction accuracy in scenarios where historical pipeline inspection data is scarce; the integration of multi-source prior knowledge can improve the adaptability of the defect development prediction model to pipelines of different materials and different service environments, and improve the problem of insufficient generalization of pipeline defect development state prediction models; at the same time, through the standardized and quantified processing of multi-source prior knowledge, the complexity of knowledge processing is reduced and the reliability of prediction is improved, thereby better meeting the precise needs of pipeline safety operation and maintenance.

[0007] In one possible implementation, the pipeline defect development state of the target pipeline is determined by a pipeline defect development state prediction model, including: obtaining basic information of the target pipeline, which includes at least one of the following: material property parameters, environmental influencing factors, and operating condition parameters; inputting the basic information of the target pipeline into the pipeline defect development state prediction model, and outputting the pipeline defect development state of the target pipeline.

[0008] In one possible implementation, the pipeline defect development status of the target pipeline is determined by using a pipeline defect development status prediction model, including: acquiring the current pipeline inspection data of the target pipeline; performing a global sensitivity analysis based on the current pipeline inspection data using the pipeline defect development status prediction model to uncover the pipeline defect development pattern, and performing dynamic prediction using a rolling time window mechanism based on the current pipeline inspection data; and combining the pipeline defect development pattern and the dynamic prediction results to determine the pipeline defect development status of the target pipeline.

[0009] In one possible implementation, the multi-source prior knowledge is quantitatively represented, including: converting deterministic prior knowledge into numerical or interval form and assigning values; and / or, converting empirical prior knowledge into computable probability values ​​through mathematical methods; and / or, describing uncertain prior knowledge using a probability distribution model.

[0010] In one possible implementation, multi-source prior knowledge includes at least one of the following: industry standards and specifications, historical test data, material property parameters, environmental influencing factors, and expert experience knowledge.

[0011] In one possible implementation, historical pipeline inspection data includes key characteristic parameters of pipeline defect development. Obtaining historical pipeline inspection data includes: preprocessing the original historical pipeline inspection data based on multi-source prior knowledge. The preprocessing includes at least one of the following: removing abnormal noise data, interpolating to complete missing data, and correcting and completing the results based on expert experience. Based on multi-source prior knowledge, characteristic parameters are constructed from the preprocessed historical pipeline inspection data, and key characteristic parameters of pipeline defect development are selected.

[0012] In one possible implementation, a pipeline defect development status prediction model is constructed based on quantified multi-source prior knowledge and historical pipeline inspection data. This includes: setting the quantified multi-source prior knowledge as the prior distribution of the model, using historical pipeline inspection data as observation data, updating the model parameters through a Bayesian inference algorithm to obtain the posterior distribution, and constructing a pipeline defect development probability prediction model based on the posterior distribution.

[0013] Secondly, this application provides a pipeline defect development state prediction device, which includes: an acquisition unit and a processing unit; the acquisition unit is used to acquire multi-source prior knowledge and historical pipeline inspection data related to pipeline defect development; the processing unit is used to quantify and characterize the multi-source prior knowledge to obtain quantified multi-source prior knowledge; the processing unit is also used to construct a pipeline defect development state prediction model based on the quantified multi-source prior knowledge and historical pipeline inspection data; the processing unit is also used to determine the pipeline defect development state of the target pipeline through the pipeline defect development state prediction model.

[0014] In one possible implementation, the acquisition unit is further used to acquire basic information of the target pipeline, which includes at least one of the following: material property parameters, environmental influencing factors, and operating condition parameters; the processing unit is used to input the basic information of the target pipeline into the pipeline defect development state prediction model and output the pipeline defect development state of the target pipeline.

[0015] In one possible implementation, the acquisition unit is further configured to acquire the current pipeline inspection data of the target pipeline; the processing unit is configured to perform a global sensitivity analysis based on the current pipeline inspection data through a pipeline defect development state prediction model to mine the pipeline defect development pattern, and to perform dynamic prediction based on the current pipeline inspection data using a rolling time window mechanism; the processing unit is configured to combine the pipeline defect development pattern and the dynamic prediction results to determine the pipeline defect development state of the target pipeline.

[0016] In one possible implementation, the processing unit is specifically used to: convert deterministic prior knowledge into numerical or interval form and assign values; and / or, convert empirical prior knowledge into computable probability values ​​using mathematical methods; and / or, describe uncertain prior knowledge using a probability distribution model.

[0017] In one possible implementation, multi-source prior knowledge includes at least one of the following: industry standards and specifications, historical test data, material property parameters, environmental influencing factors, and expert experience knowledge.

[0018] In one possible implementation, the processing unit is specifically used to: preprocess the original historical pipeline inspection data based on multi-source prior knowledge, the preprocessing including at least one of the following: removing abnormal noise data, interpolating to complete missing data, and correcting and completing the results based on expert experience; constructing feature parameters from the preprocessed historical pipeline inspection data based on multi-source prior knowledge, and selecting key feature parameters for pipeline defect development.

[0019] In one possible implementation, the processing unit is specifically used to: set the quantified multi-source prior knowledge as the prior distribution of the model, and use historical pipeline inspection data as observation data to update the model parameters through a Bayesian inference algorithm to obtain the posterior distribution; and construct a pipeline defect development probability prediction model based on the posterior distribution.

[0020] Thirdly, this application provides another pipeline defect development state prediction device, which includes: a processor and a communication interface; the communication interface and the processor are coupled, and the processor is used to run computer programs or instructions to implement the pipeline defect development state prediction method as described in the first aspect and any possible implementation of the first aspect.

[0021] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a terminal, cause the terminal to perform the pipeline defect development state prediction method as described in the first aspect and any possible implementation thereof.

[0022] Fifthly, this application provides a computer program product containing instructions that, when run on a pipeline defect development state prediction device, cause the pipeline defect development state prediction device to execute the pipeline defect development state prediction method as described in the first aspect and any possible implementation thereof.

[0023] In a sixth aspect, this application provides a chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run computer programs or instructions to implement the pipeline defect development state prediction method as described in the first aspect and any possible implementation thereof.

[0024] Specifically, the chip provided in this application also includes a memory for storing computer programs or instructions. Attached Figure Description

[0025] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a schematic diagram of the structure of a pipeline defect development state prediction device provided in an embodiment of this application; Figure 2 A flowchart illustrating a method for predicting the development state of pipeline defects provided in this application embodiment; Figure 3A flowchart illustrating another method for predicting the development state of pipeline defects provided in this application embodiment; Figure 4 A schematic diagram of another pipeline defect development state prediction device provided in an embodiment of this application. Detailed Implementation

[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] In the description of this application, it should be understood that the terms "upper," "lower," "left," "right," "front," "rear," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or relative positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and for simplification, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. Unless otherwise specified, the above-mentioned orientational descriptions can be flexibly set in practical applications, provided that the relative positional relationships shown in the accompanying drawings are satisfied.

[0029] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0030] As a critical infrastructure for energy transmission, the safe and stable operation of pipelines is directly related to the security of energy supply and the safety of production operations. The dynamic evolution of pipeline defects (such as corrosion, cracks, and pits) is a major cause of pipeline failure. Accurate prediction of the development trend of pipeline defects is an important prerequisite for ensuring the safe operation and maintenance of pipelines throughout their entire life cycle.

[0031] Current pipeline defect development analysis and prediction mainly rely on in-line inspection (ILI) data, and the models used are mainly divided into two categories: pure data-driven models and deterministic physical models.

[0032] For data-driven models, traditional statistical methods such as time series and regression analysis rely heavily on large amounts of continuous and high-quality historical inspection data. For newly built pipelines, pipelines with long inspection cycles, or pipelines with scarce historical data, the prediction accuracy drops significantly. At the same time, such technical solutions are difficult to effectively integrate the prior knowledge such as industry standards, expert experience, material properties, and service environment accumulated over a long period of time. The generalization and extrapolation capabilities of the model are limited, and the uncertainty of pipeline defect development trends is difficult to analyze systematically and quantitatively.

[0033] For deterministic physical models, prediction methods based on deterministic physical equations such as corrosion propagation and stress evolution often oversimplify and idealize factors such as complex and variable geological environments, media conditions, and operating conditions. This makes it difficult to truly reflect the stochastic evolution characteristics and uncertainty of pipeline defects in actual complex scenarios, resulting in deviations between prediction results and actual field conditions, and limiting applicability.

[0034] In summary, the aforementioned general technologies generally suffer from insufficient utilization of prior knowledge. Specifically, prior knowledge such as industry standards, expert experience, materials science principles, and failure mechanisms often exist in isolation in traditional prediction systems as qualitative criteria, boundary constraints, or auxiliary rules. They are not deeply embedded in the prediction process in a parameterized, quantified, and systematic manner, failing to form a prediction mechanism where prior knowledge and data-driven approaches mutually reinforce and iterate synergistically. This restricts the accuracy, reliability, and scenario adaptability of the prediction models.

[0035] Therefore, there is an urgent need for a pipeline defect development state prediction method that can systematically integrate multi-dimensional and multi-source prior knowledge. By quantitatively embedding prior knowledge, the reliability of prediction can be improved, thereby better meeting the precise needs of pipeline safety operation and maintenance.

[0036] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," and "communication" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection. They can refer to a direct connection or an indirect connection through an intermediate medium, or a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0037] In embodiments of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, article, or apparatus that includes that element.

[0038] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0039] In the description of this specification, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0040] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0041] Figure 1 This is a schematic diagram of the structure of a pipeline defect development state prediction device 10 provided in an embodiment of this application. Figure 1 As shown, the pipeline defect development state prediction device 10 may include a processor 101, a bus 102, a communication interface 103, and a memory 104.

[0042] The processor 101, memory 104 and communication interface 103 can be connected via bus 102.

[0043] The processor 101 can be a CPU, a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 101 can also be other devices with processing capabilities, such as circuits, devices, or software modules, without limitation.

[0044] Bus 102 is used to transmit information between the components included in the pipeline defect development state prediction device 10.

[0045] Communication interface 103 is used to communicate with other devices or other communication networks. These other communication networks can be Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc. Communication interface 103 can be a module, circuit, communication interface, or any device capable of enabling communication.

[0046] Memory 104 is used to store instructions. These instructions can be computer programs.

[0047] The memory 104 can be a read-only memory (ROM) or other type of static storage device that can store static information and / or instructions; it can also be a random access memory (RAM) or other type of dynamic storage device that can store information and / or instructions; it can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, etc., without limitation.

[0048] It should be noted that the memory 104 can exist independently of the processor 101 or be integrated with the processor 101. The memory 104 can be used to store instructions, program code, or some data. The memory 104 can be located inside or outside the pipeline defect development state prediction device 10, without limitation. The processor 101 is used to execute the instructions stored in the memory 104 to implement the blind detection method provided in the following embodiments of this application.

[0049] In one example, processor 101 may include one or more CPUs.

[0050] As an optional implementation, the pipeline defect development state prediction device 10 includes multiple processors.

[0051] As an optional implementation, the pipeline defect development state prediction device 10 also includes an output device and an input device, which are not shown in the figure.

[0052] In this embodiment of the application, the chip system may be composed of chips or may include chips and other discrete devices.

[0053] Furthermore, the actions, terms, etc., involved in the various embodiments of this application can be referenced interchangeably without limitation. The message names or parameter names in the messages exchanged between the various devices in the embodiments of this application are merely examples, and other names may be used in specific implementations without limitation.

[0054] The following is combined with Figure 1 The pipeline defect development state prediction device shown describes the pipeline defect development state prediction method provided in the embodiments of this application. The actions, terminology, etc., involved in the various embodiments of this application can be referred to mutually without limitation. The message names or parameter names in the messages between the various devices in the embodiments of this application are merely examples; other names can be used in specific implementations without limitation. The actions involved in the various embodiments of this application are merely examples; other names can be used in specific implementations, such as replacing "included in" with "carried on" or "carried in," etc.

[0055] like Figure 2 As shown in the figure, this application provides a method for predicting the development state of pipeline defects, which includes: S201-S204.

[0056] S201, The pipeline defect development state prediction device acquires multi-source prior knowledge and historical pipeline inspection data related to pipeline defect development.

[0057] In some embodiments, multi-source prior knowledge includes at least one of the following: industry standards and specifications, historical test data, material property parameters, environmental influencing factors, and expert experience knowledge.

[0058] In some embodiments, historical pipeline inspection data includes key characteristic parameters of pipeline defect development. The process by which the pipeline defect development state prediction device acquires historical pipeline inspection data can be as follows: the pipeline defect development state prediction device preprocesses the original historical pipeline inspection data based on multi-source prior knowledge, and constructs characteristic parameters from the preprocessed historical pipeline inspection data based on multi-source prior knowledge, and selects key characteristic parameters of pipeline defect development. The preprocessing includes at least one of the following: removing abnormal noise data, interpolating to complete missing data, and correcting and completing the results based on expert experience.

[0059] S202, the pipeline defect development state prediction device quantifies and characterizes multi-source prior knowledge to obtain quantified multi-source prior knowledge.

[0060] In some embodiments, the implementation process of S202 described above may be: the pipeline defect development state prediction device converts deterministic prior knowledge into numerical or interval form and assigns values; and / or, Transforming empirical prior knowledge into computable probability values ​​using mathematical methods; and / or, The prior knowledge of uncertainty is described using a probability distribution model.

[0061] S203, the pipeline defect development state prediction device constructs a pipeline defect development state prediction model based on quantified multi-source prior knowledge and historical pipeline inspection data.

[0062] In some embodiments, the implementation process of S203 described above can be as follows: the pipeline defect development state prediction device sets the quantified multi-source prior knowledge as the prior distribution of the model, and uses historical pipeline inspection data as observation data to update the model parameters through a Bayesian inference algorithm to obtain the posterior distribution. The pipeline defect development state prediction device constructs a pipeline defect development probability prediction model based on the posterior distribution.

[0063] S204. The pipeline defect development state prediction device determines the pipeline defect development state of the target pipeline through the pipeline defect development state prediction model.

[0064] In some embodiments, the implementation process of S204 above may be as follows: the pipeline defect development state prediction device acquires the basic information of the target pipeline, inputs the basic information of the target pipeline into the pipeline defect development state prediction model, and outputs the pipeline defect development state of the target pipeline, wherein the basic information includes at least one of the following: material characteristic parameters, environmental influencing factors, and operating condition parameters.

[0065] The above embodiments can be applied to pipelines that cannot be internally inspected. Specifically, by constructing a pipeline defect development state prediction model as described above, relevant information about pipelines that cannot be internally inspected (i.e., basic information of the target pipeline, mainly key factors affecting pipeline defect development) can be input. By calling the pipeline defect development state prediction model, the pipeline defect development state of the target pipeline that cannot be internally inspected can be given (i.e., the distribution of pipeline defect development and the pipeline defect development trend (e.g., short-term pipeline defect development trend and long-term pipeline defect development trend)). The above-mentioned multi-source prior knowledge can be fully utilized to make up for the lack of current pipeline inspection data and to predict and analyze pipelines that cannot be internally inspected.

[0066] In some embodiments, the implementation process of S204 above can be as follows: The pipeline defect development state prediction device acquires the current pipeline inspection data of the target pipeline. Based on the current pipeline inspection data, the pipeline defect development state prediction device performs a global sensitivity analysis through a pipeline defect development state prediction model to uncover the pipeline defect development pattern, and performs dynamic prediction using a rolling time window mechanism based on the current pipeline inspection data. The pipeline defect development state prediction device combines the pipeline defect development pattern and the dynamic prediction results to determine the pipeline defect development state of the target pipeline.

[0067] This application breaks away from the reliance of traditional solutions on massive historical pipeline inspection data by integrating and quantifying multi-source prior knowledge, thus ensuring prediction accuracy even in scenarios where historical pipeline inspection data is scarce. The integration of multi-source prior knowledge enhances the adaptability of the defect development prediction model to pipelines of different materials and service environments, and improves the problem of insufficient generalization of pipeline defect development state prediction models. At the same time, by standardizing and quantifying multi-source prior knowledge, the complexity of knowledge processing is reduced, and the reliability of prediction is improved, thereby better meeting the precise needs of pipeline safety operation and maintenance.

[0068] For example, to provide a complete explanation of the pipeline defect development state prediction method, namely, through the systematic sorting, quantitative representation, and deep integration of the aforementioned multi-source prior knowledge, a pipeline defect development state prediction and analysis system is constructed. This system covers the processing and optimization of the aforementioned multi-source prior knowledge, the construction of the pipeline defect development state prediction model, the mining of pipeline defect development patterns, the application of pipeline defect development patterns, and so on. This aims to address the problems of strong data dependence, insufficient generalization, and insufficient reliability in current pipeline defect development state prediction schemes. Figure 3 A flowchart of another method for predicting the development state of pipeline defects is shown, such as... Figure 3 As shown, the information transmission method includes the following steps S301 to S305.

[0069] S301, The pipeline defect development state prediction device acquires multi-source prior knowledge related to pipeline defect development, and systematically sorts out and quantitatively represents the above-mentioned multi-source prior knowledge.

[0070] In some embodiments, the process of the pipeline defect development state prediction device systematically sorting out the multi-source prior knowledge may include: the pipeline defect development state prediction device comprehensively collects and classifies the multi-source prior knowledge related to pipeline defect development, constructs a standardized knowledge classification system, and clarifies the coupling relationship between various types of multi-source prior knowledge based on the standardized knowledge classification system.

[0071] For example, the aforementioned multi-source prior knowledge includes, but is not limited to: industry standards and norms, historical testing data, material property parameters, environmental influencing factors, and expert experience.

[0072] Industry standards and regulations include, but are not limited to: industry standards and regulations related to pipeline design, pipeline construction, pipeline inspection, and pipeline maintenance.

[0073] Historical inspection data includes, but is not limited to: the location of pipeline defects in each inspection record, the type of pipeline defects in each inspection record, the size of pipeline defects in each inspection record, and the inspection methods in each inspection record.

[0074] Among them, material characteristic parameters include, but are not limited to, parameters such as corrosion rate, mechanical properties, and aging behavior corresponding to the pipe material.

[0075] Environmental factors include, but are not limited to: soil corrosivity, ambient temperature, ambient humidity, pipeline operating pressure, cathodic protection potential, and stray current interference.

[0076] Among them, expert experience and knowledge include, but are not limited to: industry experts’ accumulated experience and methods related to pipeline defect development, judgments on specific pipeline defect development patterns, and assessment results on the uncertainty of pipeline defect evolution.

[0077] For example, the coupling relationships between various types of multi-source prior knowledge mentioned above include, but are not limited to: the coupling relationship between material properties and corrosion rate, the mapping relationship between environmental parameters and pipeline defect development trends, etc.

[0078] In some embodiments, the process by which the pipeline defect development state prediction device quantifies the multi-source prior knowledge may include: the pipeline defect development state prediction device converts the non-quantitative multi-source prior knowledge into a quantitative form that can be adapted to a mathematical model.

[0079] Specifically, for example, the pipeline defect development state prediction device directly converts the aforementioned deterministic multi-source prior knowledge into numerical values ​​or intervals and assigns values; for another example, the pipeline defect development state prediction device converts empirical knowledge (e.g., experts' judgments on the development trend of pipeline defects) into calculable weights or probability values ​​through mathematical processing; for yet another example, the pipeline defect development state prediction device uses probabilistic statistical models (e.g., normal distribution, Weibull distribution) to describe random and uncertain knowledge (e.g., the randomness of corrosion rate, environmental influencing factors, etc.), forming a unified quantitative prior information foundation.

[0080] S302, The pipeline defect development status prediction device acquires historical pipeline inspection data and integrates it to perform preprocessing and feature extraction.

[0081] In some embodiments, the implementation process of the above-mentioned pipeline defect development state prediction device integrating the preprocessing of historical pipeline inspection data may include: the pipeline defect development state prediction device performing preprocessing on historical pipeline inspection data (which may also be referred to as raw pipeline inspection data) based on the above-mentioned multi-source prior knowledge.

[0082] Specifically, for example, the pipeline defect development state prediction device identifies and eliminates abnormal noise data through the constraints of the aforementioned multi-source prior knowledge, interpolates and completes the missing data based on the evolution characteristics of similar pipeline defects, and uses expert experience to correct the completion results; another example is that the pipeline defect development state prediction device uses the measurement error of the ILI tool as prior information to construct a measurement error model and completes uncertainty correction for pipeline defect size data.

[0083] In some embodiments, the process of integrating the pipeline defect development state prediction device with the feature extraction of historical pipeline inspection data may include: the pipeline defect development state prediction device combines the above-mentioned multi-source prior knowledge and statistical analysis methods (e.g., correlation analysis, principal component analysis (PCA)) to construct and screen key feature parameters of pipeline defect development from historical pipeline inspection data, forming a standardized feature set that adapts to the model input.

[0084] S303, the pipeline defect development state prediction device constructs a pipeline defect development state prediction model based on quantified multi-source prior knowledge and historical pipeline inspection data.

[0085] In some embodiments, the implementation process of S303 above may include: the pipeline defect development state prediction device uses the quantified multi-source prior knowledge as the prior distribution of the pipeline defect development state prediction model, uses historical pipeline inspection data as observation data, updates the model parameters through Bayesian inference to obtain the posterior distribution, and thus constructs a pipeline defect development state prediction model (which can also be called a pipeline defect development probability prediction model) that integrates the above-mentioned multi-source prior knowledge and historical pipeline inspection data.

[0086] Furthermore, for different types of pipeline defects such as corrosion, cracks, and mechanical damage, the pipeline defect development state prediction device constructs a dedicated statistical model as a subdivision and adaptation model for the pipeline defect development state prediction model. Based on the multi-source prior knowledge of the corresponding pipeline defect type, the device initializes the parameters of the dedicated statistical model, thereby realizing the personalized adaptation of the pipeline defect development state prediction model to different types of pipeline defects.

[0087] For example, the pipeline defect development status prediction model can output the probability distribution of the pipeline defect size evolution over time, thereby achieving a quantitative characterization of prediction uncertainty.

[0088] S304. The pipeline defect development state prediction device acquires the current pipeline inspection data of the target pipeline. Based on the current pipeline inspection data, it performs a global sensitivity analysis through the pipeline defect development state prediction model to explore the pipeline defect development pattern. Based on the current pipeline inspection data, it performs dynamic prediction using a rolling time window mechanism. Combining the pipeline defect development pattern and the dynamic prediction results, it determines the pipeline defect development state of the target pipeline.

[0089] In some embodiments, the process by which the pipeline defect development state prediction device performs a global sensitivity analysis through a pipeline defect development state prediction model to uncover the pipeline defect development law may include: using the Sobol index method (SIM) to quantify the contribution of various influencing factors (e.g., the material of the target pipeline, environmental influencing factors, the pressure of the target pipeline, detector accuracy, etc.) to the pipeline defect development rate and prediction uncertainty, and identifying the key driving factors of pipeline defect evolution and the pipeline defect development law.

[0090] In some embodiments, the process of the pipeline defect development state prediction device performing dynamic prediction based on current pipeline inspection data using a rolling time window mechanism may include: the pipeline defect development state prediction device performing dynamic prediction using a rolling time window mechanism, triggering a Bayesian inference update when acquiring new current pipeline inspection data, taking the historical posterior distribution as the new prior distribution and combining it with the new current pipeline inspection data, iteratively generating an updated posterior prediction distribution, thereby realizing the self-correction and continuous learning of the pipeline defect development state prediction model.

[0091] S305. The pipeline defect development state prediction device acquires the basic information of the target pipeline, inputs the basic information of the target pipeline into the pipeline defect development state prediction model, and outputs the pipeline defect development state of the target pipeline.

[0092] The basic information includes at least one of the following: material property parameters, environmental impact factors, and operating condition parameters.

[0093] The above-mentioned S305 can be applied to pipelines that cannot be internally inspected. Specifically, by constructing a pipeline defect development state prediction model as described above, relevant information about pipelines that cannot be internally inspected (i.e., basic information of the target pipeline, mainly the key factors affecting pipeline defect development) can be input. By calling the pipeline defect development state prediction model, the pipeline defect development state of the target pipeline that cannot be internally inspected can be given (i.e., the distribution of pipeline defect development and the pipeline defect development trend (e.g., short-term pipeline defect development trend and long-term pipeline defect development trend)). The above-mentioned multi-source prior knowledge can be fully utilized to make up for the lack of current pipeline inspection data and to predict and analyze pipelines that cannot be internally inspected.

[0094] For example, for pipelines where ILI cannot be implemented, the pipeline defect development status prediction device records the key influencing factors of pipeline defect development, calls the optimized pipeline defect development status prediction model, and outputs the pipeline defect distribution status and short- and long-term development trends, relying on multi-source prior knowledge to make up for the prediction limitations caused by data gaps.

[0095] In addition, S304 and S305 mentioned above can be considered as parallel alternatives.

[0096] This application implements a full-process prediction method that integrates the aforementioned multi-source prior knowledge through a pipeline defect development state prediction device. This method optimizes the pipeline inspection data processing and pipeline defect development state prediction model construction process by systematically integrating and quantifying prior knowledge, thereby improving the accuracy of pipeline defect development state prediction and the ability to quantify uncertainty, and providing support for pipeline operation and maintenance safety. In other words, this method constructs a dynamically iteratively updated pipeline defect development state prediction model by systematically sorting out, quantifying, and deeply integrating multi-source prior knowledge, realizing in-depth mining of pipeline defect development laws and accurate prediction of short- and long-term pipeline defect development trends, while providing an effective means of pipeline defect development analysis for pipelines that cannot implement ILI.

[0097] Specifically, this application breaks away from the reliance of traditional prediction models on massive amounts of historical inspection data, significantly improving the accuracy of pipeline defect prediction in newly built pipelines and data-scarce scenarios; by introducing prior distributions and probabilistic outputs, it achieves a quantitative characterization of the uncertainty of pipeline defect development, providing comprehensive support for pipeline risk assessment; it can complete pipeline defect evolution analysis for pipelines where ILI (In-line Pipeline) cannot be carried out, filling the gap in existing technology applications; and it accurately identifies key influencing factors and evolution patterns of pipeline defect development, providing precise technical guidance for operation and maintenance decisions such as pipeline maintenance timing and scope.

[0098] It is understood that the above-mentioned method for predicting the development state of pipeline defects can be implemented by a pipeline defect development state prediction device. To achieve the above functions, the pipeline defect development state prediction device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, the embodiments disclosed in this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments disclosed in this application.

[0099] The embodiments disclosed in this application can divide the pipeline defect development state prediction device generated by the above method example into functional modules. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in the embodiments disclosed in this application is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0100] Figure 4 This is a schematic diagram of another pipeline defect development state prediction device 40 provided in an embodiment of this application. Figure 4 As shown, the pipeline defect development state prediction device 40 can be used to perform... Figure 1 as well as Figure 2 The pipeline defect development state prediction method is shown. The pipeline defect development state prediction device 40 includes: an acquisition unit 401 and a processing unit 402.

[0101] The acquisition unit 401 is used to acquire multi-source prior knowledge and historical pipeline inspection data related to pipeline defect development; the processing unit 402 is used to quantify and characterize the multi-source prior knowledge to obtain quantified multi-source prior knowledge; the processing unit 402 is also used to construct a pipeline defect development state prediction model based on the quantified multi-source prior knowledge and historical pipeline inspection data; the processing unit 402 is also used to determine the pipeline defect development state of the target pipeline through the pipeline defect development state prediction model.

[0102] In one possible implementation, the acquisition unit 401 is further used to acquire basic information of the target pipeline, which includes at least one of the following: material property parameters, environmental influencing factors, and operating condition parameters; the processing unit 402 is used to input the basic information of the target pipeline into the pipeline defect development state prediction model and output the pipeline defect development state of the target pipeline.

[0103] In one possible implementation, the acquisition unit 401 is further configured to acquire the current pipeline inspection data of the target pipeline; the processing unit 402 is configured to perform a global sensitivity analysis based on the current pipeline inspection data through a pipeline defect development state prediction model to mine the pipeline defect development pattern, and to perform dynamic prediction based on the current pipeline inspection data using a rolling time window mechanism; the processing unit 402 is configured to combine the pipeline defect development pattern and the dynamic prediction results to determine the pipeline defect development state of the target pipeline.

[0104] In one possible implementation, the processing unit 402 is specifically used to: convert deterministic prior knowledge into numerical or interval form and assign values; and / or, convert empirical prior knowledge into computable probability values ​​through mathematical methods; and / or, describe uncertain prior knowledge using a probability distribution model.

[0105] In one possible implementation, multi-source prior knowledge includes at least one of the following: industry standards and specifications, historical test data, material property parameters, environmental influencing factors, and expert experience knowledge.

[0106] In one possible implementation, the processing unit 402 is specifically used to: preprocess the original historical pipeline inspection data based on multi-source prior knowledge, the preprocessing including at least one of the following: removing abnormal noise data, interpolating to complete missing data, and correcting and completing the results based on expert experience; constructing feature parameters from the preprocessed historical pipeline inspection data based on multi-source prior knowledge, and selecting key feature parameters for pipeline defect development.

[0107] In one possible implementation, the processing unit 402 is specifically used to: set the quantified multi-source prior knowledge as the prior distribution of the model, and use historical pipeline inspection data as observation data to update the model parameters through a Bayesian inference algorithm to obtain the posterior distribution; and construct a pipeline defect development probability prediction model based on the posterior distribution.

[0108] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0109] This application also provides a computer-readable storage medium storing instructions that, when executed by a processor of an electronic device, enable the electronic device to perform the pipeline defect development state prediction method provided in the embodiments of this application.

[0110] This application also provides a computer program product containing instructions that, when run on an electronic device, causes the electronic device to execute the pipeline defect development state prediction method provided in the above-described embodiments of this application.

[0111] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires; a portable computer disk drive; a hard disk drive; a random access memory (RAM); a read-only memory (ROM); an erasable programmable read-only memory (EPROM); a register; a hard disk drive; an optical fiber; a portable compact disc read-only memory (CD-ROM); an optical storage device; a magnetic storage device; or any suitable combination thereof; or any other form of computer-readable storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may reside in an application-specific integrated circuit (ASIC). In the embodiments of this application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0112] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for predicting the development state of pipeline defects, characterized in that, include: Acquire multi-source prior knowledge and historical pipeline inspection data related to pipeline defect development; The multi-source prior knowledge is quantitatively represented to obtain the quantified multi-source prior knowledge. Based on the quantified multi-source prior knowledge and the historical pipeline inspection data, a pipeline defect development state prediction model is constructed. The pipeline defect development state prediction model is used to determine the pipeline defect development state of the target pipeline.

2. The method according to claim 1, characterized in that, The step of determining the pipeline defect development state of the target pipeline using the pipeline defect development state prediction model includes: Obtain basic information about the target pipeline, including at least one of the following: material property parameters, environmental influencing factors, and operating condition parameters; The basic information of the target pipeline is input into the pipeline defect development state prediction model, and the pipeline defect development state of the target pipeline is output.

3. The method according to claim 1, characterized in that, The step of determining the pipeline defect development state of the target pipeline using the pipeline defect development state prediction model includes: Obtain the current pipeline inspection data of the target pipeline; Based on the current pipeline inspection data, a global sensitivity analysis is performed using the pipeline defect development status prediction model to uncover the development patterns of pipeline defects, and a rolling time window mechanism is used to perform dynamic prediction based on the current pipeline inspection data. Based on the aforementioned pipeline defect development patterns and dynamic prediction results, the pipeline defect development status of the target pipeline is determined.

4. The method according to claim 1, characterized in that, The quantitative representation of the multi-source prior knowledge includes: Transform deterministic prior knowledge into numerical or range forms and assign values; and / or, Transforming empirical prior knowledge into computable probability values ​​using mathematical methods; and / or, The prior knowledge of uncertainty is described using a probability distribution model.

5. The method according to claim 1 or 4, characterized in that, The multi-source prior knowledge includes at least one of the following: industry standards and norms, historical test data, material property parameters, environmental influencing factors, and expert experience knowledge.

6. The method according to claim 1, characterized in that, The historical pipeline inspection data includes key characteristic parameters of pipeline defect development. The acquisition of historical pipeline inspection data includes: Based on the aforementioned multi-source prior knowledge, the original historical pipeline inspection data is preprocessed. The preprocessing includes at least one of the following: removing abnormal noise data, interpolating to complete missing data, and correcting and completing the results by combining expert experience. Based on the aforementioned multi-source prior knowledge, feature parameters are constructed from preprocessed historical pipeline inspection data, and key feature parameters for pipeline defect development are obtained by screening.

7. The method according to claim 1, characterized in that, The method for constructing a pipeline defect development state prediction model based on the quantified multi-source prior knowledge and the historical pipeline inspection data includes: The quantified multi-source prior knowledge is set as the prior distribution of the pipeline defect development state prediction model, and the historical pipeline detection data is used as the observation data. The model parameters are updated through a Bayesian inference algorithm to obtain the posterior distribution. A pipeline defect development probability prediction model is constructed based on the posterior distribution.

8. A device for predicting the development state of pipeline defects, characterized in that, include: Acquisition unit and processing unit; The acquisition unit is used to acquire multi-source prior knowledge and historical pipeline inspection data related to pipeline defect development; The processing unit is used to quantify the multi-source prior knowledge to obtain quantified multi-source prior knowledge. The processing unit is also used to construct a pipeline defect development state prediction model based on the quantified multi-source prior knowledge and the historical pipeline inspection data. The processing unit is also used to determine the pipeline defect development state of the target pipeline using the pipeline defect development state prediction model.

9. A device for predicting the development state of pipeline defects, characterized in that, include: Processor, communication interface, and memory; The communication interface is coupled to the processor, and the memory is used to store computer programs or instructions. The processor is used to execute computer programs or instructions stored in the memory to implement the pipeline defect development state prediction method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed by a computer, enable the computer to perform the pipeline defect development state prediction method as described in any one of claims 1-7.

Images