High-temperature pipeline health on-line monitoring method and system

Abstract

The invention discloses a high-temperature pipeline health on-line monitoring method and system. The method comprises the following steps: constructing a pipeline model; stress and temperature data are obtained through pipeline model simulation, a pipeline dangerous point is obtained, and the internal and external wall temperature stress relation is determined; dynamically obtaining a predicted wall thickness reduction rate model by combining the dangerous point wall thickness with the environmental parameters; analyzing the dynamic characteristics of the wall thickness and the temperature to obtain a temperature-wall thickness dual-drive stress threshold value; based on the dual-cycle matrix, a pipeline fatigue model is obtained by combining the coupling characteristics of the wall thickness and the temperature; and a time-varying residual life prediction model is obtained by combining damage accumulation, and the service life of the pipeline is predicted. According to the method, the model is constructed based on the distribution rule of the pipeline temperature and stress along the pipeline wall, accurate calculation of the inner wall temperature and stress is achieved, the pipeline wall thickness reduction rate is dynamically calculated, and early warning is achieved for abnormal increase of the pipeline wall thickness reduction rate; the residual life of the monitored pipeline is accurately predicted, the detection efficiency is improved, and the detection cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline detection, and in particular to a method and system for online health monitoring of high-temperature pipelines. Background Art

[0002] Supercritical pressure thermal power generation is a new technology for efficient energy utilization. Its steam temperature and pressure exceed those of previous units, significantly improving thermal efficiency. However, these high parameters also place higher demands on the safety of various unit components and on-site monitoring. To prevent premature failure of critical metal components in thermal power units, China currently relies primarily on offline, indirect, and static preventive inspections. This involves utilizing downtime for maintenance to conduct on-site inspections of critical components using nondestructive testing (NDT), promptly identifying and addressing defects. This has also led to the development of systematic inspection and maintenance procedures.

[0003] However, the disadvantages of this treatment method are: (1) limited inspection opportunities: that is, inspection and testing can only be carried out during shutdown and maintenance, and online real-time monitoring cannot be achieved; (2) high cost and long cycle: in order to ensure the metal inspection needs of unit components, the unit needs to be cooled in advance, scaffolding needs to be erected, insulation needs to be removed, and polishing needs to be done, which not only consumes a long downtime, but also consumes a lot of maintenance costs; (3) the inspection results are limited: the current inspection is an offline, indirect static inspection, which is based on the calculation of a theoretical model containing defects and predicts the impact of defects on component safety, but cannot achieve direct, real-time visual monitoring and prediction purposes. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method and system for online monitoring of high-temperature pipeline health to solve the problems of existing detection and monitoring methods, such as limited timing, requiring the unit to be cooled and prepared in advance, and high time and material costs; at the same time, the detection results are static data, which cannot predict wall thickness changes and service life in real time, and provide corresponding visual early warnings.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for online health monitoring of a high-temperature pipeline, comprising:

[0008] Obtain pipeline parameters and build pipeline model;

[0009] By simulating the pipeline model, stress and temperature data are obtained to obtain pipeline danger points and determine the temperature-stress relationship between the inner and outer walls;

[0010] The wall thickness at the dangerous point is combined with the environmental parameters to dynamically obtain a model for predicting the wall thickness reduction rate, which is used for the first prediction of the pipeline inner wall.

[0011] Combined with the first prediction, the dynamic characteristics of the wall thickness and temperature are analyzed to obtain the temperature-wall thickness dual-driven stress threshold, and a second prediction of the pipeline inner wall is performed;

[0012] Based on the double-loop matrix, the pipeline fatigue model is obtained by combining the coupling characteristics of wall thickness and temperature;

[0013] The pipeline fatigue model is combined with damage accumulation to obtain a time-varying remaining life prediction model to predict the pipeline life.

[0014] As a preferred solution of the high-temperature pipeline health online monitoring method of the present invention, wherein: obtaining stress and temperature data through pipeline model simulation to obtain pipeline danger points includes:

[0015] By simulating the operation status of the pipeline model, the temperature and stress distribution diagram of the pipeline under the influence of wall thickness is obtained;

[0016] Determine the maximum temperature and stress area of ​​the pipeline, which is the danger point.

[0017] As a preferred solution of the high-temperature pipeline health online monitoring method of the present invention, the determining of the relationship between the inner and outer wall temperature stresses includes:

[0018] Based on the pipeline model simulation operation status, the temperature gradient model is obtained by setting the thermal conductivity, outer wall heat flux density change rate, thermal-mechanical coupling correction coefficient and real-time wall thickness.

[0019] Based on the pipeline model simulation operation status, the real-time stress is calculated by combining the wall thickness stress concentration index, temperature-related elastic modulus, and material thermal expansion coefficient to obtain the stress gradient model.

[0020] As a preferred solution of the high-temperature pipeline health online monitoring method of the present invention, a model for predicting the wall thickness thinning rate is obtained by dynamically combining the wall thickness at the dangerous point with environmental parameters, including:

[0021] Based on the current dangerous point wall thickness value, the weighted sum of the wall thickness difference values ​​in the historical time period is superimposed and the residual correction is performed;

[0022] Introducing the coupled acceleration term of temperature and stress;

[0023] Based on the curvature direction function, the concave-convex change of the wall thickness thinning rate is judged to obtain the wall thickness thinning rate.

[0024] As a preferred embodiment of the high-temperature pipeline health online monitoring method of the present invention, the dynamic characteristics of the wall thickness and temperature are analyzed to obtain the temperature-wall thickness dual-drive stress threshold, and a second prediction of the pipeline inner wall is performed, including:

[0025] The rain flow matrix of dangerous points is obtained by rain flow counting method; the stress allowable cycle matrix is ​​obtained according to SN curve;

[0026] Based on the dual matrix to quantify the effect of temperature change on fatigue life, the temperature correction term is obtained;

[0027] By setting the degradation rate coefficient of the combined temperature, the weakening effect of wall thickness reduction on the load-bearing capacity is quantified, and the wall thickness degradation correction term is obtained;

[0028] Based on the two correction terms and combined with the baseline reference stress, the dual-drive stress threshold is obtained;

[0029] Based on the dual-drive stress threshold, different warning coefficients are set and compared with the actual stress value to perform safety prediction and warning.

[0030] As a preferred solution of the high-temperature pipeline health online monitoring method of the present invention, a pipeline fatigue model is obtained based on a double-loop matrix and the coupling characteristics of wall thickness and temperature, including:

[0031] Based on the actual number of cycles under different working conditions and the number of fatigue failure cycles under the corresponding working conditions, combined with the coupling index of temperature and wall thickness, the cyclic damage is obtained;

[0032] At the same time, an exponential decay function is introduced to obtain the damage of pipeline degradation caused by wall thickness thinning;

[0033] The pipeline fatigue model is obtained by combining the cyclic damage and degradation damage.

[0034] As a preferred solution of the high-temperature pipeline health online monitoring method of the present invention, a time-varying remaining life prediction model is obtained by combining the pipeline fatigue model with damage accumulation, including:

[0035] Obtain the potential capacity of the remaining life through pipeline fatigue model;

[0036] The remaining life is obtained by the ratio of potential capacity to damage evolution rate.

[0037] In a second aspect, the present invention provides a high-temperature pipeline health online monitoring system, comprising: an acquisition module for acquiring pipeline parameters and constructing a pipeline model;

[0038] A first calculation module is used to obtain stress and temperature data through the pipeline model simulation, obtain pipeline danger points, and determine the temperature-stress relationship between the inner and outer walls;

[0039] The first model builds a prediction module, which is used to dynamically obtain a predicted wall thickness thinning rate model by combining the wall thickness at the dangerous point with environmental parameters, and is used for the first prediction of the pipeline inner wall;

[0040] The second model constructs a prediction module, which is used to analyze the dynamic characteristics of the wall thickness and temperature in combination with the first prediction, obtain the temperature-wall thickness dual-drive stress threshold, and perform a second prediction of the pipeline inner wall;

[0041] The third model builds a prediction module, which is used to obtain the pipeline fatigue model based on the double-loop matrix and the coupling characteristics of wall thickness and temperature;

[0042] The fourth model construction prediction module is used to predict the pipeline life by obtaining a time-varying remaining life prediction model based on the pipeline fatigue model in combination with damage accumulation.

[0043] In a third aspect, the present invention provides an electronic device, comprising:

[0044] memory and processor;

[0045] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the high-temperature pipeline health online monitoring method are implemented.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the high-temperature pipeline health online monitoring method.

[0047] Compared with existing technologies, the present invention offers the following advantages: By simulating pipelines and combining them with actual monitoring sensors, it enables online monitoring of temperature, stress, and wall thickness at key locations. Based on the distribution patterns of pipeline temperature and stress along the pipe wall, a model is constructed to accurately estimate the inner wall temperature and stress, dynamically calculate the rate of thinning of the pipe wall thickness, and provide early warning of abnormal increases in the rate of thinning. Furthermore, by optimizing algorithms and reference factors, a corresponding temperature-wall-thickness dual-driven stress threshold and pipeline fatigue model is constructed. Combined with damage accumulation, a time-varying remaining life prediction model is derived, accurately predicting the remaining life of the monitored pipeline. This improves detection efficiency, reduces detection costs, and achieves high-precision predictions and early warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 The figure is a schematic diagram of the overall process of a method for online health monitoring of high-temperature pipelines according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0051] Example 1, with reference to Figure 1 , as one embodiment of the present invention, provides a method for online health monitoring of high-temperature pipelines, comprising:

[0052] S100: Obtain pipeline parameters and build a pipeline model;

[0053] S200: Obtain stress and temperature data through pipeline model simulation, obtain pipeline danger points, and determine the temperature-stress relationship between the inner and outer walls;

[0054] S300: A model for predicting wall thickness reduction rate is obtained by combining the wall thickness at the dangerous point with environmental parameters, which is used for the first prediction of the pipeline inner wall.

[0055] S400: Combined with the first prediction, the dynamic characteristics of wall thickness and temperature are analyzed to obtain the temperature-wall thickness dual-drive stress threshold, and a second prediction of the pipeline inner wall is performed;

[0056] S500: Based on a double-loop matrix, the pipeline fatigue model is obtained by combining the coupling characteristics of wall thickness and temperature;

[0057] S600: The pipeline life is predicted by combining the pipeline fatigue model with the damage accumulation to obtain a time-varying remaining life prediction model.

[0058] It should be noted that thermal power plant steam pipelines are thick-walled. During operation, parameters such as internal and external temperature, pressure, and medium flow rate fluctuate significantly, resulting in significant temperature and stress gradients in the pipelines. The pipe wall thickness also changes due to the influence of condensate backflow. Operating pipelines are exposed to high temperature and high pressure, making the measurement of temperature and stress gradients difficult and often leading to delayed safety warnings. Furthermore, steam scouring within the steam pipelines causes the pipe wall thickness to decrease, which in turn endangers the pipeline's health. The high temperature and high pressure environment significantly affects wall thickness measurement and can also cause pipeline damage due to fatigue. Therefore, monitoring and predicting pipeline health are crucial.

[0059] Therefore, in response to the above-mentioned operation monitoring and health prediction problems, a model is constructed through steps S100-S600 to simulate the operating status of the pipeline under typical working conditions, and the temperature and stress distribution diagram and relationship of the pipeline under the influence of wall thickness are obtained, so as to accurately calculate the inner wall temperature and stress; realize real-time monitoring of pipeline wall thickness, dynamically calculate the pipeline wall thickness thinning rate, and provide early warning for abnormal increases in the pipeline thinning rate; at the same time, based on fatigue damage and remaining life models, accurate prediction of the remaining life of the pipeline is achieved.

[0060] Example 2, reference Figure 1 , which is an embodiment of the present invention, provides a high-temperature pipeline health online monitoring method based on the above embodiment.

[0061] In the embodiment of the present application, in step S100 , pipeline parameters are obtained and a pipeline model is constructed by obtaining basic parameters such as size and environment, and then a finite element model is constructed for simulation.

[0062] In an optional embodiment, the pipeline model constructed in step S100 can also be simulated by the finite volume method, which divides the pipeline into discrete control volumes and performs simulation and numerical solution based on the mass, momentum and energy conservation equations.

[0063] In another optional embodiment, the pipeline model constructed in step S100 can also be constructed by using the finite difference method to discretize the differential equations, replace the derivatives with difference approximations, and directly solve the pipeline parameters, such as temperature distribution and stress field.

[0064] In the embodiment of the present application, step S200 obtains stress and temperature data through pipeline model simulation to obtain pipeline danger points, including the following steps A1-A2:

[0065] A1: Use pipeline model to simulate the operating status and obtain the temperature and stress distribution diagram of the pipeline under the influence of wall thickness;

[0066] A2: Determine the maximum temperature and stress area of ​​the pipeline. The maximum value area is the danger point.

[0067] In an optional embodiment, the method for obtaining the pipeline dangerous point in step S200 can also be through analyzing the interaction between the temperature field and the stress field, such as the thermal stress concentration effect and combining the thermal expansion coefficient and constraint conditions of the material to calculate the thermal stress distribution, that is, simulating the superposition effect of the temperature field gradient and the mechanical stress, and identifying the area of ​​stress mutation under the action of thermal-mechanical coupling.

[0068] In another optional embodiment, the method for obtaining the pipeline dangerous point in step S200 can also be to simulate the dynamic loads in the actual operation of the pipeline, such as pressure fluctuations, transient temperature changes, etc., combined with fatigue damage accumulation theory, such as Miner's law, to identify the area with the fastest damage accumulation rate and determine the dangerous point.

[0069] In the embodiment of the present application, determining the temperature stress relationship between the inner and outer walls in step S200 includes the following steps B1-B2:

[0070] B1: Based on the pipeline model, the operating status is simulated. The temperature gradient model is obtained by setting the thermal conductivity, the outer wall heat flux density change rate, the thermal-mechanical coupling correction factor and the real-time wall thickness.

[0071] B2: Based on the pipeline model simulation operation status, the real-time stress is calculated by combining the wall thickness stress concentration index, temperature-related elastic modulus, and material thermal expansion coefficient to obtain the stress gradient model.

[0072] Specifically, in B1, the specific representation of the temperature gradient model is:

[0073]

[0074] Where, T in (t), T out (t) is the inner / outer wall temperature (°C); δ(t) is the real-time wall thickness (mm), which can be dynamically updated by ultrasonic thickness measurement; λ(T out ) is the temperature-dependent dynamic thermal conductivity, which can be fitted by high-temperature thermal conductivity experiments; is the rate of change of heat flux density on the outer wall; α is the thermal-mechanical coupling correction coefficient, which can be calibrated experimentally; Δε is the strain increment on the outer wall; is the partial derivative of stress with respect to temperature, reflecting the sensitivity of material stress to temperature changes; β is the influencing factor of wall thickness degradation, which can be dynamically corrected by the finite element model; δ0 is the initial wall thickness of the pipe; ln(·) is the natural logarithm function;

[0075] It should be noted that in the formula is the dynamic thermal-mechanical coupling term, To describe the cumulative effect of wall thickness reduction on temperature distribution, such as local corrosion leading to reduced thermal resistance and increased inner wall temperature.

[0076] Specifically, in B2, the specific representation of the stress gradient model is:

[0077]

[0078] Where, σ in , σ outis the equivalent stress of the inner / outer wall; γ and n are the stress concentration index of the wall thickness, which can be calibrated by the experimental platform; E(T out ) is the temperature-dependent elastic modulus; α th is the thermal expansion coefficient of the material; ΔT grad is the temperature gradient between the inner and outer walls; v is the Poisson's ratio;

[0079] It should be noted that in the formula It is mainly used to describe the local stress amplification effect caused by wall thickness reduction; in the formula Mainly used to calculate the temperature difference ΔT between the inner and outer walls grad The thermal stress caused by this is accurately quantified by coupling wall thickness degradation with thermal loads, which is used for subsequent fatigue life prediction.

[0080] In an optional embodiment, determining the temperature-stress relationship between the inner and outer walls in step S200 may further include jointly verifying the temperature-stress relationship using finite element analysis and experiments, converting the model accuracy into a measurable indicator to ensure the accuracy of the model prediction. This not only verifies single-point data, but also verifies whether the spatial or temporal gradient distribution of temperature and stress is consistent with the experiment, thereby avoiding the accumulation of local errors that may lead to overall failure.

[0081] For example, it can be verified by the following formula:

[0082]

[0083] Among them, ValidationIndex is a measurable indicator of model accuracy and is set to 5%.

[0084] It should be noted that the above-mentioned temperature-stress relationship model of the inner and outer walls introduces the thermal-mechanical-thickness coupling term, which avoids the limitations of a single heat transfer model. Key parameters such as thermal conductivity and elastic modulus use temperature-related functions rather than empirical fixed values. At the same time, the degradation process is quantified and dynamic characteristics are taken into account, providing an accurate judgment basis for subsequent steps.

[0085] In the embodiment of the present application, in step S300, a model for predicting the wall thickness reduction rate is obtained by dynamically combining the wall thickness at the dangerous point with the environmental parameters, and a first prediction is performed, including the following steps C1-C3:

[0086] C1: Based on the current dangerous point wall thickness value, the weighted sum of the wall thickness difference values ​​in the historical time period is superimposed and the residual correction is performed;

[0087] C2: Introducing the coupled acceleration term of temperature and stress;

[0088] C3: Based on the curvature direction function, the concave-convex change of the wall thickness thinning rate is judged to obtain the wall thickness thinning rate.

[0089] The first prediction is to predict and deduce the inner wall thickness, and the wall thickness is predicted by combining the wall thinning rate model through the step S200.

[0090] Specifically, the wall thickness thinning rate model of C1-C3 can be expressed by the following formula:

[0091]

[0092] Where, is the predicted wall thickness value in the next k hours (mm); δ(t) is the actual wall thickness measurement value at the current time t; p is the order of the autoregressive term; φ i (t) is the time-varying autoregressive coefficient, which is dynamically updated by the recursive least squares method RLS; Δ d is the adaptive difference operator, d is the dynamically adjusted difference order; i is the time cycle index; θ j (t) is the moving average coefficient, which is optimized in real time by the online EM expectation maximization algorithm; η is the degradation acceleration factor, which is fitted by the wall thickness historical data; λ is the environmental coupling coefficient, which is associated with the real-time temperature / stress monitoring value; is the curvature direction indicator function, which is used to capture the sudden change characteristics of the thinning rate; ∈(tj) is the residual term at the historical moment tj; e λk To describe the nonlinear amplification effect of environmental factors (temperature / stress) on the degradation rate.

[0093] For example, some coupling coefficients can be calculated as follows:

[0094]

[0095] In the formula, the d value is dynamically adjusted with the ADF test statistic;

[0096]

[0097] It should be noted that this model is preferred because its core logic is divided into four parts. One is the autoregressive historical trend, which is based on the current wall thickness value δ(t) and the weighted sum of the past p-order wall thickness difference values ​​(i.e., φ i (t) is dynamically updated to capture the historical attenuation law; the weighted sum of the past q-order prediction error terms ∈(tj) is introduced to correct the model residuals; the exponential term η·e λk Amplify the nonlinear effects of temperature and pressure on degradation and use the curvature direction function Determine the unevenness of the wall thinning rate, such as accelerated or decelerated thinning), enhance the response to sudden anomalies, and achieve multi-factor coupled prediction of the wall thickness in the next k hours.

[0098] In an optional embodiment, in step S300, a model for predicting the wall thickness thinning rate is obtained by dynamically combining the wall thickness at the dangerous point with environmental parameters. A quantitative relationship between the corrosion rate and the physical and chemical conditions can also be established based on the corrosion mechanism of the pipeline material, such as electrochemical corrosion, combined with environmental parameters such as flow rate, which is suitable for pipelines with richer scenarios.

[0099] In another optional embodiment, in step S300, a wall thickness thinning rate prediction model is obtained by dynamically combining the wall thickness of the dangerous point with the environmental parameters. It can also be predicted by fusion of multi-source data through machine learning. For example, historical monitoring data such as wall thickness, temperature, stress, environmental parameters and machine learning algorithms such as LSTM and random forest are used to train an end-to-end wall thickness thinning rate prediction model.

[0100] In the embodiment of the present application, in step S400: combining the first prediction, analyzing the dynamic characteristics of wall thickness and temperature, obtaining the temperature-wall thickness dual-drive stress threshold, and performing the second prediction of the pipeline inner wall, including the following steps D1-D5:

[0101] D1: The rain flow matrix of the dangerous point is obtained by the rain flow counting method; the stress allowable cycle number matrix is ​​obtained according to the SN curve;

[0102] D2: Quantify the effect of temperature change on fatigue life based on the dual matrix and obtain the temperature correction term;

[0103] D3: By setting the degradation rate coefficient of the combined temperature, the weakening effect of wall thickness thinning on the load-bearing capacity is quantified to obtain the wall thickness degradation correction term;

[0104] D4: Based on the two correction terms, the dual-drive stress threshold is obtained in combination with the baseline reference stress;

[0105] D5: Based on the dual-drive stress threshold, different warning coefficients are set and compared with the actual stress value to perform safety prediction and warning.

[0106] Specifically, the temperature-wall thickness dual-drive stress threshold of D1-D4 can be expressed by the following formula:

[0107]

[0108] Where, ln(N f / N ref ) represents the number of rain flow matrix cycles N f (ie: actual number of cycles) relative to the SN curve to obtain the stress allowable cycle number N ref (ie, reference cycle number) life decay; ln(R T) represents the accelerating effect of temperature on life; f(δ) introduces the regulating effect of wall thickness δ on the temperature-life relationship, reflecting the nonlinear coupling of wall thickness degradation and temperature effect; δ0-δ(t) represents the loss of current wall thickness relative to the initial value; λ(T)·δ crit Indicates the temperature-material failure sensitivity;

[0109] For example, the above parameters can be specifically expressed as:

[0110]

[0111] Where Q is the activation energy, which can be used for temperature fatigue test calibration; is the real-time temperature change rate;

[0112]

[0113] Where α and β are material constants calibrated by experiments; δ crit is the critical wall thickness;

[0114]

[0115] Where, T trans is the ductile-brittle transition temperature of the material; T It is a temperature-sensitive broadband and can be determined by DMA testing.

[0116] It should be noted that the construction form of the above-mentioned threshold model quantifies the influence of actual temperature fluctuations through dynamic temperature integration, thereby replacing the traditional equivalent temperature method. It can solve the temperature mutation caused by condensate backflow, and separate the degradation effect of wall thickness and temperature effect through the f(δ) function; the additional damage caused by sudden temperature change can be captured in the accelerated effect of temperature on life, and λ(T) can automatically enhance the weight of wall thickness correction in the form of an error function.

[0117] For example, in D5, different warning coefficients are set based on the dual-drive stress threshold and compared with the actual stress value, which can be expressed as:

[0118] If Δσ 实际 ≥Δσ th (T,δ), then a first-level warning is issued;

[0119] If 0.8Δσ th (T,δ)≤Δσ 实际 <Δσ th (T,δ), then a second-level warning is issued;

[0120] If Δσ 实际 <0.8Δσ th (T,δ), it is judged to be a safe state.

[0121] In an optional embodiment, the dynamic characteristics of wall thickness and temperature are analyzed in step S400 to obtain a temperature-wall thickness dual-driven stress threshold. The stress threshold can also be defined by dynamically calculating the effects of wall thickness thinning and temperature fluctuations on the critical crack size by combining the fracture toughness and crack growth rate of the pipeline material.

[0122] In another optional embodiment, the dynamic characteristics of wall thickness and temperature are analyzed in step S400 to obtain the temperature-wall thickness dual-driven stress threshold. Monte Carlo simulation can also be used to consider the uncertainty of temperature, wall thickness and environmental parameters, calculate the failure probability, and define a dynamic stress threshold, which is mainly used to quantify risks and avoid the conservatism of deterministic models.

[0123] In the embodiment of the present application, step S500 obtains a pipeline fatigue model based on a double-loop matrix and in combination with the coupling characteristics of wall thickness and temperature, including the following steps E1-E3:

[0124] E1: Based on the actual number of cycles under different working conditions and the number of cycles to fatigue failure under the corresponding working conditions, combined with the coupling index of temperature and wall thickness, the cyclic damage is obtained;

[0125] E2: At the same time, an exponential decay function is introduced to obtain the damage caused by wall thickness thinning to pipeline degradation;

[0126] E3: The pipeline fatigue model is obtained by combining the cyclic damage and degradation damage.

[0127] Specifically, the pipeline fatigue model of E1-E3 can be expressed by the following formula:

[0128]

[0129] Where D(t) is the total fatigue damage value, ranging from [0, 1). If it is greater than or equal to 1, the pipeline fails. m is the number of working condition classification dimensions, such as the number of temperature levels. n is the number of working condition classification dimensions, such as the number of stress level levels. i is the corresponding temperature category index. j is the stress category index. n is the number of working condition classification dimensions, such as the number of stress level levels. ij is the actual number of cycles under working condition (i, j); N f,ij is the number of fatigue failure cycles under working condition (i, j); Γ(T ij ,δ ij ) is the temperature-wall thickness coupling correction index; α is the degradation damage coupling coefficient; is the wall thinning rate; N f,δ (τ) is the remaining fatigue life (number of cycles) under the current wall thickness; τ is the time variable.

[0130] For example, some of the above parameters can be expressed as:

[0131]

[0132] Among them, when T>500℃ and δ<0.8δ0, the Γ value is automatically amplified by 2-3 times;

[0133]

[0134] Among them, the remaining number of cycles N under the current wall thickness f,δ (τ) An exponential decay function is introduced to quantify the nonlinear effect of wall thickness reduction on lifespan;

[0135]

[0136] Among them, this part assigns higher weights to super-threshold stress cycles through the sigmoid function;

[0137]

[0138] m(T)=3.0+0.02(T-400)(400℃≤T≤600℃)

[0139] In an optional embodiment, if S400 combines the fracture toughness and crack growth rate of the pipeline material, then S500 can be based on the continuous damage mechanics coupled evolution model, regard wall thickness thinning and temperature fluctuations as continuous damage variables, and describe the accumulation process of fatigue damage through the thermal-mechanical coupling constitutive equation rather than a simple linear superposition.

[0140] In the embodiment of the present application, in step S600, a time-varying remaining life prediction model is obtained by combining the pipeline fatigue model with damage accumulation, including the following steps F1-F2:

[0141] F1: Potential capacity of remaining life obtained through pipeline fatigue model;

[0142] F2: The remaining life is obtained by the ratio of potential capacity to damage evolution rate.

[0143] Specifically, the time-varying remaining life prediction model of F1-F2 can be expressed by the following formula:

[0144]

[0145] Where, L rem (t) is the time-varying remaining life prediction value; D(t) is the cumulative fatigue damage value, which comes from the pipeline fatigue model; η(T) is the temperature-related nonlinear correction coefficient; is the damage accumulation rate, which indicates the instantaneous growth rate of damage at the current moment; is the damage acceleration, which indicates the growth trend of the damage rate; β is the damage acceleration weight coefficient; Indicates that only non-negative values ​​of damage acceleration are considered;

[0146] For example, some of the above parameters can be expressed as:

[0147]

[0148] It should be noted that the 1-D(t) of the above model 1 / η(T) is used to quantify the remaining healthy capacity of the pipeline under the current damage state; η(T) adjusts the nonlinear effect of damage according to temperature; the denominator of the above model is the damage evolution rate, which combines the current damage rate and acceleration to predict future damage trends.

[0149] Exemplarily, the pipeline is operated at a low temperature T = -10°C;

[0150] η(T) = 0.8, current damage D(t) = 0.6;

[0151] Remaining capacity: 1-0.6 1 / 0.8 ≈1-0.6 1.25 ≈1-0.52=0.48;

[0152] Damage rate: β = 1.5;

[0153] Denominator calculation: 0.15 + 1.5 × 0.05 = 0.225 / year 0.15 + 1.5 × 0.05 = 0.225 / year;

[0154] Remaining life: L rem =0.48 / 0.225≈2.13 years.

[0155] It should be noted that the model dynamically corrects the damage capacity and evolution rate, quantifies the nonlinear effect of temperature on the remaining life, and combines damage acceleration to warn of sudden risks, providing real-time and adaptive prediction results for pipeline health detection.

[0156] In an optional embodiment, the physical pipeline and the virtual model, such as the finite element model constructed in step S100, can be synchronized in real time through digital twin technology, combining damage evolution and multi-source data to drive the remaining life prediction.

[0157] In another optional embodiment, if machine learning is used in S400, then S500 can use pipeline multi-source monitoring data, such as wall thickness time series, temperature field, stress spectrum, corrosion rate, etc. to train a deep learning model to directly predict fatigue damage or the remaining life of S600.

[0158] In summary, the present invention clarifies the distribution law of high-temperature pipeline temperature and stress along the pipe wall, constructs a dynamic model based on the detection data of the outer wall of the pipe, realizes the accurate calculation of the inner wall temperature and stress; determines the safety threshold of high-temperature pipeline temperature and stress, realizes over-temperature and overload warning; realizes real-time monitoring of pipeline wall thickness, dynamically calculates the pipeline wall thickness thinning rate, and realizes warning of abnormal increase in pipeline thinning rate; based on fatigue damage model and life prediction model, accurately predicts the remaining life of the monitored pipeline. It can provide intelligent safety warning information for important components, reduce equipment failure and accidents, improve unit operation efficiency, reduce costs and improve benefits,

[0159] Example 3. The above is a schematic diagram of a method for online health monitoring of high-temperature pipelines. It should be noted that the technical solution of this system for online health monitoring of high-temperature pipelines is based on the same concept as the technical solution of the above-mentioned method. For details not described in detail in the technical solution of the system for online health monitoring of high-temperature pipelines in this example, please refer to the description of the technical solution of the above-mentioned method for online health monitoring of high-temperature pipelines.

[0160] This embodiment also provides a high-temperature pipeline health online monitoring system, including:

[0161] The acquisition module is used to obtain pipeline parameters and build pipeline models;

[0162] The first calculation module is used to obtain stress and temperature data through pipeline model simulation, obtain pipeline danger points, and determine the temperature-stress relationship between the inner and outer walls;

[0163] The first model builds a prediction module, which is used to dynamically obtain a predicted wall thickness thinning rate model by combining the wall thickness at the dangerous point with environmental parameters, and is used for the first prediction of the pipeline inner wall;

[0164] The second model builds a prediction module, which is used to combine the first prediction, analyze the dynamic characteristics of wall thickness and temperature, obtain the temperature-wall thickness dual-drive stress threshold, and perform a second prediction of the pipeline inner wall;

[0165] The third model builds a prediction module, which is used to obtain the pipeline fatigue model based on the double-loop matrix and the coupling characteristics of wall thickness and temperature;

[0166] The fourth model construction prediction module is used to predict the pipeline life by using the pipeline fatigue model and combining it with the damage accumulation to obtain a time-varying remaining life prediction model.

[0167] This embodiment also provides an electronic device suitable for online health monitoring of high-temperature pipelines, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method for online health monitoring of high-temperature pipelines proposed in the above embodiment.

[0168] This embodiment further provides a storage medium having a computer program stored thereon. When the program is executed by a processor, the method for online health monitoring of high-temperature pipelines proposed in the above embodiment is implemented.

[0169] The storage medium proposed in this embodiment and the method for realizing online health monitoring of high-temperature pipelines proposed in the above embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0170] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general hardware, and of course can also be implemented by hardware. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0171] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A high-temperature pipeline health online monitoring method, characterized in that: include: Obtain pipeline parameters and build pipeline model; By simulating the pipeline model, stress and temperature data are obtained to obtain pipeline danger points and determine the temperature-stress relationship between the inner and outer walls; The wall thickness at the dangerous point is combined with the environmental parameters to dynamically obtain a model for predicting the wall thickness reduction rate, which is used for the first prediction of the pipeline inner wall. Combined with the first prediction, the dynamic characteristics of the wall thickness and temperature are analyzed to obtain the temperature-wall thickness dual-driven stress threshold, and a second prediction of the pipeline inner wall is performed; Based on the double-loop matrix, the pipeline fatigue model is obtained by combining the coupling characteristics of wall thickness and temperature; The pipeline fatigue model is combined with damage accumulation to obtain a time-varying remaining life prediction model to predict the pipeline life.

2. The high-temperature pipeline health online monitoring method according to claim 1, characterized in that: The stress and temperature data are obtained by simulating the pipeline model to obtain pipeline danger points, including: By simulating the operation status of the pipeline model, the temperature and stress distribution diagram of the pipeline under the influence of wall thickness is obtained; Determine the maximum temperature and stress area of ​​the pipeline, which is the danger point.

3. The high-temperature pipeline health online monitoring method according to claim 2, characterized in that: Determining the relationship between the temperature stress of the inner and outer walls includes: Based on the pipeline model simulation operation status, the temperature gradient model is obtained by setting the thermal conductivity, outer wall heat flux density change rate, thermal-mechanical coupling correction coefficient and real-time wall thickness. Based on the pipeline model simulation operation status, the real-time stress is calculated by combining the wall thickness stress concentration index, temperature-related elastic modulus, and material thermal expansion coefficient to obtain the stress gradient model.

4. The high-temperature pipeline health online monitoring method according to claim 3, characterized in that: The wall thickness at the dangerous point is combined with the environmental parameters to dynamically obtain a model for predicting the wall thickness thinning rate, including: Based on the current dangerous point wall thickness value, the weighted sum of the wall thickness difference values ​​in the historical time period is superimposed and the residual correction is performed; Introducing the coupled acceleration term of temperature and stress; Based on the curvature direction function, the concave-convex change of the wall thickness thinning rate is judged to obtain the wall thickness thinning rate.

5. The high-temperature pipeline health online monitoring method according to claim 4, characterized in that: Analyze the dynamic characteristics of the wall thickness and temperature to obtain the temperature-wall thickness dual-drive stress threshold, and perform a second prediction of the pipeline inner wall, including: The rain flow matrix of dangerous points is obtained by rain flow counting method; the stress allowable cycle number matrix is ​​obtained according to SN curve; Based on the dual matrix to quantify the effect of temperature change on fatigue life, the temperature correction term is obtained; By setting the degradation rate coefficient combined with temperature, the weakening effect of wall thickness reduction on load-bearing capacity is quantified, and the wall thickness degradation correction term is obtained; Based on the two correction terms and combined with the baseline reference stress, the dual-drive stress threshold is obtained; Based on the dual-drive stress threshold, different warning coefficients are set and compared with the actual stress value to perform safety prediction and warning.

6. The high-temperature pipeline health online monitoring method according to claim 5, characterized in that: Based on the double-loop matrix and the coupling characteristics of wall thickness and temperature, the pipeline fatigue model is obtained, including: Based on the actual number of cycles under different working conditions and the number of fatigue failure cycles under the corresponding working conditions, combined with the coupling index of temperature and wall thickness, the cyclic damage is obtained; At the same time, an exponential decay function is introduced to obtain the damage of pipeline degradation caused by wall thickness thinning; The pipeline fatigue model is obtained by combining the cyclic damage and degradation damage.

7. The high-temperature pipeline health online monitoring method according to claim 6, characterized in that: The pipeline fatigue model is combined with damage accumulation to obtain a time-varying remaining life prediction model, including: Obtain the potential capacity of the remaining life through pipeline fatigue model; The remaining life is obtained by the ratio of potential capacity to damage evolution rate.

8. A high-temperature pipeline health online monitoring system, applying the method according to any one of claims 1 to 7, characterized in that: include: The acquisition module is used to obtain pipeline parameters and build pipeline models; A first calculation module is used to obtain stress and temperature data through the pipeline model simulation, obtain pipeline danger points, and determine the temperature-stress relationship between the inner and outer walls; The first model builds a prediction module, which is used to dynamically obtain a predicted wall thickness thinning rate model by combining the wall thickness at the dangerous point with environmental parameters, and is used for the first prediction of the pipeline inner wall; The second model constructs a prediction module, which is used to analyze the dynamic characteristics of the wall thickness and temperature in combination with the first prediction, obtain the temperature-wall thickness dual-drive stress threshold, and perform a second prediction of the pipeline inner wall; The third model builds a prediction module, which is used to obtain the pipeline fatigue model based on the double-loop matrix and the coupling characteristics of wall thickness and temperature; The fourth model construction prediction module is used to predict the pipeline life by obtaining a time-varying remaining life prediction model based on the pipeline fatigue model in combination with damage accumulation.

9. An electronic device comprising: memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the high-temperature pipeline health online monitoring method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the high-temperature pipeline online health monitoring method according to any one of claims 1 to 7.

Images