Multi-modal quantitative evaluation method and system for stray current corrosion degree of oil and gas pipeline

Abstract

The invention discloses an oil and gas pipeline stray current corrosion degree multi-mode quantitative evaluation method and system. The method comprises the steps that stray current parameters, potential gradient distribution and magnetic field intensity data of an oil and gas pipeline are collected in real time; dynamic current density characteristics are extracted from the stray current parameters, and a corrosion hot spot area is constructed according to the dynamic current density characteristics and potential gradient distribution; on the basis of the corrosion hot spot area, the magnetic field intensity data and the soil resistivity parameter are fused, and a stray current corrosion intensity index is calculated; and establishing a corrosion rate prediction model based on the historical stray current corrosion intensity index and the environmental variable, inputting the currently calculated stray current corrosion intensity index into the corrosion rate prediction model, and outputting the corrosion degree and the residual safety life of the pipeline. According to the method, multi-modal information such as dynamic current density characteristics, potential gradient distribution and soil resistivity can be integrated, the corrosion hot spot area can be accurately identified, and the accuracy of the evaluation result of the stray current corrosion degree of the oil and gas pipeline is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas pipeline operation and maintenance, and in particular to a multi-modal quantitative evaluation method and system for the stray current corrosion degree of an oil and gas pipeline. Background Art

[0002] The threat of stray current corrosion to oil and gas pipelines remains a significant challenge for the industry. Current approaches to addressing stray current corrosion in oil and gas pipelines suffer from numerous shortcomings. Traditional monitoring methods struggle to comprehensively and real-timely acquire stray current parameters, potential gradient distribution, and magnetic field strength data. Previously, single-point or scattered point detection was often employed, failing to provide a holistic understanding of the pipeline's condition and easily overlooking key areas of corrosion risk. Furthermore, most corrosion assessment methods rely solely on a single or limited set of parameters, lacking comprehensive analysis and integration of multimodal data. For example, stray current intensity is determined solely by the positive offset of the pipe-to-ground potential relative to the natural potential or the soil potential gradient. This one-sided assessment method fails to accurately reflect the actual corrosion condition of the pipeline, leading to inaccurate identification of corrosion hotspots and inability to accurately calculate the stray current corrosion intensity index. Furthermore, existing technologies for predicting pipeline corrosion rates and remaining safe life often rely on simple empirical models or single environmental factors, resulting in inaccurate predictions and failing to provide a reliable and scientific basis for pipeline maintenance. Summary of the Invention

[0003] In order to solve at least one of the above-mentioned technical problems, the present invention provides a multi-modal quantitative assessment method and system for the degree of stray current corrosion in oil and gas pipelines.

[0004] In a first aspect, the present invention provides a multimodal quantitative assessment method for the degree of stray current corrosion in oil and gas pipelines, characterized in that the method comprises:

[0005] The stray current parameters, potential gradient distribution and magnetic field strength data of oil and gas pipelines are collected in real time through a multimodal sensor array;

[0006] Extract dynamic current density characteristics from stray current parameters and construct corrosion hotspot areas based on dynamic current density characteristics and potential gradient distribution;

[0007] Based on the corrosion hotspot area, the stray current corrosion intensity index is calculated by integrating the magnetic field intensity data and soil resistivity parameters;

[0008] A corrosion rate prediction model is established based on the historical stray current corrosion intensity index and environmental variables. The currently calculated stray current corrosion intensity index is input into the corrosion rate prediction model to output the corrosion degree and remaining safe life of the pipeline.

[0009] Preferably, the real-time collection of stray current parameters, potential gradient distribution, and magnetic field strength data of the oil and gas pipeline by a multimodal sensor array includes:

[0010] Potential gradient probes, Hall current sensors, and magnetic field strength detection units are deployed at equal intervals along the axial direction of the oil and gas pipeline to form distributed nodes;

[0011] Set up a synchronous sampling module to synchronously collect current intensity, potential difference and magnetic field intensity data of each distributed node at a fixed frequency;

[0012] All collected data are marked according to time and space coordinates to construct a three-dimensional data matrix, where the time and space coordinates are determined by the pipeline location, detection time and burial depth parameters.

[0013] Preferably, the step of constructing a corrosion hotspot area according to the dynamic current density characteristics and the potential gradient distribution includes:

[0014] Based on the dynamic current density characteristics, a sliding window algorithm is used to identify the current density peak area and mark it as the initial hot spot area;

[0015] Calculate the potential offset of the initial hotspot area based on the potential gradient distribution, and select the area that meets the potential offset threshold as the candidate corrosion area;

[0016] Obtain the soil resistivity of the candidate corrosion area, and use the weighted fusion algorithm to normalize the current density, potential gradient distribution, and soil resistivity of the candidate corrosion area to generate a corrosion intensity thermodynamic map.

[0017] The areas in the corrosion intensity thermodynamic map where the intensity value exceeds the critical intensity value are marked as corrosion hot spots.

[0018] Preferably, the calculation of the stray current corrosion intensity index comprises:

[0019] ;

[0020] Where, is the stray current corrosion intensity index, is the environmental corrosion sensitivity coefficient, dimensionless, ranging from 0.5 to 3; is the maximum current density in the corrosion hotspot area, in units of ; is the soil infiltration correction factor, dimensionless, ranging from 0.8 to 2.5; is the equivalent penetration depth of stray current, in units of ; is the soil resistivity, in units of .

[0021] Preferably, the corrosion rate prediction model is established based on the historical stray current corrosion intensity index and environmental variables, including:

[0022] Obtaining historical stray current corrosion intensity indices and corresponding environmental variable datasets as training samples, wherein the environmental variables include humidity, temperature, soil pH value, and alternating current frequency;

[0023] Based on the training samples, the multivariate regression model is trained using the random forest algorithm until the model converges to generate a corrosion rate prediction model.

[0024] Preferably, the currently calculated stray current corrosion intensity index is input into a corrosion rate prediction model to output the corrosion degree and remaining safe life of the pipeline, including:

[0025] Input the currently calculated stray current corrosion intensity index into the corrosion rate prediction model, output the corrosion rate prediction value, and determine the current pipeline corrosion degree according to the corrosion rate prediction value;

[0026] Construct a pipeline wall thickness degradation curve based on the corrosion rate prediction value and obtain the current pipeline wall thickness detection data;

[0027] Based on the pipeline wall thickness degradation curve and the current pipeline wall thickness inspection data, the remaining safe life probability distribution is generated through Monte Carlo simulation.

[0028] Preferably, the method further includes real-time monitoring of the mutation characteristics of the stray current parameters, and triggering a graded warning if the stray current parameters exceed a preset threshold, including:

[0029] Calculate the coefficient of variation of stray current parameters in real time. If the coefficient of variation exceeds the first threshold, a first-level warning is triggered and a local detection instruction is generated.

[0030] If the current density exceeds the second threshold continuously within the preset time, a second-level warning is triggered and the emergency current diversion device is activated;

[0031] When the corrosion intensity index and the remaining safe life prediction value both exceed the safety range, a third-level warning is triggered and a pipeline replacement recommendation is pushed.

[0032] In a second aspect, the present invention further provides a multi-modal quantitative assessment system for the degree of stray current corrosion in oil and gas pipelines, the system comprising:

[0033] The oil and gas pipeline data acquisition module is used to collect the stray current parameters, potential gradient distribution and magnetic field strength data of the oil and gas pipeline in real time through a multi-modal sensor array;

[0034] The corrosion hotspot construction module is used to extract dynamic current density characteristics from stray current parameters and construct corrosion hotspots based on the dynamic current density characteristics and potential gradient distribution;

[0035] The corrosion intensity index calculation module is used to calculate the stray current corrosion intensity index based on the corrosion hotspot area by integrating magnetic field intensity data and soil resistivity parameters;

[0036] The remaining safe life assessment module is used to establish a corrosion rate prediction model based on the historical stray current corrosion intensity index and environmental variables, input the currently calculated stray current corrosion intensity index into the corrosion rate prediction model, and output the corrosion degree and remaining safe life of the pipeline.

[0037] In a third aspect, the present invention also provides an electronic device comprising a processor and a memory, wherein the memory is used to store computer program code, and the computer program code comprises computer instructions. When the processor executes the computer instructions, the electronic device executes the method as described in the first aspect above and any possible implementation thereof.

[0038] In a fourth aspect, the present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions, and when the program instructions are executed by a processor of an electronic device, the processor executes the method as described in the first aspect above and any possible implementation method thereof.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The multimodal quantitative assessment method for stray current corrosion severity in oil and gas pipelines proposed in this paper effectively addresses the aforementioned technical challenges. By deploying potential gradient probes, Hall current sensors, and magnetic field strength detection units at equal intervals along the axial direction of the oil and gas pipeline and constructing a three-dimensional data matrix using a synchronous sampling module, comprehensive and real-time data collection of stray current parameters, potential gradient distribution, and magnetic field strength is achieved. During the construction of corrosion hotspots, multimodal information such as dynamic current density characteristics, potential gradient distribution, and soil resistivity is integrated. A sliding window algorithm, potential offset screening, weighted fusion algorithm, and corrosion intensity heatmaps are utilized to accurately identify corrosion hotspots. The calculation of the stray current corrosion intensity index (SCCI) fully considers multiple factors, including the environmental corrosion sensitivity coefficient and soil permeability correction factor, significantly improving the accuracy of the index calculation. A corrosion rate prediction model is constructed by training a random forest algorithm based on historical data and multiple environmental variables. The current SCCI index is then input into the model to quickly and accurately output the pipeline's corrosion severity and remaining safe life. Furthermore, the present invention features real-time monitoring of stray current parameter mutation characteristics and provides graded early warnings, significantly improving pipeline safety and reliability.

[0041] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0043] The accompanying drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to explain the technical solutions of the present disclosure.

[0044] Figure 1 A schematic flow chart of a multi-modal quantitative assessment method for the degree of stray current corrosion in oil and gas pipelines provided by an embodiment of the present invention;

[0045] Figure 2 for Figure 1 Schematic diagram of the flow of sub-steps of step S10;

[0046] Figure 3 for Figure 1 Schematic diagram of the flow of sub-steps of step S20;

[0047] Figure 4 for Figure 1 A schematic flow chart of a sub-step of step S40;

[0048] Figure 5 for Figure 1 A schematic flow chart of another sub-step of step S40;

[0049] Figure 6 A schematic flow chart of the sub-steps of step S50 in another multi-modal quantitative assessment method for the degree of stray current corrosion in oil and gas pipelines provided by an embodiment of the present invention;

[0050] Figure 7 A schematic structural diagram of a multi-modal quantitative assessment system for the degree of stray current corrosion in oil and gas pipelines provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0052] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0053] See also Figure 1 , Figure 1 The present invention provides a flow chart of a multi-modal quantitative evaluation method for the degree of stray current corrosion in oil and gas pipelines. Figure 1 As shown, a multi-modal quantitative assessment method for the degree of stray current corrosion in oil and gas pipelines includes:

[0054] S10, collecting stray current parameters, potential gradient distribution, and magnetic field strength data of the oil and gas pipeline in real time through a multimodal sensor array;

[0055] During the operation of oil and gas pipelines, stray current parameters, potential gradient distribution, and magnetic field strength data are important indicators for assessing pipeline safety, corrosion risk, and electromagnetic interference.

[0056] Stray current parameters refer to currents that leak through soil or pipelines along undesigned paths, such as those from high-voltage transmission lines, rail transit systems, other buried metal infrastructure, or variations in the geomagnetic field. These currents can cause electrochemical corrosion of pipeline metals (stray current corrosion). By measuring stray currents, pipeline corrosion risks can be assessed, cathodic protection system design optimized, and drainage measures implemented. Key parameters include:

[0057] Current intensity: The magnitude of stray current (unit: ampere, A) directly affects the corrosion rate.

[0058] Current direction: The direction in which current flows into or out of the pipeline, used to locate areas of corrosion risk.

[0059] Fluctuation characteristics: The time-varying nature of the current (such as DC, AC or pulsed current) affects the corrosion mechanism.

[0060] Frequency (such as AC stray current): High-frequency current may cause stronger alternating electromagnetic interference.

[0061] The potential gradient distribution is the change in potential per unit distance on the pipeline surface or in the surrounding soil (unit: mV / m), reflecting the distribution of current at the pipeline-soil interface or in the soil. Key scenarios are as follows: Cathodic protection effectiveness: By measuring the pipeline's potential to ground, it is determined whether the cathodic protection meets the standards. Corrosion hotspot location: An abnormal increase in potential gradient may indicate coating damage or current leakage points. Near-surface potential gradient: Dangerous step voltages may be generated near high-voltage transmission lines. The measurement method usually uses reference electrodes to measure points along the pipeline direction or perpendicular to the pipeline direction, combined with numerical models to analyze the current path.

[0062] Magnetic field strength reflects the magnetic field intensity around pipelines generated by stray currents or external electromagnetic sources (such as high-voltage lines and electrified railways). Magnetic field anomalies indirectly indicate the presence and distribution of stray currents. Dynamic monitoring of the time-varying magnetic field characteristics can assess the risk of AC corrosion or the impact of electromagnetic interference on pipelines. This can be accomplished using magnetometers (such as Hall effect sensors) or electromagnetic field mapping systems, combined with geographic information systems to analyze the spatial distribution of the magnetic field.

[0063] Stray current parameters and potential gradient distribution are directly related to pipeline corrosion risk, while magnetic field strength data can help locate interference sources. Abnormal potential gradients may indicate coating damage or step voltage risks. Therefore, combining these three data allows for a comprehensive analysis of corrosion mechanisms (e.g., DC corrosion, AC corrosion) and the effectiveness of protective measures.

[0064] In this way, step S10 can comprehensively and real-timely obtain multimodal data related to the oil and gas pipeline, form an overall perception of the conditions along the pipeline, avoid missing key corrosion risk areas, and lay the foundation for subsequent accurate assessment of the degree of corrosion.

[0065] See also Figure 2 In one embodiment, the real-time collection of stray current parameters, potential gradient distribution, and magnetic field strength data of the oil and gas pipeline by a multimodal sensor array includes:

[0066] S101. Potential gradient probes, Hall current sensors, and magnetic field strength detection units are deployed at equal intervals along the axial direction of the oil and gas pipeline to form distributed nodes.

[0067] First, plan the deployment spacing. Determine an appropriate spacing based on factors such as the length and diameter of the oil and gas pipelines, and the complexity of the surrounding environment. For example, for long pipelines with relatively stable surroundings, the spacing can be increased. For pipelines passing through complex geological areas or near electrical facilities, the spacing should be reduced, typically ranging from tens to hundreds of meters. Then, when installing the sensors, install the potential gradient probes, Hall effect current sensors, and magnetic field strength detection units in sequence along the oil and gas pipeline according to the planned spacing. During installation, ensure good contact between the sensors and the pipeline to avoid inaccurate data collection due to improper installation. Each sensor should be numbered and its location recorded for subsequent data management and analysis. To facilitate detection, further distributed nodes are constructed: the potential gradient probes, Hall effect current sensors, and magnetic field strength detection units installed in the same location are considered a distributed node. Each node is connected via wired or wireless communication to form a complete sensor network.

[0068] By deploying multiple sensors at equal intervals, comprehensive monitoring along the entire oil and gas pipeline is possible, acquiring data on stray current parameters, potential gradient distribution, and magnetic field strength at various locations, thus avoiding blind spots. The distributed node configuration associates data from each sensor with a specific location, facilitating accurate assessment of the conditions at various points along the pipeline and providing precise location information for subsequent identification of potential corrosion risk areas.

[0069] S102 , setting a synchronous sampling module to synchronously collect current intensity, potential difference and magnetic field intensity data of each distributed node at a fixed frequency.

[0070] Select an appropriate synchronous sampling module based on the sensor network's scale and data collection requirements. This module should feature high-precision clock synchronization and multi-channel data acquisition capabilities to ensure consistent data collection across distributed nodes. Set a fixed sampling frequency based on the stray current's changing characteristics and monitoring requirements. For example, for rapidly changing stray currents, the sampling frequency can be increased to capture dynamic changes. For relatively stable conditions, the sampling frequency can be reduced. Typically, the sampling frequency can range from a few times per second to a few times per minute.

[0071] After the synchronous sampling module is started, the current intensity, potential difference and magnetic field intensity data of each distributed node are collected at the same time according to the set sampling frequency, and the collected data are temporarily stored in the local memory.

[0072] Synchronous sampling ensures temporal consistency of data across distributed nodes, making data from different locations comparable and facilitating subsequent comprehensive analysis and processing. Fixed-frequency sampling enables real-time tracking of changes in stray current parameters, potential differences, and magnetic field strength, enabling timely detection of abnormal fluctuations and providing a basis for timely warning and action.

[0073] S103: Mark all collected data according to time-space coordinates to construct a three-dimensional data matrix, wherein the time-space coordinates are determined by pipeline position, detection time, and burial depth parameters.

[0074] Specifically, when marking the time-space coordinates, after obtaining the collected data from the synchronous sampling module, the pipeline location information is added to each data point based on the number and location record of each sensor. At the same time, the time of data acquisition is recorded, and combined with the sensor's burial depth parameters, each data point is assigned complete time-space coordinates. The data marked with time-space coordinates are then sorted and arranged according to certain rules to construct a three-dimensional data matrix. The three dimensions of the matrix correspond to the pipeline location, detection time, and burial depth parameters, respectively. Each matrix element stores the stray current parameters, potential difference, or magnetic field strength data under the corresponding time-space coordinates. Constructing a three-dimensional data matrix makes the collected data clearer and allows for convenient query and extraction of data at different locations, times, and depths, thereby providing a more comprehensive understanding of the condition of the oil and gas pipeline and providing a reliable data foundation for accurately assessing the degree of corrosion.

[0075] S20, extracting dynamic current density characteristics from stray current parameters, and constructing corrosion hotspot areas based on the dynamic current density characteristics and potential gradient distribution;

[0076] Existing technologies usually rely on a single or a few parameters during evaluation, and these are often static data, such as focusing only on the positive offset of the pipe-to-ground potential compared to the natural potential or the value of the soil potential gradient at a fixed moment. Therefore, when identifying corrosion hotspots, they may lack systematicity and accuracy, and are prone to misjudgment or omissions. Stray current is one of the important factors that cause corrosion in oil and gas pipelines, and the current density directly reflects the strength of the stray current's effect on pipeline corrosion. The dynamic current density characteristic can reflect the change of current over time. Compared with the static current value, it can better reflect the actual action process of the stray current. The potential gradient distribution can reflect the distribution of the electric field around the pipeline and is closely related to the flow of stray current. By analyzing the dynamic current density characteristics and the potential gradient distribution, it is possible to more accurately locate which areas on the pipeline are most affected by stray currents and are prone to corrosion.

[0077] Therefore, by comprehensively considering the dynamic current density characteristics and potential gradient distribution, we can more comprehensively and accurately reflect the corrosive effects of stray current on pipelines, thereby improving the accuracy of pipeline corrosion assessment. Subsequent calculations and predictions based on accurate corrosion hotspots also provide more reliable results.

[0078] See also Figure 3 Furthermore, in one embodiment, the step of constructing a corrosion hotspot region based on dynamic current density characteristics and potential gradient distribution includes:

[0079] S201, based on the dynamic current density characteristics, using a sliding window algorithm to identify the current density peak area and mark it as the initial hot spot area;

[0080] First, select an appropriate window size based on the characteristics of the dynamic current density data and the actual pipeline conditions. For example, if the data fluctuates frequently, the window can be set smaller; if the data is relatively stable, the window can be appropriately increased. Then perform a sliding window traversal: slide the sliding window on the dynamic current density data sequence, and calculate the average or maximum value of the current density in the window each time. When the average or maximum value of the current density in the window exceeds the preset threshold, the area corresponding to the window is marked as the current density peak area, that is, the initial hot spot area. The sliding window algorithm can capture the peak value of the current density in the dynamically changing data in a timely manner, mark these peak areas as initial hot spots, and preliminarily locate areas that may be at risk of corrosion. Taking into account the dynamic characteristics of stray currents, the algorithm can adapt to changes in current density over time, thereby improving the accuracy of identifying potential corrosion areas.

[0081] S202, calculating the potential offset of the initial hotspot area according to the potential gradient distribution, and screening areas that meet the potential offset threshold as candidate corrosion areas;

[0082] For each initial hotspot, the potential offset relative to the reference potential is calculated based on the potential gradient distribution within that area. The reference potential can be the pipeline's natural potential or a stable potential value. A potential offset threshold is set based on experience or historical data. Initial hotspots with potential offsets exceeding the threshold are identified as candidate corrosion areas. The potential offset calculated based on the potential gradient distribution is then used to further screen the initial hotspots. This eliminates areas with high current density but insignificant potential offsets, improving the accuracy of candidate corrosion areas.

[0083] S203, obtaining the soil resistivity of the candidate corrosion area, performing normalized calculation on the current density, potential gradient distribution and soil resistivity of the candidate corrosion area using a weighted fusion algorithm, and generating a corrosion intensity thermodynamic map;

[0084] To obtain soil resistivity, a soil resistivity measuring instrument is used to measure the soil resistivity of candidate corrosion zones. The current density, potential gradient distribution, and soil resistivity of these candidate corrosion zones are normalized to convert the data from different dimensions into a unified scale, facilitating subsequent fusion calculations. Furthermore, in a weighted fusion algorithm, different weights are assigned to the current density, potential gradient distribution, and soil resistivity, and a comprehensive corrosion intensity value is calculated for each candidate corrosion zone using a weighted fusion algorithm. Finally, a visualization tool is used to generate a corrosion intensity heatmap based on the comprehensive corrosion intensity values, with different colors representing different corrosion intensities.

[0085] S204: Mark the area in the corrosion intensity thermodynamic map where the intensity value exceeds the intensity critical value as a corrosion hotspot area.

[0086] A critical corrosion intensity value is set based on factors such as the pipeline material and operating environment. In the corrosion intensity heat map, areas where the intensity value exceeds the critical value are marked as the final corrosion hotspot area.

[0087] This example uses a weighted fusion of current density, potential gradient distribution, and soil resistivity to more comprehensively and accurately assess the corrosion severity of candidate corrosion zones. A corrosion intensity heatmap visually displays the corrosion intensity distribution of each candidate corrosion zone. By setting intensity thresholds, it is possible to pinpoint the corrosion hotspots requiring attention within the candidate zones, providing clear targets for subsequent protection and maintenance efforts.

[0088] S30, based on the corrosion hotspot area, the stray current corrosion intensity index is calculated by integrating the magnetic field intensity data and the soil resistivity parameters;

[0089] Preferably, the calculation of the stray current corrosion intensity index comprises:

[0090] ;

[0091] Where, is the stray current corrosion intensity index, is the environmental corrosion sensitivity coefficient, dimensionless, ranging from 0.5 to 3; is the maximum current density in the corrosion hotspot area, in units of ; is the soil infiltration correction factor, dimensionless, ranging from 0.8 to 2.5; is the equivalent penetration depth of stray current, in units of ; is the soil resistivity, in units of .

[0092] Stray current corrosion is a complex process influenced by a combination of factors. In corrosion hotspots, the distribution of stray currents, soil environment, and magnetic fields all contribute to pipeline corrosion.

[0093] In the above formula, current is the direct factor that causes corrosion, and the maximum current density in the corrosion hotspot area is The larger it is, the stronger the effect of stray current in the area is, and the greater the corrosion driving force on the pipeline is. Reflects the conductivity of the soil. The lower the soil resistivity, the easier it is for stray current to flow in the soil, thereby increasing the possibility of pipeline corrosion. Equivalent penetration depth of stray current Indicates the effective depth to which stray current can affect the pipeline. The greater the penetration depth, the wider the impact of stray current on the pipeline, and the greater the corrosion risk. Environmental Corrosion Sensitivity Coefficient The influence of environmental factors on corrosion is taken into account, such as humidity, temperature, soil pH, etc. Under different environmental conditions, the sensitivity of pipelines to stray current corrosion varies. This coefficient can be used to correct the corrosion conditions in different environments. Soil penetration correction factor This factor considers the impact of soil physical properties on stray current penetration, such as porosity and particle size. Different soil types have varying permeability to stray current, and this factor can be used to adjust for these soil characteristics. By integrating these factors, a more comprehensive and accurate assessment of the severity of stray current corrosion on pipelines can be achieved.

[0094] Specifically, the corrosion hotspot area is constructed based on the dynamic current density characteristics and potential gradient distribution in the previous steps. Soil resistivity can be extracted from the data collected by the multimodal sensor array. Soil resistivity measuring instruments can be used to measure the soil in the corrosion hotspot area to obtain the equivalent penetration depth of stray current. It can be determined by theoretical calculation, numerical simulation or field test. For example, according to the distribution law of stray current and the physical properties of soil, the equivalent penetration depth can be calculated using numerical simulation software. and soil infiltration correction factor They have their own value ranges, and you can choose the appropriate one within the given value range according to the actual environmental conditions and soil characteristics. and Value. For example,

[0095] About Environmental Corrosion Sensitivity Coefficient The value of:

[0096] Low-corrosive environments (such as dry, neutral soils): ;

[0097] Moderately corrosive environments (such as moist, weakly acidic / alkaline soils): ;

[0098] Highly corrosive environments (such as high salt, strong acid / alkaline or industrial pollution areas): ;

[0099] Regarding the soil infiltration correction factor The value of:

[0100] Low permeability soils (such as clay, high water content): ;

[0101] Medium permeability soils (such as loam, sandy loam): ;

[0102] Highly permeable soils (such as sand and gravel): ;

[0103] Therefore, this embodiment comprehensively considers multiple factors influencing stray current corrosion, avoiding the limitations of single-factor assessments and providing a more comprehensive and accurate reflection of pipeline corrosion intensity in real-world environments. The calculated corrosion intensity index allows for a quantitative comparison of the corrosion risk of different corrosion hotspots. Based on the index, targeted protective measures can be implemented, such as strengthening anti-corrosion coatings and installing drainage devices in areas with high corrosion intensity indices, thereby improving the effectiveness and cost-effectiveness of these protective measures.

[0104] S40. Establish a corrosion rate prediction model based on the historical stray current corrosion intensity index and environmental variables, input the currently calculated stray current corrosion intensity index into the corrosion rate prediction model, and output the corrosion degree and remaining safe life of the pipeline.

[0105] The stray current corrosion intensity index itself is influenced by factors such as the environmental corrosion sensitivity coefficient, maximum current density, soil penetration correction factor, stray current equivalent penetration depth, and soil resistivity. Furthermore, environmental variables such as humidity, temperature, soil pH, and alternating current frequency also influence the corrosion process. These intertwined factors make it difficult to accurately predict corrosion rates through simple observation or single-factor analysis. Therefore, a model that comprehensively considers these factors is necessary to predict corrosion rates.

[0106] See also Figure 4 In one embodiment, the corrosion rate prediction model is established based on the historical stray current corrosion intensity index and environmental variables, including:

[0107] S401 obtains a historical stray current corrosion intensity index and a corresponding environmental variable data set as a training sample, wherein the environmental variables include humidity, temperature, soil pH value, and alternating current frequency;

[0108] Historical stray current corrosion intensity index (SCCI) data is extracted from the long-term monitoring system of oil and gas pipelines. Corresponding environmental variable data are also collected, including humidity, temperature, soil pH, and alternating current frequency. This data can come from various sensors distributed along the pipeline, such as temperature and humidity sensors, soil pH meters, and current monitors. The collected data is initially organized to remove data points with obvious errors or anomalies. For example, extreme values ​​caused by sensor failure or data that does not conform to actual physical laws are removed. The organized SCCI data is paired with the environmental variable data to form a complete dataset. Each data set contains the SCCI data and the corresponding humidity, temperature, soil pH, and alternating current frequency. This dataset is divided into training and testing samples, typically in an 8:2 or 7:3 ratio. The training samples are used for model training, and the testing samples are used for evaluating model performance.

[0109] S402. Based on the training samples, a multivariate regression model is trained using a random forest algorithm until the model converges to generate a corrosion rate prediction model.

[0110] The random forest algorithm was selected to construct a multivariate regression model. Random forest is an ensemble learning method composed of multiple decision trees. Environmental variable data (humidity, temperature, soil pH, and alternating current frequency) from the training sample was used as input features, and the stray current corrosion intensity index was used as the target variable. These were input into the random forest regressor for training. During the training process, model parameters were continuously adjusted and model performance was evaluated using test samples. Common evaluation metrics include mean squared error (MSE) and root mean square error (RMSE). The model is considered converged when the evaluation metrics no longer show significant improvement after multiple iterations. For example, a small error threshold can be set, and training is terminated when the change in mean squared error over multiple consecutive iterations is less than the threshold. Once the model converges, the resulting random forest regression model is the corrosion rate prediction model.

[0111] The corrosion rate of oil and gas pipelines is influenced by the combined influence of the stray current corrosion intensity index and multiple environmental variables, which exhibit complex nonlinear relationships. The random forest algorithm automatically captures this complex nonlinear relationship without requiring prior assumptions about the specific functional form between the variables, enabling a more accurate fit of the data and improving the model's predictive accuracy. By integrating multiple decision trees, the random forest algorithm reduces the risk of overfitting in a single decision tree and exhibits strong generalization capabilities. Furthermore, in real-world applications, sensor data may contain some noise and missing information. The random forest algorithm maintains relatively stable predictive performance despite these conditions, improving the model's reliability.

[0112] See also Figure 5 In one embodiment, the currently calculated stray current corrosion intensity index is input into a corrosion rate prediction model to output the corrosion degree and remaining safe life of the pipeline, including:

[0113] S403, inputting the currently calculated stray current corrosion intensity index into the corrosion rate prediction model, outputting a corrosion rate prediction value, and determining the current corrosion degree of the pipeline based on the corrosion rate prediction value;

[0114] The calculated stray current corrosion intensity index and its corresponding environmental variable data (humidity, temperature, soil pH, and alternating current frequency) are fed into a previously trained corrosion rate prediction model. The corrosion rate prediction model calculates based on the input data and outputs a predicted corrosion rate for the current pipeline.

[0115] When determining the degree of corrosion, it is usually possible to pre-set the corrosion severity levels corresponding to different corrosion rate ranges, such as mild corrosion, moderate corrosion, severe corrosion, etc. The predicted corrosion rate value is compared with these preset ranges to determine the current corrosion severity level of the pipeline.

[0116] S404, constructing a pipeline wall thickness degradation curve based on the corrosion rate prediction value, and obtaining current pipeline wall thickness detection data;

[0117] The pipeline wall thickness degradation curve visually illustrates the changing trend of pipeline wall thickness over time, helping managers understand pipeline aging in advance. Assuming the pipeline corrosion process is continuous, with time as the horizontal axis and pipe wall thickness as the vertical axis, the corrosion rate is predicted. Based on the initial wall thickness, the pipeline wall thickness at various future time points is calculated at regular intervals, such as annually or semi-annually. This creates a curve showing the change in pipeline wall thickness over time, known as the pipeline wall thickness degradation curve. Nondestructive testing techniques, such as ultrasonic thickness gauges, are then used to measure the current pipeline wall thickness to obtain accurate data.

[0118] S405 , generating a probability distribution of the remaining safe life through Monte Carlo simulation according to the pipeline wall thickness degradation curve and the current pipeline wall thickness detection data.

[0119] Determine the critical wall thickness value related to pipeline safety. That is, when the pipeline wall thickness is lower than this value, the pipeline will not be able to ensure safe operation. At the same time, considering the uncertainty of the corrosion rate, set the probability distribution function of the corrosion rate, such as normal distribution, lognormal distribution, etc. Its parameters can be estimated based on historical data or experience.

[0120] Furthermore, the Monte Carlo simulation process is as follows:

[0121] Random sampling: randomly extract a large number of corrosion rate samples from the set corrosion rate probability distribution function.

[0122] Simulation calculation: For each corrosion rate sample extracted, combined with the current pipeline wall thickness inspection data and pipeline wall thickness degradation curve, calculate the time required for the pipeline wall thickness to drop to the critical wall thickness, that is, the remaining safe life.

[0123] Statistical analysis: Repeat the above sampling and calculation process many times (e.g., thousands or even tens of thousands of times) to obtain a large number of remaining safe life samples. Statistical analysis is performed on these samples to plot a probability distribution histogram of the remaining safe life, thereby obtaining the probability distribution of the remaining safe life.

[0124] Therefore, this embodiment inputs the current stray current corrosion intensity index into the model to obtain a corrosion rate prediction value, and determines the corrosion degree based on this, so as to timely and accurately understand the current corrosion condition of the pipeline and provide a basis for taking corresponding protective measures. The pipeline wall thickness degradation curve intuitively shows the trend of pipeline wall thickness changes over time, helping managers to understand the aging of the pipeline in advance. The Monte Carlo simulation takes into account the uncertainty of the corrosion rate and can provide a more comprehensive and objective remaining safe life assessment result by generating a probability distribution of the remaining safe life. The comprehensive information of the corrosion degree and the probability distribution of the remaining safe life provides a scientific decision-making basis for the management and maintenance of the pipeline. Based on this information, resource allocation can be optimized to avoid excessive or insufficient maintenance, thereby improving the economic benefits and safety of pipeline operations.

[0125] See also Figure 6 In one embodiment, the method further comprises:

[0126] S50: Real-time monitoring of the sudden change characteristics of stray current parameters. If the preset threshold is exceeded, a graded warning is triggered, including:

[0127] S501, calculating the coefficient of variation of the stray current parameter in real time, and if the coefficient of variation exceeds a first threshold, triggering a first-level warning and generating a local detection instruction;

[0128] S502: If the current density continuously exceeds the second threshold within a preset time, a second-level warning is triggered and an emergency current diversion device is activated;

[0129] S503. When the corrosion intensity index and the remaining safe life prediction value both exceed the safety range, a third-level warning is triggered and a pipeline replacement recommendation is pushed.

[0130] The Stray Current Corrosion Intensity Index (SCCI) can be used as an important indicator to predict pipeline corrosion trends and provide early warning. When the index exceeds a certain threshold, an alarm is issued, prompting personnel to take appropriate measures to ensure safe pipeline operation.

[0131] In this embodiment, the stray current parameter data is continuously collected, and its coefficient of variation is calculated in real time according to the coefficient of variation formula, that is, the coefficient of variation is the ratio of the standard deviation to the mean. A first threshold is set in advance. When the calculated coefficient of variation exceeds the threshold, a first-level warning is immediately triggered, and the system automatically generates instructions for detailed inspection of specific areas of the pipeline. The current density is monitored in real time, and a preset time and a second threshold are set. Once the current density is continuously higher than the second threshold within the preset time, a second-level warning is triggered, and the emergency current diversion device is automatically turned on to guide the stray current to a safe area. The corrosion intensity index and the remaining safe life prediction value are continuously obtained, and their safety ranges are set respectively. When both exceed the safety range at the same time, a third-level warning is triggered, and the system automatically pushes a recommendation for pipeline replacement to the relevant management personnel.

[0132] In this way, real-time monitoring can quickly capture changes in stray current parameters, identify potential hazards immediately, and issue timely warnings. This tiered warning mechanism can implement different response measures based on the severity of the risk, rationally allocate resources, and improve response efficiency. Timely warnings and appropriate measures can prevent the worsening of pipeline corrosion, reduce the probability of pipeline damage and safety accidents, and ensure the safety of oil and gas transportation.

[0133] In a preferred embodiment, the method further comprises a corrosion protection optimization step:

[0134] Dynamically adjust the output current and potential distribution of the cathodic protection system according to the corrosion hotspot area;

[0135] Based on the spatial distribution of the corrosion intensity index, differentiated coating repair plans are generated, with high-index areas being given priority.

[0136] In the aforementioned embodiment, corrosion hotspots have been identified and connected to the intelligent control system of the cathodic protection system. This intelligent control system dynamically adjusts the output current of the cathodic protection system in real time based on the corrosion conditions in different areas as reflected by the model. For corrosion hotspots, the output current is increased to enhance the cathodic protection effect; for areas with lower corrosion levels, the output current is appropriately reduced to avoid energy waste caused by overprotection. Simultaneously, by optimizing the anode layout and parameter settings, the potential distribution is adjusted to ensure that the entire protected area receives reasonable and effective cathodic protection. Furthermore, based on the spatial distribution map of the corrosion intensity index, CAD and optimization algorithms can be used to generate differentiated coating repair plans. Areas with high corrosion intensity indices are marked as priority repair areas, and a detailed repair plan is developed, including coating material selection, coating thickness requirements, and construction techniques. For areas with lower corrosion intensity indices, the coating repair cycle can be appropriately extended or simple maintenance measures can be implemented. A construction team is then organized to carry out the coating repair work according to the repair plan, and quality monitoring is carried out throughout the repair process to ensure the expected results.

[0137] In summary, the multimodal quantitative assessment method for stray current corrosion severity in oil and gas pipelines proposed in this paper effectively addresses the aforementioned technical challenges. By deploying potential gradient probes, Hall current sensors, and magnetic field strength detection units at equal intervals along the axial direction of the oil and gas pipeline and constructing a three-dimensional data matrix using a synchronous sampling module, comprehensive and real-time data collection of stray current parameters, potential gradient distribution, and magnetic field strength is achieved. During the construction of corrosion hotspots, multimodal information such as dynamic current density characteristics, potential gradient distribution, and soil resistivity is integrated. A sliding window algorithm, potential offset screening, a weighted fusion algorithm, and corrosion intensity heatmaps are utilized to accurately identify corrosion hotspots. The calculation of the stray current corrosion intensity index (SCCI) fully considers multiple factors, including the environmental corrosion sensitivity coefficient and soil permeability correction factor, significantly improving the accuracy of the index calculation. By training a random forest algorithm based on historical data and multiple environmental variables to construct a corrosion rate prediction model, and inputting the current SCCI into the model, the corrosion severity and remaining safe life of the pipeline can be quickly and accurately output. Furthermore, this method also features real-time monitoring of stray current parameter mutation characteristics and provides graded early warnings, significantly improving pipeline safety and reliability.

[0138] See also Figure 7 In one embodiment, the present invention further provides a multi-modal quantitative assessment system for the degree of stray current corrosion in oil and gas pipelines, the system comprising:

[0139] The oil and gas pipeline data acquisition module 100 is used to collect the stray current parameters, potential gradient distribution and magnetic field strength data of the oil and gas pipeline in real time through a multi-modal sensor array;

[0140] A corrosion hotspot region construction module 200 is used to extract dynamic current density characteristics from stray current parameters and construct a corrosion hotspot region based on the dynamic current density characteristics and potential gradient distribution;

[0141] The corrosion intensity index calculation module 300 is used to calculate the stray current corrosion intensity index based on the corrosion hotspot area by fusing the magnetic field intensity data and the soil resistivity parameter;

[0142] The remaining safe life assessment module 400 is used to establish a corrosion rate prediction model based on the historical stray current corrosion intensity index and environmental variables, input the currently calculated stray current corrosion intensity index into the corrosion rate prediction model, and output the corrosion degree and remaining safe life of the pipeline.

[0143] It can be understood that the functions or modules included in the system provided in this embodiment can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0144] The present invention also provides an electronic device, including a processor and a memory, wherein the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any one of the possible implementation modes.

[0145] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any one of the possible implementation methods described above.

[0146] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians 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 present invention.

Claims

1. A multi-modal quantitative assessment method for the degree of stray current corrosion in oil and gas pipelines, characterized by: The method comprises: The stray current parameters, potential gradient distribution and magnetic field strength data of oil and gas pipelines are collected in real time through a multimodal sensor array; Extract dynamic current density characteristics from stray current parameters and construct corrosion hotspot areas based on dynamic current density characteristics and potential gradient distribution; Based on the corrosion hotspot area, the stray current corrosion intensity index is calculated by integrating the magnetic field intensity data and soil resistivity parameters; A corrosion rate prediction model is established based on the historical stray current corrosion intensity index and environmental variables. The currently calculated stray current corrosion intensity index is input into the corrosion rate prediction model to output the corrosion degree and remaining safe life of the pipeline.

2. The multi-modal quantitative assessment method for the degree of stray current corrosion in oil and gas pipelines according to claim 1 is characterized in that: The real-time collection of stray current parameters, potential gradient distribution, and magnetic field strength data of the oil and gas pipeline by the multimodal sensor array includes: Potential gradient probes, Hall current sensors, and magnetic field strength detection units are deployed at equal intervals along the axial direction of the oil and gas pipeline to form distributed nodes; Set up a synchronous sampling module to synchronously collect current intensity, potential difference and magnetic field intensity data of each distributed node at a fixed frequency; All collected data are marked according to time and space coordinates to construct a three-dimensional data matrix, where the time and space coordinates are determined by the pipeline location, detection time and burial depth parameters.

3. The multi-modal quantitative assessment method for the degree of stray current corrosion in oil and gas pipelines according to claim 1 is characterized in that: The method of constructing a corrosion hotspot area according to the dynamic current density characteristics and the potential gradient distribution includes: Based on the dynamic current density characteristics, a sliding window algorithm is used to identify the current density peak area and mark it as the initial hot spot area; Calculate the potential offset of the initial hotspot area based on the potential gradient distribution, and select the area that meets the potential offset threshold as the candidate corrosion area; Obtain the soil resistivity of the candidate corrosion area, and use the weighted fusion algorithm to normalize the current density, potential gradient distribution, and soil resistivity of the candidate corrosion area to generate a corrosion intensity thermodynamic map. The areas in the corrosion intensity thermodynamic map where the intensity value exceeds the critical intensity value are marked as corrosion hot spots.

4. The multi-modal quantitative assessment method for the degree of stray current corrosion in oil and gas pipelines according to claim 1 is characterized in that: The calculation of the stray current corrosion intensity index includes: ； Where, is the stray current corrosion intensity index, is the environmental corrosion sensitivity coefficient, dimensionless, ranging from 0.5 to 3; is the maximum current density in the corrosion hotspot area, in units of ; is the soil infiltration correction factor, dimensionless, ranging from 0.8 to 2.5; is the equivalent penetration depth of stray current, in units of ; is the soil resistivity, in units of .

5. The multi-modal quantitative assessment method for the degree of stray current corrosion in oil and gas pipelines according to claim 1 is characterized in that: The corrosion rate prediction model is established based on the historical stray current corrosion intensity index and environmental variables, including: Obtaining historical stray current corrosion intensity indices and corresponding environmental variable datasets as training samples, wherein the environmental variables include humidity, temperature, soil pH value, and alternating current frequency; Based on the training samples, the multivariate regression model is trained using the random forest algorithm until the model converges to generate a corrosion rate prediction model.

6. The multi-modal quantitative assessment method for the degree of stray current corrosion in oil and gas pipelines according to claim 1 is characterized in that: The currently calculated stray current corrosion intensity index is input into the corrosion rate prediction model, which outputs the corrosion degree and remaining safe life of the pipeline, including: Input the currently calculated stray current corrosion intensity index into the corrosion rate prediction model, output the corrosion rate prediction value, and determine the current pipeline corrosion degree according to the corrosion rate prediction value; Construct a pipeline wall thickness degradation curve based on the corrosion rate prediction value and obtain the current pipeline wall thickness detection data; Based on the pipeline wall thickness degradation curve and the current pipeline wall thickness inspection data, the remaining safe life probability distribution is generated through Monte Carlo simulation.

7. The multi-modal quantitative assessment method for the degree of stray current corrosion in oil and gas pipelines according to claim 1 is characterized in that: The method further includes real-time monitoring of the mutation characteristics of stray current parameters, and triggering a graded warning if the stray current parameters exceed a preset threshold, including: Calculate the coefficient of variation of stray current parameters in real time. If the coefficient of variation exceeds the first threshold, a first-level warning is triggered and a local detection instruction is generated. If the current density exceeds the second threshold continuously within the preset time, a second-level warning is triggered and the emergency current diversion device is activated; When the corrosion intensity index and the remaining safe life prediction value both exceed the safety range, a third-level warning is triggered and a pipeline replacement recommendation is pushed.

8. A multi-modal quantitative assessment system for the degree of stray current corrosion in oil and gas pipelines, characterized by: The system comprises: The oil and gas pipeline data acquisition module is used to collect the stray current parameters, potential gradient distribution and magnetic field strength data of the oil and gas pipeline in real time through a multi-modal sensor array; The corrosion hotspot construction module is used to extract dynamic current density characteristics from stray current parameters and construct corrosion hotspots based on the dynamic current density characteristics and potential gradient distribution; The corrosion intensity index calculation module is used to calculate the stray current corrosion intensity index based on the corrosion hotspot area by integrating magnetic field intensity data and soil resistivity parameters; The remaining safe life assessment module is used to establish a corrosion rate prediction model based on the historical stray current corrosion intensity index and environmental variables, input the currently calculated stray current corrosion intensity index into the corrosion rate prediction model, and output the corrosion degree and remaining safe life of the pipeline.

9. An electronic device, characterized in that: include: A processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, and when the processor executes the computer instructions, the electronic device executes the multimodal quantitative assessment method for the degree of stray current corrosion of oil and gas pipelines as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the multimodal quantitative assessment method for the degree of stray current corrosion of oil and gas pipelines according to any one of claims 1 to 7.

Images