A pipeline wall thickness calculation method and device based on magnetic signal change, electronic equipment and storage medium

Abstract

The application relates to the technical field of pipeline monitoring, and discloses a pipeline wall thickness calculation method and device based on magnetic signal change, electronic equipment and a storage medium, the method comprising the following steps: arranging an external magnetic field around a pipeline, and acquiring magnetic signal data of the pipeline; performing noise processing on the magnetic signal data to obtain second magnetic signal data; performing normalization processing on the second magnetic signal data to obtain third magnetic signal data; collecting external environment data to correct the third magnetic signal data; performing feature extraction on the corrected third magnetic signal data, using a linear regression method to establish a mathematical relationship model of the magnetic signal and the pipeline wall thickness; calculating the pipeline wall thickness; performing trend analysis on the pipeline wall thickness based on historical wall thickness data to obtain predicted wall thickness data, setting a wall thickness safety threshold value according to the predicted wall thickness data, and triggering an alarm system when the specific wall thickness value of the current pipeline is lower than the wall thickness safety threshold value. The application can solve the problems that the pipeline wall thickness detection is not convenient and accurate in the prior art.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pipeline monitoring, in particular to a pipeline wall thickness calculation method and device based on magnetic signal change, an electronic device and a storage medium. BACKGROUND

[0002] Pipelines play an important role in industrial and civilian fields, and are widely used in oil, natural gas, water treatment, power and other industries. The safety and reliability of the pipeline are directly related to production efficiency, environmental protection and personal safety. With the extension of the use time of the pipeline and the change of the external environment, the pipeline wall thickness may gradually thin due to corrosion, wear, fatigue and other factors, which not only affects the carrying capacity of the pipeline, but also may cause pipeline leakage or rupture, and further cause major safety accidents. Therefore, regular monitoring and evaluation of the pipeline wall thickness is a necessary measure to ensure the safe operation of the pipeline.

[0003] Currently, the detection methods of pipeline wall thickness mainly include ultrasonic detection: using the difference in the propagation speed of ultrasonic waves in materials to measure the wall thickness of the pipeline, which has high precision, but requires expensive equipment and complex operation, X-ray detection: obtaining internal structure information of the pipeline through X-ray imaging, which is suitable for checking welds and defects, but has radiation risk and high cost, magnetic detection: mainly used for detecting pipelines of ferromagnetic materials, which judges the pipeline wall thickness by inductive change, but also needs complex equipment and high operation technology.

[0004] In recent years, detection methods based on magnetic signal change have gradually attracted attention. The magnetic signal change method uses the change of the internal and external magnetic field of the pipeline to study the change of the pipeline wall thickness. This method can avoid physical damage to the pipeline, is suitable for various complex environments, can realize online monitoring, is convenient for real-time acquisition of pipeline state information, has lower equipment cost compared with traditional detection methods, and is easy to popularize and apply. Although some studies have shown that there is a certain correlation between magnetic signal change and pipeline wall thickness, systematic methods are still lacking.

[0005] Therefore, it is a technical problem to be solved in the current pipeline monitoring field to develop a pipeline wall thickness calculation method based on magnetic signal change to improve the accuracy and convenience of pipeline detection. SUMMARY

[0006] In view of this, the present application provides a pipeline wall thickness calculation method and device based on magnetic signal change, an electronic device and a storage medium, which aims to solve the problem of inconvenient and inaccurate pipeline wall thickness detection in the current technology.

[0007] The pipeline wall thickness calculation method based on magnetic signal change provided by the present application comprises:

[0008] S1: Arrange a uniform and penetrating external magnetic field around the pipe, and use a magnetic field sensor to acquire the magnetic signal data of the pipe.

[0009] S2: Perform noise processing on the magnetic signal data to obtain second magnetic signal data;

[0010] S3: Normalize the second magnetic signal data to obtain the third magnetic signal data;

[0011] S4: Collect external environmental data to correct the third magnetic signal data and obtain the corrected third magnetic signal data;

[0012] S5: Extract feature parameters from the corrected third magnetic signal data, and establish a mathematical relationship model between the magnetic signal and the pipe wall thickness using the linear regression method based on the feature parameters;

[0013] S6: Substitute the characteristic parameters into the mathematical relationship model between the magnetic signal and the pipe wall thickness to calculate the specific wall thickness value of the current pipe;

[0014] S7: Based on the historical wall thickness data, perform wall thickness trend analysis on the pipe wall thickness to obtain predicted wall thickness data. Set a wall thickness safety threshold according to the predicted wall thickness data. If the current specific wall thickness value of the pipe is lower than the wall thickness safety threshold, trigger the alarm system.

[0015] Specifically, step S4 involves collecting temperature data of the external environment of the pipeline through a temperature sensor and correcting the temperature of the third magnetic signal data based on the thermal expansion coefficient of the pipeline material.

[0016] The external magnetic field in S1 is an integrated electromagnet and magnetic signal enhancer;

[0017] In S1, the magnetic field sensor can be any one of a Hall sensor, a fluxgate sensor, or a magnetoresistive sensor.

[0018] The specific content of noise processing of the magnetic signal data described in S2 is as follows:

[0019] The magnetic signal data is acquired, and obvious outliers are removed from the magnetic signal data using the three-standard-deviation method, including:

[0020] The formulas for calculating the mean and standard deviation of magnetic signal data are as follows:

[0021]

[0022]

[0023] Where μ is the mean of the magnetic signal data, σ is the standard deviation of the magnetic signal data, and X i Let be the i-th magnetic signal data point, and N be the total number of magnetic signal data points;

[0024] When |X i When -μ|>3σ, the magnetic signal data at point i is discarded. The data at the discarded position is then filled in using linear interpolation to obtain the filled data. The formula is:

[0025]

[0026] Where, X′ i To complete the data, X i-1 Let X be the previous magnetic signal data point of the i-th magnetic signal data point. i+1 The next magnetic signal data point after the i-th magnetic signal data point;

[0027] The completed data is added to the rejection position to obtain the second magnetic signal data.

[0028] The specific content of the normalization processing of the second magnetic signal data described in S3 is as follows:

[0029] The second magnetic signal data is normalized using the minimum-maximum normalization method. The normalized second magnetic signal data is then used to replace the second magnetic signal data before noise processing and output to obtain the third magnetic signal data.

[0030] The normalization formula is:

[0031]

[0032] Where, X″ i The normalized second magnetic signal data, i.e., the third magnetic signal data, X min X is the minimum value in the second magnetic signal data. max This is the maximum value in the second magnetic signal data.

[0033] The specific content of the corrected third magnetic signal data obtained by collecting external environmental data in S4 is as follows:

[0034] Temperature data of the external environment of the pipeline is collected by a temperature sensor, and the third magnetic signal data is corrected for temperature based on the thermal expansion coefficient of the pipeline material. The formula is as follows:

[0035] X″′=X″ i ×(1+α×(T-T0));

[0036] Where X″′ is the corrected third magnetic signal data, X″ i This is the third magnetic signal data, where α is the linear thermal expansion coefficient of the pipe material, in °C. -1T is the temperature of the external environment collected by the temperature sensor, in units of ℃, and T0 is the standard temperature, in units of ℃.

[0037] The characteristic parameters in S5 include the amplitude and phase of the corrected third magnetic signal data.

[0038] In S5, the characteristic parameters of the corrected third magnetic signal data are extracted, and a mathematical relationship model between the magnetic signal and the pipeline wall thickness is established using a linear regression method according to the characteristic parameters.

[0039] The amplitude and phase of the corrected third magnetic signal data are extracted using a wavelet transform method, and a mathematical relationship model between the magnetic signal and the pipeline wall thickness is established using a linear regression method according to the amplitude and phase of the corrected third magnetic signal data, including:

[0040] The amplitude and phase of the corrected third magnetic signal data are obtained, and the formula is:

[0041] A(t) = |W s (a,b) |;

[0042] where A(t) is the amplitude of the corrected third magnetic signal data; W s (a,b) is the wavelet transform coefficient at scale a and position b;

[0043] φ(t) = arg(W s (a,b));

[0044] where φ(t) is the phase of the corrected third magnetic signal data;

[0045]

[0046] where a is the scale factor, b is the translation factor, is the conjugate complex of the mother wavelet;

[0047] A mathematical relationship model between the magnetic signal and the pipeline wall thickness is established using a linear regression method according to the amplitude and phase of the corrected third magnetic signal data, and the formula is:

[0048] d = β0 + β1A(t) + β2φ(t) + ∈;

[0049] where d is the pipeline wall thickness, β0 is the regression model intercept term, β1 is the first regression coefficient related to the amplitude, β2 is the second regression coefficient related to the phase, and ∈ is the random error term.

[0050] In S1, the magnetic field sensors are arranged in a uniform distribution along the pipeline axis.

[0051] The magnetic signal data acquisition frequency in S1 is adjustable.

[0052] In S7, the moving average method is used to analyze the pipeline wall thickness trend based on the historical wall thickness data to obtain predicted wall thickness data.

[0053] Compared with the prior art, the present application has the following advantages:

[0054] The pipeline wall thickness calculation method based on magnetic signal change can improve the accuracy of pipeline wall thickness detection: through the application of external magnetic field and high-precision magnetic field sensor uniformly arranged around the pipeline, the magnetic signal data of the pipeline can be accurately obtained, the present application combines noise processing, normalization and temperature correction technology, which significantly improves the accuracy of wall thickness measurement and reduces the influence of environmental factors on the detection results. The present application can enhance the real-time monitoring capability: the present application realizes online monitoring of pipeline wall thickness, can real-time obtain current wall thickness value, and timely reflect the state change of pipeline. This has important significance for early detection of potential risks of pipeline and prevention of accidents. The present application can effectively analyze and predict trends: through analysis of historical wall thickness data, the moving average method is used for trend prediction, which can provide scientific basis for subsequent pipeline maintenance and management. The present application can help relevant personnel to make maintenance plan in advance and reduce maintenance cost. The present application can realize intelligent alarm system: when the current pipeline wall thickness value is lower than the set safety threshold, the system can automatically trigger alarm, timely remind relevant management personnel to check and maintain, and further improve the safety and reliability of pipeline. The present application can simplify the operation process: the wavelet transform method is introduced for signal processing and feature extraction, which simplifies the data processing process, makes the pipeline wall thickness calculation method more efficient and easy to operate. This reduces the requirement for professional skills of operators, so that the technology is easy to popularize and apply. The present application can reduce detection cost: the detection method based on magnetic signal change can greatly reduce equipment procurement and maintenance cost compared with traditional detection means. The implementation of the present application can improve the quality and frequency of pipeline monitoring without increasing much investment. The present application is suitable for various types of pipelines, whether new or old, can effectively monitor the wall thickness change, has good adaptability and wide application prospect. The present application adopts linear regression model, which can flexibly adjust the model according to the actual magnetic signal characteristic parameters, thereby improving the correlation between wall thickness and magnetic signal, making the result more reliable. BRIEF DESCRIPTION OF DRAWINGS

[0055] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments with reference made to the accompanying drawings. The drawings are for purposes of illustration only and are not intended to be limiting in any respect. Further, like reference numerals are used throughout the drawings and textual to designate identical or like components. In the drawings:

[0056] Figure 1 A flow chart of a pipeline wall thickness calculation method based on magnetic signal change provided by an embodiment of the present application is shown in the figure;

[0057] Figure 2 A structural schematic diagram of a pipeline wall thickness calculation device based on magnetic signal change provided by an embodiment of the present application is shown in the figure;

[0058] Figure 3 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0059] Exemplary embodiments of the present disclosure will be described in greater detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be accurately conveyed to those skilled in the art. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0060] The pipeline wall thickness calculation method based on magnetic signal change establishes a quantitative relationship between the wall thickness and the magnetic signal by analyzing the change rule of the magnetic signal, provides effective technical support for the safety monitoring of the pipeline, and through this method, real-time and accurate detection of the pipeline wall thickness is expected to be realized to ensure the safe and reliable operation of the pipeline system.

[0061] Referring to Figure 1 The embodiment of the present application provides a pipeline wall thickness calculation method based on magnetic signal change, which comprises the following steps:

[0062] S1: An external magnetic field that is uniform and penetrates the pipeline is arranged around the pipeline, and a magnetic field sensor is used to obtain magnetic signal data of the pipeline, and the uniformly arranged external magnetic field ensures that the magnetic signal around the pipeline can be comprehensively monitored, reduces local interference, and improves the accuracy of measurement;

[0063] S2: The magnetic signal data is subjected to noise processing to obtain second magnetic signal data, and the noise processing can effectively eliminate irrelevant interference signals, so that the subsequent data analysis is more accurate;

[0064] S3: The second magnetic signal data is subjected to normalization processing to obtain third magnetic signal data, and the normalization processing converts the data into a unified range, so that different data characteristics have comparability in analysis, reduces the error caused by different dimensions, and at the same time, the normalized data is more suitable for machine learning and statistical analysis, which helps to improve the convergence speed and accuracy of the model;

[0065] S4: collecting external environment data to correct the third magnetic signal data to obtain corrected third magnetic signal data;

[0066] S5: extracting a characteristic parameter from the corrected third magnetic signal data, and establishing a mathematical relationship model of the magnetic signal and the pipeline wall thickness using a linear regression method according to the characteristic parameter;

[0067] S6: bringing the characteristic parameter into the mathematical relationship model of the magnetic signal and the pipeline wall thickness to calculate a specific wall thickness value of the current pipeline, which can discover potential problems in time, improve the safety and reliability of the pipeline, provide accurate wall thickness data to support subsequent maintenance decisions, and help operation management personnel to make reasonable maintenance plans;

[0068] S7: performing wall thickness trend analysis on the pipeline wall thickness based on the historical wall thickness data to obtain predicted wall thickness data, setting a wall thickness safety threshold according to the predicted wall thickness data, and triggering an alarm system if the specific wall thickness value of the current pipeline is lower than the wall thickness safety threshold;

[0069] In S4, the temperature data of the external environment of the pipeline is collected by a temperature sensor, and the third magnetic signal data is temperature corrected according to the thermal expansion coefficient of the pipeline material.

[0070] Further, the external magnetic field in S1 is integrally arranged with an electromagnet and a magnetic signal enhancer.

[0071] The magnetic field sensor in S1 is any one of a Hall sensor, a fluxgate sensor and a magnetic resistance sensor, and the selection of multiple sensors provides flexibility for different application scenarios, so that the method is more adaptable and can be adjusted according to actual needs.

[0072] Further, the noise processing of the magnetic signal data in S2 includes:

[0073] The magnetic signal data is obtained, and the three standard deviation method is used to eliminate obvious outliers in the magnetic signal data, including:

[0074] The mean of the magnetic signal data and the standard deviation of the magnetic signal data are calculated, and the formula is:

[0075]

[0076]

[0077] Wherein, μ is the mean of the magnetic signal data, σ is the standard deviation of the magnetic signal data, Xi is the i-th magnetic signal data point, and N is the total number of magnetic signal data. i

[0078] ​Specifically, by calculating the average value and standard deviation of the magnetic signal data of each measurement point, the three standard deviation method can effectively eliminate extreme values. Because in the normal distribution, 95% of the data should fall within the range of mean value ± 2 standard deviations, and three standard deviations further limit the occurrence of extreme values, ensuring the representativeness and reliability of the data.

[0079] If the magnetic signal data at a certain measurement point is [7.2, 7.0, 7.4, 85.0] (assuming 85.0 is an abnormal value), the method can eliminate 85.0, ensuring that subsequent calculations are based on reasonable data and avoiding the influence of individual abnormal values on the entire measurement result.

[0080] When ∣X i -μ∣>3σ, the magnetic signal data of the i-th point is eliminated, and the data at the eliminated position is completed according to the linear interpolation method to obtain the completed data. Through the completion processing, the integrity of the data set is ensured, and the analysis deviation caused by abnormal values is reduced. The formula is:

[0081]

[0082] Where X′ i is the completed data, X i-1 is the previous magnetic signal data point of the i-th magnetic signal data point, and X i+1 is the next magnetic signal data point of the i-th magnetic signal data point.

[0083] The completed data is added to the eliminated position to obtain the second magnetic signal data.

[0084] Specifically, assuming that there is a value to be eliminated in a measurement sequence, the previous and next values are 7.2 and 7.4 respectively, and the interpolation can generate 7.3 as the completed value, thereby ensuring that the data record of the measurement point is continuous, which is crucial for subsequent trend analysis and monitoring.

[0085] Further, the specific content of normalizing the second magnetic signal data in S3 is:

[0086] The second magnetic signal data is normalized by using the minimum-maximum normalization method. The normalized second magnetic signal data replaces the second magnetic signal data before noise processing and is output to obtain the third magnetic signal data.

[0087] The normalization formula is:

[0088]

[0089] Where X″ i is the normalized second magnetic signal data, i.e. the third magnetic signal data, and X minX is the minimum value in the second magnetic signal data max Y is the maximum value in the second magnetic signal data.

[0090] Specifically, the application of minimum-maximum normalization:

[0091] By standardizing the magnetic signal data to the range of 0 to 1, the problem of different measurement points having different data magnitudes due to environmental changes or equipment differences can be eliminated. The normalized data can be more easily compared and analyzed, especially in subsequent model construction, avoiding the problem of algorithm instability or performance decline caused by data magnitude differences.

[0092] After normalization of the magnetic signal data of different measurement points, regardless of the original magnitude of the data, it can be mapped to the interval [0, 1], so that when data fusion is performed, the contribution of each measurement point is balanced, ensuring the fairness and accuracy of the analysis.

[0093] Effect of comprehensive noise processing:

[0094] Through the above steps, the entire data processing process becomes more robust. Since the rejection and completion process can effectively eliminate sudden external interference and measurement errors, in complex environments, effective data can be stably obtained, enhancing the anti-interference ability of the monitoring equipment.

[0095] Risk analysis supported by accurate data:

[0096] In subsequent wall thickness trend analysis and risk assessment, the processed data provide an accurate basis, making the assessment of historical data trends more timely and effective. Accurate wall thickness data can help engineers detect abnormal changes in the pipeline early and implement appropriate maintenance measures to reduce potential safety hazards.

[0097] If a trend analysis reveals that the wall thickness of a certain measurement point is continuously decreasing, and the data is confirmed to be reliable through data processing, maintenance procedures can be initiated in a timely manner to prevent future pipeline leaks or ruptures, reducing economic losses and environmental risks.

[0098] Further, the collection of external environmental data in S4 to correct the third magnetic signal data to obtain corrected third magnetic signal data specifically includes:

[0099] It should be noted that the introduction of temperature correction helps to correct the deviation of magnetic signal data caused by temperature change, thereby improving the accuracy of measurement results, so that the corrected third magnetic signal data is closer to the actual situation. By considering the linear expansion coefficient of the pipeline and the pressure factor, the measurement error caused by environmental changes can be effectively reduced, and the reliability of the data can be enhanced, providing a more solid foundation for subsequent data analysis. The calculation method of the temperature correction coefficient allows adaptive adjustment under different environmental conditions, ensuring stable measurement results in a variable temperature environment. The accurate corrected third magnetic signal data provides a more reliable basis for subsequent trend analysis and risk assessment, helping to identify potential safety hazards in advance and improve the efficiency of pipeline management and maintenance. The correction considering temperature and pressure factors can prevent pipeline damage risks caused by environmental condition changes to some extent, ensuring the safety and stability of the pipeline during operation. The introduction of temperature correction coefficient and its related parameter calculation makes the monitoring more intelligent, which can respond to environmental changes in real time and achieve more accurate monitoring and management.

[0100] Temperature data of the external environment of the pipeline is collected by a temperature sensor, and temperature correction can eliminate signal errors caused by environmental changes, ensuring that the obtained magnetic signal data is more reliable. The third magnetic signal data is temperature corrected according to the thermal expansion coefficient of the pipeline material, considering the thermal expansion characteristics of the pipeline material, so that the measurement results are more consistent with the actual situation, enhancing the scientificity of the method. The formula is:

[0101] X″′=X″ i ×(1+α×(T-T0));

[0102] Wherein, X″′ is the corrected third magnetic signal data, X″ i is the third magnetic signal data, α is the linear thermal expansion coefficient of the pipeline material, unit is ℃ -1 , T is the temperature of the external environment collected by the temperature sensor, unit is ℃, T0 is the standard temperature, unit is ℃.

[0103] Furthermore, by introducing the environmental temperature factor, the necessary correction can be made to the magnetic signal data, making the corrected third magnetic signal data closer to the real situation. This is because the environmental factor is very important in the operation state of the pipeline, directly affecting the wall thickness performance of the pipeline. Temperature rise may cause thermal expansion of the pipeline material. Through the corresponding correction, the real wall thickness of the pipeline can be more accurately reflected. Through the unified correction formula, the magnetic signal data of different measurement points can be compared under the same standard. For data obtained under different environmental conditions, the influence of environmental differences can be eliminated after correction, enhancing the comparability between data. The corrected data provides a reliable basis for subsequent trend analysis and risk assessment, which helps to effectively predict and intervene before potential problems occur. For example, if the corrected data shows that the wall thickness of a certain measurement point is decreasing at an accelerated rate, the relevant management department can take timely maintenance measures to prevent potential pipeline leakage or rupture incidents. In the case of multiple measurements and environmental changes, the correction based on environmental parameters helps to reduce measurement errors caused by environmental fluctuations, making the monitoring data more consistent and enhancing stability. For example, in the case of long-term monitoring, real-time correction of environmental parameters can ensure the continuous reliability of monitoring results, so that the maintenance team can rely on these data for longer period management and maintenance.

[0104] By collecting and correcting environmental parameters, the accuracy, stability and comparability of pipeline wall thickness monitoring can be effectively improved, the risk assessment capability can be enhanced, and the reliability in complex temperature environment can be ensured. These beneficial effects not only improve the quality of monitoring data, but also provide important protection for the safe operation of the pipeline.

[0105] Further, the feature parameters in S5 include the amplitude and phase of the corrected third magnetic signal data.

[0106] Further, the feature parameters in S5 include the amplitude and phase of the corrected third magnetic signal data.

[0107] The amplitude and phase of the corrected third magnetic signal data are extracted by wavelet transformation, which effectively extracts useful information from the signal and improves the prediction ability of the model. According to the amplitude and phase of the corrected third magnetic signal data, a linear regression method is used to establish a mathematical relationship model between the magnetic signal and the wall thickness of the pipeline. The linear regression model provides a theoretical basis for subsequent wall thickness calculation, establishes a direct relationship between the magnetic signal and the wall thickness, and improves the application value of the method, including:

[0108] The amplitude and phase of the corrected third magnetic signal data are obtained by the formula:

[0109] A(t) = |W s (a, b) |;

[0110] wherein A(t) is the amplitude of the corrected third magnetic signal data; W s (a, b) is the wavelet transform coefficient at scale a and position b;

[0111] φ(t) = arg(W s (a, b));

[0112] wherein φ(t) is the phase of the corrected third magnetic signal data;

[0113]

[0114] wherein a is a scale factor, b is a translation factor, is the conjugate complex of the mother wavelet, t is the integration variable, and X''' is the corrected third magnetic signal data;

[0115] A linear regression method is used to establish a mathematical relationship model between the magnetic signal and the pipeline wall thickness according to the amplitude and phase of the corrected third magnetic signal data, and the formula is:

[0116] d = β0+ β1A(t) + β2φ(t) + ε;

[0117] wherein d is the pipeline wall thickness, β0is the regression model intercept term, β1is the first regression coefficient related to the amplitude, β2is the second regression coefficient related to the phase, and ε is the random error term.

[0118] It should be noted that linear regression is a basic and widely used statistical method, which is simple to calculate and easy to implement. Compared with complex nonlinear models, linear regression can quickly obtain results, which is conducive to real-time data processing and monitoring; linear regression has good stability and can still maintain good prediction effect under data noise or slight abnormal conditions, ensuring the stability of pipeline wall thickness detection. At the same time, if the data points are reasonably distributed, linear regression can well fit the relationship between the magnetic signal and the wall thickness; the linear regression model is easy to adjust and optimize, and the accuracy of the model can be improved by adding or excluding specific variables, and various regularization techniques (such as Lasso or Ridge) can be easily used to avoid overfitting and improve the generalization ability of the model; linear regression is efficient when processing a large amount of data, and is suitable for large amounts of magnetic signal data continuously obtained in real-time monitoring systems, which helps to quickly establish and update the model and improve the accuracy of pipeline wall thickness prediction.

[0119] Further, the arrangement of the magnetic field sensors in S1 is uniformly distributed along the pipeline axis.

[0120] Specifically, according to the diameter of the pipeline and the area to be monitored, an appropriate number of sensors are selected, which should be evenly distributed around the outer surface of the pipeline to form a sensor network around the pipeline. Ensure that the position of the sensor can cover all the key areas of the pipeline, and ensure that the height of all sensors is consistent during installation to avoid inconsistent data caused by height differences, for example, for a pipeline with a diameter of 100 mm, it is recommended to install 5-10 sensors. The sensors are evenly arranged around the pipeline to ensure that the distance between adjacent sensors is as consistent as possible.

[0121] It should be noted that the uniform distribution of sensors along the axial direction of the pipeline ensures comprehensive monitoring of the magnetic field around the pipeline, which helps to capture small changes in the magnetic signal caused by uneven pipe wall thickness. This layout design can improve the accuracy of measurement, reduce errors caused by local magnetic field interference, and make the wall thickness calculation more accurate. The uniform distribution of sensors can quickly respond to changes in the environment around the pipeline, such as fluctuations in temperature and pressure, and adjust the data processing strategy in a timely manner. The uniform arrangement of sensors reduces the impact of a single sensor failure on the overall monitoring system, improving the reliability and stability of the system.

[0122] Further, the magnetic signal data acquisition frequency in S1 is adjustable.

[0123] Specifically, the magnetic signal data acquisition frequency can be set to once every 5 seconds to ensure real-time data.

[0124] It should be noted that the adjustable acquisition frequency can be flexibly adjusted according to actual needs and environmental conditions to improve the adaptability of the system. For example, when the pipeline is being maintained or monitored, the frequency can be adjusted to be higher to obtain more data. By reducing the acquisition frequency when high-frequency data is not needed, the system can save power and data storage resources, prolonging the service life of the equipment. High-frequency acquisition can be used during abnormal monitoring or critical moments to capture transient changes, ensuring the accuracy and integrity of the data and improving the reliability of subsequent analysis. Flexible acquisition frequency settings allow the system to quickly respond and improve data acquisition speed when a fault or abnormal situation occurs, providing timely alerts or warning information. The adjustable acquisition frequency setting provides users with greater flexibility, allowing operators to easily adjust system configurations according to specific monitoring needs and improve user experience.

[0125] Further, the moving average method is used to analyze the wall thickness trend based on the historical wall thickness data in S7 to obtain predicted wall thickness data.

[0126] Specifically, the moving average method is used to obtain predicted wall thickness data, and the formula is:

[0127]

[0128] where T预测 To predict the wall thickness data, T 历史 (i) is the i-th historical wall thickness data, M is the sample number of historical wall thickness data, M can be set as all historical wall thickness data, or the latest M historical wall thickness data, which can be set according to actual conditions, and the present application does not make specific limitations.

[0129] Further, the specific wall thickness value of the current pipeline is monitored in real time, which is compared with the set safety threshold value periodically, the safety threshold value is adjusted periodically according to the change of pipeline use condition and external environment, if the wall thickness value of the current pipeline is lower than the set safety threshold value, the alarm system is triggered, and the alarm is sent. The alarm mode can include audible and visual alarm, short message notification, email notification, etc., to ensure that the relevant personnel can respond in time, after the alarm is triggered, the system can automatically record the alarm event, generate a report for subsequent analysis and investigation, and the pipeline maintenance personnel should go to the scene to check, evaluate the pipeline condition, and perform necessary maintenance or replacement operation after receiving the alarm.

[0130] It should be noted that the trend analysis based on historical data and the setting of safety threshold value can identify the possible risks of pipeline wall thickness in advance, and ensure the safe operation of the pipeline; through the analysis of historical data, the management personnel can more scientifically formulate maintenance and operation strategies, and improve the management efficiency; the real-time monitoring and alarm system can timely respond to potential safety hazards, thereby reducing the probability of accidents and protecting the safety of personnel and property; by dynamically adjusting the safety threshold value, the pipeline can maintain a safe state under various operating conditions, and the overall operation efficiency is improved.

[0131] Further, the present application also includes monitoring the pipeline in the deep sea or the rapid flow area of the river, the environmental change is frequent, and the stability of the monitoring data can be ensured by real-time correction, and the safety monitoring capability of the pipeline is improved, at this time, the external environment data in the collection of external environment data to correct the third magnetic signal data in S4 is the water flow velocity and the depth of water;

[0132] The water flow velocity outside the pipeline is collected by a water flow velocity sensor, and the third magnetic signal data is corrected by the water flow velocity, and the formula is:

[0133] X''' = X'' i ×(1+β×(V-V0))

[0134] Wherein, β is the correction coefficient of the influence of water flow velocity on magnetic signal, V is the current water flow velocity, V0 is the standard water flow velocity, X''' and X i '' are the corrected magnetic signal data and the uncorrected magnetic signal data respectively;

[0135] It should be noted that the water flow velocity correction corrects the third magnetic signal data, which is:

[0136] Improved measurement accuracy: Water flow rate correction ensures that the corrected data accurately reflects the actual wall thickness of the pipeline by considering the impact of flow rate on the magnetic signal. This improvement in accuracy ensures high reliability under different water flow conditions, effectively avoiding measurement errors caused by flow rate changes.

[0137] Reduced environmental interference: In underwater environments, flow rate changes can cause fluctuations in measurement signals. By introducing a water flow rate correction coefficient, the interference of flow rate on the magnetic signal can be effectively filtered out, significantly reducing the impact of environmental noise on monitoring results and making the data more stable and reliable.

[0138] Enhanced adaptability: The application of water flow rate correction enables stronger adaptability in complex underwater environments. Whether in still water or strong flow conditions, real-time correction can maintain data consistency, thereby improving the universality in practical applications.

[0139] Ensuring pipeline safety: Through precise water flow rate correction, potential abnormalities in the pipeline can be detected in advance, and maintenance measures can be taken in a timely manner. This effectively prevents pipeline damage or leakage risks caused by inaccurate measurements, ensuring the safety and reliability of pipelines in various underwater environments.

[0140] Improved credibility: Accurate water flow rate correction improves the credibility of monitoring. This is crucial for promoting new technologies and gaining user recognition, contributing to the widespread application and popularization of technology.

[0141] The water depth sensor collects the position of the pipeline in the water, and the water depth correction is performed on the third magnetic signal data, with the formula:

[0142] X″′=X″ i ×(1+γ×(D-D0))

[0143] where γ is the correction coefficient of water depth on the magnetic signal, D is the current depth of the pipeline in the water, D0 is the standard detection depth, and X″′ and X i ″ are the corrected magnetic signal data and the uncorrected magnetic signal data, respectively.

[0144] It should be noted that the introduction of water depth correction is to ensure that the magnetic data can be effectively corrected under different measurement depths, eliminating the data deviation caused by changes in depth.

[0145] By correcting the depth, the influence of different measurement depths on magnetic data can be effectively reduced, ensuring the comparability of data from each measurement point in the case of inconsistent depths. Since the depth correction takes into account the impact of depth differences on measurement accuracy, more accurate wall thickness data can be obtained under different measurement conditions. The change in depth has a cumulative effect on wall thickness measurement, and depth correction can minimize this cumulative error, ensuring the consistency of data at different depths. By correcting the depth and water density, the corrected wall thickness data is more stable and less affected by environmental factors, which helps subsequent data analysis and processing. This method can automatically correct according to different measurement depths and is suitable for wall thickness data collection and processing in various underwater environments.

[0146] After the above correction, measurements taken in environments with fast and slow water flow rates can yield directly comparable results, effectively evaluating the health status of each measurement point. The flow rate and depth of the underwater environment often have variability, and by monitoring these environmental parameters in real time and correcting the data, different underwater conditions can be adapted to. This enables efficient operation under various complex conditions. For example, monitoring in the deep sea or river rapids, where the environment changes frequently, real-time correction can ensure the stability of the monitoring data and improve the safety monitoring capability of the pipeline. The corrected data provides a reliable basis for subsequent trend analysis and risk assessment, helping to effectively predict and intervene before potential problems occur.

[0147] In summary, the pipeline wall thickness calculation method based on magnetic signal change can improve the accuracy of pipeline wall thickness detection: through the application of external magnetic field and high-precision magnetic field sensor uniformly arranged around the pipeline, the magnetic signal data of the pipeline can be accurately obtained, the noise processing, normalization and temperature correction technology are combined, the accuracy of wall thickness measurement is significantly improved, and the influence of environmental factors on the detection result is reduced; the real-time monitoring capability can be enhanced: the online monitoring of the pipeline wall thickness is realized, the current wall thickness value can be obtained in real time, and the state change of the pipeline can be timely reflected. This has important significance for early detection of potential risks of the pipeline and prevention of accidents; effective trend analysis and prediction can be achieved: through analysis of historical wall thickness data, the moving average method is used for trend prediction, which can provide a scientific basis for subsequent pipeline maintenance and management. The present application can help relevant personnel to make maintenance plan in advance and reduce maintenance cost; an intelligent alarm system can be realized: when the current pipeline wall thickness value is lower than the set safety threshold, the system can automatically trigger an alarm to remind the relevant management personnel to check and maintain in time, further improving the safety and reliability of the pipeline; the operation process can be simplified: the wavelet transform method is introduced for signal processing and feature extraction, which simplifies the data processing process, makes the pipeline wall thickness calculation method more efficient and easy to operate. This reduces the requirement for professional skills of the operator, making the technology easy to popularize and apply; the detection cost can be reduced: compared with traditional detection methods, the detection method based on magnetic signal change can greatly reduce the equipment procurement and maintenance cost. The implementation of the present application can improve the quality and frequency of pipeline monitoring without increasing much investment; strong adaptability: the present application is suitable for various types of pipelines, whether it is a new pipeline or an old pipeline, the wall thickness change can be effectively monitored, and it has good adaptability and wide application prospect; flexibility of data processing and analysis: since the linear regression model is used, the model can be flexibly adjusted according to the actual magnetic signal characteristic parameters, thereby improving the correlation between the wall thickness and the magnetic signal, and making the result more reliable.

[0148] Figure 2 The structure diagram of the pipeline wall thickness calculation device based on magnetic signal change provided by the embodiment of the present application can be realized by software and / or hardware, and can be configured in a terminal and / or server to realize the pipeline wall thickness calculation method based on magnetic signal change in the embodiment of the present application. The device can specifically include: a magnetic signal data acquisition module 310, a noise processing module 320, a data normalization processing module 330, a magnetic signal data correction module 340, a characteristic parameter extraction module 350, a wall thickness value calculation module 360, and an alarm module 370.

[0149] The magnetic signal data acquisition module 310 is configured to arrange an external magnetic field that is uniform and penetrates the pipeline around the pipeline, and acquire magnetic signal data of the pipeline by using a magnetic field sensor; the noise processing module 320 is configured to perform noise processing on the magnetic signal data to obtain second magnetic signal data; the data normalization processing module 330 is configured to perform normalization processing on the second magnetic signal data to obtain third magnetic signal data; the magnetic signal data correction module 340 is configured to collect external environment data to correct the third magnetic signal data to obtain corrected third magnetic signal data; the collecting external environment data to correct the third magnetic signal data to obtain corrected third magnetic signal data includes: collecting temperature data of an external environment of the pipeline by using a temperature sensor, and correcting the third magnetic signal data according to a thermal expansion coefficient of a pipeline material; the characteristic parameter extraction module 350 is configured to extract characteristic parameters from the corrected third magnetic signal data, and establish a mathematical relationship model of the magnetic signal and the pipeline wall thickness by using a linear regression method according to the characteristic parameters; the wall thickness value calculation module 360 is configured to input the characteristic parameters into the mathematical relationship model of the magnetic signal and the pipeline wall thickness to calculate a specific wall thickness value of the current pipeline; and the alarm module 370 is configured to perform wall thickness trend analysis on the pipeline wall thickness based on the historical wall thickness data to obtain predicted wall thickness data, set a wall thickness safety threshold according to the predicted wall thickness data, and trigger an alarm system if the specific wall thickness value of the current pipeline is lower than the wall thickness safety threshold.

[0150] The technical scheme of the embodiment can accurately acquire the magnetic signal data of the pipeline by applying the external magnetic field uniformly arranged around the pipeline and the high-precision magnetic field sensor, significantly improves the accuracy of the wall thickness measurement by combining noise processing, normalization and temperature correction technology, and reduces the influence of environmental factors on the detection result. The application can enhance the real-time monitoring capability: the application realizes online monitoring of the pipeline wall thickness, can acquire the current wall thickness value in real time, and timely reflects the state change of the pipeline. This has important significance for early detection of potential risks of the pipeline and prevention of accidents. The application can effectively analyze and predict trends: by analyzing historical wall thickness data and using the moving average method for trend prediction, scientific basis can be provided for subsequent pipeline maintenance and management. The application can help relevant personnel to make maintenance plans in advance and reduce maintenance costs. The application can realize an intelligent alarm system: when the current pipeline wall thickness value is lower than the set safety threshold, the system can automatically trigger an alarm to timely remind the relevant management personnel to check and maintain, further improving the safety and reliability of the pipeline. The application can simplify the operation process: by introducing the wavelet transform method for signal processing and feature extraction, the data processing process is simplified, making the pipeline wall thickness calculation method more efficient and easy to operate. This reduces the requirement for the professional skills of the operator, making the technology easy to popularize and apply. The application can reduce the detection cost: the detection method based on the change of the magnetic signal can greatly reduce the equipment procurement and maintenance cost compared with the traditional detection means. The implementation of the application can improve the quality and frequency of pipeline monitoring without increasing much investment. The application is suitable for various types of pipelines, whether new or old, and can effectively monitor the wall thickness change, has good adaptability and wide application prospect. The application adopts a linear regression model, which can flexibly adjust the model according to the actual magnetic signal characteristic parameters, thereby improving the correlation between the wall thickness and the magnetic signal, and making the result more reliable.

[0151] The pipeline wall thickness calculation device based on the change of the magnetic signal can execute the method for calculating the pipeline wall thickness based on the change of the magnetic signal provided by any embodiment of the application, has the corresponding function modules and beneficial effects of executing the method for calculating the pipeline wall thickness based on the change of the magnetic signal.

[0152] Figure 3 A structural schematic diagram of an electronic device provided by an embodiment of the application is shown in Figure 3 The electronic device includes a processor 410, a memory 420, an input device 430 and an output device 440; the number of processors 410 in the device can be one or more, Figure 3 and an example of one processor 410 is taken; the processor 410, the memory 420, the input device 430 and the output device 440 in the device can be connected through a bus or other means, Figure 3 and an example of connection through a bus is taken.

[0153] The memory 420, as a kind of computer readable storage medium, can be used to store software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the pipeline wall thickness calculation method based on magnetic signal change in the embodiments of the present application.The processor 410 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 420.

[0154] The memory 420 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required by a function; the data storage area can store data created according to the use of the terminal, etc. In addition, the memory 420 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state memory device. In some examples, the memory 420 can further include a memory remotely arranged with respect to the processor 410, which can be connected to the device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0155] The input device 430 can be used to receive input digital or character information, and generate signal input related to the user settings and function control of the device. The output device 440 can include a display device such as a display screen.

[0156] The embodiment of the present application also provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute a pipeline wall thickness calculation method based on magnetic signal change, comprising the following steps: S1, arranging an external magnetic field which is uniform and penetrates the pipeline around the pipeline, and acquiring magnetic signal data of the pipeline by using a magnetic field sensor; S2, performing noise processing on the magnetic signal data to obtain second magnetic signal data; S3, performing normalization processing on the second magnetic signal data to obtain third magnetic signal data; S4, collecting external environment data to correct the third magnetic signal data to obtain corrected third magnetic signal data; S5, extracting feature parameters from the corrected third magnetic signal data, and using a linear regression method to establish a mathematical relationship model of the magnetic signal and the pipeline wall thickness according to the feature parameters; S6, bringing the feature parameters into the mathematical relationship model of the magnetic signal and the pipeline wall thickness to calculate a specific wall thickness value of the current pipeline; S7, performing wall thickness trend analysis on the pipeline wall thickness based on the historical wall thickness data to obtain predicted wall thickness data, setting a wall thickness safety threshold according to the predicted wall thickness data, and triggering an alarm system when the specific wall thickness value of the current pipeline is lower than the wall thickness safety threshold; wherein, the step S4 specifically comprises collecting temperature data of the external environment of the pipeline by using a temperature sensor, and correcting the third magnetic signal data according to the thermal expansion coefficient of the pipeline material.

[0157] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may, for example, be but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples (non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus or device.

[0158] A computer readable signal medium can include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal can take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium can be any computer readable medium that can be involved in

[0159] The computer readable program code embodied on a computer readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0160] Computer program code for carrying out operations of embodiments of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0161] Note that the foregoing are merely preferred embodiments and the principles of the present application. It will be understood by those skilled in the art that the present application is not limited to the specific embodiments described herein, and that various obvious changes, modifications and substitutions can be made without departing from the scope of the present application. Therefore, although the present application has been described in detail with reference to the above embodiments, the present application is not limited to the above embodiments, and can include other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A method for calculating pipe wall thickness based on changes in magnetic signals, characterized in that, include: S1: Arrange a uniform and penetrating external magnetic field around the pipe, and use a magnetic field sensor to acquire the magnetic signal data of the pipe. S2: Perform noise processing on the magnetic signal data to obtain second magnetic signal data; S3: Normalize the second magnetic signal data to obtain the third magnetic signal data; S4: Collect external environmental data to correct the third magnetic signal data and obtain the corrected third magnetic signal data; S5: Extract feature parameters from the corrected third magnetic signal data, and establish a mathematical relationship model between the magnetic signal and the pipe wall thickness using the linear regression method based on the feature parameters; S6: Substitute the characteristic parameters into the mathematical relationship model between the magnetic signal and the pipe wall thickness to calculate the specific wall thickness value of the current pipe; S7: Perform wall thickness trend analysis on the pipe wall thickness based on historical wall thickness data to obtain predicted wall thickness data. Set a wall thickness safety threshold based on the predicted wall thickness data. If the current specific wall thickness value of the pipe is lower than the wall thickness safety threshold, trigger the alarm system. Specifically, step S4 involves collecting temperature data of the external environment of the pipeline through a temperature sensor and correcting the third magnetic signal data for temperature based on the thermal expansion coefficient of the pipeline material. The specific content of S5, which describes extracting feature parameters from the corrected third magnetic signal data and establishing a mathematical relationship model between the magnetic signal and the pipe wall thickness using a linear regression method based on the feature parameters, is as follows: The amplitude and phase of the corrected third magnetic signal data are extracted using wavelet transform. Based on the amplitude and phase of the corrected third magnetic signal data, a mathematical relationship model between the magnetic signal and the pipe wall thickness is established using linear regression, including: The formula for obtaining the amplitude and phase of the corrected third magnetic signal data is as follows: ； in, The amplitude of the corrected third magnetic signal data; These are the wavelet transform coefficients under the scaling factor a and the translation factor b; ； in, The phase of the corrected third magnetic signal data; ； Where a is the scaling factor and b is the translation factor. The complex conjugate of the mother wavelet; Based on the amplitude and phase of the corrected third magnetic signal data, a mathematical model of the relationship between the magnetic signal and the pipe wall thickness is established using a linear regression method. The formula is as follows: ； Where d is the pipe wall thickness. For the intercept term of the regression model, The first regression coefficient related to the amplitude. The second regression coefficient is related to the phase. This is the random error term.

2. The method for calculating pipe wall thickness based on magnetic signal variation according to claim 1, characterized in that, The external magnetic field in S1 is an integrated electromagnet and magnetic signal enhancer; In S1, the magnetic field sensor can be any one of a Hall sensor, a fluxgate sensor, or a magnetoresistive sensor.

3. The method for calculating pipe wall thickness based on magnetic signal variation according to claim 2, characterized in that, The specific content of noise processing of the magnetic signal data described in S2 is as follows: The magnetic signal data is acquired, and obvious outliers are removed from the magnetic signal data using the three-standard-deviation method, including: The formulas for calculating the mean and standard deviation of magnetic signal data are as follows: ； ； in, This represents the mean of the magnetic signal data. The standard deviation of the magnetic signal data. Let be the i-th magnetic signal data point, and N be the total number of magnetic signal data points; When satisfied At that time, the magnetic signal data at point i is removed, and the data at the removed position is completed using linear interpolation to obtain the completed data. The formula is as follows: ； in, To complete the data, For the i-th magnetic signal data point, the previous magnetic signal data point is... The next magnetic signal data point after the i-th magnetic signal data point; The completed data is added to the rejection position to obtain the second magnetic signal data.

4. The method for calculating pipe wall thickness based on magnetic signal variation according to claim 3, characterized in that, The specific content of the normalization processing of the second magnetic signal data described in S3 is as follows: The second magnetic signal data is normalized using the minimum-maximum normalization method. The normalized second magnetic signal data is then used to replace the second magnetic signal data before noise processing and output to obtain the third magnetic signal data. The normalization formula is: ； in, The normalized second magnetic signal data is the third magnetic signal data. This is the minimum value in the second magnetic signal data. This is the maximum value in the second magnetic signal data.

5. The method for calculating pipe wall thickness based on magnetic signal variation according to claim 4, characterized in that, The specific content of the corrected third magnetic signal data obtained by collecting external environmental data in S4 is as follows: Temperature data of the external environment of the pipeline is collected by a temperature sensor, and the third magnetic signal data is corrected for temperature based on the thermal expansion coefficient of the pipeline material. The formula is as follows: ； in, The corrected third magnetic signal data, This is the third magnetic signal data. The linear thermal expansion coefficient of the pipe material, in units of... T represents the ambient temperature as measured by the temperature sensor, in degrees Celsius (°C). Standard temperature, unit: °C; The characteristic parameters in S5 include the amplitude and phase of the corrected third magnetic signal data.

6. The method for calculating pipe wall thickness based on magnetic signal variation according to claim 5, characterized in that, The magnetic field sensors described in S1 are arranged in a uniform distribution along the pipe axis; The magnetic signal data acquisition frequency described in S1 is adjustable; S7 describes using the moving average method to analyze the wall thickness trend based on the historical wall thickness data to obtain predicted wall thickness data.

7. A pipe wall thickness calculation device based on magnetic signal variation, characterized in that, include: The magnetic signal data acquisition module is used to arrange a uniform and penetrating external magnetic field around the pipe and to acquire the magnetic signal data of the pipe using a magnetic field sensor. A noise processing module is used to process the magnetic signal data to obtain a second magnetic signal data. The data normalization processing module is used to normalize the second magnetic signal data to obtain the third magnetic signal data; The magnetic signal data correction module is used to collect external environmental data to correct the third magnetic signal data and obtain the corrected third magnetic signal data. The step of collecting external environmental data to correct the third magnetic signal data to obtain the corrected third magnetic signal data includes: collecting temperature data of the external environment of the pipeline through a temperature sensor, and correcting the third magnetic signal data for temperature based on the thermal expansion coefficient of the pipeline material. The feature parameter extraction module is used to extract feature parameters from the corrected third magnetic signal data, and to establish a mathematical relationship model between the magnetic signal and the pipe wall thickness using a linear regression method based on the feature parameters. The wall thickness calculation module is used to input the characteristic parameters into the mathematical relationship model between the magnetic signal and the pipe wall thickness to calculate the specific wall thickness of the current pipe. The alarm module is used to perform wall thickness trend analysis on the pipe wall thickness based on historical wall thickness data to obtain predicted wall thickness data. A wall thickness safety threshold is set according to the predicted wall thickness data. If the current specific wall thickness value of the pipe is lower than the wall thickness safety threshold, the alarm system is triggered. The feature parameter extraction module is specifically used for: The amplitude and phase of the corrected third magnetic signal data are extracted using wavelet transform. Based on the amplitude and phase of the corrected third magnetic signal data, a mathematical relationship model between the magnetic signal and the pipe wall thickness is established using linear regression, including: The formula for obtaining the amplitude and phase of the corrected third magnetic signal data is as follows: ； in, The amplitude of the corrected third magnetic signal data; These are the wavelet transform coefficients under the scaling factor a and the translation factor b; ； in, The phase of the corrected third magnetic signal data; ； Where a is the scaling factor and b is the translation factor. The complex conjugate of the mother wavelet; Based on the amplitude and phase of the corrected third magnetic signal data, a mathematical model of the relationship between the magnetic signal and the pipe wall thickness is established using a linear regression method. The formula is as follows: ； Where d is the pipe wall thickness. For the intercept term of the regression model, The first regression coefficient related to the amplitude. The second regression coefficient is related to the phase. This is the random error term.

8. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the pipe wall thickness calculation method based on magnetic signal variation as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the pipe wall thickness calculation method based on magnetic signal variation as described in any one of claims 1-6.

Images