Defect identification method for magnetic flux leakage detection robot

Abstract

The invention provides a defect identification method for a magnetic flux leakage detection robot, and relates to the technical field of artificial intelligence, and the method comprises the following steps: configuring an excitation part magnetization storage tank, adding a performance test standard, and receiving a simulation sample; a detection scene is drawn up, a magnetic flux leakage detection device is integrated on the wall-climbing robot, compatibility testing is achieved by starting the robot to move, receiving changes of a magnetic flux leakage field and outputting defect results, and the problems that when the surface form of the storage tank is complex or corrosion and crack forms are diversified, the accuracy and comprehensiveness of magnetic flux leakage detection are insufficient, and missing detection or false detection is prone to occurring are solved. The technical problem that effective automatic detection cannot be achieved on the surfaces of different types of storage tanks is solved, the coverage rate and efficiency of detection are improved through movement of the wall-climbing robot along the preset path of the surfaces of the storage tanks, it is ensured that each area of the surfaces of the storage tanks can be effectively detected, the precision and reliability of magnetic flux leakage detection are improved, and the safety of storage tank detection is improved. The technical effect of accurately recognizing the surface defects of the storage tank is achieved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a defect recognition method for a magnetic flux leakage detection robot. Background Art

[0002] With the rapid development of modern industry, various types of storage tanks (such as oil tanks, gas tanks, water tanks, etc.) are increasingly used in chemical, petroleum, energy and other industries. Storage tanks are important storage equipment. Once leakage or corrosion occurs, it will cause serious losses and environmental hazards. Therefore, in order to ensure the long-term safe operation of storage tanks, various detection technologies have emerged. Among them, non-destructive testing technologies (such as ultrasonic testing, magnetic particle testing and magnetic flux leakage testing) are widely used in the inspection process of storage tanks. Magnetic flux leakage detection technology is widely used for defect detection of metal materials and structures, especially for detecting surface defects and inner wall corrosion of equipment such as storage tanks. However, on some more complex or difficult to access storage tank surfaces, missed detection or false detection is prone to occur, and the efficiency and accuracy of magnetic flux leakage detection are limited.

[0003] In the prior art, when the surface morphology of the storage tank is complex or the corrosion and crack morphology are diverse, the accuracy and comprehensiveness of magnetic flux leakage detection are insufficient, and missed detection or false detection may easily occur, and effective automated detection cannot be achieved on the surfaces of different types of storage tanks. Summary of the invention

[0004] The present application provides a defect identification method for a magnetic flux leakage detection robot, which solves the technical problem that when the surface morphology of the tank is complex or the corrosion and crack morphology are diverse, the magnetic flux leakage detection is insufficient in accuracy and comprehensiveness, and missed detection or false detection is prone to occur, and effective automated detection cannot be achieved on the surfaces of different types of tanks. By moving the wall-climbing robot along a predetermined path on the tank surface, the coverage and efficiency of the detection are improved, ensuring that each area on the tank surface can be effectively detected, improving the accuracy and reliability of magnetic flux leakage detection, and improving the safety of tank detection, achieving the technical effect of accurately identifying surface defects of the tank.

[0005] In view of the above problems, the present application provides a defect identification method for a magnetic flux leakage detection robot.

[0006] The present application provides a defect identification method for a magnetic flux leakage detection robot, wherein the method comprises: configuring an excitation component, the excitation component magnetizing the storage tank to obtain a leakage magnetic field; configuring a magnetic flux leakage detection device based on the tank cavity structure, the magnetic flux leakage detection device having a built-in longitudinally arranged dual probe array; adding performance test standards according to the magnetic flux leakage detection device, and receiving corrosion thinning simulation samples of the same type of storage tank; formulating a magnetic flux leakage detection scenario through the corrosion thinning simulation samples, integrating the magnetic flux leakage detection device into a wall-climbing robot, and performing a compatibility test; after the compatibility test passes, in the magnetic flux leakage detection scenario, starting the wall-climbing robot to move along a predetermined path on the surface of the tank, receiving changes in the leakage magnetic field, and converting them into electrical signals for defect threshold determination, and outputting defect identification results.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By detecting the real-time changes of the leakage magnetic field and converting them into electrical signals, the defect threshold is automatically determined and accurate defect identification results are output. The wall-climbing robot moves along a predetermined path on the tank surface, which improves the coverage and efficiency of detection, ensures that every area on the tank surface can be effectively detected, improves the accuracy and reliability of leakage magnetic detection, improves the safety of tank detection, and achieves the technical effect of accurately identifying tank surface defects (such as corrosion, cracks, etc.). BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 This is a flow chart of the defect identification method for a magnetic flux leakage detection robot used in this application. DETAILED DESCRIPTION

[0010] The present application provides a defect identification method for a magnetic flux leakage detection robot, which solves the technical problem that when the surface morphology of the tank is complex or the corrosion and crack morphology are diverse, the magnetic flux leakage detection is insufficient in accuracy and comprehensiveness, and missed detection or false detection is prone to occur, and effective automated detection cannot be achieved on the surfaces of different types of tanks. By moving the wall-climbing robot along a predetermined path on the tank surface, the coverage and efficiency of the detection are improved, ensuring that each area on the tank surface can be effectively detected, improving the accuracy and reliability of magnetic flux leakage detection, and improving the safety of tank detection, achieving the technical effect of accurately identifying surface defects of the tank.

[0011] Embodiment 1

[0012] like Figure 1 As shown, the present application provides a defect identification method for a magnetic flux leakage detection robot, wherein the method comprises:

[0013] S100: configuring an excitation component, which magnetizes the storage tank to obtain a leakage magnetic field; S200: configuring a leakage magnetic field detection device based on the tank cavity structure, wherein the leakage magnetic field detection device has a built-in longitudinally arranged dual probe array; S300: adding performance test standards according to the leakage magnetic field detection device, and receiving corrosion thinning simulation samples of the same type of storage tank.

[0014] Specifically, the excitation component is responsible for generating a strong magnetic field to magnetize the tank so as to generate a leakage magnetic field in the metal structure of the tank. The strength and direction of this magnetic field can be adjusted as needed to accommodate different types of tanks and expected defect types. The leakage magnetic field refers to the leakage of the magnetic field caused by material discontinuities (such as cracks, corrosion, etc.) in the metal structure. Changes in the leakage magnetic field can be used to detect defects in the tank. The leakage magnetic field detection device is used to detect changes in the leakage magnetic field. It has a built-in longitudinally arranged dual probe array, which can more accurately capture changes in the leakage magnetic field. The performance test standard is used to evaluate the performance of the leakage magnetic field detection device to ensure that the device can accurately detect and identify defects in the tank. The corrosion and thinning simulation sample simulates the corrosion and thinning that may occur in the actual tank during long-term use, and is used to test and calibrate the leakage magnetic field detection device.

[0015] The excitation component is configured near the tank to magnetize the tank and generate a leakage magnetic field. This process involves adjusting the magnetic field strength and direction of the excitation component to ensure that the tank is uniformly magnetized, providing the necessary magnetic field environment for subsequent defect detection. The change in the leakage magnetic field is the basis for detecting tank defects. Based on the cavity structure of the tank, a leakage magnetic field detection device is configured. This device has a built-in longitudinally arranged dual probe array, which can more accurately capture changes in the leakage magnetic field. The design and arrangement of the probe array needs to be determined according to the specific structure of the tank and the expected defect type. By accurately capturing changes in the leakage magnetic field, detailed information about tank defects is provided, thereby improving the accuracy and reliability of detection.

[0016] On the basis of the magnetic flux leakage detection device, performance test standards are added, and corrosion and thinning simulation samples of the same type of tanks are received. These samples are used to simulate the corrosion and thinning that may occur in actual tanks during long-term use, so as to test and calibrate the performance of the magnetic flux leakage detection device and ensure that the magnetic flux leakage detection device can accurately detect and identify defects in the tanks. Through these tests, the parameters of the detection device can be adjusted and optimized to improve its performance and reliability in actual applications.

[0017] S400: A magnetic flux leakage detection scenario is formulated through the corrosion and thinning simulation sample, the magnetic flux leakage detection device is integrated into a wall-climbing robot, and a compatibility test is performed; S500: After the compatibility test is passed, in the magnetic flux leakage detection scenario, the wall-climbing robot is started to move along a predetermined path on the surface of the tank, the change of the magnetic flux leakage field is received, and converted into an electrical signal for defect threshold determination, and the defect identification result is output.

[0018] Specifically, the magnetic flux leakage detection scenario refers to a test environment that simulates the actual tank inspection environment, which is used to verify the performance and accuracy of the magnetic flux leakage detection device before actual application; the wall-climbing robot is able to move along the surface of the tank and is usually used to perform inspection, cleaning or other maintenance tasks; the compatibility test refers to a test to ensure that the magnetic flux leakage detection device and the wall-climbing robot can work together without technical conflicts; the predetermined path refers to the pre-set path followed by the wall-climbing robot when moving on the surface of the tank to ensure that the detection covers all critical areas of the tank; the electrical signal refers to the signal converted from the leakage magnetic field change received by the magnetic flux leakage detection device, which is used for further analysis and defect identification.

[0019] A simulated magnetic flux leakage detection scenario is created using corrosion thinning simulation samples. This scenario is used to simulate various defect conditions that may be encountered in actual storage tanks. Then, the magnetic flux leakage detection device is integrated into the wall-climbing robot so that it can move along the surface of the tank and detect changes in the leakage magnetic field. By simulating the actual detection environment, the performance of the magnetic flux leakage detection device can be verified, and it can be ensured that its integration with the wall-climbing robot will not affect the detection effect. After the magnetic flux leakage detection device is integrated into the wall-climbing robot, a series of compatibility tests are carried out to ensure that the two can work together and that the detection device can accurately receive and process changes in the leakage magnetic field. Through compatibility tests, possible problems can be discovered and resolved to ensure the accuracy and reliability of the detection data.

[0020] After the compatibility test is passed, the wall-climbing robot is started to move along a predetermined path on the surface of the tank. The magnetic flux leakage detection device carried by the wall-climbing robot receives changes in the leakage magnetic field and converts them into electrical signals, which are then used for defect threshold determination. The mobility of the wall-climbing robot enables the detection to cover the entire surface of the tank, while the magnetic flux leakage detection device provides detailed information about the tank's defects. By converting changes in the leakage magnetic field into electrical signals, defects in the tank can be further analyzed and identified. Based on the received electrical signals and the preset defect threshold, it is automatically determined whether a defect exists and the defect identification result is output, that is, an accurate defect identification result is provided, which not only helps to promptly repair potential problems of the tank, but also improves the safety and reliability of the tank.

[0021] Furthermore, the excitation component magnetizes the storage tank to obtain a leakage magnetic field, and the method includes:

[0022] The wall thickness data is obtained, and the expected defect type is determined in combination with the historical defect records; the wall thickness data, the expected defect type, and the tank material are combined and adaptation conditions are formulated to determine the adaptation magnetization method; according to the adaptation magnetization method, the tank is magnetized to obtain the leakage magnetic field.

[0023] Specifically, wall thickness data refers to the thickness information of the tank wall, which is an important parameter for evaluating the structural integrity of the tank and has a direct impact on determining the magnetization intensity and method; historical defect records refer to the defect records found in previous tank inspections, which help predict and identify the types of defects that may recur; expected defect types are based on wall thickness data and historical defect records, predicting the types of defects that may occur in the current tank; adaptation conditions refer to the magnetization conditions determined based on wall thickness data, expected defect types and tank materials to ensure the accuracy and effectiveness of leakage magnetic detection; adaptive magnetization method is the magnetization method determined based on the adaptation conditions, which can be circumferential magnetization or longitudinal magnetization to adapt to different tank structures and the distribution of expected defects.

[0024] By measuring or obtaining the thickness data of the tank wall from the database and combining it with historical defect records, the possible defect types are analyzed, which provides important prerequisite information for magnetic flux leakage detection. Wall thickness data and expected defect types are key factors in determining the magnetization method and detection strategy; taking the wall thickness data, expected defect type and tank material into consideration, a magnetization method suitable for the current tank conditions is formulated, which may include selecting circumferential magnetization or longitudinal magnetization, as well as adjusting other magnetization parameters; determining the adaptation conditions is a key step in ensuring the effectiveness of magnetic flux leakage detection. The correct magnetization method can improve the sensitivity and accuracy of detection and reduce false alarms and missed alarms.

[0025] According to the magnetization method determined in the previous steps, the tank is magnetized using an excitation component to generate a leakage magnetic field. This step requires precise control of the magnetization parameters to ensure the uniformity and stability of the leakage magnetic field. Magnetization is the basis of leakage magnetic field detection and directly affects the accuracy of subsequent detection. Through the adaptive magnetization method, the defects in the tank can be detected to the maximum extent, providing a reliable leakage magnetic field signal for subsequent defect identification. Through the above steps, the personalization and accuracy of leakage magnetic field detection are ensured, so that the detection process can be optimized according to the specific conditions of the tank, thereby improving the efficiency and accuracy of the detection.

[0026] Furthermore, the wall thickness data, expected defect type, and tank material are combined and matching conditions are formulated to determine the matching magnetization mode. The method includes:

[0027] According to the tank structure, an initial magnetization mode is determined, and an initial magnetization parameter set is collected; through the initial magnetization mode and the initial magnetization parameter set, an adaptive magnetization parameter set is determined according to the adaptive condition.

[0028] Specifically, the initial magnetization method refers to the general method or strategy used for tank magnetization before it is optimized for the specific tank structure and expected defect type; the initial magnetization parameter set refers to a series of parameters related to the initial magnetization method, including magnetic field strength, magnetization direction, etc., which are used for adjustment during the magnetization process; the adaptive magnetization parameter set refers to the magnetization parameter set adjusted according to factors such as the specific structure of the tank, expected defect type and material, in order to achieve the best magnetization effect and detection sensitivity.

[0029] Based on the general structural characteristics of the storage tank, a standard magnetization method is selected as the starting point, including the direction (circumferential or longitudinal) and strength of the magnetic field. At the same time, all parameters related to this initial method are collected to form an initial magnetization parameter set, which provides a benchmark for subsequent magnetization parameter adjustments. The initial magnetization method and parameter set are the basis for personalized adaptation, ensuring the rationality of the starting point of the magnetization process.

[0030] Using the initial magnetization method and parameter set as a reference, combined with wall thickness data, expected defect types, and tank material adaptation conditions, the initial parameters are adjusted to determine the magnetization parameter set that best suits the current tank conditions; by adjusting the magnetization parameters, the effect of magnetic flux leakage detection can be optimized, the accuracy and reliability of defect detection can be improved, and the determination of the adaptive magnetization parameter set can be made so that the magnetization process can better adapt to the specific conditions of the tank, thereby maximizing the detection effect. The magnetization parameter adjustment process from general to specific ensures that magnetic flux leakage detection can be optimized for different tank conditions to achieve the best detection effect.

[0031] Furthermore, the method comprises:

[0032] The adaptive magnetization method includes a circumferential magnetization method and a longitudinal magnetization method. If the direction of the expected defects is distributed along the circumferential direction of the tank, the circumferential magnetization method is used as the adaptive magnetization method; if the direction of the expected defects is distributed along the axial direction of the tank, the longitudinal magnetization method is used as the adaptive magnetization method.

[0033] Specifically, the circumferential magnetization method refers to the magnetic field lines applied along the circumferential direction of the tank. This method is suitable for detecting defects distributed along the circumferential direction of the tank; the longitudinal magnetization method refers to the magnetic field lines applied along the axial direction of the tank. This method is suitable for detecting defects distributed along the axial direction of the tank.

[0034] According to the structural characteristics of the tank and the distribution direction of the expected defects, the most appropriate magnetization method is selected. If the expected defects are mainly distributed along the circumference of the tank, the circumferential magnetization method is selected; if the expected defects are mainly distributed along the axial direction of the tank, the longitudinal magnetization method is selected. Selecting the appropriate magnetization method is crucial to improving the efficiency and accuracy of magnetic flux leakage detection. The correct magnetization direction can make the change of the leakage magnetic field more obvious, making it easier to be captured by the detection device, thereby improving the sensitivity of defect detection.

[0035] By analyzing historical data and the specific usage of the tank, the possible distribution direction of defects is predicted. If the defects are mainly distributed along the circumference of the tank, the circumferential magnetization method is selected; if the defects are mainly distributed along the axial direction of the tank, the longitudinal magnetization method is selected. The selection method based on the expected defect direction allows leakage magnetic detection to be more targeted. For example, the circumferential magnetization method can better detect circumferential welds and circumferential cracks, while the longitudinal magnetization method is more suitable for detecting axial welds and axial cracks.

[0036] After determining the adaptive magnetization method, the tank is magnetized accordingly through the excitation component. For example, if the circumferential magnetization method is selected, the excitation component needs to be set to generate a magnetic field along the circumferential direction of the tank. The adaptive magnetization method directly affects the generation of the leakage magnetic field and the subsequent defect detection effect. By precisely controlling the magnetization direction, the detection device's defect recognition ability can be maximized. According to the specific situation of the tank and the expected defect distribution direction, the adaptive magnetization method is selected and implemented to improve the accuracy and efficiency of leakage magnetic detection. Through this personalized magnetization strategy, it is ensured that leakage magnetic detection can play the greatest role in different application scenarios.

[0037] Furthermore, by using the corrosion and thinning simulation sample, a magnetic flux leakage detection scenario is proposed, and the method further includes:

[0038] A defect threshold range is set; based on the corrosion thinning simulation sample, a difference calculation is performed through the defect threshold range to determine the degree of deviation; based on the degree of deviation, a potential risk indicator is identified.

[0039] Specifically, the defect threshold range refers to the range of electrical signal strength used to distinguish between normal and abnormal (defect) conditions in magnetic flux leakage detection. Signal changes beyond this range are considered to be signs of defects; difference calculation refers to comparing the actual detected signal value with the preset threshold and calculating the difference between the two; the degree of deviation refers to the degree of difference between the actual detection signal and the threshold, which can be used to assess the severity of the defect; potential risk indicators refer to characteristics or parameters that may indicate risks in the tank based on the degree of deviation.

[0040] According to the historical data of magnetic flux leakage detection, the material properties of the tank and the expected defect types, a range of electrical signal strength is set as the standard for judging whether there are defects. This threshold range needs to be sensitive enough to capture small defects while avoiding false alarms. The setting of the defect threshold range directly affects the accuracy of the detection results. Reasonable threshold settings can ensure that the detection system is both sensitive and stable.

[0041] Use corrosion thinning simulation samples for testing to obtain actual leakage magnetic field signals, compare them with the preset defect threshold range, and calculate the difference between the actual signal and the threshold. Through difference calculation, it is possible to quantitatively evaluate whether the defect signal in the simulation sample exceeds the preset threshold, thereby verifying the rationality of the threshold setting and providing a reference for actual detection. According to the results of the difference calculation, the degree of deviation between the actual signal and the threshold is evaluated, and this degree can reflect the size and severity of the defect. The degree of deviation is an important indicator for evaluating the severity of defects. By determining the degree of deviation, defects can be graded to provide a basis for subsequent repair and maintenance decisions. Based on the degree of deviation, combined with the operating history and environmental factors of the tank, characteristics or parameters that may indicate risks to the tank are identified, such as specific signal patterns or abnormal signal changes. Through potential risk indicators, potential problems of the tank can be discovered in advance, and preventive measures can be taken to avoid accidents.

[0042] Furthermore, the defect threshold range is set, and the method includes:

[0043] Adding magnetization influencing factors, wherein the magnetization influencing factors include a conductive layer and a surface coating; and elastically optimizing the defect threshold range based on the magnetization influencing factors.

[0044] Specifically, magnetization influencing factors refer to factors that may affect the distribution and intensity of the magnetic field during the magnetization process, which may interfere with the results of magnetic flux leakage detection; the conductive layer refers to the conductive material layer on the surface or inside the tank, which may affect the distribution of the magnetic field because the conductive layer can redistribute the current and thus affect the magnetic field; the surface coating refers to the protective layer or decorative layer on the surface of the tank, which may affect the penetration and distribution of the magnetic field and thus affect the accuracy of magnetic flux leakage detection; elastic optimization refers to the dynamic adjustment of the defect threshold range according to actual conditions to adapt to different detection conditions and environments.

[0045] During the MFL test, all factors that may affect the magnetization effect are identified and considered, such as conductive layers and surface coatings, which may change the distribution of the magnetic field and thus affect the accuracy of the MFL test. By identifying and considering these magnetization influencing factors, the behavior of the magnetic field in the tank can be more accurately simulated and predicted, which is crucial to improving the accuracy and reliability of MFL testing.

[0046] According to the specific influence of magnetization factors such as conductive layer and surface coating, the defect threshold range is adjusted. This adjustment may increase or decrease the sensitivity of the threshold to adapt to different detection conditions; elastic optimization of the defect threshold range enables magnetic flux leakage detection to adapt to different tank conditions and environments, improving the flexibility and adaptability of the detection system. Through this optimization, false alarms and missed alarms can be reduced to ensure the accuracy of the detection results. By considering the influence of magnetization to optimize the defect threshold range, the accuracy and reliability of magnetic flux leakage detection can be improved. Through this optimization, it is ensured that the magnetic flux leakage detection system can provide accurate detection results under different tank conditions and environments.

[0047] Furthermore, based on the magnetization influencing factors, the defect threshold range is elastically optimized, and the method includes:

[0048] Through external environmental variables, false signals are marked, wherein the false signals represent abnormal electrical signals not caused by defects. Based on the false signals, a compensation mechanism is introduced, and a multi-round iterative verification process is set.

[0049] Specifically, external environmental variables refer to factors other than the tank itself, such as surrounding magnetic fields, electromagnetic interference, etc., which may affect the signal readings of the magnetic flux leakage detection device; false signals refer to abnormal electrical signals that are not caused by actual defects in the tank, which may be caused by external environmental variables or other non-defect factors; compensation mechanism refers to the method or algorithm used to correct or compensate for errors or deviations caused by non-defect factors during the detection process; the multi-round iterative verification process refers to the process of verifying and improving the accuracy of the detection results through repeated detection and analysis.

[0050] During the magnetic flux leakage detection process, external environmental variables that may affect the detection results, such as temperature, humidity, and surrounding electromagnetic fields, are monitored and recorded. These data are used to identify and mark abnormal electrical signals that are not caused by tank defects, that is, false signals. Correctly identifying and marking false signals is crucial to improving the accuracy of detection results. By eliminating interference caused by these non-defects, the detection system can be focused on real defect signals and reduce false alarms. Once false signals are identified, corresponding compensation mechanisms are introduced to correct these errors. The compensation mechanism may include algorithm correction, signal filtering, or model adjustment to eliminate or reduce the impact of false signals. The introduction of the compensation mechanism improves the robustness of magnetic flux leakage detection, allowing the detection system to maintain high accuracy and reliability in the presence of external interference.

[0051] During the detection process, multiple rounds of iterative verification are implemented. After each round of detection, the results are analyzed, especially those abnormal results that may be caused by false signals. According to the analysis results, the compensation mechanism is adjusted, and the next round of detection is carried out until the results are stable or reach the preset accuracy standard. The multiple rounds of iterative verification process is an effective quality control method. It improves the accuracy and reliability of the test results through continuous testing and adjustment. This process is particularly suitable for complex environments or critical applications to ensure the accuracy and credibility of the test results. In the above steps, the accuracy and reliability of magnetic flux leakage detection are improved by identifying and processing false signals and implementing multiple rounds of iterative verification processes, which helps to ensure the authenticity and effectiveness of the test results and ensure the safe operation of the tank.

[0052] Furthermore, based on the false signal, a compensation mechanism is introduced, and a multi-round iterative verification process is set. The method also includes:

[0053] A plurality of independent probe arrays are arranged at the same position to collect multi-channel signals simultaneously; through the multi-channel signals, local interference is ignored according to a redundant detection channel mechanism.

[0054] Specifically, multiple independent probe arrays refer to multiple probe groups arranged in the same position or area, each probe group can independently collect signals; multi-path signals refer to different signal paths collected simultaneously by multiple independent probe arrays; redundant detection channel mechanism refers to a method of using multiple signal sources to improve the reliability and accuracy of the detection system, and to identify and eliminate errors or interference by comparing data from different signal sources.

[0055] Multiple independent probe arrays are installed at the same position or area of ​​the tank. Each probe array is capable of independently collecting leakage magnetic field signals. These probe arrays may have different directions or configurations to ensure that signals can be captured from multiple angles. By arranging multiple probe arrays, the redundancy of signal acquisition can be increased and the reliability of the detection system can be improved. This method helps to capture changes in the leakage magnetic field from different angles, thereby providing more comprehensive defect information. Signals are collected from multiple independent probe arrays at the same time to form multi-channel signals. These signals may contain different information because they are collected from different positions or angles. The collection of multi-channel signals can provide more comprehensive tank status information and help identify and analyze defects. This method can increase the accuracy of the detection results because it allows the existence of defects to be verified from multiple angles.

[0056] By comparing and analyzing the multi-channel signals collected by multiple probe arrays, a redundant detection channel mechanism is used to identify and eliminate local interference or erroneous signals, involving signal processing algorithms such as average filtering, median filtering or more complex statistical analysis methods; the use of a redundant detection channel mechanism can effectively reduce the impact of local interference on the detection results, improve the accuracy and reliability of detection, and by comparing data from different signal sources, outliers can be identified, and erroneous signals can be eliminated or corrected accordingly, ensuring that the final detection results are more accurate.

[0057] In the above steps, the accuracy and reliability of magnetic flux leakage detection are improved by arranging multiple independent probe arrays and utilizing a redundant detection channel mechanism, which helps to ensure that the detection system can work stably under complex environmental conditions, reduce false alarms and missed alarms, and provide strong protection for the safe operation of storage tanks.

[0058] In summary, the defect identification method for a magnetic flux leakage detection robot provided in this application has the following technical effects:

[0059] Due to the use of an excitation component, the excitation component magnetizes the tank to obtain a leakage magnetic field; based on the tank cavity structure, a leakage magnetic detection device is configured, and the leakage magnetic detection device has a built-in longitudinally arranged dual probe array; according to the leakage magnetic detection device, performance test standards are added, and corrosion thinning simulation samples of the same type of tank are received; through the corrosion thinning simulation samples, a leakage magnetic detection scenario is proposed, the leakage magnetic detection device is integrated into the wall-climbing robot, and a compatibility test is performed; after the compatibility test passes, in the leakage magnetic detection scenario, the wall-climbing robot is started to move along a predetermined path on the surface of the tank, the change of the leakage magnetic field is received, and it is converted into an electrical signal for defect threshold judgment, and the defect identification result is output. This application provides a defect identification method for a leakage magnetic detection robot, and through the movement of the wall-climbing robot along a predetermined path on the surface of the tank, the detection coverage and efficiency are improved, ensuring that each area on the surface of the tank can be effectively detected, improving the accuracy and reliability of leakage magnetic detection, improving the safety of tank detection, and achieving the technical effect of accurate identification of tank surface defects.

[0060] This specification and drawings are merely exemplary illustrations of the present application. Various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. These modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, and the present application is intended to include these modifications and variations.

Claims

1. A defect identification method for a magnetic flux leakage detection robot, characterized in that: The method comprises: An excitation component is configured, wherein the excitation component magnetizes the storage tank to obtain a leakage magnetic field; Based on the tank cavity structure, a magnetic flux leakage detection device is configured, and the magnetic flux leakage detection device has a built-in longitudinally arranged double probe array; According to the magnetic flux leakage detection device, performance test standards are added, and corrosion thinning simulation samples of the same type of storage tanks are received; By using the corrosion and thinning simulation sample, a magnetic flux leakage detection scenario is proposed, the magnetic flux leakage detection device is integrated into the wall-climbing robot, and a compatibility test is performed; After the compatibility test is passed, in the magnetic flux leakage detection scenario, the wall-climbing robot is started to move along a predetermined path on the surface of the tank, receives changes in the magnetic flux leakage field, converts them into electrical signals for defect threshold determination, and outputs defect identification results.

2. The method according to claim 1, characterized in that The excitation component magnetizes the storage tank to obtain a leakage magnetic field, and the method includes: Obtain wall thickness data and determine expected defect types based on historical defect records; The wall thickness data, expected defect type, and tank material are combined and matching conditions are formulated to determine the matching magnetization method; According to the adapted magnetization method, the storage tank is magnetized to obtain a leakage magnetic field.

3. The method according to claim 2, characterized in that The wall thickness data, expected defect type, and tank material are combined and matching conditions are formulated to determine a matching magnetization method. The method includes: According to the tank structure, determine the initial magnetization method and collect the initial magnetization parameter set; An adaptive magnetization parameter set is determined through the initial magnetization mode and the initial magnetization parameter set according to the adaptation condition.

4. The method according to claim 3, characterized in that The adapted magnetization mode includes a circumferential magnetization mode and a longitudinal magnetization mode; If the direction of the expected defects is distributed along the circumference of the tank, the circumferential magnetization method is used as the adaptive magnetization method; If the direction of the expected defects is distributed along the axis of the tank, the longitudinal magnetization method is used as the adaptive magnetization method.

5. The method according to claim 3, characterized in that By using the corrosion and thinning simulation sample, a magnetic flux leakage detection scenario is formulated, and the method further includes: Set defect threshold range; Based on the corrosion thinning simulation sample, performing difference calculation through the defect threshold range to determine the degree of deviation; Based on the degree of deviation, potential risk indicators are identified.

6. The method according to claim 5, characterized in that Setting a defect threshold range, the method comprising: Adding magnetization influencing factors, wherein the magnetization influencing factors include a conductive layer and a surface coating; Based on the magnetization influencing factors, the defect threshold range is elastically optimized.

7. The method according to claim 6, characterized in that Based on the magnetization influencing factors, the defect threshold range is elastically optimized, and the method includes: By using external environmental variables, a false signal is marked, wherein the false signal represents an abnormal electrical signal not caused by a defect; Based on the false signal, a compensation mechanism is introduced and a multi-round iterative verification process is set up.

8. The method according to claim 7, characterized in that Based on the false signal, a compensation mechanism is introduced, and a multi-round iterative verification process is set. The method further includes: Arrange multiple independent probe arrays at the same location to collect multiple signals simultaneously; Through the multiplexed signals, local interference is ignored according to a redundant detection channel mechanism.

Images