Oil and gas pipeline internal detection and defect quantification system and method based on speed compensation

Abstract

The invention discloses an oil and gas pipeline internal detection and defect quantification system and method based on speed compensation, and relates to the technical field of oil and gas pipeline internal detection, and the system comprises a pipeline internal detection device, a speed detection device and a defect quantification device. The in-pipeline detection device is used for moving in the axial direction of the oil and gas pipeline under the driving of a medium in the oil and gas pipeline and detecting the oil and gas pipeline in the moving process to obtain a magnetic detection signal, and the speed detection device is used for detecting the moving speed of the in-pipeline detection device in real time to obtain an instantaneous moving speed; and the defect quantification device is used for carrying out feature extraction on the magnetic detection signal to obtain a magnetic detection signal feature, and carrying out defect quantification based on the magnetic detection signal feature and the instantaneous movement speed to obtain size information of the defect in the oil and gas pipeline. The quantization precision of the defects in the oil and gas pipeline can be improved based on speed compensation.

Description

Technical Field

[0001] This application relates to the field of oil and gas pipeline internal inspection technology, and in particular to a system and method for oil and gas pipeline internal inspection and defect quantification based on velocity compensation. Background Technology

[0002] Electromagnetic nondestructive testing (EMT) is a technique that detects defects based on the electrical conductivity and magnetism of objects. It can examine the internal structure and potential defects of the object being tested without damaging or altering its structure and properties. Due to its advantages such as non-contact operation, high efficiency, and reliable results, it is widely used to assess pipeline integrity. Magnetic testing technology (also known as magnetic detection technology) can be categorized according to magnetization intensity: metallic magnetic memory testing, weak magnetic testing, unsaturated magnetization testing, and magnetic flux leakage testing. Pipeline internal inspection devices based on magnetic testing technology have been widely used in detecting defects on the inner surface of oil and gas pipelines.

[0003] However, under high-speed operation of the medium in oil and gas pipelines, the relative motion between the oil and gas pipeline and the two magnetic poles (i.e., the two ends of the magnet) of the detection device inside the pipeline will generate motion-induced eddy currents. This is because when there is relative motion between the oil and gas pipeline and the two magnetic poles of the detection device inside the pipeline, according to Faraday's law of electromagnetic induction, an induced electromotive force will be generated in the oil and gas pipeline, thus forming motion-induced eddy currents in the oil and gas pipeline. When the motion-induced eddy currents appear in the oil and gas pipeline being detected, according to Lenz's law, the motion-induced eddy currents will generate a magnetic field opposite to the static magnetic field. This reverse magnetic field will interact with the static magnetic field, thereby weakening the magnetization effect of the static magnetic field, resulting in a weakening of the magnetization of the oil and gas pipeline. Regardless of the magnetic detection technology, the magnetization intensity of the oil and gas pipeline will change due to the velocity effect, resulting in a weakening of the magnetization of the oil and gas pipeline. At this time, the magnetic detection signal obtained by the magnetic sensor in the detection device inside the pipeline will be distorted. When quantifying the defect size based on the characteristics of the distorted magnetic detection signal obtained by the magnetic sensor, the quantification accuracy of defects in the oil and gas pipeline will be reduced. Summary of the Invention

[0004] The purpose of this application is to provide a velocity-compensated system and method for detecting and quantifying defects in oil and gas pipelines, which can improve the quantification accuracy of defects in oil and gas pipelines based on velocity compensation.

[0005] To achieve the above objectives, this application provides the following solution.

[0006] In a first aspect, this application provides a velocity-compensated in-pipeline inspection and defect quantification system, the velocity-compensated in-pipeline inspection and defect quantification system comprising: The pipeline detection device is located inside the oil and gas pipeline. It is used to move along the axial direction of the oil and gas pipeline under the drive of the medium in the oil and gas pipeline, and to detect the oil and gas pipeline during the movement to obtain magnetic detection signals. A speed detection device is located inside the oil and gas pipeline and is installed on the pipeline detection device to detect the moving speed of the pipeline detection device in real time and obtain the instantaneous moving speed. The defect quantification device is communicatively connected to the pipeline detection device and the speed detection device, respectively. It is used to extract features from the magnetic detection signal to obtain magnetic detection signal features, and to quantify defects based on the magnetic detection signal features and the instantaneous moving speed to obtain the size information of defects in the oil and gas pipeline.

[0007] Optionally, the pipeline detection device includes a mounting base, a magnetizing component, and a detection component; The magnetizing component is arranged around the mounting base, and the outer surface of the magnetizing component is in contact with the inner surface of the oil and gas pipeline. The magnetizing component is used to apply a static magnetic field to the inner surface of the oil and gas pipeline, so that the oil and gas pipeline is magnetized. The detection component is mounted on the mounting base and is used to receive the induced magnetic field generated on the inner surface of the oil and gas pipeline in a magnetized state, and output the magnetic detection signal.

[0008] Optionally, the magnetizing component includes a first magnet, a first magnetic conductor, a second magnet, and a second magnetic conductor; The first magnet and the second magnet are both arranged around the mounting base, and there is a gap between the first magnet and the second magnet. The first magnet and the second magnet are used to generate the static magnetic field. The first magnetic conductor is arranged around the first magnet, and the outer surface of the first magnetic conductor is in contact with the inner surface of the oil and gas pipeline. The second magnetic conductor is arranged around the second magnet, and the outer surface of the second magnetic conductor is in contact with the inner surface of the oil and gas pipeline. The first magnetic conductor and the second magnetic conductor are used to apply the static magnetic field to the inner surface of the oil and gas pipeline, so that the oil and gas pipeline is magnetized. Both the first magnetic conductor and the second magnetic conductor are steel brushes.

[0009] Optionally, the detection component includes multiple probe holders and multiple detection probes, with one probe holder corresponding to one detection probe; Multiple probe brackets are arranged in a circumferential array along the mounting base, the probe brackets are located between the first magnet and the second magnet, and there are gaps between the probe brackets and both the first magnet and the second magnet; The detection probe is mounted on the probe bracket and is used to receive the induced magnetic field generated on the inner surface of the oil and gas pipeline in a magnetized state, and output the magnetic detection signal.

[0010] Optionally, the speed detection device includes several speed detection components, each of which includes a mounting bracket, a mileage wheel, a gear, and a gear encoder. The mounting bracket is installed on the mounting base of the pipeline detection device; The odometer wheel is mounted on the mounting bracket and is in contact with the inner surface of the oil and gas pipeline. The odometer wheel is used to rotate when the detection device moves inside the pipeline. The gear is fixedly connected to the mileage wheel on the same axis and in the same phase. The gear is used to rotate when the mileage wheel rotates, and the rotation speed and direction of the gear are the same as those of the mileage wheel. The gear encoder is mounted on the mounting bracket and is arranged opposite to the gear. The gear encoder is used to output a pulse square wave voltage signal when the gear rotates one tooth, and to determine the real-time moving speed of the detection device in the pipeline based on the pulse square wave voltage signal. When there is one speed detection component, the real-time moving speed of the detection device inside the pipeline determined by the gear encoder in the speed detection component is taken as the instantaneous moving speed. When there are multiple speed detection components, the average value of the real-time moving speed of the detection device inside the pipeline determined by the gear encoders in all the speed detection components is taken as the instantaneous moving speed, so as to detect the moving speed of the detection device inside the pipeline in real time and obtain the instantaneous moving speed.

[0011] Optionally, in determining the real-time moving speed of the detection device inside the pipeline based on the pulse square wave voltage signal, the gear encoder is used to determine the high-level duration based on the pulse square wave voltage signal and calculate the ratio of the tooth tip length of the gear to the high-level duration to obtain the real-time moving speed of the detection device inside the pipeline.

[0012] Optionally, when each of the detection probes outputs a magnetic detection signal, the defect quantization device is used to extract features from the magnetic detection signal for each magnetic detection signal to obtain magnetic detection signal features, and to perform defect quantization based on the magnetic detection signal features and the instantaneous moving speed to obtain the size information of the defect in the oil and gas pipeline; the size information includes the length, width and depth of the defect; The detection probe is a triaxial magnetic sensor, and the magnetic detection signal includes an axial magnetic field signal, a radial magnetic field signal, and a circumferential magnetic field signal. The characteristics of the magnetic detection signal include the peak-to-valley difference and peak-to-valley spacing of the axial magnetic field signal, the peak-to-valley difference and peak-to-valley spacing of the radial magnetic field signal, and the peak-to-valley difference and peak-to-valley spacing of the circumferential magnetic field signal. The peak-to-valley difference is the difference between the peak value and the valley value, and the peak-to-valley spacing is the time interval between the peak value and the valley value.

[0013] Optionally, in terms of extracting features from the magnetic detection signal to obtain magnetic detection signal features, and performing defect quantization based on the magnetic detection signal features and the instantaneous moving speed to obtain the size information of the defect in the oil and gas pipeline, the defect quantization device is used to determine the defect response signal corresponding to the defect based on the magnetic detection signal, extract features from the defect response signal to obtain magnetic detection signal features, and use the magnetic detection signal features and the instantaneous moving speed as input to perform defect quantization using a trained defect quantization model to obtain the size information of the defect in the oil and gas pipeline; The trained defect quantification model adopts an SSA-BP neural network model, which is a BP neural network model obtained by initializing the network parameters of the BP neural network model using the SSA algorithm. The network parameters include weights and biases. When initializing the network parameters of the BP neural network model using the SSA algorithm, the fitness function is the validation error of the validation set.

[0014] Optionally, the pipeline detection device further includes an anti-collision head, which is mounted on the mounting base.

[0015] Secondly, this application provides a velocity-compensated method for in-pipeline inspection and defect quantification, applied to the aforementioned velocity-compensated system for in-pipeline inspection and defect quantification. The velocity-compensated method for in-pipeline inspection and defect quantification includes: The magnetic detection signal obtained by the pipeline detection device and the instantaneous moving speed obtained by the velocity detection device are acquired. Feature extraction is performed on the magnetic detection signal to obtain magnetic detection signal features. Based on the magnetic detection signal features and the instantaneous moving speed, defect quantification is performed to obtain the size information of the defect in the oil and gas pipeline.

[0016] According to the specific embodiments provided in this application, this application has the following technical effects: This application provides a velocity-compensated system and method for in-pipeline inspection and defect quantification, including an in-pipeline inspection device, a velocity detection device, and a defect quantification device. The in-pipeline inspection device moves axially along the oil and gas pipeline under the drive of the medium within the pipeline, and inspects the pipeline during movement to obtain a magnetic detection signal. The velocity detection device detects the movement speed of the in-pipeline inspection device in real time to obtain an instantaneous movement speed. The defect quantification device extracts features from the magnetic detection signal to obtain magnetic detection signal characteristics, and performs defect quantification based on the magnetic detection signal characteristics and the instantaneous movement speed to obtain the size information of the defects in the oil and gas pipeline. This application, based on the traditional defect quantification based on magnetic detection signal characteristics, introduces instantaneous movement speed. Defect quantification based on both magnetic detection signal characteristics and instantaneous movement speed can eliminate the influence of motion-induced eddy currents causing magnetization weakening and further distortion of the magnetic detection signal. Velocity compensation can improve the quantification accuracy of defects in oil and gas pipelines. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of a speed-compensated oil and gas pipeline internal detection and defect quantification system provided in Embodiment 1 of this application.

[0019] Figure 2 This is a three-dimensional schematic diagram showing the relative positions of the gear and the gear encoder provided in Embodiment 1 of this application.

[0020] Figure 3 This is a two-dimensional schematic diagram showing the relative positions of the gear and the gear encoder provided in Embodiment 1 of this application.

[0021] Figure 4 This is a schematic diagram of the high-level signal of the pulse square wave voltage signal corresponding to different instantaneous moving speeds provided in Embodiment 1 of this application.

[0022] Figure 5 This is a schematic diagram of the pulse square wave voltage signal output by the gear encoder provided in Embodiment 1 of this application; wherein, Figure 5 In the diagram, (a) represents the A-phase TTL differential square wave signal. Figure 5 (b) in the diagram represents the B-phase TTL differential square wave signal. Figure 5 (c) in the equation represents the origin signal of the Z phase.

[0023] Figure 6 This is a partial dimensional diagram of the gear provided in Embodiment 1 of this application.

[0024] Figure 7 This is a schematic diagram illustrating the working principle of a velocity-compensated oil and gas pipeline internal detection and defect quantification system provided in Embodiment 1 of this application.

[0025] Figure 8 This is a schematic diagram illustrating the process of initializing the network parameters of a BP neural network model using the Sparrow Search Algorithm (SSA) as provided in Embodiment 1 of this application.

[0026] Figure 9 This is a schematic diagram of the network structure of the BP neural network model provided in Embodiment 1 of this application.

[0027] Figure 10 This is a flowchart illustrating a speed-compensated method for detecting and quantifying defects in oil and gas pipelines, as provided in Embodiment 2 of this application.

[0028] Figure 11 This is a schematic diagram of the structure of a computer device provided in Embodiment 3 of this application.

[0029] Figure label: 1-Anti-collision head; 2-First magnet; 3-First magnetic conductor; 4-Probe bracket; 5-Detection probe; 6-Second magnetic conductor; 7-Second magnet; 8-Odometer wheel; 9-Integrated electronic system; 10-Gear; 11-Gear encoder. Detailed Implementation

[0030] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0031] Example 1.

[0032] This embodiment provides a velocity-compensated in-pipeline inspection and defect quantification system, such as... Figure 1 As shown, the velocity-compensated oil and gas pipeline in-pipeline detection and defect quantification system includes the following devices.

[0033] The pipeline detection device is located inside the oil and gas pipeline. It is used to move along the axial direction of the oil and gas pipeline under the drive of the medium in the oil and gas pipeline, and to detect the oil and gas pipeline during the movement to obtain magnetic detection signals.

[0034] The speed detection device is located inside the oil and gas pipeline and is installed on the pipeline detection device. It is used to detect the moving speed of the pipeline detection device in real time and obtain the instantaneous moving speed.

[0035] The defect quantification device is communicatively connected to the pipeline detection device and the velocity detection device, respectively. It is used to extract features from the magnetic detection signal to obtain the magnetic detection signal features, and to quantify the defects based on the magnetic detection signal features and the instantaneous moving speed to obtain the size information of the defects in the oil and gas pipeline.

[0036] The following, combined with Figure 1 This embodiment provides a detailed description of the velocity-compensated oil and gas pipeline in-pipeline inspection and defect quantification system used in this study.

[0037] (1) Pipeline detection device.

[0038] The pipeline inspection device in this embodiment is located inside the oil and gas pipeline. Driven by the medium in the pipeline, it moves along the axial direction of the pipeline and continuously inspects the pipeline during its movement, obtaining a magnetic detection signal. This magnetic detection signal is a voltage signal that varies with time. Different times correspond to different positions along the axial direction of the oil and gas pipeline. If there is no defect, the amplitude of the voltage signal at the corresponding position is a fixed value, and the magnetic detection signal is theoretically a straight line. If there is a defect, the amplitude of the voltage signal at the corresponding position will change, and the magnetic detection signal will fluctuate, producing peaks and troughs. Therefore, by judging whether the difference between the amplitude of the magnetic detection signal at each time point and the fixed value is greater than a preset threshold, it can be determined whether there is a defect. If it is greater than the preset threshold, it means there is a defect; if it is less than or equal to the preset threshold, it means there is no defect.

[0039] The pipe inspection device in this embodiment can be any structure based on the magnetic detection principle. As an example, such as... Figure 1 As shown, the pipeline detection device includes a mounting base, a magnetizing component, and a detection component. The magnetizing component is arranged around the mounting base, and its outer surface is in contact with the inner surface of the oil and gas pipeline. The magnetizing component is used to apply a static magnetic field to the inner surface of the oil and gas pipeline, thus magnetizing the pipeline. The detection component is mounted on the mounting base and is used to receive the induced magnetic field generated by the magnetized inner surface of the oil and gas pipeline and output a magnetic detection signal.

[0040] In this embodiment, the magnetizing component can be any structure capable of applying a static magnetic field to the inner surface of the oil and gas pipeline, thereby magnetizing the pipeline. As an example, such as... Figure 1 As shown, the magnetizing component includes a first magnet 2, a first magnetic conductor 3, a second magnet 7, and a second magnetic conductor 6.

[0041] The first magnet 2 and the second magnet 7 are both arranged around the mounting base, and there is a gap between the first magnet 2 and the second magnet 7. The first magnet 2 and the second magnet 7 are used to generate a static magnetic field. Specifically, the outer surface of the mounting base can be a cylindrical surface, and the inner surface of the first magnet 2 and the inner surface of the second magnet 7 can both be cylindrical surfaces.

[0042] The first magnetic conductor 3 is arranged around the first magnet 2, and the outer surface of the first magnetic conductor 3 is in contact with the inner surface of the oil and gas pipeline. The second magnetic conductor 6 is arranged around the second magnet 7, and the outer surface of the second magnetic conductor 6 is in contact with the inner surface of the oil and gas pipeline. The first magnetic conductor 3 and the second magnetic conductor 6 are used to apply a static magnetic field to the inner surface of the oil and gas pipeline, so that the oil and gas pipeline is magnetized. Specifically, the outer surface of the first magnet 2 and the outer surface of the second magnet 7 can both be cylindrical surfaces, and the inner and outer surfaces of the first magnetic conductor 3 and the second magnetic conductor 6 can both be cylindrical surfaces.

[0043] A static magnetic field can be generated by setting the first magnet 2 and the second magnet 7. The magnetic conduction function can be realized by setting the first magnetic conductor 3 and the second magnetic conductor 6. The static magnetic field is applied to the inner surface of the oil and gas pipeline, thereby magnetizing the oil and gas pipeline.

[0044] While magnets possess strong magnetic properties, they also exhibit high brittleness. If only the first magnet 2 and the second magnet 7 are provided, with their outer surfaces directly contacting the inner surface of the oil and gas pipeline, although a static magnetic field can be applied to the pipeline's inner surface to magnetize it, the first magnet 2 and the second magnet 7 may be damaged by impact. To protect the first magnet 2 and the second magnet 7, this embodiment further includes a first magnetic conductor 3 and a second magnetic conductor 6. The first magnetic conductor 3 and the second magnetic conductor 6 are selected from components with good toughness. They can both cooperate with the first magnet 2 and the second magnet 7 to apply a static magnetic field to the inner surface of the oil and gas pipeline to magnetize it, and also protect the first magnet 2 and the second magnet 7. Furthermore, the first magnetic conductor 3 and the second magnetic conductor 6 themselves are not easily damaged by impact with the inner surface of the oil and gas pipeline. Therefore, in this embodiment, the first magnetic conductor 3 and the second magnetic conductor 6 are selected from components with good toughness, such as yokes or steel brushes. Optionally, in this embodiment, both the first magnetic conductor 3 and the second magnetic conductor 6 are steel brushes, which have magnetic conduction function, good toughness, and will not be damaged by the inner surface of the oil and gas pipeline, and can also clean the inner surface of the oil and gas pipeline.

[0045] In this embodiment, the detection component can be any structure capable of receiving the induced magnetic field generated by the inner surface of a magnetized oil and gas pipeline, outputting a magnetic detection signal, and realizing the magnetic detection function. As an example, such as... Figure 1As shown, the detection component includes multiple probe brackets 4 and multiple detection probes 5, with one probe bracket 4 corresponding to one detection probe 5.

[0046] Multiple probe brackets 4 are arranged in a circumferential array along the mounting base. There is a gap between two adjacent probe brackets 4. Each probe bracket 4 is located between the first magnet 2 and the second magnet 7, and there is a gap between the probe bracket 4 and the first magnet 2 and the second magnet 7. Optionally, the distance from each probe bracket 4 to the first magnet 2 and the distance to the second magnet 7 are equal.

[0047] The detection probe 5 is mounted on the probe bracket 4, that is, the detection probe 5 is mounted on the probe bracket 4 corresponding to the detection probe 5. The detection probe 5 is used to receive the induced magnetic field generated on the inner surface of the oil and gas pipeline in a magnetized state and output a magnetic detection signal.

[0048] The detection component in this embodiment uses an array-type detection probe 5. The detection probe 5 can be any type of magnetic sensor. The magnetic sensor can be a triaxial magnetic sensor. A triaxial magnetic sensor is a sensor that can simultaneously measure magnetic field components in three mutually perpendicular directions (usually X, Y, and Z axes). The magnetic detection signal at this time is an axial magnetic field signal, a radial magnetic field signal, and a circumferential magnetic field signal (also called a ring magnetic field signal). Radial refers to the straight line direction from the center of the object outward, axial refers to the direction along the central axis of the object, and circumferential refers to the direction along the circumference of the object's surface.

[0049] It should be noted that for each position along the axial direction of the oil and gas pipeline, each detection probe 5 detects a region of the inner surface of the oil and gas pipeline at that position. The region detected by all detection probes 5 constitutes the inner surface of the oil and gas pipeline at that position, thereby ensuring that the inner surface of the oil and gas pipeline at any position can be fully covered and detected.

[0050] Since there are multiple detection probes 5, each of which outputs a magnetic detection signal, the magnetic detection signal output by each detection probe 5 is processed separately during subsequent defect quantification.

[0051] The pipe detection device in this embodiment also includes an anti-collision head 1, which is installed on the mounting base, specifically on the head of the mounting base, to prevent other objects from colliding with the pipe detection device.

[0052] (2) Speed ​​detection device.

[0053] The speed detection device in this embodiment is located inside the oil and gas pipeline and is installed on the pipeline detection device. It is used to detect the moving speed of the pipeline detection device in real time and obtain the instantaneous moving speed. Therefore, it can also be called the pipeline detection device instantaneous speed recording module.

[0054] Traditional speed measurement methods based on odometer wheels and encoders work by having the encoder output a pulse signal after the odometer wheel completes one revolution. The speed of the object being measured during the odometer wheel's one revolution is then calculated based on this pulse signal. Obviously, the speed calculated based on the pulse signal is only the average speed of the object during the odometer wheel's one revolution, not the instantaneous speed of the object.

[0055] To address this problem, this embodiment designs a novel speed detection device, such as... Figure 1 , Figure 2 and Figure 3 As shown, the speed detection device includes several speed detection components, each with the same structure. Each speed detection component includes a mounting bracket, a mileage wheel 8, a gear 10, and a gear encoder 11.

[0056] The mounting bracket is installed on the mounting base of the pipeline inspection device, specifically at the rear of the mounting base. The mounting bracket is a mechanical support arm used to install and support the odometer wheel 8, gear 10, and gear encoder 11.

[0057] The odometer wheel 8 is mounted on the mounting bracket and is in contact with the inner surface of the oil and gas pipeline. The odometer wheel 8 is used to rotate (or rotate) when the detection device moves inside the pipeline due to the friction of the inner surface of the oil and gas pipeline.

[0058] Gear 10 is fixedly connected to the odometer wheel 8 on the same axis and in the same phase. Gear 10 is used to rotate when the odometer wheel 8 rotates, and the rotation speed and direction of gear 10 are the same as those of the odometer wheel 8.

[0059] It should be noted that the coaxial and phase-coordinated fixed connection between the odometer wheel 8 and the gear 10 is a common mechanical connection method. This connection method ensures that the odometer wheel 8 and the gear 10 maintain the same rotational speed and phase relationship during rotation. Coaxial connection means that the central axes of the odometer wheel 8 and the gear 10 are completely coincident, specifically, the odometer wheel 8 and the gear 10 are mounted on the same shaft. Phase-coordinated connection means that the odometer wheel 8 and the gear 10 maintain the same phase relationship during rotation, which means that their rotation angle is always consistent. Specifically, the odometer wheel 8 and the gear 10 are fixedly connected by means of key connection, welding, riveting, or bolt connection. Therefore, in this embodiment, the fixed shaft is mounted on the mounting bracket, and both the odometer wheel 8 and the gear 10 are mounted on the fixed shaft, and the odometer wheel 8 and the gear 10 are fixedly connected. When the odometer wheel 8 rotates, it drives the gear 10 to rotate.

[0060] like Figure 2 and Figure 3As shown, the gear encoder 11 is mounted on the mounting bracket and is positioned opposite to the gear 10 (i.e., facing the gear 10). There is a gap d between the gear encoder 11 and the gear 10. At this time, the gear encoder 11 is fixed and encodes the rotating gear 10. The gear encoder 11 is used to output a pulse square wave voltage signal when the gear 10 rotates one tooth. The real-time moving speed of the detection device in the pipeline is determined based on the pulse square wave voltage signal.

[0061] The speed detection component in this embodiment includes a mileage wheel 8, a gear 10, and a gear encoder 11. When the detection device inside the pipeline moves (i.e. moves) along the axial direction of the oil and gas pipeline, the mileage wheel 8 rotates, driving the gear 10 to rotate. The gear encoder 11 records the rotation information of the gear 10. For each tooth of the gear 10 that rotates, the gear encoder 11 outputs a corresponding pulse square wave voltage signal. The real-time moving speed of the detection device inside the pipeline can be calculated by the tooth tip length of the gear 10 and the high-level duration of the pulse square wave voltage signal. The real-time moving speed refers to the real-time speed of the detection device inside the pipeline. The instantaneous moving speed can be obtained later.

[0062] like Figure 4 As shown, Figure 4 In t 1 and t 2 represents the duration of the high-level signal of the pulse square wave voltage signal corresponding to different instantaneous moving speeds. It can be seen that when the instantaneous moving speed of the detection device in the pipeline is different, the duration of the high-level signal of the pulse square wave voltage signal output by the speed detection device is different. Therefore, it can be proven that the instantaneous moving speed of the detection device in the pipeline can be calculated by the tooth tip length of gear 10 and the duration of the high-level signal of the pulse square wave voltage signal.

[0063] The gear encoder 11 in this embodiment can be any type of encoder with encoding function. As an example, the gear encoder 11 can be a TMR gear encoder. A TMR gear encoder is an incremental encoder based on tunnel magnetoresistive (TMR) sensor technology, used to measure the angle and speed of a rotating object and convert these motion parameters into digital signal outputs, such as... Figure 5 As shown, the TMR gear encoder belongs to the GE-T type encoder (i.e., square wave incremental encoder). It has six output terminals: A+, A-, B+, B-, Z+, and Z-. It can output A-phase TTL differential square wave signals (including A+ and A-), B-phase TTL differential square wave signals (including B+ and B-), and Z-phase origin signals (including Z+ and Z-). The phase difference between the A-phase and B-phase TTL differential square wave signals is 90°, and the pulse width of the Z-phase origin signal is half the pulse width of the A / B-phase TTL differential square wave signals. Figure 5The meanings of each parameter are shown in Table 1 below.

[0064] Table 1 Parameter Meaning

[0065] In Table 1, the subdivision factor refers to the ability to subdivide a pulse signal into multiple small step angles. It divides the entire operation into several small steps. Subdivision can improve positioning accuracy and operational stability. RPM is an abbreviation for Revolutions Per Minute, which refers to revolutions per minute.

[0066] like Figure 6 As shown, it illustrates the tooth tip length L of gear 10.

[0067] At this time, as Figure 7 As shown, in determining the real-time moving speed of the detection device inside the pipeline based on the pulse square wave voltage signal, the gear encoder 11 is used to determine the high-level duration based on the pulse square wave voltage signal and calculate the ratio of the tooth tip length of the gear 10 to the high-level duration to obtain the real-time moving speed of the detection device inside the pipeline.

[0068] When there is only one speed detection component, the real-time moving speed of the detection device inside the pipeline determined by the gear encoder 11 in the speed detection component is taken as the instantaneous moving speed. When there are multiple speed detection components, the average value of the real-time moving speed of the detection device inside the pipeline determined by the gear encoder 11 in all speed detection components is taken as the instantaneous moving speed. The moving speed of the detection device inside the pipeline is detected in real time to obtain the instantaneous moving speed.

[0069] It should be noted that since the speed detection device continuously detects the moving speed of the detection device inside the pipeline, multiple instantaneous moving speeds will be obtained.

[0070] (3) Defect quantification device.

[0071] like Figure 7 As shown, the defect quantification device is... Figure 1 The integrated electronic system 9 in this embodiment is connected to the pipeline detection device and the speed detection device in communication. It is used to extract features from the magnetic detection signal to obtain magnetic detection signal features, and to perform defect quantification based on the magnetic detection signal features and instantaneous moving speed to obtain the size information of the defects in the oil and gas pipeline.

[0072] When each detection probe 5 outputs a magnetic detection signal, the defect quantization device is used to extract features from each magnetic detection signal to obtain magnetic detection signal features, and to quantify the defects based on the magnetic detection signal features and instantaneous moving speed to obtain the size information of the defects in the oil and gas pipeline. The size information includes the length, width and depth of the defects.

[0073] Among them, the detection probe 5 is a triaxial magnetic sensor. The magnetic detection signal includes axial magnetic field signal, radial magnetic field signal and circumferential magnetic field signal. The characteristics of the magnetic detection signal include the peak-valley difference and peak-valley spacing of the axial magnetic field signal, the peak-valley difference and peak-valley spacing of the radial magnetic field signal and the peak-valley difference and peak-valley spacing of the circumferential magnetic field signal. The peak-valley difference is the difference between the peak value and the valley value, and the peak-valley spacing is the time interval between the peak value and the valley value.

[0074] In terms of feature extraction from magnetic detection signals to obtain magnetic detection signal features, and defect quantization based on magnetic detection signal features and instantaneous movement speed to obtain defect size information in oil and gas pipelines, the defect quantization device is used to determine the defect response signal corresponding to the defect based on the magnetic detection signal (the signal segment corresponding to the defect in the magnetic detection signal, which can be determined by the amplitude of the magnetic detection signal). Feature extraction is performed on the defect response signal to obtain magnetic detection signal features. The magnetic detection signal features and instantaneous movement speed (specifically, each instantaneous movement speed in the time period corresponding to the defect response signal) are used as inputs, and a trained defect quantization model is used to quantize the defect to obtain the size information of the defect in the oil and gas pipeline.

[0075] The trained defect quantification model adopts the SSA-BP neural network model. The SSA-BP neural network model is a BP neural network model obtained by initializing the network parameters of the BP neural network model using the SSA algorithm. The network parameters include weights and biases. Weights are parameters that connect adjacent neurons in the neural network, and biases are an additional parameter for each neuron. They act as offsets in the activation function of the neuron to optimize the initial network parameters of the BP neural network model and improve the training effect.

[0076] In the initialization of the network parameters of the BP neural network model using the SSA algorithm, the fitness function is the validation error of the validation set, which can be expressed as RMSE (Root Mean Square Error). The population size is set to 30, with 70% being explorers and the rest being followers. The maximum number of training iterations and the learning rate are set to 10000 and 0.01, respectively, when training with the training set. The termination criterion is that the current iteration count reaches the maximum number of iterations or the fitness function value of the current best individual is less than the target value. The maximum number of iterations is set to 50, and the target value is set to 1e-5.

[0077] like Figure 8 As shown, the specific process of initializing the network parameters of the BP neural network model using the SSA algorithm includes: reading sample data (including multiple samples and the label corresponding to each sample; the samples include historical magnetic detection signal features and historical instantaneous movement speed; the labels are historical defect size information); normalizing the sample data; and dividing the normalized sample data into training set and validation set. The initial population for the SSA algorithm is constructed, consisting of multiple individuals. Each individual represents a value of the network parameters (including weights and biases) of the BP neural network model. For each individual, the network structure of the BP neural network model is determined, and the weights and biases are initialized. The BP neural network model is trained using the training set to obtain the trained model. The trained model is then validated using the validation set to obtain the validation error. The fitness function value of each individual in the initial population is obtained. Based on the fitness function value of each individual, the optimal individual is updated (the individual with the smallest fitness function value is the optimal individual). The individual positions are updated through the foraging and feeding behaviors of the SSA algorithm to obtain the updated population. It is then determined whether the termination criterion is met. If so, the optimal individual is output, and the optimal network parameters (i.e., optimal weights and biases) of the BP neural network model are determined. After obtaining the optimal network parameters, the BP neural network model with the optimal network parameters is trained using normalized sample data to obtain a trained defect quantification model. The trained defect quantification model is used for prediction. If not, the updated population is used as the initial population for the next iteration.

[0078] like Figure 9 As shown, the BP neural network model consists of an input layer, a hidden layer, and an output layer connected in sequence.

[0079] This embodiment addresses the problems of magnetic detection signal distortion and low defect quantification accuracy in oil and gas pipelines by proposing a speed-compensated in-pipeline detection and defect quantification system. A speed detection device is installed, employing a fixed connection scheme where a mileage wheel 8 and a gear 10 are coaxial and in phase. The rotation of the mileage wheel 8 drives the rotation of the gear 10. A fixed TMR gear encoder collects the pulse square wave voltage signal generated by the rotation of the gear 10 in real time. The tooth tip length is determined based on the size of the gear 10. Based on the tooth tip length and the high-level duration of the pulse square wave voltage signal, the instantaneous moving speed of the in-pipeline detection device is calculated and transmitted to the data storage module of the defect quantification device. The in-pipeline detection device also uses a triaxial magnetic sensor to acquire magnetic detection signals in space and transmits them to the data storage module of the defect quantification device for offline acquisition and storage. Finally, the defect quantification device uses the instantaneous moving speed output by the TMR gear encoder and the magnetic detection signal characteristics output by the triaxial magnetic sensor as feature inputs. An SSA-BP neural network model is then used to quantify the size of defects in the oil and gas pipeline under speed compensation.

[0080] The operation process of the velocity-compensated oil and gas pipeline in-pipeline detection and defect quantification system in this embodiment includes the following steps.

[0081] (1) Connect the pipeline detection device and the speed detection device to the defect quantification device.

[0082] (2) The detection device and velocity detection device inside the pipeline move along the axial direction of the oil and gas pipeline under the driving pressure difference of the medium in the oil and gas pipeline.

[0083] (3) When the mileage wheel 8 in the speed detection device rotates, it drives the gear 10 to rotate. The fixed TMR gear encoder collects the pulse square wave voltage signal output by the gear 10 in real time. According to the size of the gear 10, the tooth tip length is determined. Based on the tooth tip length and the high level duration of the pulse square wave voltage signal, the instantaneous moving speed of the detection device in the pipeline is calculated and transmitted to the data storage module of the defect quantification device.

[0084] (4) The magnetic field information is obtained by the triaxial magnetic sensor of the pipeline detection device, the magnetic detection signal is obtained, and it is transmitted to the data storage module of the defect quantification device for offline acquisition and storage.

[0085] (5) Build an SSA-BP neural network model, using the instantaneous moving speed of the detection device in the pipeline and the multi-dimensional magnetic detection signal characteristics as feature parameters, input into the SSA-BP neural network model, and use the SSA-BP neural network model to quantify the defect size of the defects in the oil and gas pipeline.

[0086] When magnetized components operate at high speeds, they generate motion-induced eddy currents. The direction of the magnetic field of these eddy currents is opposite to the magnetization direction of the magnetized components, resulting in a decrease in magnetization intensity within the oil and gas pipeline. Consequently, when the detection device scans to the defect location, the response signal weakens, and the defect quantification accuracy decreases without considering speed. Using a magnetic rotary encoder sensor (i.e., a TMR gear encoder) can record the instantaneous rotational speed of the mileage wheel 8 (gear 10), determining the instantaneous moving speed of the detection device within the pipeline. Using this instantaneous moving speed as one of the input features can compensate for changes in the characteristics of the magnetic detection signal, improving the defect quantification accuracy of the magnetic detection signal.

[0087] Studies on the sensitivity and reliability of pipeline magnetic inspection technology to volumetric defects have shown that the magnetization intensity of the pipeline inspection device decreases significantly under high-speed operation, leading to different defect response signal characteristics at different speeds. Therefore, relying solely on magnetic sensors to acquire spatial magnetic detection signal characteristics results in a significant reduction in the quantification accuracy of pipeline defects under high-speed operation of the pipeline inspection device. This embodiment proposes a velocity-compensated pipeline inspection and defect quantification system. It calculates the instantaneous moving speed of the pipeline inspection device by recording the pulse square wave voltage signal of a magnetic rotary encoder sensor. This instantaneous moving speed is used as a feature parameter of the defect quantification model. Specifically, when the oil and gas pipeline contains defects, the magnetic sensor can extract multi-dimensional magnetic field information in space and further extract multi-dimensional magnetic detection signal features from the original magnetic detection signal. An optimized neural network model is then built, using the instantaneous moving speed of the pipeline inspection device and the multi-dimensional magnetic detection signal features as input parameters. This enables velocity-compensated pipeline defect quantification, improving the accuracy of pipeline defect identification.

[0088] When magnetic testing technology dynamically inspects a test piece, it generates a dynamic eddy current effect. The magnetic field produced by these eddy currents partially cancels out the excitation magnetic field. Furthermore, the faster the speed, the more pronounced this cancellation effect. For a test piece with a specific defect, varying speeds lead to different levels of magnetization within the piece, resulting in different waveform characteristics in the defect response signal. If speed is not incorporated as an input parameter for defect quantization, insufficient input information will be provided, significantly reducing the accuracy of defect quantization under dynamic conditions.

[0089] Example 2.

[0090] This embodiment provides a velocity-compensated method for in-pipeline inspection and defect quantification in oil and gas pipelines, applied to the velocity-compensated in-pipeline inspection and defect quantification system described in Embodiment 1, such as... Figure 10As shown, the method for detecting and quantifying defects in oil and gas pipelines based on velocity compensation includes the following steps.

[0091] S1: Obtain the magnetic detection signal detected by the pipeline detection device and the instantaneous moving speed detected by the speed detection device.

[0092] S2: Extract features from the magnetic detection signal to obtain magnetic detection signal features, and quantify the defects based on the magnetic detection signal features and the instantaneous moving speed to obtain the size information of the defects in the oil and gas pipeline.

[0093] Example 3.

[0094] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 11 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When executed by the processor, the computer program implements a speed-compensated method for detecting and quantifying defects in oil and gas pipelines.

[0095] Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0096] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the speed-compensated method for in-pipeline detection and defect quantification in embodiment 2.

[0097] Example 4.

[0098] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the speed-compensated method for in-pipeline detection and defect quantification in embodiment 2.

[0099] Example 5.

[0100] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the speed-compensated method for in-pipeline detection and defect quantification in embodiment 2.

[0101] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0102] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0103] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A velocity-compensated in-pipeline inspection and defect quantification system, characterized in that, The velocity-compensated in-pipeline inspection and defect quantification system includes: The pipeline detection device is located inside the oil and gas pipeline. It is used to move along the axial direction of the oil and gas pipeline under the drive of the medium in the oil and gas pipeline, and to detect the oil and gas pipeline during the movement to obtain magnetic detection signals. A speed detection device is located inside the oil and gas pipeline and is installed on the pipeline detection device to detect the moving speed of the pipeline detection device in real time and obtain the instantaneous moving speed. The defect quantification device is communicatively connected to the pipeline detection device and the speed detection device, respectively. It is used to extract features from the magnetic detection signal to obtain magnetic detection signal features, and to quantify defects based on the magnetic detection signal features and the instantaneous moving speed to obtain the size information of defects in the oil and gas pipeline.

2. The velocity-compensated in-pipeline detection and defect quantification system according to claim 1, characterized in that, The pipeline detection device includes a mounting base, a magnetizing component, and a detection component; The magnetizing component is arranged around the mounting base, and the outer surface of the magnetizing component is in contact with the inner surface of the oil and gas pipeline. The magnetizing component is used to apply a static magnetic field to the inner surface of the oil and gas pipeline, so that the oil and gas pipeline is magnetized. The detection component is mounted on the mounting base and is used to receive the induced magnetic field generated on the inner surface of the oil and gas pipeline in a magnetized state, and output the magnetic detection signal.

3. The velocity-compensated oil and gas pipeline internal detection and defect quantification system according to claim 2, characterized in that, The magnetizing component includes a first magnet, a first magnetic conductor, a second magnet, and a second magnetic conductor; The first magnet and the second magnet are both arranged around the mounting base, and there is a gap between the first magnet and the second magnet. The first magnet and the second magnet are used to generate the static magnetic field. The first magnetic conductor is arranged around the first magnet, and the outer surface of the first magnetic conductor is in contact with the inner surface of the oil and gas pipeline. The second magnetic conductor is arranged around the second magnet, and the outer surface of the second magnetic conductor is in contact with the inner surface of the oil and gas pipeline. The first magnetic conductor and the second magnetic conductor are used to apply the static magnetic field to the inner surface of the oil and gas pipeline, so that the oil and gas pipeline is magnetized. Both the first magnetic conductor and the second magnetic conductor are steel brushes.

4. The velocity-compensated oil and gas pipeline in-pipeline detection and defect quantification system according to claim 3, characterized in that, The detection component includes multiple probe brackets and multiple detection probes, with one probe bracket corresponding to one detection probe. Multiple probe supports are arranged in a circumferential array along the mounting base, the probe supports are located between the first magnet and the second magnet, and there are gaps between the probe supports and both the first magnet and the second magnet; The detection probe is mounted on the probe bracket and is used to receive the induced magnetic field generated on the inner surface of the oil and gas pipeline in a magnetized state, and output the magnetic detection signal.

5. The velocity-compensated oil and gas pipeline internal detection and defect quantification system according to claim 1, characterized in that, The speed detection device includes several speed detection components, each of which includes a mounting bracket, a mileage wheel, a gear, and a gear encoder. The mounting bracket is installed on the mounting base of the pipeline detection device; The odometer wheel is mounted on the mounting bracket and is in contact with the inner surface of the oil and gas pipeline. The odometer wheel is used to rotate when the detection device moves inside the pipeline. The gear is fixedly connected to the mileage wheel on the same axis and in the same phase. The gear is used to rotate when the mileage wheel rotates, and the rotation speed and direction of the gear are the same as those of the mileage wheel. The gear encoder is mounted on the mounting bracket and is arranged opposite to the gear. The gear encoder is used to output a pulse square wave voltage signal when the gear rotates one tooth, and to determine the real-time moving speed of the detection device in the pipeline based on the pulse square wave voltage signal. When there is one speed detection component, the real-time moving speed of the detection device inside the pipeline determined by the gear encoder in the speed detection component is taken as the instantaneous moving speed. When there are multiple speed detection components, the average value of the real-time moving speed of the detection device inside the pipeline determined by the gear encoders in all the speed detection components is taken as the instantaneous moving speed, so as to detect the moving speed of the detection device inside the pipeline in real time and obtain the instantaneous moving speed.

6. The velocity-compensated oil and gas pipeline in-pipeline detection and defect quantification system according to claim 5, characterized in that, In determining the real-time moving speed of the detection device inside the pipeline based on the pulse square wave voltage signal, the gear encoder is used to determine the high-level duration based on the pulse square wave voltage signal and calculate the ratio of the tooth tip length of the gear to the high-level duration to obtain the real-time moving speed of the detection device inside the pipeline.

7. The velocity-compensated in-pipeline inspection and defect quantification system according to claim 4, characterized in that, When each of the detection probes outputs a magnetic detection signal, the defect quantization device is used to extract features from each magnetic detection signal to obtain magnetic detection signal features, and to perform defect quantization based on the magnetic detection signal features and the instantaneous moving speed to obtain the size information of the defect in the oil and gas pipeline; the size information includes the length, width and depth of the defect; The detection probe is a triaxial magnetic sensor, and the magnetic detection signal includes an axial magnetic field signal, a radial magnetic field signal, and a circumferential magnetic field signal. The characteristics of the magnetic detection signal include the peak-to-valley difference and peak-to-valley spacing of the axial magnetic field signal, the peak-to-valley difference and peak-to-valley spacing of the radial magnetic field signal, and the peak-to-valley difference and peak-to-valley spacing of the circumferential magnetic field signal. The peak-to-valley difference is the difference between the peak value and the valley value, and the peak-to-valley spacing is the time interval between the peak value and the valley value.

8. The velocity-compensated oil and gas pipeline internal detection and defect quantification system according to claim 1, characterized in that, In terms of extracting features from the magnetic detection signal to obtain magnetic detection signal features, and performing defect quantization based on the magnetic detection signal features and the instantaneous moving speed to obtain the size information of the defects in the oil and gas pipeline, the defect quantization device is used to determine the defect response signal corresponding to the defect based on the magnetic detection signal, extract features from the defect response signal to obtain magnetic detection signal features, and use the magnetic detection signal features and the instantaneous moving speed as input to perform defect quantization using a trained defect quantization model to obtain the size information of the defects in the oil and gas pipeline. The trained defect quantification model adopts an SSA-BP neural network model, which is a BP neural network model obtained by initializing the network parameters of the BP neural network model using the SSA algorithm. The network parameters include weights and biases. When initializing the network parameters of the BP neural network model using the SSA algorithm, the fitness function is the validation error of the validation set.

9. The velocity-compensated oil and gas pipeline internal detection and defect quantification system according to claim 2, characterized in that, The pipeline detection device also includes an anti-collision head, which is mounted on the mounting base.

10. A velocity-compensated method for in-pipeline inspection and defect quantification, applied to the velocity-compensated in-pipeline inspection and defect quantification system according to any one of claims 1-9, characterized in that, The method for detecting and quantifying defects in oil and gas pipelines based on velocity compensation includes: The magnetic detection signal obtained by the pipeline detection device and the instantaneous moving speed obtained by the velocity detection device are acquired. Feature extraction is performed on the magnetic detection signal to obtain magnetic detection signal features. Based on the magnetic detection signal features and the instantaneous moving speed, defect quantification is performed to obtain the size information of the defect in the oil and gas pipeline.

Images