Method, processor, device and storage medium for correcting pipeline detection data

Abstract

The present application relates to the technical field of pipeline detection, and specifically to a correction method, processor, device and storage medium for pipeline detection data. The method includes: when the internal detection device moves in the pipeline, the travel speed and travel time of the internal detection device are determined by an encoder; when the position point passed by the internal detection device is determined to be a pipeline weld, the position point where the pipeline weld is located is marked; according to the first position point where the two adjacent pipeline welds are located, the travel speed and travel time of the internal detection device are determined; when the internal detection device moves in the pipeline, the travel mileage of the internal detection device and the weld length between any two pipelines are determined by a mileage wheel; according to the travel mileage and the weld length, the second pipeline length between any two adjacent pipeline welds is determined; and the first pipeline length is used to correct the second pipeline length to obtain the corrected pipeline length.

Description

Technical Field

[0001] The present application relates to the technical field of pipeline detection, and in particular, to a correction method, processor, device and storage medium for pipeline detection data. Background Art

[0002] Pipeline centerline in-line inspection is an effective method for pipeline centerline positioning, displacement and bending strain detection. The in-line inspection tool uses the medium in the pipeline as a driving force to push the in-line inspection tool to complete mapping in the pipeline and complete the detection of the geographical coordinates of the pipeline centerline. As a completely autonomous navigation method, inertial navigation technology does not need to receive external information and can independently complete pipeline inspection. After the inspection is completed, the inspection data stored in the in-line inspection tool will be further processed to obtain the centerline information and location information of the pipeline, as well as the displacement of the pipe body and the bending deformation of the pipeline caused by the additional external force caused by geological disasters.

[0003] The existing method uses IMU to complete the measurement of the entire pipeline. The whole process lasts more than ten hours. Since it cannot provide continuous satellite positioning information to ensure the absolute accuracy of mileage, there will be cumulative errors as the absolute mileage measured increases. In order to ensure the surveying and mapping accuracy of the pipeline centerline, it is necessary to check the position information of the internal detector at the GPS reference point. After the detection is completed, the system will download the GPS position data provided by the storage and ground reference points, complete data conversion and processing in the computer, and obtain the spatial position data and centerline trajectory of the entire pipeline. Affected by the accuracy of GPS itself, the accuracy is usually around 0.1 meters, which cannot meet the accuracy requirements of the pipeline centerline. It is necessary to correct the pipeline centerline detection data with more accurate mileage data. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method, processor, device and storage medium for correcting pipeline detection data, which can reduce noise interference and make the calculation of bending strain more accurate.

[0005] In order to achieve the above object, an embodiment of the present invention provides a correction method for pipeline detection data, wherein the internal detection device includes an encoder and an odometer, and the correction method includes:

[0006] When the internal detection device moves in the pipeline, the moving speed and moving time of the internal detection device are determined by the encoder;

[0007] When it is determined that the position point where the internal detection equipment passes is the pipeline weld, the position point where the pipeline weld is located is marked;

[0008] Determine the pipeline length between any two adjacent pipeline welds as the first pipeline length according to the first position points where the two adjacent pipeline welds are located, the travel speed and travel time of the internal detection device;

[0009] When the internal inspection equipment moves in the pipeline, the travel distance of the internal inspection equipment and the length of the weld between any two pipelines are determined by the mileage wheel;

[0010] Determine the pipeline length between any two adjacent pipeline welds as the second pipeline length according to the travel mileage and the weld length;

[0011] The second pipeline length is corrected by the first pipeline length to obtain a corrected pipeline length.

[0012] In one embodiment of the present application, the internal detection device further includes a magnetic sensitive element, and the correction method further includes: when the internal detection device moves in the pipeline, the magnetic sensitive element collects leakage magnetic field signals in the pipeline; generates a magnetic field distribution image of the pipeline according to the leakage magnetic field signal; converts the magnetic field distribution image into an RGB image; inputs the RGB image into a convolutional neural network model to obtain a prediction value output by the convolutional neural network model, the prediction value including a first prediction value indicating that the RGB image contains a girth weld segment and a second prediction value indicating that the RGB image does not contain a girth weld segment; when the prediction value of the magnetic field distribution image corresponding to the position point passed by the internal detection device is a first prediction value, it is determined that the position point passed by the internal detection device is a pipeline weld. When the prediction value of the magnetic field distribution image corresponding to the position point passed by the internal detection device is a second prediction value, it is determined that the position point passed by the internal detection device is not a pipeline weld.

[0013] In one embodiment of the present application, determining the travel speed and travel time of the internal detection device through an encoder includes: determining the angular velocity of the internal detection device through the encoder; determining the rotational speed of the encoder; and determining the travel speed of the internal detection device based on the rotational speed of the encoder and the angular velocity of the internal detection device.

[0014] In one embodiment of the present application, determining the pipeline length between any two adjacent pipeline welds as the first pipeline length according to the first position points where the two adjacent pipeline welds are located, the travel speed and the travel time of the internal detection equipment includes: determining the first weld length between the two adjacent pipelines according to the first position points where the two adjacent pipeline welds are located, and the travel speed and the travel time between the first position points where the internal detection equipment is located; determining the first total length of the two adjacent pipelines according to the travel speed and the travel time between the two adjacent pipelines; and determining the difference between the first total length and the first weld length as the first pipeline length.

[0015] In one embodiment of the present application, determining the mileage of the internal detection device and the weld length between any two pipes by using an odometer includes: acquiring posture data of the internal detection device; determining a second position point at which the pipe weld is located based on the posture data; and determining a second weld length between any two pipes based on the second position point.

[0016] In one embodiment of the present application, determining the pipeline length between any two adjacent pipeline welds as the second pipeline length based on the travel mileage and the weld length includes: determining the difference between the travel mileage and the total second weld length as the total pipeline length; determining the number of pipelines corresponding to the travel mileage; and determining the ratio of the total pipeline length to the number of pipelines as the second pipeline length between any two adjacent pipeline welds.

[0017] In one embodiment of the present application, the posture data includes posture data corresponding to each time point, and the second pipeline length is corrected by the first pipeline length to obtain the corrected pipeline length, which includes: determining the number of each pipeline weld; corresponding the travel time, the first pipeline length and the number, and generating a corresponding weld length comparison table; corresponding the posture data with the data in the weld length comparison table according to time, so as to correct the second pipeline length by the first pipeline length, so as to obtain the corrected pipeline length corresponding to each number.

[0018] A second aspect of the present application provides a processor configured to execute any one of the above methods for correcting pipeline detection data.

[0019] A third aspect of the present application provides a device for correcting pipeline detection data, comprising the above-mentioned processor.

[0020] A fourth aspect of the present application provides a machine-readable storage medium, on which instructions are stored. When the instructions are executed by a processor, the processor is configured to execute any one of the above-mentioned methods for correcting pipeline detection data.

[0021] Through the above technical solution, the first pipeline length is determined by determining the position of the pipeline weld, and then the second pipeline length is determined by the mileage moved by the mileage wheel of the internal detection equipment, and then the second pipeline length is corrected by the first pipeline length, so as to obtain more accurate pipeline data.

[0022] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0024] Figure 1 A schematic diagram of a process flow of a method for correcting pipeline detection data according to an embodiment of the present application is schematically shown;

[0025] Figure 2 A schematic diagram of the odometer wheel detecting tube length and calculating tube length according to an embodiment of the present application is schematically shown;

[0026] Figure 3 A flowchart of girth weld identification according to an embodiment of the present application is schematically shown;

[0027] Figure 4 A schematic diagram of an example of a traction test pipeline according to an embodiment of the present application is shown;

[0028] Figure 5 Schematically shows an example diagram of the initial pitch angle of the inner detector according to an embodiment of the present application;

[0029] Figure 6 An example diagram of pipe bending strain according to an embodiment of the present application is schematically shown;

[0030] Figure 7 An example diagram of a pitch angle after denoising of an inner detector according to an embodiment of the present application is schematically shown;

[0031] Figure 8 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0032] The specific implementation of the present application is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present application, and is not used to limit the present application.

[0033] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0034] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0035] like Figure 1 As shown, a schematic diagram of a flow chart of a method for correcting pipeline detection data according to an embodiment of the present application is shown. Figure 1 As shown, in one embodiment of the present application, a method for correcting pipeline detection data is provided, comprising the following steps:

[0036] Step 101, during the movement of the internal detection device in the pipeline, the travel speed and travel time of the internal detection device are determined by an encoder;

[0037] Step 102, when it is determined that the position point where the internal detection device passes is a pipeline weld, mark the position point where the pipeline weld is located;

[0038] Step 103, determining the pipeline length between any two adjacent pipeline welds as a first pipeline length according to the first position points where the two adjacent pipeline welds are located, the travel speed and travel time of the internal detection device;

[0039] Step 104, during the movement of the internal detection device in the pipeline, the travel distance of the internal detection device and the length of the weld between any two pipelines are determined by the mileage wheel;

[0040] Step 105, determining the pipeline length between any two adjacent pipeline welds as the second pipeline length according to the travel mileage and the weld length;

[0041] Step 106, correcting the second pipeline length by the first pipeline length to obtain a corrected pipeline length.

[0042] The long-distance pipeline is made up of pipelines connected in series one by one, and each pipeline is welded to obtain the long-distance pipeline. The internal detection device may include an encoder and an odometer, and the internal detection device may move in the pipeline to detect the required pipeline data. During the movement of the internal detection device in the pipeline, the internal detection device may determine the travel speed and travel time of the internal detection device through the encoder. When the processor determines that the internal detection device moves through the position point of the pipeline weld in the pipeline, the processor may mark the position point where the pipeline weld is located. The processor may determine the position point where two adjacent pipeline welds are located as the first position point, and the processor may determine the pipeline length between any two adjacent pipeline welds based on the first position point, the travel speed and travel time of the internal detection device moving in the pipeline, and determine the pipeline length between any two adjacent pipeline welds as the first pipeline length.

[0043] During the movement of the internal detection device in the pipeline, the mileage of the internal detection device and the length of the weld between any two pipelines can be determined by the mileage wheel of the internal detection device. The processor can determine the pipeline length between any two adjacent pipeline welds according to the received mileage of the internal detection device and the length of the weld between any two pipelines, and determine the pipeline length between any two adjacent pipeline welds as the second pipeline length. The processor can correct the second pipeline length according to the determined first pipeline length, thereby obtaining the corrected pipeline length.

[0044] In one embodiment, the internal detection device further includes a magnetic sensitive element, and the correction method further includes: when the internal detection device moves in the pipeline, the magnetic sensitive element collects leakage magnetic field signals in the pipeline; generates a magnetic field distribution image of the pipeline according to the leakage magnetic field signal; converts the magnetic field distribution image into an RGB image; inputs the RGB image into a convolutional neural network model to obtain a prediction value output by the convolutional neural network model, the prediction value including a first prediction value indicating that the RGB image contains a girth weld segment and a second prediction value indicating that the RGB image does not contain a girth weld segment; when the prediction value of the magnetic field distribution image corresponding to the position point passed by the internal detection device is a first prediction value, it is determined that the position point passed by the internal detection device is a pipeline weld. When the prediction value of the magnetic field distribution image corresponding to the position point passed by the internal detection device is a second prediction value, it is determined that the position point passed by the internal detection device is not a pipeline weld.

[0045] Based on the magnetic conductivity characteristics of ferromagnetic materials, there are different leakage magnetic fields for normal pipe walls, circumferential welds, and defect locations. The magnetic sensitive elements can be used to collect the leakage magnetic field signals being detected. After the detection is completed, the data signals in the storage unit of the internal detection equipment can be downloaded by a computer to obtain the magnetic field distribution image of the entire pipeline.

[0046] The internal detection device also includes a magnetically sensitive element. During the movement of the internal detection device in the pipeline, the magnetically sensitive element included can collect leakage magnetic field signals in the pipeline, and the processor can generate a magnetic field distribution image of the pipeline according to the leakage magnetic field signals collected by the internal detection device. The processor can convert the magnetic field distribution image into an RGB image, and input the converted RGB image into a convolutional neural network model, so as to obtain a prediction value output by the convolutional neural network model, and the prediction value includes a first prediction value indicating that the RGB image contains a girth weld segment and a second prediction value indicating that the RGB image does not contain a girth weld segment. When the processor converts the magnetic field distribution image corresponding to the position point passed by the internal detection device into an RGB image and inputs it into the convolutional neural network model, and the prediction value output by the convolutional neural network model is a first prediction value, the processor can determine that the position point passed by the internal detection device is a pipeline weld. When the processor converts the magnetic field distribution image corresponding to the position point passed by the internal detection device into an RGB image and inputs it into the convolutional neural network model, and the prediction value obtained is a second prediction value, the processor can determine that the position point passed by the internal detection device is not a pipeline weld.

[0047] In one embodiment, the processor may train the convolutional neural network model in advance so that the accuracy of the predicted value of the convolutional neural network model can reach the expected accuracy. The processor may divide the magnetic field distribution image generated by the existing magnetic flux leakage signal, i.e., the historical magnetic flux leakage signal, into a ring weld segment image and a non-ring weld segment image, and mark them with labels, the ring weld segment is marked as 1, and the non-ring weld segment is marked as 0. The magnetic field distribution image is a grayscale image. The processor may use a color conversion method to convert the magnetic field distribution image obtained by magnetic flux leakage detection into an RGB image. The method transmits the grayscale value of the black and white grayscale magnetic field distribution image to three converters with red (R), green (G), and blue (B) to generate three color components of the RGB space, and then linearly combines the three primary colors of red, green, and blue to obtain a continuous color map. The original grayscale image f(x, y) is converted according to the following formula (1).

[0048]

[0049] The specifications of the converted magnetic leakage image are [M, N, 3], where M represents the number of rows of the image, N represents the number of columns of the image, and 3 represents the number of channels of the RGB image. The processor can build the basic framework of the convolutional neural network model and use the converted RGB image to train the constructed convolutional neural network model, thereby realizing the binary classification of the magnetic leakage signal through the convolutional neural network model.

[0050] The convolutional neural network can be divided into five parts: input layer, convolution layer, pooling layer, fully connected layer, and output layer. The preset shape of the input layer must be consistent with the specifications of the magnetic field distribution image. Its function is to pass the magnetic field distribution image into the neural network according to the specified size.

[0051] The convolution layer is used to extract the data features of the magnetic field distribution image. The image data of the input layer is convolved with the convolution kernel to obtain new features. The definition of effective convolution is as follows: The pooling layer is used to reduce the dimensionality of the features obtained by convolution. Pooling is divided into average pooling and maximum pooling. The average pooling method reduces the feature map obtained by convolution to one-n of the original, where n represents the size of the convolution kernel of the pooling layer, and the maximum pooling method retains the maximum value of the input feature. The output feature matrix Z after pooling is as follows. After multiple convolution and pooling alternations, the final data feature matrix is ​​obtained, and then the matrix is ​​flattened and passed to the fully connected layer. The neurons of the two hidden layers before and after the fully connected layer are fully connected, which plays the role of screening and combining data features. Finally, the classification result is obtained at the output layer. The result is a girth weld segment or a non-girth weld segment, and the performance of the convolutional neural network model is verified in combination with some test set data. After determining that the convolutional neural network model training is completed, the processor can convert the magnetic field distribution image generated by the leakage magnetic field signal into an RGB image, and input the RGB image into the trained convolutional neural network model to determine whether the RGB image value contains a girth weld segment.

[0052] In one embodiment, determining the travel speed and travel time of the internal detection device through the encoder includes: determining the angular velocity of the internal detection device through the encoder; determining the rotation speed of the encoder; and determining the travel speed of the internal detection device based on the rotation speed of the encoder and the angular velocity of the internal detection device.

[0053] The internal detection device includes an encoder and an odometer. During the movement of the internal detection device in the pipeline, the processor can determine the travel speed and travel time of the internal detection device through the encoder. The processor can determine the angular velocity of the internal detection device through the encoder, and determine the rotation speed of the encoder. According to the rotation speed of the encoder and the angular velocity of the internal detection device, the processor can determine the travel speed of the internal detection device. Specifically, for example, the processor can use the encoder speed measurement method to measure the speed of the internal detection device, wherein the encoder speed measurement method may include a frequency measurement M method or a period measurement T method. This method simultaneously measures a certain number of pulses and the time taken to generate these pulses, which can effectively suppress the influence of the quantization error of the sampling time interval, and obtain a measurement result with higher accuracy in the entire speed range. The angular velocity w within the time interval is calculated as follows: Where N is the output resolution of the encoder. The speed measurement process can be compared to a discrete time random process, and the accuracy of the angular velocity obtained by the test can be verified by the system equation. Assume that the equation of the linear discrete system is: k =A k .X k-1 +B k .U k +W k , the observation equation is: k =H k .X k +V k , where W k is random noise, V k is the noise of the observation equation, X k is the estimated state variable at time k, Y k is the measured value at time k. The above system equation represents the optimal estimate of the encoder speed output in real time, X = [Ω]; Y k is the measured value at time k, that is, the angular velocity measurement value W obtained by the frequency measurement method M or the period measurement method T k , Y=[W]; where A k is the state transfer matrix at time k, H k is the measurement transfer matrix at time k, where A is taken k =H k =1; B k , U k is the state control parameter matrix at time k, B k =(W k -1-W k -2) / (t k-1 -t k-2 ), U k =t k -t k-1 In summary, the angular velocity measurement value w can be obtained by the encoder speed measurement method.

[0054] In one embodiment, determining the pipeline length between any two adjacent pipeline welds as the first pipeline length according to the first position points where the two adjacent pipeline welds are located, the travel speed and the travel time of the internal detection equipment includes: determining the first weld length between the two adjacent pipelines according to the first position points where the two adjacent pipeline welds are located, and the travel speed and the travel time between the first position points where the internal detection equipment is located; determining the first total length of the two adjacent pipelines according to the travel speed and the travel time between the two adjacent pipelines; and determining the difference between the first total length and the first weld length as the first pipeline length.

[0055] When welding a pipeline, a weld is generated, and the processor can mark the location of the pipeline weld and determine it as a first location point. The processor can determine the pipeline length between any two adjacent pipeline welds based on the first location points of the two adjacent pipeline welds, the travel speed and travel time of the internal detection device, and determine the pipeline length between any two adjacent pipeline welds as the first pipeline length.

[0056] The processor can determine the length of the first weld between two adjacent pipes based on the first position points where the welds of the two adjacent pipes are located, and the travel speed and travel time of the internal detection device between the first position points where the welds of the two adjacent pipes are located. The processor can determine the length of the two adjacent pipes based on the travel speed and travel time of the internal detection device between the two adjacent pipes. The processor can determine the length of the two adjacent pipes as the first total length. Since connecting two pipes in series requires welding the two pipes together, and welds are generated during the welding process, and distances are generated between the welds, the first total length obtained includes the length of the pipe and the length of the weld. Therefore, the processor can determine the difference between the first total length and the first weld length as the first pipe length.

[0057] In one embodiment, determining the mileage of the internal detection device and the length of the weld between any two pipes by using an odometer includes: acquiring posture data of the internal detection device; determining a second position point of the pipe weld according to the posture data; and determining a second weld length between any two pipes according to the second position point.

[0058] The internal detection device includes an encoder and an odometer wheel, and the processor can determine the mileage of the internal detection device and the length of the weld between any two pipes through the odometer wheel. The processor can obtain the posture data of the internal detection device, and the processor can determine the second position point where the pipe weld is located according to the posture data of the internal detection device, and can determine the second weld length between any two pipes according to the determined second position.

[0059] In one embodiment, determining the pipeline length between any two adjacent pipeline welds as the second pipeline length based on the travel mileage and the weld length includes: determining the difference between the travel mileage and the total second weld length as the total pipeline length; determining the number of pipelines corresponding to the travel mileage; and determining the ratio of the total pipeline length to the number of pipelines as the second pipeline length between any two adjacent pipeline welds.

[0060] Since the length obtained after the pipeline welding is completed includes the pipeline length and the weld length. The processor determines the second weld length between any two pipelines through the mileage wheel of the internal detection device. The mileage of the internal detection device includes the length of the pipeline passed and the length of the second weld between the pipelines passed. When multiple pipelines are welded together, multiple second weld lengths can be obtained. The difference between the mileage of the internal detection device and the total second weld length is the total length of the pipeline. The processor can determine the number of pipelines corresponding to the mileage, determine the ratio of the total length of the pipeline to the number of pipelines as the pipeline length between any two adjacent pipeline welds, and determine the determined pipeline length between any two adjacent pipeline welds as the second pipeline length.

[0061] In one embodiment, the posture data includes posture data corresponding to each time point, and the second pipeline length is corrected by the first pipeline length to obtain the corrected pipeline length, which includes: determining the number of each pipeline weld; making the travel time, the first pipeline length and the number correspond, and generating a corresponding weld length comparison table; making the posture data correspond to the data in the weld length comparison table according to time, so as to correct the second pipeline length by the first pipeline length, so as to obtain the corrected pipeline length corresponding to each number.

[0062] The posture data of the internal detection device may include posture data corresponding to each time point. After determining the first pipeline length and the second pipeline length, the processor may correct the second pipeline length by the first pipeline length. The processor may determine the number of each pipeline weld, correspond the travel time of the internal detection device, the first pipeline length and the number, and generate a corresponding weld length comparison table. The posture data is matched with the data in the weld length comparison table according to time, so as to correct the second pipeline length by the first pipeline length, so as to obtain the corrected pipeline length corresponding to each number.

[0063] Through the above technical solution, the first pipeline length is determined by determining the position of the pipeline weld, and then the second pipeline length is determined by the mileage moved by the mileage wheel of the internal detection device, and then the second pipeline length is corrected by the first pipeline length, so as to obtain more accurate pipeline data. In one embodiment, a processor is provided, which is configured to execute the above correction method for pipeline detection data.

[0064] Long-distance pipelines are made up of pipes connected in series one by one. Each pipe is welded together to form a long-distance pipeline. The internal detection equipment may include an encoder, a mileage wheel, and a magnetically sensitive element. The internal detection equipment can move inside the pipeline to detect the required pipeline data. Based on the magnetic conductivity characteristics of ferromagnetic materials, there are different leakage magnetic fields for normal pipe walls, circumferential welds, and defect locations. The internal detection equipment can use magnetically sensitive elements to collect the leakage magnetic field signals being detected. After the detection is completed, the data signal in the storage unit of the internal detection equipment can be downloaded through the processor to obtain a magnetic field distribution image of the entire pipeline.

[0065] The processor can convert the magnetic field distribution image into an RGB image, and input the converted RGB image into the convolutional neural network model, so as to obtain the predicted value output by the convolutional neural network model, and the predicted value includes a first predicted value indicating that the RGB image contains a girth weld segment and a second predicted value indicating that the RGB image does not contain a girth weld segment. In order to correct the absolute mileage and speed cumulative errors of the long-distance pipeline, the relevant staff can place marking points on the ground every one to two kilometers to obtain the position points, and the marked position points can provide accurate three-dimensional position information. When the processor converts the magnetic field distribution image corresponding to the position point passed by the internal detection device into an RGB image and inputs it into the convolutional neural network model, and the predicted value output by the convolutional neural network model is the first predicted value, the processor can determine that the position point passed by the internal detection device is a pipeline weld. When the processor converts the magnetic field distribution image corresponding to the position point passed by the internal detection device into an RGB image and inputs it into the convolutional neural network model, and the predicted value obtained is the second predicted value, the processor can determine that the position point passed by the internal detection device is not a pipeline weld.

[0066] During the movement of the internal detection device in the pipeline, the processor can determine the travel speed and travel time of the internal detection device through the encoder. The processor can determine the angular velocity of the internal detection device through the encoder and determine the rotation speed of the encoder. The processor can determine the travel speed of the internal detection device based on the rotation speed of the encoder and the angular velocity of the internal detection device.

[0067] When the convolutional neural network model determines that the internal detection device moves in the pipeline and passes through the position point of the pipeline weld, the processor can mark the position point where the pipeline weld is located. When welding the pipeline, a weld is generated, and the processor can mark the position point where the pipeline weld is located and determine it as the first position point. The processor can determine the pipeline length between any two adjacent pipeline welds according to the first position point where the two adjacent pipeline welds are located, the travel speed and travel time of the internal detection device, and determine the pipeline length between any two adjacent pipeline welds as the first pipeline length. The processor can determine the first weld length between the two adjacent pipelines according to the first position point where the two adjacent pipeline welds are located, and the travel speed and travel time of the internal detection device between the first position points where the two adjacent pipeline welds are located. The processor can determine the length of the two adjacent pipelines according to the travel speed and travel time of the internal detection device between the two adjacent pipelines. The processor can determine the length of the two adjacent pipelines as the first total length. Since the two pipelines need to be welded together when the two pipelines are connected in series, and a weld is generated during the welding process, and a distance is generated between the welds, the first total length obtained includes the length of the pipeline and the length of the weld. The processor may therefore determine the first pipe length as a difference between the first total length and the first weld length.

[0068] The internal detection device includes an encoder and an odometer wheel, and the processor can determine the mileage of the internal detection device and the length of the weld between any two pipes through the odometer wheel. The processor can obtain the posture data of the internal detection device, and the processor can determine the second position point where the pipe weld is located according to the posture data of the internal detection device, and can determine the length of the second weld between any two pipes according to the determined second position. Since the length obtained after the pipe welding is completed includes the pipe length and the weld length. The processor determines the length of the second weld between any two pipes through the odometer wheel of the internal detection device. The mileage of the internal detection device includes the length of the pipe passed and the length of the second weld between the pipes passed. When multiple pipes are welded together, multiple second weld lengths can be obtained. The difference between the mileage of the internal detection device and the total length of the second weld is the total length of the pipe. The processor can determine the number of pipes corresponding to the mileage, determine the ratio of the total length of the pipe to the number of pipes as the pipe length between any two adjacent pipe welds, and determine the determined pipe length between any two adjacent pipe welds as the second pipe length.

[0069] The posture data of the internal detection device may include posture data corresponding to each time point. After determining the first pipeline length and the second pipeline length, the processor may modify the second pipeline length by the first pipeline length. Specifically, for example Figure 2The schematic diagram of the odometer wheel detecting pipe length and calculating pipe length shown in the figure shows that the pipe length between welds can be determined by marking the weld position points, that is, by calculating the length between pipes. After the pipe length is determined by calculation, the pipe length can be measured by the odometer wheel of the internal detection equipment. Since the odometer wheel measurement accuracy is not high, there will be cumulative errors, so if Figure 2 As shown, the pipe length measured by the odometer wheel must be corrected by calculating the pipe length.

[0070] The processor can determine the number of each pipeline weld, match the travel time of the internal detection device, the first pipeline length and the number, and generate a corresponding weld length comparison table. According to the time, the posture data is matched with the data in the weld length comparison table to correct the second pipeline length by the first pipeline length to obtain the corrected pipeline length corresponding to each number. Specifically, as shown in Table 1:

[0071]

[0072] Table 1 Girth weld comparison table

[0073] Through the above technical solution, the first pipeline length is determined by determining the position of the pipeline weld, and then the second pipeline length is determined by the mileage moved by the mileage wheel of the internal detection equipment, and then the second pipeline length is corrected by the first pipeline length, so as to obtain more accurate pipeline data.

[0074] In one embodiment, Figure 3 As shown in FIG. , a flowchart of girth weld identification is schematically shown. Figure 3 As shown, firstly, the magnetic flux leakage is internally detected. After the magnetic flux leakage detection data is obtained through the magnetic flux leakage internal detection, the magnetic flux leakage detection data can be classified to obtain two categories of girth welds and non-girth welds, and the labels are marked respectively. At the same time, the magnetic flux leakage detection data can be determined as auxiliary positioning data. The magnetic flux leakage detection data is converted into RGB images, and a convolutional neural network model is constructed. The model is trained by the magnetic flux leakage detection data with the girth weld and non-girth weld labels marked, so that the girth weld can be identified through the convolutional neural network, and the position of the girth weld can be determined through the auxiliary positioning data. The pipe length is calculated by the encoder, so that the absolute mileage of the pipeline obtained by the mileage wheel of the internal detection equipment is corrected by the calculated pipe length and the pipeline centerline data.

[0075] In one embodiment, the accuracy can be verified by using a traction test, specifically, for example, during the experiment, such as Figure 4The traction test pipeline shown in the figure has a 90-meter straight pipeline installed. The bottom of the pipeline is supported by 5 piers to keep it as straight as possible in the initial stage. The support in the middle is adjusted to make the pipeline sink or move upward. At the same time, the pipeline is equipped with a strain gauge to compare the measured value with the bending strain calculation result of the internal detector. The pipeline bending strain data analysis and calculation are performed on the straight pipe and the immersed pipe respectively. Figure 5 and Figure 6 Example graphs showing the initial pitch angle of the inner detector and the calculated values ​​of the pipe bending strain, respectively. Figure 5 It can be seen that IIT is affected by vibration, girth weld and other factors, which affect the calculation of bending strain.

[0076] According to the proposed method, the attitude information (pitch angle, heading angle, etc.) is first processed. The attitude information is analyzed and denoised by decomposing it into 8 levels of Sym8 wavelet. The denoised pitch angle of the inner detector is as follows Figure 7 As shown. From the results, it can be seen that first, the fixed-frequency noise interference caused by the vibration of the inner detector during operation is eliminated. Secondly, due to the presence of girth welds and spiral welds in the pipeline, the inner detector will generate vibrations and shocks when passing through these features. IMU can sensitively collect these vibrations and shocks, so the attitude data will be disturbed by these noises. These noise interferences will further affect the calculation of bending strain. After processing the attitude data by the proposed method, the noise interference caused by these vibrations and shocks can be effectively reduced, and the calculation of bending strain is more accurate. The attitude changes caused by the beating when the inner detector passes through the girth weld are reduced. In further calculations, the pipeline bending strain is closer to the unstrained state of the straight pipeline. According to the field conditions, the calculated bending strain of each girth weld is about ±0.05%, which provides an effective reference for the location of abnormal bending strain.

[0077] In order to verify the accuracy of the bending strain change of the proposed method, a strain gauge is installed at the location where the pipeline strain changes the most when the pipeline sinks. The strain gauge is used to measure the strain change caused by pipeline deviation, and then the internal detection calculation results are compared with the strain gauge measurement value.

[0078] When the load is the largest, the pipeline sinks 25.5 cm, and the maximum change in pipeline strain is in the middle of the pipeline. The strain gauge is installed at 47m to measure the change in the maximum position of the pipeline strain. When conducting experiments, these strain gauges should be avoided from being installed at the annular seam. Table 2 shows the comparison of bending strain before and after optimization when the pipeline settles. The strain change measurement value of the strain gauge is 0.04926%. The calculated value of the bending strain measured by the unoptimized internal detection is 0.062%, and its absolute deviation and relative deviation from the strain gauge are 0.013% and 25.8%, respectively. The optimized bending strain is calculated to be 0.046%, and its absolute deviation and relative deviation relative to the strain gauge are 0.003% and 6.7%, respectively. At present, some papers show that the absolute deviation of bending strain is 0.005% to 0.01% based on the moving average or low-pass filtering method. Some specifications or standards stipulate an absolute deviation of 0.02%. It can be seen from the results that the optimized calculation of pipeline bending strain is more accurate and can effectively measure and evaluate the bending strain of the deformed pipeline. This method provides an effective method for online detection of bending strain in long-distance and small-size pipelines.

[0079]

[0080] Table 2 Comparison of bending strain before and after pipeline settlement

[0081] In one embodiment, a device for correcting pipeline detection data is provided, comprising the above-mentioned processor.

[0082] In one embodiment, a machine-readable storage medium is provided. The machine-readable storage medium stores instructions. When the instructions are executed by a processor, the processor is configured to execute any one of the above methods for correcting pipeline detection data.

[0083] In one embodiment, a computer program product is provided, comprising a computer program, wherein the computer program implements any one of the above methods for correcting pipeline detection data when executed by a processor.

[0084] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0085] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store relevant data of the internal detection device. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a correction method for pipeline detection data is implemented.

[0086] Figure 1 FIG. 1 is a flow chart of a method for correcting pipeline detection data in one embodiment. It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0087] An embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: when an internal detection device moves in a pipeline, the travel speed and travel time of the internal detection device are determined by an encoder; when it is determined that a position point passed by the internal detection device is a pipeline weld, the position point where the pipeline weld is located is marked; according to the first position point where two adjacent pipeline welds are located, the travel speed and travel time of the internal detection device, the pipeline length between any two adjacent pipeline welds is determined as a first pipeline length; when the internal detection device moves in the pipeline, the travel mileage of the internal detection device and the weld length between any two pipelines are determined by an mileage wheel; according to the travel mileage and the weld length, the pipeline length between any two adjacent pipeline welds is determined as a second pipeline length; and the second pipeline length is corrected by the first pipeline length to obtain a corrected pipeline length.

[0088] In one embodiment, when the internal detection device moves in the pipeline, the leakage magnetic field signal in the pipeline is collected through the magnetic sensitive element; the magnetic field distribution image of the pipeline is generated according to the leakage magnetic field signal; the magnetic field distribution image is converted into an RGB image; the RGB image is input into the convolutional neural network model to obtain the predicted value output by the convolutional neural network model, and the predicted value includes a first predicted value indicating that the RGB image contains a girth weld segment and a second predicted value indicating that the RGB image does not contain a girth weld segment; when the predicted value of the magnetic field distribution image corresponding to the position point passed by the internal detection device is the first predicted value, it is determined that the position point passed by the internal detection device is a pipeline weld. When the predicted value of the magnetic field distribution image corresponding to the position point passed by the internal detection device is the second predicted value, it is determined that the position point passed by the internal detection device is not a pipeline weld.

[0089] In one embodiment, determining the travel speed and travel time of the internal detection device through the encoder includes: determining the angular velocity of the internal detection device through the encoder; determining the rotation speed of the encoder; and determining the travel speed of the internal detection device based on the rotation speed of the encoder and the angular velocity of the internal detection device.

[0090] In one embodiment, determining the pipeline length between any two adjacent pipeline welds as the first pipeline length according to the first position points where the two adjacent pipeline welds are located, the travel speed and the travel time of the internal detection equipment includes: determining the first weld length between the two adjacent pipelines according to the first position points where the two adjacent pipeline welds are located, and the travel speed and the travel time between the first position points where the internal detection equipment is located; determining the first total length of the two adjacent pipelines according to the travel speed and the travel time between the two adjacent pipelines; and determining the difference between the first total length and the first weld length as the first pipeline length.

[0091] In one embodiment, determining the mileage of the internal detection device and the length of the weld between any two pipes by using an odometer includes: acquiring posture data of the internal detection device; determining a second position point of the pipe weld according to the posture data; and determining a second weld length between any two pipes according to the second position point.

[0092] In one embodiment, determining the pipeline length between any two adjacent pipeline welds as the second pipeline length based on the travel mileage and the weld length includes: determining the difference between the travel mileage and the total second weld length as the total pipeline length; determining the number of pipelines corresponding to the travel mileage; and determining the ratio of the total pipeline length to the number of pipelines as the second pipeline length between any two adjacent pipeline welds.

[0093] In one embodiment, the posture data includes posture data corresponding to each time point, and the second pipeline length is corrected by the first pipeline length to obtain the corrected pipeline length, which includes: determining the number of each pipeline weld; making the travel time, the first pipeline length and the number correspond, and generating a corresponding weld length comparison table; making the posture data correspond to the data in the weld length comparison table according to time, so as to correct the second pipeline length by the first pipeline length, so as to obtain the corrected pipeline length corresponding to each number.

[0094] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0095] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0096] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0098] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0099] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0100] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0101] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0102] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for correcting pipeline detection data, characterized in that: The internal detection device includes an encoder and a mileage wheel, and the correction method includes: During the movement of the internal detection device in the pipeline, the travel speed and travel time of the internal detection device are determined by the encoder; When it is determined that the position point where the internal detection device passes is a pipeline weld, marking the position point where the pipeline weld is located; Determine the pipeline length between any two adjacent pipeline welds as the first pipeline length according to the first position points where the two adjacent pipeline welds are located, the travel speed and the travel time of the internal detection device; During the movement of the internal detection device in the pipeline, the travel mileage of the internal detection device and the length of the weld between any two pipelines are determined by the mileage wheel; Determine the pipeline length between any two adjacent pipeline welds as a second pipeline length according to the travel mileage and the weld length; Correcting the second pipeline length by the first pipeline length to obtain a corrected pipeline length; Wherein, determining the travel mileage of the internal detection device and the length of the weld between any two pipes by the mileage wheel includes: Acquiring posture data of the internal detection device; Determine a second position point where the pipeline weld is located according to the posture data; Determine a second weld length between any two pipes according to the second position point; The posture data includes posture data corresponding to each time point, and the second pipeline length is corrected by the first pipeline length to obtain the corrected pipeline length, which includes: Determine the number of each pipe weld; Matching the travel time, the first pipeline length and the number, and generating a corresponding weld length comparison table; The posture data is matched with the data in the weld length comparison table according to time, so as to correct the second pipeline length by the first pipeline length, so as to obtain the corrected pipeline length corresponding to each number.

2. The method for correcting pipeline detection data according to claim 1, characterized in that: The internal detection device also includes a magnetic sensitive element, and the correction method also includes: When the internal detection device moves in the pipeline, the magnetic field leakage signal in the pipeline is collected by the magnetic sensitive element; generating a magnetic field distribution image of the pipeline according to the leakage magnetic field signal; Converting the magnetic field distribution image into an RGB image; Inputting the RGB image into a convolutional neural network model to obtain a prediction value output by the convolutional neural network model, the prediction value comprising a first prediction value indicating that the RGB image contains a girth weld segment and a second prediction value indicating that the RGB image does not contain a girth weld segment; When the predicted value of the magnetic field distribution image corresponding to the position point passed by the internal detection device is the first predicted value, determining that the position point passed by the internal detection device is a pipeline weld; When the predicted value of the magnetic field distribution image corresponding to the position point passed by the internal detection device is the second predicted value, it is determined that the position point passed by the internal detection device is not a pipeline weld.

3. The method for correcting pipeline detection data according to claim 1, characterized in that: Determining the travel speed and travel time of the internal detection device by the encoder comprises: determining the angular velocity of the inner detection device by means of the encoder; determining a rotational speed of the encoder; The travel speed of the inner detection device is determined according to the rotation speed of the encoder and the angular velocity of the inner detection device.

4. The method for correcting pipeline detection data according to claim 1, characterized in that: The step of determining the pipeline length between any two adjacent pipeline welds as the first pipeline length according to the first position points where the two adjacent pipeline welds are located, the travel speed and the travel time of the internal detection device comprises: Determine the length of the first weld between the two adjacent pipelines according to the first position points where the two adjacent pipeline welds are located, and the travel speed and travel time of the internal detection device between the first position points where the two adjacent pipeline welds are located; Determine a first total length of the two adjacent pipelines according to a travel speed and a travel time of the internal detection device between the two adjacent pipelines; The difference between the first total length and the first weld length is determined as the first pipeline length.

5. The method for correcting pipeline detection data according to claim 1, characterized in that: Determining the pipeline length between any two adjacent pipeline welds as the second pipeline length according to the travel mileage and the weld length includes: The difference between the travel distance and the total length of the second weld is determined as the total length of the pipeline; Determine the number of pipelines corresponding to the travel mileage; The ratio of the total length of the pipeline to the number of pipelines is determined as the second pipeline length between any two adjacent pipeline welds.

6. A processor, characterized in that: The method is configured to execute the pipeline detection data correction method according to any one of claims 1 to 5.

7. A correction device for pipeline detection data, characterized in that: Comprising a processor according to claim 6.

8. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the method for correcting pipeline detection data according to any one of claims 1 to 5.

Images