Drilling tool damage detection method and device

Abstract

The invention discloses a drilling tool damage detection method and device. The method comprises the following steps: determining a target three-way magnetic flux leakage signal of a target drilling tool, wherein the three-way magnetic flux leakage signal comprises an axial magnetic flux leakage signal, a radial magnetic flux leakage signal and a circumferential magnetic flux leakage signal; magnetic flux leakage signal characteristic analysis is conducted on the target three-way magnetic flux leakage signal, and a target damage type corresponding to the target drilling tool is determined; for different target damage types, converting the target three-way magnetic flux leakage signal to generate a target three-way two-dimensional damage image, and performing image feature fusion on the target two-dimensional damage image to generate a target three-dimensional damage model; the three-way two-dimensional damage image comprises an axial two-dimensional damage image, a radial two-dimensional damage image and a circumferential two-dimensional damage image. According to the technical scheme, when drilling is conducted through the drilling tool, the problems that damage of the drilling tool is difficult to detect, and the service life cannot be estimated can be solved.

Description

Technical Field

[0001] This invention relates to the field of equipment risk management technology, and in particular to a method and apparatus for detecting drill bit damage. Background Technology

[0002] Oil extraction is an important way to obtain energy, and drilling is an important means of extracting oil.

[0003] With the development of deep horizontal wells with complex well trajectories and large drilling parameters (high drilling pressure, high rotation speed and large displacement, etc.), the methods of single pipe station inspection and evaluation and high steel grade drilling tools have the disadvantage of inaccurate inspection results and lack of prediction of the service life of drilling tools, which makes it difficult to meet the needs of avoiding drilling tool damage. Summary of the Invention

[0004] This invention provides a method and apparatus for detecting drill bit damage, in order to solve the problems of difficult detection of drill bit damage and inability to estimate its lifespan.

[0005] According to one aspect of the present invention, a method for detecting drill bit damage is provided, the method comprising:

[0006] Determine the target three-dimensional magnetic flux leakage signal of the target drilling tool. The three-dimensional magnetic flux leakage signal includes the axial magnetic flux leakage signal, the radial magnetic flux leakage signal, and the circumferential magnetic flux leakage signal.

[0007] Magnetic flux leakage signal characteristic analysis is performed on the target triaxial magnetic flux leakage signal to determine the target damage type corresponding to the target drill bit.

[0008] For different target damage types, the target triaxial leakage magnetic signal is converted to generate a target triaxial two-dimensional damage image, and the target two-dimensional damage image is fused with image features to generate a target three-dimensional damage model; the triaxial two-dimensional damage image includes axial two-dimensional damage image, radial two-dimensional damage image and circumferential two-dimensional damage image.

[0009] According to another aspect of the present invention, a drill bit damage detection device is provided, the device comprising:

[0010] The magnetic flux leakage signal determination module is used to determine the target three-dimensional magnetic flux leakage signal of the target drilling tool. The three-dimensional magnetic flux leakage signal includes axial magnetic flux leakage signal, radial magnetic flux leakage signal and circumferential magnetic flux leakage signal.

[0011] The damage type determination module is used to perform leakage magnetic signal feature analysis on the target triaxial leakage magnetic signal to determine the target damage type corresponding to the target drill bit.

[0012] The damage 3D determination module is used to convert the target triaxial leakage magnetic field signal for different target damage types, generate the target triaxial 2D damage image, and perform image feature fusion on the target 2D damage image to generate the target 3D damage model; the triaxial 2D damage image includes axial 2D damage image, radial 2D damage image and circumferential 2D damage image.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory that is communicatively connected to at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the drill bit damage detection method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the drill bit damage detection method of any embodiment of the present invention.

[0018] The technical solution of this invention utilizes a real-time non-destructive testing device at the wellhead to determine the target triaxial magnetic flux leakage signal of the target drilling tool. This allows for a comprehensive and rapid magnetic flux leakage detection of the target drilling tool without moving it. By analyzing the characteristics of the target triaxial magnetic flux leakage signal, the corresponding damage type of the target drilling tool is determined, enabling rapid identification based on the target triaxial magnetic flux leakage signal, thereby improving the system's processing efficiency. Furthermore, the target triaxial magnetic flux leakage signal is converted for different damage types to generate a target triaxial two-dimensional damage image. Image feature fusion of this two-dimensional image generates a target three-dimensional damage model, thus determining the damage to the target drilling tool. The combined use of these steps improves both the detection efficiency and accuracy of target drilling tool damage. This allows for rapid detection of damage to the target drilling tool, preventing excessive damage that could negatively impact oil and gas extraction efficiency.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a drill bit damage detection method provided in Embodiment 1 of the present invention;

[0022] Figure 2 This is a schematic diagram of a real-time non-destructive testing device for wellheads provided according to Embodiment 1 of the present invention;

[0023] Figure 3 This is a flowchart of another drill bit damage detection method provided according to Embodiment 2 of the present invention;

[0024] Figure 4 This is a schematic diagram of the structure of a drill bit damage detection device according to Embodiment 3 of the present invention;

[0025] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the drill bit damage detection method of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Example 1

[0029] Figure 1 This is a flowchart of a drill string damage detection method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of damage detection of drilling tools. The method can be executed by a drill string damage detection device, which can be implemented in hardware and / or software. The drill string damage detection device can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0030] S110, Determine the target triaxial magnetic flux leakage signal of the target drill bit.

[0031] The three-dimensional magnetic flux leakage signal includes axial magnetic flux leakage signal, radial magnetic flux leakage signal, and circumferential magnetic flux leakage signal.

[0032] Magnetic flux leakage signal can be the change in magnetic field signal generated during the magnetic flux leakage detection of the target drilling tool due to magnetic flux leakage caused by damage.

[0033] To determine the target three-dimensional magnetic flux leakage signal of the target drilling tool, a wellhead non-destructive testing device can be installed on the rotary table to perform magnetic flux leakage testing on the target drilling tool.

[0034] See Figure 2 The real-time non-destructive testing (NDT) device at the wellhead features a ring-shaped permanent magnet axial magnetization design. An excitation device magnetizes the target drill string to saturation. When damage exists on the surface or inside the target drill string, a leakage magnetic field is generated at the damage site, leaking beyond the surface of the drill string. This leakage magnetic field reflects the type and extent of damage to the target drill string. The device employs a Hall sensor array, concentrating multiple leakage and residual magnetic field sensors on a single unit. Eight leakage magnetic field probes and sixteen residual magnetic field probes are arranged in parallel along an arc on the drill string to detect defects and fatigue stress.

[0035] By using a real-time non-destructive testing device at the wellhead, the target three-dimensional magnetic flux leakage signal of the target drill string is determined, enabling a more comprehensive and rapid magnetic flux leakage detection of the target drill string without moving it during the determination process.

[0036] S120. Perform magnetic flux leakage signal characteristic analysis on the target's three-dimensional magnetic flux leakage signal to determine the target damage type corresponding to the target drill bit.

[0037] Damage types include, but are not limited to, hole-shaped defects, groove-shaped defects, and crack defects.

[0038] Since the leakage magnetic flux signals corresponding to different damage types have certain differences in characteristics, feature analysis can be performed on different damage types in advance to determine the candidate leakage magnetic flux signal characteristics corresponding to each damage type. After obtaining the target three-phase leakage magnetic flux signal, leakage magnetic flux signal feature analysis is performed on the target three-dimensional leakage magnetic flux signal to determine the candidate leakage magnetic flux signal characteristics that are the same as those exhibited by the target three-dimensional leakage magnetic flux signal, and the damage type corresponding to the candidate leakage magnetic flux signal characteristics is determined, thereby determining the target damage type corresponding to the target drill bit.

[0039] By performing flux leakage signal feature analysis on the target triaxial flux leakage signal, the target damage type corresponding to the target drill bit can be determined. This enables rapid determination of the target damage type based on the target triaxial flux leakage signal, thereby improving the system's processing efficiency.

[0040] S130. For different target damage types, the target triaxial leakage magnetic signal is converted to generate a target triaxial two-dimensional damage image, and the target two-dimensional damage image is fused with image features to generate a target three-dimensional damage model.

[0041] Three-dimensional two-dimensional damage images include axial two-dimensional damage images, radial two-dimensional damage images, and circumferential two-dimensional damage images.

[0042] After determining the target damage type of the target drill bit, it is also necessary to determine the specific size of the damage to the target drill bit.

[0043] This can be addressed by treating different types of target damage separately. The processing procedure is the same for different types of target damage.

[0044] After obtaining the target's triaxial magnetic flux leakage signal, it can be converted using existing algorithms to generate a target triaxial two-dimensional damage image. Then, image feature fusion is performed on each of the target's two-dimensional damage images to generate a target three-dimensional damage model.

[0045] Optionally, for different target damage types, the target triaxial leakage magnetic signal is converted to generate a target triaxial two-dimensional damage image, and the target two-dimensional damage image is fused with image features to generate a target three-dimensional damage model, including:

[0046] The drill string damage detection model converts the target's three-dimensional magnetic flux leakage signal for different target damage types, generates a target three-dimensional two-dimensional damage image, and then fuses the target's two-dimensional damage image with image features to generate a target three-dimensional damage model.

[0047] To accelerate the inversion efficiency and accuracy of the target three-dimensional damage model, a pre-trained drill string damage detection model can be used.

[0048] The drill string damage detection model employs a Mask R-CNN network to enhance image feature extraction, enabling the filling, labeling, and localization of various defects. Multiple ResNet networks are designed to fuse magnetic flux leakage signal features and perform 3D inversion. For each damage type, a separate ResNet network fuses magnetic flux leakage signal features and performs 3D inversion. The Gramian Angular Field (GAF) method is used to convert the magnetic flux leakage signals in three directions for each type of damage into 2D images, which are then input into their respective ResNet networks for image feature fusion. Finally, 3D inversion of various drill string defects is achieved.

[0049] Furthermore, the drill damage detection model in this application uses the ResNet101 network as the main architecture to build the Mask R-CNN network, and incorporates the FCN algorithm in each RoIAlign operation. The Mean Of Average Precision (MAP) is used as the evaluation metric during the segmentation and localization process.

[0050] Correspondingly, the training process for the drill string damage detection model includes A1-A4:

[0051] Step A1: Determine the sample triaxial magnetic flux leakage signal, sample damage type, and sample damage three-dimensional model of at least one sample drill bit.

[0052] Step A2: For each sample drill bit corresponding to a sample damage type, the drill bit damage detection model is based on the Gram angle field method. The sample three-dimensional leakage magnetic signals of the sample drill bit corresponding to the sample damage type are converted to generate a sample three-dimensional two-dimensional damage image.

[0053] Step A3: For each sample's two-dimensional damage image in the three-dimensional damage image of the sample, perform image feature fusion through a residual network to generate a three-dimensional damage model of the sample.

[0054] Step A4: Adjust the drill bit damage detection model based on the calculated three-dimensional damage model of the sample.

[0055] To ensure the accuracy of the drill string damage detection model, it is necessary to train the model, which requires obtaining the sample triaxial magnetic flux leakage signal, sample damage type, and sample damage three-dimensional model of at least one sample drill string.

[0056] Due to the different types of damage, in order to ensure the accuracy of the calculation results, the drill bit damage detection model of this application contains a residual network corresponding to each damage type, which is used to generate a three-dimensional damage model of the calculation sample.

[0057] Based on the different damage types, each sample drill bit and its corresponding sample triaxial magnetic flux leakage signal and sample damage three-dimensional model are classified, and different damage types are trained separately.

[0058] The Gram angle field method is a technique for converting one-dimensional time series data into two-dimensional images. It treats each data point in the one-dimensional time series data as a point in a vector space and calculates the cosine value of the angle between these points. These cosine values ​​reflect the similarity or correlation between data points at different time points. Finally, the calculated cosine values ​​are mapped onto the pixels of the two-dimensional image to generate an image that reflects the dynamic and periodic characteristics of the time series.

[0059] Based on the characteristics of the Gram corner field method, this application uses the Gram corner field method to convert the one-dimensional sample triaxial leakage magnetic signal into a three-dimensional two-dimensional damage image of the sample.

[0060] By fusing features from the generated three-dimensional two-dimensional damage image of the sample through a residual network, a three-dimensional damage model of the sample is obtained.

[0061] To ensure the accuracy of the drill string damage detection model, this application adjusts the drill string damage detection model by calculating the differences between the sample three-dimensional damage models and the sample three-dimensional damage models.

[0062] In addition to the sample 3D damage model, the sample drill may not have a sample 3D damage model. In this case, the sample damage on the surface of the sample drill can be photographed by a camera and used to replace the sample 3D damage model to adjust the drill damage detection model.

[0063] Optionally, a fully convolutional network algorithm is added to each RoIAlign operation of the drill string damage detection model, and the average accuracy is used as the evaluation index of the RoIAlign operation.

[0064] According to the technical solution of this invention, a real-time non-destructive testing device at the wellhead is used to determine the target triaxial magnetic flux leakage signal of the target drilling tool. This allows for a more comprehensive and rapid magnetic flux leakage detection of the target drilling tool without moving it. By performing magnetic flux leakage signal feature analysis on the target triaxial magnetic flux leakage signal, the target damage type of the target drilling tool is determined. This enables rapid determination of the target damage type based on the target triaxial magnetic flux leakage signal, thereby improving the system's processing efficiency. Furthermore, the target triaxial magnetic flux leakage signal is converted for different target damage types to generate a target triaxial two-dimensional damage image. Image feature fusion of the target two-dimensional damage image generates a target three-dimensional damage model, thus determining the damage to the target drilling tool. The combined use of these steps improves both the detection efficiency and accuracy of target drilling tool damage. This allows for rapid detection of damage to the target drilling tool, preventing excessive damage that could negatively impact oil and gas extraction efficiency.

[0065] Example 2

[0066] Figure 3 This invention provides a flowchart of another drill bit damage detection method. Based on the above embodiments, this embodiment further optimizes the process after fusing image features from the target two-dimensional damage image to generate a target three-dimensional damage model. This embodiment can be combined with various optional solutions from one or more of the above embodiments. Figure 3 As shown, the drill bit damage detection method of this embodiment may include the following steps:

[0067] S210, Determine the target three-dimensional leakage magnetic signal of the target drill bit.

[0068] The three-dimensional magnetic flux leakage signal includes axial magnetic flux leakage signal, radial magnetic flux leakage signal, and circumferential magnetic flux leakage signal.

[0069] S220. Perform magnetic flux leakage signal characteristic analysis on the target's three-dimensional magnetic flux leakage signal to determine the target damage type corresponding to the target drill bit.

[0070] S230. For different target damage types, the target triaxial leakage magnetic signal is converted to generate a target triaxial two-dimensional damage image, and the target two-dimensional damage image is fused with image features to generate a target three-dimensional damage model.

[0071] Three-dimensional two-dimensional damage images include axial two-dimensional damage images, radial two-dimensional damage images, and circumferential two-dimensional damage images.

[0072] S240. Determine the target usage time of the target drilling tool and the target triaxial stress threshold.

[0073] S250. Based on the target damage type and the three-dimensional model of the target damage, determine the target triaxial stress coefficient from at least one pre-determined candidate triaxial stress coefficient.

[0074] After determining the target damage type and the three-dimensional model of the target drill bit, the remaining service life of the target drill bit can be determined based on the target damage type and the three-dimensional model of the target damage.

[0075] In this regard, the target triaxial stress coefficient can be found from at least one pre-determined candidate triaxial stress coefficient using the target damage type and the target damage three-dimensional model. This candidate triaxial stress coefficient can then be used as the target triaxial stress coefficient for the target drilling tool.

[0076] In one alternative approach, candidate triaxial stress coefficients are determined by a stress coefficient determination model.

[0077] Correspondingly, the stress coefficient determination model's process for determining candidate triaxial stress coefficients includes B1-B4:

[0078] Step B1: Determine the sample triaxial magnetic flux leakage signal, sample damage type, sample triaxial stress, and sample damage three-dimensional model of at least one sample drill bit.

[0079] Step B2: Determine the total magnetic flux leakage signal intensity of each sample drill bit based on the sample three-dimensional magnetic flux leakage signal of at least one sample drill bit.

[0080] Step B3: Based on the sample damage type and the three-dimensional model of sample damage, classify the sample drill bit to obtain at least one type of sample drill bit and the total leakage magnetic signal intensity and triaxial stress of each type of sample drill bit.

[0081] Step B4: For different types of sample drill bits, determine the total leakage magnetic signal intensity and the stress coefficients of each direction of the triaxial stress of the sample as candidate triaxial stress coefficients for the damage type of the sample.

[0082] Due to different damage types and three-dimensional damage sizes, the coefficients between the total leakage magnetic field strength and the triaxial stress may differ. Therefore, this application determines the candidate triaxial stress coefficients separately based on the different damage types and three-dimensional damage models of the samples.

[0083] To improve the efficiency and accuracy of determining each candidate triaxial stress coefficient, this application uses a stress coefficient determination model to determine each candidate triaxial stress coefficient.

[0084] This application specifies different types of sample damage and three-dimensional models of sample damage.

[0085] In determining the total leakage magnetic field strength, this application identifies the stress coefficients of the total leakage magnetic field strength and the stresses in each direction of the triaxial stress of the sample as candidate triaxial stress coefficients for the sample damage type. This is illustrated in the following formula:

[0086]

[0087] Where Bsum is the total leakage magnetic signal intensity; σ2 represents the circumferential stress in the triaxial stress of the sample; and a to e represent the candidate triaxial stress coefficients.

[0088] S260. Based on the target triaxial stress coefficient and the target triaxial leakage magnetic signal, determine the target triaxial stress of the target drill bit.

[0089] Once the target triaxial stress coefficient and the target triaxial magnetic flux leakage signal are obtained, the target total magnetic flux leakage signal intensity corresponding to the target drill bit can be determined through the target triaxial magnetic flux leakage signal. At this time, the target triaxial stress of the target drill bit can be determined through the target triaxial stress coefficient and the target total magnetic flux leakage signal intensity.

[0090] S270. Determine the target remaining service life of the target drilling tool based on the target triaxial stress, the target service time, and the target triaxial stress threshold.

[0091] Triaxial stress includes axial stress, radial stress, and circumferential stress.

[0092] In one alternative approach, the target remaining service life of the target drilling tool is determined based on the target triaxial stress, the target service duration, and the target triaxial stress threshold, including steps C1-C3:

[0093] Step C1: Determine the first relationship based on the target triaxial stress and the target usage time. The first relationship is the mapping relationship between the target triaxial stress and the target usage time. The longer the target usage time, the smaller the target triaxial stress.

[0094] Step C2: Determine the residual stress based on the difference between the target triaxial stress and the target triaxial stress threshold.

[0095] Step C3: Based on the first relationship and the residual stress, determine the service life corresponding to the residual stress, which is taken as the target remaining service life.

[0096] After obtaining the target triaxial stress and the target usage time, the correspondence between the target triaxial stress and the target usage time can be determined, that is, the attenuation law of the target triaxial stress as the usage time increases. At this time, the first relationship can be obtained.

[0097] By subtracting the target triaxial stress from the target triaxial stress threshold, the residual stress of the target drill string in the three directions can be determined. Then, based on the first relationship and the residual stress in the three directions, the remaining service life of the target drill string can be estimated.

[0098] By determining the first relationship based on the target triaxial stress and the target service life, the remaining stress is determined based on the difference between the target triaxial stress and the target triaxial stress threshold. Finally, based on the first relationship and the remaining stress, the service life corresponding to the remaining stress is determined as the target remaining service life. This makes the process of determining the target remaining service life of the target drilling tool clearer and the result of determining the target remaining service life more accurate.

[0099] According to the technical solution of the present invention, the target triaxial stress coefficient is determined from at least one pre-determined candidate triaxial stress coefficient based on the target damage type and the three-dimensional model of the target damage; and the target triaxial stress of the target drill bit is determined based on the target triaxial stress coefficient and the target triaxial leakage magnetic signal; finally, the target remaining service life of the target drill bit is determined based on the target triaxial stress, the target service life, and the target triaxial stress threshold, so that the determination of the target remaining service life of the target drill bit can be quantified, which enables the target drill bit to avoid damage due to excessive damage to the target drill bit, thus affecting the oil and gas extraction efficiency.

[0100] Example 3

[0101] Figure 4 This invention provides a structural block diagram of a drill string damage detection device, applicable to situations involving damage detection of drilling tools. The device can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 4 As shown, the drill bit damage detection device of this embodiment may include: a magnetic flux leakage signal determination module 310, a damage type determination module 320, and a three-dimensional damage determination module 330. Wherein:

[0102] The magnetic flux leakage signal determination module 310 is used to determine the target three-dimensional magnetic flux leakage signal of the target drilling tool. The three-dimensional magnetic flux leakage signal includes axial magnetic flux leakage signal, radial magnetic flux leakage signal and circumferential magnetic flux leakage signal.

[0103] Damage type determination module 320 is used to perform leakage magnetic signal feature analysis on the target triaxial leakage magnetic signal to determine the target damage type corresponding to the target drill bit.

[0104] The damage 3D determination module 330 is used to convert the target triaxial leakage magnetic signal for different target damage types, generate the target triaxial 2D damage image, and perform image feature fusion on the target 2D damage image to generate the target 3D damage model; the triaxial 2D damage image includes axial 2D damage image, radial 2D damage image and circumferential 2D damage image.

[0105] Based on the above embodiments, optionally, after the damage three-dimensional determination module 330, the following component is also included:

[0106] Determine the target service life of the target drilling tool and the target triaxial stress threshold;

[0107] Based on the target damage type and the three-dimensional model of the target damage, the target triaxial stress coefficient is determined from at least one pre-determined candidate triaxial stress coefficient.

[0108] The target triaxial stress of the target drill bit is determined based on the target triaxial stress coefficient and the total flux leakage signal intensity.

[0109] The target remaining service life of the target drilling tool is determined based on the target triaxial stress, the target service life, and the target triaxial stress threshold; the triaxial stress includes axial stress, radial stress, and circumferential stress.

[0110] Based on the above embodiments, optionally, the damage three-dimensional determination module 330 includes:

[0111] The drill string damage detection model converts the target triaxial leakage magnetic field signal for different target damage types, generates a target triaxial two-dimensional damage image, and then performs image feature fusion on the target two-dimensional damage image to generate a target three-dimensional damage model.

[0112] Correspondingly, the training process of the drill string damage detection model includes:

[0113] Determine the sample triaxial magnetic flux leakage signal, sample damage type, and sample damage three-dimensional model of at least one sample drill bit;

[0114] For each sample drill string corresponding to a different damage type, the drill string damage detection model is based on the Gram angle field method. It converts the three-dimensional leakage magnetic field signal of the sample drill string corresponding to the damage type of the sample to generate a three-dimensional two-dimensional damage image of the sample.

[0115] For each sample's two-dimensional damage image in the three-dimensional damage image of the sample, the image features are fused through a residual network to generate a three-dimensional damage model of the sample.

[0116] The drill string damage detection model is adjusted based on the calculated three-dimensional damage model of the sample and the sample three-dimensional damage model.

[0117] Based on the above embodiments, optionally, the drill string damage detection model can be adjusted, including:

[0118] The drill string damage detection model is adjusted using the mean squared error loss function.

[0119] Based on the above embodiments, optionally, a fully convolutional network algorithm is added to each RoIAlign operation of the drill string damage detection model, and the average accuracy is used as the evaluation index of the RoIAlign operation.

[0120] Based on the above embodiments, optionally, the candidate triaxial stress coefficients are determined by the stress coefficient determination model;

[0121] Correspondingly, the process of determining candidate triaxial stress coefficients using the stress coefficient determination model includes:

[0122] Determine the sample triaxial magnetic flux leakage signal, sample damage type, sample triaxial stress, and sample damage three-dimensional model of at least one sample drill bit;

[0123] Determine the total magnetic flux leakage signal intensity of each sample drill bit based on the sample triaxial magnetic flux leakage signal of at least one sample drill bit.

[0124] Based on the sample damage type and the three-dimensional model of sample damage, the sample drill string is classified to obtain at least one type of sample drill string, the total leakage magnetic signal intensity and the triaxial stress of each type of sample drill string.

[0125] For different types of sample drill bits, the total leakage magnetic field strength and the stress coefficients of each direction of the triaxial stress of the sample are determined as candidate triaxial stress coefficients for the damage type of the sample.

[0126] Based on the above embodiments, optionally, the target remaining service life of the target drilling tool is determined according to the target triaxial stress, the target service time, and the target triaxial stress threshold, including:

[0127] Based on the target's triaxial stress and the target's usage time, a primary relationship is determined. This primary relationship is the mapping relationship between the target's triaxial stress and the target's usage time. The longer the target's usage time, the smaller the target's triaxial stress.

[0128] The residual stress is determined based on the difference between the target triaxial stress and the target triaxial stress threshold.

[0129] Based on the first relationship and the residual stress, the service life corresponding to the residual stress is determined as the target remaining service life.

[0130] The drill bit damage detection device provided in this embodiment of the invention can execute the drill bit damage detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0131] Example 4

[0132] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0133] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0134] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0135] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as drill string damage detection methods.

[0136] In some embodiments, the drill string damage detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the drill string damage detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the drill string damage detection method by any other suitable means (e.g., by means of firmware).

[0137] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0138] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0139] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0140] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0141] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0142] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0143] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0144] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting damage to drilling tools, characterized in that, include: Determine the target triaxial magnetic flux leakage signal of the target drilling tool, wherein the triaxial magnetic flux leakage signal includes axial magnetic flux leakage signal, radial magnetic flux leakage signal and circumferential magnetic flux leakage signal; The leakage magnetic flux signal feature analysis is performed on the target triaxial leakage magnetic flux signal to determine the target damage type corresponding to the target drill bit; For different types of target damage, the target triaxial leakage magnetic signal is converted to generate a target triaxial two-dimensional damage image, and the target two-dimensional damage image is fused with image features to generate a target three-dimensional damage model; the triaxial two-dimensional damage image includes an axial two-dimensional damage image, a radial two-dimensional damage image, and a circumferential two-dimensional damage image.

2. The method according to claim 1, characterized in that, After fusing image features from the two-dimensional damage image of the target to generate a three-dimensional damage model, the process also includes: Determine the target usage time and target triaxial stress threshold of the target drilling tool; Based on the target damage type and the target damage three-dimensional model, the target triaxial stress coefficient is determined from at least one pre-determined candidate triaxial stress coefficient; Based on the target triaxial stress coefficient and the target triaxial leakage magnetic signal, the target triaxial stress of the target drill bit is determined; The target remaining service life of the target drill bit is determined based on the target triaxial stress, the target service life, and the target triaxial stress threshold; the triaxial stress includes axial stress, radial stress, and circumferential stress.

3. The method according to claim 1, characterized in that, For different target damage types, the target's triaxial leakage magnetic field signal is converted to generate a target triaxial two-dimensional damage image. Then, the target's two-dimensional damage image is fused with image features to generate a target three-dimensional damage model, including: The drill string damage detection model converts the target triaxial leakage magnetic field signal for different target damage types, generates a target triaxial two-dimensional damage image, and then performs image feature fusion on the target two-dimensional damage image to generate a target three-dimensional damage model. Accordingly, the training process of the drill string damage detection model includes: Determine the sample triaxial magnetic flux leakage signal, sample damage type, and sample damage three-dimensional model of at least one sample drill bit; For each of the aforementioned sample damage types, the drill string damage detection model is based on the Gram angle field method, which converts the sample triaxial leakage magnetic field signal of the sample drill string corresponding to the sample damage type to generate a sample triaxial two-dimensional damage image. For each sample's two-dimensional damage image in the three-dimensional damage image of the sample, the image features are fused through a residual network to generate a three-dimensional damage model of the sample. The drill bit damage detection model is adjusted based on the calculated sample three-dimensional damage model and the sample three-dimensional damage model.

4. The method according to claim 3, characterized in that, Adjustments were made to the drill string damage detection model, including: The drill bit damage detection model is adjusted using the mean squared error loss function.

5. The method according to claim 3, characterized in that, The fully convolutional network algorithm is incorporated into each RoIAlign operation of the drill bit damage detection model, and the average accuracy is used as the evaluation index for the RoIAlign operation.

6. The method according to claim 2, characterized in that, The candidate triaxial stress coefficients are determined by the stress coefficient determination model; Accordingly, the process of determining candidate triaxial stress coefficients using the stress coefficient determination model includes: Determine the sample triaxial magnetic flux leakage signal, sample damage type, sample triaxial stress, and sample damage three-dimensional model of at least one sample drill bit; Determine the total magnetic flux leakage signal intensity of each sample drill bit based on the sample triaxial magnetic flux leakage signal of at least one sample drill bit. Based on the sample damage type and the sample damage three-dimensional model, the sample drill bit is classified to obtain at least one type of sample drill bit and the total leakage magnetic signal intensity and triaxial stress of each type of sample drill bit; For different types of sample drill bits, the total leakage magnetic field strength and the stress coefficients of each direction of the triaxial stress in the sample are determined as candidate triaxial stress coefficients for the damage type of the sample.

7. The method according to claim 2, characterized in that, The target remaining service life of the target drill bit is determined based on the target triaxial stress, the target usage time, and the target triaxial stress threshold, including: Based on the target triaxial stress and the target usage time, a first relationship is determined. The first relationship is a mapping relationship between the target triaxial stress and the target usage time. The longer the target usage time, the smaller the target triaxial stress. The remaining stress is determined based on the difference between the target triaxial stress and the target triaxial stress threshold. Based on the first relationship and the remaining stress, the service life corresponding to the remaining stress is determined as the target remaining service life.

8. A drill bit damage detection device, characterized in that, include: The magnetic flux leakage signal determination module is used to determine the target triaxial magnetic flux leakage signal of the target drilling tool. The triaxial magnetic flux leakage signal includes axial magnetic flux leakage signal, radial magnetic flux leakage signal and circumferential magnetic flux leakage signal. The damage type determination module is used to perform leakage magnetic signal feature analysis on the target triaxial leakage magnetic signal to determine the target damage type corresponding to the target drill bit. The damage 3D determination module is used to convert the target triaxial leakage magnetic field signal for different target damage types, generate the target triaxial 2D damage image, and perform image feature fusion on the target 2D damage image to generate the target 3D damage model; the triaxial 2D damage image includes axial 2D damage image, radial 2D damage image and circumferential 2D damage image.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the drill bit damage detection method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the drill bit damage detection method according to any one of claims 1-7.

Images