CN117392081A

CN117392081A - Drill bit abrasion detection method, device and system

Info

Publication number: CN117392081A
Application number: CN202311326423.8A
Authority: CN
Inventors: 宋先知; 杨东晗; 祝兆鹏; 李根生; 黄中伟; 史怀忠; 王斌; 熊超
Original assignee: China University of Petroleum Beijing
Current assignee: China University of Petroleum Beijing
Priority date: 2023-10-13
Filing date: 2023-10-13
Publication date: 2024-01-12

Abstract

The present disclosure relates to the field of petroleum drilling technologies, and in particular, to a method, an apparatus, and a system for detecting drill wear. Wherein the drill bit wear detection method comprises: acquiring a drill bit image of a drilling site; preprocessing the drill bit image; identifying the wear state of the drill bit according to the preprocessed drill bit image; if the identified abrasion state is a normal abrasion state, determining a first image characteristic of the abraded drill bit according to the preprocessed drill bit image; determining the abrasion loss of the drill bit according to the first image feature and the second image feature before abrasion of the drill bit; generating a drill bit abrasion detection report according to the abrasion loss; or if the identified wear state is an abnormal wear state, generating a drill wear detection report according to the identified abnormal wear state. The embodiments of the present disclosure can efficiently and quantitatively evaluate the wear of a drill bit.

Description

Drill bit abrasion detection method, device and system

Technical Field

The present disclosure relates to the field of petroleum drilling technologies, and in particular, to a method, an apparatus, and a system for detecting drill wear.

Background

With the development of oil and gas exploration towards the fields of unconventional oil and gas and depth complexity, a drill bit is used as the most direct and important rock breaking tool in the oil and gas drilling process, and the reduction of drilling efficiency, the aggravation of abrasion condition and the occurrence of abnormal condition become main factors for restricting drilling efficiency and safety. Although the international association of drill contractors (International Association of Drilling Contractors, IADC) has established a rating scale for drill wear. However, due to the lack of quantitative and scientific evaluation technical means, the abrasion detection of the current field drill bit still depends on the manual measurement and experience of field engineers. So that the efficiency of bit wear detection is low and the accuracy is also poor.

Disclosure of Invention

The embodiment of the specification provides a drill bit abrasion detection method, device and system, which are used for efficiently and quantitatively evaluating the abrasion condition of a drill bit.

The embodiment of the specification provides a drill bit abrasion detection method, which comprises the following steps:

acquiring a drill bit image of a drilling site;

preprocessing the drill bit image;

identifying the wear state of the drill bit according to the preprocessed drill bit image;

if the identified abrasion state is a normal abrasion state, determining a first image characteristic of the abraded drill bit according to the preprocessed drill bit image; determining the abrasion loss of the drill bit according to the first image feature and the second image feature before abrasion of the drill bit; generating a drill bit abrasion detection report according to the abrasion loss; or if the identified wear state is an abnormal wear state, generating a drill wear detection report according to the identified abnormal wear state.

The embodiment of the specification also provides a drill bit abrasion detection device, which comprises:

the acquisition unit is used for acquiring a drill bit image of a drilling site;

the processing unit is used for preprocessing the drill bit image;

the identifying unit is used for identifying the abrasion state of the drill bit according to the preprocessed drill bit image;

The determining unit is used for determining a first image characteristic of the worn drill bit according to the preprocessed drill bit image if the identified wear state is a normal wear state; determining the abrasion loss of the drill bit according to the first image feature and the second image feature before abrasion of the drill bit; generating a drill bit abrasion detection report according to the abrasion loss; or if the identified wear state is an abnormal wear state, generating a drill wear detection report according to the identified abnormal wear state.

The embodiments of the present specification also provide a drill bit wear detection system, comprising:

shooting equipment for acquiring drill bit images of a drilling site;

the drill bit abrasion detection equipment is used for preprocessing the drill bit image; identifying the wear state of the drill bit according to the preprocessed drill bit image; if the abrasion state is a normal abrasion state, determining a first image characteristic of the abraded drill bit according to the preprocessed drill bit image; and determining the abrasion loss of the drill bit according to the first image characteristic and the second image characteristic before the drill bit is abraded.

According to the drill bit abrasion detection method disclosed by the embodiment of the specification, the drill bit image of a drilling site can be acquired; the drill bit image may be preprocessed; the abrasion state of the drill bit can be identified according to the preprocessed drill bit image; if the identified abrasion state is a normal abrasion state, determining a first image characteristic of the abraded drill bit according to the preprocessed drill bit image; determining the abrasion loss of the drill bit according to the first image feature and the second image feature before abrasion of the drill bit; generating a drill bit abrasion detection report according to the abrasion loss; or if the identified wear state is an abnormal wear state, generating a drill wear detection report according to the identified abnormal wear state. This allows the wear state of the drill bit to be identified from the drill bit image. When the abrasion state is a normal abrasion state, the drill bit image can be analyzed and processed through a computer vision method, and the abrasion amount of the drill bit can be obtained, so that a drill bit abrasion detection report is obtained. When the wear state is an abnormal wear state, a bit wear detection report may be generated according to the identified abnormal wear state. By the drill bit abrasion detection report, the abrasion condition of the drill bit can be estimated in a high-efficiency quantitative mode.

Drawings

In order to more clearly illustrate the embodiments of the present description or the solutions in the prior art, the drawings that are required for the embodiments or the description of the prior art will be briefly described, the drawings in the following description are only some embodiments described in the present description, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic flow chart of a method for detecting drill wear in an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of a method of bit wear detection in an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of a drill bit wear detection process in an embodiment of the present disclosure;

fig. 4 is a schematic structural view of a drill wear detection device according to an embodiment of the present disclosure.

Detailed Description

The technical solutions of the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is apparent that the described embodiments are only some embodiments of the present specification, not all embodiments. The specific embodiments described herein are to be considered in an illustrative rather than a restrictive sense. All other embodiments derived by a person of ordinary skill in the art based on the described embodiments of the present disclosure fall within the scope of the present disclosure. In addition, relational terms such as "first" and "second", and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.

The present description embodiments provide a drill wear detection system. The drill wear detection system may include a photographing device and a drill wear detection device. The photographing apparatus may include a camera and a video camera. The drill bit wear detection device may include a portable computer (e.g., a notebook computer), desktop computer, server, etc. The photographing apparatus and the bit wear apparatus may be separate apparatuses. Alternatively, the photographing device and the drill bit wear device may also be integrated into one device. For example, the device may include a smart phone carrying a camera, a tablet, a portable computer (e.g., a notebook), a desktop, a server, etc.

The shooting equipment is used for acquiring drill bit images of a drilling site. The drill bit abrasion detection equipment is used for acquiring the drill bit image acquired by the shooting equipment; identifying the wear state of the drill bit according to the drill bit image; if the abrasion state is a normal abrasion state, determining a first image characteristic of the abraded drill bit according to the drill bit image; determining the abrasion loss of the drill bit according to the first image feature and the second image feature before abrasion of the drill bit; generating a drill bit abrasion detection report according to the abrasion loss; or if the wear state is an abnormal wear state, generating a drill wear detection report according to the identified abnormal wear state. When the abrasion state is in a normal abrasion state, the drill bit image can be analyzed and processed through a computer vision method, so that the abrasion amount of the drill bit can be obtained, and a drill bit abrasion detection report can be obtained. When the wear state is an abnormal wear state, a bit wear detection report may be generated according to the identified abnormal wear state. By the drill bit abrasion detection report, the abrasion condition of the drill bit can be estimated in a high-efficiency quantitative mode.

Please refer to fig. 1, fig. 2 and fig. 3 together. The embodiment of the specification provides a drill bit abrasion detection method. The drill bit wear detection method can be applied to electronic equipment such as the drill bit wear detection equipment. The drill bit wear detection method may include the following steps.

Step 11: a bit image of a drilling site is acquired.

In some embodiments, the photographing device may acquire images of the drill bit at the drilling site; the bit image may be transmitted to the bit wear detection device. The bit wear detection device may receive the bit image.

The drill bit image can be acquired by shooting equipment according to preset shooting parameters. Specifically, shooting parameters of the drill bit may be preset. The shooting parameters include, but are not limited to, shooting angle, shooting distance, shooting light, etc. The shooting device can acquire the drill bit image according to the shooting parameters. This facilitates obtaining a clear bit image on the one hand. On the other hand, the abrasion loss of the drill bit can be obtained in a mode of image characteristic comparison.

In some embodiments, a drill bit may be lowered into the well to perform the drilling operation. After the tripping condition is met, the drill bit in the well may be lifted to the surface. After being lifted to the ground, the shooting equipment can acquire a bit image of the bit; the bit image may be transmitted to the bit wear detection device. The bit wear detection device may receive the bit image. Wherein it may be that after drilling the paragraph, the drill bit in the well is lifted to the surface. Alternatively, the drill bit in the well may be lifted to the surface when the core is desired to be extracted. Of course, it is also possible to raise the drill bit in the well to the surface after other tripping conditions are met. The embodiment of the present specification is not particularly limited thereto.

Step 12: the drill bit image is preprocessed.

In some embodiments, the quality of the drill bit image can be improved by preprocessing the drill bit image, so that the subsequent image analysis processing is more accurate and reliable.

In some embodiments, a standard image preprocessing procedure may be preset; the preprocessing of the drill bit image can be realized by executing the image preprocessing flow. For example, the bit image may be grayed to obtain a gray image; the gray scale image may be subjected to a filtering process. For another example, the bit image may be subjected to graying processing to obtain a gray image; the gray scale image can be filtered; the gray-scale image after the filtering process may be smoothed.

Filtering algorithms such as mean filtering, median filtering, gaussian filtering and the like can be adopted to carry out filtering processing on the gray level image. The gray-scale image may be smoothed by a smoothing method such as an interpolation method, a linear smoothing method, a convolution method, or the like.

Step 13: and identifying the abrasion state of the drill bit according to the preprocessed drill bit image.

In some embodiments, the wear state of the drill bit may be identified by a deep learning method. Specifically, the wear state recognition model may be trained in advance; the drill bit image can be input into a trained wear state identification model to obtain the wear state of the drill bit. The wear state of the drill bit may include at least one normal wear state and at least one abnormal wear state. The normal wear state of the drill bit is used to indicate that the drill bit is in a normal wear state. The at least one normal wear condition of the drill bit may include a normal wear condition of at least one component in the drill bit. The abnormal wear state of the drill bit is used to indicate that the drill bit is in a damaged state. The at least one abnormal wear condition of the drill bit may include an abnormal wear condition of at least one component in the drill bit.

The drill bit may include cutting teeth, a matrix, nozzles, and the like. The wear state identification model may detect a target region in which one or more components are located in the bit image; the wear state of the one or more components may be determined for a target area in which the one or more components are located. The wear state recognition model may include a target detection model and a classification model. The target detection model may detect a target region in which one or more components are located in the bit image. The classification model may determine a wear state of one or more components based on a target area in which the one or more components are located.

The wear state output by the wear state identification model may include a wear state of one or more components. The wear state of each of the components may be selected from a normal wear state and at least one abnormal wear state. The normal wear state is used to indicate that the component is in a normal wear state. The abnormal wear state is used to indicate that the component is in a damaged state. Abnormal wear conditions of the cutting tooth include, but are not limited to, cutting tooth chipping, cutting tooth breakage, and the like. Abnormal wear conditions of the carcass include, but are not limited to, bit shrinkage, etc. Abnormal wear conditions of the nozzle include, but are not limited to, dropping the nozzle, nozzle clogging, and the like.

In some embodiments, a set of drill bit images may be acquired. The set of bit images may include bit images of at least one bit type. The drill bit image can be acquired by shooting equipment according to the shooting parameters. The bit image may be marked to obtain one or more wear state labels for the bit image. The one or more wear state tags may include a wear state tag of one or more components. The wear status label of each of the components may be selected from a normal wear label and at least one abnormal wear label. The normal wear tab is used to indicate normal wear of the component. The abnormal wear tab is used to indicate component damage. Abnormal wear labels for cutting teeth include cutting tooth chipping, cutting tooth breakage, and the like. The abnormal wear signature of the carcass may include bit shrinkage. Abnormal wear labels for nozzles may include nozzle drop, nozzle blockage, etc. For example, the wear status label of a certain bit image includes chipping of cutting teeth, normal wear of a carcass, and nozzle drop.

The bit image and its corresponding wear state label may be used as a training sample. The wear state recognition model may be trained based on the training samples. The wear state recognition model may include a model based on an attention mechanism. The wear state recognition model can strengthen the learning of key information by introducing an attention mechanism and combining methods such as feature enhancement, feature fusion and the like, so that the recognition efficiency and accuracy can be improved. The wear state identification model may include an R-CNN model, a YOLO model, a Swin transducer model, and the like. Of course, the wear state recognition model may also include other models, such as an SSD model, a RetinaNet model, and the like. The embodiment of the present specification is not particularly limited thereto.

It should be noted that the object detection model and the classification model may be functional modules in the wear state recognition model. Thus, by training the abrasion state recognition model, a trained target detection model and a trained classification model can be obtained. Of course, the object detection model and the classification model may be trained separately. For example, a plurality of drill bit images may be acquired; the drill bit image may be marked to obtain one or more profile labels for the drill bit image. Each profile label corresponds to a component in the drill bit for representing a profile area of the component in the drill bit image. The drill bit image and its corresponding profile label may be used as a training sample. The target detection model may be trained based on the training samples. For another example, multiple drill bit images may be acquired; the bit image may be marked to obtain one or more wear state labels for the bit image. The one or more wear state tags may include a wear state tag of one or more components in the drill bit. The wear status label of each component may be selected from a normal wear label and at least one abnormal wear label. The normal wear tab is used to indicate normal wear of the component. The abnormal wear tab is used to indicate component damage. Abnormal wear labels for cutting teeth include cutting tooth chipping, cutting tooth breakage, and the like. The abnormal wear signature of the carcass may include bit shrinkage. Abnormal wear labels for nozzles may include nozzle drop, nozzle blockage, etc. For example, the wear status label of a certain bit image includes chipping of cutting teeth, normal wear of a carcass, and nozzle drop. The bit image and its corresponding wear state label may be used as a training sample. The classification model may be trained based on training samples.

In some embodiments, a plurality of wear state recognition models may be trained from the set of bit images; the performance indexes of the plurality of trained wear state identification models can be obtained; selecting a target model from the plurality of wear state identification models according to the performance index; the bit image may be input into a target model to obtain the wear state of the bit. The performance indicators may include recognition speed, recognition accuracy, length of time required for training, etc. For example, the plurality of wear state identification models may include an R-CNN model, a YOLO model, a Swin transducer model, and the like. The YOLO model can ensure the rapid recognition speed, and meanwhile, the recognition accuracy is relatively high and the stability is good. The R-CNN model and the Swin transducer model can train a better model in a shorter time. The results of training the Swin transducer model in a shorter time are more accurate than the R-CNN model, but the time required for recognition is relatively longer. Therefore, a YOLO model can be selected as a target model; the bit image may be input into a target model to obtain the wear state of the bit.

Step 14: and if the abrasion state of the drill bit is a normal abrasion state, determining a first image characteristic of the drill bit after abrasion according to the preprocessed drill bit image.

In some embodiments, if the wear state is a normal wear state, the bit image may be analyzed using computer vision methods to determine a first image feature of the bit. And the abrasion condition of the drill bit is convenient to quantify through a computer vision method.

The first image features of the drill bit may include first image features of one or more components in the drill bit.

In some embodiments, the wear state output by the wear state identification model may include a wear state of one or more components. It may be determined whether the wear state of the one or more components is a normal wear state; if yes, the abrasion state of the drill bit can be determined to be a normal abrasion state; if not, the wear state of the drill bit can be determined to be an abnormal wear state.

Further, the drill bit may include at least one first component and at least one second component. The first component may include cutting teeth, a carcass, and the like. The second part may comprise a nozzle or the like. It may be determined whether the wear states of the at least one first component are all normal wear states; if yes, the abrasion state of the drill bit can be determined to be a normal abrasion state; if not, the wear state of the drill bit can be determined to be an abnormal wear state. The first image feature of the drill bit may comprise a first image feature of the at least one first component. Such as the first image feature of the cutting tooth and/or the carcass. In addition, the first image features of the drill bit do not include the first image features of the second component, considering that the second component such as the nozzle does not wear.

In some embodiments, a first edge profile after bit wear may be determined from the bit image. The first edge profile of the drill bit may include the first edge profile of the one or more first components. For example, the first edge profile of the drill bit may include the first edge profile of the cutting teeth and/or the carcass. In practical applications, the first edge profile may be determined by an object detection model. The target detection model may include an R-CNN model, a YOLO model, a Swin transducer model, and the like. For example, the bit image may be input into a target detection model resulting in a first edge profile of one or more first components. Alternatively, gray processing can be performed on the drill bit image to obtain a gray image; one or more segmentation thresholds may be determined; determining a target area where one or more first components are located in the gray scale image according to the one or more segmentation thresholds; an edge contour of the one or more target regions may be extracted as a first edge contour of the one or more first components.

Each of the segmentation thresholds may correspond to one of the first components. One or more segmentation thresholds may thus be determined, from which one or more target regions in which the first component or components are located may be determined in the greyscale image. Alternatively, the division threshold may also correspond to a plurality of first components. A segmentation threshold may thus be determined, from which a target region in which one or more first components are located may be determined in the greyscale image. The segmentation threshold comprises a gray value. The segmentation threshold may be an empirical value. Alternatively, the segmentation threshold may be obtained by an image segmentation algorithm. The image segmentation algorithm may include an oxford method (OTSU), a mean iteration method, a maximum entropy method, and the like.

After the target area where the first component is located is determined, the edge contour of the target area may be directly extracted. Alternatively, morphological operations may also be performed on the target region; the edge contour of the target region after morphological operation can be extracted. Filling of the cavity in the target area and deburring of the target area can be achieved through morphological operation. The edge contour of the target area after morphological operation is more similar to the real edge contour. The morphological operations may include image open operations and/or image close operations, etc. The edge profile of the target area may include a closed curve formed by a plurality of pixel points.

The first edge profile of each first component may be the first image feature of that first component. The first image feature of the drill bit may thus comprise a first edge profile of one or more first components.

Or, ellipse fitting can be performed on the worn first edge profile to obtain a first ellipse parameter. The first ellipse parameters include one or more of a major axis, a minor axis, an eccentricity, and a center point. The first ellipse parameter is used to characterize the first edge profile. For example, an ellipse fitting may be performed on the first edge profile of each first component, respectively, to obtain the first ellipse parameters of the first component. The first ellipse parameter of each first component may be the first image characteristic of the first component. The first image characteristic of the drill bit may thus comprise a first ellipse parameter of the one or more first components.

Step 15: and determining the abrasion loss of the drill bit according to the first image characteristic and the second image characteristic before the drill bit is abraded.

In some embodiments, as previously described, a drill bit may be lowered into a well to perform a drilling operation. After the tripping condition is met, the drill bit in the well may be lifted to the surface. The camera may acquire an image of the drill bit as a reference image before lowering the drill bit into the well; the reference image may be transmitted to a drill bit wear detection device. The drill bit wear detection apparatus may receive a reference image; a second image characteristic of the drill bit before wear may be determined from the reference image. The reference image may be acquired by the photographing apparatus according to a predetermined photographing parameter. The reference image may be an image of the drill bit in an unused condition. The second image feature of the drill bit may be a pre-wear second image feature. The second image features of the drill bit may include the second image features of the one or more first components. Such as cutting teeth and/or a second image feature of the carcass.

A second edge profile of the drill bit before wear may be determined from the reference image. The second edge profile of the drill bit may include the second edge profile of the one or more first components. For example, the second edge profile of the drill bit may include the second edge profile of the cutting teeth and/or the carcass. In practical applications, the second edge profile may be determined by an object detection model. The target detection model may include an R-CNN model, a YOLO model, a Swin transducer model, and the like. For example, a reference image may be input into the object detection model resulting in a second edge profile of the one or more first components. Alternatively, the reference image may be subjected to graying processing to obtain a gray image; one or more segmentation thresholds may be determined; determining a target area where the one or more first components are located in the gray scale image according to the one or more segmentation thresholds; an edge contour of the one or more target regions may be extracted as a second edge contour of the one or more first components.

The second edge profile of each first component may be a second image feature of the first component. The second image feature of the drill bit may thus comprise a second edge profile of the one or more first components.

Alternatively, ellipse fitting may be performed on the pre-wear second edge profile to obtain a second ellipse parameter. The second ellipse parameters may include one or more of a major axis, a minor axis, an eccentricity, and a center point. The second ellipse parameter is used to characterize the second edge profile. For example, an ellipse fitting may be performed on the second edge profile of each first component separately, resulting in a second ellipse parameter for that first component. The second ellipse parameter of each first component may be the second image characteristic of the first component. The second image characteristic of the drill bit may thus comprise second ellipse parameters of the one or more first components.

In some embodiments, the drill bit may include a plurality of components such as cutting teeth, a carcass, nozzles, and the like. The amount of wear of the drill bit may include an amount of wear of at least one of the plurality of components. The amount of wear is used to indicate the degree of wear and may in particular be positively correlated with the degree of wear. Further, the plurality of components may include at least one first component and at least one second component. The amount of wear of the drill bit may include the amount of wear of the at least one first component.

In some embodiments, the first image feature of the drill bit may be compared to the second image feature of the drill bit to obtain the wear of the drill bit. The amount of wear of the drill bit includes an amount of wear of the one or more first components. The wear amount is used to indicate the degree of wear of the first component. The amount of wear may be a numerical value. The magnitude of the amount of wear may be positively correlated with the degree of wear.

In some implementations of this embodiment, the first image feature of the drill bit includes one or more first edge profiles after wear of the first component. The second image feature of the drill bit includes one or more second edge profiles of the first component prior to wear. The first edge profile and the second edge profile can be compared to obtain the variation of the edge profile; the amount of wear of the drill bit may be determined from the amount of change in the edge profile. Specifically, for each first component of the one or more first components, a first edge profile of the first component may be compared with a second edge profile of the first component, resulting in an amount of change in the edge profile; the amount of wear of the first component may be determined from the amount of change in the edge profile. For example, the first edge profile may include a closed curve formed by a plurality of pixel points. The second edge profile may include a closed curve formed by a plurality of pixels. The distance between the first edge profile and the second edge profile can be calculated as the amount of change in the edge profile; the distance may be mapped to an amount of wear.

For example, a plurality of pixels in the first edge contour may form a first set of pixels. The plurality of pixels in the second edge profile may form a second set of pixels. A Hausdorff distance (Hausdorff distance) between the first set of pixel points and the second set of pixel points may be calculated. Of course, this is by way of example only. In practice, the distance between the first edge contour and the second edge contour may also be calculated in other ways. The embodiment of the present specification is not particularly limited thereto.

The mapping coefficients may be determined from the aforementioned photographing parameters. Specifically, the camera can be calibrated according to the shooting parameters, so as to obtain the mapping coefficient. For example, an image of the calibration plate may be acquired according to the aforementioned photographing parameters. The mapping coefficients may be determined from an image of the calibration plate. The mapping coefficient is used to represent the ratio between the physical length and the pixel length. The amount of wear may be determined from the mapping coefficients. For example, the mapping coefficient may be multiplied by the distance to obtain the wear amount.

Of course, other ways of determining the amount of wear may be used depending on the first edge profile and the second edge profile.

In other implementations of this embodiment, as previously mentioned, the first image characteristic of the drill bit may include a first ellipse parameter of one or more first components. The second image characteristic of the drill bit may include a second ellipse parameter of the one or more first components. The amount of wear of the drill bit may be determined based on the first elliptical parameter and the second elliptical parameter. Specifically, for each of the one or more first components, an amount of wear of the first component may be determined based on a first elliptical parameter of the first component and a second elliptical parameter of the first component.

The first ellipse parameter and the second ellipse parameter can be compared to obtain the variation of the ellipse parameter; the amount of wear may be determined from the amount of change in the elliptical parameter. Specifically, for each first component of the one or more first components, a first ellipse parameter of the first component may be compared with a second ellipse parameter of the first component to obtain a variation of the ellipse parameter; the amount of wear of the first component may be determined based on the amount of change in the elliptical parameter. For example, the first ellipse parameter and the second ellipse parameter may include a center point. The distance between the center point in the first ellipse parameter and the center point in the second ellipse parameter may be calculated; the distance may be mapped to an amount of wear. For example, the mapping coefficient may be multiplied by the distance to obtain the wear amount.

Alternatively, the first elliptical area may be calculated according to the first elliptical parameter; the second elliptical area may be calculated from the second elliptical parameters. The first elliptical area may be understood as the area of the first edge profile. The second ellipse parameter may be understood as the area of the second edge contour. The ratio between the first elliptical area and the second elliptical area can be calculated as the amount of wear.

In some embodiments, the wear level of the drill bit may also be determined based on the amount of wear of the drill bit. The amount of wear of the drill bit may include an amount of wear of the at least one first component. The wear level of the drill bit may include a wear level of the at least one first component.

A set of wear classes may be provided. The wear level set includes at least one wear level. The wear level may include a wear level of the first component. Each abrasion grade corresponds to an abrasion loss section. The wear level of the drill bit may be selected from the set of wear levels according to the amount of wear of the drill bit. The abrasion loss interval where the abrasion loss is located can be obtained according to the abrasion loss of the drill bit; the wear level corresponding to the obtained wear section may be selected from the wear level set as the wear level of the drill bit.

The wear level set may include at least one subset of wear level sets. Each set of sub-wear levels may correspond to a first component and may specifically include at least one wear level. Each wear level may correspond to a wear level interval. For example, the set of wear levels may include a first set of sub-wear levels and a second set of sub-wear levels. The first set of sub-wear levels corresponds to the cutting tooth and may specifically include at least one wear level of the cutting tooth. The second set of sub-wear levels corresponds to the carcass, and may specifically include at least one wear level of the carcass. The amount of wear of the drill bit may include an amount of wear of the at least one first component. A respective set of sub-wear levels may be selected from the set of wear levels for each of the at least one first component; the wear amount interval in which the wear amount of the first component is located can be obtained; the wear level corresponding to the obtained wear section may be selected from the selected subset of wear levels as the wear level of the first component.

The wear level may include a wear level that meets IADC standards.

In some embodiments, a bit wear detection report may also be generated based on the amount of wear of the bit.

The bit wear detection report may be generated according to the wear state of the bit and the wear amount of the bit. The bit wear detection report is used to indicate wear of the bit. The wear state of the drill bit may include, among other things, a wear state of the first component and a wear state of the second component. The amount of wear of the drill bit may include an amount of wear of the first component. The bit wear detection report may include a wear state of the bit and an amount of wear of the bit. The bit wear detection report may include a report compliant with an IADC standard.

Alternatively, the wear level of the drill bit may also be determined by the amount of wear of the drill bit. A bit wear detection report may be generated based on the wear state of the bit and the wear level of the bit. The bit wear detection report is used to indicate wear of the bit. The wear state of the drill bit may include, among other things, a wear state of the first component and a wear state of the second component. The wear level of the drill bit may include a wear level of the first component. The bit wear detection report includes a wear state of the bit and a wear level of the bit.

In some embodiments, engineering data for the drilling site may also be obtained; a bit type of the bit may be obtained; engineering data, bit type, and wear amount may be correspondingly stored to the bit engineering information dataset. The drill bit types may include, among others, drag bits, diamond bits, PDC bits, dental bits, coring bits, and the like. The engineering data may include logging data, geological data, and the like. The logging data may include human operational data during drilling such as weight on bit, rotational speed, pump displacement, etc. The logging data may include wellbore measurement data such as offset, well inclination, azimuth, and the like. The geological data may include measured geological data, such as GR, RT, SP, AC, DEN, and the like.

In some embodiments, engineering data for a drilling site, bit type of bit, and wear amount of the bit may be obtained for different drilling operations, and the engineering data, bit type, and wear amount may be correspondingly stored to a bit engineering information dataset. The continuous accumulation and enrichment of the drill engineering information data sets are realized. By being constantly accumulated and enriched, the bit engineering information dataset may comprise a plurality of sub-datasets. Each sub-data set may correspond to engineering data and may include a bit type and its corresponding plurality of wear amounts. The plurality of wear amounts can be indicative of wear of the full life cycle of the drill bit. In each sub-data set, wear trend data for a bit type may be determined based on a plurality of wear amounts corresponding to the bit type. The wear trend data is used to represent the change of the wear amount with time. The wear trend data may include growth rate, etc.

It should be noted that each sub-data set may include a plurality of drill bit types and wear amounts corresponding to the plurality of drill bit types. Each bit type may correspond to a plurality of wear amounts. The multiple wear levels corresponding to the bit type can be indicative of the wear of the full life cycle of the bit. The wear trend data for each bit type may be determined for a corresponding plurality of wear amounts for that bit type in each sub-data set. The wear trend data is used to represent the change of the wear amount with time.

It is also noted that the amount of wear of the drill bit includes the amount of wear of the one or more first components. The wear trend data for the drill bit includes wear trend data for one or more first components. In each sub-data set, for each of the one or more first components, wear trend data for the first component may be determined from a plurality of wear amounts for the first component.

In some embodiments, when drilling operations need to be performed on the target well, engineering data of the target well may be obtained as target engineering data; selecting a corresponding sub-data set from the drill engineering information data set according to the target engineering data; the bit type appropriate for the target well may be selected from the subset of data based on the wear trend data in the subset of data.

The selected subset of data may include at least one bit type and its corresponding wear trend data. So that the bit type adapted to the target well can be determined from the wear trend data of the at least one bit type. Specifically, for example, wear trend data, in which the amount of wear changes most slowly with time, may be selected from at least one wear trend data, and the bit type corresponding to the wear trend data may be used as the bit type adapted to the target well. Specifically, for example, the wear trend data may include a rate of increase in the amount of wear. The bit type corresponding to the minimum growth rate may be selected from the subset of data as the bit type appropriate for the target well.

In some examples of scenarios, the wear trend data of the drill bit may include wear trend data of one or more first components. The wear trend data may include an increase rate of the amount of wear, and the like. The reference growth rate of the drill bit may be determined based on the growth rate of one or more first components in the drill bit. So that the bit type corresponding to the minimum reference growth rate can be selected from the subset of data as the bit type appropriate for the target well. Wherein in particular the largest one of the growth rates of the one or more first components may be selected as the reference growth rate for the drill bit. Alternatively, an average, median, etc. of the one or more first component growth rates may also be calculated as a reference growth rate for the drill bit.

Thus, based on the bit engineering information data set, the bit optimization of the drilling site is realized by combining the target engineering data of the target well.

In some embodiments, if the wear state of the drill bit is an abnormal wear state, design advice for the drill bit may be determined based on the identified abnormal wear state. So as to optimally design the processing and manufacturing of the drill bit and avoid abnormal abrasion state. The wear state of the drill bit being an abnormal wear state includes: all the components are in an abnormal wear state, and part of the components are in an abnormal wear state.

The components corresponding to the abnormal wear state may include at least one first component, or may also include at least one second path, or may also include at least one first component and at least one second component at the same time.

For each component whose wear state is an abnormal wear state, a design recommendation for the component may be determined based on the abnormal wear state of the component. The design advice may include, for example, optimizing the step teeth, optimizing the cutting tooth angle, optimizing the number of nozzles, etc. In practical applications, multiple knowledge maps may be provided. Each knowledge graph may correspond to a component. And selecting a knowledge graph from the plurality of knowledge graphs for each part with the abnormal wear state, and inquiring reasons and corresponding design suggestions in the selected knowledge graph according to the abnormal wear state of the part.

In this way, the cause of the damage can be analyzed to determine design advice. Providing empirical support for the custom design of the drill bit.

In some embodiments, if the wear state of the drill bit is an abnormal wear state, a drill bit wear detection report may be generated according to the wear state of the drill bit. The bit wear detection report may be used to indicate wear of components in the bit. The wear state of the drill bit may include, among other things, a wear state of the first component and a wear state of the second component. The bit wear detection report may include a wear state of the bit. Of course, the bit wear detection report may be generated based on the wear state of the bit and the design advice of the bit. Such that the bit wear detection report may include the wear status of the bit and design advice for the bit.

According to the drill bit abrasion detection method disclosed by the embodiment of the specification, the drill bit image of a drilling site can be acquired; the drill bit image may be preprocessed; the abrasion state of the drill bit can be identified according to the preprocessed drill bit image; if the abrasion state is a normal abrasion state, determining a first image characteristic of the abraded drill bit according to the preprocessed drill bit image; determining the abrasion loss of the drill bit according to the first image feature and the second image feature before abrasion of the drill bit; generating a drill bit abrasion detection report according to the abrasion loss; or if the wear state is an abnormal wear state, generating a drill wear detection report according to the identified abnormal wear state. This allows the wear state of the drill bit to be identified from the drill bit image. When the abrasion state is a normal abrasion state, the drill bit image can be analyzed and processed through a computer vision method, and the abrasion amount of the drill bit can be obtained, so that a drill bit abrasion detection report is obtained. When the wear state is an abnormal wear state, a bit wear detection report may be generated according to the identified abnormal wear state. By the drill bit abrasion detection report, the abrasion condition of the drill bit can be estimated in a high-efficiency quantitative mode.

According to the drill bit abrasion detection method, the abrasion state of the drill bit can be identified through the abrasion state identification model. The amount of wear of the drill bit may be determined by computer vision methods. Thus, by combining the deep learning method with the computer vision method, the abrasion condition of the drill bit can be automatically evaluated and analyzed. The speed is faster, the precision is higher, and the method is more scientific.

According to the drill bit abrasion detection method disclosed by the embodiment of the specification, a drill bit engineering information data set can be constructed. Advice may be provided for drill bit preferences at the drilling site through the drill bit engineering information dataset. In addition, if the wear state is an abnormal wear state, design advice may be determined based on the abnormal wear state. Thus, a data base, an experience support and a scheme design can be provided for the optimal design of the drill bit. The method is the beginning of intelligent analysis, design and manufacture of the drill bit, and can further release the accelerating potential of the difficult-to-drill stratum.

Please refer to fig. 4. The embodiment of the specification also provides a drill bit wear detection device, which comprises the following units.

An acquisition unit 41 for acquiring a bit image of a drilling site;

a processing unit 42 for preprocessing the bit image;

An identification unit 43 for identifying the wear state of the drill bit from the preprocessed drill bit image;

a determining unit 44, configured to determine a first image feature of the worn drill bit according to the preprocessed drill bit image if the identified wear state is a normal wear state; determining the abrasion loss of the drill bit according to the first image feature and the second image feature before abrasion of the drill bit; generating a drill bit abrasion detection report according to the abrasion loss; or if the identified wear state is an abnormal wear state, generating a drill wear detection report according to the identified abnormal wear state.

The embodiment of the specification also provides a computer device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the drill bit abrasion detection method when executing the computer program.

The present specification embodiment also provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the drill bit wear detection method described above.

Embodiments of the present specification also provide a computer program product comprising a computer program which, when executed by a processor, implements the drill bit wear detection method described above.

Those skilled in the art will appreciate that the present description may be provided as a method, system, or computer program product. The description may thus take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present description is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. The computer may be a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

Each functional unit in the embodiments of the present disclosure may be integrated in one processing unit, or each functional unit may exist alone physically, or two or more functional units may be integrated in one processing unit.

Those skilled in the art will appreciate that the descriptions of various embodiments are provided herein with respect to each of the embodiments, and that reference may be made to the relevant descriptions of other embodiments for parts of one embodiment that are not described in detail. In addition, it will be appreciated that those skilled in the art, upon reading the present specification, may conceive of any combination of some or all of the embodiments set forth herein without any inventive effort, and that such combination is within the scope of the disclosure and protection of the present specification.

Although the present specification is depicted by way of example, it will be appreciated by those skilled in the art that the above examples are merely intended to aid in understanding the core ideas of the present specification. Those skilled in the art will appreciate numerous modifications and variations therefrom. It is intended that the appended claims cover such modifications and variations as fall within the true spirit of this present description.

Claims

1. A method of detecting bit wear, comprising:

Acquiring a drill bit image of a drilling site;

preprocessing the drill bit image;

2. The method of claim 1, wherein in the step of identifying the wear state comprises:

inputting the drill bit image into a wear state identification model to obtain wear states of a plurality of parts in the drill bit;

the component is selected from the group consisting of a cutting tooth, a carcass, and a nozzle;

the wear amount includes an amount of wear of at least one of the plurality of components.

3. The method of claim 1, wherein the step of determining the first image feature comprises:

determining a first edge profile of the worn drill bit according to the drill bit image;

The step of determining the amount of wear includes:

comparing the first edge profile with the second edge profile before the drill bit is worn to obtain the variation of the edge profile;

and determining the abrasion loss of the drill bit according to the change quantity of the edge profile.

4. The method of claim 1, wherein the step of determining the first image feature comprises:

performing ellipse fitting on the first edge profile to obtain a worn first ellipse parameter;

the step of determining the amount of wear includes:

and determining the abrasion loss of the drill bit according to the first ellipse parameter and the second ellipse parameter before the drill bit is abraded.

5. The method according to claim 1, wherein the method further comprises:

acquiring engineering data of the drilling site;

and correspondingly storing engineering data, drill bit types and abrasion loss into a drill bit engineering information data set.

6. The method of claim 5, wherein the bit engineering information dataset comprises a plurality of sub-datasets; each sub-data set corresponds to engineering data and comprises a drill bit type and a plurality of corresponding abrasion loss;

The method further comprises the steps of:

in each sub-data set, wear trend data for a bit type is determined based on a plurality of wear amounts corresponding to the bit type.

7. The method of claim 6, wherein the method further comprises:

acquiring target engineering data of a target well;

selecting a corresponding sub-data set from the drill bit engineering information data set according to the target engineering data;

and selecting the drill bit type suitable for the target well from the selected sub-data set according to the wear trend data.

8. The method according to claim 1, wherein the method further comprises:

and if the identified wear state is an abnormal wear state, determining design advice of the drill bit according to the identified abnormal wear state.

9. A drill wear detection device, comprising:

the processing unit is used for preprocessing the drill bit image;

the determining unit is used for determining a first image characteristic of the worn drill bit according to the preprocessed drill bit image if the identified wear state is a normal wear state; the second determining unit is used for determining the abrasion loss of the drill bit according to the first image characteristic and the second image characteristic before abrasion of the drill bit; generating a drill bit abrasion detection report according to the abrasion loss; or if the identified wear state is an abnormal wear state, generating a drill wear detection report according to the identified abnormal wear state.

10. A drill bit wear detection system, comprising:

shooting equipment for acquiring drill bit images of a drilling site;

the drill bit abrasion detection equipment is used for preprocessing the drill bit image; identifying the wear state of the drill bit according to the preprocessed drill bit image; if the identified abrasion state is a normal abrasion state, determining a first image characteristic of the abraded drill bit according to the preprocessed drill bit image; determining the abrasion loss of the drill bit according to the first image feature and the second image feature before abrasion of the drill bit; generating a drill bit abrasion detection report according to the abrasion loss; or if the identified wear state is an abnormal wear state, generating a drill wear detection report according to the identified abnormal wear state.