CN115542337B - Method and device for monitoring rock debris returned from drilling well and storage medium - Google Patents
Method and device for monitoring rock debris returned from drilling well and storage medium Download PDFInfo
- Publication number
- CN115542337B CN115542337B CN202211497418.9A CN202211497418A CN115542337B CN 115542337 B CN115542337 B CN 115542337B CN 202211497418 A CN202211497418 A CN 202211497418A CN 115542337 B CN115542337 B CN 115542337B
- Authority
- CN
- China
- Prior art keywords
- terminal
- volume
- data
- rock debris
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/10—Processing, recording or transmission of stereoscopic or multi-view image signals
- H04N13/106—Processing image signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/275—Image signal generators from 3D object models, e.g. computer-generated stereoscopic image signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q9/00—Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar, Positioning & Navigation (AREA)
- Electromagnetism (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Excavating Of Shafts Or Tunnels (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The application discloses a rock debris monitoring method, device and storage medium for returning out of a well, which are used for monitoring the rock debris condition of an outlet of a vibrating screen in real time according to the rock debris volume, and realizing quantification of the rock debris returned out of the well, thereby achieving the effect of judging the cleanliness of a well drilling shaft or the underground abnormal condition. The method comprises the following steps: the terminal obtains a scanning result of the laser radar on the outlet of the drilling vibrating screen, and obtains video stream data obtained by shooting rock debris at the outlet of the drilling vibrating screen by the camera; the terminal generates 3D point cloud data according to the scanning result; the terminal calculates through the 3D point cloud data to obtain a first volume of rock debris; the terminal calculates through the video stream data to obtain a second volume of rock debris; the terminal monitors rock debris conditions of the vibrating screen opening according to the first volume and the second volume.
Description
Technical Field
The application relates to the technical field of petroleum drilling, in particular to a method and a device for monitoring rock debris returned from drilling and a storage medium.
Background
During drilling, after the underground rock is broken by the drill bit, the drilling fluid reaches the surface, and the rock fragments are called cuttings, also commonly referred to as "sand". In drilling, the drilling fluid is circulated to carry cuttings back to the surface, and the cuttings in the drilling fluid need to be separated by a drilling shaker.
During the drilling process, staff can perform irregular observation on the outlet of the vibrating screen, know the state of rock debris returned in the well, including estimation of total amount, estimation of size and shape, and the like, and judge whether abnormal conditions exist underground or the cleaning efficiency in a shaft by combining experience.
In the process of observing the vibrating screen outlet by a worker, if abnormal conditions are not found in time, serious engineering accidents such as drill sticking, even blowout and the like are easily caused.
Disclosure of Invention
In order to solve the technical problems, the application provides a rock debris monitoring method, a device and a storage medium for drilling return,
the first aspect of the application provides a rock debris monitoring method for drilling return, comprising the following steps:
the terminal obtains a scanning result of the laser radar on the outlet of the vibrating screen, and obtains video stream data obtained by shooting rock debris on the outlet of the vibrating screen by the camera;
the terminal generates 3D point cloud data according to the scanning result;
the terminal calculates through the 3D point cloud data to obtain a first volume of rock debris;
the terminal calculates through the video stream data to obtain a second volume of rock debris;
the terminal monitors rock debris conditions of the vibrating screen opening according to the first volume and the second volume.
Optionally, the monitoring of the rock debris condition of the vibrating screen port by the terminal according to the first volume and the second volume includes:
the terminal generates target rock debris monitoring data according to the first volume and the second volume;
the terminal inputs the video stream data into a pre-trained machine learning model so as to calculate a prediction result, wherein the machine learning model is a convergent model obtained by training 3D point cloud data, video stream data and data in drilling;
and the terminal monitors the rock debris condition of the vibrating screen opening according to the target rock debris monitoring data and the prediction result.
Optionally, the terminal generating target cuttings monitoring data from the first volume and the second volume includes:
the terminal calculates the difference value average between the first volume and the second volume;
and the terminal combines the data after the difference average calculation with the data in the current drilling well to obtain target rock debris monitoring data, and the data in the current drilling well is acquired in real time by the drilling working equipment and is sent to the terminal.
Optionally, the monitoring, by the terminal, of the rock debris condition of the vibrating screen opening according to the target rock debris monitoring data and the prediction result includes:
the terminal comprehensively judges whether abnormal conditions exist in the rock fragments at the vibrating screen opening according to the target rock fragment monitoring data and the prediction result;
if yes, the terminal sends out an abnormal warning and continues to monitor work;
if not, the terminal continues to monitor the work.
Optionally, the calculating, by the terminal, the first volume of the rock debris by using the 3D point cloud data includes:
the terminal performs plane segmentation on the 3D point cloud data;
the terminal uses an outlier algorithm to the data after the plane segmentation to remove redundancy of the data after the plane segmentation;
the terminal uses a clustering algorithm to the data with redundancy removed, and stacks adjacent rock fragments of the target rock fragments into a rock fragment stack of the same cluster;
the terminal calculates a first volume for each cluster of cuttings pile, respectively.
Optionally, the calculating, by the terminal, the second volume of the rock debris includes:
the terminal processes the video stream data by using an image binarization algorithm to obtain processed video stream data;
the terminal establishes a target dynamic model for the processed video stream data;
the terminal processes the target dynamic model by using a method of segmentation and clustering, difference compensation and outlier removal to obtain a processed dynamic model;
the terminal combines the processed dynamic model with an integral algorithm to calculate a second volume;
and the terminal combines the first volume and the second volume, establishes a loss function system and corrects the calculation result of the volume.
A second aspect of the present application provides a cuttings monitoring device for drilling returns, the device comprising:
the terminal acquires a scanning result of the laser radar on the outlet of the vibrating screen and acquires video stream data obtained by shooting rock debris on the outlet of the vibrating screen by the camera;
the generation unit is used for generating 3D point cloud data according to the scanning result by the terminal;
the terminal calculates through the 3D point cloud data to obtain a first volume of rock debris;
the second calculation unit is used for calculating the terminal through the video stream data to obtain a second volume of rock debris;
and the monitoring unit is used for monitoring the rock debris condition of the vibrating screen opening according to the first volume and the second volume by the terminal.
Optionally, the monitoring unit includes:
a generation subunit, wherein the terminal generates target rock debris monitoring data according to the first volume and the second volume;
the terminal inputs the video stream data into a pre-trained machine learning model so as to calculate a prediction result, wherein the machine learning model is a convergent model obtained by training 3D point cloud data, video stream data and data in drilling;
and the monitoring subunit is used for monitoring the rock debris condition of the vibrating screen opening according to the target rock debris monitoring data and the prediction result by the terminal.
A third aspect of the present application provides a cuttings monitoring device for drilling returns, the device comprising:
the system comprises a laser radar, a camera device, an explosion-proof shell, a processor, a memory, an input/output unit and a bus;
the laser radar, the camera equipment and the processor are connected with the memory, the input and output unit and the bus to form intelligent central control;
the explosion-proof housing is arranged outside the laser radar, the camera equipment and the intelligent central control;
the memory holds a program that the processor invokes to perform the method of any of the first aspect and optionally the method of the first aspect.
A fourth aspect of the present application provides a computer readable storage medium having a program stored thereon, which when executed on a computer performs the cuttings monitoring method of the first aspect and optionally of any of the first aspects.
From the above technical scheme, the application has the following advantages:
the laser radar can generate rock debris 3D point cloud data with depth information, the imaging equipment can more accurately record the condition of the vibrating screen outlet, and meanwhile, the terminal is used for assisting in processing the data, so that a discrimination warning system is established, and the volume and abnormal condition of the rock debris can be monitored in real time. If abnormal conditions of rock debris are found, the terminal can give alarm information timely, and safety in drilling construction is improved.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for monitoring cuttings returned from a well according to one embodiment of the present application;
FIG. 2 is a flow chart of a method for monitoring cuttings returned from a well according to another embodiment of the present application;
FIG. 3 is a schematic structural view of a drill return cuttings monitoring device provided in one embodiment of the present application;
FIG. 4 is a schematic structural view of a drill return cuttings monitoring device provided in accordance with another embodiment of the present application;
fig. 5 is a schematic general structural view of a drill return cuttings monitoring device provided in one embodiment of the present application.
Detailed Description
After the underground rock is broken by the drill bit, the drilling fluid reaches the surface, and these rock fragments are called cuttings, also commonly referred to as "sand". During the drilling process, geological personnel continuously collect and observe rock cuttings and restore the underground geological profile according to a certain sampling interval and delay time, which is called as a rock cuttings logging. The rock debris logging has the advantages of low cost, simplicity, easiness, convenience, easiness in understanding underground conditions, high data systematicness and the like, and is widely used in the exploration and development process of oil and gas fields.
In the prior art, rock debris sampling of a rock debris logging is carried out by a worker to a vibrating screen, a certain amount of rock debris falling from the lower part of a guide plate of the vibrating screen is connected by a screen disc, and then attached slurry is washed away, a white porcelain disc is filled, and a logging workshop is provided for logging engineers, geological engineers and the like to carry out rock sample qualitative and analysis. When the uphole footage is faster, the staff needs to continuously run at the logging room and the vibrating screen;
before and after the staff retrieves the detritus from the shale shaker, all need monitor shale shaker department detritus condition to reduce the potential safety hazard, avoid the emergence of engineering accident.
Based on the method, the rock debris monitoring method for drilling return is used for monitoring abnormal rock debris at the outlet of the vibrating screen in real time and giving out alarm information.
The drill cuttings monitoring method provided by the application can be applied to a terminal, a system and a server. For convenience of explanation, the terminal is taken as an execution body for illustration in the application.
It should be further noted that the terms "first," "second," and the like in the description and in the drawings are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order, or importance.
Referring to fig. 1, fig. 1 is a flow chart of an embodiment of a method for monitoring returned cuttings from a well, where the method includes:
101. the terminal obtains a scanning result of the laser radar on the outlet of the vibrating screen, and obtains video stream data obtained by shooting rock debris on the outlet of the vibrating screen by the camera;
102. the terminal generates 3D point cloud data according to the scanning result;
in this embodiment, a lidar is used to scan the debris conditions at the exit of the shaker. After the terminal issues the monitoring instruction, the laser radar starts to execute the scanning modeling task at a fixed rate of 5 times per second. After the scanning result is obtained, the scanning result is transmitted to the terminal, and the terminal continuously generates 3D point cloud data according to the scanning result.
The image pickup device is used for shooting the whole condition of the vibrating screen outlet. After the terminal issues a shooting instruction, the shooting device shoots. The frame rate of the acquired video stream data may generally be up to 30 frames per second, with 10 frames per second being taken for calculation in this embodiment.
The laser radar can scan to obtain original three-dimensional data, so that the data has depth information, and real rock debris conditions are digitized in more detail and accurately, thereby facilitating subsequent processing on a terminal. The camera equipment can be used for assisting the laser radar, video stream data and 3D cloud point data are combined, and data which are closer to the actual situation can be obtained more accurately.
103. The terminal calculates through the 3D point cloud data to obtain a first volume of rock debris;
in this embodiment, the terminal needs to process the 3D point cloud data. For example, firstly, carrying out plane segmentation on the 3D point cloud data, removing partial information with a vibrating screen as a plane, and highlighting a rock debris main body;
after carrying out plane segmentation on the 3D point cloud data, using an outlier algorithm on the data after plane segmentation to remove outlier noise points which are inconsistent in the periphery or the inside, increasing the calculation speed and enabling the data after plane segmentation to remove redundancy; then, using a clustering algorithm to enable the rock fragments to be piled up into the same cluster near the rock fragments, so that calculation is simplified;
and finally, calculating the volume of each cluster of rock debris piles respectively, constructing a convex hull according to the target point cloud, and obtaining rock debris volume data, namely the first volume.
104. The terminal calculates through the video stream data to obtain a second volume of rock debris;
in this embodiment, in order to assist the lidar in performing numerical adjustment on the monitoring data, binarization processing is required to be performed on the cuttings image in the video stream data, and the relevant threshold is dynamically adjusted, so that each video frame presents a corresponding result, and the result after the whole video stream data processing is the target dynamic model.
After the target dynamic model is obtained, the target objects containing the rock fragments are presented in a video frame and distributed in an irregular state, and then the calculation is carried out by using the method comprising segmentation and clustering (tightly connected rock fragment image piles are gathered to form a plurality of pile-shaped distributions), difference compensation (the image gathering piles are presented in a convex shape, partial concave compensation or partial large fluctuation edge smoothing and cutting are carried out), outlier removal and integration thought.
Let the first volume be X and the second volume be Y, a volume calculation function v=ax+by+β is constructed, where a, b, β are parameters that are continuously modified according to the monitored true values, so that the overall result tends to be true.
The target dynamic model is generated to facilitate subsequent computation of the volume. And obtaining the model of the target object after processing, namely obtaining the calculation content. After the data processing is performed by using a plurality of methods, the rock debris volume, namely the second volume, in the target object of the video stream data can be calculated more clearly.
After the 3D point cloud data and the video stream data are further processed, the 3D point cloud data and the video stream data are intuitively closer to the true value by utilizing calculation and correction of the volume.
105. The terminal monitors rock debris conditions of the vibrating screen opening according to the first volume and the second volume.
The laser radar can generate rock debris 3D point cloud data with depth information, the imaging equipment can more accurately record the condition of the vibrating screen outlet, and meanwhile, the terminal is used for assisting in processing data, so that a discrimination warning system is established, and the rock debris condition can be monitored in real time. If abnormal conditions of rock debris are found, the terminal can give alarm information timely, and safety in drilling construction is improved.
In practice, the step of monitoring the condition of the rock debris at the vibrating screen opening by the terminal according to the first volume and the second volume requires further processing, and another embodiment is provided herein to explain this in detail:
referring to fig. 2, this embodiment includes:
201. the terminal obtains a scanning result of the laser radar on the outlet of the vibrating screen, and obtains video stream data obtained by shooting rock debris on the outlet of the vibrating screen by the camera;
202. the terminal generates 3D point cloud data according to the scanning result;
203. the terminal calculates through the 3D point cloud data to obtain a first volume of rock debris;
204. the terminal calculates through the video stream data to obtain a second volume of rock debris;
205. The terminal generates target rock debris monitoring data according to the first volume and the second volume;
in this embodiment, the terminal first performs a difference average calculation on the first volume and the second volume, and then combines the data obtained by the difference average calculation with the data in the current well drilling to obtain the target cuttings monitoring data. The data in the current drilling is acquired in real time by the drilling working equipment and sent to the terminal.
Because the laser radar scanning and the shooting of the camera equipment have fixed rates, the terminal obtains multiple groups of data in fixed interval time. Therefore, the fixed interval time may be set to 1 to 2 seconds, and the data obtained in this fixed interval time is difference-averaged.
The electronic data obtained by radar scanning and shooting video can be different from the real data, and after difference value average processing, the electronic data can be corrected, so that the electronic data is continuously close to the real data, and the error is reduced.
206. The terminal inputs the video stream data into a pre-trained machine learning model so as to calculate a prediction result, wherein the machine learning model is a convergent model obtained by training 3D point cloud data, video stream data and data in drilling;
in the embodiment of the application, the machine learning model is a model which is prepared by simulation before the monitoring work starts, and in the normal monitoring work, the machine learning model can directly execute the work. The machine learning model is an image processing model, and the input model is image data, namely video stream data is required to be sent into the machine learning model for calculation, so that a prediction result is obtained.
For example, before monitoring, the data of the outlet of the vibrating screen needs to be scanned and shot, then step 205 is performed to obtain a large amount of rock debris data of the outlet of the current vibrating screen, and the rock debris data of the outlet of the current vibrating screen is used for building and training a machine learning model.
In the training process, a convolutional neural network (ResNet) is used as a backbone structure by a terminal, optimization strategies such as cosine annealing and wakeup are combined, generalization performance is smoothly increased by using a label, a plurality of data enhancement methods including CutMix and Mixup are introduced, and parameters are continuously adjusted to obtain an optimal model.
The construction of the machine learning model can calculate the data of the vibrating screen outlet under the normal condition of rock debris, so that the follow-up comparison with the monitoring data is facilitated, and whether the monitoring data are different or not is judged.
207. And the terminal monitors the rock debris condition of the vibrating screen opening according to the target rock debris monitoring data and the prediction result.
In the embodiment, the terminal comprehensively judges whether abnormal conditions exist in the rock fragments at the vibrating screen opening according to the target rock fragment monitoring data and the prediction result; if yes, the terminal sends out an abnormal warning and continues to monitor work; if not, the terminal continues to monitor the work.
The laser radar can generate rock debris 3D point cloud data with depth information, the imaging equipment can more accurately record the condition of the vibrating screen outlet, and meanwhile, the terminal is used for assisting in processing data, so that a discrimination warning system is established, and the rock debris condition can be monitored in real time. If abnormal conditions of rock debris are found, the terminal can give alarm information timely, and safety in drilling construction is improved.
The foregoing embodiments describe a method for monitoring drill cuttings returned from the present application, and the following describes embodiments of a device for monitoring drill cuttings returned from the present application and a storage medium thereof:
referring to fig. 3, this embodiment includes:
the acquisition unit 301 is used for acquiring a scanning result of the laser radar on the outlet of the vibrating screen and acquiring video stream data obtained by shooting rock debris on the outlet of the vibrating screen by the camera;
a generating unit 302, wherein the terminal generates 3D point cloud data according to the scanning result;
a first calculation unit 303, where the terminal calculates through the 3D point cloud data to obtain a first volume of rock debris;
a second calculating unit 304, where the terminal calculates through the video stream data to obtain a second volume of the rock debris;
and a monitoring unit 305, wherein the terminal monitors the rock debris condition of the vibrating screen according to the first volume and the second volume.
Optionally, the monitoring unit 305 includes:
a generation subunit 3051, the terminal generating target cuttings monitoring data from the first volume and the second volume;
the prediction subunit 3052 inputs the video stream data into a pre-trained machine learning model, so as to calculate a prediction result, wherein the machine learning model is a converged model obtained through training of 3D point cloud data, video stream data and data in drilling;
and the monitoring subunit 3053 is used for monitoring the rock debris condition of the vibrating screen according to the target rock debris monitoring data and the prediction result by the terminal.
Optionally, the generating subunit 3051 includes:
a difference averaging module 30511, wherein the terminal performs difference average calculation on the first volume and the second volume;
and the combination module 30512 is used for combining the data after the difference average calculation with the data in the current drilling to obtain target rock debris monitoring data, wherein the data in the current drilling is acquired in real time by the drilling working equipment and is sent to the terminal.
Optionally, the monitoring subunit 3053 includes:
the judging module 30531 is used for comprehensively judging whether the rock debris at the vibrating screen port has abnormal conditions or not according to the target rock debris monitoring data and the prediction result;
the warning module 30532 is used for sending out an abnormal warning by the terminal and continuing monitoring work;
and executing a module 30533, wherein the terminal continues to monitor the work.
Optionally, the first computing unit 303 includes:
a plane segmentation subunit 3031, the terminal performs plane segmentation on the 3D point cloud data;
an outlier subunit 3032, where the terminal uses an outlier algorithm to the data after the plane segmentation to remove redundancy from the data after the plane segmentation;
a clustering algorithm subunit 3033, wherein the terminal uses a clustering algorithm to the data with redundancy removed to stack adjacent rock fragments of the target rock fragments into a same cluster of rock fragment stacks;
the first calculating subunit 3034, the terminal calculates the first volume for each cluster of rock debris pile respectively.
Optionally, the second computing unit 304 includes:
an image processing subunit 3041, where the terminal processes the video stream data by using an image binarization algorithm to obtain processed video stream data;
a dynamic model subunit 3042, where the terminal establishes a target dynamic model for the processed video stream data;
the model processing subunit 3043 is used for processing the target dynamic model by using a method of segmentation, clustering, difference compensation and outlier removal to obtain a processed dynamic model;
a second calculating subunit 3044, where the terminal combines the processed dynamic model with an integration algorithm to calculate a second volume;
and a correction subunit 3045, wherein the terminal combines the first volume and the second volume, and establishes a loss function system, so as to correct the calculation result of the volume.
Referring to fig. 4, the present application further provides a drill return cuttings monitoring device, including:
a laser radar 401, an image pickup apparatus 402, an explosion-proof housing 403, a processor 404, a memory 405, an input-output unit 406, and a bus 407;
the laser radar 401, the camera device 402 and the processor 404 are connected with the memory 405, the input/output unit 406 and the bus 407 to form an intelligent central control;
the explosion-proof housing 403 is disposed outside the laser radar 401, the image pickup apparatus 402, and the intelligent central control;
the memory 405 holds a program that the processor 404 invokes to perform any of the above-described cuttings monitoring methods of drilling returns.
Referring to fig. 5, the present application provides a general structure of a rock debris apparatus according to an embodiment, including:
a laser radar 401, a camera device 402, an explosion-proof housing 403, a vibrating screen 501, and an explosion-proof sleeve 502;
the laser radar 401 and the intelligent central control are arranged inside the explosion-proof housing 403;
the laser radar 401 and the camera device 402 are arranged above the vibrating screen 501 and are used for scanning and shooting rock debris conditions at the outlet of the vibrating screen 501;
wires such as bus 407 are disposed inside the explosion proof enclosure 502.
The present application also relates to a computer readable storage medium having a program stored thereon, characterized in that the program, when run on a computer, causes the computer to perform any of the methods as above.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (RAM, random access memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Claims (7)
1. A method of monitoring drill returns, the method comprising:
the terminal obtains a scanning result of the laser radar on the outlet of the vibrating screen, and obtains video stream data obtained by shooting rock debris on the outlet of the vibrating screen by the camera;
the terminal generates 3D point cloud data according to the scanning result;
the terminal calculates through the 3D point cloud data to obtain a first volume of rock debris;
the terminal calculates through the video stream data to obtain a second volume of rock debris;
the terminal monitors rock debris conditions of the vibrating screen opening according to the first volume and the second volume;
the terminal monitors the rock debris condition of the vibrating screen opening according to the first volume and the second volume and comprises:
the terminal generates target rock debris monitoring data according to the first volume and the second volume;
the terminal inputs the video stream data into a pre-trained machine learning model so as to calculate a prediction result, wherein the machine learning model is a convergent model obtained by training 3D point cloud data, video stream data and data in drilling, and the prediction result represents the rock debris condition of the machine learning model for outputting prediction to a vibrating screen outlet;
the terminal monitors the rock debris condition of the vibrating screen opening according to the target rock debris monitoring data and the prediction result;
the terminal generating target cuttings monitoring data from the first volume and the second volume includes:
the terminal calculates the difference value average between the first volume and the second volume;
and the terminal combines the data after the difference average calculation with the data in the current drilling well to obtain target rock debris monitoring data, and the data in the current drilling well is acquired in real time by the drilling working equipment and is sent to the terminal.
2. The method of monitoring drill return cuttings as claimed in claim 1, wherein the terminal monitoring cuttings conditions of a shaker screen based on the target cuttings monitoring data and the predicted results comprises:
the terminal comprehensively judges whether abnormal conditions exist in the rock fragments at the vibrating screen opening according to the target rock fragment monitoring data and the prediction result;
if yes, the terminal sends out an abnormal warning and continues to monitor work;
if not, the terminal continues to monitor the work.
3. The method of monitoring returned cuttings from a well of claim 1, wherein the computing by the terminal from the 3D point cloud data to obtain a first volume of cuttings comprises:
the terminal performs plane segmentation on the 3D point cloud data;
the terminal uses an outlier algorithm to the data after the plane segmentation to remove redundancy of the data after the plane segmentation;
the terminal uses a clustering algorithm to the data with redundancy removed, and stacks adjacent rock fragments of the target rock fragments into a rock fragment stack of the same cluster;
the terminal calculates a first volume for each cluster of cuttings pile, respectively.
4. The method of monitoring drill returns of claim 1, wherein the terminal calculating from the video stream data to obtain a second volume of drill returns comprises:
the terminal processes the video stream data by using an image binarization algorithm to obtain processed video stream data;
the terminal establishes a target dynamic model for the processed video stream data;
the terminal processes the target dynamic model by using a method of segmentation and clustering, difference compensation and outlier removal to obtain a processed dynamic model;
the terminal combines the processed dynamic model with an integral algorithm to calculate a second volume;
and the terminal combines the first volume and the second volume, establishes a loss function system and corrects the calculation result of the volume.
5. A cuttings monitor apparatus for drilling returns, comprising:
the terminal acquires a scanning result of the laser radar on the outlet of the vibrating screen and acquires video stream data obtained by shooting rock debris on the outlet of the vibrating screen by the camera;
the generation unit is used for generating 3D point cloud data according to the scanning result by the terminal;
the terminal calculates through the 3D point cloud data to obtain a first volume of rock debris;
the second calculation unit is used for calculating the terminal through the video stream data to obtain a second volume of rock debris;
the monitoring unit is used for monitoring the rock debris condition of the vibrating screen opening according to the first volume and the second volume by the terminal;
the monitoring unit includes:
a generation subunit, wherein the terminal generates target rock debris monitoring data according to the first volume and the second volume;
the terminal inputs the video stream data into a pre-trained machine learning model so as to calculate a prediction result, wherein the machine learning model is a convergent model obtained by training 3D point cloud data, video stream data and data in drilling;
the monitoring subunit monitors the rock debris condition of the vibrating screen opening according to the target rock debris monitoring data and the prediction result by the terminal;
the generation subunit includes:
the difference value average module is used for carrying out difference value average calculation on the first volume and the second volume by the terminal;
and the combination module is used for combining the data after the difference value average calculation with the data in the current drilling well to obtain target rock debris monitoring data, and the data in the current drilling well is acquired in real time by the drilling working equipment and is sent to the terminal.
6. A drill return cuttings monitoring device, the device comprising:
the system comprises a laser radar, a camera device, an explosion-proof shell, a processor, a memory, an input/output unit and a bus;
the laser radar, the camera equipment and the processor are connected with the memory, the input and output unit and the bus to form intelligent central control;
the explosion-proof housing is arranged outside the laser radar, the camera equipment and the intelligent central control;
the memory holds a program which the processor invokes to perform a cuttings monitoring method of drilling returns as claimed in any one of claims 1 to 4.
7. A computer readable storage medium, characterized in that it has stored thereon a program which, when executed on a computer, performs the cuttings monitoring method of drilling returns according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211497418.9A CN115542337B (en) | 2022-11-28 | 2022-11-28 | Method and device for monitoring rock debris returned from drilling well and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211497418.9A CN115542337B (en) | 2022-11-28 | 2022-11-28 | Method and device for monitoring rock debris returned from drilling well and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115542337A CN115542337A (en) | 2022-12-30 |
| CN115542337B true CN115542337B (en) | 2023-05-12 |
Family
ID=84722399
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211497418.9A Active CN115542337B (en) | 2022-11-28 | 2022-11-28 | Method and device for monitoring rock debris returned from drilling well and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115542337B (en) |
Family Cites Families (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3802259A (en) * | 1970-11-27 | 1974-04-09 | Marathon Oil Co | Well logging method |
| CN103308418A (en) * | 2013-06-25 | 2013-09-18 | 中国海洋石油总公司 | Method for monitoring sand carrying effect of drilling fluid |
| CN107109915A (en) * | 2014-11-03 | 2017-08-29 | 贝克休斯公司 | From subsurface formations in-situ retorting ore |
| CN104675382A (en) * | 2015-02-13 | 2015-06-03 | 中国石油集团渤海钻探工程有限公司 | Rock debris return monitoring system and method during gas drilling |
| GB2583843B (en) * | 2018-02-05 | 2022-05-25 | Halliburton Energy Services Inc | Volume, size, and shape analysis of downhole particles |
| WO2019160859A1 (en) * | 2018-02-13 | 2019-08-22 | Halliburton Energy Services, Inc. | Shaker vibration and downhole cuttings measurement and processing |
| CN108442927B (en) * | 2018-03-12 | 2020-05-01 | 中国地质大学（北京） | Rock debris porosity measuring method and device for field logging application and application |
| NO20201171A1 (en) * | 2018-06-04 | 2020-10-26 | Halliburton Energy Services Inc | Velocity measurement of drilled cuttings on a shaker |
| WO2020005850A1 (en) * | 2018-06-25 | 2020-01-02 | Motive Drilling Technologies, Inc. | System and method for well drilling control based on borehole cleaning |
| CN208894575U (en) * | 2018-07-16 | 2019-05-24 | 广东融泉汇混凝土有限公司 | A kind of architectural engineering sandstone screening plant |
| CN110118526B (en) * | 2019-03-08 | 2020-12-08 | 浙江中海达空间信息技术有限公司 | Shipborne sand volume automatic calculation method supporting real-time monitoring |
| CN110043252B (en) * | 2019-05-24 | 2022-01-11 | 成都理工大学 | Rock debris image characteristic monitoring device while drilling |
| CN110346349A (en) * | 2019-07-30 | 2019-10-18 | 辽宁石油化工大学 | Landwaste detection device |
| GB2592553B (en) * | 2019-09-17 | 2022-03-30 | Equinor Energy As | Apparatus and method for analysing drilling fluid |
| CN112696186B (en) * | 2019-10-18 | 2024-04-16 | 中国石油化工股份有限公司 | Method and system for automatically identifying drilling cuttings |
| CN110887440B (en) * | 2019-12-03 | 2021-05-04 | 西安科技大学 | Real-time measuring method and device for volume of earth of excavator bucket based on structured light |
| US11015404B1 (en) * | 2019-12-16 | 2021-05-25 | Halliburton Energy Services, Inc. | Cuttings volume measurement away from shale shaker |
| CN111275753B (en) * | 2020-01-17 | 2023-03-24 | 中国建筑第八工程局有限公司 | Method for measuring volume of sand and stone in carriage |
| CN112001102B (en) * | 2020-07-27 | 2022-04-15 | 中南大学 | Ore drawing automatic control method, controller, ore drawing machine, system and storage medium |
| CN114352255B (en) * | 2020-09-30 | 2023-12-22 | 中国石油天然气集团有限公司 | Method and device for monitoring state of oil and gas drilling shaft |
| CN112184707A (en) * | 2020-10-30 | 2021-01-05 | 三峡大学 | Method and system for judging earth and stone load of muck vehicle based on point cloud data |
| CN114016999B (en) * | 2021-10-15 | 2024-06-25 | 中国石油天然气集团有限公司 | Borehole cleaning quantitative evaluation method based on rock debris return situation |
| CN114812388B (en) * | 2022-04-01 | 2023-11-17 | 西安理工大学 | Petroleum drilling rock debris online volume detection system based on depth camera |
| CN114963991A (en) * | 2022-07-04 | 2022-08-30 | 湖南理工学院 | Hull stone volume measurement system based on three-dimensional reconstruction |
| CN115199262A (en) * | 2022-08-02 | 2022-10-18 | 四川恒铭泽石油天然气工程有限公司 | Ultra-deep well underground condition detection and early warning method and system |
-
2022
- 2022-11-28 CN CN202211497418.9A patent/CN115542337B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115542337A (en) | 2022-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11697969B2 (en) | Method for predicting drill bit wear | |
| EP3437067B1 (en) | Automated core description | |
| KR102011227B1 (en) | Methods, and apparatus for monitoring failures of computer storage media, computer program products, and wind generator sets | |
| CN112148772A (en) | Alarm root cause identification method, device, equipment and storage medium | |
| US10822923B2 (en) | Resource identification using historic well data | |
| WO2015126537A2 (en) | Apparatus, system and methods for alerting of abnormal drilling conditions | |
| WO2015060865A1 (en) | Real-time risk prediction during drilling operations | |
| CN108124489B (en) | Information processing method, apparatus, cloud processing device and computer program product | |
| US20170306726A1 (en) | Stuck pipe prediction | |
| CN103606221A (en) | Fault automatic diagnostic method of counter and device | |
| Li et al. | Incipient fault detection for geological drilling processes using multivariate generalized Gaussian distributions and Kullback–Leibler divergence | |
| CN112031839B (en) | Mine pressure space-time bi-periodic prediction method, device and equipment under limited data condition | |
| CN116343436A (en) | Landslide detection method, landslide detection device, landslide detection equipment and landslide detection medium | |
| CN115542337B (en) | Method and device for monitoring rock debris returned from drilling well and storage medium | |
| CN115878598A (en) | Monitoring data processing method, electronic device and storage medium | |
| CN113645215A (en) | Method, device, equipment and storage medium for detecting abnormal network traffic data | |
| CN114817850A (en) | Method and system for anomaly detection of bolt tightening data | |
| CN112664410A (en) | Big data-based modeling method for unit online monitoring system | |
| CN116245838A (en) | Monitoring method, monitoring device, equipment and medium for rock-soil exploration behaviors | |
| CN116823233A (en) | User data processing method and system based on full-period operation and maintenance | |
| CN115239108B (en) | Weak broken surrounding rock sensing method based on TBM real-time broken rock data | |
| US11514719B1 (en) | Systems and methods for hierarchical facial image clustering | |
| US11880427B2 (en) | Time-series data processing method, corresponding processing system, device and computer program product | |
| JP7239824B2 (en) | Image inspection system, image inspection device and image inspection program | |
| JP2018022305A (en) | Boundary value determination program, boundary value determination method, and boundary value determination device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zhang Wei Inventor after: Xu Hao Inventor after: Gao Yuan Inventor after: Zeng Qijun Inventor after: Liu Ling Inventor before: Xu Hao Inventor before: Gao Yuan Inventor before: Zeng Qijun Inventor before: Liu Ling |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |