CN111126469B - Downhole tool identification method, downhole tool identification device and electronic equipment - Google Patents
Downhole tool identification method, downhole tool identification device and electronic equipment Download PDFInfo
- Publication number
- CN111126469B CN111126469B CN201911302685.4A CN201911302685A CN111126469B CN 111126469 B CN111126469 B CN 111126469B CN 201911302685 A CN201911302685 A CN 201911302685A CN 111126469 B CN111126469 B CN 111126469B
- Authority
- CN
- China
- Prior art keywords
- magnetic positioning
- tool
- downhole tool
- classification model
- training sample
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000013145 classification model Methods 0.000 claims abstract description 108
- 238000002372 labelling Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims description 128
- 230000008569 process Effects 0.000 claims description 10
- 238000012360 testing method Methods 0.000 abstract description 20
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000010200 validation analysis Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000004807 localization Effects 0.000 description 7
- 238000012795 verification Methods 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000000877 morphologic effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001595 flow curve Methods 0.000 description 2
- 230000004907 flux Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geophysics And Detection Of Objects (AREA)
- Image Analysis (AREA)
Abstract
The application discloses an identification method and device for an underground tool and electronic equipment. The method comprises the following steps: the method comprises the steps of obtaining a magnetic positioning image of a downhole tool, inputting the magnetic positioning image of the downhole tool into a classification model which is trained in advance, and obtaining a tool type to which the magnetic positioning image of the downhole tool output by the classification model belongs, wherein the classification model is trained by utilizing magnetic positioning sample images of various downhole tools and tool type labeling information. Based on the technical scheme disclosed by the application, the magnetic positioning curve section generated by the downhole tool can be accurately and efficiently identified, and the workload of well testing personnel is reduced.
Description
Technical Field
The application belongs to the technical field of oil and gas reservoir exploration and development, and particularly relates to an identification method, an identification device and electronic equipment of an underground tool.
Background
The magnetic positioning curve is the basic data in the logging data, and is mainly used for determining the position of each downhole tool.
Currently, the actual position of each downhole tool is determined by mainly identifying the magnetic positioning curve segments corresponding to the downhole tools in the magnetic positioning curve based on experience by a logging staff, and then further identifying which downhole tool each magnetic positioning curve segment is specifically generated by. And then, determining the deviation between the actual position and the design position of each downhole tool, so as to adjust the position of each downhole tool, ensure that the actual position and the design position of each downhole tool are within an allowable error range and ensure the operation quality.
It can be seen that in the existing technical scheme, the efficiency is low, the labor capacity of the well testing personnel is high, the influence of human factors is high, and the accuracy is adversely affected by judging which type of downhole tool the magnetic positioning curve section is generated according to the experience of the well testing personnel.
Disclosure of Invention
In view of the foregoing, it is an object of the present application to provide a method, an apparatus and an electronic device for identifying a downhole tool, so as to accurately and efficiently identify which downhole tool the magnetically positioned curve segment generated by the downhole tool is generated from, while reducing the workload of a well tester.
In order to achieve the above purpose, the present application provides the following technical solutions:
in one aspect, the present application provides a method of identifying a downhole tool, comprising:
obtaining a magnetic positioning image of a downhole tool, the magnetic positioning image of the downhole tool being: a magnetic positioning curve section corresponding to the downhole tool is cut from the magnetic positioning curve of the well;
inputting the magnetic positioning image of the downhole tool into a classification model which is trained in advance, and obtaining the tool category to which the magnetic positioning image of the downhole tool output by the classification model belongs;
the classification model is obtained by training magnetic positioning sample images of various downhole tools and tool type labeling information.
Optionally, in the above method, the obtaining a magnetic positioning image of the downhole tool includes:
obtaining a magnetic positioning curve of the well;
receiving at least one set of depth information, wherein each set of depth information includes a start depth and an end depth;
based on the starting depth and the ending depth in each set of depth information, magnetic localization curve segments corresponding to each set of depth information are truncated from the magnetic localization curve of the well.
Optionally, on the basis of the method, the method further comprises:
obtaining depth information of a magnetic positioning image of the downhole tool;
and labeling the magnetic positioning image of the downhole tool by utilizing the tool type and the depth information output by the classification model.
Optionally, the training process of the classification model includes:
obtaining a training sample set, wherein the training sample set comprises training samples of a plurality of downhole tools, each training sample is a magnetic positioning sample image of one downhole tool, and each training sample has tool class marking information for representing the downhole tool to which the training sample belongs;
carrying out category prediction on the training sample by utilizing a pre-constructed classification model to obtain a tool category prediction result of the training sample;
and adjusting model parameters of the classification model according to the tool class marking information and the tool class prediction result of the training sample until the adjusted classification model meets the preset convergence condition.
Optionally, the difference between the number of training samples of the plurality of downhole tools in the training sample set is within a preset range.
In another aspect, the present application provides an identification device for a downhole tool, comprising:
a magnetic positioning image acquisition unit for acquiring a magnetic positioning image of a downhole tool, the magnetic positioning image of the downhole tool being: a magnetic positioning curve section corresponding to the downhole tool is cut from the magnetic positioning curve of the well;
the identification unit is used for inputting the magnetic positioning image of the downhole tool into a classification model which is trained in advance, and obtaining the tool category to which the magnetic positioning image of the downhole tool output by the classification model belongs;
the classification model is obtained by training magnetic positioning sample images of various downhole tools and tool type labeling information.
Optionally, the magnetic positioning image acquisition unit is specifically configured to:
obtaining a magnetic positioning curve of the well; receiving at least one set of depth information, wherein each set of depth information includes a start depth and an end depth; based on the starting depth and the ending depth in each set of depth information, magnetic localization curve segments corresponding to each set of depth information are truncated from the magnetic localization curve of the well.
Optionally, on the basis of the device, the device further comprises a magnetic positioning image labeling unit;
the magnetic positioning image labeling unit is used for: and obtaining depth information of the magnetic positioning image of the downhole tool, and labeling the magnetic positioning image of the downhole tool by utilizing the tool type and the depth information output by the classification model.
Optionally, on the basis of the device, the device further comprises a model training unit;
the model training unit is used for: obtaining a training sample set, wherein the training sample set comprises training samples of a plurality of downhole tools, each training sample is a magnetic positioning sample image of one downhole tool, and each training sample has tool class marking information for representing the downhole tool to which the training sample belongs; carrying out category prediction on the training sample by utilizing a pre-constructed classification model to obtain a tool category prediction result of the training sample; and adjusting model parameters of the classification model according to the tool class marking information and the tool class prediction result of the training sample until the adjusted classification model meets the preset convergence condition.
In another aspect, the present application provides an electronic device comprising a processor and a memory;
the processor is used for calling and executing the program stored in the memory;
the memory is used for storing the program, and the program is at least used for:
obtaining a magnetic positioning image of a downhole tool, the magnetic positioning image of the downhole tool being: a magnetic positioning curve section corresponding to the downhole tool is cut from the magnetic positioning curve of the well;
inputting the magnetic positioning image of the downhole tool into a classification model which is trained in advance, and obtaining the tool category to which the magnetic positioning image of the downhole tool output by the classification model belongs;
the classification model is obtained by training magnetic positioning sample images of various downhole tools and tool type labeling information.
Therefore, the beneficial effects of the application are as follows:
according to the method for identifying the downhole tool, the magnetic positioning sample images and tool class marking information of various downhole tools are used in advance for training the classification model, the magnetic positioning images of the downhole tools to be identified are input into the classification model for completing training, the tool class to which the magnetic positioning images of the downhole tools output by the classification model belong is obtained, and the identification of the downhole tools is completed. Based on the identification method of the downhole tool disclosed by the application, the magnetic positioning curve section generated by the downhole tool can be identified efficiently, particularly by which downhole tool, the workload of well testing personnel is reduced, and the influence of human factors is removed, so that the identification result has high accuracy.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present application, and 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 of identifying a downhole tool disclosed herein;
FIG. 2 is a schematic illustration of flow curves and magnetic positioning curves in the log data disclosed herein;
FIG. 3-1 is a schematic illustration of a corresponding magnetically localized curved segment of a collar disclosed herein;
FIG. 3-2 is a schematic illustration of a corresponding magnetically positioned curve segment of a packer disclosed herein;
3-3 are schematic illustrations of corresponding magnetically positioned curve segments of the water dispenser disclosed herein;
FIG. 4 is a schematic illustration of the presently disclosed addition of downhole tool identification in a magnetic localization curve;
FIG. 5 is a flow chart of a training method of the classification model disclosed in the present application;
FIG. 6 is a schematic diagram of an identification device for a downhole tool according to the present disclosure;
fig. 7 is a hardware configuration diagram of an electronic device disclosed in the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The application provides an identification method, an identification device and electronic equipment of a downhole tool, so that a magnetic positioning curve segment generated by the downhole tool is accurately and efficiently identified, and the workload of a well testing person is reduced.
Referring to fig. 1, fig. 1 is a flow chart of a method of identifying a downhole tool as disclosed herein. The method comprises the following steps:
step S101: a magnetic positioning image of the downhole tool is obtained.
Wherein the magnetic positioning image of the downhole tool is: and a magnetic positioning curve section corresponding to the downhole tool is cut from the magnetic positioning curve of the well.
The magnetic positioning logging device adopts the electromagnetic induction principle and mainly comprises a permanent magnet and a measuring coil. When the magnetic positioning logging device moves along the shaft, the magnetic resistance of the medium around the magnetic positioning logging device changes due to the change of the inner diameter and the pipe wall thickness of the downhole tool in the shaft, so that magnetic force lines in the measuring coil are redistributed, the magnetic flux density changes, and induced electromotive force is generated at the two ends of the measuring coil. The larger the magnetic flux change rate, the larger the induced electromotive force generated in the measurement coil.
FIG. 2 is a schematic diagram of flow curves and magnetic positioning curves in the log data disclosed herein. The magnetic positioning profile of the well is generated by a magnetic positioning logging device.
In addition, the magnetic positioning curve segments corresponding to different types of downhole tools have specific morphological characteristics. Fig. 3-1 is a schematic diagram of a magnetic positioning curve segment corresponding to a collar disclosed in the present application, fig. 3-2 is a schematic diagram of a magnetic positioning curve segment corresponding to a packer disclosed in the present application, and fig. 3-3 is a schematic diagram of a magnetic positioning curve segment corresponding to a water distributor disclosed in the present application. In fig. 3-1, 3-2 and 3-3, the abscissa represents depth and the ordinate represents induced electromotive force. It should be noted that the downhole tool may include a production distributor and a guide cone in addition to the collar, packer and water distributor.
In practice, the magnetic positioning curve segment corresponding to the downhole tool may be manually cut from the magnetic positioning curve of the well, or the magnetic positioning curve segment corresponding to the downhole tool may be cut from the magnetic positioning curve of the well by the electronic device according to morphological features of the magnetic positioning curve segment corresponding to the downhole tool.
Step S102: and inputting the magnetic positioning image of the downhole tool into a classification model which is trained in advance, and obtaining the tool category to which the magnetic positioning image of the downhole tool output by the classification model belongs. The classification model is obtained by training magnetic positioning sample images of various downhole tools and tool class marking information.
The morphological characteristics of the magnetic positioning curve segments generated by the same class of downhole tools have commonalities, while the morphological characteristics of the magnetic positioning curve segments generated by different classes of downhole tools are different. The classification model in the application is a neural network model and is obtained by training magnetic positioning sample images of various downhole tools and tool class marking information. The trained classification model has the ability to trend tool class predictions for the magnetically positioned images toward actual tool classes.
According to the method for identifying the downhole tool, the magnetic positioning sample images and tool class marking information of various downhole tools are used in advance for training the classification model, the magnetic positioning images of the downhole tools to be identified are input into the classification model for completing training, the tool class to which the magnetic positioning images of the downhole tools output by the classification model belong is obtained, and the identification of the downhole tools is completed. Based on the identification method of the downhole tool disclosed by the application, the magnetic positioning curve section generated by the downhole tool can be identified efficiently, particularly by which downhole tool, the workload of well testing personnel is reduced, and the influence of human factors is removed, so that the identification result has high accuracy.
In the method shown in fig. 1 of the present application, the following scheme may be adopted to obtain a magnetic positioning image of the downhole tool:
(1) Obtaining the magnetic positioning curve of the well.
(2) At least one set of depth information is received, wherein each set of depth information includes a start depth and an end depth.
(3) And intercepting magnetic positioning curve segments corresponding to the sets of depth information from the magnetic positioning curve of the well based on the starting depth and the ending depth in each set of depth information. The cut magnetic positioning curve section is the magnetic positioning curve of the downhole tool.
For example, a set of depth information having a starting depth of 1068 meters and an ending depth of 1070 meters, then a magnetic positioning curve segment having a depth between 1068 meters and 1070 meters (inclusive) is taken from the magnetic positioning curve of the well, the magnetic positioning curve segment being a magnetic positioning curve corresponding to a downhole tool.
On the basis of the method shown in fig. 1 of the present application, the following steps may be further set:
obtaining depth information of a magnetic positioning image of the downhole tool;
and labeling the magnetic positioning image of the downhole tool by using the tool type and the depth information output by the classification model.
That is, after determining the tool type to which the magnetic positioning image of the downhole tool belongs, depth information of the magnetic positioning image of the downhole tool is obtained, and the tool type and the depth information to which the magnetic positioning image of the downhole tool belongs are labeled.
Based on the above, the well tester can intuitively see what kind of downhole tool is set at certain depths downhole.
In practice, the tool category to which the magnetic positioning image of the downhole tool belongs may be represented by an identifier.
Referring to fig. 4, fig. 4 is a schematic diagram of the downhole tool identifier added to the magnetic positioning curve disclosed in the present application. In fig. 4, 401 is the identification of the packer, 402 is the identification of the collar, and 403 is the identification of the water distributor.
The training process of the classification model used in the above embodiment is described below.
Referring to fig. 5, fig. 5 is a flowchart of a training method of the classification model disclosed in the present application. The method comprises the following steps:
step S501: a training sample set is obtained.
The training sample set includes training samples of a plurality of downhole tools. Each training sample is a magnetic positioning sample image of a downhole tool, and each training sample has tool type labeling information for representing the downhole tool to which the training sample belongs.
Preferably, the difference between the number of training samples of the plurality of downhole tools in the training sample set is within a preset range. That is, the number of training samples for the plurality of downhole tools should be balanced in the training sample set to avoid bias in classification results for the classification model toward tool classes with a greater number of training samples due to imbalance in the number of training samples.
For example, the training sample set includes training samples of a collar, packer, water distributor, production distributor, and guide cone, and the difference between the number of training samples of the 5 downhole tools needs to be within a preset range.
Optionally, the number of training samples for the plurality of downhole tools is the same in the training sample set.
Step S502: and carrying out category prediction on the training sample by utilizing a pre-constructed classification model to obtain a tool category prediction result of the training sample.
Step S503: and adjusting model parameters of the classification model according to tool class marking information and tool class prediction results of the training sample until the adjusted classification model meets preset convergence conditions.
The initial model parameters of the pre-constructed classification model are all self-defined values, and the process of training the classification model is the process of optimizing the model parameters so that the classification model gradually converges and the accuracy of the prediction result gradually improves.
In one possible implementation, the preset convergence condition is: the value of the loss function of the classification model is less than a preset value.
The loss function value of the classification model characterizes the prediction accuracy of the classification model, and the smaller the loss function value is, the higher the prediction accuracy of the classification model is, otherwise, the larger the loss function value is, and the lower the prediction accuracy of the classification model is.
Alternatively, the loss function of the classification model may employ a cross entropy function.
In another possible implementation, the preset convergence condition is: the value of the loss function of the classification model is no longer reduced or the prediction accuracy of the classification model is no longer increased.
According to the training method for the classification model shown in fig. 5, firstly, a training sample set is obtained, the training sample set comprises training samples of various downhole tools, each training sample is a magnetic positioning sample image of one downhole tool, each training sample is provided with tool type marking information, then, the classification model is trained based on the training samples, when preset convergence conditions are met, the deviation between a tool type predicting result obtained by analyzing the training samples and the tool type marking information by the classification model is sufficiently small, the training process of the classification model is completed, and the classification model after training can accurately predict the type of the downhole tool to be identified.
In another embodiment, a method of training a classification model includes:
(1) Obtaining a training sample set, a validation sample set and a test sample set.
The training sample set comprises a plurality of training samples, each training sample is a magnetic positioning sample image of a downhole tool, and in addition, each training sample is provided with tool type marking information.
The validation sample set includes a plurality of validation samples, each validation sample being a magnetically localized sample image of a downhole tool, and further each validation sample having tool class labeling information, in practice, for the validation samples in the validation sample set, their tool classes are labeled manually.
The test sample set includes a plurality of test samples, each test sample being a magnetically positioned sample image of a downhole tool, and further each test sample having tool class labeling information, in practice, for the test samples in the test sample set, their tool classes are labeled manually.
(2) And constructing a plurality of classification models. Wherein the architecture of the plurality of classification models is different.
(3) For each classification model, performing:
1) Carrying out category prediction on the training sample by utilizing a pre-constructed classification model to obtain a tool category prediction result of the training sample; according to tool class marking information and tool class prediction results of the training samples, model parameters of the classification model are adjusted until the prediction accuracy of the classification model is not increased any more;
2) Performing category prediction on the verification samples in the verification sample set by using the classification model to obtain a tool category prediction result of the verification samples; determining the prediction accuracy of the classification model for the verification sample set according to the tool class labeling information and the tool class prediction result of the verification sample;
if the prediction accuracy for the verification sample set reaches a preset threshold, performing: carrying out category prediction on the test samples in the test sample set by using the classification model to obtain a tool category prediction result of the test samples; determining the prediction accuracy of the classification model for the test sample set according to the tool class labeling information and the tool class prediction result of the test sample, and executing the step (4);
if the prediction accuracy for the validation sample set does not reach the preset threshold, performing: and (3) adjusting super parameters of the classification model or adjusting the architecture of the classification model, and executing the step 1) and the subsequent steps again aiming at the adjusted classification model.
(4) And taking the classification model with highest prediction accuracy aiming at the test sample set as an optimal model.
And then, performing category analysis of the downhole tool by using the optimal network.
In an alternative implementation, the classification model in the present application employs a Deep Neural Network (DNN) or a Recurrent Neural Network (RNN).
In a preferred implementation, the classification model in the present application employs a Convolutional Neural Network (CNN). The convolutional neural network has strong capability of extracting characteristics and a deep network structure, and can improve the learning capability and model performance of the network. Compared with the classification model adopting the deep neural network and the cyclic neural network, the classification model adopting the convolutional neural network is faster in processing, and can greatly improve the efficiency of class analysis.
The present application provides a method for identifying a downhole tool, and correspondingly, the present application also provides an apparatus for identifying a downhole tool, and descriptions of the two may be referred to each other in the specification.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an identification device for generating a logging tool as disclosed in the present application. The apparatus comprises a magnetic positioning image acquisition unit 601 and an identification unit 602.
Wherein:
the magnetic positioning image acquisition unit 601 is used to obtain a magnetic positioning image of the downhole tool. The magnetic positioning image of the downhole tool is: and a magnetic positioning curve section corresponding to the downhole tool is cut from the magnetic positioning curve of the well.
The identification unit 602 is configured to input a magnetic positioning image of the downhole tool into a classification model that is trained in advance, and obtain a tool class to which the magnetic positioning image of the downhole tool output by the classification model belongs. The classification model is obtained by training magnetic positioning sample images of various downhole tools and tool class marking information.
Based on the identification device of the downhole tool disclosed by the application, the magnetic positioning curve section generated by the downhole tool can be identified efficiently, and particularly, the magnetic positioning curve section is generated by which downhole tool, so that the workload of well testing personnel is reduced, the influence of human factors is removed, and the identification result has high accuracy.
In one embodiment, the magnetic positioning image acquisition unit 601 is specifically configured to:
obtaining a magnetic positioning curve of the well; receiving at least one set of depth information, wherein each set of depth information includes a start depth and an end depth; based on the starting depth and the ending depth in each set of depth information, magnetic localization curve segments corresponding to each set of depth information are truncated from the magnetic localization curve of the well.
In one embodiment, a magnetic positioning image labeling unit is further provided on the basis of the apparatus shown in fig. 6.
The magnetic positioning image labeling unit is used for: and obtaining depth information of a magnetic positioning image of the downhole tool, and labeling the magnetic positioning image of the downhole tool by utilizing the tool type and the depth information output by the classification model.
In one embodiment, the model training unit is further provided on the basis of the identification means of the downhole tool shown in fig. 6 of the present application.
The model training unit is used for:
obtaining a training sample set, wherein the training sample set comprises training samples of a plurality of downhole tools, each training sample is a magnetic positioning sample image of one downhole tool, and each training sample has tool class marking information for representing the downhole tool to which the training sample belongs; carrying out category prediction on the training sample by utilizing a pre-constructed classification model to obtain a tool category prediction result of the training sample; and adjusting model parameters of the classification model according to tool class marking information and tool class prediction results of the training sample until the adjusted classification model meets preset convergence conditions.
On the other hand, the embodiment of the invention also provides electronic equipment.
Referring to fig. 7, fig. 7 is a hardware configuration diagram of an electronic device according to an embodiment of the present invention. The electronic device may include a processor 701 and a memory 702.
Optionally, the terminal may further include: a communication interface 703, an input unit 704, a display 705 and a communication bus 706. The processor 701, the memory 702, the communication interface 703, the input unit 704 and the display 705 all perform communication with each other through the communication bus 706.
In an embodiment of the present invention, the processor 701 may be a central processing unit (Central Processing Unit, CPU), an asic, a dsp, an off-the-shelf programmable gate array, or other programmable logic device.
The processor 701 may call a program stored in the memory 702.
The memory 702 is used to store one or more programs, which may include program code including computer operating instructions. In the embodiment of the present invention, at least a program for realizing the following functions is stored in the memory:
obtaining a magnetic positioning image of the downhole tool, the magnetic positioning image of the downhole tool being: a magnetic positioning curve section corresponding to the downhole tool is cut from the magnetic positioning curve of the well;
inputting the magnetic positioning image of the downhole tool into a classification model which is trained in advance, and obtaining the tool category to which the magnetic positioning image of the downhole tool output by the classification model belongs;
the classification model is obtained by training magnetic positioning sample images of various downhole tools and tool class marking information.
In one possible implementation, the memory 702 may include a stored program area and a stored data area, where the stored program area may store an operating system, the programs mentioned above, and the like; the storage data area may store data or the like created during use of the computer device.
In addition, memory 702 may include high-speed random access memory, and may also include non-volatile memory.
The communication interface 703 may be an interface of a communication module.
The input unit 704 may include a touch sensing unit sensing a touch event on the touch display panel, a keyboard, and the like.
The display 705 includes a display panel such as a touch display panel or the like.
Of course, the electronic device structure shown in fig. 7 is not limited to the electronic device in the embodiment of the present invention, and the electronic device may include more or fewer components than those shown in fig. 7 or may combine some components in practical applications.
Finally, it is further noted that relational terms such as first and second, and the like are 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. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. The device and the electronic equipment disclosed in the embodiments correspond to the method disclosed in the embodiments, so that the description is simpler, and the relevant parts are referred to in the description of the method.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (3)
1. A method of identifying a downhole tool, comprising:
obtaining a magnetic positioning image of a downhole tool, the magnetic positioning image of the downhole tool being: a magnetic positioning curve section corresponding to the downhole tool is cut from the magnetic positioning curve of the well;
inputting the magnetic positioning image of the downhole tool into a classification model which is trained in advance, and obtaining the tool category to which the magnetic positioning image of the downhole tool output by the classification model belongs;
the classification model is obtained by training magnetic positioning sample images of various downhole tools and tool class marking information;
wherein the obtaining a magnetic positioning image of the downhole tool comprises:
obtaining a magnetic positioning curve of the well;
receiving at least one set of depth information, wherein each set of depth information includes a start depth and an end depth;
intercepting magnetic positioning curve segments corresponding to each set of depth information from the magnetic positioning curve of the well based on the starting depth and the ending depth in each set of depth information;
obtaining depth information of a magnetic positioning image of the downhole tool;
labeling a magnetic positioning image of the downhole tool by utilizing the tool type and the depth information output by the classification model;
the training process of the classification model comprises the following steps:
obtaining a training sample set, wherein the training sample set comprises training samples of a plurality of downhole tools, each training sample is a magnetic positioning sample image of one downhole tool, and each training sample has tool class marking information for representing the downhole tool to which the training sample belongs;
carrying out category prediction on the training sample by utilizing a pre-constructed classification model to obtain a tool category prediction result of the training sample;
according to the tool category labeling information and the tool category prediction result of the training sample, adjusting model parameters of the classification model until the adjusted classification model meets a preset convergence condition;
the difference between the number of training samples of the plurality of downhole tools in the training sample set is within a preset range.
2. An identification device for a downhole tool, comprising:
a magnetic positioning image acquisition unit for acquiring a magnetic positioning image of a downhole tool, the magnetic positioning image of the downhole tool being: a magnetic positioning curve section corresponding to the downhole tool is cut from the magnetic positioning curve of the well;
the identification unit is used for inputting the magnetic positioning image of the downhole tool into a classification model which is trained in advance, and obtaining the tool category to which the magnetic positioning image of the downhole tool output by the classification model belongs;
the classification model is obtained by training magnetic positioning sample images of various downhole tools and tool class marking information;
wherein, the magnetic positioning image acquisition unit is specifically used for:
obtaining a magnetic positioning curve of the well; receiving at least one set of depth information, wherein each set of depth information includes a start depth and an end depth; intercepting magnetic positioning curve segments corresponding to each set of depth information from the magnetic positioning curve of the well based on the starting depth and the ending depth in each set of depth information;
the system also comprises a magnetic positioning image labeling unit;
the magnetic positioning image labeling unit is used for: obtaining depth information of a magnetic positioning image of the downhole tool, and labeling the magnetic positioning image of the downhole tool by utilizing the tool type and the depth information output by the classification model;
the system further comprises a model training unit;
the model training unit is used for: obtaining a training sample set, wherein the training sample set comprises training samples of a plurality of downhole tools, each training sample is a magnetic positioning sample image of one downhole tool, and each training sample has tool class marking information for representing the downhole tool to which the training sample belongs; carrying out category prediction on the training sample by utilizing a pre-constructed classification model to obtain a tool category prediction result of the training sample; according to the tool category labeling information and the tool category prediction result of the training sample, adjusting model parameters of the classification model until the adjusted classification model meets a preset convergence condition; the difference between the number of training samples of the plurality of downhole tools in the training sample set is within a preset range.
3. An electronic device comprising a processor and a memory;
the processor is used for calling and executing the program stored in the memory;
the memory is used for storing the program, and the program is at least used for:
obtaining a magnetic positioning image of a downhole tool, the magnetic positioning image of the downhole tool being: a magnetic positioning curve section corresponding to the downhole tool is cut from the magnetic positioning curve of the well;
inputting the magnetic positioning image of the downhole tool into a classification model which is trained in advance, and obtaining the tool category to which the magnetic positioning image of the downhole tool output by the classification model belongs;
the classification model is obtained by training magnetic positioning sample images of various downhole tools and tool class marking information;
wherein the obtaining a magnetic positioning image of the downhole tool comprises:
obtaining a magnetic positioning curve of the well;
receiving at least one set of depth information, wherein each set of depth information includes a start depth and an end depth;
intercepting magnetic positioning curve segments corresponding to each set of depth information from the magnetic positioning curve of the well based on the starting depth and the ending depth in each set of depth information;
obtaining depth information of a magnetic positioning image of the downhole tool;
labeling a magnetic positioning image of the downhole tool by utilizing the tool type and the depth information output by the classification model;
the training process of the classification model comprises the following steps:
obtaining a training sample set, wherein the training sample set comprises training samples of a plurality of downhole tools, each training sample is a magnetic positioning sample image of one downhole tool, and each training sample has tool class marking information for representing the downhole tool to which the training sample belongs;
carrying out category prediction on the training sample by utilizing a pre-constructed classification model to obtain a tool category prediction result of the training sample;
according to the tool category labeling information and the tool category prediction result of the training sample, adjusting model parameters of the classification model until the adjusted classification model meets a preset convergence condition;
the difference between the number of training samples of the plurality of downhole tools in the training sample set is within a preset range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911302685.4A CN111126469B (en) | 2019-12-17 | 2019-12-17 | Downhole tool identification method, downhole tool identification device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911302685.4A CN111126469B (en) | 2019-12-17 | 2019-12-17 | Downhole tool identification method, downhole tool identification device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111126469A CN111126469A (en) | 2020-05-08 |
| CN111126469B true CN111126469B (en) | 2024-02-06 |
Family
ID=70498257
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911302685.4A Active CN111126469B (en) | 2019-12-17 | 2019-12-17 | Downhole tool identification method, downhole tool identification device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111126469B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115471769B (en) * | 2022-08-16 | 2023-04-07 | 上海航翼高新技术发展研究院有限公司 | Visual identification method for existing state of tool in tool cabinet |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197652A (en) * | 2018-01-02 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | For generating the method and apparatus of information |
| CN109543625A (en) * | 2018-11-27 | 2019-03-29 | 郑州芯力波通信息技术有限公司 | A kind of mine personnel uniqueness identifying system and method |
| CN109886344A (en) * | 2019-02-26 | 2019-06-14 | 广东工业大学 | Leather failure evaluation method, system and equipment and medium based on deep learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127248A (en) * | 2016-06-24 | 2016-11-16 | 平安科技（深圳）有限公司 | Car plate sorting technique based on degree of depth study and system |
-
2019
- 2019-12-17 CN CN201911302685.4A patent/CN111126469B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197652A (en) * | 2018-01-02 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | For generating the method and apparatus of information |
| CN109543625A (en) * | 2018-11-27 | 2019-03-29 | 郑州芯力波通信息技术有限公司 | A kind of mine personnel uniqueness identifying system and method |
| CN109886344A (en) * | 2019-02-26 | 2019-06-14 | 广东工业大学 | Leather failure evaluation method, system and equipment and medium based on deep learning |
Non-Patent Citations (2)
| Title |
|---|
| 刘烨 ; 郭超 ; 马微 ; 程国建 ; .基于神经网络的测井曲线砂体解释与应用研究.测井技术.2015,(05),全文. * |
| 张洪 ; 邱金权 ; 王青川 ; 甘常建 ; 刘彦鑫 ; 周峰 ; .超声波-多普勒三相流测井及其在青海油田的应用.测井技术.2016,(04),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111126469A (en) | 2020-05-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105787104B (en) | Method and device for acquiring user attribute information | |
| EP3397833B1 (en) | Machine learning for production prediction | |
| Goulet et al. | Model falsification diagnosis and sensor placement for leak detection in pressurized pipe networks | |
| CN105046366B (en) | model training method and device | |
| CN108549817A (en) | A kind of software security flaw prediction technique based on text deep learning | |
| CN106240839A (en) | For analyzing the system and method for flutter test data | |
| CN110134961A (en) | Processing method, device and the storage medium of text | |
| CN112990035B (en) | Text recognition method, device, equipment and storage medium | |
| KR20190115319A (en) | Mobile apparatus and method for classifying a sentence into a plurality of classes | |
| CN110019660A (en) | A kind of Similar Text detection method and device | |
| Song et al. | Potential for vertical heterogeneity prediction in reservoir basing on machine learning methods | |
| CN111126469B (en) | Downhole tool identification method, downhole tool identification device and electronic equipment | |
| WO2023093919A2 (en) | Washing machine abnormal sound detection method and apparatus, electronic device, and storage medium | |
| CN106935038B (en) | Parking detection system and detection method | |
| CN117056452B (en) | Knowledge point learning path construction method, device, equipment and storage medium | |
| CN111626377A (en) | Lithofacies identification method, device, equipment and storage medium | |
| TW201435613A (en) | Control method, control program and control device | |
| CN110991079A (en) | Oil and gas reservoir parameter interpretation method and device based on neural network and electronic equipment | |
| KR102445233B1 (en) | Method and apparatus for estimating missing section of oil well logging data | |
| EP3482042B1 (en) | Tool and method to make high resolution and high penetration measurement of corrosion | |
| CN115356400B (en) | BiLSTM-based ultrasonic wood nondestructive testing method and BiLSTM-based ultrasonic wood nondestructive testing system | |
| CN114285587A (en) | Domain name identification method and device and domain name classification model acquisition method and device | |
| CN115081485B (en) | AI-based magnetic flux leakage internal detection data automatic analysis method | |
| CN110552693A (en) | layer interface identification method of induction logging curve based on deep neural network | |
| CN114036829A (en) | Geological profile generation method, system, equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |