CN115082454B

CN115082454B - Core discriminating method, core discriminating device, electronic device and storage medium

Info

Publication number: CN115082454B
Application number: CN202210891941.3A
Authority: CN
Inventors: 陈彪
Original assignee: Shenzhen Xinrun Fulian Digital Technology Co Ltd
Current assignee: Shenzhen Xinrun Fulian Digital Technology Co Ltd
Priority date: 2022-07-27
Filing date: 2022-07-27
Publication date: 2022-12-09
Anticipated expiration: 2042-07-27
Also published as: CN115082454A

Abstract

The invention discloses a method and a device for distinguishing a rock core, electronic equipment and a storage medium. The method comprises the steps of obtaining a core image, a rock stratum image and a core drilling speed; performing image processing on the rock core image to determine the degree of rock core breakage; inputting the core image, the core drilling speed and the core crushing degree into a CAD core judgment algorithm model to obtain a first core judgment result; inputting the rock stratum image, the core drilling speed and the core crushing degree into a CAD rock stratum judgment algorithm model to obtain a second core judgment result; and determining the core category according to the first core judgment result and the second core judgment result. By adopting the scheme provided by the invention, the core distinguishing precision can be improved.

Description

Core discriminating method, core discriminating device, electronic device and storage medium

Technical Field

The invention relates to the technical field of core judgment, in particular to a core judgment method and device, electronic equipment and a storage medium.

Background

With the development of economy in China, the capital construction strength in China is continuously increased, and large-scale roads, buildings, tunnels and the like are put into construction. Before a building is built, geological conditions in an area range need to be surveyed, and geotechnical conditions and geological environments in the area are analyzed through surveying. Drilling is an important means for exploring geological conditions, and aims to find out the stratum structure and distribution characteristics of each hole through core analysis and judgment on drilling of a drilling machine.

At present, the common rock core judging methods include artificial rock judgment and neural network rock judgment. However, the above processes have many problems, and the discrimination accuracy of the core cannot be guaranteed, so that the existing core discrimination process still has a large improvement space.

Disclosure of Invention

Based on this, in order to solve the technical problem of low precision in the existing core identification process, embodiments of the present invention provide a core identification method, an apparatus, an electronic device, and a storage medium.

The technical scheme of the embodiment of the invention is realized as follows:

the embodiment of the invention provides a method for distinguishing a rock core, which comprises the following steps: obtaining a core image, a rock stratum image and a core drilling speed; performing image processing on the rock core image to determine the rock core crushing degree; inputting the core image, the core drilling speed and the core crushing degree into a CAD core judgment algorithm model to obtain a first core judgment result; inputting the rock stratum image, the core drilling speed and the core crushing degree into a CAD rock stratum judgment algorithm model to obtain a second core judgment result; and determining the core type according to the first core judgment result and the second core judgment result.

In the above solution, the acquiring the core image includes: acquiring 360-degree images of the rock core to obtain an annular image of the rock core; acquiring an image of a rock core fracture surface to obtain a rock core fracture surface image; and taking the core annular image and the core section image as the core image.

In the above scheme, the inputting the core image, the core drilling speed and the core crushing degree into a CAD core determination algorithm model to obtain a first core determination result includes: inputting the core image, the core drilling speed and the core crushing degree into a first CNN network, and extracting first characteristic data and position information; and inputting the first characteristic data and the position information into a first transform model to obtain a first core judgment result.

In the above scheme, the inputting the rock stratum image, the core drilling speed and the core crushing degree into a CAD rock stratum decision algorithm model to obtain a second core decision result includes: inputting the rock stratum image, the core drilling speed and the core crushing degree into a second CNN network, and extracting second characteristic data and position information; and inputting the second characteristic data and the position information into a second transform model to obtain a second core judgment result.

The embodiment of the invention also provides a core distinguishing device, which is characterized by comprising: the core image basic feature identification module is used for acquiring a core image; the core crushing degree characteristic identification module is used for carrying out image processing on the core image and determining the core crushing degree; the rock stratum layer characteristic module is used for acquiring a rock stratum image; the drilling data characteristic module is used for acquiring the core drilling speed; the CAD core judgment algorithm model is used for processing the core image, the core drilling speed and the core crushing degree to obtain a first core judgment result; the CAD rock stratum judgment algorithm model is used for processing the rock stratum image, the core drilling speed and the core crushing degree to obtain a second core judgment result; and the correction module is used for determining the core category according to the first core judgment result and the second core judgment result.

In the above scheme, the core image basic feature identification module is specifically configured to perform 360-degree image acquisition on a core to obtain an annular core image; acquiring an image of a rock core fracture surface to obtain a rock core fracture surface image; and taking the core annular image and the core section image as the core image.

In the above scheme, the CAD core decision algorithm model includes: the first CNN network module is used for extracting first characteristic data and position information according to the rock core image, the rock core drilling speed and the rock core crushing degree; and the second transform model is used for obtaining a first rock core judgment result according to the first characteristic data and the position information.

In the above solution, the CAD rock layer decision algorithm model includes: the second CNN network module is used for extracting second characteristic data and position information according to the rock stratum image, the core drilling speed and the core crushing degree; and the second transform model is used for obtaining a second core judgment result according to the second characteristic data and the position information.

An embodiment of the present invention further provides an electronic device, including: a processor and a memory for storing a computer program capable of running on the processor; wherein the content of the first and second substances,

the processor is adapted to perform the steps of any of the above methods when running the computer program.

The embodiment of the invention also provides a storage medium, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the steps of any one of the methods are realized.

The method, the device, the electronic equipment and the storage medium for judging the rock core provided by the embodiment of the invention are used for acquiring the rock core image, the rock stratum image and the rock core drilling speed; performing image processing on the rock core image to determine the degree of rock core breakage; inputting the core image, the core drilling speed and the core crushing degree into a CAD core judgment algorithm model to obtain a first core judgment result; inputting the rock stratum image, the core drilling speed and the core crushing degree into a CAD rock stratum judgment algorithm model to obtain a second core judgment result; and determining the core category according to the first core judgment result and the second core judgment result. By adopting the scheme provided by the invention, the core distinguishing precision can be improved.

Drawings

FIG. 1 is a schematic flow chart of a core discriminating method according to an embodiment of the present invention;

FIG. 2 is a schematic structural diagram of a core discriminating apparatus according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of an embodiment of the system;

FIG. 4 is a schematic view of an annular acquisition mode according to an embodiment of the present invention;

FIG. 5 is a schematic view of an annular acquisition process according to an embodiment of the present invention;

FIG. 6 is a schematic representation of a core fragmentation image according to an embodiment of the invention;

FIG. 7 is a schematic diagram of rock-hole layer feature acquisition according to an embodiment of the invention;

FIG. 8 is a schematic illustration of drilling data acquisition according to an embodiment of the present invention;

FIG. 9 is a schematic diagram of a system building process according to an embodiment of the present invention;

FIG. 10 is a general diagram of a network architecture according to an embodiment of the present invention;

FIG. 11 is a schematic diagram of the structural workflow of a CAD core determination algorithm of the embodiment of the invention;

FIG. 12 is a schematic structural flow diagram of a CAD rock formation determination algorithm in accordance with an embodiment of the present invention;

fig. 13 is an internal structural diagram of a computer device according to an embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples.

The embodiment of the invention provides a core distinguishing method, as shown in figure 1, the method comprises the following steps:

step 101: obtaining a core image, a rock stratum image and a core drilling speed;

step 102: performing image processing on the rock core image to determine the degree of rock core breakage;

step 103: inputting the core image, the core drilling speed and the core crushing degree into a CAD core judgment algorithm model to obtain a first core judgment result;

step 104: inputting the rock stratum image, the core drilling speed and the core crushing degree into a CAD rock stratum judgment algorithm model to obtain a second core judgment result;

step 105: and determining the core category according to the first core judgment result and the second core judgment result.

According to the scheme, the rock core image characteristics are combined with the rock core crushing degree, the rock pore layer characteristics and the drilling condition for judgment, so that the judgment data is more comprehensive, and the judgment precision of the rock core is higher.

In the embodiment, the rock core can be divided into strong differentiation, total weathering, medium weathering and micro weathering according to the weathering degree of the rock core; in addition, the rock sample can be divided into granite, sandstone and the like according to different rock samples.

In practical application, the core image and the rock stratum image can be obtained through an industrial camera and the like. The core drilling speed may be obtained by a speed sensor.

The CAD core determination algorithm model and the CAD rock stratum determination algorithm model in the embodiment can extract features of input data, and the features are matched with database information after passing through the classifier, so that a determination result is obtained.

In one embodiment, the acquiring a core image comprises:

acquiring 360-degree images of the rock core to obtain an annular image of the rock core;

acquiring an image of a rock core fracture surface to obtain a rock core fracture surface image;

and taking the core annular image and the core section image as the core image.

In this embodiment, through carrying out image acquisition to 360 degrees on the core, through handling, constitute the plane image, also gather the section simultaneously, the comprehensiveness of the image information of assurance.

In an embodiment, the inputting the core image, the core drilling speed, and the core crushing degree into a CAD core determination algorithm model to obtain a first core determination result includes:

inputting the core image, the core drilling speed and the core crushing degree into a first CNN network, and extracting first characteristic data and position information;

and inputting the first characteristic data and the position information into a first transform model to obtain a first core judgment result.

In this embodiment, the first CNN network may be obtained by adding the weighting of the fragmentation coefficient and the drilling coefficient to the conventional CNN network.

The first CNN network can perform dimension reduction processing and sequence expansion processing in the process of processing the core image, the core drilling speed and the core crushing degree. Namely, resNet is used as backbone to extract picture features, and meanwhile, the convolution of 1*1 is used for dimension reduction. The CNN features are spread out into a sequence, which is input to the encoder module for detection.

In an embodiment, the inputting the rock stratum image, the core drilling speed, and the core crushing degree into a CAD rock stratum determination algorithm model to obtain a second core determination result includes:

inputting the rock stratum image, the core drilling speed and the core crushing degree into a second CNN network, and extracting second characteristic data and position information;

and inputting the second characteristic data and the position information into a second transform model to obtain a second core judgment result.

Here, the processing flow of the CAD formation determination algorithm model may be identical to the processing flow of the CAD core determination algorithm model. Specifically, refer to the processing flow of the CAD core decision algorithm model.

The method for distinguishing the core obtains the core image, the rock stratum image and the core drilling speed; performing image processing on the rock core image to determine the degree of rock core breakage; inputting the core image, the core drilling speed and the core crushing degree into a CAD core judgment algorithm model to obtain a first core judgment result; inputting the rock stratum image, the core drilling speed and the core crushing degree into a CAD rock stratum judgment algorithm model to obtain a second core judgment result; and determining the core category according to the first core judgment result and the second core judgment result. By adopting the scheme provided by the invention, the core distinguishing precision can be improved.

An embodiment of the present invention further provides a core identification device, as shown in fig. 2, the device includes:

a core image basic feature identification module 201, configured to obtain a core image;

the core crushing degree characteristic identification module 202 is used for performing image processing on the core image and determining the core crushing degree;

a rock pore layer characteristic module 203 for acquiring a rock layer image;

a drilling data characterization module 204 for obtaining a core drilling rate;

the CAD core determination algorithm model 205 is used for processing the core image, the core drilling speed and the core crushing degree to obtain a first core determination result;

the CAD rock stratum judgment algorithm model 206 is used for processing the rock stratum image, the core drilling speed and the core crushing degree to obtain a second core judgment result;

and the correcting module 207 is used for determining the core category according to the first core judgment result and the second core judgment result.

Specifically, the core image basic feature identification module 201 may extract basic core visual features; the core crushing degree characteristic identification module 202 can identify the basic category of the core by extracting mechanical characteristics such as hardness and the like of the core fed back by the crushing degree index; the rock stratum characteristic module 203 can extract the characteristic information of the rock stratum layer left after drilling is finished, and the rock stratum is classified according to the characteristic information of the rock stratum layer; the drilling data characteristic module 204 can assist in judging the core according to the drilling speed of drilling and mechanical characteristic information such as the hardness of the core; the calibration module 207 may provide a weight-weighted analysis for each module.

In an embodiment, the core image basic feature identification module 201 is specifically configured to perform 360-degree image acquisition on a core to obtain an annular core image; acquiring an image of a rock core fracture surface to obtain a rock core fracture surface image; and taking the core annular image and the core section image as the core image.

In particular, the core image basis feature identification module 201 in this embodiment may be an industrial surround camera.

In one embodiment, the CAD core decision algorithm model 205 comprises:

the first CNN network module is used for extracting first characteristic data and position information according to the rock core image, the rock core drilling speed and the rock core crushing degree;

and the second transform model is used for obtaining a first core judgment result according to the first characteristic data and the position information.

The first CNN network can perform dimension reduction processing and sequence expansion processing in the process of processing the core image, the core drilling speed and the core crushing degree. Namely, resNet is used as a background to extract picture features, and meanwhile, the convolution of 1*1 is used for dimensionality reduction. The CNN features are spread out into a sequence, which is input to the encoder block for detection.

In one embodiment, the CAD formation determination algorithm model 206 includes:

the second CNN network module is used for extracting second characteristic data and position information according to the rock stratum image, the core drilling speed and the core crushing degree;

and the second transform model is used for obtaining a second core judgment result according to the second characteristic data and the position information.

Here, the processing flow of the CAD formation determination algorithm model may coincide with the processing flow of the CAD core determination algorithm model. Specifically, refer to the processing flow of the CAD core decision algorithm model.

It should be noted that: the apparatus provided in the foregoing embodiment is only illustrated by dividing the program modules, and in practical applications, the processing allocation may be completed by different program modules as needed, that is, the internal structure of the terminal is divided into different program modules, so as to complete all or part of the processing described above. In addition, the apparatus provided in the above embodiment and the method embodiment belong to the same concept, and the specific implementation process thereof is described in the method embodiment, which is not described herein again.

The rock core distinguishing device provided by the embodiment of the invention comprises a rock core image basic characteristic identifying module, a rock core image judging module and a rock core image judging module, wherein the rock core image basic characteristic identifying module is used for acquiring a rock core image; the core crushing degree characteristic identification module is used for carrying out image processing on the core image and determining the core crushing degree; the rock stratum layer characteristic module is used for acquiring a rock stratum image; the drilling data characteristic module is used for acquiring the core drilling speed; the CAD core judgment algorithm model is used for processing the core image, the core drilling speed and the core crushing degree to obtain a first core judgment result; the CAD rock stratum judgment algorithm model is used for processing the rock stratum image, the core drilling speed and the core crushing degree to obtain a second core judgment result; and the correction module is used for determining the core category according to the first core judgment result and the second core judgment result. By adopting the scheme provided by the invention, the core distinguishing precision can be improved.

Further, the core discriminating process will be described in detail below in conjunction with the above method and apparatus.

Referring to fig. 3, the process of discriminating the core in this embodiment is:

firstly, acquiring target image data of a rock sample to be judged by a data acquisition system such as an industrial camera; then extracting core characteristic information through a CDA algorithm, and performing matching analysis on the core characteristic information and database information through a classifier; and finally, classifying and positioning specific information of the rock core to obtain a rock core judgment result, and displaying the result on a PC (personal computer) terminal.

In this embodiment, the development and operation environment of the CDA algorithm model may be as follows:

watch 1

Based on the above operating environment, the core is determined in this embodiment, and data needs to be acquired and processed first. When data processing is carried out, labeling is carried out on an original data set, and the data set is divided into a training set, a testing set and a verification set.

Specifically, the data acquisition of the present embodiment includes the following parts:

(1) Core image basic feature identification module (CBFID)

Referring to fig. 4, it can be seen from the core acquisition condition that the core is cylindrical, and in order to extract characteristic information in an all-round manner, the invention provides an annular core characteristic extraction method. Referring to fig. 5, the acquisition process is as follows:

annular image acquisition and cross-sectional image acquisition are carried out on the rock core by utilizing an annular acquisition device such as an annular camera, and bottom surface images and surface side images, namely rock core images, are obtained.

(2) Core fragmentation characterization Module (CFDCID)

The situation of gathering by annular core can be seen, when there is the breakage in the core, wherein the degree of breakage is: a = B/(a + B), and its face image is as shown in fig. 6.

(3) Rock-hole layer feature module (PLFM)

Referring to fig. 7, the rock-bore layer feature module is mainly extended into the bore hole by a camera to acquire images of the inside of the bore hole.

(4) Drilling Data Feature Module (DDFM)

Referring to fig. 8, the module is primarily the rate of penetration v of the drill rods of the drilling machine, such as a rate of penetration v of 15.3m-15.5 m.

Based on the data acquisition process, the process idea of this embodiment is as follows:

referring to fig. 9, the process idea of the present invention includes data processing, model building, training optimization, and system building. The steps are buckled with each other. Firstly, analyzing the data of the rock core, and performing data; then, building a detection algorithm model based on a deep learning theory; then, training and optimizing the built data set; and finally, deploying and building a system for the trained model.

Next, the CDA network structure of the present embodiment will be described in detail.

Specifically, referring to fig. 10, the overall flow is described as follows:

step 1: an image of the core is input. Obtaining core data, crushing degree data and drilling data, inputting a rock stratum image and obtaining rock stratum data;

step 2: the CAD core judgment algorithm judges the core according to the core data, the crushing degree data and the drilling data, and the CAD rock stratum judgment algorithm judges the rock stratum according to the rock stratum data, the crushing degree data and the drilling data;

and 3, step 3: calculating by an algorithm to obtain a CAD core judgment value and a CAD rock stratum judgment value;

and 4, step 4: adjusting and correcting the CAD core judgment value and the CAD rock stratum judgment value;

and 5: and obtaining a final judgment result after the numerical value is harmoniously corrected.

Specifically, referring to fig. 11, the main workflow of the cad core decision algorithm structure is shown as follows:

(1) An image of the core is input. Obtaining core data, crushing degree data and drilling data;

(2) The CFCID module calculates the degree of breakage, obtains a degree of breakage coefficient a, calculates the drilling speed and converts the drilling speed into a drilling coefficient b;

(3) Extracting characteristic image information by a DeformableDETR network;

(4) Weighting the characteristic image information extracted by the DeformableDETR network according to the fragmentation coefficient a and the drilling coefficient b;

(5) And calculating by using a DeformableDETR algorithm to obtain a CAD core judgment value.

Wherein, for DeformableDETR network

In this embodiment, the DETR integrates the transforms into a target detection framework for detecting the pipeline center building block. In contrast to other target detection methods, the DETR in this project effectively eliminates the need for many manually designed components, such as the Non-maximum suppression (NMS) program, anchor point (Anchor) generation, and the like.

In the invention, the DETR is divided into three parts, the first part is a traditional CNN, and in the network, the weight of a fragmentation coefficient and a drilling coefficient is added into the part of the DETR for extracting the characteristics of a picture Gao Wei; the second part is a transform structure, encoder and Decoder to extract BoundingBox; finally, the Bipartitematic training loss is used for training the network.

The DETR firstly inputs a 3-channel picture into a network with a backhaul CNN, extracts picture features, then inputs the picture features into an encoder and a decoder of a transform model by combining position information, and obtains detection results of the transform, wherein each result is a box, and each box represents a tuple and comprises the class of an object and the position of a detection frame.

ResNet part. The ResNet is used as a backbone to extract picture features, and meanwhile, the convolution of 1*1 is used for dimension reduction. Since the encoder module of the transformer only processes the sequence input, the CNN features need to be spread out into one sequence subsequently.

DETRTransformer section. Firstly, a position coding part converts a characteristic diagram extracted by ResNet into a characteristic sequence, and then an image loses the spatial distribution information of pixels, so that a Transformer introduces position coding. And splicing the characteristic sequence and the position coding sequence to be used as input of the code.

The DETR proposes a coding scheme: spatialocationalencoding.

spatialpositioningcoding is input to both the encoder and decoder. spatialocationalencoding also includes two calculation methods:

first, left: an emmiding vector, learned from the network;

second, sine:

PE (pos, 2 i) = sin (pos/100002 i/dnodel) formula (1)

PE (pos, 2i + 1) = cos (pos/100002 i/dmodel) formula (2)

PE is a two-dimensional matrix, the size of the matrix is the same as the dimension of input embedding, a row represents a word, and a column represents a word vector; pos represents the position of the word in the sentence; dmoded _ { model } dmodel represents dimensions of a word vector; i denotes the position of the word vector. Thus, the above formula shows that sin variables are added at even positions and cos variables are added at odd positions of the word vector of each word to fill the entire PE matrix, and then concatenate is sent to the encoder.

DeformableDETR. Due to the limitation of the Transformer attention module in processing the image feature map, the convergence speed is low, and the spatial resolution of the features is limited. To alleviate these problems, the present invention applies the idea of variability convolution to the det, whose attention module only focuses on a small set of key sample points around the reference point. DeformableAttention is cited in the item, and under the guidance of an important area in feature mapping, the relation between tokens is effectively modeled. These concentrated regions are determined by the sets of Deformablesamplification points learned from the query by the offset network. And sampling the characteristics in the characteristic mapping by adopting bilinear interpolation, and then inputting the sampled characteristics into a key for projection to obtain the DeformableKey.

The Hungarian nMacher realizes bipartitematic learning, uses the Hungarian algorithm, and the final matching scheme is to select the minimum distribution mode of 'sum of loss'.

The algorithm realizes the optimal matching between the predicted values and the true values, and the predicted values are in one-to-one correspondence, so that a plurality of predicted values are not matched to the same group route, and the NMS post-processing is not needed.

The DETR loss contains two parts: classification loss, cross entropy loss function

Detecting the position loss of the frame: the weighted sum of the L1 loss and the IOU loss, and the calculation of Iou adopts the GIou algorithm, so that the problem that Iou is always 0 when a real frame and a detection frame are not overlapped is solved.

DETHREAD. And directly sending the transform output sequence to an FFN classifier to obtain a prediction class and a detection frame coordinate.

In addition, referring specifically to FIG. 12, the main workflow of the CAD formation determination algorithm structure is shown:

step 1: an image of the rock formation is input. Obtaining rock stratum data, crushing degree data and drilling data;

and 2, step: the CFCID module calculates the degree of breakage, obtains a degree of breakage coefficient a, calculates the drilling speed and converts the drilling speed into a drilling coefficient b;

and step 3: extracting characteristic image information by a DeformableDETR network;

and 4, step 4: weighting the characteristic image information extracted by the DeformableDETR network according to the fragmentation coefficient a and the drilling coefficient b;

and 5: and calculating by using a DeformableDETR algorithm to obtain a CAD rock stratum judgment value.

The rest parts are also the same as the CAD core judgment algorithm structure, and the specific description of the CAD core judgment algorithm structure can be referred.

The embodiment provides a Core labeling method based on Core characteristics, constructs a CDA network result based on double-layer correction discrimination of a Core and a rock stratum, and provides a Core image basic feature identification module (CBFID), a Core fragmentation degree feature identification module (CFDCID), a Drilling layer feature module (PLFM), and a Drilling Data Feature Module (DDFM). The embodiment is based on a CDA system, analyzes the data set, constructs the system, and can realize core judgment through experimental prediction, and partial accuracy rate is up to 80%.

In order to implement the method of the embodiment of the present invention, the embodiment of the present invention further provides a computer program product, where the computer program product includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the steps of the above-described method.

Based on the hardware implementation of the program module, in order to implement the method according to the embodiment of the present invention, an electronic device (computer device) is further provided in the embodiment of the present invention. Specifically, in one embodiment, the computer device may be a terminal, and its internal structure diagram may be as shown in fig. 13. The computer apparatus includes a processor a01, a network interface a02, a display screen a04, an input device a05, and a memory (not shown in the figure) connected through a system bus. Wherein the processor a01 of the computer device is adapted to provide computing and control capabilities. The memory of the computer device includes an internal memory a03 and a nonvolatile storage medium a06. The nonvolatile storage medium a06 stores an operating system B01 and a computer program B02. The internal memory a03 provides an environment for running the operating system B01 and the computer program B02 in the nonvolatile storage medium a06. The network interface a02 of the computer apparatus is used for communicating with an external terminal through a network connection. The computer program is executed by the processor a01 to implement the method of any of the above embodiments. The display screen a04 of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device a05 of the computer device may be a touch layer covered on the display screen, a key, a trackball or a touch pad arranged on a casing of the computer device, or an external keyboard, a touch pad or a mouse.

Those skilled in the art will appreciate that the architecture shown in fig. 13 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

The device provided by the embodiment of the present invention includes a processor, a memory, and a program stored in the memory and capable of running on the processor, and when the processor executes the program, the method according to any one of the embodiments described above is implemented.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

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

The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory computer readable media (transmyedia) such as modulated data signals and carrier waves.

It will be appreciated that the memory of embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. Among them, the nonvolatile Memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a magnetic random access Memory (FRAM), a magnetic random access Memory (Flash Memory), a magnetic surface Memory, an optical Disc, or a Compact Disc Read-Only Memory (CD-ROM); the magnetic surface storage may be disk storage or tape storage. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of illustration and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), synchronous Static Random Access Memory (SSRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), enhanced Synchronous Dynamic Random Access Memory (ESDRAM), enhanced Synchronous Dynamic Random Access Memory (Enhanced DRAM), synchronous Dynamic Random Access Memory (SLDRAM), direct Memory (DRmb Access), and Random Access Memory (DRAM). The described memory for embodiments of the present invention is intended to comprise, without being limited to, these and any other suitable types of memory.

It should also be noted that 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 a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art to which the present application pertains. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for core discrimination, the method comprising:

obtaining a core image, a rock stratum image and a core drilling speed; the rock stratum image is obtained by extending a camera into a drill hole and acquiring an image in the hole, and the rock stratum image contains characteristic information of a rock stratum layer left after the completion of drilling of a core;

performing image processing on the rock core image to determine the degree of rock core breakage; the core fragmentation degree reflects mechanical characteristics of the core, and the mechanical characteristics comprise hardness;

inputting the core image, the core drilling speed and the core crushing degree into a core judgment algorithm model to obtain a first core judgment result;

inputting the rock stratum image, the core drilling speed and the core crushing degree into a rock stratum judgment algorithm model to obtain a second core judgment result;

determining the core type according to the first core judgment result and the second core judgment result;

inputting the core image, the core drilling speed and the core crushing degree into a core judgment algorithm model to obtain a first core judgment result, wherein the method comprises the following steps:

inputting the first characteristic data and the position information into a first transform model to obtain a first core judgment result;

inputting the rock stratum image, the core drilling speed and the core crushing degree into a rock stratum judgment algorithm model to obtain a second core judgment result, wherein the second core judgment result comprises the following steps:

inputting the second characteristic data and the position information into a second transform model to obtain a second core judgment result;

the first CNN network and the second CNN network are obtained by adding a fragmentation coefficient and a drilling coefficient on the basis of a traditional CNN network.

2. The method of claim 1, wherein the acquiring a core image comprises:

and taking the core annular image and the core section image as the core image.

3. A core discriminating apparatus, the apparatus comprising:

the core image basic feature identification module is used for acquiring a core image;

the core crushing degree characteristic identification module is used for carrying out image processing on the core image and determining the core crushing degree; the core fragmentation degree reflects mechanical characteristics of the core, and the mechanical characteristics comprise hardness;

the rock stratum layer characteristic module is used for acquiring a rock stratum image; the rock stratum image is obtained by extending a camera into a drill hole and acquiring an image in the hole, and the rock stratum image contains characteristic information of a rock stratum layer left after the completion of drilling of a core;

the drilling data characteristic module is used for acquiring the core drilling speed;

the core judgment algorithm model is used for processing the core image, the core drilling speed and the core crushing degree to obtain a first core judgment result;

the rock stratum judgment algorithm model is used for processing the rock stratum image, the core drilling speed and the core crushing degree to obtain a second core judgment result;

the correction module is used for determining the type of the rock core according to the first rock core judgment result and the second rock core judgment result;

wherein the core decision algorithm model comprises:

the second transform model is used for obtaining a first rock core judgment result according to the first characteristic data and the position information;

wherein the formation determination algorithm model comprises:

the second transform model is used for obtaining a second core judgment result according to the second characteristic data and the position information;

and the first CNN network and the second CNN network are obtained by adding the weight of a fragmentation coefficient and a drilling coefficient on the basis of the traditional CNN network.

4. The device according to claim 3, wherein the core image basis feature identification module is specifically configured to perform 360-degree image acquisition on the core to obtain a core annular image; acquiring an image of a rock core fracture surface to obtain a rock core fracture surface image; and taking the core annular image and the core section image as the core image.

5. An electronic device, comprising: a processor and a memory for storing a computer program capable of running on the processor; wherein the content of the first and second substances,

the processor is adapted to perform the steps of the method of any one of claims 1 to 2 when running the computer program.

6. A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the steps of the method of any one of claims 1 to 2.