Automatic Recognition System and Method for Core Rock Sampling Based on Image Processing and Machine Learning

Abstract

The present invention discloses an automatic identification system and method for core rock sampling based on image processing and machine learning. The system includes a drilling component, a sensor component, a measurement and control lamp component, an identification component, a relay component, and a control and display component. The method includes: conducting core rock drilling to obtain core rock samples; collecting images of the core rock samples and monitoring parameters during the drilling process; sorting out physical and appearance characteristics of the obtained core rock samples and the core rock sample images and storing them in a database; preprocessing the collected core rock sample images and extracting key features; training a core rock category recognition model using a machine learning algorithm; and applying the trained core rock category recognition model to newly obtained core rock sample image data to obtain classification and recognition results. The present invention combines sensors, image processing, and convolutional neural networks to achieve automated and real-time core rock identification, improve the efficiency and accuracy of identification, and can be flexibly applied in field environments.

Description

Technical Field

[0001] The present invention relates to the technical field of geological drilling, and particularly relates to an automatic core rock sampling identification system and method based on image processing and machine learning. Background Art

[0002] In the field of geological exploration, core identification is one of the key technologies. Traditional core identification mainly relies on manual operation, and geological researchers need to observe rock thin sections through a microscope to determine the core type and its parameters. This method highly depends on the experience of experts, not only takes a long time, but also has high costs, and the identification efficiency and accuracy are relatively low. In addition, traditional methods are difficult to achieve real-time monitoring and rapid feedback, especially in the complex field environment, it is more difficult to ensure timely and accurate acquisition of core information.

[0003] To solve these problems, in recent years, image processing technology has gradually been introduced into the field of core identification. By using the imaging of rock thin sections under a microscope and combining image analysis and feature extraction technologies, researchers have made remarkable progress in aspects such as core texture, rock composition, grain size, and lithology. However, such technologies are mainly limited to the laboratory environment and require large equipment for high-precision imaging, making it difficult to be popularized and applied in the field environment.

[0004] With the development of artificial intelligence technology, the automatic identification method of rock thin section minerals based on deep learning automatically extracts image features through a convolutional neural network (CNN), greatly improving the accuracy of identification. Especially the application of lightweight convolutional neural networks has greatly reduced the model parameters and improved the identification speed and model portability. However, existing identification methods mostly rely on microscope imaging or require expensive and bulky equipment for image acquisition, which is not suitable for on-site real-time operation.

[0005] Traditional core identification technologies rely on the subjective judgment of experts, resulting in difficulties in ensuring the reliability and consistency of identification results; traditional methods require complex experimental equipment and long sample processing times, resulting in high costs and low efficiency, and it is difficult to meet the needs of large-scale geological exploration; existing technologies are difficult to achieve on-site real-time and convenient core identification and information feedback, and cannot timely guide the next step of geological exploration operations; some advanced image recognition technologies require expensive and large imaging equipment and cannot be widely applied on-site. Summary of the Invention

[0006] The purpose of the present invention is to provide an automatic core rock sampling identification system and method based on image processing and machine learning to solve at least one of the above technical problems. By combining technologies such as sensors, image processing, and convolutional neural networks, it realizes automated and real-time core identification, improves the identification efficiency and accuracy, and can be flexibly applied in the field environment.

[0007] Embodiments of the present invention are implemented as follows:

[0008] An automatic recognition system for core rock sampling based on image processing and machine learning, comprising:

[0009] A drilling component for core rock drilling to extract core rock samples.

[0010] A sensor component for collecting images of core rock samples and monitoring parameters during the drilling process.

[0011] A measurement and control light component for providing illumination to provide clear vision for image collection by the sensor component.

[0012] An identification component for processing and identifying the collected core rock sample images to obtain the identification result of the core rock category.

[0013] A relay component for controlling the on / off states of various electrical components.

[0014] A control and display component for displaying and adjusting various parameters during the drilling process and controlling the operations of the measurement and control light component, the drilling component, the sensor component, the identification component, and the relay component.

[0015] In a preferred embodiment of the present invention, in the above automatic recognition system for core rock sampling based on image processing and machine learning, the drilling component includes a drill tool module, a power output module, a battery module, and a drilling propulsion module.

[0016] The drill tool module includes a drill bit, a drill pipe, a drill collar, wing blades, a blade releaser, and a sampling inner pipe. The drill bit is installed at the front end of the drill pipe. The drill bit and the drill pipe are arranged inside the drill collar. The rear end of the drill pipe is connected to the drill collar. The wing blades are arranged at the front end of the drill bit. The rear end of the drill bit is connected to the blade releaser. The sampling inner pipe is arranged inside the front end of the drill bit.

[0017] The power output module includes an electric motor, a reducer, a coupling, and a bearing. The output end of the electric motor is connected to the reducer. The output end of the reducer is connected to the drill collar and the drill pipe through the coupling.

[0018] The battery module is connected to the electric motor and also connected to the control and display component.

[0019] Its technical effects are as follows: The structural design of the drill tool module and the cooperation of components such as the drill bit, drill pipe, flank blades, and sampling inner pipe enable the system to accurately obtain core rock samples from the formation without manual intervention, realizing automated core rock sampling and greatly improving the sampling efficiency; The measurement and control lamp assembly provides stable and uniform lighting conditions, ensuring visual clarity during image acquisition and improving the quality of the images.

[0020] In a preferred embodiment of the present invention, in the above-mentioned automatic recognition system for core rock sampling based on image processing and machine learning, the drill tool module further includes a rubber shock absorber, a drill sleeve, and a shear pin.

[0021] The rubber shock absorber is arranged at the connection between the drill pipe and the drill collar.

[0022] The drill sleeve is sleeved outside the drill collar, and the drill collar and the drill pipe move along the drill sleeve.

[0023] The shear pin is arranged at the rear end of the drill pipe, and when a predetermined load is reached, the shear pin breaks.

[0024] Its technical effects are as follows: The rubber shock absorber arranged at the connection between the drill pipe and the drill collar can effectively absorb and relieve the energy generated by mechanical vibration and impact during drilling, reduce the adverse effects on the integrity of the core rock sample, and ensure the smoothness of the drilling process; The drill sleeve is sleeved outside the drill collar, enabling the drill collar and the drill pipe to move smoothly along the drill sleeve, providing a guiding function, ensuring that the drill tool maintains a stable path during drilling, avoiding deflection, protecting the core components of the drill tool, and reducing the direct wear of the drill collar and the drill pipe by the external environment; The shear pin is designed to break when a predetermined load is reached, thereby preventing equipment damage caused by overload. As a load protection device, when the drill tool encounters abnormal resistance or load during drilling, the shear pin will break first, cutting off the connection between the drill pipe and the power transmission part, and avoiding more serious mechanical failures.

[0025] In a preferred embodiment of the present invention, in the above-mentioned automatic recognition system for core rock sampling based on image processing and machine learning, the drilling assembly further includes a cooling and lubrication module.

[0026] The cooling and lubrication module includes a cooling pump, a water inlet pipe, and a recovery pipe. The water inlet pipe is connected to the output port of the cooling pump, the recovery pipe is connected to the input port of the cooling pump, the liquid outlet of the water inlet pipe extends into the drill collar, and the liquid inlet of the recovery pipe extends into the drill collar.

[0027] Its technical effects are: through the cooling and lubrication module, the temperature around the drill bit and drill rod is effectively reduced, ensuring the normal operation of the drill tool under high load conditions, and providing lubrication for the drill bit and drill rod to reduce the friction between the drill bit and the formation, thereby reducing wear and extending the service life of the drill tool; the rock cuttings accumulated around the drill bit are taken away by the coolant and discharged out of the drill collar through the recovery pipe, thereby keeping the drill bit clean and preventing the drill bit from getting stuck or decreasing efficiency due to rock cuttings accumulation. Under various complex geological conditions, such as high temperature or high friction geological environments, the cooling and lubrication module can effectively adjust and control the temperature and lubrication state during the drilling process, allowing the system to adapt to different working environments and enhancing the system's diversified application capabilities.

[0028] In a preferred embodiment of the present invention, in the above-mentioned core rock sampling automatic identification system based on image processing and machine learning, the measurement and control light assembly includes a protective cover, a measurement and control light bracket, a light source and a radiator, the protective cover and the measurement and control light bracket are sealed and connected to form a sealed space inside, and the light source and the radiator are both installed on the measurement and control light bracket and are located in the sealed space.

[0029] The sensor component includes an image sensor, a temperature sensor, a pressure sensor, a vibration sensor and a data processing unit. The image sensor captures an image of the front end of the drill bit, the temperature sensor monitors the temperature of the power output module, the pressure sensor monitors the pressure applied to the drill bit, and the vibration sensor monitors the vibration of the drill rod. The data processing unit connects the image sensor, the temperature sensor, the pressure sensor and the vibration sensor through wires to transmit the collected data to the identification component and the control and display component.

[0030] The relay assembly comprises a relay, a wiring terminal and a connecting wire, one end of the wiring terminal is connected to the relay via the connecting wire, and the other end is connected to a component to be controlled.

[0031] Its technical effect is: combined with the protection design of the measurement and control light components and the real-time monitoring of the sensor components, the system can maintain an efficient and stable working state under a variety of complex and harsh environmental conditions. Whether it is strong light, dust environment, or high temperature, high pressure, and severe vibration drilling scenes, the system can adaptively adjust to ensure the normal operation of the equipment.

[0032] In a preferred embodiment of the present invention, in the above-mentioned core rock sampling automatic identification system based on image processing and machine learning, the identification component includes:

[0033] The feature acquisition module is used to receive the core rock sample image acquired by the sensor component, organize the physical and appearance features of the core rock sample extracted by the drilling component, and store them in a database.

[0034] A preprocessing module for preprocessing the collected core rock sample images and extracting key features.

[0035] A model training module for training a core rock category recognition model using machine learning algorithms.

[0036] A real-time recognition module for applying the trained core rock category recognition model to newly acquired core rock sample image data to obtain the recognition result of the core rock category and feedback it to the control and display component.

[0037] Its technical effect is that: through the mutual cooperation of the feature acquisition, preprocessing, model training, and real-time recognition modules of the recognition component, high-precision and efficient recognition of the core rock sample category is achieved. The system can automatically adapt to changes in different environments and core rock types, improving the stability and accuracy of recognition; by automatically identifying the core rock sample category, the system significantly reduces the workload and error of manual recognition, improves work efficiency and safety. At the same time, the automated recognition process can achieve continuous and uninterrupted core rock category analysis, providing strong support for the intelligent decision-making of the drilling process.

[0038] In a preferred embodiment of the present invention, in the above-mentioned automatic core rock sampling recognition system based on image processing and machine learning, the control and display component includes:

[0039] A data receiving module for receiving the recognition result of the core rock category obtained by the recognition component.

[0040] A data parsing module for extracting sample category, feature value, and confidence information according to the recognition result.

[0041] An adjustment and control module for adjusting the working parameters and working modes of the drilling component, the sensor component, and the measurement and control lamp component.

[0042] A status monitoring module for monitoring the working status of the measurement and control lamp component, the drilling component, the sensor component, the recognition component, and the relay component, and sending an alarm if an abnormality occurs.

[0043] A display module for presenting the recognition result, the working parameters, the working mode, and the monitoring information to the user interface.

[0044] Its technical effects are as follows: Through the close cooperation of each module, the control and display components achieve the intelligent control, real-time data processing, and full-range monitoring of the system; it can automatically adjust working parameters according to real-time data, optimize the operating states of each component, and significantly improve the efficiency of drilling operations; the display module provides an intuitive and easy-to-understand interface for operators, facilitating the real-time understanding of the system status and operation progress, and enhancing the user's operation experience and the operability of the system.

[0045] An automatic recognition method for core rock sampling based on image processing and machine learning, which includes: conducting core rock drilling to extract core rock samples.

[0046] Collect images of the core rock samples and monitor the parameters during the drilling process.

[0047] For the obtained core rock samples and core rock sample images, organize the physical and appearance characteristics and store them in a database.

[0048] Preprocess the collected core rock sample images and extract key features.

[0049] Use machine learning algorithms to train a core rock category recognition model.

[0050] Apply the trained core rock category recognition model to newly obtained core rock sample image data to obtain classification and recognition results.

[0051] In a preferred embodiment of the present invention, in the above automatic recognition method for core rock sampling based on image processing and machine learning, the structure of the core rock category recognition model includes a convolutional layer, a pooling layer, a fully connected layer, and a loss function.

[0052] The input of the convolutional layer is , which is a multi-dimensional matrix representing the color, texture, and morphological characteristics of the core rock sample image, where W is the width of the image, H is the height of the image, and C is the number of channels of the image.

[0053] The convolutional layer performs a convolution operation on the input feature map X and the convolution kernel W, and outputs the generated feature map Z, representing the local features of the core rock sample image.

[0054] The input of the pooling layer is the feature map output by the convolutional layer, where is the width after pooling, is the height after pooling, and K is the number of convolution kernels.

[0055] The pooling layer downsamples the feature map Z and outputs the generated size-reduced feature map P, representing the significant local features of the core rock sample image.

[0056] The input of the fully connected layer is a one-dimensional vector obtained by flattening the dimension-reduced feature map P for the overall description of the core rock category. , and the dimension size is N.

[0057] The fully connected layer maps the one-dimensional vector to the category space and outputs the category scores y representing the possibility of each category.

[0058] The input of the loss function is the category scores y and the corresponding actual core rock category labels. .

[0059] The loss function calculates the difference between the predicted value and the actual value and outputs the loss value for updating the model parameters.

[0060] Its technical effect lies in: by using the organic combination of the convolutional layer, pooling layer, fully connected layer and loss function, feature extraction, dimensionality reduction, category mapping and error optimization are performed on the core rock sample image, and finally high-precision core rock category recognition is achieved. Through the local receptive field and weight sharing mechanism of the convolutional layer, the color, texture and morphological features of the core rock sample image are effectively extracted, and the local features in the image are captured, such as the fine texture and edge features of the rock; the pooling layer downsamples the feature map output by the convolutional layer, retains the significant local features of the image, pays more attention to the key features in the image, significantly reduces the data dimension, not only reduces the computational complexity, improves the training efficiency of the model, but also effectively reduces the risk of model overfitting; the fully connected layer flattens the pooled feature map into a one-dimensional vector and maps it to the category space, generating the possibility scores for each category, enabling the model to accurately judge the category of the entire core rock sample based on the local features extracted by the pooling layer, enhancing the overall expression ability of the model and improving the accuracy of core rock category recognition; the loss function calculates the difference between the model predicted value and the actual label, and feeds back the error for updating the model parameters. By continuously optimizing the loss function, the convolutional kernel, pooling parameters and weights of the fully connected layer are gradually adjusted to make the prediction result more accurate.

[0061] In a preferred embodiment of the present invention, in the above-mentioned automatic core rock sampling recognition method based on image processing and machine learning, applying the trained core rock category recognition model to newly acquired core rock sample image data, the classification and recognition results include:

[0062] The outputs of multiple trained core rock category recognition models are respectively .

[0063] Integrate the outputs of several models for the newly acquired core rock sample image data to obtain the final classification and recognition results , where is the weight of the j-th model.

[0064] Its technical effects are as follows: By introducing multiple trained core rock category recognition models, each model being good at recognizing different types of core rock samples, and weighted fusion of the outputs of these models, the overall performance of the recognition system is effectively improved, which helps to enhance the generalization ability of the recognition system for unseen samples. By synthesizing the prediction results of multiple models, the system can exhibit better stability and accuracy when dealing with different geological conditions, different image qualities or different sample types.

[0065] The beneficial effects of the embodiments of the present invention are:

[0066] The present invention integrates drilling, image acquisition, parameter monitoring and recognition processing into one system. Through the collaborative work of each component, automatic sampling and recognition of core rock samples are realized, forming a complete sampling image acquisition and sample classification recognition process. The efficient cooperation of each module enables the system to quickly respond to changes in actual applications, ensuring adaptability under different environments and conditions. By automating the traditional manual sampling and recognition process, the work efficiency and recognition accuracy are significantly improved. The automatic recognition system for core rock sampling based on image processing and machine learning of the present invention can perform parallel sampling at multiple drilling positions simultaneously, greatly improving the overall drilling efficiency. Through the parallel sampling method, not only the utilization rate of resources is improved, but also the geological exploration cycle is effectively shortened.

[0067] In terms of the recognition method, the present invention adopts an advanced deep learning network structure, uses advanced machine learning algorithms such as convolutional neural network (CNN) to train the core rock sample images, including convolutional layers, pooling layers and fully connected layers, etc., improving the recognition ability of the model. The self-learning ability of image features is fully utilized, enabling the system to gradually improve the recognition rate during the process of continuously accumulating data. Through the fusion recognition of multiple models, the present invention effectively overcomes the limitations of a single model in feature learning, thereby further improving the recognition accuracy of core rock categories. Compared with traditional feature extraction and classification algorithms, it has stronger adaptability and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0069] Figure 1 It is a schematic structural diagram of the drilling component in the automatic recognition system for core rock sampling based on image processing and machine learning of the present invention;

[0070] Figure 2 Schematic flow diagram of the automatic identification method for core rock sampling based on image processing and machine learning of the present invention.

[0071] In the figure: 1 - drill bit; 2 - drill pipe; 3 - drill collar; 4 - flank blade; 5 - blade release device; 6 - sampling inner pipe; 7 - rubber shock absorber; 8 - drill sleeve; 9 - shear pin; 10 - water inlet pipe; 11 - recovery pipe. Specific embodiments

[0072] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations.

[0073] Please refer to Figure 1 , the first embodiment of the present invention provides an automatic identification system for core rock sampling based on image processing and machine learning, which includes: a drilling component for performing core rock drilling and extracting core rock samples; a sensor component for collecting images of core rock samples and monitoring parameters during the drilling process; a measurement and control lamp component for providing illumination to provide clear vision for the image collection of the sensor component; an identification component for processing and identifying the collected core rock sample images to obtain an identification result of the core rock category; a relay component for controlling the on-off states of various electrical components; a control and display component for displaying and adjusting various parameters during the drilling process and controlling the operation of the measurement and control lamp component, the drilling component, the sensor component, the identification component and the relay component.

[0074] In a preferred embodiment of the present invention, in the above automatic identification system for core rock sampling based on image processing and machine learning, the drilling component includes a drill tool module, a power output module, a battery module and a drilling propulsion module; the drill tool module includes a drill bit 1, a drill pipe 2, a drill collar 3, a flank blade 4, a blade release device 5 and a sampling inner pipe 6, the drill bit 1 is installed at the front end of the drill pipe 2, the drill bit 1 and the drill pipe 2 are arranged inside the drill collar 3, the rear end of the drill pipe 2 is connected to the drill collar 3, the flank blade 4 is arranged at the front end of the drill bit 1, the rear end of the drill bit 1 is connected to the blade release device 5, and the sampling inner pipe 6 is arranged inside the front end of the drill bit 1; the power output module includes a motor, a reducer, a coupling and a bearing, the output end of the motor is connected to the reducer, and the output end of the reducer is connected to the drill collar 3 and the drill pipe 2 through the coupling; the battery module is connected to the motor and also connected to the control and display component.

[0075] Its technical effects are as follows: The structural design of the drill tool module and the cooperation of components such as the drill bit, drill pipe, flank blades, and sampling inner pipe enable the system to accurately obtain core rock samples from the formation without manual intervention, achieving automated core rock sampling and greatly improving the sampling efficiency; The measurement and control lamp assembly provides stable and uniform lighting conditions, ensuring visual clarity during image acquisition and improving the quality of the images.

[0076] In a preferred embodiment of the present invention, in the above-mentioned automatic recognition system for core rock sampling based on image processing and machine learning, the drill tool module further includes a rubber shock absorber 7, a drill sleeve 8, and a shear pin 9; The rubber shock absorber 7 is arranged at the connection of the drill pipe 2 and the drill collar 3; The drill sleeve 8 is sleeved outside the drill collar 3, and the drill collar 3 and the drill pipe 2 move along the drill sleeve 8; The shear pin 9 is arranged at the rear end of the drill pipe 2, and when a predetermined load is reached, the shear pin 9 breaks.

[0077] Its technical effects are as follows: The rubber shock absorber 7 is arranged at the connection of the drill pipe 2 and the drill collar 3, which can effectively absorb and relieve the energy generated by mechanical vibration and impact during drilling, reduce the adverse impact on the integrity of the core rock sample, and ensure the smoothness of the drilling process; The drill sleeve 8 is sleeved outside the drill collar 3, enabling the drill collar 3 and the drill pipe 2 to move smoothly along the drill sleeve 8, providing a guiding function, ensuring that the drill tool maintains a stable path during drilling, avoiding deviation, protecting the core components of the drill tool, and reducing the direct wear of the drill collar and drill pipe by the external environment; The shear pin is designed to break when a predetermined load is reached, thereby preventing equipment damage caused by overload. The shear pin 9, as a load protection device, will break first when the drill tool encounters abnormal resistance or load during drilling, cutting off the connection between the drill pipe and the power transmission part and avoiding more serious mechanical failures.

[0078] In a preferred embodiment of the present invention, in the above-mentioned automatic recognition system for core rock sampling based on image processing and machine learning, the drilling assembly further includes a cooling and lubrication module; The cooling and lubrication module includes a cooling pump, a water inlet pipe 10, and a recovery pipe 11. The water inlet pipe 10 is connected to the output port of the cooling pump, the recovery pipe 11 is connected to the input port of the cooling pump, the liquid outlet of the water inlet pipe 10 extends into the drill collar 3, and the liquid inlet of the recovery pipe 11 extends into the drill collar 3.

[0079] Its technical effects are as follows: Through the cooling and lubrication module, the temperature around the drill bit and drill pipe is effectively reduced, ensuring the normal operation of the drilling tool under high-load conditions. It can also provide lubrication for the drill bit and drill pipe, reducing the friction between the drill bit and the formation, thereby reducing wear and extending the service life of the drilling tool. The coolant takes away the cuttings accumulated around the drill bit and discharges them outside the drill collar 3 through the recovery pipe 11, thus keeping the drill bit clean and preventing the drill bit from getting stuck or the efficiency from decreasing due to the accumulation of cuttings. Under various complex geological conditions, such as high-temperature or high-friction geological environments, the cooling and lubrication module can effectively adjust and control the temperature and lubrication state during the drilling process, enabling the system to adapt to different working environments and enhancing the diversified application ability of the system.

[0080] In a preferred embodiment of the present invention, in the above-mentioned core rock sampling automatic recognition system based on image processing and machine learning, the measurement and control lamp assembly includes a protective cover, a measurement and control lamp bracket, a light source, and a radiator. The protective cover and the measurement and control lamp bracket are hermetically connected to form a sealed space inside. The light source and the radiator are both installed on the measurement and control lamp bracket and are located inside the sealed space. Specifically, the protective cover is installed on the measurement and control lamp bracket through a sealing ring and a threaded structure, and the edges are closely fitted to ensure waterproof and dustproof performance. The transparent part of the protective cover faces the light source directly to ensure that the light passes through unobstructed. The radiator and the light source adopt an integrated design and are directly installed on the back of the light source, and are in close contact with the light source through thermal conductive paste or a heat pipe to ensure effective heat conduction and dissipation.

[0081] The sensor assembly includes an image sensor, a temperature sensor, a pressure sensor, a vibration sensor, and a data processing unit. The image sensor collects images of the front end of the drill bit 1. The temperature sensor monitors the temperature of the power output module. The pressure sensor monitors the pressure received by the drill bit 1. The vibration sensor monitors the vibration of the drill pipe 2. The data processing unit is connected to the image sensor, the temperature sensor, the pressure sensor, and the vibration sensor through wires and transmits the collected data to the recognition assembly and the control and display assembly. Specifically, the installation position of the image sensor needs to be consistent with the direction of the light source in the measurement and control lamp assembly to ensure clear images can be obtained. The brightness and angle adjustment of the light source must be coordinated with the viewing angle of the image sensor. The temperature sensor is installed near heat-generating components such as motors and reducers and is fixed by thermal conductive glue or a fixture to monitor the temperature change in real time. The pressure sensor is installed near the drill pipe or drill bit and is fixed by threaded connection or flange to monitor the pressure received by the drilling tool in real time. The vibration sensor is installed on the drill pipe or the support structure and is fixed by bolts or a fixture to detect the vibration during the drilling process and ensure the smoothness of the drilling process.

[0082] The relay assembly includes a relay, a terminal block, and connecting wires. One end of the terminal block is connected to the relay through the connecting wire, and the other end is connected to the component to be controlled. The terminal block fixes the connecting wire through screws or spring connectors and is connected to devices such as motors, measurement and control lamp assemblies, and sensors. The functions achieved by the relay assembly include: controlling the switch and brightness adjustment of the lights through the relay to ensure the best illumination under different drilling conditions; controlling the start and stop of the motor and adjusting the drilling speed and direction; controlling the power supply state of the sensor to ensure data collection when needed and saving energy consumption in the non-working state; controlling the power supply and operating state of the image processing device to ensure recognition after image acquisition; and connecting to the control and display assembly to achieve centralized control of each module. Through reasonable installation, connection, and layout design, the relay assembly effectively manages the electrical components in the system and ensures the efficient operation of the entire automatic core rock sampling and recognition system based on image processing and machine learning.

[0083] Its technical effect is that: combined with the protection design of the measurement and control lamp assembly and the real-time monitoring of the sensor assembly, the system can maintain an efficient and stable working state under various complex and harsh environmental conditions. Whether it is a strong light, dusty environment, or a drilling scenario with high temperature, high pressure, and severe vibration, the system can adaptively adjust to ensure the normal operation of the equipment.

[0084] In a preferred embodiment of the present invention, in the above-mentioned automatic core rock sampling and recognition system based on image processing and machine learning, the recognition assembly includes: a feature acquisition module for receiving the core rock sample image obtained by the sensor assembly, sorting out the physical and appearance features of the core rock sample extracted by the drilling assembly, and storing them in the database; a preprocessing module for preprocessing the collected core rock sample image and extracting key features; a model training module for training a core rock category recognition model using machine learning algorithms; and a real-time recognition module for applying the trained core rock category recognition model to newly acquired core rock sample image data to obtain the recognition result of the core rock category and feedback it to the control and display assembly.

[0085] Its technical effect is that: through the mutual cooperation of the feature acquisition, preprocessing, model training, and real-time recognition modules of the recognition assembly, high-precision and efficient recognition of the core rock sample category is achieved. The system can automatically adapt to changes in different environments and core rock types, improving the stability and accuracy of recognition; by automatically recognizing the core rock sample category, the system significantly reduces the workload and error of manual recognition, improves work efficiency and safety. At the same time, the automated recognition process can achieve continuous and uninterrupted core rock category analysis, providing strong support for the intelligent decision-making in the drilling process.

[0086] In a preferred embodiment of the present invention, in the above-mentioned automatic core rock sampling recognition system based on image processing and machine learning, the control and display component includes: a data receiving module for receiving the recognition result of the core rock category obtained by the recognition component; a data parsing module for extracting sample category, feature value and confidence information according to the recognition result; an adjustment and control module for adjusting the working parameters and working modes of the drilling component, the sensor component and the measurement and control lamp component; a status monitoring module for monitoring the working status of the measurement and control lamp component, the drilling component, the sensor component, the recognition component and the relay component, and sending an alarm if an abnormality occurs; and a display module for presenting the recognition result, the working parameters, the working mode and the monitoring information to the user interface.

[0087] The technical effect is that: through the close cooperation of each module of the control and display component, the intelligent control, real-time data processing and all-round monitoring of the system are realized; it can automatically adjust the working parameters according to the real-time data, optimize the operation status of each component, and significantly improve the efficiency of the drilling operation; the display module provides an intuitive and easy-to-understand interface for the operator, facilitating the real-time understanding of the system status and operation progress, and enhancing the user's operation experience and the operability of the system.

[0088] Please refer to Figure 2 , the second embodiment of the present invention provides an automatic core rock sampling recognition method based on image processing and machine learning, which includes: performing core rock drilling to extract core rock samples; performing core rock sample image acquisition and monitoring parameters during the drilling process; sorting out physical and appearance features for the obtained core rock samples and core rock sample images and storing them in a database; preprocessing the collected core rock sample images and extracting key features; using a machine learning algorithm to train a core rock category recognition model; and applying the trained core rock category recognition model to newly obtained core rock sample image data to obtain classification and recognition results.

[0089] In a preferred embodiment of the present invention, in the above-mentioned automatic core rock sampling recognition method based on image processing and machine learning, the structure of the core rock category recognition model includes a convolutional layer, a pooling layer, a fully connected layer and a loss function; the input of the convolutional layer is , which is a multi-dimensional matrix representing the color, texture and morphological features of the core rock sample image, where W is the width of the image, H is the height of the image, and C is the number of channels of the image; the convolutional layer performs a convolution operation on the input feature map X and the convolution kernel W, and outputs the generated feature map Z, representing the local features of the core rock sample image, , where, is the value at position (i, j) and the kth feature map, is the weight of the convolution kernel, is the bias, is the value of the input image at position (i + m, j + n) and the l-th channel; the input of the pooling layer is the feature map output by the convolutional layer , where is the width after pooling, is the height after pooling, K is the number of convolutional kernels; the pooling layer downsamples the feature map Z and outputs a generated reduced-size feature map P, representing the significant local features of the core rock sample image , is the value of the reduced-size feature map P at position (i, j) and the k-th feature map; the input of the fully connected layer is a one-dimensional vector obtained by flattening the reduced-size feature map P for the overall description of the core rock category , with a dimension size of N; the fully connected layer maps the one-dimensional vector to the category space and outputs a generated category score y representing the possibility of each category , where is the weight matrix of the fully connected layer, is the bias vector; the input of the loss function is the category score y and the corresponding actual category label of the core rock ; the loss function calculates the difference between the predicted value and the actual value and outputs a loss value for updating the model parameters , is the predicted score for the i-th class, is the actual label for the i-th class.

[0090] Its technical effect lies in: using the organic combination of the convolutional layer, pooling layer, fully connected layer and loss function to perform feature extraction, dimensionality reduction, category mapping and error optimization on the core rock sample image, and finally achieving high-precision core rock category recognition. Through the local receptive field and weight sharing mechanism of the convolutional layer, it effectively extracts the color, texture and morphological features of the core rock sample image, captures the local features in the image, such as the fine texture and edge features of the rock; the pooling layer downsamples the feature map output by the convolutional layer, retains the significant local features of the image, pays more attention to the key features in the image, significantly reduces the data dimension, not only reduces the computational complexity, improves the training efficiency of the model, but also effectively reduces the risk of model overfitting; the fully connected layer flattens the pooled feature map into a one-dimensional vector and maps it to the category space, generating the possibility scores of each category, enabling the model to accurately judge the category of the entire core rock sample based on the local features extracted by the pooling layer, enhancing the overall expression ability of the model and improving the accuracy of core rock category recognition; the loss function calculates the difference between the model predicted value and the actual label, and feeds back the error for updating the model parameters. By continuously optimizing the loss function, gradually adjusting the convolutional kernels, pooling parameters and weights of the fully connected layer, the prediction results become more accurate.

[0091] In a preferred embodiment of the present invention, in the above-mentioned automatic identification method of core rock sampling based on image processing and machine learning, applying the trained core rock category recognition model to newly acquired core rock sample image data to obtain classification and recognition results includes: the outputs of multiple trained core rock category recognition models are respectively ; synthesizing the outputs of several models for the newly acquired core rock sample image data to obtain the final classification and recognition results , where is the weight of the j-th model.

[0092] Its technical effect lies in that: by introducing multiple trained core rock category recognition models, each model is good at identifying different types of core rock samples, and weighting and fusing the outputs of these models can effectively improve the overall performance of the recognition system and help improve the generalization ability of the recognition system for unseen samples. By synthesizing the prediction results of multiple models, the system can show better stability and accuracy when dealing with different geological conditions, different image qualities or different sample types.

[0093] It should be understood that the above specific embodiments of the present invention are only used for exemplary illustration or explanation of the principle of the present invention, and do not constitute a limitation to the present invention. Therefore, any modifications, equivalent replacements, improvements, etc. made without departing from the spirit and scope of the present invention shall be included within the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or equivalent forms of such scope and boundaries.

Claims

1. An automatic recognition system for core rock sampling based on image processing and machine learning, characterized in that Comprising: A drilling assembly for core rock drilling to extract core rock samples; A sensor assembly for collecting images of core rock samples and monitoring parameters during the drilling process; A measurement and control lamp assembly for providing illumination to provide clear vision for the image collection of the sensor assembly; An identification assembly for processing and identifying the collected core rock sample images to obtain an identification result of the core rock category; A relay assembly for controlling the on / off states of various electrical components; A control and display assembly for displaying and adjusting various parameters during the drilling process and controlling the operation of the measurement and control lamp assembly, the drilling assembly, the sensor assembly, the identification assembly, and the relay assembly; The drilling assembly includes a drilling tool module, a power output module, a battery module, and a drilling propulsion module; The drilling tool module includes a drill bit (1), a drill pipe (2), a drill collar (3), a flank blade (4), a blade release (5), and a sampling inner tube (6). The drill bit (1) is installed at the front end of the drill pipe (2). The drill bit (1) and the drill pipe (2) are disposed within the drill collar (3). The rear end of the drill pipe (2) is connected to the drill collar (3). The flank blade (4) is disposed at the front end of the drill bit (1). The rear end of the drill bit (1) is connected to the blade release (5). The sampling inner tube (6) is disposed inside the front end of the drill bit (1); The power output module includes an electric motor, a reducer, a coupling, and a bearing. The output end of the electric motor is connected to the reducer. The output end of the reducer is connected to the drill collar (3) and the drill pipe (2) through the coupling; The battery module is connected to the electric motor and also connected to the control and display assembly.

2. The automatic core rock sampling and identification system based on image processing and machine learning according to claim 1, wherein The drilling tool module further includes a rubber shock absorber (7), a drill sleeve (8), and a shear pin (9); The rubber shock absorber (7) is disposed at the connection between the drill pipe (2) and the drill collar (3); The drill sleeve (8) is sleeved outside the drill collar (3). The drill collar (3) and the drill pipe (2) move along the drill sleeve (8); The shear pin (9) is disposed at the rear end of the drill pipe (2). When a predetermined load is reached, the shear pin (9) breaks.

3. The automatic recognition system for core rock sampling based on image processing and machine learning according to claim 1, characterized in that The drilling assembly further includes a cooling and lubrication module; The cooling and lubrication module includes a cooling pump, a water inlet pipe (10), and a recovery pipe (11). The water inlet pipe (10) is connected to the output port of the cooling pump. The recovery pipe (11) is connected to the input port of the cooling pump. The liquid outlet of the water inlet pipe (10) extends into the drill collar (3). The liquid inlet of the recovery pipe (11) extends into the drill collar (3); 4. The automatic recognition system for core rock sampling based on image processing and machine learning according to claim 1, wherein The measurement and control lamp assembly includes a protective cover, a measurement and control lamp bracket, a light source, and a radiator. The protective cover and the measurement and control lamp bracket are hermetically connected to form a sealed space inside. The light source and the radiator are both installed on the measurement and control lamp bracket and are located within the sealed space; The sensor assembly includes an image sensor, a temperature sensor, a pressure sensor, a vibration sensor, and a data processing unit. The image sensor captures images of the front end of the drill bit (1). The temperature sensor monitors the temperature of the power output module. The pressure sensor monitors the pressure exerted on the drill bit (1). The vibration sensor monitors the vibration of the drill pipe (2). The data processing unit is connected to the image sensor, the temperature sensor, the pressure sensor, and the vibration sensor through wires, and transmits the collected data to the recognition assembly and the control and display assembly; The relay assembly includes a relay, a terminal block, and connecting wires. One end of the terminal block is connected to the relay through the connecting wire, and the other end is connected to the element to be controlled.

5. The automatic recognition system for core rock sampling based on image processing and machine learning according to claim 1, wherein The recognition assembly includes: A feature acquisition module, which is used to receive the core rock sample image obtained by the sensor assembly, sort out the physical and appearance features of the core rock sample extracted by the drilling assembly, and store them in a database; A preprocessing module, which is used to preprocess the acquired core rock sample image and extract key features; A model training module, which is used to train a core rock category recognition model using machine learning algorithms; A real-time recognition module, which is used to apply the trained core rock category recognition model to newly acquired core rock sample image data to obtain the recognition result of the core rock category, and feedback it to the control and display assembly.

6. The automatic recognition system for core rock sampling based on image processing and machine learning according to claim 1, characterized in that, The control and display assembly includes: A data receiving module, which is used to receive the recognition result of the core rock category obtained by the recognition assembly; A data analysis module, which is used to extract sample category, feature value, and confidence information according to the recognition result; An adjustment and control module, which is used to adjust the working parameters and working modes of the drilling assembly, the sensor assembly, and the measurement and control lamp assembly; A status monitoring module, which is used to monitor the working status of the measurement and control lamp assembly, the drilling assembly, the sensor assembly, the recognition assembly, and the relay assembly. If an abnormality occurs, an alarm is issued; A display module, which is used to display the recognition result, the working parameters, the working mode, and the monitoring information to the user interface.

Images