Computer Vision-Based Drilling Rock Formation Exploration Method and System

Abstract

The present invention discloses a drilling rock formation exploration method and system based on computer vision. The present invention constructs an algorithm input dimension according to the porosity, permeability, lithology, and formation sequence drilling geological data of the drilling rock formation under different formation pressures, constructs algorithms for identifying the porosity, permeability, lithology, and formation sequence of the drilling rock formation according to the algorithm input dimension, conducts an exploration risk assessment based on the abnormal data of the porosity, permeability, lithology, and formation sequence of the drilling rock formation in the core samples at different formation temperatures, generates an exploration risk assessment coefficient, and finally sets mining risk prevention measures according to the exploration risk assessment coefficient, and conducts human resource and material resource scheduling based on the mining risk prevention measures. The present invention can automatically classify and detect anomalies in drilling geological data, timely discover potential exploration risks, optimize the risk assessment process, and reduce human intervention.

Description

Technical Field

[0001] The present invention relates to the field of drilling rock formation exploration, and particularly to a method and system for drilling rock formation exploration based on computer vision. Background Art

[0002] With the continuous growth of global energy demand, drilling operations have become an important part of oil and gas exploration. However, geological exploration work during drilling often faces complex challenges, including rock formation identification, measurement of porosity and permeability, and assessment of potential exploitation risks. Traditional drilling exploration methods usually rely on manual operations and limited sensor data, with problems such as low data acquisition accuracy, poor real-time performance, and difficulty in comprehensively covering the dynamic changes of different strata. In addition, existing technologies often fail to detect abnormal situations in a timely manner when dealing with deep drilling geological data, resulting in inaccurate prediction of exploitation risks and affecting production efficiency and safety. Therefore, a method for drilling rock formation exploration based on computer vision has emerged, using advanced computer vision technology, combined with a multi-modal sensing platform and algorithm optimization, aiming to improve data acquisition and risk assessment capabilities during drilling, and further optimize resource scheduling and exploitation safety.

[0003] Current drilling rock formation exploration technologies mainly rely on traditional physical detection tools and data analysis methods, such as seismic exploration, drilling fluid analysis, etc. Although they can provide geological information to a certain extent, there are still some obvious disadvantages. First, traditional technologies are usually slow in obtaining geological data and rely on a large amount of manual intervention, resulting in poor real-time performance and difficulty in meeting the requirements of modern drilling operations for rapid response. Second, most existing exploration methods are limited to data acquisition in a single dimension and lack comprehensive analysis of complex formation characteristics, unable to fully reflect the diversity of geological changes. For example, traditional core analysis can only be carried out through manual inspection, often ignoring the dynamic changes during drilling and easily missing potential risk points. In addition, most existing risk assessment systems rely on historical data for prediction and are difficult to cope with the complex effects of dynamic factors such as formation pressure on rock formation stability, resulting in inaccurate assessment results. Summary of the Invention

[0004] The present invention overcomes the deficiencies of the prior art and provides a method and system for drilling rock formation exploration based on computer vision.

[0005] In a first aspect of the present invention, a method for drilling rock formation exploration based on computer vision is provided, including the following steps:

[0006] Build a multi-modal computer vision sensing platform, and optimize the multi-modal computer vision sensing platform to obtain an optimized multi-modal computer vision sensing platform. Use the multi-modal computer vision sensing platform to control the RockSense+Seequent Leapfrog system to obtain the location of different regions and drilling geological data at different depths of the drilling rock formation;

[0007] Obtain porosity, permeability, lithology, and formation sequence drilling geological data of the drilling rock formation under different formation pressures through the rock formation edge computing gateway. Build the algorithm input dimension based on the porosity, permeability, lithology, and formation sequence drilling geological data of the drilling rock formation under different formation pressures, and build an identification algorithm for the porosity, permeability, lithology, and formation sequence of the drilling rock formation according to the algorithm input dimension;

[0008] Use the identification algorithm for the porosity, permeability, lithology, and formation sequence of the drilling rock formation to identify the drilling geological data at different locations and depths of the drilling rock formation, obtain the abnormal data of the porosity, permeability, lithology, and formation sequence of the drilling rock formation in the core samples at different formation temperatures, and conduct an exploration risk assessment based on the abnormal data of the porosity, permeability, lithology, and formation sequence of the drilling rock formation in the core samples at different formation temperatures to generate an exploration risk assessment coefficient;

[0009] Set mining risk prevention measures according to the exploration risk assessment coefficient, and schedule human and material resources based on the mining risk prevention measures.

[0010] Furthermore, in this method, build a multi-modal computer vision sensing platform, and optimize the multi-modal computer vision sensing platform to obtain an optimized multi-modal computer vision sensing platform, specifically including:

[0011] Build a multi-modal computer vision sensing platform, and test the multi-modal computer vision sensing platform to obtain the fluctuation range of the RockSense+Seequent Leapfrog system monitoring rock formation hardness threshold under different formation pressures of the multi-modal computer vision sensing platform. Build a prediction model for the RockSense+Seequent Leapfrog system monitoring rock formation hardness threshold fluctuation through random forest;

[0012] Input the fluctuation range of the RockSense+Seequent Leapfrog system monitoring rock formation hardness threshold under different formation pressures of the multi-modal computer vision sensing platform into the prediction model for the RockSense+Seequent Leapfrog system monitoring rock formation hardness threshold fluctuation for training to obtain a trained prediction model for the RockSense+Seequent Leapfrog system monitoring rock formation hardness threshold fluctuation;

[0013] Obtain the fluctuation range of the RockSense+SeequentLeapfrog system monitoring the rock formation hardness threshold within a preset time for the multimodal computer vision sensing platform and input it into the trained RockSense+SeequentLeapfrog system monitoring the rock formation hardness threshold fluctuation prediction model for prediction, and obtain the RockSense+Seequent Leapfrog system of the multimodal computer vision sensing platform monitoring the fluctuation of the rock formation hardness threshold with the fracture density and morphology per unit depth;

[0014] Obtain the real-time RockSense+Seequent Leapfrog system monitoring fluctuation range of the multimodal computer vision sensing platform. When the real-time RockSense+Seequent Leapfrog system monitoring fluctuation range is greater than the RockSense+Seequent Leapfrog system of the multimodal computer vision sensing platform monitoring the fluctuation of the rock formation hardness threshold with the fracture density and morphology per unit depth, then adjust the real-time RockSense+SeequentLeapfrog system monitoring fluctuation range according to the RockSense+Seequent Leapfrog system of the multimodal computer vision sensing platform monitoring the fluctuation of the rock formation hardness threshold with the fracture density and morphology per unit depth to obtain an optimized multimodal computer vision sensing platform.

[0015] Furthermore, in this method, obtain the porosity, permeability, lithology, and formation sequence drilling geological data of the drilling rock formation under different formation pressures through the rock formation edge computing gateway, and build the algorithm input dimension according to the porosity, permeability, lithology, and formation sequence drilling geological data of the drilling rock formation under different formation pressures. Build the porosity, permeability, lithology, and formation sequence identification algorithm of the drilling rock formation according to the algorithm input dimension, specifically including:

[0016] Obtain the porosity, permeability, lithology, and formation sequence drilling geological data of the drilling rock formation under different formation pressures through the rock formation edge computing gateway, and classify the porosity, permeability, lithology, and formation sequence types of the porosity, permeability, lithology, and formation sequence drilling geological data of the drilling rock formation under different formation pressures to obtain the drilling geological data of each porosity, permeability, lithology, and formation sequence type. Build the algorithm input dimension of each porosity, permeability, lithology, and formation sequence type according to the drilling geological data of each porosity, permeability, lithology, and formation sequence type;

[0017] Input the drilling geological data in the algorithm input dimensions of each porosity, permeability, lithology, and formation sequence type into the anomaly One-Class SVM model to obtain the porosity, permeability, lithology, and formation sequence anomaly data existing in different groups of drilling geological data, and determine whether the porosity, permeability, lithology, and formation sequence anomaly data existing in the drilling geological data exceed the preset interval, and introduce the Autoencoder;

[0018] When the porosity, permeability, lithology, and formation sequence anomaly data existing in the drilling geological data exceed the preset interval, obtain the porosity, permeability, lithology, and formation sequence anomaly data corresponding to the porosity, permeability, lithology, and formation sequence type labels of the drilling geological data per unit depth as the relevant porosity, permeability, lithology, and formation sequence anomaly data. When the porosity, permeability, lithology, and formation sequence anomaly data existing in the drilling geological data exceed the preset value, take the porosity, permeability, lithology, and formation sequence anomaly data corresponding to the porosity, permeability, lithology, and formation sequence type labels of the drilling geological data per unit depth as the relevant porosity, permeability, lithology, and formation sequence anomaly data;

[0019] Input the relevant porosity, permeability, lithology, and formation sequence anomaly data into the Autoencoder, so that the encoding layer focuses on the relevant porosity, permeability, lithology, and formation sequence anomaly data, obtain the dimension of the neurons in the encoding layer, build an algorithm for identifying the porosity, permeability, lithology, and formation sequence of the drilling rock formation based on Threshold-based Methods, and input the dimension of the neurons in the encoding layer in the algorithm input dimension into the algorithm for identifying the porosity, permeability, lithology, and formation sequence of the drilling rock formation to perform a safety peak judgment.

[0020] Furthermore, in this method, identify the drilling geological data at different regional positions and different depths of the drilling rock formation through the algorithm for identifying the porosity, permeability, lithology, and formation sequence of the drilling rock formation, obtain the porosity, permeability, lithology, and formation sequence anomaly data of the drilling rock formation in different formation temperature core samples, and perform an exploration risk assessment based on the porosity, permeability, lithology, and formation sequence anomaly data of the drilling rock formation in different formation temperature core samples to generate an exploration risk assessment coefficient, specifically including:

[0021] Input the drilling geological data at different regional positions and different depths of the drilling rock formation into the algorithm for identifying the porosity, permeability, lithology, and formation sequence of the drilling rock formation for identification, obtain the porosity, permeability, lithology, and formation sequence anomaly data of the drilling rock formation in different formation temperature core samples, and preset different exploitation red lines for exploring oil and gas reserves;

[0022] According to different exploitation red lines for exploring oil and gas reserves, classify different magnitudes of oil and gas reserves by exploring the porosity, permeability, lithology, and abnormal data of formation sequences in core samples of drilling rock formations at different formation temperatures, obtain different magnitudes of oil and gas reserves from the porosity, permeability, lithology, and abnormal data of formation sequences in core samples of drilling rock formations at different formation temperatures, and obtain mineral distribution data at the preset depth where sedimentation occurs;

[0023] Generate an exploration risk assessment and an exploration risk assessment coefficient based on different magnitudes of oil and gas reserves explored from the porosity, permeability, lithology, and abnormal data of formation sequences in core samples of drilling rock formations at different formation temperatures, mineral distribution data at the preset depth where sedimentation occurs, and the porosity, permeability, lithology, and abnormal data of formation sequences in core samples of drilling rock formations at different formation temperatures.

[0024] Furthermore, in this method, set exploitation risk prevention measures according to the exploration risk assessment coefficient, specifically including:

[0025] Obtain mineral distribution data at the preset depth where sedimentation occurs based on the exploration risk assessment coefficient, build a retrieval tag based on the mineral distribution data at the preset depth where sedimentation occurs, and perform a retrieval according to the retrieval tag to obtain a fluid sample of the drilling rock formation;

[0026] Obtain the location distributions of the oil and gas layers and the water layer based on the fluid sample of the drilling rock formation, build a device for measuring the material content of the location distributions of the oil and gas layers and the water layer, input the location distributions of the oil and gas layers and the water layer into the device for measuring the material content of the location distributions of the oil and gas layers and the water layer to perform material content measurement, and obtain different carbon concentration measurement results from high to low concentration;

[0027] Set exploitation risk prevention measures at the preset depth based on the different carbon concentration measurement results from high to low concentration, and form a document report on the exploitation risk prevention measures.

[0028] Furthermore, in this method, perform human resource and material resource scheduling based on the exploitation risk prevention measures, specifically including:

[0029] Obtain the stress and strain depth information of crustal movement per unit depth and the mineral distribution data of the porosity, permeability, lithology, and formation sequence at the preset depth where an underground river exists. Calculate the influence weights of the rock formation stability at the locations of each crustal movement and the mineral distribution data at the preset depth where sedimentation occurs under different faults based on the stress and strain depth information of crustal movement per unit depth and the mineral distribution data at the preset depth where sedimentation occurs;

[0030] Introduce a multi-modal parameter comprehensive evaluation model, set the coefficient of the influence weight of rock layer stability according to the multi-modal parameter comprehensive evaluation model, initialize the parameter category of the multi-modal parameter comprehensive evaluation model of crustal movement according to the mineral distribution data at the preset depth where sedimentation occurs at the location of each crustal movement and the influence weight of rock layer stability under different faults, and obtain the mining cost of crustal movement per unit area;

[0031] Judge whether the influence weight of rock layer stability under different faults of the mineral distribution data at the preset depth where sedimentation occurs at the location of the crustal movement is greater than the preset influence weight of rock layer stability. When the influence weight of rock layer stability under different faults of the mineral distribution data at the preset depth where sedimentation occurs at the location of the crustal movement is less than the preset influence weight of rock layer stability, output the mining cost of crustal movement per unit area;

[0032] When the influence weight of rock layer stability under different faults of the mineral distribution data at the preset depth where sedimentation occurs at the location of the crustal movement is greater than the preset influence weight of rock layer stability, re-evaluate the mining cost of crustal movement per unit area until the influence weight of rock layer stability under different faults of the mineral distribution data at the preset depth where sedimentation occurs at the location of the crustal movement is less than the preset influence weight of rock layer stability, and dispatch human and material resources according to the mining risk prevention measures.

[0033] The second aspect of the present invention provides a drilling rock layer exploration system based on computer vision, and the system includes:

[0034] A multi-modal computer vision sensing data integration module, which builds a multi-modal computer vision sensing platform, and obtains an optimized multi-modal computer vision sensing platform by optimizing the multi-modal computer vision sensing platform, and controls the RockSense+Seequent Leapfrog system through the multi-modal computer vision sensing platform to obtain the drilling geological data at different regional positions and different depths of the drilling rock layer;

[0035] A rock layer edge computing gateway data acquisition module, which acquires the porosity, permeability, lithology, and stratigraphic sequence drilling geological data under different formation pressures of the drilling rock layer through the rock layer edge computing gateway, builds an algorithm input dimension according to the porosity, permeability, lithology, and stratigraphic sequence drilling geological data under different formation pressures of the drilling rock layer, and builds an identification algorithm for the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock layer according to the algorithm input dimension;

[0036] An exploration risk assessment coefficient generation module, which identifies the drilling geological data at different regional positions and different depths of the drilling rock formation through algorithms for the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation, obtains the abnormal data of the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation in the core samples of different formation temperatures, and conducts an exploration risk assessment based on the abnormal data of the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation in the core samples of different formation temperatures to generate an exploration risk assessment coefficient;

[0037] A different resource scheduling module, which sets mining risk prevention measures according to the exploration risk assessment coefficient and schedules human resources and material resources based on the mining risk prevention measures.

[0038] Beneficial effects:

[0039] The present invention builds a multi-modal computer vision sensing platform, optimizes the multi-modal computer vision sensing platform to obtain an optimized multi-modal computer vision sensing platform, controls the RockSense+Seequent Leapfrog system through the multi-modal computer vision sensing platform to obtain the position of different regions of the drilling rock formation and the drilling geological data at different depths, and then obtains the porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures through the rock formation edge computing gateway. An algorithm input dimension is built based on the porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures, and an identification algorithm for the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation is built according to the algorithm input dimension. Thus, the identification algorithm for the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation is used to identify the drilling geological data at different positions and depths of the drilling rock formation, and the abnormal data of the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation in the core samples at different formation temperatures is obtained. An exploration risk assessment is carried out based on the abnormal data of the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation in the core samples at different formation temperatures to generate an exploration risk assessment coefficient. Finally, mining risk prevention measures are set according to the exploration risk assessment coefficient, and human and material resources are scheduled based on the mining risk prevention measures. By integrating advanced vision sensing technology and intelligent algorithms, the present invention can greatly improve the accuracy and efficiency of data collection during the drilling process. By building a multi-modal computer vision sensing platform and combining the RockSense and Seequent Leapfrog systems, the characteristics of the rock formation can be monitored in real time at different formation positions and depths, and key geological data such as porosity, permeability, and lithology can be automatically identified. This technology can acquire and process large-scale image and sensor data in real time, greatly improving the real-time and comprehensiveness of data collection. In addition, algorithm models (such as One-Class SVM and Autoencoder) can automatically classify and detect anomalies in the drilling geological data, timely discover potential exploration risks, optimize the risk assessment process, and reduce human intervention. Generally speaking, the present invention provides a more efficient and accurate technical means for drilling operations, solving many deficiencies in the prior art in aspects such as real-time data processing, risk assessment, and resource scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The flowchart of the method of the present invention is shown;

[0041] Figure 2 The composition diagram of the system module of the present invention is shown. DETAILED DESCRIPTION OF THE INVENTION

[0042] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The following further describes the present application in detail with reference to the drawings and specific embodiments.

[0043] As Figure 1 shown, the first aspect of the present invention provides a drilling rock formation exploration method based on computer vision, including the following steps:

[0044] Step A1: Build a multi-modal computer vision sensing platform, and obtain the optimized multi-modal computer vision sensing platform by optimizing the multi-modal computer vision sensing platform. Control the RockSense+Seequent Leapfrog system through the multi-modal computer vision sensing platform to obtain the drilling geological data of different regional positions and different depths of the drilling rock formation;

[0045] Step A2: Obtain the porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures through the formation edge computing gateway, build the algorithm input dimension according to the porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures, and build the identification algorithm for the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation according to the algorithm input dimension;

[0046] Step A3: Identify the drilling geological data of different regional positions and different depths of the drilling rock formation through the identification algorithm for the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation, obtain the abnormal data of the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation in the core samples of different formation temperatures, and conduct exploration risk assessment according to the abnormal data of the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation in the core samples of different formation temperatures, and generate an exploration risk assessment coefficient;

[0047] Step A4: Set mining risk prevention measures according to the exploration risk assessment coefficient, and conduct human resource and material resource scheduling based on the mining risk prevention measures.

[0048] It should be noted that the present invention processes the target porosity, permeability, lithology, and stratigraphic sequence abnormal data in the algorithm input dimension through the Autoencoder, so that the encoding layer focuses on the target porosity, permeability, lithology, and stratigraphic sequence abnormal data in the algorithm input dimension, which can suppress the interference brought by multi-scale features to the identification algorithm for the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation, and can improve the identification accuracy of the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation.

[0049] Further, building a multi-modal computer vision sensing platform, and obtaining the optimized multi-modal computer vision sensing platform by optimizing the multi-modal computer vision sensing platform, specifically includes:

[0050] Build a multi-modal computer vision sensing platform, and through testing the multi-modal computer vision sensing platform, obtain the fluctuation range of the rock layer hardness threshold monitored by the RockSense+Seequent Leapfrog system under different formation pressures of the multi-modal computer vision sensing platform. Build a prediction model for the fluctuation of the rock layer hardness threshold monitored by the RockSense+Seequent Leapfrog system through random forest;

[0051] Input the fluctuation range of the rock layer hardness threshold monitored by the RockSense+Seequent Leapfrog system under different formation pressures of the multi-modal computer vision sensing platform into the prediction model for the fluctuation of the rock layer hardness threshold monitored by the RockSense+Seequent Leapfrog system for training, and obtain the trained prediction model for the fluctuation of the rock layer hardness threshold monitored by the RockSense+Seequent Leapfrog system;

[0052] Obtain the fluctuation range of the rock layer hardness threshold monitored by the RockSense+Seequent Leapfrog system of the multi-modal computer vision sensing platform within a preset time and input it into the trained prediction model for the fluctuation of the rock layer hardness threshold monitored by the RockSense+Seequent Leapfrog system for prediction, and obtain the fluctuation of the rock layer hardness threshold monitored by the RockSense+Seequent Leapfrog system of the multi-modal computer vision sensing platform for the fracture density and morphology per unit depth;

[0053] Obtain the real-time RockSense+Seequent Leapfrog system monitoring fluctuation range of the multi-modal computer vision sensing platform. When the real-time RockSense+Seequent Leapfrog system monitoring fluctuation range is greater than the fluctuation of the rock layer hardness threshold monitored by the RockSense+Seequent Leapfrog system of the multi-modal computer vision sensing platform for the fracture density and morphology per unit depth, adjust the real-time RockSense+Seequent Leapfrog system monitoring fluctuation range according to the fluctuation of the rock layer hardness threshold monitored by the RockSense+Seequent Leapfrog system of the multi-modal computer vision sensing platform for the fracture density and morphology per unit depth, and obtain the optimized multi-modal computer vision sensing platform.

[0054] It should be noted that RockSense is a technology launched by Schlumberger. It is mainly used to measure and analyze relevant data such as the mechanical properties of rocks in real time during the drilling process. By monitoring and analyzing various parameters (such as torque, rotational speed, and drilling pressure) during the drilling process of the drill bit, and combining relevant algorithms and models, the characteristics of the drilled rocks can be inferred, such as information about the hardness and strength of the rocks. Seequent Leapfrog is a powerful geological modeling and analysis software developed by Seequent. It can integrate data from multiple sources, including geological, geophysical, and geochemical data, and build a three-dimensional geological model through advanced algorithms and visualization techniques. It has a wide range of applications in fields such as geological exploration, resource assessment, and underground engineering design. Users can use this software to conduct detailed analysis and display of geological structures, and predict the distribution and property changes of geological bodies, etc.

[0055] When RockSense is combined with Seequent Leapfrog to form the RockSense + Seequent Leapfrog system, it means combining the rock property data obtained in real time during the drilling process (from RockSense) with the powerful geological modeling and analysis capabilities of Seequent Leapfrog. In this method, this system can more accurately monitor the fluctuation range of the rock hardness threshold under different formation pressures. Specifically, RockSense provides real-time rock mechanical property data, while Seequent Leapfrog integrates, models, and analyzes these data and other relevant geological data to help researchers and engineers better understand the characteristics and change laws of underground rock formations, thereby providing a more reliable basis for subsequent predictions and decisions. For example, in fields such as oil and gas extraction and underground mineral resource development, this combined system can more accurately evaluate the formation conditions, optimize the extraction plan, and improve the resource extraction efficiency and safety. Through this method, the RockSense + Seequent Leapfrog system of the multimodal computer vision sensing platform based on the fracture density and morphology per unit depth can adjust the monitoring fluctuation range of the rock hardness threshold for the real-time RockSense + Seequent Leapfrog system monitoring fluctuation range, so that the human-machine integrated control network controls the RockSense + Seequent Leapfrog system monitoring fluctuation range to meet the predetermined requirements and ensure the stability of the multimodal computer vision sensing platform.

[0056] Further, obtain the porosity, permeability, lithology, and formation sequence drilling geological data of the drilling formation under different formation pressures through the formation edge computing gateway, build the algorithm input dimension based on the porosity, permeability, lithology, and formation sequence drilling geological data of the drilling formation under different formation pressures, and build the identification algorithm for the porosity, permeability, lithology, and formation sequence of the drilling formation according to the algorithm input dimension, specifically including:

[0057] Obtain the porosity, permeability, lithology, and formation sequence drilling geological data of the drilling formation under different formation pressures through the formation edge computing gateway, classify the porosity, permeability, lithology, and formation sequence types of the porosity, permeability, lithology, and formation sequence drilling geological data of the drilling formation under different formation pressures to obtain the drilling geological data of each porosity, permeability, lithology, and formation sequence type, and build the algorithm input dimension of each porosity, permeability, lithology, and formation sequence type according to the drilling geological data of each porosity, permeability, lithology, and formation sequence type;

[0058] Input the drilling geological data in the algorithm input dimension of each porosity, permeability, lithology, and formation sequence type into the anomaly One-Class SVM model to obtain the porosity, permeability, lithology, and formation sequence anomaly data existing in different groups of drilling geological data, and determine whether the porosity, permeability, lithology, and formation sequence anomaly data existing in the drilling geological data exceeds the preset interval, and introduce the Autoencoder;

[0059] When the porosity, permeability, lithology, and formation sequence anomaly data existing in the drilling geological data exceeds the preset interval, obtain the porosity, permeability, lithology, and formation sequence anomaly data corresponding to the porosity, permeability, lithology, and formation sequence type label information of the drilling geological data per unit depth as the relevant porosity, permeability, lithology, and formation sequence anomaly data. When the porosity, permeability, lithology, and formation sequence anomaly data existing in the drilling geological data exceeds the preset value, use the porosity, permeability, lithology, and formation sequence anomaly data corresponding to the porosity, permeability, lithology, and formation sequence type label information of the drilling geological data per unit depth as the relevant porosity, permeability, lithology, and formation sequence anomaly data;

[0060] Input the relevant porosity, permeability, lithology, and formation sequence anomaly data into the Autoencoder, so that the encoding layer focuses on the relevant porosity, permeability, lithology, and formation sequence anomaly data, obtain the neuron dimension of the encoding layer, build an identification algorithm for the porosity, permeability, lithology, and formation sequence of the drilling rock formation based on Threshold-based Methods, and input the neuron dimension of the encoding layer in the algorithm input dimension into the identification algorithm for the porosity, permeability, lithology, and formation sequence of the drilling rock formation to perform safety peak judgment.

[0061] It should be noted that the drilling geological data of porosity, permeability, lithology, and formation sequence include data such as crack porosity, permeability, lithology, and formation sequence drilling geological data, corrosion porosity, permeability, lithology, and formation sequence drilling geological data, porosity, permeability, lithology, and formation sequence drilling geological data after burning, etc. Since there may be at least two types of porosity, permeability, lithology, and formation sequence in the drilling geological data in the algorithm input dimension of each porosity, permeability, lithology, and formation sequence type, such as crack porosity, permeability, lithology, and formation sequence, corrosion porosity, permeability, lithology, and formation sequence, etc. Since during training, the algorithm input dimensions of multiple porosity, permeability, lithology, and formation sequence types should be input into Threshold-based Methods for training. When there are at least two types of label information of porosity, permeability, lithology, and formation sequence in a drilling geological data during training, interference will occur at this time. By integrating the Autoencoder with this method, the encoding layer can be concentrated on the relevant porosity, permeability, lithology, and formation sequence anomaly data, and the interference of multi-scale porosity, permeability, lithology, and formation sequence anomaly data on the identification algorithm for the porosity, permeability, lithology, and formation sequence of the drilling rock formation can be suppressed, thereby improving the prediction accuracy of the model.

[0062] Furthermore, in this method, identify the drilling geological data at different regional positions and different depths of the drilling rock formation through the identification algorithm for the porosity, permeability, lithology, and formation sequence of the drilling rock formation, obtain the porosity, permeability, lithology, and formation sequence anomaly data of the drilling rock formation in the core samples of different formation temperatures, and conduct exploration risk assessment based on the porosity, permeability, lithology, and formation sequence anomaly data of the drilling rock formation in the core samples of different formation temperatures to generate an exploration risk assessment coefficient, specifically including:

[0063] Input the drilling geological data at different regional positions and different depths of the drilling rock formation into the identification algorithm for the porosity, permeability, lithology, and formation sequence of the drilling rock formation for identification, obtain the porosity, permeability, lithology, and formation sequence anomaly data of the drilling rock formation in the core samples of different formation temperatures, and preset different extraction red lines for exploration oil and gas reserves;

[0064] According to different exploitation red lines for exploring oil and gas reserves, classify different magnitudes of exploring oil and gas reserves for the porosity, permeability, lithology, and abnormal data of formation sequences of the drilling rock formation in core samples at different formation temperatures, obtain different magnitudes of exploring oil and gas reserves for the porosity, permeability, lithology, and abnormal data of the drilling rock formation in core samples at different formation temperatures, and obtain the mineral distribution data at the preset depth where sedimentation occurs;

[0065] Generate an exploration risk assessment and an exploration risk assessment coefficient based on different magnitudes of exploring oil and gas reserves for the porosity, permeability, lithology, and abnormal data of the drilling rock formation in core samples at different formation temperatures, the mineral distribution data at the preset depth where sedimentation occurs, and the porosity, permeability, lithology, and abnormal data of the drilling rock formation in core samples at different formation temperatures.

[0066] It should be noted that the criteria for different magnitudes of exploring oil and gas reserves can be set according to the porosity, permeability, lithology, types of formation sequences, porosity, permeability, lithology, and magnitudes of formation sequences. Among them, different magnitudes of exploring oil and gas reserves include low magnitudes of exploring oil and gas reserves, medium magnitudes of exploring oil and gas reserves, high magnitudes of exploring oil and gas reserves, etc.

[0067] Furthermore, set mining risk prevention measures according to the exploration risk assessment coefficient, specifically including:

[0068] Obtain the mineral distribution data at the preset depth where sedimentation occurs according to the exploration risk assessment coefficient, build a retrieval tag based on the mineral distribution data at the preset depth where sedimentation occurs, and perform a retrieval according to the retrieval tag to obtain the fluid sample of the drilling rock formation;

[0069] Obtain the location distributions of the oil and gas layer and the water layer according to the fluid sample of the drilling rock formation, build a device for measuring the material content of the location distributions of the oil and gas layer and the water layer, input the location distributions of the oil and gas layer and the water layer into the device for measuring the material content of the location distributions of the oil and gas layer and the water layer to perform material content measurement, and obtain different carbon concentration measurement results from high to low;

[0070] Set mining risk prevention measures at the preset depth based on different carbon concentration measurement results from high to low, and form a document report on the mining risk prevention measures.

[0071] It should be noted that due to the limited crustal movement, more reasonable mining risk prevention measures can be formulated through this method.

[0072] Furthermore, perform human resource and material resource scheduling based on the mining risk prevention measures, specifically including:

[0073] Obtain the stress and strain depth information of crustal movement per unit depth, as well as the porosity, permeability, lithology, and mineral distribution data of the preset depth of the underground river in the formation sequence. Calculate the influence weights of the rock layer stability at the location of each crustal movement and the mineral distribution data at the preset depth where sedimentation occurs under different faults based on the stress and strain depth information of crustal movement per unit depth and the mineral distribution data at the preset depth where sedimentation occurs.

[0074] Introduce a multi-modal parameter comprehensive evaluation model. Set the coefficient of the influence weight of the rock layer stability according to the multi-modal parameter comprehensive evaluation model. Initialize the parameter category of the multi-modal parameter comprehensive evaluation model of crustal movement based on the influence weights of the rock layer stability at the location of each crustal movement and the mineral distribution data at the preset depth where sedimentation occurs under different faults, and obtain the mining cost of crustal movement per unit area.

[0075] Judge whether the influence weights of the rock layer stability at the location of crustal movement and the mineral distribution data at the preset depth where sedimentation occurs under different faults are greater than the preset influence weight of the rock layer stability. When the influence weights of the rock layer stability at the location of crustal movement and the mineral distribution data at the preset depth where sedimentation occurs under different faults are less than the preset influence weight of the rock layer stability, output the mining cost of crustal movement per unit area.

[0076] When the influence weights of the rock layer stability at the location of crustal movement and the mineral distribution data at the preset depth where sedimentation occurs under different faults are greater than the preset influence weight of the rock layer stability, re-evaluate the mining cost of crustal movement per unit area until the influence weights of the rock layer stability at the location of crustal movement and the mineral distribution data at the preset depth where sedimentation occurs under different faults are less than the preset influence weight of the rock layer stability, and dispatch human and material resources according to the mining risk prevention measures.

[0077] It should be noted that introducing a multi-modal parameter comprehensive evaluation model means adopting an evaluation model that can comprehensively consider various different types of parameters. These parameters can cover different modal information, such as geological data, mechanical data, chemical data, etc., aiming to comprehensively and accurately evaluate various characteristics related to the rock layer. The implementation process is as follows:

[0078] First, set the coefficient of the influence weight of the rock layer stability through the multi-modal parameter comprehensive evaluation model. Since different factors have different degrees of influence on the rock layer stability, the model will set corresponding weight coefficients for each relevant factor according to professional knowledge and experience. For example, factors such as the hardness of the rock, structural integrity, and groundwater conditions may have different degrees of influence on the rock layer stability. By setting weight coefficients, the role degrees of these factors can be quantified.

[0079] Next, using the mineral distribution data at the locations of each crustal movement and the preset depths where sedimentation occurs, the parameter categories of the comprehensive evaluation model for multi-modal parameters of crustal movement are initialized with the influence weights of rock layer stability under different faults. This step combines specific geological data, such as the location information of crustal movement and the mineral distribution at specific depths, with the influence weights of different faults on rock layer stability to initialize the parameter categories of the model. That is to say, based on these actual geological conditions and influencing factors, an initial parameter configuration is set for the model so that it can more accurately reflect the actual geological situation.

[0080] Finally, obtain the mining cost of crustal movement per unit area. After completing the above settings and initializations of the model parameters, use the model to analyze and evaluate the crustal movement situation per unit area, taking into account the influence of various factors such as rock layer stability on the mining process, and then calculate the mining cost of crustal movement per unit area. The result of this cost calculation can provide an important reference for subsequent resource mining decisions, helping decision-makers reasonably plan the mining scheme, reduce costs, and improve mining efficiency.

[0081] By introducing the comprehensive evaluation model for multi-modal parameters, various geological data can be integrated, factors such as rock layer stability can be comprehensively evaluated, and finally the mining cost of crustal movement per unit area can be obtained, providing a scientific basis for geological resource development.

[0082] It should be noted that through this method, the rock layer of the drilling well to be repaired at the preset depth can be configured, enabling each maintenance area to respond quickly, and making the scheduling of human and material resources for crustal movement more reasonable.

[0083] In addition, by using the multi-modal computer vision sensing platform to control the RockSense+Seequent Leapfrog system to obtain the location of different areas and the geological data of the drilling well at different depths, the following steps can also be included:

[0084] System setup and equipment calibration: According to the actual situation at the drilling site, reasonably install and arrange various sensors of the multi-modal computer vision sensing platform, such as cameras, lidar, etc., to ensure that it can cover the key areas of drilling operations and at the same time establish a stable connection with the RockSense+Seequent Leapfrog system. Calibrate the installed sensors to ensure the accuracy and reliability of their measurement data. This includes adjusting parameters such as the focal length, viewing angle, and white balance of the camera, as well as calibrating the distance measurement accuracy of the lidar.

[0085] Set data acquisition parameters: According to the drilling objectives and geological characteristics, set appropriate data acquisition parameters in the RockSense+SeequentLeapfrog system, such as sampling interval, measurement range, data accuracy, etc. Determine the data acquisition strategies for different depths and regional locations. For example, according to the change of drilling depth, adjust the scanning frequency and resolution of the sensors to ensure that detailed geological data can be obtained at different depths.

[0086] Real-time data acquisition: During the drilling operation, use a multi-modal computer vision sensing platform to collect relevant data of the drilling rock formation in real time. The camera can capture the image information of the drilling hole wall for identifying features such as the structure, color, and texture of the rock formation; the lidar can measure the distance and shape of the hole wall to obtain the three-dimensional geometric information of the rock formation. Transmit the collected multi-modal data to the RockSense+Seequent Leapfrog system for storage and preliminary processing in real time. The system will integrate and preprocess the data, removing noise and abnormal data to improve the data quality.

[0087] Data annotation and feature extraction: Manually or automatically annotate the collected images and other data, marking different rock formation areas, geological structure features, etc. Use computer vision and machine learning algorithms to extract key geological features from the annotated data, such as the boundaries, thicknesses, dips, and strikes of the rock formations. These features will serve as important bases for subsequent data analysis and modeling.

[0088] Depth and position association: Combine the drilling depth records and the position information of the sensors to accurately associate the collected geological data with specific depths and regional locations. By establishing a depth-position coordinate system, map the data collected at different time points to the corresponding depths and positions to form a continuous geological data profile.

[0089] Data analysis and processing: In the RockSense+Seequent Leapfrog system, use various geological data analysis algorithms and models to deeply analyze the collected data. For example, infer the geological structure and evolutionary history of the drilling area through methods such as stratigraphic correlation, lithology identification, and structural analysis. Visualize the analysis results to generate geological profiles, three-dimensional geological models, etc., so that geological engineers and relevant personnel can intuitively understand the drilling geological conditions.

[0090] Data verification and update: Compare and verify the analyzed geological data with existing geological data, drilling records, etc. to check the accuracy and reliability of the data. During the drilling operation, as new data is continuously collected, timely update and correct the existing geological models and data to ensure that they can accurately reflect the current drilling geological conditions.

[0091] Data storage and sharing: Properly store the collected raw data, processed data, analysis results, etc., and establish a geological data database. Share relevant data with other departments or partners as needed to provide support for subsequent geological research, resource assessment, drilling engineering design, etc.

[0092] In addition, the method may further include the following steps: obtaining, through a gateway at the edge of the rock formation, different regional positions of each set of sensing parameters under each lithology, characteristic information of drilling geological data at different depths, and the lithology of the area where the RockSense+Seequent Leapfrog system is located per unit depth, and obtaining different regional positions of the RockSense+Seequent Leapfrog system of each sensing parameter, characteristic information of drilling geological data at different depths based on the different regional positions of each set of sensing parameters under each lithology, characteristic information of drilling geological data at different depths, and the lithology of the area where the RockSense+Seequent Leapfrog system is located per unit depth; obtaining the adjustable range of the sensing parameters of the camera of the RockSense+Seequent Leapfrog system per unit depth, and determining whether there is at least one sensing parameter among the sensing parameters such that the different regional positions of the RockSense+Seequent Leapfrog system, characteristic information of drilling geological data at different depths are greater than the preset characteristic thresholds of drilling geological data at different regional positions and different depths; if there is at least one sensing parameter among the sensing parameters such that the different regional positions of the RockSense+Seequent Leapfrog system, characteristic information of drilling geological data at different depths are greater than the preset characteristic thresholds of drilling geological data at different regional positions and different depths, then randomly output a sensing parameter such that the different regional positions of the RockSense+Seequent Leapfrog system, characteristic information of drilling geological data at different depths are greater than the preset characteristic thresholds of drilling geological data at different regional positions and different depths and use it as the sensing parameter of the RockSense+Seequent Leapfrog system; if there is no sensing parameter among the sensing parameters such that the different regional positions of the RockSense+Seequent Leapfrog system, characteristic information of drilling geological data at different depths are greater than the preset characteristic thresholds of drilling geological data at different regional positions and different depths, then adjust the data acquisition period and data acquisition points of the RockSense+Seequent Leapfrog system until there is at least one sensing parameter among the sensing parameters such that the different regional positions of the RockSense+Seequent Leapfrog system, characteristic information of drilling geological data at different depths are greater than the preset characteristic thresholds of drilling geological data at different regional positions and different depths.

[0093] It should be noted that due to the influence of the environment, no matter how the sensing parameters are adjusted, there is no parameter that makes the characteristic information of drilling geological data at different regional locations and different depths of the RockSense+Seequent Leapfrog system greater than the preset characteristic threshold of drilling geological data at different regional locations and different depths, making it impossible to obtain drilling geological data of the predetermined standard. This method can further improve the rationality of data acquisition.

[0094] like Figure 2 As shown, the second aspect of the present invention provides a drilling rock formation exploration system based on computer vision, the system comprising:

[0095] Multimodal computer vision sensor data integration module, which builds a multimodal computer vision sensor platform and optimizes the multimodal computer vision sensor platform to obtain the optimized multimodal computer vision sensor platform. The multimodal computer vision sensor platform is used to control the RockSense+Seequent Leapfrog system to obtain drilling geological data at different locations and depths of drilling rock formations.

[0096] The rock formation edge computing gateway data acquisition module, which obtains the porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures through the rock formation edge computing gateway, and builds the algorithm input dimension according to the porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures, and builds the drilling rock formation porosity, permeability, lithology, and stratigraphic sequence identification algorithm according to the algorithm input dimension;

[0097] An exploration risk assessment coefficient generation module, which uses a drilling rock porosity, permeability, lithology, and stratigraphic sequence identification algorithm to identify drilling geological data at different locations and depths of the drilling rock formation, obtains abnormal data on the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation in core samples at different formation temperatures, and performs exploration risk assessment based on the abnormal data on the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation in core samples at different formation temperatures, and generates an exploration risk assessment coefficient;

[0098] Different resource scheduling modules, which set mining risk prevention measures according to the exploration risk assessment coefficient, and schedule human and material resources based on the mining risk prevention measures.

[0099] Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A drilling rock formation exploration method based on computer vision, characterized in that: The following steps are involved: Building a multimodal computer vision sensing platform, optimizing the multimodal computer vision sensing platform to obtain an optimized multimodal computer vision sensing platform, and controlling the RockSense+Seequent Leapfrog system to obtain drilling geological data at different locations and depths of drilling rock formations based on the multimodal computer vision sensing platform; The porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures are obtained through the rock formation edge computing gateway, and the algorithm input dimension is established based on the porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures, and the drilling rock formation porosity, permeability, lithology, and stratigraphic sequence identification algorithm is established based on the algorithm input dimension; According to the drilling rock formation porosity, permeability, lithology, and stratigraphic sequence identification algorithm, the drilling geological data of different regional locations and different depths of the drilling rock formation are identified, and the porosity, permeability, lithology, and stratigraphic sequence abnormal data of the drilling rock formation in the core samples with different formation temperatures are obtained, and the exploration risk assessment is performed based on the porosity, permeability, lithology, and stratigraphic sequence abnormal data of the drilling rock formation in the core samples with different formation temperatures, and an exploration risk assessment coefficient is generated; Setting mining risk prevention measures according to the exploration risk assessment coefficient, and dispatching human and material resources based on the mining risk prevention measures; The porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures are obtained through the rock formation edge computing gateway, and the algorithm input dimension is built according to the porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures, and the drilling rock formation porosity, permeability, lithology, and stratigraphic sequence identification algorithm is built according to the algorithm input dimension, specifically including: The porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures are obtained through the rock formation edge computing gateway, and the porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures are classified into porosity, permeability, lithology, and stratigraphic sequence types to obtain the drilling geological data of each porosity, permeability, lithology, and stratigraphic sequence type, and the algorithm input dimensions of each porosity, permeability, lithology, and stratigraphic sequence type are established based on the drilling geological data of each porosity, permeability, lithology, and stratigraphic sequence type; Input the drilling geological data in the algorithm input dimensions of each porosity, permeability, lithology, and stratigraphic sequence type into the abnormal One-Class SVM model, obtain the abnormal porosity, permeability, lithology, and stratigraphic sequence data in different groups of drilling geological data, and determine whether the abnormal porosity, permeability, lithology, and stratigraphic sequence data in the drilling geological data exceeds a preset interval, and introduce Autoencoder; If the porosity, permeability, lithology, and stratigraphic sequence abnormal data in the drilling geological data exceeds a preset interval, the porosity, permeability, lithology, and stratigraphic sequence abnormal data corresponding to the porosity, permeability, lithology, and stratigraphic sequence type label information of the unit depth drilling geological data are obtained as the relevant porosity, permeability, lithology, and stratigraphic sequence abnormal data; if the porosity, permeability, lithology, and stratigraphic sequence abnormal data in the drilling geological data exceeds a preset value, the porosity, permeability, lithology, and stratigraphic sequence abnormal data corresponding to the porosity, permeability, lithology, and stratigraphic sequence type label information of the unit depth drilling geological data are used as the relevant porosity, permeability, lithology, and stratigraphic sequence abnormal data; The related porosity, permeability, lithology, and stratigraphic sequence abnormal data are input into the Autoencoder, so that the coding layer is concentrated on the related porosity, permeability, lithology, and stratigraphic sequence abnormal data, and the coding layer neuron dimension is obtained. Based on Threshold-based Methods, a drilling rock formation porosity, permeability, lithology, and stratigraphic sequence identification algorithm is built, and the coding layer neuron dimension is input into the drilling rock formation porosity, permeability, lithology, and stratigraphic sequence identification algorithm for safety peak judgment; The step of building a multimodal computer vision sensing platform and optimizing the multimodal computer vision sensing platform to obtain an optimized multimodal computer vision sensing platform specifically includes: Build a multimodal computer vision sensing platform, and test the multimodal computer vision sensing platform to obtain the fluctuation range of the threshold value of rock hardness monitored by the RockSense+Seequent Leapfrog system at different formation pressures of the multimodal computer vision sensing platform, and build a prediction model for the fluctuation of the threshold value of rock hardness monitored by the RockSense+Seequent Leapfrog system through random forest; Inputting the fluctuation range of the threshold value of rock formation hardness monitored by the RockSense+Seequent Leapfrog system for different formation pressures of the multimodal computer vision sensing platform into the prediction model for the fluctuation of the threshold value of rock formation hardness monitored by the RockSense+Seequent Leapfrog system for training, and obtaining the trained prediction model for the fluctuation of the threshold value of rock formation hardness monitored by the RockSense+Seequent Leapfrog system; Obtaining the fluctuation range of the threshold value of rock hardness monitored by the RockSense+Seequent Leapfrog system of the multimodal computer vision sensing platform within a preset time and inputting it into the trained prediction model of the threshold value fluctuation of rock hardness monitored by the RockSense+Seequent Leapfrog system for prediction, and obtaining the fluctuation of the threshold value of rock hardness monitored by the RockSense+Seequent Leapfrog system of the multimodal computer vision sensing platform of the unit depth crack density and morphology; A real-time RockSense+Seequent Leapfrog system monitoring fluctuation range of the multimodal computer vision sensing platform is obtained. If the real-time RockSense+Seequent Leapfrog system monitoring fluctuation range is greater than a threshold fluctuation of rock formation hardness monitored by the RockSense+Seequent Leapfrog system of the multimodal computer vision sensing platform of unit depth crack density and morphology, the real-time RockSense+Seequent Leapfrog system monitoring fluctuation range is adjusted according to the threshold fluctuation of rock formation hardness monitored by the RockSense+Seequent Leapfrog system of the multimodal computer vision sensing platform of unit depth crack density and morphology to obtain an optimized multimodal computer vision sensing platform.

2. The computer vision-based drilling rock exploration method according to claim 1, characterized in that: According to the drilling rock formation porosity, permeability, lithology, and stratigraphic sequence identification algorithm, the drilling geological data of different regional locations and different depths of the drilling rock formation are identified, and the porosity, permeability, lithology, and stratigraphic sequence abnormal data of the drilling rock formation in the core samples with different formation temperatures are obtained. Based on the porosity, permeability, lithology, and stratigraphic sequence abnormal data of the drilling rock formation in the core samples with different formation temperatures, exploration risk assessment is performed to generate an exploration risk assessment coefficient, which specifically includes: Input the drilling geological data of different regional locations and different depths of the drilling rock formation into the porosity, permeability, lithology, and stratigraphic sequence identification algorithm for identification, obtain the porosity, permeability, lithology, and stratigraphic sequence abnormal data of the drilling rock formation in the core samples of different formation temperatures, and preset different mining red lines for oil and gas reserves exploration; According to the different red lines for oil and gas exploration, the porosity, permeability, lithology, and stratigraphic sequence abnormal data of the drilling rock formations in the core samples with different formation temperatures are divided into different levels for oil and gas exploration, and the porosity, permeability, lithology, and stratigraphic sequence abnormal data of the drilling rock formations in the core samples with different formation temperatures are obtained to explore different levels of oil and gas reserves, and the mineral distribution data at the preset depth where the sedimentation phenomenon occurs are obtained; An exploration risk assessment is generated based on the porosity, permeability, lithology, and stratigraphic sequence abnormal data of the drilling rock formations in the core samples with different formation temperatures, the mineral distribution data of different levels of oil and gas reserves, the preset depths of sedimentation phenomena, and the porosity, permeability, lithology, and stratigraphic sequence abnormal data of the drilling rock formations in the core samples with different formation temperatures, and an exploration risk assessment coefficient is generated.

3. The computer vision-based drilling rock exploration method according to claim 1, characterized in that: The mining risk prevention measures are set according to the exploration risk assessment coefficient, including: Obtaining mineral distribution data at a preset depth where sedimentation occurs according to the exploration risk assessment coefficient, building a search tag based on the mineral distribution data at the preset depth where sedimentation occurs, and performing a search according to the search tag to obtain a fluid sample of the drilling stratum; Obtaining the position distribution of the oil and gas layer and the water layer according to the fluid sample of the drilling rock formation, and building a material content determination device for the position distribution data of the oil and gas layer and the water layer, inputting the position distribution of the oil and gas layer and the water layer into the material content determination device for the position distribution data of the oil and gas layer and the water layer to perform material content determination, and obtaining different carbon concentration content determination results from high to low concentrations; Based on the determination results of different carbon concentrations from high to low, mining risk prevention measures for a preset depth are set, and the mining risk prevention measures are documented and reported.

4. The computer vision-based drilling rock exploration method according to claim 1, characterized in that: Based on the mining risk prevention measures, human and material resources are dispatched, including: Obtain the stress and strain depth information of the crustal movement per unit depth, as well as the porosity, permeability, lithology, and mineral distribution data of the preset depth of the stratigraphic sequence where the underground river exists; calculate the influence weight of the rock stability of each crustal movement location and the mineral distribution data of the preset depth where the sedimentation phenomenon occurs under different faults based on the stress and strain depth information of the crustal movement per unit depth and the mineral distribution data of the preset depth where the sedimentation phenomenon occurs; A multimodal parameter comprehensive evaluation model is introduced, and the coefficient of the rock stability influence weight is set according to the multimodal parameter comprehensive evaluation model. The rock stability influence weight under different faults is initialized according to the mineral distribution data of the location of each crustal movement and the preset depth of the sedimentation phenomenon, and the parameter category of the crustal movement multimodal parameter comprehensive evaluation model is obtained to obtain the mining cost of the crustal movement per unit area; Determine whether the influence weight of the rock formation stability under different faults of the mineral distribution data at the location where the crust movement is located and the preset depth where the sedimentation phenomenon occurs is greater than the preset influence weight of the rock formation stability; if the influence weight of the rock formation stability under different faults of the mineral distribution data at the location where the crust movement is located and the preset depth where the sedimentation phenomenon occurs is less than the preset influence weight of the rock formation stability, output the mining cost of the crust movement per unit area; If the weight of the impact of the mineral distribution data at the location where the crust movement is located and the preset depth of the sedimentation phenomenon on the rock stability under different faults is greater than the preset rock stability impact weight, the mining cost per unit area of ​​the crust movement will be re-evaluated until the weight of the impact of the mineral distribution data at the location where the crust movement is located and the preset depth of the sedimentation phenomenon on the rock stability under different faults is less than the preset rock stability impact weight, and human and material resources are dispatched according to the mining risk prevention measures.

5. A system for implementing the drilling rock formation exploration method based on computer vision according to any one of claims 1 to 4, characterized in that: The system includes: Multimodal computer vision sensor data integration module, which builds a multimodal computer vision sensor platform and optimizes the multimodal computer vision sensor platform to obtain the optimized multimodal computer vision sensor platform. The multimodal computer vision sensor platform is used to control the RockSense+Seequent Leapfrog system to obtain drilling geological data at different locations and depths of drilling rock formations. The rock formation edge computing gateway data acquisition module, which obtains the porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures through the rock formation edge computing gateway, and builds the algorithm input dimension according to the porosity, permeability, lithology, and stratigraphic sequence drilling geological data of the drilling rock formation under different formation pressures, and builds the drilling rock formation porosity, permeability, lithology, and stratigraphic sequence identification algorithm according to the algorithm input dimension; An exploration risk assessment coefficient generation module, which uses a drilling rock porosity, permeability, lithology, and stratigraphic sequence identification algorithm to identify drilling geological data at different locations and depths of the drilling rock formation, obtains abnormal data on the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation in core samples at different formation temperatures, and performs exploration risk assessment based on the abnormal data on the porosity, permeability, lithology, and stratigraphic sequence of the drilling rock formation in core samples at different formation temperatures, and generates an exploration risk assessment coefficient; Different resource scheduling modules, which set mining risk prevention measures according to the exploration risk assessment coefficient, and schedule human and material resources based on the mining risk prevention measures.

Images