Real-time analysis system for geological structure image in uranium mine drilling process

Abstract

The invention discloses a real-time analysis system for a geological structure image in a uranium mine drilling process, and relates to the technical field of mineral resource exploration and geological analysis, and the system comprises a radiation intensity measurement module used for obtaining a radiation intensity measurement value, an image collection module used for adjusting an image collection parameter in real time based on the radiation intensity measurement value, and a processing module used for processing the image collection parameter. The system comprises an image processing module used for preprocessing the acquired image and reducing the noise influence, a deep learning processing module used for performing feature extraction and classification on the preprocessed image, a drilling guidance module used for performing feature extraction and classification on the preprocessed image, and an image processing module used for acquiring the geological structure image in the drilling process through a multi-band imaging technology. The server is used for receiving classification results and guiding drilling operation in real time; according to the real-time analysis system for the geological structure image in the uranium mine drilling process, the problem that in the prior art, image noise is increased due to radiation interference in an area containing high-radioactive substances is solved.

Description

Technical Field

[0001] The invention relates to the technical field of mineral resource exploration and geological analysis, and in particular to a real-time analysis system for geological structure images during uranium ore drilling. Background Art

[0002] In the process of uranium drilling, real-time analysis of geological structure images is a key means of obtaining geological information. This method can reflect the texture, structure and composition of rock formations through high-resolution images, providing a reliable basis for the development of mineral resources. Common geological image acquisition technologies include optical imaging, X-ray scanning and ultrasonic detection, which have been widely used in mineral exploration, especially in areas with complex geological conditions.

[0003] However, in areas containing highly radioactive materials, the image acquisition process often faces the problem of radiation interference. High-intensity radioactive radiation will affect the image sensor, which is manifested as increased image noise and signal distortion. Specifically, radiation will affect the working stability of the image sensor through electromagnetic interference, resulting in additional high-frequency interference or error signals in its output signal, and even damage to the equipment in severe cases. These noises not only reduce the clarity and resolvability of the image, but also bring great challenges to subsequent image processing and analysis. At present, the solutions to the problem of radiation interference are mostly concentrated in hardware and software. In hardware, the direct impact of radiation on the sensor is reduced by using radiation shielding materials or adding protective covers; in software, image post-processing algorithms such as noise filtering and enhancement algorithms are used to improve image quality. However, these methods still have certain limitations. Hardware protection measures often increase the weight and cost of the equipment, and their effectiveness depends on the performance of the shielding material; while software methods can improve image quality, they cannot completely eliminate noise in a strong radiation environment, and have high requirements for real-time performance. Summary of the invention

[0004] The purpose of the present invention is to provide a real-time analysis system for geological structure images during uranium mining, so as to solve the problem of increased image noise due to radiation interference in areas containing highly radioactive materials in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: a real-time analysis system for geological structure images during uranium ore drilling, the system comprising: A radiation intensity measurement module, used for obtaining radiation intensity measurement values; The image acquisition module connected to the radiation intensity measurement module is used to adjust the image acquisition parameters in real time based on the radiation intensity measurement value to reduce the noise in the image, and obtain the geological structure image during the drilling process through the multi-band imaging technology, including establishing a finite element model of multi-band imaging, simulating the influence of radiation intensity on imaging quality, solving the node response, and analyzing the influence of radiation intensity changes on the parameters of the imaging system. The specific formula for solving the node response is: [K]u=g; Wherein, [K] represents the influence weight matrix used to describe the imaging parameters in the multi-band imaging system, u represents the change vector of the imaging parameters in the multi-band imaging system, and g represents the external interference effect of the radiation intensity on the multi-band imaging system; The image processing module connected to the image acquisition module is used to preprocess the acquired image and reduce the influence of noise, including establishing a diffusion equation model for the image data, setting the initial intensity distribution, solving the diffusion equation, gradually diffusing the high-frequency noise, and retaining the low-frequency characteristics. The specific formula is: ; Where x represents the position of the pixel in the image, t represents the time, q(x, t) represents the intensity distribution of the image in space x and time t, and D(q) represents the intensity of pixel diffusion during image denoising. is the gradient operator, which represents the spatial variation of pixel values ​​in the image, and S(x, t) represents the intensity distribution of additional source terms in the image; A deep learning processing module connected to the image processing module is used to extract features and classify the pre-processed images; The drilling guidance module connected to the deep learning processing module is used to receive the classification results and guide the drilling operation in real time.

[0006] Preferably, the radiation intensity measurement module obtains the radiation intensity measurement value including: Collect time series data from the radiation intensity measurement device, fit the periodic variation characteristics of the radiation intensity, calculate the fluctuation frequency and amplitude, predict the instantaneous value of the radiation intensity, and pass the result to the image acquisition module. The specific formula for predicting the instantaneous value of the radiation intensity is: ; Among them, F(t) represents the radiation intensity value actually measured at time t, F0 represents the average value of the radiation intensity, ΔF represents the fluctuation amplitude of the radiation intensity, and f represents the fluctuation frequency of the radiation signal. represents the phase shift of the fluctuation, and t represents time.

[0007] Preferably, the deep learning processing module extracts features and classifies the preprocessed image, including: The preprocessed image data is used as input to optimize and initialize the weights of the deep learning model. The fitness function is used to evaluate the prediction performance of each generation of weights. The weight values ​​are selected for crossover and mutation operations. The optimized deep learning network is trained to classify image features. The geological structure classification results are output to the drilling guidance module. The fitness function is used to evaluate the prediction performance of each generation of weights. The specific formula is: f(W)=1 / (1+E(W)); Among them, f(W) represents the prediction performance indicator of the current weight of the deep learning network, E(W) represents the classification error of the network for the input image features under the current weight, and W represents the adjustable parameters in the deep learning network.

[0008] Preferably, the drilling guidance module receives the classification result and guides the drilling operation in real time, including: The drilling operation is modeled as a path optimization problem. The path set and operation cost are defined. The optimal path and drilling operation parameter combination are iteratively calculated. The optimized operation strategy is output to the drilling equipment. The specific formula is: ; Among them, c ij represents the operating cost required to move the drilling equipment from geological region i to region j, y ijk It indicates whether the kth drilling equipment chooses to move from geological area i to area j, i and j represent the specific geological area numbers involved in the uranium drilling operation, k represents the total number of drilling equipment involved in the path optimization, and n represents the total number of geological areas that need to be covered in the drilling operation.

[0009] Preferably, the calculation formula for obtaining the average value F0 of the radiation intensity in the radiation intensity measurement value in the continuous time condition by the radiation intensity measurement module is: F0= ; Wherein, F0 represents the average value of the radiation intensity, T represents the time period, F(t) represents the radiation intensity value actually measured at time t, and t represents time.

[0010] Preferably, the calculation formula for obtaining the average value F0 of the radiation intensity in the radiation intensity measurement value in the discrete time condition by the radiation intensity measurement module is: F0= ; Among them, F0 represents the average value of radiation intensity, t represents time, h represents the number of measured time points, r represents the index variable, and F(t r ) indicates that at time t r The actual radiation intensity value measured at time t r represents the rth time point.

[0011] Preferably, the image acquisition module adjusts the image acquisition parameters in real time based on the radiation intensity measurement value, including predicting image noise based on the currently measured radiation intensity level, enhancing the image signal through an adaptive gain adjustment circuit, introducing frequency compensation technology to reduce frequency band interference caused by high radioactivity, and adjusting the imaging frequency band when N>a×R+b, wherein R represents the measured radiation intensity, N represents the noise level in the environment, a is a constant related to the sensitivity of the equipment, and b is a fixed threshold.

[0012] Preferably, the image noise prediction based on the currently measured radiation intensity level includes collecting the gamma ray counting information in the body and performing preliminary filtering processing, calculating the fluctuation coefficient in each counting interval, analyzing the fluctuation trend to estimate the number of noise points in the next frame, and based on the current count and the calculated standard deviation, if σ 2 / C>γ, the anti-interference measures are started, where C represents the total gamma-ray count value in the window, σ represents the variance of the count value change, and γ represents the index value of the noise impact degree.

[0013] Preferably, the image acquisition module adjusts the image acquisition parameters in real time based on the radiation intensity measurement value, and the adaptive gain adjustment circuit includes a gain control unit and a feedback adjustment unit. The gain control unit automatically adjusts the signal amplification factor according to the ambient noise level and the radiation intensity. The feedback adjustment unit monitors the signal output quality in real time and optimizes the gain parameters through closed-loop control.

[0014] Preferably, the image acquisition module introduces frequency compensation technology in real-time adjustment of image acquisition parameters based on radiation intensity measurement values ​​to reduce frequency band interference caused by high radioactivity, including automatically adjusting the working frequency band based on real-time monitored radiation intensity through a tunable filter.

[0015] It can be seen from the above technical solution that the present invention has the following beneficial effects: The real-time analysis system of geological structure images during uranium mine drilling obtains radiation intensity measurement values ​​through the radiation intensity measurement module. The image acquisition module adjusts the image acquisition parameters in real time based on the radiation intensity measurement values ​​to reduce the noise in the image, and obtains the geological structure images during the drilling process through multi-band imaging technology. The image processing module preprocesses the acquired images to reduce the influence of noise. The deep learning processing module extracts and classifies the preprocessed images. The drilling guidance module receives the classification results and guides the drilling operation in real time. It can respond to the changes in radiation intensity and noise level in real time, ensuring that the system can quickly adjust the image acquisition parameters, thereby improving the real-time and stability of geological image acquisition and effectively reducing the influence of high-frequency radiation interference on the image acquisition signal. The frequency compensation technology dynamically adjusts the working frequency band to avoid the interfered frequency band area, further improves the clarity and resolvability of the image signal, ensures the accuracy and robustness of the acquired image, and provides a high-quality data basis for subsequent image processing and analysis. It can be extended to other mineral resource exploration fields, such as oil, natural gas or other resource exploration with high radiation characteristics, and solves the problem of increased image noise due to radiation interference in the existing technology in areas containing highly radioactive materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the connection of the system modules of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, the present invention provides a technical solution: a real-time analysis system of geological structure images during uranium ore drilling, the system comprising: A radiation intensity measurement module, used for obtaining radiation intensity measurement values; The image acquisition module connected to the radiation intensity measurement module is used to adjust the image acquisition parameters in real time based on the radiation intensity measurement value to reduce the noise in the image, and obtain the geological structure image during the drilling process through the multi-band imaging technology, including establishing a finite element model of multi-band imaging, simulating the influence of radiation intensity on imaging quality, solving the node response, and analyzing the influence of radiation intensity changes on the parameters of the imaging system. The specific formula for solving the node response is: [K]u=g; Wherein, [K] represents the influence weight matrix used to describe the imaging parameters in the multi-band imaging system, u represents the change vector of the imaging parameters in the multi-band imaging system, and g represents the external interference effect of the radiation intensity on the multi-band imaging system; The image processing module connected to the image acquisition module is used to preprocess the acquired image and reduce the influence of noise, including establishing a diffusion equation model for the image data, setting the initial intensity distribution, solving the diffusion equation, gradually diffusing the high-frequency noise, and retaining the low-frequency characteristics. The specific formula is: ; Where x represents the position of the pixel in the image, t represents the time, q(x, t) represents the intensity distribution of the image in space x and time t, and D(q) represents the intensity of pixel diffusion during image denoising. is the gradient operator, which represents the spatial variation of pixel values ​​in the image, and S(x, t) represents the intensity distribution of additional source terms in the image; A deep learning processing module connected to the image processing module is used to extract features and classify the pre-processed images; The drilling guidance module connected to the deep learning processing module is used to receive the classification results and guide the drilling operation in real time.

[0019] Based on the real-time measurement values ​​obtained by the radiation intensity measurement module, the system adjusts the image parameters in real time through the image acquisition module to optimize the imaging quality and reduce noise interference. At the same time, by establishing a finite element model to simulate the influence of radiation intensity on the imaging system, the node response formula [K]u=g is analyzed to clarify the influence of radiation intensity changes on the system. The acquired images are preprocessed by the image processing module to remove high-frequency noise and retain low-frequency features, thereby improving the clarity and accuracy of the image. The preprocessed images are input into the deep learning module to extract key features and classify them. Finally, the classification results are output through the drilling guidance module to adjust and optimize the drilling strategy in real time. The system improves the quality and clarity of geological structure images through real-time radiation intensity measurement and imaging parameter adjustment; denoising technology effectively reduces the impact of external interference on imaging; combined with the deep learning module for feature extraction and classification, efficient analysis of geological structures is achieved; and finally, the drilling guidance module optimizes the real-time decision-making of the drilling process and improves efficiency and accuracy.

[0020] The radiation intensity measurement module obtains the radiation intensity measurement value by collecting time series data from the radiation intensity measurement device, fitting the periodic change characteristics of the radiation intensity, calculating the fluctuation frequency and amplitude, predicting the instantaneous value of the radiation intensity, and passing the result to the image acquisition module. The specific formula for predicting the instantaneous value of the radiation intensity is: ; Among them, F(t) represents the radiation intensity value actually measured at time t, F0 represents the average value of the radiation intensity, ΔF represents the fluctuation amplitude of the radiation intensity, and f represents the fluctuation frequency of the radiation signal. represents the phase shift of the fluctuation, and t represents time.

[0021] In this embodiment, the radiation intensity measurement module collects time series data, analyzes the periodic variation characteristics of the radiation intensity, and extracts key parameters such as the fluctuation frequency f and the fluctuation amplitude ΔF. , combining time t and phase offset , accurately predicting the instantaneous radiation intensity value at each moment. Subsequently, the prediction result is transmitted to the image acquisition module for real-time adjustment of image acquisition parameters, thereby optimizing image quality and reducing environmental noise interference. Through time series analysis of radiation intensity, the system can capture the periodic variation characteristics of radiation intensity and predict instantaneous values. This real-time prediction method improves the dynamic response capability of image acquisition, effectively reduces the interference of radiation signal fluctuations on image acquisition, and makes the imaging effect more stable and clear. At the same time, this calculation method is simple and efficient, and is easy to implement in practical engineering.

[0022] The deep learning processing module extracts and classifies features of the preprocessed image, including: taking the preprocessed image data as input, optimizing and initializing the weights of the deep learning model, using the fitness function to evaluate the prediction performance of each generation of weights, selecting weight values ​​for crossover and mutation operations, training the optimized deep learning network to classify image features, outputting geological structure classification results to the drilling guidance module, and using the fitness function to evaluate the prediction performance of each generation of weights. The specific formula is: f(W)=1 / (1+E(W)); Among them, f(W) represents the prediction performance indicator of the current weight of the deep learning network, E(W) represents the classification error of the network for the input image features under the current weight, and W represents the adjustable parameters in the deep learning network.

[0023] In this embodiment, the deep learning processing module receives the preprocessed image data as input and optimizes the weight parameter W in the deep learning network. By initializing the weights and using the fitness function f(W)=1 / (1+E(W)), the performance of each generation of weights is evaluated. The higher the fitness value, the lower the classification error E(W). Subsequently, the weights are crossover and mutation operations are performed to further improve the classification accuracy. After multiple generations of optimization, a deep learning model that can efficiently extract image features is finally obtained, and the classification results are output to the drilling guidance module to guide the drilling operation. This embodiment significantly improves the classification accuracy and effectively reduces the image feature classification error. The model optimization process improves the convergence speed and robustness of network training. The geological structure classification results finally output can more accurately guide drilling operations and improve the efficiency and reliability of the overall system.

[0024] The drilling guidance module receives the classification results and guides the drilling operation in real time, including modeling the drilling operation as a path optimization problem, defining the path set and operation cost, iteratively calculating the optimal path and drilling operation parameter combination, and outputting the optimized operation strategy to the drilling equipment. The specific formula is: ; Among them, c ij represents the operating cost required to move the drilling equipment from geological region i to region j, y ijk It indicates whether the kth drilling equipment chooses to move from geological area i to area j, i and j represent the specific geological area numbers involved in the uranium drilling operation, k represents the total number of drilling equipment involved in the path optimization, and n represents the total number of geological areas that need to be covered in the drilling operation.

[0025] In this embodiment, the drilling guidance module converts the drilling task into a path optimization problem according to the geological structure classification results. By defining the path set and the relevant operation cost, the objective function is used to calculate the optimal path and equipment parameter combination. The optimization process will comprehensively consider the operating cost of the drilling equipment, the efficiency of covering the geological area, and the synergy between the equipment, and gradually converge to an optimal solution that can meet the requirements of covering all target areas with the lowest cost. The optimized operation strategy is transmitted to the drilling equipment in real time to guide its specific drilling operations. This embodiment mathematizes the planning problem of the drilling task through the path optimization model, which can significantly reduce the operating cost of the drilling equipment and improve the coverage efficiency. By defining the objective function and constraints that adapt to the actual scenario, the model realizes the optimization of the collaborative work of multiple devices, and provides an efficient solution for drilling in complex geological environments. At the same time, the optimization model can generate operation strategies in real time, so that the drilling equipment has a strong dynamic adaptability.

[0026] The calculation formula for obtaining the average value F0 of the radiation intensity in the radiation intensity measurement value in the continuous time condition is: F0 = ; Wherein, F0 represents the average value of the radiation intensity, T represents the time period, F(t) represents the radiation intensity value actually measured at time t, and t represents time.

[0027] In this embodiment, the radiation intensity measurement module obtains the average value F0 of the radiation intensity by integrating the radiation intensity in the time period T. Formula F0= It shows that the average value F0 is the ratio of the time integral result of the intensity value F(t) within the measurement period T to the period length T. This method provides a more stable intensity value by smoothing the fluctuation of radiation intensity, which is used for parameter adjustment and optimization of subsequent image acquisition modules to ensure the robustness of the system to changes in the external environment. By calculating the average value F0 of the radiation intensity, this implementation significantly improves the system's tolerance to fluctuations in radiation signals and reduces the impact of instantaneous fluctuations on image acquisition quality. The continuous time integral calculation method can accurately capture the overall change trend of radiation intensity, so that the system can still provide stable image quality in complex environments. This method is simple to calculate and efficient, and is suitable for application scenarios with high real-time requirements.

[0028] The calculation formula for obtaining the average value F0 of the radiation intensity in the radiation intensity measurement value in the discrete time condition is: F0 = ; Among them, F0 represents the average value of radiation intensity, t represents time, h represents the number of measured time points, r represents the index variable, and F(t r ) indicates that at time t r The actual radiation intensity value measured at time t r represents the rth time point.

[0029] In this embodiment, the radiation intensity measurement module calculates the average value of the radiation intensity based on the measurement data at discrete time. r ), formula F0= The measured values ​​at each time point are taken arithmetic average to smooth out the fluctuations in radiation intensity. This method does not require continuous time integral calculations and is suitable for the processing requirements of discrete measurement data. The calculation results can be directly used to optimize the parameters of the image acquisition module. By averaging the measurement data at discrete time points, this implementation simplifies the calculation process of the average radiation intensity value, which is particularly suitable for scenarios with high real-time requirements or limited sampling frequency of measurement equipment. The discrete average calculation method can eliminate the influence of accidental noise on the results while retaining the main characteristics of the radiation intensity, thereby improving the robustness and stability of image acquisition. In addition, since this method is based on simple arithmetic operations of limited measurement points, its computational efficiency is higher.

[0030] The image acquisition module adjusts the image acquisition parameters in real time based on the radiation intensity measurement value, including image noise prediction based on the current measured radiation intensity level, enhancing the image signal through an adaptive gain adjustment circuit, introducing frequency compensation technology to reduce the frequency band interference caused by high radioactivity, and adjusting the imaging frequency band when N>a×R+b, where R represents the measured radiation intensity, N represents the noise level in the environment, a is a constant related to the sensitivity of the equipment, and b is a fixed threshold.

[0031] In this embodiment, the image acquisition module monitors the radiation intensity R and the environmental noise level N in real time. Based on the current level of radiation intensity, the module predicts possible image noise and dynamically adjusts the gain parameters through an adaptive gain adjustment circuit to enhance the intensity of the image signal. In order to cope with the problem of frequency band interference in a high-radioactivity environment, a frequency compensation technology is introduced to adjust the response amplitude of different frequency bands in signal processing to reduce the impact of high-frequency noise. When detected, the system adjusts the imaging frequency band to avoid the high-noise interference area, thereby ensuring the clarity and stability of image acquisition. The adjustment logic is based on the sensitivity constant a and fixed threshold b of the device, ensuring flexibility in environments with different radiation intensities. By adjusting the image acquisition parameters in real time, this embodiment effectively improves the quality and reliability of image acquisition in a high-radioactivity environment. The adaptive gain adjustment circuit enhances the dynamic range of the image signal, and the frequency compensation technology significantly reduces the interference of high-frequency noise, making the image clearer. In addition, by dynamically adjusting the imaging frequency band to avoid the noise area, the method improves the adaptability of the system to complex environments and optimizes the robustness and performance of image acquisition.

[0032] Image noise prediction based on the currently measured radiation intensity level includes collecting the gamma-ray count information in the body and performing preliminary filtering, calculating the fluctuation coefficient within each counting interval, analyzing the fluctuation trend to estimate the number of noise points in the next frame, and calculating the standard deviation based on the current count. If σ 2 / C>γ, the anti-interference measures are started, where C represents the total gamma-ray count value in the window, σ represents the variance of the count value change, and γ represents the index value of the noise impact degree.

[0033] In this embodiment, the system collects gamma ray count information in the body through sensors and performs preliminary filtering on the raw data to remove obvious outliers or invalid data. Subsequently, the system processes the gamma ray counts in segments, calculates the coefficient of fluctuation within each counting interval, and extracts the fluctuation trend based on statistical analysis methods to predict the number of noise points in the next frame. At the same time, the system uses the total gamma ray count value C in the current window and the variance σ of the count value change to calculate the noise impact index σ 2 When the index exceeds the preset threshold γ, the system considers the noise level to be too high and initiates anti-interference measures, such as dynamically adjusting the image gain or using a stronger signal filtering algorithm, to reduce the impact of noise on image quality. By analyzing the fluctuation trend and change amplitude of the gamma-ray count, this implementation method can effectively predict the number of noise points in the next frame, thereby achieving forward-looking control of image noise. 2 The indicator dynamically evaluates the noise impact level, allowing anti-interference measures to respond quickly when the noise exceeds the control range, thereby improving the robustness of the system and image clarity. In addition, the method combines the statistical correlation between gamma-ray counts and the degree of noise impact to provide an efficient and accurate noise prediction and processing mechanism.

[0034] The image acquisition module adjusts the image acquisition parameters in real time based on the radiation intensity measurement value. The adaptive gain adjustment circuit includes a gain control unit and a feedback adjustment unit. The gain control unit automatically adjusts the signal amplification factor according to the ambient noise level and the radiation intensity. The feedback adjustment unit monitors the signal output quality in real time and optimizes the gain parameters through closed-loop control.

[0035] The core of the adaptive gain adjustment circuit consists of a gain control unit and a feedback adjustment unit. The gain control unit dynamically adjusts the signal amplification factor according to the real-time measured environmental noise level and radiation intensity value to ensure that the image signal has a moderate amplification effect under noise interference conditions. For example, when the environmental noise level is low, the gain control unit reduces the signal amplification factor to avoid signal overload; when the noise level is high or the radiation intensity is weak, the amplification factor is appropriately increased to enhance the signal strength. The feedback adjustment unit monitors the signal output quality after gain adjustment in real time and continuously optimizes the gain parameters through a closed-loop control mechanism. The closed-loop control detects the output signal quality indicators, such as signal-to-noise ratio or dynamic range, and feedback adjusts the parameter settings of the gain control unit to achieve the optimal configuration of gain adjustment. This implementation significantly improves the system's ability to cope with different environmental noise and radiation intensity changes by combining the gain control unit and the feedback adjustment unit of the adaptive gain adjustment circuit. The dynamic amplification factor adjustment function ensures the effective acquisition of signals in a noisy environment and avoids the problem of over-amplification or signal overload; the closed-loop feedback adjustment mechanism further optimizes the gain parameter settings and improves the quality and stability of the signal output. The overall system can achieve efficient and reliable image acquisition under complex environmental conditions.

[0036] The image acquisition module introduces frequency compensation technology in real-time adjustment of image acquisition parameters based on the radiation intensity measurement value to reduce the frequency band interference caused by high radioactivity, including automatic adjustment of the working frequency band based on the real-time monitored radiation intensity through a tunable filter.

[0037] The image acquisition module dynamically evaluates the frequency band interference in a high-radioactivity environment by monitoring the radiation intensity value in real time. The system uses a tunable filter to automatically adjust the working frequency band of the filter according to the monitored radiation intensity changes to avoid the interfered frequency band area. Specifically, when the radiation intensity increases and the interference of certain frequency band signals increases, the tunable filter changes its center frequency or bandwidth parameters in real time through the control circuit and switches to the undisturbed frequency band to ensure the integrity of the signal and the clarity of image acquisition. This dynamic frequency compensation technology can adaptively adjust according to environmental changes and reduce the impact of high-radioactivity environment on system performance. By introducing a tunable filter to achieve frequency compensation, this implementation method can significantly reduce the impact of frequency band interference on image acquisition quality in a high-radioactivity environment. The ability to dynamically adjust the working frequency band enables the system to flexibly adapt to different radiation intensity conditions, avoid the limitations brought by fixed frequency band operation, and thus improve the stability and clarity of the image signal. The overall system shows stronger anti-interference ability and adaptability in a complex radiation environment, ensuring high-quality geological structure image acquisition.

[0038] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various 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 real-time analysis system for geological structure images during uranium ore drilling, characterized in that: The system comprises: A radiation intensity measurement module, used for obtaining radiation intensity measurement values; The image acquisition module connected to the radiation intensity measurement module is used to adjust the image acquisition parameters in real time based on the radiation intensity measurement value to reduce the noise in the image, and obtain the geological structure image during the drilling process through the multi-band imaging technology, including establishing a finite element model of multi-band imaging, simulating the influence of radiation intensity on imaging quality, solving the node response, and analyzing the influence of radiation intensity changes on the parameters of the imaging system. The specific formula for solving the node response is: [K]u=g; Wherein, [K] represents the influence weight matrix used to describe the imaging parameters in the multi-band imaging system, u represents the change vector of the imaging parameters in the multi-band imaging system, and g represents the external interference effect of the radiation intensity on the multi-band imaging system; The image processing module connected to the image acquisition module is used to preprocess the acquired image and reduce the influence of noise, including establishing a diffusion equation model for the image data, setting the initial intensity distribution, solving the diffusion equation, gradually diffusing the high-frequency noise, and retaining the low-frequency characteristics. The specific formula is: ； Where x represents the position of the pixel in the image, t represents the time, q(x, t) represents the intensity distribution of the image in space x and time t, and D(q) represents the intensity of pixel diffusion during image denoising. is the gradient operator, which represents the spatial variation of pixel values ​​in the image, and S(x, t) represents the intensity distribution of additional source terms in the image; A deep learning processing module connected to the image processing module is used to extract features and classify the pre-processed images; The drilling guidance module connected to the deep learning processing module is used to receive the classification results and guide the drilling operation in real time.

2. The real-time analysis system of geological structure images during uranium ore drilling according to claim 1, characterized in that: The radiation intensity measurement module obtains the radiation intensity measurement value including: Collect time series data from the radiation intensity measurement device, fit the periodic variation characteristics of the radiation intensity, calculate the fluctuation frequency and amplitude, predict the instantaneous value of the radiation intensity, and pass the result to the image acquisition module. The specific formula for predicting the instantaneous value of the radiation intensity is: ； Among them, F(t) represents the radiation intensity value actually measured at time t, F0 represents the average value of the radiation intensity, ΔF represents the fluctuation amplitude of the radiation intensity, and f represents the fluctuation frequency of the radiation signal. represents the phase shift of the fluctuation, and t represents time.

3. The real-time analysis system of geological structure images during uranium ore drilling according to claim 1, characterized in that: The deep learning processing module extracts features and classifies the preprocessed image, including: The preprocessed image data is used as input to optimize and initialize the weights of the deep learning model. The fitness function is used to evaluate the prediction performance of each generation of weights. The weight values ​​are selected for crossover and mutation operations. The optimized deep learning network is trained to classify image features. The geological structure classification results are output to the drilling guidance module. The fitness function is used to evaluate the prediction performance of each generation of weights. The specific formula is: f(W)=1 / (1+E(W)); Among them, f(W) represents the prediction performance indicator of the current weight of the deep learning network, E(W) represents the classification error of the network for the input image features under the current weight, and W represents the adjustable parameters in the deep learning network.

4. The real-time analysis system of geological structure images during uranium ore drilling according to claim 1, characterized in that: The drilling guidance module receives the classification result and guides the drilling operation in real time, including: The drilling operation is modeled as a path optimization problem. The path set and operation cost are defined. The optimal path and drilling operation parameter combination are iteratively calculated. The optimized operation strategy is output to the drilling equipment. The specific formula is: ； Among them, c ij represents the operating cost required to move the drilling equipment from geological region i to region j, y ijk It indicates whether the kth drilling equipment chooses to move from geological area i to area j, i and j represent the specific geological area numbers involved in the uranium drilling operation, k represents the total number of drilling equipment involved in the path optimization, and n represents the total number of geological areas that need to be covered in the drilling operation.

5. The real-time analysis system of geological structure images during uranium ore drilling according to claim 2, characterized in that: The calculation formula for obtaining the average value F0 of the radiation intensity in the radiation intensity measurement value in the continuous time condition by the radiation intensity measurement module is: F0＝ ； Wherein, F0 represents the average value of the radiation intensity, T represents the time period, F(t) represents the radiation intensity value actually measured at time t, and t represents time.

6. The real-time analysis system of geological structure images during uranium ore drilling according to claim 2, characterized in that: The calculation formula for obtaining the average value F0 of the radiation intensity in the radiation intensity measurement value in the discrete time condition by the radiation intensity measurement module is: F0＝ ； Among them, F0 represents the average value of radiation intensity, t represents time, h represents the number of measured time points, r represents the index variable, and F(t r ) indicates that at time t r The actual radiation intensity value measured at time t r represents the rth time point.

7. The real-time analysis system of geological structure images during uranium ore drilling according to claim 1, characterized in that: The image acquisition module adjusts the image acquisition parameters in real time based on the radiation intensity measurement value, including predicting image noise based on the currently measured radiation intensity level, enhancing the image signal through an adaptive gain adjustment circuit, introducing frequency compensation technology to reduce the frequency band interference caused by high radioactivity, and adjusting the imaging frequency band when N>a×R+b, wherein R represents the measured radiation intensity, N represents the noise level in the environment, a is a constant related to the sensitivity of the equipment, and b is a fixed threshold.

8. The real-time analysis system of geological structure images during uranium ore drilling according to claim 7, characterized in that: The image noise prediction based on the currently measured radiation intensity level includes collecting the gamma ray counting information in the body and performing preliminary filtering, calculating the fluctuation coefficient in each counting interval, analyzing the fluctuation trend to estimate the number of noise points in the next frame, and calculating the standard deviation based on the current count. If σ 2 / C>γ, the anti-interference measures are started, where C represents the total gamma-ray count value in the window, σ represents the variance of the count value change, and γ represents the index value of the noise impact degree.

9. The real-time analysis system of geological structure images during uranium ore drilling according to claim 7, characterized in that: The image acquisition module adjusts the image acquisition parameters in real time based on the radiation intensity measurement value. The adaptive gain adjustment circuit includes a gain control unit and a feedback adjustment unit. The gain control unit automatically adjusts the signal amplification factor according to the environmental noise level and the radiation intensity. The feedback adjustment unit monitors the signal output quality in real time and optimizes the gain parameters through closed-loop control.

10. The real-time analysis system of geological structure images during uranium ore drilling according to claim 7, characterized in that: The image acquisition module introduces frequency compensation technology in real-time adjustment of image acquisition parameters based on the radiation intensity measurement value to reduce the frequency band interference caused by high radioactivity, including automatically adjusting the working frequency band based on the real-time monitored radiation intensity through a tunable filter.

Images