Optimization Method for Digital Acquisition of Deposit Information Data

Abstract

The present invention relates to the technical field of ore deposit data, and specifically relates to an optimized method for digital acquisition of ore deposit information data. Based on the geological evolution history data of the mining area, a three-dimensional geological model is established to simulate the formation and change of the ore deposit at different evolution stages; dynamic simulation of the key parameters of the ore deposit is carried out; according to the prediction of the geological model, the acquisition parameters are adjusted; combined with the geological evolution simulation model, the layout scheme of the sensor array is set; the sensor array adjusts the acquisition angle, azimuth and sensing area in real time through the built-in adaptive algorithm; multi-modal data from different sensors are collected in real time, and feature extraction is carried out through a deep learning model to identify the association patterns of various types of data; during the data fusion process, noise and redundant data are removed; through the anomaly detection module, the collected data is analyzed in real time; according to the geological simulation data and the deployment scheme of the acquisition equipment, the acquisition path and strategy are designed.

Description

Technical Field

[0001] The present invention relates to the technical field of ore deposit data, and specifically relates to an optimization method for digital acquisition of ore deposit information data. Background Art

[0002] The "Ore Deposit Digital Information Analysis and Display System and Method" proposed in Chinese Patent 2018114678634 is based on the metallogenic belt division map of the National Geological Archives and Baidu Map. Through the digital information display system of typical ore deposits, combined with geological and mineral maps, rock and ore specimen exploration, and scientific research data, the ore deposit information is integrated and displayed. However, the current optimization method for ore deposit information data collection has obvious deficiencies in aspects such as dynamic data collection, real-time monitoring, system intelligence, and the linkage of information display. First of all, the static characteristics of the existing method are relatively obvious. Although traditional ore deposit data collection methods can cover some geological information, they mostly rely on historical data and static data display, and do not fully consider the dynamic changes in the geological environment. Compared with the method in the comparative document, the current digital collection is often limited to collecting at fixed sampling points in the mining area, lacking the ability to capture dynamic geological phenomena in real time. For example, when geological activities, mine tremors, or fault slips occur in the mining area, the existing collection methods are difficult to adjust the sensor layout and collection frequency in real time according to the changes. In the comparative document, through the combination of Baidu Map and the data of the National Geological Archives, the metallogenic belt information of the mining area can be better displayed, but this is still a relatively static information display, and the dynamic update and feedback of the collected data cannot be realized. Therefore, like the technology shown in the comparative document, the traditional collection method lacks a dynamic response mechanism to complex geological activities in the mining area and cannot adapt to the rapidly changing conditions inside the mining area. Especially during the mining area development process, the lack of real-time collection and rapid adjustment will affect the timeliness and reliability of the data.

[0003] Secondly, the deficiencies in data processing and fusion are also a major problem in traditional methods. As mentioned in the comparative document, a digital data database was established by digitizing and integrating existing geological maps, rock and ore specimens, and scientific research materials in the deposit laboratory. However, this data integration still mainly relies on historical data and geological maps, without conducting dynamic analysis by combining real-time sensor data. Existing acquisition methods usually face the problem of fusing multi-modal data. Especially for heterogeneous data collected by different types of sensors (such as seismic sensors, gravity sensors, electromagnetic sensors, etc.), there are no effective means of fusion and processing. In practical applications, the complexity and diversity of the mining area require the sensor data to be fused and processed at multiple levels. However, existing acquisition optimization methods often only process single data types and lack the comprehensive analysis ability of cross-modal data. This results in a large gap in the collected data in terms of space and time, and it is unable to accurately reflect the three-dimensional structure and dynamic changes of the deposit. In contrast, although the technology in the comparative document can display typical deposit information in different mining areas, it mainly focuses on the data display level rather than real-time data fusion and analysis, and cannot provide effective support for real-time mining area monitoring.

[0004] Furthermore, existing methods also have deficiencies in terms of intelligence and automation levels. The method in the comparative document uses Baidu Maps and a positioning module to achieve automatic positioning and information display of the mining area, which enhances the user's interaction experience to some extent. However, the current acquisition methods still rely on manual intervention and control. Most existing acquisition optimization systems require manual setting of acquisition strategies, sensor arrangements, and data processing procedures, lacking an adaptive and intelligent adjustment mechanism. For example, when geological activities or mine tremors occur in the mining area, the existing systems cannot automatically identify abnormal situations and quickly adjust the acquisition strategies. The acquisition frequency, density, and location of the sensors remain fixed and cannot be flexibly adjusted according to real-time monitoring data. This fixed acquisition strategy is extremely likely to cause data redundancy or miss key data, having an adverse impact on the development of the mining area. Summary of the Invention

[0005] The purpose of the present invention is to provide an acquisition optimization method for digitalizing deposit information data, thereby solving some of the drawbacks and deficiencies pointed out in the background art.

[0006] The present invention adopts the following technical solutions to solve its above technical problems: An acquisition optimization method for digitalizing deposit information data, including: S1. Dynamically adjusting acquisition parameters based on geological evolution simulation:

[0007] S1.1. Based on the geological evolution historical data of the mining area, establish a three-dimensional geological model to simulate the formation and changes of the deposit at different evolution stages;

[0008] S1.2. Dynamically simulate the key parameters of the deposit, including ore body thickness, ore grade, and mineral distribution;

[0009] S1.3. Adjust the acquisition parameters including sensor sensitivity, acquisition spacing, and acquisition density according to the prediction of the geological model;

[0010] S2. Dynamic Adaptive Sensor Array and Spatial Optimization:

[0011] S2.1. Combine the geological evolution simulation model, set the layout scheme of the sensor array, and adjust the density of the sensor array according to the geological conditions of the mining area;

[0012] S2.2. The said sensor array adjusts the acquisition angle, azimuth, and sensing area in real time through the built-in adaptive algorithm;

[0013] S2.3. During the data acquisition process, the sensor array dynamically optimizes the layout according to geological changes, including increasing the sensor density when the activity of the mining area increases, or reducing the acquisition frequency in stable areas;

[0014] S3. Deep Learning-Driven Multimodal Data Real-Time Fusion and Anomaly Detection:

[0015] S3.1. Conduct real-time synchronous acquisition of multimodal data from different sensors, extract features through a deep learning model, and identify the correlation patterns of various types of data;

[0016] S3.2. Eliminate noise and redundant data during the data fusion process;

[0017] S3.3. Through the anomaly detection module, analyze the acquired data in real time, identify geological anomalies in the mining area including faults, mining tremors, and sudden changes in geological structures, and dynamically adjust the acquisition strategy according to the anomaly situation;

[0018] S4. Acquisition Path and Acquisition Strategy Iteration:

[0019] S4.1. In the initial stage, design the acquisition path and strategy based on the geological simulation data and the deployment scheme of the acquisition equipment;

[0020] S4.2. During the acquisition process, based on the Bayesian optimization algorithm, receive the acquisition data and model feedback in real time, and adjust the running path of the acquisition equipment to cover the valuable ore deposit area in a short time;

[0021] S4.3. After each data acquisition iteration, use the feedback data to update the acquisition strategy to identify the path and acquisition frequency.

[0022] Furthermore, the dynamic optimization layout method includes: dynamically adjusting sensor arrangement, acquisition density, and path planning according to the real-time acquired feedback data, and describing the three-dimensional structure of the ore deposit, mineral distribution, and thickness change over time through the following integral equation, and combining adaptive weights for acquisition optimization:

[0023]

[0024] Among them, G(t) represents the dynamic change of the three-dimensional structure of the ore deposit, which is updated with the change of time t and is one of the key variables of the acquired data, used to reflect the internal spatial characteristics of the ore deposit; D(t) represents the time change of mineral distribution, reflecting the migration or distribution change of minerals during the acquisition period; M(t) is the time change of the thickness of the ore body, which is predicted to change with the change of geological conditions; α, β, γ are the weight factors in the adaptive learning algorithm, corresponding to the influence weights of the three-dimensional structure, mineral distribution, and ore body thickness respectively. t0 and t1 represent the start and end periods of the acquisition time, and the integral operation is used to comprehensively process the change of geological characteristics during the entire acquisition period.

[0025] Furthermore, the dynamic optimization layout method includes: adopting a progressive multi-scale acquisition strategy. In the initial stage, sensors are used to scan the entire mining area to identify potential key areas; subsequently, the acquisition strategy is dynamically adjusted, and sensors are used to perform refined acquisition in the key areas; the hierarchical progressive acquisition strategy allocates the acquisition density and resources of different areas through a priority function:

[0026]

[0027] Among them, f s (A) represents the acquisition priority of a certain area, indicating the dynamic allocation of acquisition resources in the area; P h represents the thickness of the ore body, which is a key parameter in the area and is used to indicate the geological importance of the area during the acquisition process; P d represents the mineral density, indicating the abundance of mineral distribution in the area; P r is the reference value of the area, used to standardize the influence of thickness and density; λ1 and λ2 are weight coefficients, used to adjust the influence of the ore body thickness and mineral density in different acquisition areas; ∈ is an adaptive adjustment coefficient, which is dynamically adjusted according to the actual acquisition situation; δ is a precision adjustment factor, used to control the precision requirements during data acquisition.

[0028] Furthermore, the dynamic optimization layout method includes: introducing the changes of physical fields including stress field, gravity field, and magnetic field, and combining geological characteristics for dynamic monitoring of the ore deposit structure; through the linkage analysis of geology and physical fields, dynamically adjusting sensor arrangement and acquisition frequency, and monitoring and adjusting the acquisition strategy through the physical field linkage equation:

[0029]

[0030] Among them, S represents the change of the stress field, which is used to monitor the dynamic change of the pressure or stress on the ore deposit; G represents the change of the gravity field, which reflects the gravity anomaly change inside and outside the ore deposit and indicates the collapse of the underground structure or the change of the mineral distribution; M represents the change of the magnetic field, which reflects the change of the mineral composition or structure in the mining area; S0, G0, and M0 are the reference values of the stress field, gravity field, and magnetic field respectively, which are used to standardize the change amplitude of each physical field; η is the coupling coefficient, which is used to control the correlation strength between geology and the physical field.

[0031] Furthermore, the method for constructing the anomaly detection module includes: collecting multi-modal data of the mining area through various types of sensors, where the sensors include seismic sensors, gravity sensors, and electromagnetic induction sensors, which are respectively responsible for collecting key data of seismic fluctuations, gravity changes, and electromagnetic field fluctuations; preprocessing and denoising the multi-source data using a data fusion algorithm to eliminate redundant data and noise; the data fusion uses the following formula for the integration and preprocessing of multi-source data:

[0032] F fusion (x i ,y i ,z i ,t)=∫0 T (α·f1(x i ,t)+β·f2(y i ,t)+γ·f3(z i ,t))dt

[0033] Among them, x i represents the seismic fluctuation data collected by the sensor, as a function of time t, which reflects the impact of seismic activities on the ore deposit structure; y i represents the gravity change data, which records the gravity field anomaly in the mining area and reflects the change of mineral density or structure through t; z i is the electromagnetic field change data, which captures the electromagnetic characteristics of different regions in the mining area and is used to identify the change of mineral composition in the ore body; f1(x i ,t), f2(y i ,t), f3(z i ,t) are the acquisition functions respectively, which are used to describe the change trend of each sensor data over time t; α, β, γ are the corresponding weight factors, which are used to adjust the importance of different types of data in the overall fusion and reflect the contribution of different sensor data to geological analysis; T represents the time range of data acquisition, and the integral calculation is used to summarize and fuse each data source within the time interval.

[0034] Furthermore, the method for constructing the anomaly detection module includes: establishing a model of normal geological activities through learning historical geological data; detecting abnormal phenomena occurring inside the mining area, including faults, mining tremors, or sudden changes in geological structures, when the real-time collected data significantly deviates from the standard pattern; identifying abnormal situations through comparison of historical and real-time data; the anomaly detection module learns the standard feature patterns under different geological conditions through an adaptive neural network and uses non-linear analysis methods to detect and compare the collected data in real time:

[0035]

[0036] Among them, D obs (t i ) represents the real-time data observed by the sensor at time t i , which is multi-modal data collected at the current moment; D ref (t i ) represents the reference data corresponding to time t i in the historical data, reflecting the normal state of the geological structure; n is the number of samples collected within a time period, and the mean value is calculated through data at multiple time points; calculates the relative deviation between the real-time observed data and the historical reference data, which can quantify the degree of difference between the current data and the standard pattern; Through square sum and square root extraction, the core measurement method of non-linear anomaly detection is formed, which is used to smooth the differences between different data.

[0037] Furthermore, the method for constructing the anomaly detection module includes: adjusting the data collection strategy according to the detected abnormal situations; the adjustment strategies include dynamically increasing the collection frequency, adjusting the collection range, and dynamically deploying the sensor types;

[0038] When a mining tremor signal is detected, increase the collection frequency of the sensors in this area; when regional gravity or magnetic field anomalies are detected, redeploy the sensors to expand the collection range and capture the areas affected by the anomaly prediction; the adjustment of the collection strategy dynamically manages the collection frequency and collection density through a formula:

[0039] f adjust (A, ω, t) = A·sin(ωt) + ΔA

[0040] Among them, A is the initial sensor acquisition density, representing the sensor distribution and acquisition frequency in a certain area under normal circumstances; ω is the acquisition frequency adjustment factor after an abnormal event is triggered, usually set according to the detected abnormal intensity; t represents time, which is used to capture the acquisition rhythm that changes with events over time when dynamically adjusting the acquisition frequency and density; sin(ωt) represents the fluctuation pattern of the acquisition frequency with changes in time and abnormal detection, and ω controls the frequency of the fluctuation; ΔA is the additional acquisition density dynamically increased according to the abnormal detection result, increasing the acquisition intensity in key areas or periods.

[0041] Advantages of the present invention:

[0042] 1. Improve acquisition accuracy and efficiency: By dynamically optimizing the sensor layout and acquisition strategy, the system can adjust the acquisition density, path, and frequency according to real-time feedback, so as to achieve precise monitoring of key areas in the mining area, avoid resource waste, and improve the efficiency of data acquisition.

[0043] 2. Comprehensive multi-dimensional data fusion: This method introduces multi-modal sensors, including various data sources such as seismic, gravity, and electromagnetic induction, and effectively integrates information through data fusion algorithms to form a more comprehensive geological feature of the ore deposit, ensuring the effective utilization of different types of data and improving the ability to capture the complexity and diversity of the ore deposit.

[0044] 3. Real-time abnormal detection and response: Through adaptive neural networks and non-linear analysis methods, the system can real-time identify abnormal situations in the mining area, including faults, mine tremors, and sudden changes in geological structures, and immediately adjust the acquisition strategy according to the detection results to achieve efficient response and data supplementation, and timely capture key data.

[0045] 4. Dynamic adaptive acquisition strategy: The system combines the linkage analysis of geology and physical fields, and can adaptively adjust the sensor arrangement and acquisition frequency according to the dynamic changes in the mining area, ensuring high-density data acquisition in key areas, while reducing the acquisition frequency in stable areas, so as to achieve reasonable allocation and optimization of acquisition resources. Description of the drawings

[0046] Figure 1 It is a flow chart of the acquisition optimization method for digitalization of ore deposit information data of the present invention.

[0047] Figure 2 It is a flow chart of real-time fusion and abnormal detection of multi-modal data driven by deep learning of the present invention.

[0048] Figure 3 It is a flow chart of the iteration of the acquisition path and acquisition strategy of the present invention.

[0049] Figure 4 It is a flow chart of the dynamic optimization layout method of the present invention.

[0050] Figure 5 This is the flowchart for constructing the anomaly detection module of the present invention. Detailed implementation manners

[0051] The following will give a detailed description of the specific implementation manners of the present invention with reference to the accompanying drawings.

[0052] Combined with the attached Figure 1 For the method of optimizing the acquisition of digitalized deposit information data of the present invention, it aims to improve the efficiency and accuracy of deposit data acquisition through scientific parameter adjustment and dynamic simulation. First, for the dynamic adjustment of acquisition parameters based on geological evolution simulation, the primary task in this process is to establish a three-dimensional geological model with the help of the geological evolution history data of the mining area. This model not only reflects the spatial distribution of the deposit but also can effectively simulate the formation and changes of the deposit at different evolution stages, helping to better understand the geological characteristics of the mining area. Next, focus on the dynamic simulation of the key parameters of the deposit, including ore body thickness, ore grade, and mineral distribution, etc. The dynamic simulation of these key parameters is the basis, which can reveal the potential changes inside the deposit and thus provide an important reference basis for subsequent acquisition strategies. Finally, according to the prediction of the geological model, adjust various acquisition parameters, such as sensor sensitivity, acquisition spacing, and acquisition density, etc., to meet the data acquisition requirements at different evolution stages. For example, when the model predicts significant changes in ore body thickness, it is necessary to increase the sensor sensitivity and acquisition frequency to capture more detailed data; while in the stable area of the deposit, the acquisition spacing can be appropriately increased and the acquisition density can be reduced to improve the acquisition efficiency and reduce unnecessary data redundancy.

[0053] The second step involves a dynamic adaptive sensor array and spatial optimization, aiming to improve the effectiveness and accuracy of data acquisition through flexible sensor layout and real-time adjustment. First, combined with the geological evolution simulation model, set the layout scheme of the sensor array and adjust the density of the sensor array according to the specific geological conditions of the mining area. This process ensures that the distribution of sensors can match the geological characteristics of the deposit. For example, increase the sensor density in areas with thicker ore bodies or higher ore grades to obtain more detailed data. Next, the described sensor array is equipped with a built-in adaptive algorithm that can adjust the acquisition angle, azimuth, and sensing area in real time. The sensors can work according to the fixed layout and flexibly adjust according to real-time data feedback, thereby maximizing the coverage rate and quality of data acquisition. Finally, during the data acquisition process, the sensor array dynamically optimizes the layout according to geological changes. For example, when the activity of the mining area increases, the system will actively increase the sensor density to densely collect more detailed geological information, while in the stable area, the acquisition frequency will be appropriately reduced to reduce resource waste and optimize the data processing efficiency.

[0054] Combined with Figure 2, The third step involves real-time fusion and anomaly detection of multi-modal data driven by deep learning, aiming to improve the data integration and analysis capabilities through advanced algorithms for a better understanding of the geological characteristics of the mining area. First, multi-modal data from different sensors are collected in real-time synchronization. This process ensures that different types of data, such as seismic waves, gravity changes, and electromagnetic field data, can be integrated within the same time frame. Through feature extraction by deep learning models, the correlation patterns between various types of data can be effectively identified, thus revealing potential geological phenomena. For example, deep learning models can learn the complex relationships between seismic signals and geological structure changes. Then, during the data fusion process, noise and redundant data are removed. This step is crucial for ensuring data quality. By removing irrelevant or duplicate information, the accuracy and effectiveness of data analysis can be improved. Finally, through the anomaly detection module, the collected data is analyzed in real-time. The function of this module is to identify geological anomalies in the mining area, including faults, mining tremors, and sudden changes in geological structures. Anomaly detection can not only timely discover potential risks but also dynamically adjust the acquisition strategy according to the anomalies to cope with the complex changes in the mining area. For example, when a mining tremor is detected, the data acquisition frequency can be increased or the sensor position can be adjusted.

[0055] Combined with Figure 3 , The fourth step involves the iteration of the acquisition path and acquisition strategy, aiming to improve the effectiveness and coverage rate of data by continuously optimizing the acquisition process. First, in the initial stage, according to the geological simulation data and the deployment plan of the acquisition equipment, the acquisition path and strategy are designed. This process includes evaluating the geological characteristics of the mining area to formulate a reasonable acquisition plan to ensure that the important areas in the ore deposit are preferentially covered. Next, during the acquisition process, based on the Bayesian optimization algorithm, the acquisition data and model feedback are received in real-time. The key to this step is to use the ability of Bayesian optimization to dynamically adjust the running path of the acquisition equipment to ensure the maximum coverage of valuable ore deposit areas in a short time. The Bayesian optimization algorithm can intelligently predict which areas are most likely to contain rich mineral deposits based on the distribution of existing data, thus guiding the acquisition equipment to adjust its direction and position. Finally, after each iteration of data acquisition, the acquisition strategy is updated using the feedback data to identify the path and acquisition frequency, and further optimize the subsequent acquisition plan according to the actual acquisition results. For example, after significant changes in the ore body thickness are found in certain areas, the future acquisition frequency needs to be adjusted to obtain more detailed data.

[0056] Example 1:

[0057] Refer to Figure 4, in this embodiment, the dynamic optimization layout method includes dynamically adjusting sensor arrangement, acquisition density, and path planning according to the real-time collected feedback data, and describing the three-dimensional structure of the ore deposit, mineral distribution, and thickness change over time through the following integral equation, and combining adaptive weights for acquisition optimization:

[0058]

[0059] In this formula, G(t) represents the dynamic change of the three-dimensional structure of the ore deposit, which is updated with the change of time t and is used to reflect the internal spatial characteristics of the ore deposit; D(t) represents the time change of mineral distribution, reflecting the migration or distribution change of minerals during the acquisition period; M(t) is the time change of the ore body thickness, which is predicted to change with the change of geological conditions; α, β, γ are the weight factors in the adaptive learning algorithm, corresponding to the influence weights of the three-dimensional structure, mineral distribution, and ore body thickness respectively; t0 and t1 represent the start and end periods of the acquisition time, and the integral operation is used to comprehensively process the change of geological characteristics during the entire acquisition period.

[0060] It is assumed that the three-dimensional structure G(t) of the ore deposit in a certain mining area has undergone multiple stages of changes within one year. The initial thickness of the ore deposit is 15 meters, and it is expected to increase to 20 meters due to geological activities in the sixth month. The mineral distribution D(t) shows uneven migration in different regions. The collected data shows that the ore grade (such as metal content) has increased from 5% to 8% within six months. Through the real-time feedback of the sensor, the set weight factors are α = 0.5, β = 0.3, γ = 0.2, which reflects that the three-dimensional structure is more important for the overall data than the mineral distribution and the ore body thickness. The set acquisition period is t0 = 0, t1 = 12 months.

[0061] During the data acquisition process, by dynamically adjusting the sensor arrangement and acquisition density, the feedback data received by the system in real time enables the sensor to increase the density in key areas. For example, the density increases to 5 sensors per square kilometer in areas with frequent mine tremors, usually 2 sensors. At the same time, the optimization of the path planning enables each data acquisition to cover more valuable areas in a short time.

[0062] Next, integral calculation is carried out to evaluate the change of geological characteristics during the entire acquisition period. It is assumed that within the 12 months of acquisition, the change record of the three-dimensional structure G(t) is: G0 = 15, G6 = 20, G12 = 18, and the average change can be simplified to G(t) = 15 + 0.5t (linear change). The change record of the mineral distribution is that D(t) increases linearly from 5% to 8% and can be expressed as D(t) = 5 + 0.25t, and the ore body thickness M(t) can also be expressed linearly as M(t) = 15 + 0.5t.

[0063] Substitute these formulas into the main integral formula:

[0064] F(G, D, M, t) = ∫₀ 12 (0.5·(15 + 0.5t) + 0.3·(5 + 0.25t) + 0.2·(15 + 0.5t))dt

[0065] After further simplification, we get:

[0066] F(G, D, M, t) = ∫₀ 12 (0.5·(15) + 0.3·(5) + 0.2·(15) + (0.25·0.3 + 0.5·0.5)t)dt

[0067] = ∫₀ 12 (7.5 + 1.5t)dt

[0068] After calculation, we get:

[0069] = [7.5t + 0.75t 2 1 ₀ 2 = 7.5×12 + 0.75×12 2 = 90 + 108 = 198

[0070] The final calculation result is 198, indicating that within this year, through the dynamic optimization of the sensor layout and acquisition strategy, the amount of geological feature information successfully obtained is 198.

[0071] Then, a progressive multi-scale acquisition strategy is adopted to make the data acquisition more efficient and accurate. Initially, the entire mining area is widely scanned by sensors to identify potential key areas. The preliminary scan of a certain mining area shows several areas where the thickness of the ore body exceeds 15 meters, and the ore grade fluctuates between 5% and 1%0. At this stage, the acquisition team sets up 5 sensors, evenly distributed in the mining area, to monitor the deposit information in real time. The scan results show that some areas exhibit higher mineral density and thickness, and these areas are marked as key acquisition areas.

[0072] Next, the acquisition strategy is dynamically adjusted to enter the refined acquisition stage. Using a hierarchical progressive acquisition strategy, the acquisition density and resources of different areas are allocated through a priority function. Here, the set priority function is:

[0073]

[0074] Among them, P h represents the thickness of the ore body. In the key area A, P h is 20 meters; P d represents the mineral density, set to 8 tons per cubic meter; P r ​is the reference value of the area, set as a combination of 10 meters and 6 tons per cubic meter. The weight coefficients are set as λ1 = 0.6 and λ2 = 0.4, the adaptive adjustment coefficient ∈ ranges from 1 to 3, and the precision adjustment factor δ ranges from 1 to 2. Through these settings, the acquisition priority of area A can be calculated:

[0075]

[0076] Substitute into the calculation. First, calculate each part:

[0077]

[0078] When ∈ = 2 is set, we get:

[0079] = 2·(1.733) 0.6667 ≈ 2·1.464 ≈ 2.928

[0080] Therefore, the acquisition priority of area A is 2.928, indicating that more intensive data acquisition should be carried out in this area first. According to the priority, further increase the sensor density in this area to 8 sensors per square kilometer and collect data intensively.

[0081] After the refined acquisition, the system can analyze these data in real time and adjust the acquisition strategy through feedback. If subsequent data acquisition shows that the thickness of the ore body in this area has increased or the mineral distribution has changed, the system will adjust the acquisition density or path planning accordingly to ensure the effective utilization of resources and the accuracy of data.

[0082] Finally, by introducing the changes in physical fields including the stress field, gravity field, and magnetic field, combined with geological characteristics, dynamic monitoring of the ore deposit structure is carried out to ensure the efficiency and accuracy of data acquisition. Set the stress field change (S) in a certain mining area as 300 kPa, the gravity field change (G) as 0.04 g, and the magnetic field change (M) as 20 nT. Set the reference values So as 250 kPa, Go as 0.02 g, and Mo as 15 nT, and the coupling coefficient η ranges from 1 to 5. Take η = 2 for calculation. In this case, the coupling equation can be expressed as:

[0083]

[0084] Substitute the specific values into the formula:

[0085]

[0086] Calculate each part:

[0087]

[0088] Therefore,

[0089]

[0090] This indicates that the physical field of the current ore deposit varies greatly, suggesting the need for intensive data collection in this area. Combining these results, the exploration team immediately increased the sensor layout density to 10 per square kilometer in order to more effectively monitor the dynamic changes of the ore deposit.

[0091] During the process of dynamically adjusting the sensor layout and acquisition frequency, the team also monitors the data feedback in real time. If it is detected that the change frequencies of the stress field and the gravity field increase, the system will further optimize the acquisition path and increase the data acquisition frequency to ensure valuable information can be obtained at critical moments.

[0092] Example 2:

[0093] Combined with Figure 5 , in this embodiment, for the method of constructing the anomaly detection module, by constructing the anomaly detection module, various types of sensors are used to collect multi-modal data of the mining area to improve the accuracy of ore deposit structure monitoring. It is set that ten seismic sensors, five gravity sensors, and eight electromagnetic induction sensors are installed in a certain mining area. The seismic sensors are responsible for monitoring seismic fluctuations, the gravity sensors detect the gravity changes in the mining area, and the electromagnetic sensors are used to capture electromagnetic field fluctuations. It is set that during the one-month monitoring process, the sensors recorded the following data: The seismic fluctuation data (x i ) showed obvious outliers during certain periods, the gravity change (y i ) data showed sudden fluctuations in the gravity field in certain areas, and the electromagnetic field change (z i ) data indicated changes in the electromagnetic characteristics within the mining area.

[0094] To process this multi-source data, first, a data fusion algorithm is applied to preprocess the collected data to eliminate redundant data and noise. According to the formula:

[0095] F fusion (x i , y i , z i , t) = ∫0 T (α · f1(x i , t) + β · f2(y i , t) + γ · f3(z i , t))dt

[0096] Here, the time range T is set to 30 days, and α, β, and γ are 0.5, 0.3, and 0.2 respectively, representing the weights of seismic fluctuations, gravity changes, and electromagnetic field changes in data fusion.

[0097] It is set that within 30 days, the change trend of the seismic fluctuation data is: f1(xi , t) = 2sin(0.1t) + 3, the gravity change is: f2(y i , t) = 1.5t + 1, the electromagnetic field change is: f3(z i , t) = 0.5t 2 - 2.

[0098] Substitute these functions into the formula and perform integral calculations:

[0099] 1. Calculate the integral of f1:

[0100]

[0101] 2. Calculate the integral of f2:

[0102]

[0103] 3. Calculate the integral of f3:

[0104]

[0105] Substitute these results into the main formula for the final calculation:

[0106] F fusion = ∫0 30 (0.5·110 + 0.3·705 + 0.2·4440)dt = 0.5·110 + 0.3·705 + 0.2·4440

[0107] = 55 + 211.5 + 888 = 1154.5

[0108] This fusion result (1154.5) provides a basis for subsequent anomaly detection, indicating that the geological activities in the mining area are relatively active during the monitored time, and further analysis of the geological changes in specific areas is required. When the fusion data exceeds the preset threshold, the system will trigger the anomaly detection module. By analyzing the feedback from various sensors, it can timely identify potential geological risks, such as mining tremors or structural changes, and adjust the data collection strategy and frequency to ensure the timeliness and accuracy of the data.

[0109] The construction of the anomaly detection module depends on the learning of historical geological data to establish a model of normal geological activities. Suppose a research team in a mining area has collected geological activity data for the past ten years and established a benchmark model of normal geological activities. By comparing the real-time collected data with the historical data, the team can identify abnormal phenomena within the mining area, such as faults, mining tremors, or sudden changes in geological structures.

[0110] To achieve this goal, the team adopted an adaptive neural network to learn the standard feature patterns under different geological conditions. Suppose that during a certain period, the team collected the following data in real time: the observed data D obs (t1) = 105, and the corresponding historical reference data D ref (t1) = 100; the observed data D obs (t2) = 200, and the historical reference data is D ref (t2) = 150; the observed data D obs (t3) = 180, and the historical reference data is D ref (t3) = 190.

[0111] Anomaly detection is carried out using the formula:

[0112]

[0113] Here, b = 3 (corresponding to three time points), and the calculation is as follows:

[0114] 1. For t1:

[0115]

[0116] Its square is 0.0025.

[0117] 2. For t2:

[0118]

[0119] Its square is 0.1111.

[0120] 3. For t3:

[0121]

[0122] Its square is 0.0028.

[0123] Substitute these results into the formula:

[0124]

[0125] The detection result is 0.197. If the set threshold is 0.15, this value exceeds the preset normal range, indicating that there is an abnormal phenomenon in the mining area during this period.

[0126] After discovering the anomaly, the team will further analyze the geological risks. For example, when an anomaly in mining tremors is detected, the system will trigger an alarm and increase the acquisition frequency in this area by rearranging the sensors in order to obtain more detailed data and further identify the fault location and its activity.

[0127] When the anomaly detection module identifies a mine tremor signal, the system will quickly adjust the data acquisition strategy to ensure timely capture of dynamic information on geological changes. For example, in a certain mining area during a monitoring, the sensor detected a mine tremor signal with an amplitude reaching 1.5 times that of historical data, indicating a relatively high anomaly intensity. According to the preset response mechanism, the research team set the initial acquisition density of the sensors as A = 10 sensors, and the normal acquisition frequency of each sensor was once per hour.

[0128] In this case, the acquisition frequency adjustment factor ω after the anomaly event is triggered can be set to 2 rad / h, that is, the acquisition frequency is increased by two times per hour. The team set ΔA to 5, indicating that the acquisition frequencies of 5 sensors need to be increased in the mine tremor affected area. Through the formula:

[0129] f adjust (A, ω, t) = A·sin(ωt) + ΔA

[0130] At t = 0, calculate the acquisition frequency:

[0131] f adjust (10, 2, 0) = 10·sin(2·0) + 5 = 0 + 5 = 5

[0132] This means that at t = 0, after the mine tremor occurs, 5 additional acquisition frequencies are required in this area, making the total acquisition frequency 5 times per hour.

[0133] When the time progresses to t = 0.5 hours, the acquisition frequency becomes:

[0134] f adjust (10, 2, 0.5) = 10·sin(2·0.5) + 5 = 10·sin1 + 5 ≈ 10·0.8415 + 5 ≈ 8.415 + 5

[0135] = 13.415

[0136] At this time, the acquisition frequency dynamically adjusted by the system is approximately 13 times per hour to monitor the mine tremor affected area at a higher frequency.

[0137] If regional gravity or magnetic field anomalies are detected, for example, a 2.5% fluctuation is caused by the change in the gravity field, the team will redeploy the sensors to expand the acquisition range. Set the reference gravity value as t0 = 9.81 m / s 2 , and calculate the gravity anomaly amplitude through the formula:

[0138] ΔG = 0.025·G0 = 0.025·9.81 ≈ 0.24525 m / s 2

[0139] This amplitude indicates that the team should expand the acquisition range in areas with significant gravity changes, increasing the number of sensors from 10 to 15 and simultaneously increasing the monitoring frequency around the abnormal area.

[0140] Through such dynamic adjustments, the research team can obtain key data in a timely manner when mine tremors and other abnormal events occur, predict the risks in the mining area, and ensure the safety and effectiveness of the ore deposit development process.

[0141] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of the present invention claimed is defined by the appended claims and their equivalents.

Claims

1. An acquisition optimization method for digitalizing deposit information data, characterized in that It includes the following steps: S1. Dynamically adjust the acquisition parameters based on geological evolution simulation: S1.

1. Based on the geological evolution history data of the mining area, establish a three-dimensional geological model to simulate the formation and changes of the ore deposit at different evolution stages; S1.

2. Dynamically simulate the key parameters of the ore deposit, including ore body thickness, ore grade, and mineral distribution; S1.

3. Adjust the acquisition parameters including sensor sensitivity, acquisition spacing, and acquisition density according to the prediction of the geological model; S2. Dynamically adaptive sensor array and spatial optimization: S2.

1. Combine the geological evolution simulation model, set the layout scheme of the sensor array, and adjust the density of the sensor array according to the geological conditions of the mining area; S2.

2. The said sensor array adjusts the acquisition angle, azimuth, and sensing area in real time through the built-in adaptive algorithm; S2.

3. During the data acquisition process, the sensor array dynamically optimizes the layout according to geological changes, including increasing the sensor density when the activity of the mining area increases, or reducing the acquisition frequency in stable areas; S3. Deep learning-driven real-time fusion and anomaly detection of multi-modal data: S3.

1. Collect multi-modal data from different sensors in real time, extract features through a deep learning model, and identify the correlation patterns of various types of data; S3.

2. During the data fusion process, eliminate noise and redundant data; S3.

3. Through the anomaly detection module, analyze the collected data in real time, identify geological anomalies in the mining area including faults, mine tremors, and sudden changes in geological structures, and dynamically adjust the acquisition strategy according to the anomaly situation; S4. Iteration of acquisition path and acquisition strategy: S4.

1. In the initial stage, design the acquisition path and strategy based on the geological simulation data and the deployment scheme of the acquisition equipment; S4.

2. During the acquisition process, based on the Bayesian optimization algorithm, receive the acquisition data and model feedback in real time, and adjust the running path of the acquisition equipment to cover the valuable ore deposit area in a short time; S4.

3. After each data acquisition iteration, use the feedback data to update the acquisition strategy to identify the path and acquisition frequency; The said dynamic optimization layout method includes: dynamically adjusting the sensor arrangement, acquisition density, and path planning according to the real-time collected feedback data, and describing the three-dimensional structure, mineral distribution, and thickness of the ore deposit over time through the following integral equation, and combining adaptive weights for acquisition optimization: Among them, G(t) represents the dynamic change of the three-dimensional structure of the ore deposit, which is updated with the change of time t and is one of the key variables of the acquisition data, used to reflect the internal spatial characteristics of the ore deposit; D(t) represents the time change of the mineral distribution, reflecting the migration or distribution change of minerals during the acquisition time period; M(t) is the time change of the ore body thickness, which is predicted to change with the change of geological conditions; α, β, γ are the weight factors in the adaptive learning algorithm, corresponding to the influence weights of the three-dimensional structure, mineral distribution, and ore body thickness respectively. t0 and t1 represent the start and end periods of the acquisition time, and the integral operation is used to comprehensively process the changes in geological characteristics during the entire acquisition period; The dynamic optimization layout method includes: adopting a progressive multi-scale acquisition strategy, initially using sensors to scan the entire mining area to identify potential key areas; subsequently dynamically adjusting the acquisition strategy and using sensors to conduct refined acquisition in the key areas; the hierarchical progressive acquisition strategy allocates the acquisition density and resources of different areas through a priority function: Among them, f s (A) is the acquisition priority of a certain area, indicating the dynamic allocation of acquisition resources in the area; P h represents the ore body thickness, which is a key parameter within the area and is used to indicate the geological importance of the area during the acquisition process; P d represents the mineral density, indicating the abundance of mineral distribution in the area; P r is the baseline reference value of the area, used to standardize the effects of thickness and density; λ1 and λ2 are weight coefficients, used to adjust the effects of ore body thickness and mineral density in different acquisition areas; ∈ is an adaptive adjustment coefficient, dynamically adjusted according to the actual acquisition situation; δ is a precision adjustment factor, used to control the precision requirements during data acquisition; The dynamic optimization layout method includes: introducing the changes of physical fields including stress field, gravity field and magnetic field, and combining with geological characteristics to conduct dynamic monitoring of the deposit structure; through the linkage analysis of geology and physical fields, dynamically adjusting the sensor layout and acquisition frequency, and monitoring and adjusting the acquisition strategy through the physical field linkage equation: Among them, S represents the change of the stress field, which is used to monitor the dynamic change of the pressure or stress received by the deposit; G represents the change of the gravity field, which reflects the gravity anomaly change inside and outside the deposit, indicating the collapse of the underground structure or the change of mineral distribution; M represents the change of the magnetic field, which reflects the change of the mineral composition or structure in the mining area; S0, G0, and M0 are the reference values of the stress field, gravity field and magnetic field respectively, which are used to standardize the change range of each physical field; η is the linkage coefficient, which is used to control the correlation strength between geology and physical fields.

2. The method for optimizing the acquisition of digital deposit information data according to claim 1, wherein The method for constructing the anomaly detection module includes: collecting multi-modal data of the mining area through various types of sensors, and the sensors include seismic sensors, gravity sensors and electromagnetic induction sensors, which are respectively responsible for collecting key data such as seismic fluctuations, gravity changes, and electromagnetic field fluctuations; using a data fusion algorithm to preprocess and denoise the multi-source data, and eliminating redundant data and noise; the data fusion uses a formula to integrate and preprocess the multi-source data: where x i represents the seismic wave data collected by the sensor, as a function of time t, reflecting the impact of seismic activities on the deposit structure; y i represents the gravity change data, recording the gravity field anomaly in the mining area, and reflecting the change of mineral density or structure through t; z i is the electromagnetic field change data, capturing the electromagnetic characteristics of different regions in the mining area, and used to identify the change of mineral composition in the ore body; f1(x i ,t), f2(y i ,t), f3(z i ,t) are the acquisition functions respectively, used to describe the change trend of each sensor data with time t; α, β, γ are the corresponding weight factors, used to adjust the importance of different types of data in the overall fusion, reflecting the contribution of different sensor data to geological analysis; T represents the time range of data acquisition, and the integral calculation is used to summarize and fuse each data source within the time interval.

3. The method for optimizing the acquisition of digital deposit information data according to claim 2, characterized in that The method for constructing the anomaly detection module includes: establishing a model of normal geological activities through learning historical geological data; when the real-time collected data significantly deviates from the standard mode, detecting abnormal phenomena occurring inside the mining area, including faults, mining earthquakes or sudden changes in geological structures; identifying abnormal situations through the comparison of historical and real-time data; the anomaly detection module learns the standard feature patterns under different geological conditions through an adaptive neural network, and uses a non-linear analysis method to detect and compare the collected data in real time: Among them, D obs (t i ) represents the real-time data observed by the sensor at time t i , which is multi-modal data collected at the current moment; D ref (t i ) represents the reference data corresponding to time t i in the historical data, reflecting the normal state of the geological structure; n is the number of samples collected within the time period, and the mean value is calculated through data at multiple time points; calculates the relative deviation between the real-time observed data and the historical reference data, which can quantify the difference degree between the current data and the standard mode; Through the square root of the sum of squares, it forms the core measurement method for non-linear anomaly detection, which is used to smooth the differences between different data.

4. The method for optimizing the acquisition of digital deposit information data according to claim 3, characterized in that The method for constructing the anomaly detection module includes: adjusting the data acquisition strategy according to the detected abnormal situation; the adjustment strategy includes dynamically increasing the acquisition frequency, adjusting the acquisition range, and dynamically deploying the sensor type; When a mining earthquake signal is detected, increase the acquisition frequency of the sensors in this area; when a regional gravity or magnetic field anomaly is detected, expand the acquisition range by redeploying the sensors to capture the area affected by the anomaly prediction; the adjustment of the acquisition strategy dynamically manages the acquisition frequency and acquisition density through a formula: f adjust (A, ω, t) = A·sin(ωt) + ΔA Among them, A is the initial sensor acquisition density, representing the sensor distribution and acquisition frequency in a certain area under normal circumstances; ω is the acquisition frequency adjustment factor after an abnormal event is triggered, usually set according to the detected abnormal intensity; t represents time, which is used to capture the acquisition rhythm that changes with events over time when dynamically adjusting the acquisition frequency and density; sin(ωt) represents the fluctuation pattern of the acquisition frequency with changes in time and abnormal detection, and ω controls the frequency of the fluctuation; ΔA is the additional acquisition density dynamically increased according to the abnormal detection result, increasing the acquisition intensity in key areas or periods.

Images