A smart mine mining method, device and medium based on an industrial cloud platform

Abstract

The application discloses a kind of wisdom mine mining method, equipment and medium based on industrial cloud platform, it is related to wisdom mining technical field, including, through data service bus, digital twin analysis module is communicated with the data management fusion module, for receiving the mine comprehensive state data that data management fusion module outputs, constructs three-dimensional geological model, and carries out abnormal behavior detection by deep learning algorithm, outputs exception detection result;Intelligent decision optimization module is associated with the digital twin analysis module by algorithm coordination interface, for establishing disaster prediction model based on exception detection result and mine comprehensive state data, carries out disaster risk assessment, and utilizes reinforcement learning algorithm to optimize mining strategy, obtains optimal mining scheme, is guided by feedback control link back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is dispatched in field back to data acquisition and uploads to cloud module and is collected and is

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent mining, in particular to an intelligent mine mining method, device and medium based on an industrial cloud platform. BACKGROUND

[0002] With the rapid development of industrial internet and digital technology, intelligent mines, as an important direction of the transformation and upgrading of the mining industry, have received widespread attention and practice at home and abroad in recent years. In order to improve the efficiency and safety of mine operation, mine monitoring systems based on Internet of Things (IoT) and cloud computing have been gradually popularized and applied in recent years. In the prior art, some studies have deployed sensor networks to collect mine environment parameters (such as gas concentration, surrounding rock stress, and temperature and humidity, etc.), and transmit the data to a local server for centralized monitoring, to realize preliminary sensing and early warning of the running state of the mine. In addition, some systems introduce geographic information systems (GIS) and three-dimensional modeling technology to visualize the spatial distribution of ore bodies, to assist in mining design and production planning. To some extent, this kind of technical path improves the informatization level of the mine, promotes the transformation from "experience-driven" to "data-driven", and lays a foundation for the in-depth development of intelligent mines.

[0003] The existing technology still has obvious limitations in the deep fusion of multi-source heterogeneous data and dynamic decision support. On the one hand, mine geology, equipment state and production progress data are usually collected and managed independently by different subsystems, lacking a unified data integration architecture, resulting in problems such as inconsistent data timing and semantic heterogeneity, making it difficult to form a comprehensive understanding of the overall running state of the mine; on the other hand, most current systems still remain at the "monitoring-alarm" level, lacking intelligent analysis capabilities for the evolution process of complex geological structures, making it difficult to identify potential rock mass instability, water inrush and other disaster precursor characteristics in advance. The above problems restrict the autonomous decision-making level of the mine system under complex and variable working conditions. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides an intelligent mine mining device based on an industrial cloud platform, which solves the problems of being unable to comprehensively perceive the overall running state of the mine and being unable to effectively identify potential disaster precursor characteristics in the prior art.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides an intelligent mine mining device based on an industrial cloud platform, which comprises a data collection and cloud uploading module, a data governance and fusion module, a digital twin analysis module and an intelligent decision optimization module.

[0008] The data collection cloud uploading module is configured to acquire mine production comprehensive data, and upload the data to the industrial cloud platform after preprocessing and formatting;

[0009] The data governance fusion module is connected to the data collection cloud uploading module through a cloud data channel, configured to receive the processed mine production comprehensive data, and perform storage, cleaning, aggregation and preliminary analysis;

[0010] The digital twin analysis module is connected to the data governance fusion module through a data service bus, configured to receive the mine comprehensive state data output by the data governance fusion module, construct a three-dimensional geological model, and perform abnormal behavior detection through a deep learning algorithm, and output an abnormal detection result;

[0011] The intelligent decision optimization module is connected to the digital twin analysis module through an algorithm coordination interface, configured to establish a disaster prediction model based on the abnormal detection result and the mine comprehensive state data, perform disaster risk assessment, and optimize a mining strategy using a reinforcement learning algorithm to obtain an optimal mining scheme, and feed back to the data collection cloud uploading module through a feedback control link to guide on-site collection and scheduling.

[0012] As a preferred scheme of the intelligent mine mining equipment based on the industrial cloud platform, the digital twin analysis module includes a three-dimensional modeling submodule, a feature extraction submodule and an abnormal detection submodule.

[0013] The three-dimensional modeling submodule is configured to receive the mine comprehensive state data, and construct a three-dimensional geological model in combination with real-time monitoring operation data and historical operation records.

[0014] The feature extraction submodule is configured to perform extraction and standardization processing of multi-dimensional spatio-temporal features of the three-dimensional geological model.

[0015] The abnormal detection submodule is configured to perform abnormal behavior recognition and analysis based on a deep learning algorithm.

[0016] As a preferred scheme of the intelligent mine mining equipment based on the industrial cloud platform, the intelligent decision optimization module includes a disaster prediction and evaluation submodule, a strategy generation submodule and a reinforcement learning optimization submodule.

[0017] The disaster prediction and evaluation submodule is configured to perform construction and risk assessment of a disaster prediction model.

[0018] The strategy generation submodule is configured to perform generation of an initial mining strategy.

[0019] The reinforcement learning optimization submodule is configured to perform reinforcement learning optimization of the initial mining strategy using a reinforcement learning algorithm.

[0020] As a preferred scheme of the intelligent mine mining equipment based on the industrial cloud platform, the processed mine production comprehensive data is subjected to denoising, outlier elimination and time synchronization processing according to the multi-source original data type and the sampling frequency, and then normalized, unit-converted and coded and mapped according to the preset data standard format and field structure.

[0021] As a preferred scheme of the intelligent mine mining equipment based on the industrial cloud platform, the mine comprehensive state data is obtained by performing data cleaning on the processed mine production comprehensive data through missing value filling, repeated data elimination and noise smoothing, grouping and aggregating the related processed mine production comprehensive data according to the spatial position, the equipment category and the operation link, extracting mine operation characteristic parameters, and performing preliminary analysis on the mine operation characteristic parameters.

[0022] As a preferred scheme of the intelligent mine mining equipment based on the industrial cloud platform, the three-dimensional geological model is constructed, and the abnormal behavior is detected through the deep learning algorithm, and the abnormal detection result is output, and the specific steps are as follows,

[0023] The three-dimensional geological model is generated through spatial interpolation and voxel reconstruction algorithm based on the spatial coordinates, the rock layer attributes and the equipment operation position in the mine comprehensive state data, the operation surface deformation and the geological change information obtained through real-time monitoring are fused, and the drilling surveying and mapping and the mining track data in the historical operation records are referred to;

[0024] The multi-dimensional characteristic quantities in the spatial voxels are extracted from the three-dimensional geological model, and a multi-dimensional space-time feature matrix is constructed;

[0025] The multi-dimensional space-time feature matrix is subjected to three-dimensional Gaussian filter smoothing, and a hidden layer representation vector is extracted by using a self-encoding neural network;

[0026] The hidden layer representation vector is subjected to time series decomposition and spatial gradient mapping, the space-time change characteristics are extracted through multi-scale convolution, and the response intensity distribution of each spatial node in the space-time domain is calculated;

[0027] Based on the normalized response intensity distribution and the localized anomaly index, the comprehensive judgment result is obtained through fusion decision function;

[0028] The comprehensive judgment result is subjected to classification processing, and isolated abnormal points are eliminated by applying three-dimensional space-time connectivity constraint, and an abnormal mask and a corresponding confidence map are generated;

[0029] The abnormal mask and the corresponding confidence map are mapped to the three-dimensional geological model according to the spatial coordinate index, and the abnormal detection result is output.

[0030] As a preferred embodiment of the intelligent mining equipment based on an industrial cloud platform described in this invention, the specific steps for establishing a disaster prediction model and conducting a disaster risk assessment are as follows:

[0031] Using the abnormal areas, abnormal intensity, and spatiotemporal evolution characteristics in the anomaly detection results as input feature sources, and combining the geological structural parameters, operational environment parameters, and equipment operation status data in the comprehensive mine status data, a disaster prediction model is constructed by establishing the conditional dependencies between various geological environments and operational status characteristics and the causal chain of disaster triggering under the Bayesian network framework through a multi-source data fusion algorithm.

[0032] The anomaly detection results and comprehensive mine status data are input into the disaster prediction model, and the conditional probability of each disaster type is calculated.

[0033] The conditional probability of each type of disaster is standardized, and based on the standardized conditional probability, the disaster risk of the mining area is divided into low risk, medium risk and high risk levels, and the disaster risk assessment results are output.

[0034] As a preferred embodiment of the intelligent mining equipment based on an industrial cloud platform described in this invention, the specific steps for optimizing the mining strategy using reinforcement learning algorithms to obtain the optimal mining solution are as follows:

[0035] Extract mining operation-related features from historical operation records and combine them with preset rules and strategies and a three-dimensional geological model to obtain a preliminary mining strategy;

[0036] Using disaster risk assessment results and anomaly detection results as input, combined with comprehensive mine status data, the initial mining strategy is simulated and optimized through reinforcement learning algorithms, and the optimal mining scheme is obtained through multiple iterations of training.

[0037] Secondly, the present invention provides a smart mining method based on an industrial cloud platform, including: acquiring comprehensive mine production data and uploading it to the industrial cloud platform; storing, preprocessing, aggregating and performing preliminary analysis on mine geological data, equipment status data and production progress information through the industrial cloud platform to obtain comprehensive mine status data;

[0038] Based on comprehensive mine status data, combined with real-time operation monitoring data and historical operation record data, the industrial cloud platform constructs a three-dimensional geological model through a digital twin algorithm. The cloud platform uses a deep learning-based abnormal behavior detection algorithm to detect abnormal behavior of the ore body structure in the three-dimensional geological model and obtain the abnormal detection results.

[0039] Based on the abnormality detection result and the mine comprehensive state data, the industrial cloud platform establishes a disaster prediction model through a multi-source data fusion algorithm to predict and analyze potential mine disasters and obtain a disaster risk assessment result.

[0040] Based on the historical operation record data, the preset rule strategy and the three-dimensional geological model, an initial mining strategy is generated, and based on the disaster risk assessment result and the abnormality detection result, the industrial cloud platform simulates and optimizes the initial mining strategy by using a reinforcement learning algorithm to obtain an optimal mining strategy.

[0041] In a third aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement any step of the intelligent mine mining method based on the industrial cloud platform according to the second aspect of the present application.

[0042] The present application has the following beneficial effects: by constructing a multi-dimensional space-time feature matrix in the digital twin analysis module and combining deep learning for abnormal behavior detection, high-precision and low-false alarm identification of potential hazards in the three-dimensional geological model is achieved, and the early warning capability of the system is improved; at the same time, by introducing a reinforcement learning algorithm in the intelligent decision optimization module, the abnormality detection result and the disaster risk assessment result are fused to iteratively optimize the mining strategy, and adaptive decision-making that takes into account safety, efficiency and resource utilization in a complex dynamic environment is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0044] Fig. 1 It is a schematic diagram of the intelligent mine mining equipment based on the industrial cloud platform.

[0045] Fig. 2 It is a schematic diagram of the digital twin analysis module.

[0046] Fig. 3 It is a schematic diagram of the intelligent decision optimization module.

[0047] Fig. 4 It is a disaster risk assessment flowchart. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification.

[0049] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced without the specific details set forth in this description. In other instances, well-known methods, procedures, components, and circuits have not been described in detail so as not to unnecessarily obscure aspects of the present application.

[0050] It should also be noted that, as used in the specification, the expression "one embodiment" or "an embodiment” means a specific implementation of the application and does not indicate a single or exclusive embodiment. The implementation of the application in one embodiment does not indicate that the implementation of the application in another embodiment could not be obtained by combining the features of the described embodiment.

[0051] Reference Figs. 1-4 For one embodiment of the present application, the embodiment provides a smart mine mining equipment based on an industrial cloud platform, comprising the following steps:

[0052] The data acquisition and cloud uploading module acquires mine production comprehensive data and performs preprocessing and formatting.

[0053] The mine production comprehensive data includes spatial coordinates, rock layer attributes, equipment operation positions, operation surface deformation, geological change information, drilling survey data, and mining track data.

[0054] Further, according to the type and sampling frequency of the multi-source original data, the mine production comprehensive data is processed for denoising, outlier removal, and time synchronization. Then, the mine production comprehensive data is normalized, unit converted, and encoded and mapped for output according to the preset data standard format and field structure.

[0055] It should be noted that the preset data standard format is determined by analyzing business requirements and determining data exchange rules, formulating data interface protocols, setting database table structures to ensure efficient data storage and query, setting communication message formats to standardize data transmission methods, and setting uniform timestamp precision, numerical format, and unit identification.

[0056] The field structure is a data field arrangement according to the spatial coordinates, rock layer attributes, equipment operation positions, operation surface deformation, geological change information, drilling survey data, and mining track data involved in the mine production process, according to their physical meaning (actual physical properties of data items such as rock layer depth and equipment position) and business relevance (interrelationships between data items such as the relevance of equipment operation position and operation surface deformation).

[0057] The data governance fusion module receives the processed mine production comprehensive data and performs storage, cleaning, aggregation, and preliminary analysis.

[0058] Specific operation:

[0059] The processed mine production comprehensive data is cleaned by missing value filling, duplicate data elimination and noise smoothing, and the processed mine production comprehensive data is grouped and aggregated according to spatial position, equipment type and operation link, and mine operation characteristic parameters are extracted, and the mine operation characteristic parameters are preliminarily analyzed to obtain mine comprehensive state data.

[0060] Further, the processed mine production comprehensive data is sequentially subjected to missing value filling, duplicate data elimination and noise smoothing processing, the K nearest neighbor algorithm is used to fill in the missing values, the repeated records are eliminated by comparing the time stamps, equipment numbers and spatial coordinates, and the moving average filter is used to smooth the vibration signals of the continuous 5 time points; on this basis, the related processed mine production comprehensive data is grouped and aggregated according to spatial position, equipment type and operation link, the mean and standard deviation of each group are calculated to form a structured feature set; the mine operation characteristic parameters are extracted from the structured feature set, the trend slope is calculated through a sliding window, when the slope of the continuous 3 windows is greater than 0.5 and the current value exceeds 2 times the standard deviation of the historical mean, it is determined as abnormal growth, and the mine comprehensive state data is generated combining the analysis results.

[0061] The digital twin analysis module receives the mine comprehensive state data output by the data governance fusion module, constructs a three-dimensional geological model, and detects abnormal behavior through a deep learning algorithm to output an abnormal detection result.

[0062] The digital twin analysis module is composed of a three-dimensional modeling submodule, a feature extraction submodule and an anomaly detection submodule.

[0063] The three-dimensional modeling submodule is used to receive the mine comprehensive state data, and combine real-time monitoring operation data and historical operation records to construct a three-dimensional geological model.

[0064] Specific operation:

[0065] Based on the spatial coordinates, rock layer attributes and equipment operation positions in the mine comprehensive state data, the operation surface deformation and geological change information obtained by real-time monitoring are fused, and the drilling surveying and mining track data in the historical operation records are referred to, and a three-dimensional geological model is generated through spatial interpolation and voxel reconstruction algorithm.

[0066] Further, based on the spatial coordinates, rock stratum attributes and equipment operation positions in the mine comprehensive state data, combined with the operation face deformation and geological change information obtained by real-time monitoring, the deformation data is mapped to the corresponding position according to the time stamp and spatial coordinates, the rock stratum boundary points in the drilling and mapping data and the boundary points in the mining track data are spatially interpolated, the Kriging method is used to generate a continuous rock stratum interface, and then the voxel reconstruction algorithm is used to divide the space into a regular voxel grid, each voxel is assigned with the interpolated rock stratum attribute, density and porosity, and a three-dimensional geological model is generated.

[0067] The feature extraction submodule is configured to perform extraction and standardization processing of multi-dimensional spatio-temporal features on the three-dimensional geological model.

[0068] Specific operations:

[0069] The multi-dimensional feature quantities in the spatial voxels are extracted from the three-dimensional geological model to construct a multi-dimensional spatio-temporal feature matrix.

[0070] Further, the rock stratum attribute, density, porosity, stress state and temperature of each spatial voxel in the three-dimensional geological model are extracted as multi-dimensional feature quantities to form a feature vector of each voxel, and the feature vectors of the same spatial voxel at different time points are arranged in time sequence to construct a multi-dimensional spatio-temporal feature matrix containing the number of voxels, time steps and feature quantities, and the matrix dimension is (number of voxels x time steps x number of features).

[0071] The multi-dimensional spatio-temporal feature matrix is subjected to three-dimensional Gaussian filter smoothing, and an auto-encoding neural network is used to extract a hidden layer representation vector.

[0072] Further, the multi-dimensional spatio-temporal feature matrix is subjected to three-dimensional Gaussian filter smoothing, taking a 3x3x3 neighborhood centered on each voxel, and weighting and averaging each feature value according to the Gaussian kernel weight to reduce local noise, then the smoothed multi-dimensional spatio-temporal feature matrix is input into the auto-encoding neural network, which passes through the input layer (2048 dimensions) - encoding layer (1024 dimensions) - hidden layer (512 dimensions) - decoding layer (1024 dimensions) - output layer (2048 dimensions), calculates the output of each layer through forward propagation, and extracts a 512-dimensional feature vector as a hidden layer representation vector in the hidden layer.

[0073] It should be noted that the training of the auto-encoding neural network uses the smoothed multi-dimensional spatio-temporal feature matrix as input data, for example, the input layer dimension is set to 2048, the encoding layer dimension is set to 1024, the hidden layer dimension is set to 512, the decoding layer dimension is set to 1024, the output layer dimension is set to 2048, the mean square error is used as the loss function, the Adam optimizer is used for parameter update, for example, the learning rate is set to 0.001, the batch size is set to 64, the training rounds are set to 100 rounds, each round traverses all samples to complete forward propagation and back propagation, and the loss function converges until the loss function converges.

[0074] anomaly detection submodule, configured to perform abnormal behavior recognition and analysis based on a deep learning algorithm.

[0075] Specific operations:

[0076] The hidden layer representation vector is subjected to time series decomposition and spatial gradient mapping, time-space change features are extracted through multi-scale convolution, and the response intensity distribution of each spatial node in the time-space domain is calculated.

[0077] Further, the hidden layer representation vector is arranged in time sequence to form a time series, which is separated into a trend component and a detail component through wavelet decomposition, and a gradient vector of feature values between adjacent voxels is calculated based on the voxel space topological relationship and subjected to spatial mapping; the mapping result is input into a three-dimensional convolutional neural network, and multi-scale convolution kernels with sizes of 3x3x3, 5x5x5 and 7x7x7 are used to extract time-space change features in local, regional and global ranges respectively; the multi-scale time-space change features are fused by weighted average fusion and normalized by a Softmax function, to obtain the response intensity distribution of each spatial node in the time dimension and the spatial dimension.

[0078] It should be noted that the training of the three-dimensional convolutional neural network takes the multi-dimensional time-space feature data after spatial gradient mapping as input, the network structure includes 3 three-dimensional convolutional layers (convolution kernel sizes are 3x3x3, 5x5x5 and 7x7x7 respectively, and the number of channels is 32, 64 and 128 respectively), 3 batch normalization layers, 3 ReLU activation function layers and 1 global average pooling layer, the output layer is a 128-dimensional feature vector, a cross-entropy loss function is used, an Adam optimizer is used for parameter update, the example learning rate is set to 0.001, the batch size is 32, and the training rounds are 150 rounds. The loss value is calculated by forward propagation and the convolution kernel weight is updated by back propagation in each round until the loss value converges stably.

[0079] Based on the normalized response intensity distribution and the localized anomaly index, a comprehensive judgment is made through fusion decision function to obtain a comprehensive judgment result.

[0080] Further, the response values of all spatial nodes are subjected to Z-score standardization to generate a standardized response intensity map, eliminating the differences in dimensions or measurement conditions between different nodes, and the standard deviation of the response values in a 3x3x3 neighborhood around each node is calculated as a localized anomaly index to quantify the fluctuation and potential anomaly of the node. The localized anomaly index and the standardized response intensity are combined by weighted combination to form a decision function, the node state is comprehensively evaluated to obtain a comprehensive score value, based on the comprehensive score value and setting a dynamic judgment threshold, the spatial nodes exceeding the dynamic judgment threshold are identified as abnormal nodes, and the spatial coordinates, time stamp and response intensity are recorded to obtain a comprehensive judgment result.

[0081] It should be noted that the dynamic determination threshold is set according to the distribution of the comprehensive score value, and is used to distinguish normal nodes from abnormal nodes.

[0082] According to the statistical analysis results of historical data, such as the distribution characteristics of response intensity and the fluctuation of node state, the value range of the dynamic determination threshold is set to be between 0.75 and 0.85, which is used to distinguish the boundary between severe abnormality and moderate abnormality.

[0083] The comprehensive determination results are classified and processed, and three-dimensional space-time connectivity constraints are applied to remove isolated abnormal points, to generate an abnormal mask and a corresponding confidence map.

[0084] Further, the comprehensive determination results are classified and processed according to the response intensity level, and the nodes with response intensity higher than the dynamic determination threshold are marked as severe abnormality, the nodes between the moderate intensity determination threshold and the dynamic determination threshold are marked as moderate abnormality, and the nodes between the low intensity determination threshold and the moderate intensity determination threshold are marked as mild abnormality; On the basis of classification, three-dimensional space-time connectivity constraints are applied to construct a cubic neighborhood with a spatial dimension of 3x3x3, including the current time step and each of the previous and subsequent time steps, to check whether there is at least one node marked as mild abnormality, moderate abnormality or severe abnormality in the cubic neighborhood, if there is, it is determined that the current node meets the connectivity condition, if not, it is determined as an isolated abnormal point and is removed; Based on the results after removing the isolated points, an abnormal mask is generated, each voxel in the abnormal mask is marked as abnormal or normal state, and a corresponding confidence map is generated according to the weighted output of the standardized response intensity and the localized anomaly index, the value of each voxel in the confidence map reflects the credibility of the abnormality judgment.

[0085] It should be noted that the moderate intensity determination threshold is obtained by statistically analyzing the historical data distribution of the response intensity in the comprehensive determination results, and the 75th percentile value is taken as the set value, and the value range is set to be 0.75 to 0.85 according to the mutation inflection point feature distinguishing moderate abnormality from severe abnormality;

[0086] The low intensity determination threshold is obtained by analyzing the joint probability density of the standardized response intensity and the localized anomaly index, and the value corresponding to the valley between the two peaks of the bimodal distribution is selected as the set value, and the value range is set to be 0.40 to 0.50 according to the statistical separation point of normal state and mild abnormality state;

[0087] The three-dimensional space-time connectivity constraint is obtained based on the physical characteristics of local continuity and diffusion of mine geological anomalies in the process of spatial expansion and time evolution.

[0088] The abnormal mask and the corresponding confidence map are mapped to the three-dimensional geological model according to the spatial coordinate index to output the abnormal detection results.

[0089] Further, each voxel in the anomaly mask is position-matched with the corresponding voxel in the three-dimensional geological model according to the spatial coordinates, realizing accurate mapping of the anomaly state, while the confidence value of each voxel in the corresponding confidence map is associated with the corresponding position of the three-dimensional geological model according to the same spatial coordinate index, and the anomaly label of the anomaly mask and the confidence value of the corresponding confidence map are superimposed for each voxel in the three-dimensional geological model, and the anomaly detection result containing the anomaly region, the anomaly intensity and the spatio-temporal evolution characteristics is output.

[0090] The intelligent decision optimization module is configured to establish a disaster prediction model based on the anomaly detection result and the mine comprehensive state data, perform disaster risk assessment, and optimize the mining strategy by using a reinforcement learning algorithm to obtain an optimal mining scheme, which is fed back to the data acquisition and cloud uploading module through a feedback control link to guide the on-site collection and scheduling.

[0091] The intelligent decision optimization module comprises a disaster prediction and assessment submodule, a strategy generation submodule, and a reinforcement learning optimization submodule.

[0092] The disaster prediction and assessment submodule is configured to perform construction and risk assessment of the disaster prediction model.

[0093] Specific operations:

[0094] The anomaly region, the anomaly intensity, and the spatio-temporal evolution characteristics in the anomaly detection result are taken as input feature sources, combined with the geological structure parameters, the operation environment parameters, and the equipment operation state data in the mine comprehensive state data, and a multi-source data fusion algorithm is used to establish a condition-dependent relationship between each geological environment and operation state feature and a disaster trigger causal chain in a Bayesian network framework to construct a disaster prediction model.

[0095] Further, the abnormal region, abnormal intensity and spatio-temporal evolution characteristics in the anomaly detection result are taken as input feature sources, the spatial range, response intensity peak and time change slope of each abnormal voxel are extracted as key features; combined with the geological structure parameters, operation environment parameters and equipment operation state data in the mine comprehensive state data, the associated variables such as fault distance, rock layer inclination, gas concentration and support pressure are screened, for example, the fault distance is screened: through the geological structure data of the mine, the distance between each operation area of the mine and the known fault is extracted; using the geological survey data, drilling surveying and spatial coordinate information, the shortest distance from each operation area to the fault is calculated, and the operation area with shorter distance is screened out to evaluate its potential earthquake and collapse risk; the rock layer inclination is screened: according to the rock layer attribute data of the mine, the inclination value of the rock layer is extracted; using the geological exploration data and drilling records, the rock layer inclination of different regions is calculated, and those regions with larger inclination are screened out, because larger rock layer inclination may lead to landslide and collapse risk; the gas concentration is screened: through the real-time monitoring data of the mine, the gas concentration information of each operation area is extracted; combined with the gas sensor data, the operation area with higher gas concentration is screened out, especially in the area with larger mining depth or poor ventilation, which helps to evaluate the potential risk of gas explosion; the support pressure is screened: through the equipment monitoring and sensor data, the support pressure data of each operation area is obtained; the operation area with lower or unstable support pressure is screened out as the risk point of support structure failure, especially in deep mining or complex geological conditions.

[0096] The above features are aligned and matched in attribute by a multi-source data fusion algorithm (such as weighted average method, principal component analysis (PCA) and canonical correlation analysis (CCA)), a feature data set under unified spatio-temporal reference is constructed; in the framework of Bayesian network, a node set is defined, including abnormal feature nodes, geological environment feature nodes and disaster state nodes, the joint probability distribution between nodes is statistically calculated based on historical data, the network parameters are learned by maximum likelihood estimation method, the conditional dependence relationship between each geological environment and operation state feature and the disaster triggering causal chain are established, and a disaster prediction model is formed.

[0097] It should be noted that the multi-source data fusion algorithm is a data integration method based on feature alignment and attribute association, which matches the coordinates and aligns the time of the abnormal region, abnormal intensity and spatio-temporal evolution characteristics in the anomaly detection result and the geological structure parameters, operation environment parameters and equipment operation state data in the mine comprehensive state data through unified spatio-temporal reference, integrates redundant information by weighted fusion strategy, and extracts key components in the joint feature space by principal component analysis or canonical correlation analysis to realize the structured fusion of multi-source heterogeneous data.

[0098] The anomaly detection result and the mine comprehensive state data are input into the disaster prediction model, and the conditional probability of occurrence of each disaster type is calculated.

[0099] Further, the abnormal area, abnormal intensity and spatio-temporal evolution characteristics in the abnormality detection result are aligned with the geological structure parameters, operation environment parameters and equipment operation state data in the mine comprehensive state data according to a unified spatio-temporal index, and are input into a disaster prediction model; in the Bayesian network, the abnormal characteristics are taken as evidence nodes, and disaster types such as roof fall, water inrush and gas outburst are taken as hypothesis nodes, and probability inference is performed based on the learned conditional probability table and network structure; the Gibbs sampling algorithm is used to calculate the posterior probability of each disaster type under the current input condition, and the conditional probability values of each disaster state are output.

[0100] The conditional probability value of each disaster state is expressed as:

[0101] ;

[0102] In the formula, is the posterior probability of the i-th disaster type under the observation evidence , and is a dimensionless real number; is the posterior probability of the i-th disaster type under the observation evidence , and is a dimensionless real number; is the current sampling step number, and the value range is , and the unit is [1]; is the total number of iterations of Gibbs sampling, and is a positive integer, and the unit is [1]; is the state variable of the i-th disaster type; is the state value of the disaster variable in the j-th sampling; is an indicator function, which outputs 1 when the state in the j-th sampling is equal to the target state, and otherwise outputs 0, and is a dimensionless quantity. It should be noted that the conditional probability table is obtained by statistical analysis of historical data, calculation of the conditional probability of each node under the given parent node state, and learning using maximum likelihood estimation or Bayesian inference method. The conditional probability of each disaster type is standardized, and according to the standardized conditional probability, the disaster risk of the mine area is divided into low risk, medium risk and high risk levels, and the disaster risk assessment result is output.

[0103] It should be noted that the conditional probability table is obtained by statistical analysis of historical data, calculation of the conditional probability of each node under the given parent node state, and learning using maximum likelihood estimation or Bayesian inference method.

[0104] The conditional probability of each disaster type is standardized, and according to the standardized conditional probability, the disaster risk of the mine area is divided into low risk, medium risk and high risk levels, and the disaster risk assessment result is output.

[0105] ​​Further, the condition probability of each disaster type is Min-Max standardized to map the original condition probability value to the interval [0, 1] to form a standardized condition probability; according to the standardized condition probability, a low-risk determination threshold and a medium-risk determination threshold are set to divide the interval [0, the low-risk determination threshold) into a low-risk level, the interval [the low-risk determination threshold, the medium-risk determination threshold) into a medium-risk level, and the interval [the medium-risk determination threshold, 1] into a high-risk level; the disaster types corresponding to each region of the mine are divided into risk levels to generate a disaster risk assessment result containing spatial position, disaster type, risk level, and standardized probability value.

[0106] It should be noted that the low-risk determination threshold is selected by analyzing the condition probability distribution before the occurrence of historical disasters, and the 30th percentile value is selected as the set value, and the value range is set to 0.25 to 0.35 according to the statistical division characteristics of normal working conditions (for example, the equipment operates within the standard parameter range, and the gas concentration is below the safety threshold) and early abnormal states (for example, the equipment has a slight failure, and the gas concentration has a slight fluctuation).

[0107] The medium-risk determination threshold is selected by analyzing the mutation point of the condition probability in the disaster evolution process, and the 70th percentile of the probability value corresponding to the inflection point of the accelerated development of the disaster in the historical data is selected as the set value, and the value range is set to 0.65 to 0.75 according to the key critical characteristics of the transition from moderate abnormality to severe abnormality.

[0108] The strategy generation submodule is configured to execute generation of an initial mining strategy.

[0109] Specific operations:

[0110] Mining operation related features are extracted from historical operation record data, and a preliminary mining strategy is obtained by combining preset rule strategies and a three-dimensional geological model.

[0111] Further, drilling survey data, mining track data, equipment operation position, and operation link duration and other mining operation related features are extracted from historical operation record data to form a historical operation feature set; rule matching and feasibility evaluation are performed on the feature set in combination with the provisions of the minimum working flat width, the maximum slope angle, the safe mining depth, and the rock stratum avoidance area in the preset rule strategy; the operation mode that meets the rule strategy is spatially aligned with the rock stratum attributes, spatial coordinates, and equipment operation position in the three-dimensional geological model to generate a preliminary mining strategy containing recommended operation areas, operation sequences, and operation parameters.

[0112] It should be noted that the rule strategy is based on the statistical analysis results of high-efficiency and low-risk operation modes in historical operation records, and extracts typical operation parameter ranges and spatial layout features to form a rule set for guiding mining operations.

[0113] a reinforcement learning optimization submodule configured to perform reinforcement learning optimization on the initial mining strategy by using a reinforcement learning algorithm.

[0114] Specific operations:

[0115] The disaster risk assessment result and the anomaly detection result are taken as inputs, combined with the mine comprehensive state data, and the initial mining strategy is simulated and optimized by using a reinforcement learning algorithm. Through multiple iterations of training, an optimal mining scheme is obtained.

[0116] Further, the risk level and the standardized conditional probability in the disaster risk assessment result and the abnormal area and the confidence map in the anomaly detection result are taken as state inputs, combined with the equipment operation state, the operation environment parameters and the geological structure parameters in the mine comprehensive state data, a state space of reinforcement learning is constructed; the operation area, the operation sequence and the operation parameters in the preliminary mining strategy are taken as an initial action set, a reward function aiming to maximize the mining efficiency, minimize the risk exposure and reduce the equipment loss is defined; a deep Q network algorithm is used for simulation training, experience is accumulated through interaction with the environment and the network parameters are updated, and after multiple iterations of optimization, the optimal mining scheme is obtained.

[0117] The embodiment also provides a smart mine mining method based on an industrial cloud platform, comprising: obtaining mine production comprehensive data and uploading the mine production comprehensive data to an industrial cloud platform, storing, preprocessing, data aggregating and preliminarily analyzing mine geological data, equipment state data and production progress information by using the industrial cloud platform to obtain mine comprehensive state data;

[0118] Based on the mine comprehensive state data, combined with real-time operation monitoring data and historical operation record data, the industrial cloud platform constructs a three-dimensional geological model by using a digital twin algorithm, and the cloud platform detects abnormal behaviors of the ore body structure in the three-dimensional geological model by using an abnormal behavior detection algorithm based on deep learning to obtain an anomaly detection result;

[0119] Based on the anomaly detection result and the mine comprehensive state data, the industrial cloud platform establishes a disaster prediction model by using a multi-source data fusion algorithm to predict and analyze potential mine disasters, and obtains a disaster risk assessment result;

[0120] Based on the historical operation record data, the preset rule strategy and the three-dimensional geological model, an initial mining strategy is generated, and based on the disaster risk assessment result and the anomaly detection result, the industrial cloud platform simulates and optimizes the initial mining strategy by using a reinforcement learning algorithm to obtain an optimal mining strategy.

[0121] The embodiment also provides a storage medium on which a computer program is stored, the program being executed by a processor to implement the steps of the method for implementing the smart mine mining method based on the industrial cloud platform as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk.

[0122] To sum up, the present application realizes high-precision and low-false alarm identification of potential hidden dangers in the three-dimensional geological model by constructing a multi-dimensional space-time feature matrix in the digital twin analysis module and combining deep learning for abnormal behavior detection, and improves the early warning capability of the system; at the same time, the reinforcement learning algorithm is introduced in the intelligent decision optimization module, the abnormal detection result and the disaster risk assessment result are fused, and the mining strategy is iteratively optimized for multiple rounds, so as to realize adaptive decision-making considering safety, efficiency and resource utilization rate in a complex dynamic environment.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and all should be covered in the scope of the claims of the present application.

Claims

1. An intelligent mine mining equipment based on an industrial cloud platform, characterized in that: The system comprises a data acquisition and cloud uploading module, a data governance and fusion module, a digital twin analysis module, and an intelligent decision optimization module. The data acquisition and cloud uploading module is configured to acquire mine production comprehensive data, and upload the data to an industrial cloud platform after preprocessing and formatting. The data governance and fusion module is connected to the data acquisition and cloud uploading module through a cloud data channel, and is configured to receive the processed mine production comprehensive data, and store, clean, aggregate, and preliminarily analyze the data. The digital twin analysis module and the data governance and fusion module are connected through a data service bus, and are configured to receive mine comprehensive state data output by the data governance and fusion module, construct a three-dimensional geological model, and perform abnormal behavior detection through a deep learning algorithm to output an abnormal detection result. The three-dimensional geological model is generated based on spatial coordinates, rock layer attributes, and equipment operation positions in the mine comprehensive state data, fused with operation surface deformation and geological change information obtained through real-time monitoring, and referenced with drilling surveying and mining track data in historical operation records. Multi-dimensional feature quantities in spatial voxels are extracted from the three-dimensional geological model to construct a multi-dimensional spatio-temporal feature matrix. The multi-dimensional spatio-temporal feature matrix is subjected to three-dimensional Gaussian filter smoothing, and a hidden layer representation vector is extracted using a self-encoding neural network. The hidden layer representation vector is subjected to time series decomposition and spatial gradient mapping, time-space change features are extracted through multi-scale convolution, and response intensity distribution of each spatial node in the time-space domain is calculated. Based on the normalized response intensity distribution and the localized anomaly index, a comprehensive judgment is made through a fusion decision function to obtain a comprehensive judgment result. The comprehensive judgment result is classified and processed, and isolated abnormal points are removed by applying a three-dimensional spatio-temporal connectivity constraint to generate an abnormal mask and a corresponding confidence map. The abnormal mask and the corresponding confidence map are mapped to the three-dimensional geological model according to the spatial coordinate index to output the abnormal detection result. The intelligent decision optimization module is associated with the digital twin analysis module through an algorithm coordination interface, and is configured to establish a disaster prediction model based on the abnormal detection result and the mine comprehensive state data, perform disaster risk assessment, and optimize mining strategies using a reinforcement learning algorithm to obtain an optimal mining scheme, which is fed back to the data acquisition and cloud uploading module through a feedback control link to guide on-site acquisition and scheduling.

2. The smart mine mining equipment based on the industrial cloud platform according to claim 1, characterized in that: The digital twin analysis module comprises a three-dimensional modeling submodule, a feature extraction submodule, and an abnormal detection submodule. The three-dimensional modeling submodule is configured to receive mine comprehensive state data, and construct a three-dimensional geological model in combination with real-time monitoring operation data and historical operation records. The feature extraction submodule is configured to extract and standardize multi-dimensional spatio-temporal features of the three-dimensional geological model. The abnormal detection submodule is configured to perform abnormal behavior recognition and analysis based on a deep learning algorithm.

3. The smart mine mining equipment based on the industrial cloud platform according to claim 1, characterized in that: The intelligent decision optimization module comprises a disaster prediction and evaluation submodule, a strategy generation submodule, and a reinforcement learning optimization submodule. The disaster prediction and evaluation submodule is configured to construct a disaster prediction model and perform risk assessment. The strategy generation submodule is configured to generate an initial mining strategy. The reinforcement learning optimization submodule is configured to perform reinforcement learning optimization on the initial mining strategy by using a reinforcement learning algorithm.

4. The smart mine mining equipment based on the industrial cloud platform according to claim 1, characterized in that: The processed mine production comprehensive data is obtained by denoising, outlier removal and time synchronization processing of the mine production comprehensive data according to the types and sampling frequencies of the multiple sources of original data, and then normalizing, unit conversion and encoding mapping output of the mine production comprehensive data according to the preset data standard format and field structure.

5. The smart mine mining equipment based on the industrial cloud platform according to claim 1, characterized in that: The mine comprehensive state data is obtained by data cleaning of the processed mine production comprehensive data through missing value filling, repeated data elimination and noise smoothing, and grouping and aggregation of the processed mine production comprehensive data according to spatial position, equipment category and operation link, extraction of mine operation characteristic parameters, and preliminary analysis of the mine operation characteristic parameters.

6. The smart mine mining equipment based on the industrial cloud platform according to claim 1, characterized in that: The disaster prediction model is established, and the disaster risk assessment is performed, and the specific steps are as follows, The conditional dependency relationship between the geological environment and the operation state characteristics and the disaster trigger causal chain are established by a multi-source data fusion algorithm in a Bayesian network framework to construct a disaster prediction model, taking the abnormal area, abnormal intensity and spatio-temporal evolution characteristics in the anomaly detection result as the input characteristic source, and combining the geological structure parameters, operation environment parameters and equipment operation state data in the mine comprehensive state data; The anomaly detection result and the mine comprehensive state data are input into the disaster prediction model, and the conditional probability of occurrence of each disaster type is calculated; The conditional probability of occurrence of each disaster type is standardized, and the disaster risk of the mine area is divided into low risk, medium risk and high risk levels according to the standardized conditional probability, and the disaster risk assessment result is output.

7. The smart mine mining equipment based on the industrial cloud platform according to claim 1, characterized in that: The specific steps of optimizing the mining strategy by using the reinforcement learning algorithm to obtain the optimal mining scheme are as follows, The mining operation related features are extracted from the historical operation record data, and the preliminary mining strategy is obtained by combining the preset rule strategy and the three-dimensional geological model; The disaster risk assessment result and the anomaly detection result are input, combined with the mine comprehensive state data, and the initial mining strategy is simulated and optimized by the reinforcement learning algorithm, and the optimal mining scheme is obtained through multiple iterations.

8. A smart mine mining method based on an industrial cloud platform, based on the smart mine mining equipment based on the industrial cloud platform in any one of claims 1-7, characterized in that: The specific steps of optimizing the mining strategy by using the reinforcement learning algorithm to obtain the optimal mining scheme are as follows, The mine production comprehensive data is obtained and uploaded to the industrial cloud platform, and the mine geological data, equipment state data and production progress information are stored, preprocessed, data aggregated and preliminarily analyzed by the industrial cloud platform to obtain the mine comprehensive state data; Based on the mine comprehensive state data, combined with real-time operation monitoring data and historical operation record data, the industrial cloud platform constructs a three-dimensional geological model by a digital twin algorithm, and the cloud platform uses an abnormal behavior detection algorithm based on deep learning to detect the abnormal behavior of the ore body structure in the three-dimensional geological model to obtain the anomaly detection result; Based on the anomaly detection result and the mine comprehensive state data, the industrial cloud platform establishes a disaster prediction model by a multi-source data fusion algorithm to predict and analyze potential mine disasters and obtain the disaster risk assessment result; The initial mining strategy is generated based on historical operation record data, preset rule strategy and a three-dimensional geological model, and the industrial cloud platform simulates and optimizes the initial mining strategy based on disaster risk assessment results and abnormal detection results by using a reinforcement learning algorithm to obtain an optimal mining strategy.

9. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program, when executed by a processor, implements the steps of the intelligent mine mining method based on the industrial cloud platform according to claim 8.

Images