A coal mine underground navigation control system and device based on big data

Abstract

The present invention discloses a coal mine underground navigation control system and device based on big data, specifically relating to the technical field of underground navigation control; by real-time monitoring of underground radio signals, and using wavelet transform combined with a convolutional neural network to identify signal reflection patterns and judge the level of waveguide effect in underground roadways; at the same time, through multi-scale curvature analysis and DBSCAN clustering algorithm to process the three-dimensional point cloud data of underground roadways, the division of structural mutation regions is realized; according to the waveguide effect level and the structural mutation result, the navigation error level is determined, when the navigation error level reaches the second or third level, the dynamic time warping algorithm is used to analyze the historical navigation trajectory data to evaluate the deviation degree of the current navigation path; through comprehensive analysis by a deep belief network, the reliability of the navigation control system is evaluated, and it is judged whether to trigger a path re-planning instruction, improving the underground navigation accuracy and safety.

Description

Technical Field

[0001] The present invention relates to the technical field of underground navigation control, and more specifically, the present invention relates to a coal mine underground navigation control system and device based on big data. Background Art

[0002] With the increasingly complex underground operation environment of coal mines and the continuous improvement of safety standards, traditional underground navigation systems mostly adopt methods such as inertial navigation and radio ranging. However, in practical applications, due to factors such as roadway bends, metal support, and geological structures, radio signals are often interfered by multipath interference and waveguide effects, resulting in an increase in positioning errors. At the same time, there are structural mutations and local geological anomalies in the underground environment, and traditional single data source methods are difficult to reflect environmental changes in real time, making obvious path planning deviations.

[0003] In order to solve the above problems, a coal mine underground navigation control system and device based on big data are provided. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a coal mine underground navigation control system and device based on big data to solve the problems proposed in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A coal mine underground navigation control system based on big data includes a waveguide effect judgment module, a structural mutation division module, an error level determination module, an offset degree evaluation module, and a reliability evaluation module;

[0007] The waveguide effect judgment module judges the waveguide effect level of the underground roadway by real-time monitoring the propagation characteristics of radio signals in the underground roadway, using wavelet transform combined with a convolutional neural network to identify the radio signal reflection pattern;

[0008] The structural mutation division module performs multi-scale curvature analysis on the three-dimensional point cloud data of the underground roadway and divides the structural mutation area of the underground roadway based on the DBSCAN clustering algorithm;

[0009] The error level determination module determines the navigation error level of the underground roadway based on the waveguide effect level of the underground roadway and the division result of the structural mutation area of the underground roadway;

[0010] When the navigation error level reaches the second or third level, the offset degree evaluation module analyzes the historical navigation trajectory data set through the dynamic time warping algorithm to evaluate the offset degree of the current navigation path;

[0011] The reliability evaluation module inputs the waveguide effect level of the underground roadway, the division result of the structural mutation area of the underground roadway, and the deviation degree of the current navigation path into the deep belief network for comprehensive analysis, evaluates the reliability of the navigation control system, and determines whether to trigger a path re - planning instruction.

[0012] In a preferred embodiment, by real - time monitoring the radio signal propagation characteristics in the underground roadway, using wavelet transform combined with convolutional neural network to identify the radio signal reflection pattern, and determining the waveguide effect level of the current underground roadway, specifically:

[0013] Real - time collect the underground radio signals to obtain amplitude, phase and delay data;

[0014] Pre - process the collected data to reduce noise;

[0015] Use wavelet transform to perform time - frequency decomposition on the radio signals and extract multi - scale features;

[0016] Construct a multi - dimensional tensor and input the decomposition result into the convolutional neural network model;

[0017] Use the convolutional neural network to identify the signal reflection pattern and interference characteristics;

[0018] Judge the waveguide effect level of the underground roadway according to the recognition result.

[0019] In a preferred embodiment, judge the waveguide effect level of the underground roadway according to the recognition result, specifically:

[0020] Judge the waveguide effect level according to the preset threshold included in the decision function:

[0021] When the arithmetic mean of the key feature values is greater than or equal to the preset threshold, it is determined that the waveguide effect level of the underground roadway is a low waveguide effect level;

[0022] When the arithmetic mean of the key feature values is less than the preset threshold, it is determined that the waveguide effect level of the underground roadway is a high waveguide effect level.

[0023] In a preferred embodiment, perform multi - scale curvature analysis on the three - dimensional point cloud data of the underground roadway, and divide the structural mutation area of the underground roadway based on the DBSCAN clustering algorithm, specifically:

[0024] Collect and process the three - dimensional point cloud data;

[0025] Select multiple levels of scales and calculate the local curvature values;

[0026] Extract the super - threshold curvature regions at each scale;

[0027] Construct the multi - scale curvature features into a clustering input vector;

[0028] Calibrate the structural mutation region using the DBSCAN clustering algorithm;

[0029] Output the boundary of the structural mutation region in the underground roadway;

[0030] Conduct risk early warning for the structural mutation region in the underground roadway.

[0031] In a preferred embodiment, conducting risk early warning for the structural mutation region in the underground roadway specifically includes:

[0032] Preset a low-risk threshold and a high-risk threshold, and compare them with the warning index:

[0033] When the warning index is less than or equal to the low-risk threshold, define the structural mutation region in the underground roadway as a low-risk region;

[0034] When the warning index is greater than the low-risk threshold and less than the high-risk threshold, define the structural mutation region in the underground roadway as a medium-risk region;

[0035] When the warning index is greater than or equal to the high-risk threshold, define the structural mutation region in the underground roadway as a high-risk region.

[0036] In a preferred embodiment, based on the waveguide effect level of the underground roadway and the division result of the structural mutation region in the underground roadway, determine the navigation error level of the underground roadway specifically as follows:

[0037] When the waveguide effect level of the underground roadway is a low waveguide effect level and the warning index is less than or equal to the low-risk threshold, determine that the navigation error level of the underground roadway is level one;

[0038] When the waveguide effect level of the underground roadway is a high waveguide effect level, the warning index is greater than the low-risk threshold and less than the high-risk threshold, determine that the navigation error level of the underground roadway is level two;

[0039] When the waveguide effect level of the underground roadway is a high waveguide effect level and the warning index is greater than or equal to the high-risk threshold, determine that the navigation error level of the underground roadway is level three.

[0040] In a preferred embodiment, analyze the historical navigation trajectory data set through the dynamic time warping algorithm to evaluate the deviation degree of the current navigation path specifically as follows:

[0041] Standardize the historical navigation trajectory data set and the real-time navigation trajectory data set;

[0042] Construct a multi-dimensional feature sequence;

[0043] Select the Euclidean distance as the sequence metric criterion;

[0044] Use the dynamic time warping algorithm to perform optimal alignment on the trajectory sequence;

[0045] Calculate the trajectory alignment error and output the dynamic time warping matching score;

[0046] Compare the matching score with the matching score threshold to quantify the deviation degree of the current navigation path.

[0047] In a preferred embodiment, comparing the matching score with the matching score threshold to quantify the deviation degree of the current navigation path is specifically as follows:

[0048] Preset the matching score threshold and compare the dynamic time warping matching score with the preset matching score threshold:

[0049] When the dynamic time warping matching score is greater than or equal to the preset matching score threshold, it indicates that the deviation degree of the current navigation path is high;

[0050] When the dynamic time warping matching score is greater than or equal to the preset matching score threshold, it indicates that the deviation degree of the current navigation path is low.

[0051] In a preferred embodiment, input the waveguide effect level of the underground roadway, the division result of the underground roadway structure mutation area, and the deviation degree of the current navigation path into the deep belief network for comprehensive analysis, evaluate the reliability of the navigation control system, and determine whether to trigger the path re-planning instruction. Specifically:

[0052] Integrate the waveguide effect level of the underground roadway, the division result of the underground roadway structure mutation area, and the dynamic time warping matching score;

[0053] Construct a multi-channel input and send it to the deep belief network for learning;

[0054] Extract multi-source features in the hidden layer and identify potential associations;

[0055] Generate the reliability score of the navigation control system through network weight iteration.

[0056] In a preferred embodiment, determining whether to trigger the path re-planning instruction is specifically as follows:

[0057] Preset the reliability score threshold and compare the reliability score with the reliability score threshold:

[0058] When the reliability score is greater than the reliability score threshold, it indicates that the reliability of the navigation control system is high, and it is determined not to trigger the path re-planning instruction;

[0059] When the reliability score is less than or equal to the reliability score threshold, it indicates that the reliability of the navigation control system is poor, and it is determined to trigger the path re-planning instruction.

[0060] On the other hand, the present invention provides a coal mine underground navigation control device based on big data, comprising:

[0061] One or more processors;

[0062] A storage device for storing one or more programs;

[0063] When the one or more programs are executed by the one or more processors, the one or more processors implement a coal mine underground navigation control system based on big data.

[0064] Technical effects and advantages of the coal mine underground navigation control system and device based on big data of the present invention:

[0065] Through multi-source data fusion and intelligent processing, high-precision positioning and risk warning of the underground navigation control system are realized. By using the waveguide effect of real-time monitoring of underground radio signals and multi-scale curvature analysis of three-dimensional point cloud data, the navigation control system can accurately identify signal interference and structural mutations caused by metal support, roadway bending and geological anomalies in the environment, so as to accurately determine the navigation error level. When the navigation error reaches the second or third level, the dynamic time warping algorithm evaluates the current navigation path deviation in real time, and combines with the deep belief network to comprehensively analyze the waveguide effect level, the result of structural mutation area division and the deviation degree of the current navigation path, generates a reliability score, and then determines whether to trigger the path re-planning instruction. Compared with the traditional single data source method, it greatly improves the adaptability to complex underground environments and the decision-making accuracy, reduces the positioning error and safety risks, provides a reliable technical guarantee and risk prevention and control means for coal mine underground operations, and effectively improves the navigation accuracy and the overall reliability of the navigation control system. Brief Description of the Drawings

[0066] Figure 1 It is a structural schematic diagram of a coal mine underground navigation control system based on big data of the present invention. Detailed Embodiments

[0067] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0068] Embodiment 1:

[0069] Figure 1The present invention provides a mine underground navigation control system based on big data, including a waveguide effect judgment module, a structural mutation division module, an error level determination module, an offset degree evaluation module, and a reliability evaluation module;

[0070] The waveguide effect judgment module judges the waveguide effect level of the underground roadway by real-time monitoring of the radio signal propagation characteristics in the underground roadway, using wavelet transform combined with a convolutional neural network to identify the radio signal reflection pattern;

[0071] The structural mutation division module performs multi-scale curvature analysis on the three-dimensional point cloud data of the underground roadway, and divides the structural mutation area of the underground roadway based on the DBSCAN clustering algorithm;

[0072] The error level determination module determines the navigation error level of the underground roadway based on the waveguide effect level of the underground roadway and the division result of the structural mutation area of the underground roadway;

[0073] When the navigation error level reaches the second or third level, the offset degree evaluation module analyzes the historical navigation trajectory data set through the dynamic time warping algorithm to evaluate the offset degree of the current navigation path;

[0074] The reliability evaluation module inputs the waveguide effect level of the underground roadway, the division result of the structural mutation area of the underground roadway, and the offset degree of the current navigation path into a deep belief network for comprehensive analysis, evaluates the reliability of the navigation control system, and determines whether to trigger a path replanning instruction.

[0075] Specifically, by real-time monitoring of the radio signal propagation characteristics in the underground roadway, using wavelet transform combined with a convolutional neural network to identify the radio signal reflection pattern, and judging the waveguide effect level of the current underground roadway, it includes:

[0076] Real-time collect underground radio signals to obtain amplitude, phase, and time delay data: Deploy multiple fixed radio signal transmitting and receiving devices in the underground roadway, and use these radio signal transmitting and receiving devices to collect radio signals in real time at different measurement points. The radio signal transmitting device periodically transmits electromagnetic waves at a set power and frequency, and the radio signal receiving device captures the radio signals reflected or scattered from structures such as the roadway wall, metal support, and fork. The collected data includes the amplitude, phase information, and propagation time delay of the radio signal. The radio signal can be described by the following formula:

[0077] ; where represents the radio signal value corresponding to the time variable ; represents the time variable; represents the amplitude of the radio signal; represents the frequency of the radio signal; Represents the initial phase of the signal.

[0078] In addition, the time delay value is obtained by measuring the time interval between the transmission and reception of the radio signal, denoted as , representing the time difference experienced by the radio signal from transmission to reception.

[0079] Preprocess the collected data to reduce noise: The original signal data collected often contains environmental noise and redundant information, and needs to be preprocessed to improve the data quality. During the preprocessing, a digital filtering algorithm is used to denoise the original radio signal, usually using a Butterworth low-pass filter. Its expression is: ; where represents the radio signal after filtering; represents the overall function of the digital filtering operation.

[0080] Perform time-frequency decomposition on the signal using wavelet transform to extract multi-scale features: The preprocessed radio signal will be time-frequency decomposed by continuous wavelet transform. The wavelet transform formula is defined as follows:

[0081] ; where represents the wavelet coefficient, representing the local energy of the radio signal at scale and translation ; represents the mother wavelet function, and its complex conjugate is denoted as ; represents the scale parameter, and its value range is determined according to the characteristics of the radio signal. The smaller the scale, the more high-frequency information can be captured. The larger the scale, the more obvious the low-frequency trend is reflected; represents the translation parameter, which controls the position of the wavelet function on the time axis.

[0082] Construct a multi-dimensional tensor and input the decomposition result into a convolutional neural network model: Organize the wavelet coefficients into a multi-dimensional tensor according to time, frequency, and feature channels, denoted as , ; where represents the number of time periods; represents the number of frequency scales, that is, the number of different scale components selected from the wavelet transform; represents the number of feature channels.

[0083] Each element in the tensor represents at the th time period, the th frequency scale, and the The eigenvalue under a feature channel.

[0084] The tensor data structure retains the time-frequency feature information extracted by wavelet decomposition, provides high-dimensional input for the convolutional neural network, and facilitates deep feature extraction and pattern recognition.

[0085] Using a convolutional neural network to identify signal reflection patterns and interference features: A multi-layer convolutional neural network is used to process the constructed multi-dimensional tensor to identify the reflection patterns and interference features in radio signals. The multi-layer convolutional neural network mainly uses convolutional layers, pooling layers, and fully connected layers. Its core convolutional operation can be described as:

[0086] ; where represents the feature map value obtained at position after the convolutional operation; represents the activation function; respectively represent the sizes of the convolutional kernel in the time, frequency, and feature channel directions; represents the weight of the th element in the convolutional kernel; represents the element at the corresponding offset position in the output multi-dimensional tensor ; represents the bias term, which is a constant compensation term in the convolutional operation.

[0087] After being trained with a large amount of labeled data, the convolutional neural network can learn the features corresponding to different reflection and interference patterns, thereby accurately extracting the information on the waveguide effect hidden in radio signals.

[0088] Judging and outputting the waveguide effect level of the underground roadway according to the recognition result: After obtaining the feature map output of the convolutional neural network, the waveguide effect of the current underground roadway is classified and judged according to the output result. The obtained feature map values are screened, aggregated, and statistically processed to obtain key eigenvalues. The decision function is introduced to perform integrated calculation on the key eigenvalues. The expression of the decision function is:

[0089] ; where represents the judged waveguide effect level; represents the arithmetic mean of the selected key eigenvalues, and the calculation formula is . Where represents the th key eigenvalue; represents the total number of key eigenvalues.

[0090] Judging the waveguide effect level according to the preset threshold contained in the decision function:

[0091] When the arithmetic mean of the key feature values is greater than or equal to a preset threshold the waveguide effect level of the underground roadway is determined to be a low waveguide effect level;

[0092] When the arithmetic mean of the key feature values is less than the preset threshold the waveguide effect level of the underground roadway is determined to be a high waveguide effect level.

[0093] Specifically, perform multi-scale curvature analysis on the three-dimensional point cloud data of the underground roadway, and divide the structural mutation area of the underground roadway based on the DBSCAN clustering algorithm, including:

[0094] Collect three-dimensional point cloud data: Collect the three-dimensional point cloud data of the underground roadway through devices such as laser scanning or structured light sensors. Define the entire three-dimensional point cloud data set as:

[0095] ; where represents the collected three-dimensional point cloud data set; represents any single sampling point in the three-dimensional point cloud data set; represents the sampling point 's coordinate information. respectively represent the coordinate values of the sampling point in three orthogonal directions (such as the X-axis, Y-axis, and Z-axis); represents the three-dimensional real number space.

[0096] Select multiple scales and calculate the local curvature value: To reveal the local changes in the geometric shape of the underground roadway, use a multi-scale analysis method to calculate the local curvature of each preprocessed point. For the point at a certain scale, the point set in its local neighborhood is denoted as: ; where represents the neighborhood set centered on the point at the scale and contains all points whose distance from the point does not exceed ; represents any point in the three-dimensional point cloud data set used to form the local neighborhood of the point ; represents the point and the point the Euclidean distance between them; represents the neighborhood radius defined at the current scale .

[0097] In the neighborhood set Inside, by calculating the covariance matrix of the neighborhood and solving its eigenvalues, assume that the three obtained eigenvalues are , and define . Calculate the local curvature value, and its calculation formula is: ; where represents the local curvature value of point at scale ; represents the minimum eigenvalue obtained by calculating the covariance matrix of the neighborhood set of point at scale ; represents the middle eigenvalue obtained by calculating the covariance matrix of the neighborhood set of point at scale ; represents the maximum eigenvalue obtained by calculating the covariance matrix of the neighborhood set of point at scale .

[0098] For multiple scales, define the scale set denoted as , then for each point a series of local curvature values can be obtained (where ), reflecting the local deformation characteristics of point at different scales. represents the total number of selected scales.

[0099] Extract the super-threshold curvature region at each scale: At each scale, compare the calculated local curvature value with a pre-set local curvature threshold, and extract the region where the local curvature value is higher than the local curvature threshold. Define the local curvature threshold as , and its value is calibrated according to experimental data.

[0100] For scale , if point satisfies that the local curvature value is greater than the local curvature threshold , then it is considered that at scale , point has a local geometric mutation phenomenon and is classified into the super-threshold curvature region, denoted as . Among them, represents the set of all points whose local curvature values exceed the local curvature threshold at scale .

[0101] Construct the local curvature values at multiple scales into a clustering input vector: For point Construct a feature vector. Denote this feature vector as ; where represents the multi-scale curvature feature vector of point ; respectively represent the local curvature values calculated for point at different scales .

[0102] Apply the DBSCAN clustering algorithm to calibrate the structural mutation region: Use the multi-scale curvature feature vector of point to perform clustering analysis on the point cloud data. For the multi-scale curvature feature vector of any point , define its neighborhood set as: ; where represents the neighborhood set centered on the multi-scale curvature feature vector of point ; represents the multi-scale curvature feature vector of point compared with the multi-scale curvature feature vector of point ; represents the Euclidean distance between the multi-scale curvature feature vector and the multi-scale curvature feature vector .

[0103] If is satisfied, then define point as a core point; where represents the number of elements in the neighborhood set ; is the distance radius threshold in the DBSCAN clustering algorithm.

[0104] According to the clustering idea of DBSCAN, all core points and their neighborhood points that are mutually density-reachable will be grouped into the same cluster, thereby dividing the region with local structural mutations. For each cluster region obtained by clustering, denote it as , where is the clustering index.

[0105] Output the boundary of the structural mutation region in the underground roadway: For each cluster region , use the convex hull algorithm to calculate the outer boundary of the cluster region. Define ; where represents the boundary set of the cluster region , determined by the convex hull algorithm; represents the convex hull solving function, and its output is the point set that constitutes the smallest convex polygon of the region.

[0106] Conduct risk early warning for the structural mutation region in the underground roadway: The structural mutation region in the underground roadway consists of the cluster regions The regional boundary corresponding to the clustering region is composed of. Define the warning index. For the clustering region each point within calculate its multi-scale average local curvature value , and its calculation formula is: ; where represents the average local curvature value of point at all scales; represents the total number of selected scales.

[0107] The clustering region warning index is defined as the mean value of the average curvature values of all points within the region, that is ; where represents the warning index.

[0108] Specifically, based on the waveguide effect level of the underground roadway and the division result of the underground roadway structure mutation region, determine the underground roadway navigation error level, including:

[0109] Preset a low-risk threshold and a high-risk threshold, and compare them with the warning index:

[0110] When the warning index is less than or equal to the low-risk threshold, define the underground roadway structure mutation region as a low-risk region;

[0111] When the warning index is greater than the low-risk threshold and less than the high-risk threshold, define the underground roadway structure mutation region as a medium-risk region;

[0112] When the warning index is greater than or equal to the high-risk threshold, define the underground roadway structure mutation region as a high-risk region.

[0113] The low-risk threshold and the high-risk threshold are determined by combining the historical data of the underground structure maintenance and the navigation system, as well as the experience of safety experts and industry standards.

[0114] When the waveguide effect level of the underground roadway is the low waveguide effect level and the warning index is less than or equal to the low-risk threshold, determine that the underground roadway navigation error level is level one;

[0115] When the waveguide effect level of the underground roadway is the high waveguide effect level and the warning index is greater than the low-risk threshold and less than the high-risk threshold, determine that the underground roadway navigation error level is level two;

[0116] When the waveguide effect level of the underground roadway is the high waveguide effect level and the warning index is greater than or equal to the high-risk threshold, determine that the underground roadway navigation error level is level three.

[0117] Specifically, the dynamic time warping algorithm is used to analyze the historical navigation trajectory data set to evaluate the deviation degree of the current navigation path, including:

[0118] Normalize the historical navigation trajectory data set and the real-time navigation trajectory data set: Preprocess the historical trajectory data set and the real-time trajectory data set. The historical navigation trajectory data set is denoted as: ; where represents the historical navigation trajectory data set; represents the original data vector of the -th sampling point in the historical navigation trajectory data set; represents the dimension of the original data vector (e.g., including spatial coordinate information); represents the total number of sampling points in the historical navigation trajectory data set.

[0119] Similarly, the real-time navigation trajectory data set is denoted as: ; where represents the real-time navigation trajectory data set; represents the original data vector of the -th sampling point in the real-time navigation trajectory data set; The total number of sampling points in the real-time navigation trajectory data set.

[0120] Perform normalization processing on the historical navigation trajectory data set, define the normalization function , and obtain the normalized vector ; where represents the original data vector after normalization of the -th sampling point in the historical navigation trajectory data set. Similarly, perform normalization processing on the real-time navigation trajectory data set to obtain the normalized vector ; where represents the original data vector after normalization of the -th sampling point in the real-time navigation trajectory data set.

[0121] Construct a multi-dimensional feature sequence: For the -th sampling point in the normalized historical navigation trajectory data set , its timestamp is , and at the same time calculate the velocity vector between adjacent points:

[0122] ; where represents the instantaneous velocity vector at the -th sampling point.

[0123] Construct the historical navigation trajectory feature vector as: ; where Represents the feature vector of the th sampling point in the set of standardized historical navigation trajectory data; the vector dimension is , that is, the original position dimension plus the velocity dimension and a single time quantity.

[0124] Similarly, for the set of standardized real-time navigation trajectory data Construct a feature vector. Define the timestamp of each point in the set of standardized real-time navigation trajectory data as , and calculate the velocity vector: ; where represents the instantaneous velocity vector at the th sampling point.

[0125] Construct the real-time navigation trajectory feature vector as: ; where represents the feature vector of the th sampling point in the set of standardized real-time navigation trajectory data; the vector dimension is , that is, the original position dimension plus the velocity dimension and a single time quantity.

[0126] Select the Euclidean distance as the sequence metric criterion: To quantify the similarity between feature vectors, the Euclidean distance is selected as the metric index. Define the Euclidean distance function between the historical feature vector and the real-time feature vector as: ; where represents the Euclidean distance between the feature vector and the feature vector ; represents the component value of the feature vector at the th dimension; represents the component value of the feature vector at the th dimension; represents the total dimension of the feature vector, which is .

[0127] Apply the dynamic time warping algorithm to perform optimal alignment on the trajectory sequences: The dynamic time warping algorithm is used to calculate the best alignment path of two trajectory sequences on the time axis. Define the constructed historical navigation trajectory feature vector sequence as , and the real-time navigation trajectory feature vector sequence as . Define the cumulative distance matrix (where , ), and its recursive formula is:

[0128] ; where represents the value at the The value at the -th row and the -th column, i.e., the minimum distance accumulated on the alignment path between the -th feature vector in the historical navigation trajectory feature vector sequence and the -th feature vector in the real-time navigation trajectory feature vector sequence; represents the minimum accumulated distance selected from three possible paths; represents the accumulated distance of the adjacent cell above; represents the accumulated distance of the adjacent cell on the left;

[0129] Boundary conditions are usually , and For or is set to infinity to ensure the correctness of recursive calculation.

[0130] Through the recursive formula, the dynamic time warping algorithm can find the alignment path that minimizes the accumulated distance, thereby quantifying the similarity between two trajectory sequences.

[0131] Calculate the trajectory alignment error and output the dynamic time warping matching score: the end point of the cumulative distance matrix represents the total error on the optimal alignment path of the two trajectory sequences. Define the length of the optimal alignment path as , then the dynamic time warping matching score is defined as: ; where represents the dynamic time warping matching score; represents the length of the optimal alignment path; represents the value at the end point of the cumulative matrix.

[0132] Compare the dynamic time warping matching score with the matching score threshold to quantify the deviation degree of the current navigation path:

[0133] Preset the matching score threshold and compare the dynamic time warping matching score with the preset matching score threshold:

[0134] When the dynamic time warping matching score is greater than or equal to the preset matching score threshold, it indicates that the deviation degree of the current navigation path is high, and there is a significant deviation between the current navigation path and the pre-planned or historical reference path;

[0135] When the dynamic time warping matching score is less than the preset matching score threshold, it indicates that the deviation degree of the current navigation path is low, and the current navigation path basically coincides with the pre-planned or historical reference path.

[0136] The preset matching score threshold is a positive real number, which is determined by experimental data and expert experience.

[0137] Specifically, the waveguide effect level of the underground roadway, the division result of the underground roadway structure mutation area, and the deviation degree of the current navigation path are input into the deep belief network for comprehensive analysis to evaluate the reliability of the navigation control system and determine whether to trigger a path re-planning instruction, including:

[0138] Integrate the waveguide effect level of the underground roadway, the division result of the underground roadway structure mutation area, and the dynamic time warping matching score: Integrate the waveguide effect level of the underground roadway (including low waveguide effect and high waveguide effect), the division result of the underground roadway structure mutation area (including low-risk, medium-risk, and high-risk areas), and the dynamic time warping matching score into a comprehensive input vector. Define the comprehensive input vector as: ; where represents the comprehensive input vector; represents the waveguide effect level of the underground roadway, and its value is the numerical value 0 or 1. 0 represents the low waveguide effect level, and 1 represents the high waveguide effect level; represents the division result of the underground roadway structure mutation area, and its value is the integer 1, 2, or 3, corresponding to the low-risk area, medium-risk area, and high-risk area respectively; represents the dynamic time warping matching score.

[0139] Construct a multi-channel input and send it to the deep belief network for learning: Construct the comprehensive input vector into a multi-channel input matrix. Define the constructed multi-channel input matrix as: ; where represents the multi-channel input matrix; represents the transpose symbol.

[0140] The multi-channel input matrix is used as the input layer data of the deep belief network, and the waveguide effect level information of the underground roadway, the division result information of the underground roadway structure mutation area, and the dynamic time warping matching score information are respectively transmitted through different channels.

[0141] Extract multi-source features in the hidden layer and identify potential associations: The deep belief network has a multi-layer structure, and its hidden layer can learn the potential features and association information in the input data. Use the hidden layer to perform a non-linear transformation on the multi-channel input matrix and extract high-level features. Define the output of the hidden layer as: ; where represents the hidden layer output vector, which is an abstract expression of the deep features; represents the hidden layer weight matrix, which is used to perform a linear transformation on the multi-channel input matrix. The size of the matrix is , represents the number of neurons in the hidden layer, denotes the number of input channels, which is equal to 3; denotes the activation function; denotes the bias vector of the hidden layer, with the dimension of .

[0142] Through the calculation of the hidden layer, the deep belief network can comprehensively analyze the internal relationship between the waveguide effect level of the underground roadway, the division result of the structural mutation area of the underground roadway, and the dynamic time warping matching score, and capture the interaction effect between different information in the high-dimensional feature space to form a discriminative deep feature representation.

[0143] Through the iteration of network weights, a reliability score for the navigation control system is generated: Utilizing the multi-layer learning mechanism of the deep belief network, the network weights are continuously adjusted through the backpropagation algorithm to optimize the mapping relationship between the hidden layer and the output layer, thereby generating a reliability score for the navigation control system. The calculation formula for the output layer is defined as: ; where denotes the output of the network layer, that is, the reliability score of the navigation control system; denotes the weight matrix of the output layer; denotes the bias term of the output layer; denotes the output activation function.

[0144] A preset reliability score threshold is set, and the reliability score is compared with the reliability score threshold:

[0145] When the reliability score is greater than the reliability score threshold, it indicates that the reliability of the navigation control system is high, and at this time, it is determined not to trigger the path replanning instruction;

[0146] When the reliability score is less than or equal to the reliability score threshold, it indicates that the reliability of the navigation control system is poor, and at this time, it is determined to trigger the path replanning instruction.

[0147] Embodiment 2:

[0148] The difference between Embodiment 2 and Embodiment 1 of the present invention is that this embodiment introduces a coal mine underground navigation control device based on big data.

[0149] A coal mine underground navigation control device based on big data includes one or more processors; it also includes a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement a coal mine underground navigation control system based on big data.

[0150] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0151] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0152] Those of ordinary skill in the art will realize that the modules and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0153] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0154] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or modules can be in electrical, mechanical, or other forms.

[0155] The module described as a separation component may or may not be physically separated. The component shown as a module may or may not be a physical module. It may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0156] In addition, in each embodiment of this application, each functional module can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0157] If the described function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0158] As described above, this is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claimed rights.

[0159] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A coal mine underground navigation control system based on big data, characterized in that: It includes a waveguide effect judgment module, a structural mutation division module, an error level determination module, an offset degree assessment module and a reliability assessment module; The waveguide effect judgment module monitors the propagation characteristics of radio signals in underground tunnels in real time, uses wavelet transform combined with convolutional neural network to identify the reflection mode of radio signals, and judges the waveguide effect level of underground tunnels; Collect underground radio signals in real time to obtain amplitude, phase and delay data; Preprocess the collected data to reduce noise; Use wavelet transform to decompose radio signals in time and frequency and extract multi-scale features; Construct a multi-dimensional tensor and input the decomposition results into the convolutional neural network model; Use convolutional neural networks to identify signal reflection patterns and interference features; Determine the level of waveguide effect in underground tunnels based on the identification results; The waveguide effect level is determined based on the preset threshold contained in the decision function: When the arithmetic mean of the key characteristic values ​​is greater than or equal to the preset threshold, the waveguide effect level of the underground tunnel is determined to be a low waveguide effect level; When the arithmetic mean of the key characteristic values ​​is less than a preset threshold, the waveguide effect level of the underground tunnel is determined to be a high waveguide effect level; The feature mapping values ​​obtained by the convolutional neural network are screened, aggregated and statistically processed to obtain key feature values; The structural mutation division module performs multi-scale curvature analysis on the three-dimensional point cloud data of the underground tunnel and divides the structural mutation area of ​​the underground tunnel based on the DBSCAN clustering algorithm; The error level determination module determines the navigation error level of the underground tunnel based on the waveguide effect level of the underground tunnel and the division result of the underground tunnel structure mutation area; When the navigation error level reaches level 2 or 3, the deviation degree assessment module analyzes the historical navigation trajectory data set through the dynamic time warping algorithm to assess the deviation degree of the current navigation path; The reliability assessment module inputs the waveguide effect level of the underground tunnel, the division results of the underground tunnel structure mutation area, and the deviation degree of the current navigation path into the deep belief network for comprehensive analysis, evaluates the reliability of the navigation control system, and determines whether to trigger the path replanning instruction.

2. The coal mine underground navigation control system based on big data according to claim 1, characterized in that: Multi-scale curvature analysis is performed on the three-dimensional point cloud data of the underground tunnel, and the underground tunnel structure mutation area is divided based on the DBSCAN clustering algorithm, specifically: Collect 3D point cloud data; Select multiple layers of scales and calculate local curvature values; Extracting super-threshold curvature regions at each scale; Constructing multi-scale curvature features as clustering input vectors; The DBSCAN clustering algorithm was used to identify the structural mutation regions; Output the boundary of the underground tunnel structure mutation area; Provide risk warning for areas with sudden changes in underground tunnel structure.

3. The coal mine underground navigation control system based on big data according to claim 2 is characterized in that: Provide risk warning for areas with sudden structural changes in underground tunnels, specifically: Preset low risk threshold and high risk threshold to compare with the warning index: When the warning index is less than or equal to the low risk threshold, the area with sudden changes in the underground tunnel structure is defined as a low risk area; When the warning index is greater than the low risk threshold and less than the high risk threshold, the area with sudden changes in the underground tunnel structure is defined as a medium risk area; When the warning index is greater than or equal to the high-risk threshold, the area with sudden changes in the underground tunnel structure is defined as a high-risk area; The warning index is defined as the mean of the average curvature values ​​of all points within the cluster area.

4. The coal mine underground navigation control system based on big data according to claim 3 is characterized in that: Based on the waveguide effect level of the underground tunnel and the division results of the underground tunnel structure mutation area, the underground tunnel navigation error level is determined, specifically: When the waveguide effect level of the underground tunnel is a low waveguide effect level, and the warning index is less than or equal to the low risk threshold, the underground tunnel navigation error level is determined to be level one; When the waveguide effect level of the underground tunnel is a high waveguide effect level, and the warning index is greater than the low risk threshold and less than the high risk threshold, the underground tunnel navigation error level is determined to be level 2; When the waveguide effect level of the underground tunnel is a high waveguide effect level and the warning index is greater than or equal to the high risk threshold, the underground tunnel navigation error level is determined to be level three.

5. The coal mine underground navigation control system based on big data according to claim 4, characterized in that: The historical navigation trajectory data set is analyzed through the dynamic time warping algorithm to evaluate the deviation degree of the current navigation path, specifically: Standardized historical navigation trajectory data set and real-time navigation trajectory data set; Construct multi-dimensional feature sequences; Choose Euclidean distance as the sequence metric; Use dynamic time warping algorithm to optimally align trajectory sequences; Calculate the trajectory alignment error and output the dynamic time warping matching score; Compare the matching score with the matching score threshold to quantify the degree of deviation of the current navigation path.

6. The coal mine underground navigation control system based on big data according to claim 5, characterized in that: Compare the matching score with the matching score threshold to quantify the current navigation path deviation degree, specifically: Preset match score threshold, compare the dynamic time warping match score with the preset match score threshold: When the dynamic time warping matching score is greater than or equal to the preset matching score threshold, it indicates that the deviation degree of the current navigation path is high; When the dynamic time warping matching score is greater than or equal to the preset matching score threshold, it indicates that the deviation degree of the current navigation path is low.

7. The coal mine underground navigation control system based on big data according to claim 6, characterized in that: The waveguide effect level of the underground tunnel, the division result of the underground tunnel structure mutation area, and the deviation degree of the current navigation path are input into the deep belief network for comprehensive analysis to evaluate the reliability of the navigation control system and determine whether to trigger the path replanning instruction. Specifically: Integrate the waveguide effect level of the underground tunnel, the results of the underground tunnel structure mutation area division and the dynamic time warping matching score; Construct multi-channel input and feed it into deep belief network learning; Extract multi-source features in the hidden layer and identify potential correlations; Through network weight iteration, a reliability score of the navigation control system is generated.

8. The coal mine underground navigation control system based on big data according to claim 7, characterized in that: Determine whether to trigger the path replanning instruction, specifically: Preset the reliability score threshold and compare the reliability score with the reliability score threshold: When the reliability score is greater than the reliability score threshold, it indicates that the reliability of the navigation control system is high, and it is determined that the path replanning instruction is not triggered; When the reliability score is less than or equal to the reliability score threshold, it indicates that the reliability of the navigation control system is poor, and a path replanning instruction is triggered.

9. A coal mine underground navigation control device based on big data, characterized in that: include: one or more processors; A storage device for storing one or more programs; When one or more programs are executed by one or more processors, the one or more processors implement a coal mine underground navigation control system based on big data as described in any one of claims 1-8.

Images