Geological disaster real-time monitoring and early warning method and system based on big data and environmental feature fusion

Abstract

The invention relates to the technical field of mine potential safety hazard point monitoring, in particular to a geological disaster real-time monitoring and early warning method and system based on big data and environmental feature fusion, and the method comprises the steps: obtaining a real-time monitoring moment, receiving a tunneling vibration signal through employing a preset tunneling collection time period and a tunneling-following collection unit, and transmitting the tunneling vibration signal to a mining-following collection unit; acquiring real-time mine images and a mine monitoring signal set based on the tunneling vibration signal, otherwise, acquiring the real-time mine images and the mine monitoring signal set by using a micro-vibration monitoring unit, summarizing the real-time mine images to obtain a mine image sequence, constructing a potential safety hazard point identification data set based on the mine image sequence, analyzing the potential safety hazard point identification data set, and displaying the potential safety hazard point identification data set. And geological disaster real-time monitoring and early warning based on big data and environmental feature fusion are completed. According to the invention, the environmental characteristics of the tunneled roadway are monitored in real time by using a tunneled signal acquisition technology and a micro-seismic monitoring technology, and hidden danger detection is carried out on the environmental characteristics by using big data, so that real-time monitoring and early warning of potential safety hazards under a mine are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of mine safety hazard point monitoring, and particularly to a real-time monitoring and early warning method and system for geological disasters based on the fusion of big data and environmental characteristics. Background Technique

[0002] During the process of coal mine collection, excavation is usually carried out by a roadheader. Traditional geological disaster monitoring technologies mainly rely on manual inspections and static sensors, and the monitoring data update cycle is long. Existing along-excavation monitoring systems mostly adopt a single signal acquisition mode, such as only monitoring the cutting vibration of the roadheader. Microseismic monitoring technology can also monitor coal mine roadways.

[0003] Although the above methods can achieve real-time monitoring of geological disasters in coal mine roadways, microseismic monitoring technology is only used for stability assessment, and is interfered by the roadheader during excavation. Without the premise of combining with the real-time operation data of the roadheader, it will also be interfered by the noise of the roadheader. Therefore, a method is needed to combine the real-time operation data of the roadheader with microseismic monitoring technology, and use big data to detect potential hazards in environmental characteristics, so as to achieve real-time monitoring and early warning of safety hazards underground in mines. Summary of the Invention

[0004] The present invention provides a real-time monitoring and early warning method for geological disasters based on the fusion of big data and environmental characteristics, and a computer-readable storage medium. Its main purpose is to use the signals collected along with excavation and microseismic monitoring technology to monitor the environmental characteristics of the excavation roadway in real time, and use big data to detect potential hazards in environmental characteristics, so as to achieve real-time monitoring and early warning of safety hazards underground in mines.

[0005] To achieve the above object, a real-time monitoring and early warning method for geological disasters based on the fusion of big data and environmental characteristics provided by the present invention includes: Receiving a real-time mine environmental monitoring instruction, and confirming the coal mine detection environment based on the real-time mine environmental monitoring instruction. The coal mine detection environment includes: a roadheader, an excavation roadway, and a data acquisition unit. The data acquisition unit includes: a collection unit along with excavation and a collection unit during shutdown. The collection unit along with excavation includes a plurality of detectors along with excavation, and the collection unit during shutdown includes a plurality of static mine environmental detectors and a microseismic monitoring unit; Obtaining the real-time monitoring moment. If the real-time monitoring moment is within a preset excavation period, using the preset excavation collection period and the collection unit along with excavation to receive excavation vibration signals, and obtaining a real-time mine image and a mine monitoring signal set based on the excavation vibration signals. The excavation vibration signals come from the vibration of the roadheader; If the real-time monitoring moment is not within the excavation period, using the microseismic monitoring unit to obtain a real-time mine image and a mine monitoring signal set. The mine monitoring signal set is monitored by the microseismic monitoring unit; Summarize the real-time mine images according to the preset monitoring time sequence to obtain a mine image sequence, identify all safety hazard point identifiers in the mine image sequence to obtain a safety hazard point identifier sequence, and construct a data set for identifying safety hazard points based on the mine monitoring signal set, the mine image sequence, and the safety hazard point identifier sequence. Among them, the safety hazard point data includes an identifier hazard evolution graph sequence and an identifier hazard evolution signal sequence; Analyze the data set for identifying safety hazard points. If a safety warning instruction is generated based on the analyzed identifier hazard data set, send the safety warning instruction to the initiating end of the mine real-time environment monitoring instruction. Otherwise, return to the step of obtaining the real-time monitoring moment to complete a real-time monitoring and warning of geological disasters based on the fusion of big data and environmental characteristics.

[0006] Optionally, the obtaining of the real-time mine image and the mine monitoring signal set based on the tunneling vibration signal includes: Use the pre-constructed seismic interference technology to fit the tunneling vibration signal to obtain a virtual blast signal set, perform a low-pass filtering operation on the virtual blast signal set to obtain a noise-reduced signal, use the pre-constructed surface wave imaging method to analyze the noise-reduced signal, and visualize the analyzed noise-reduced signal to obtain a mine hazard detection image corresponding to the real-time monitoring moment; Analyze the mine hazard detection image to obtain a real-time mine image containing safety hazard point identifiers, and confirm the tunneling vibration signal as the mine monitoring signal set.

[0007] Optionally, the obtaining of the real-time mine image and the mine monitoring signal set by using the microseismic monitoring unit includes: Judge whether there is a mine static monitoring moment in the pre-constructed mine static monitoring time sequence that is the same as the real-time monitoring moment; If there is a mine static monitoring moment in the mine static monitoring time sequence that is the same as the real-time monitoring moment, use multiple static mine environment detectors to receive microseismic monitoring signals, analyze the microseismic monitoring signals, and obtain a real-time mine image based on the microseismic monitoring signals, and confirm the microseismic monitoring signals as the mine monitoring signal set.

[0008] Optionally, the judging whether there is a mine static monitoring moment in the pre-constructed mine static monitoring time sequence that is the same as the real-time monitoring moment includes: Based on the real-time monitoring moment, obtain the adjacent historical hidden danger monitoring periods, extract the latest historical hidden danger monitoring moment prior to the real-time monitoring moment from the adjacent historical hidden danger monitoring periods, calculate the hidden danger monitoring frequency control parameter based on the latest historical hidden danger monitoring moment and a pre-constructed calculation formula for the hidden danger monitoring frequency control parameter, obtain the target monitoring moment using the hidden danger monitoring frequency control parameter, and import the target monitoring moment into the pre-constructed initial mine static monitoring time sequence to obtain the mine static monitoring time sequence, where the mine static monitoring time sequence includes multiple mine static monitoring moments; Compare the target monitoring moment with the real-time monitoring moment. If the target monitoring moment lags behind the real-time monitoring moment, confirm that there is no mine static monitoring moment in the mine static monitoring time sequence that is the same as the real-time monitoring moment; otherwise, confirm that there is a mine static monitoring moment in the mine static monitoring time sequence that is the same as the real-time monitoring moment.

[0009] Optionally, the constructing the identified hidden danger point data set based on the mine monitoring signal set, the mine image sequence, and the safety hidden danger point identification sequence includes: Perform a classification operation on the safety hidden danger point identification sequence to obtain a hidden danger classification identification sequence, where the hidden danger classification identification sequence includes multiple hidden danger classification identifications, and each hidden danger classification identification corresponds to one or more classified safety hidden danger point identifications; Successively extract the hidden danger classification identifications from the hidden danger classification identification sequence to obtain the target safety hidden danger points, and perform the following operations on all the target safety hidden danger points: Extract all the mine monitoring signal sets under the monitoring time sequence from the data acquisition unit, and identify the characteristic signals of the target safety hidden danger points in all the mine monitoring signal sets under the monitoring time sequence to obtain an initial hidden danger signal sequence; Successively extract the real-time mine images from the mine image sequence, identify the safety hidden danger image areas corresponding to the target safety hidden danger points from the extracted real-time mine images, and summarize the safety hidden danger image areas to obtain an initial safety hidden danger point evolution graph sequence corresponding to the target safety hidden danger points; Use the one or more classified safety hidden danger point identifications to respectively mark the initial safety hidden danger point evolution graph sequence and the initial hidden danger signal sequence to obtain a marked hidden danger point evolution graph sequence and a marked hidden danger signal sequence, and summarize the marked hidden danger point evolution graph sequence and the marked hidden danger signal sequence to obtain the hidden danger point data; Summarize the hidden danger point data to obtain the identified hidden danger point data set corresponding to the hidden danger classification identification sequence.

[0010] Optionally, when parsing the identified hidden danger point data set, if a safety warning instruction is generated based on the parsed identified hidden danger data set, send the safety warning instruction to the initiating end of the mine real-time environment monitoring instruction; otherwise, return to the step of obtaining the real-time monitoring moment, including: Perform the following operations on all the potential safety hazard point data in the potential safety hazard point dataset: Analyze the potential safety hazard point data to obtain the analysis result of the hazard point; If the analysis result of the hazard point is a preset hazard result, send a safety warning instruction to the initiating end of the real-time mine environmental monitoring instruction; Otherwise, extract the historical hazard point data for a preset historical period from the pre-constructed historical evolution database based on the potential safety hazard point data, integrate the historical hazard point data and the potential safety hazard point data to obtain the historical-real-time hazard point integration data, and analyze the historical-real-time hazard point integration data to obtain the historical-real-time hazard point analysis result; If the historical-real-time hazard point analysis result is a preset historical-real-time hazard result, send a safety warning instruction to the initiating end of the real-time mine environmental monitoring instruction; Otherwise, summarize the analysis results of the hazard points to obtain the comprehensive data corresponding to the potential safety hazard point dataset at the monitoring time sequence. If the comprehensive data is a preset safety warning comprehensive data, send a safety warning instruction to the initiating end of the real-time mine environmental monitoring instruction; If the comprehensive data is not the preset safety warning comprehensive data, extract the historical comprehensive data for a preset historical period from the historical evolution database. If the historical comprehensive data is not the preset historical safety warning comprehensive data, return to the step of obtaining the real-time monitoring moment.

[0011] Optionally, calculating the hazard monitoring frequency control parameter based on the latest historical hazard monitoring moment and the pre-constructed hazard monitoring frequency control parameter calculation formula, and obtaining the target monitoring moment by using the hazard monitoring frequency control parameter includes: Obtain a sequence of adjacent hazard point data based on the adjacent historical hazard monitoring period. Among them, the sequence of adjacent hazard point data includes multiple adjacent hazard point data, and the multiple adjacent hazard point data are sorted in the order of time from the earliest to the latest. Each adjacent hazard point data in the multiple adjacent hazard point data includes: hazard point position characteristics, hazard point displacement characteristics, hazard point deformation characteristics, and hazard point frequency domain characteristics; Extract a target data sequence from the sequence of adjacent hazard point data, and numericalize the target data sequence to obtain a target numerical sequence. Among them, the target data sequence includes multiple target data of the same type, and the type of the target data is one of the hazard point position characteristics, hazard point displacement characteristics, hazard point deformation characteristics, and hazard point frequency domain characteristics; Successively extract target numerical values from the target numerical sequence, and perform the following operations on the extracted target numerical values: Extract the next target value lagging behind the target value from the target value sequence to obtain adjacent values, calculate the difference between the target value and the adjacent values to obtain the first-order difference, and summarize the first-order differences to obtain a first-order difference sequence; Use a preset sliding window and a preset sliding step size to slide and intercept the first-order difference sequence to obtain a sliding difference data sequence, sequentially extract sliding difference data from the sliding difference data sequence, and calculate the variance of the extracted sliding difference data to obtain the data change amount corresponding to the sliding difference data; Summarize the data change amounts to obtain a data change amount sequence; Based on the data change amount sequence and the first-order difference sequence, confirm the first adjustment coefficient and the second adjustment coefficient, and construct a calculation formula for the hidden danger monitoring frequency control parameter according to the first adjustment coefficient and the second adjustment coefficient; Use the calculation formula for the hidden danger monitoring frequency control parameter and the latest historical hidden danger monitoring time to calculate the hidden danger monitoring frequency control parameter; Based on the pre-constructed variable frequency adjustment sequence and the hidden danger monitoring frequency control parameter, obtain the target monitoring time.

[0012] Optionally, the constructing the calculation formula for the hidden danger monitoring frequency control parameter according to the first adjustment coefficient and the second adjustment coefficient includes: Sequentially extract the first-order differences from the first-order difference sequence, and sequentially extract the data change amounts corresponding to the first-order differences from the data change amount sequence, and construct an initial calculation formula for the hidden danger monitoring frequency control parameter based on the extracted first-order differences and the data change amounts corresponding to the first-order differences; Combine all the initial calculation formulas for the hidden danger monitoring frequency control parameter corresponding to the adjacent hidden danger point data sequences to obtain the calculation formula for the hidden danger monitoring frequency control parameter, where the calculation formula for the hidden danger monitoring frequency control parameter is as follows:

[0013] Among them, represents the hidden danger monitoring frequency control parameter, represents the first-order difference, and respectively represent the first adjustment coefficient and the second adjustment coefficient, and and are both constants, represents the data change amount, represents the data change amount function obtained by linearly fitting the sliding difference data, represents the subscript of the initial calculation formula for the hidden danger monitoring frequency control parameter, represents the total number of the initial calculation formulas for the hidden danger monitoring frequency control parameter, represents the initial calculation formula for the hidden danger monitoring frequency control parameter.

[0014] Optionally, obtaining the target monitoring time based on the pre-constructed frequency conversion adjustment sequence and the hidden danger monitoring frequency control parameter includes: Obtain multi-source monitoring data, extract a reference mine roadway set from the multi-source monitoring data, and sequentially extract reference mine roadways from the reference mine roadway set, and perform the following operations on the extracted reference mine roadways: Obtain a reference frequency parameter set corresponding to the reference mine roadway, and calculate a reference regulation factor set corresponding to the reference frequency parameter set based on the hidden danger monitoring frequency control parameter calculation formula, where the reference frequency parameter and the reference regulation factor are in one-to-one correspondence; Construct a mapping relationship between the reference frequency parameter set and the reference regulation factor set to obtain an initial frequency-factor data set, simplify the initial frequency-factor data set to obtain a frequency-factor set, where the frequency-factor set includes multiple frequency-factors, and the frequency-factor includes: a reference frequency parameter and a reference regulation factor; Summarize the frequency-factor set to obtain a frequency-factor set group corresponding to the reference mine roadway set; Perform a clustering operation based on the reference frequency on the frequency-factor set group using the pre-constructed clustering method and the preset number of clustering centers to obtain multiple frequency-factor clusters, where the clustering operation based on the reference frequency is a K-means clustering operation with the reference frequency as a variable, and the number of multiple frequency-factor clusters is equal to the number of clustering centers; Sequentially extract frequency-factor clusters from multiple frequency-factor clusters, identify the clustering frequency interval and the clustering factor interval of the extracted frequency-factor clusters, and calculate the mean value of the clustering frequency interval to obtain a fuzzy reference frequency; Associate the clustering factor interval with the fuzzy reference frequency to obtain a unit frequency conversion adjustment interval, summarize and integrate the unit frequency conversion adjustment interval to obtain a frequency conversion adjustment sequence; Find the unit frequency conversion adjustment interval where the hidden danger monitoring frequency control parameter is located in the frequency conversion adjustment sequence to obtain a target interval, confirm the fuzzy reference frequency corresponding to the target interval as the target frequency, and calculate the target monitoring time based on the target frequency and the latest historical hidden danger monitoring time.

[0015] To achieve the above object, the present invention also provides a geological disaster real-time monitoring and early warning system based on the fusion of big data and environmental characteristics, including: Coal mine detection environment module, used to receive real-time mine environment monitoring instructions, and confirm the coal mine detection environment based on the real-time mine environment monitoring instructions. Among them, the coal mine detection environment includes: roadheader, driving roadway and data acquisition unit. Among them, the data acquisition unit includes: driving-along acquisition unit and shutdown acquisition unit. The driving-along acquisition unit includes a plurality of driving-along detectors, and the shutdown acquisition unit includes a plurality of static mine environment detectors and a microseismic monitoring unit; Driving-along acquisition module, used to obtain the real-time monitoring moment. If the real-time monitoring moment is within the preset driving period, then use the preset driving acquisition period and the driving-along acquisition unit to receive driving vibration signals, and obtain real-time mine images and mine monitoring signal sets based on the driving vibration signals. Among them, the driving vibration signals come from the vibration of the roadheader; Static acquisition module, used to obtain real-time mine images and mine monitoring signal sets using the microseismic monitoring unit if the real-time monitoring moment is not within the driving period. Among them, the mine monitoring signal sets are monitored by the microseismic monitoring unit; Monitoring feedback module, used to summarize the real-time mine images according to the preset monitoring time sequence to obtain a mine image sequence, identify all safety hazard point identifiers in the mine image sequence to obtain a safety hazard point identifier sequence, construct an identified safety hazard point data set based on the mine monitoring signal set, mine image sequence and safety hazard point identifier sequence. Among them, the safety hazard point data includes an identified hazard evolution graph sequence and an identified hazard evolution signal sequence. Analyze the identified safety hazard point data set. If a safety warning instruction is generated based on the analyzed identified hazard data set, then send a safety warning instruction to the initiating end of the real-time mine environment monitoring instruction. Otherwise, return to the step of obtaining the real-time monitoring moment to complete a real-time monitoring and early warning of geological disasters based on the fusion of big data and environmental characteristics.

[0016] To solve the above problems, the present invention also provides an electronic device, which includes: A memory that stores at least one instruction; and a processor that executes the instruction stored in the memory to implement the above-mentioned real-time monitoring and early warning method of geological disasters based on the fusion of big data and environmental characteristics.

[0017] To solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned real-time monitoring and early warning method of geological disasters based on the fusion of big data and environmental characteristics.

[0018] To solve the problems described in the background art, the present invention obtains the real-time monitoring moment. If the real-time monitoring moment is within a preset tunneling period, the preset tunneling acquisition period and the tunneling-accompanying acquisition unit are used to receive the tunneling vibration signal, and based on the tunneling vibration signal, a real-time mine image and a mine monitoring signal set are obtained. Among them, the tunneling vibration signal comes from the vibration of the roadheader. When tunneling, the present invention uses the tunneling-accompanying acquisition unit to detect the geological structure under the rock stratum, and approximately considers that the seismic source is equivalently generated by the roadheader, thereby reducing the dependence on the active seismic source. If the real-time monitoring moment is not within the tunneling period, the microseismic monitoring unit is used to obtain the real-time mine image and the mine monitoring signal set. Among them, the mine monitoring signal set is monitored by the microseismic monitoring unit. When outside the tunneling period, the present invention uses the microseismic monitoring technology to monitor the tunneling roadway to detect the geological structure under the rock stratum and realize the real-time monitoring of the tunneling roadway. The real-time mine images are summarized according to the preset monitoring time sequence to obtain a mine image sequence, and all safety hazard point identifiers in the mine image sequence are identified to obtain a safety hazard point identifier sequence. The present invention classifies the safety hazard point identifiers of the same hazard point in the tunneling roadway, so as to facilitate observing the evolution of the same hazard point. A labeled safety hazard point data set is constructed based on the mine monitoring signal set, the mine image sequence, and the safety hazard point identifier sequence. Among them, the safety hazard point data includes a labeled hazard evolution graph sequence and a labeled hazard evolution signal sequence. In the embodiment of the present invention, the monitoring frequency is adjusted, increasing the monitoring frequency when the collected data has large fluctuations and decreasing the monitoring frequency when the data is relatively stable, so as to accurately monitor the multi-dimensional data of the coal mine roadway on the basis of saving detection energy. The labeled safety hazard point data set is analyzed. If a safety warning instruction is generated based on the analyzed labeled hazard data set, the safety warning instruction is sent to the initiating end of the mine real-time environment monitoring instruction. Otherwise, the step of obtaining the real-time monitoring moment is returned to complete a real-time monitoring and warning of geological disasters based on the fusion of big data and environmental characteristics. On the basis that the analysis result of the hazard point is not the preset hazard result, the present invention combines the historical hazard point data, analyzes the representative hazard points corresponding to the hazard classification identifiers of the safety hazard point data, adopts a data analysis method of gradually increasing the dimension, and also combines the historical comprehensive data to analyze all the representative hazard points corresponding to multiple hazard classification identifiers of the labeled safety hazard point data set, so as to grasp both the data hazard fluctuations point by point and be able to perform data analysis on the environmental characteristics of the current coal mine roadway based on big data and historical data, thereby monitoring the morphological features of the tunneling roadway and providing data support for judging whether a geological disaster has occurred. Therefore, the present invention can use the tunneling-accompanying acquisition signal and the microseismic monitoring technology to monitor the environmental characteristics of the tunneling roadway in real time, and use big data to detect hazards in the environmental characteristics to realize the real-time monitoring and warning of safety hazards in the mine. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 Schematic flowchart of a real-time monitoring and early warning method for geological disasters based on the integration of big data and environmental characteristics provided by an embodiment of the present invention; Figure 2 Functional module diagram of a real-time monitoring and early warning system for geological disasters based on the integration of big data and environmental characteristics provided by an embodiment of the present invention; Figure 3 Schematic structural diagram of an electronic device for implementing the real-time monitoring and early warning method for geological disasters based on the integration of big data and environmental characteristics provided by an embodiment of the present invention.

[0020] Explanation of reference numerals: 1, electronic device; 10, processor; 11, memory; 12, bus.

[0021] The realization, functional characteristics and advantages of the object of the present invention will be further described in conjunction with the embodiments with reference to the drawings. Detailed implementation manners

[0022] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0023] An embodiment of the present application provides a real-time monitoring and early warning method for geological disasters based on the integration of big data and environmental characteristics. The execution subject of the real-time monitoring and early warning method for geological disasters based on the integration of big data and environmental characteristics includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the real-time monitoring and early warning method for geological disasters based on the integration of big data and environmental characteristics can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0024] Refer to Figure 1 As shown, it is a schematic flowchart of a real-time monitoring and early warning method for geological disasters based on the integration of big data and environmental characteristics provided by an embodiment of the present invention. In this embodiment, the real-time monitoring and early warning method for geological disasters based on the integration of big data and environmental characteristics includes: S1. Receive a real-time mine environmental monitoring instruction, and confirm the coal mine detection environment based on the real-time mine environmental monitoring instruction. Among them, the coal mine detection environment includes: a roadheader, a driving roadway, and a data acquisition unit. Among them, the data acquisition unit includes: a driving acquisition unit and a shutdown acquisition unit. The driving acquisition unit includes a plurality of driving geophones, and the shutdown acquisition unit includes a plurality of static mine environmental geophones and a microseismic monitoring unit.

[0025] It is understandable that the real-time mine environment monitoring instruction is an instruction issued by the monitoring personnel in the driving roadway to monitor the environment of the driving roadway. According to the real-time mine environment monitoring instruction, the embodiments of the present invention perform real-time monitoring on the coal mine detection environment. If it is determined according to the monitoring results that there are potential safety hazards in the driving roadway, for example, a displacement exceeding the standard displacement occurs at a certain place inside the rock formation during the driving of the coal mine roadway, or a large amount of debris falls or vibrations that do not meet the artificial specified standards occur at the driving place in the driving roadway, etc., a warning is sent to the initiating end of the real-time mine environment monitoring instruction. Therefore, the present invention is a method for monitoring the safety state of the underground roadway in the mine and can be used in the monitoring device to implement the method described in the present invention.

[0026] Furthermore, the driving-along acquisition unit is a unit that collects data on the driving roadway during the construction of the roadheader. The driving-along geophone is an element used to receive signals emitted with the vibration of the roadheader construction as the seismic source. The shutdown acquisition unit is a unit that collects the geological state of the driving roadway when the roadheader is not under construction. Specifically, the shutdown acquisition unit uses a microseismic monitoring unit to collect the geological state. Specifically, multiple static mine environment geophones are used to receive signals.

[0027] S2. Obtain the real-time monitoring moment.

[0028] It is understandable that the real-time monitoring moment is the current moment.

[0029] S3. If the real-time monitoring moment is within the preset driving period, use the preset driving acquisition period and the driving-along acquisition unit to receive the driving vibration signal, and obtain the real-time mine image and the mine monitoring signal set based on the driving vibration signal, where the driving vibration signal comes from the vibration of the roadheader.

[0030] It should be noted that the driving period is a period set artificially for driving the driving roadway with the roadheader. The driving acquisition period is the period when the driving-along acquisition unit receives the driving vibration signal within the driving period. For example, the work arrangement of the driving roadway is to use the roadheader for excavation from 8:00 to 11:00. During the process from 8:00 to 11:00, the roadheader does not operate throughout the whole process. For example, when it is necessary to change the cutter, perform maintenance, or encounter different rock formations, the roadheader will have a pause of, for example, thirty minutes. The time when the roadheader does not have a pause is the driving acquisition period. The driving-along geophone receives the driving vibration signal with the vibration of the roadheader as the seismic source during the driving acquisition period. The driving vibration signal is the signal received by the driving-along geophone within the driving acquisition period.

[0031] Furthermore, the obtaining of the real-time mine image and the mine monitoring signal set based on the driving vibration signal includes: Use the pre - constructed seismic interferometry technique to fit the tunneling vibration signal to obtain a virtual shot signal set, perform a low - pass filtering operation on the virtual shot signal set to obtain a noise - reduced signal, use the pre - constructed surface wave imaging method to analyze the noise - reduced signal, and visualize the analyzed noise - reduced signal to obtain a mine hidden danger detection image corresponding to the real - time monitoring moment; Analyze the mine hidden danger detection image to obtain a real - time mine image containing safety hazard point marks, and confirm the tunneling vibration signal as the mine monitoring signal set.

[0032] It should be noted that the seismic interferometry technique is an existing technology, and its function is to generate data for imaging the underground geological structure using the tunneling vibration signal. The virtual shot signal set is the signal set generated after cross - correlating the tunneling vibration signals received by multiple tunneling geophones. Equivalently, when the tunneling location is fitted to an artificial excitation source, for example, after the vibration of the roadheader is equivalently generated as an artificial excitation source, the tunneling geophones A, B, C, and D all receive the tunneling vibration signals. Taking the tunneling geophone A as the virtual source and the tunneling geophones B, C, D, etc. as receiving points, 3 virtual shot signals are generated. At this time, one virtual shot signal describes the cross - correlation result of a "virtual source - receiving point". Therefore, with the support of the seismic interferometry technique, in the embodiments of the present invention, the vibration generated by the roadheader during tunneling can be equivalently regarded as a source, thus reducing the dependence on the active source. The low - pass filtering operation is an operation for noise reduction on the virtual shot signal set. Optionally, in the embodiments of the present invention, a Gaussian filter is selected for filtering.

[0033] Specifically, using the seismic scattering wave imaging method to analyze the noise - reduced signal is an existing technology, so the process of obtaining the mine hidden danger detection image corresponding to the real - time monitoring moment will not be elaborated here.

[0034] Exemplarily, assume that the tunneling vibration signal is the signal received with a 10 - s time window and there are 3 tunneling geophones. Then, a virtual shot signal set composed of 6 virtual shot signals can be generated, and the virtual shot signal set is analyzed using the surface wave imaging method (for example, the reverse time migration method in the existing technology). Finally, a mine hidden danger detection image reflecting the underground structure can be generated. Among them, a part of the mine hidden danger detection image corresponding to each virtual shot signal is used for the overall imaging process of the mine hidden danger detection image. Therefore, by superimposing the mine hidden danger detection image sets corresponding to each virtual shot signal, a mine hidden danger detection image reflecting the underground geological structure can be obtained.

[0035] Further, the purpose of parsing the mine hidden danger detection image to obtain a real-time mine image with safety hazard point identifiers is to find parts in the mine hidden danger detection image that are made of materials different from those of conventional tunneling roadways. For example, collapse columns, gangue extrusion zones, etc. It should also be noted that the mine hidden danger detection image in the embodiment of the present invention is the result of one detection. Therefore, when parsing the mine hidden danger detection image, all mine hidden danger detection images prior to the real-time monitoring moment in the tunneling acquisition period can be used as a reference to determine whether a safety hazard has occurred at the real-time monitoring moment.

[0036] Specifically, the safety hazard point identifier refers to an identifier used to identify a hazard point. The information included in the safety hazard point identifier can be artificially specified. For example: region, type, roadway code, roadheader code, predicted spatial position, etc., so as to generate a safety hazard point identifier: [N City - Collapse Column - Roadway N223 - Roadheader No. 1 - (x, y, z)].

[0037] S4. If the real-time monitoring moment is not within the tunneling period, use the microseismic monitoring unit to obtain a real-time mine image and a set of mine monitoring signals, where the set of mine monitoring signals is monitored by the microseismic monitoring unit.

[0038] Further, the using the microseismic monitoring unit to obtain a real-time mine image and a set of mine monitoring signals includes: Determine whether there is a mine static monitoring moment in the pre-constructed mine static monitoring time sequence that is the same as the real-time monitoring moment; If there is a mine static monitoring moment in the mine static monitoring time sequence that is the same as the real-time monitoring moment, use multiple static mine environment detectors to receive microseismic monitoring signals, parse the microseismic monitoring signals, and obtain a real-time mine image based on the microseismic monitoring signals, and confirm the microseismic monitoring signals as the set of mine monitoring signals.

[0039] It should be explained that the microseismic monitoring unit is a unit that uses microvibration monitoring technology to monitor the tunneling roadway during non-tunneling periods. The microseismic monitoring signal is the signal received by the corresponding multiple static mine environment detectors of the microseismic monitoring unit when monitoring the roadway being excavated.

[0040] Further, the determining whether there is a mine static monitoring moment in the pre-constructed mine static monitoring time sequence that is the same as the real-time monitoring moment includes: Based on the real-time monitoring moment, obtain the adjacent historical hidden danger monitoring period. Extract the latest historical hidden danger monitoring moment prior to the real-time monitoring moment from the adjacent historical hidden danger monitoring period. Calculate the hidden danger monitoring frequency control parameter based on the latest historical hidden danger monitoring moment and a pre-constructed calculation formula for the hidden danger monitoring frequency control parameter. Use the hidden danger monitoring frequency control parameter to obtain the target monitoring moment, and import the target monitoring moment into the pre-constructed initial mine static monitoring time sequence to obtain the mine static monitoring time sequence, where the mine static monitoring time sequence includes multiple mine static monitoring moments. Compare the target monitoring moment with the real-time monitoring moment. If the target monitoring moment lags behind the real-time monitoring moment, it is confirmed that there is no mine static monitoring moment in the mine static monitoring time sequence that is the same as the real-time monitoring moment; otherwise, it is confirmed that there is a mine static monitoring moment in the mine static monitoring time sequence that is the same as the real-time monitoring moment.

[0041] It should be noted that the adjacent historical hidden danger monitoring period is a period of time prior to the real-time monitoring moment, and the latest historical hidden danger monitoring moment is the moment of the last monitoring in the adjacent historical hidden danger monitoring period. For example, if the real-time monitoring moment is 8:00, the adjacent historical hidden danger monitoring period is 7:30 - 8:00. During 7:30 - 8:00, 7:30, 7:40, and 7:50 have all been monitored once. Among them, 7:50 is the moment of the last monitoring in terms of time in the adjacent historical hidden danger monitoring period. Therefore, the latest historical hidden danger monitoring moment is 7:50.

[0042] It should be noted that according to the hidden danger monitoring frequency control parameter, the monitoring frequency of the microseismic monitoring unit can be adjusted, so that the moment when the driving roadway needs to be detected next time can be calculated, that is, the target monitoring moment. The initial mine static monitoring time sequence is a sequence composed of all the monitoring moments before the real-time monitoring moment, and is arranged in the order from the earliest to the latest. Therefore, the mine static monitoring time sequence is the sequence obtained by importing the target monitoring moment into the initial mine static monitoring time sequence, and multiple mine static monitoring moments are also arranged in the order from the earliest to the latest. At this time, the target monitoring moment can be compared with the real-time monitoring moment to determine whether there is a mine static monitoring moment in the mine static monitoring time sequence that is the same as the real-time monitoring moment.

[0043] Exemplarily, if the target monitoring moment is 8:20, the real-time monitoring moment is 8:18, and the latest historical hidden danger monitoring moment in the initial mine static monitoring time sequence is 8:10, and the mine static monitoring time sequence includes: [8:10, 8:20], then the target monitoring moment lags behind the real-time monitoring moment, indicating that it is not yet time to use the microseismic monitoring unit for monitoring. Therefore, it is confirmed that there is no mine static monitoring moment in the mine static monitoring time sequence that is the same as the real-time monitoring moment.

[0044] Further, calculating the hidden danger monitoring frequency control parameter based on the latest historical hidden danger monitoring moment and the pre-constructed calculation formula for the hidden danger monitoring frequency control parameter, and obtaining the target monitoring moment by using the hidden danger monitoring frequency control parameter, includes: Obtaining a neighboring hidden danger point data sequence based on the neighboring historical hidden danger monitoring period. Among them, the neighboring hidden danger point data sequence includes multiple neighboring hidden danger point data, and the multiple neighboring hidden danger point data are sorted in the order from the earliest to the latest time. Each neighboring hidden danger point data in the multiple neighboring hidden danger point data includes: the position feature of the hidden danger point, the displacement feature of the hidden danger point, the deformation feature of the hidden danger point, and the frequency domain feature of the hidden danger point; Extracting a target data sequence from the neighboring hidden danger point data sequence, and numericalizing the target data sequence to obtain a target numerical sequence. Among them, the target data sequence includes multiple target data of the same type, and the type of the target data is one of the position feature of the hidden danger point, the displacement feature of the hidden danger point, the deformation feature of the hidden danger point, and the frequency domain feature of the hidden danger point; Successively extracting target numerical values from the target numerical sequence, and performing the following operations on the extracted target numerical values: Extracting the next target numerical value lagging behind the target numerical value from the target numerical sequence to obtain a neighboring numerical value, calculating the difference between the target numerical value and the neighboring numerical value to obtain a first-order difference, summarizing the first-order differences to obtain a first-order difference sequence; Using a preset sliding window and a preset sliding step length to slide and intercept the first-order difference sequence to obtain a sliding difference data sequence, successively extracting sliding difference data from the sliding difference data sequence, and calculating the variance of the extracted sliding difference data to obtain the data change amount corresponding to the sliding difference data; Summarizing the data change amounts to obtain a data change amount sequence; Confirming a first adjustment coefficient and a second adjustment coefficient based on the data change amount sequence and the first-order difference sequence, and constructing a calculation formula for the hidden danger monitoring frequency control parameter according to the first adjustment coefficient and the second adjustment coefficient; Calculating the hidden danger monitoring frequency control parameter by using the calculation formula for the hidden danger monitoring frequency control parameter and the latest historical hidden danger monitoring moment; Obtaining the target monitoring moment based on the pre-constructed frequency conversion adjustment sequence and the hidden danger monitoring frequency control parameter.

[0045] It should be noted that the neighboring hidden danger point data sequence is a sequence composed of data monitored by the data acquisition unit during the neighboring historical hidden danger monitoring period.

[0046] Exemplarily, the location feature of the potential hazard point is represented as a set of location data obtained through monitoring. For example, when using a microseismic monitoring unit for monitoring, if the crack propagation on the inner wall surface of the driving roadway is monitored and the location of the crack propagation on the inner wall surface is recorded, the location feature of the potential hazard point can be obtained. Another example is that the three-dimensional coordinates of a subsided column inside the rock under the geodetic coordinates are collected by the collection unit during tunneling. The displacement feature of the potential hazard point can be the maximum moving distance of the extended edge after the crack propagation on the inner wall surface of the driving roadway. The deformation feature of the potential hazard point can be the crack area after the crack propagation on the inner wall surface of the driving roadway, or the volume of the subsided column, etc. The frequency domain feature of the potential hazard point can be the vibration signal detected by the microseismic monitoring unit. Therefore, through the above examples, it can be understood that the location feature, displacement feature, deformation feature, and frequency domain feature of the potential hazard point are all sets of various data set by humans, unified in the data adjacent to the potential hazard point, aiming to monitor the features such as the topography of the driving roadway, so as to provide data support for judging whether a geological disaster occurs. When selecting the location feature, displacement feature, deformation feature, and frequency domain feature of the potential hazard point, it can be selected according to expert experience, big data, or papers, books, etc. The features included in the data adjacent to the potential hazard point include but are not limited to the location feature, displacement feature, deformation feature, and frequency domain feature exemplified in the embodiments of the present invention.

[0047] Specifically, according to different target data sequences, the numericalization of the target data sequence can be achieved through different existing technologies. For example, if the deformation feature of the potential hazard point is the crack area after the crack propagation on the inner wall surface of the driving roadway when using a microseismic monitoring unit for monitoring, the numerical value of the crack area can be used as the target numerical value to form a target numerical value sequence, so as to simplify the subsequent process of calculating the hazard monitoring frequency control parameter and reduce the calculation energy consumption.

[0048] Further, since each piece of data of adjacent potential hazard points includes the location characteristics, displacement characteristics, deformation characteristics, and frequency domain characteristics of the potential hazard points, and in the embodiment of the present invention when extracting the target data sequence, the purpose is to study the change of a certain characteristic in the data of adjacent potential hazard points. For example, if you want to study the change of the displacement characteristics of the potential hazard points, then all the target data in the target data sequence are sequences composed of the displacement characteristics of the potential hazard points extracted from each piece of data of adjacent potential hazard points in turn. Therefore, the target data sequence includes multiple target data of the same type, and the type of the target data is one of the location characteristics, displacement characteristics, deformation characteristics, and frequency domain characteristics of the potential hazard points. It should also be noted that the same operation is performed on each characteristic in the data of adjacent potential hazard points in the embodiment of the present invention. Since the target data sequence is arranged in the order of time from the earliest to the latest, the numericalized target data sequence, that is, the target numerical sequence, is also arranged in the order of time from the earliest to the latest instant. Exemplarily, if the target numerical sequence is [j, k, l], when the target value is j, the adjacent value is k, and the first-order difference is the target value j minus the adjacent value k, and so on. The expression of the first-order difference sequence is: [j - k, k - l].

[0049] Further, since the sliding window and the sliding step length are prior arts, their specific meanings will not be explained here. The sliding interception is an operation of intercepting values in the first-order difference sequence based on the sliding window according to the sliding step length. For example, assume that the first-order difference sequence at this time is [n, m, o, p], the sliding step length is 1, and the size of the sliding window is 2. Then the sliding difference data sequence obtained by sliding and intercepting the first-order difference sequence is [n, m], [m, o], and [o, p]. At this time, [n, m], [m, o], and [o, p] are all sliding difference data. Therefore, the meaning of the sliding difference data is the data in the sliding difference data sequence, and the data change amount corresponding to the sliding difference data is the variance of all the data in the sliding difference data. The method of calculating the variance is a prior art and will not be elaborated here.

[0050] It should also be noted that the data change amount sequence is a sequence obtained by arranging all the data change amounts in the order of acquisition time from the earliest to the latest. The first adjustment coefficient and the second adjustment coefficient are both correction coefficients in the calculation formula of the potential hazard monitoring frequency control parameter, and there are multiple prior arts to obtain them. For example, they can be obtained through empirical formulas, or through designing orthogonal experiments, using the data in the historical evolution database, and combining the least squares method to fit the correction coefficients. The embodiment of the present invention does not limit this.

[0051] Further, constructing the potential hazard monitoring frequency control parameter calculation formula according to the first adjustment coefficient and the second adjustment coefficient includes: Extract the first-order differences from the first-order difference sequence in turn, and extract the corresponding data change amounts of the first-order differences from the data change amount sequence, and construct an initial hidden danger monitoring frequency control parameter calculation formula based on the extracted first-order differences and the corresponding data change amounts of the first-order differences; Merge all the initial hidden danger monitoring frequency control parameter calculation formulas corresponding to the adjacent hidden danger point data sequences to obtain the hidden danger monitoring frequency control parameter calculation formula, where the hidden danger monitoring frequency control parameter calculation formula is as follows:

[0052] Among them, represents the hidden danger monitoring frequency control parameter, represents the first-order difference, and represent the first adjustment coefficient and the second adjustment coefficient respectively, and and are both constants, represents the data change amount, represents the data change amount function obtained by linearly fitting the sliding difference data, represents the subscript of the initial hidden danger monitoring frequency control parameter calculation formula, represents the total number of the initial hidden danger monitoring frequency control parameter calculation formulas, represents the initial hidden danger monitoring frequency control parameter calculation formula.

[0053] Exemplarily, the first-order difference sequence is [n, m, o, p], the sliding step is 1, and the size of the sliding window is 2. At this time, the sliding difference data sequence is [n, m], [m, o], and [o, p]. Calculate the differences corresponding to the sliding difference data sequence to obtain [n 1 , m 1 , o 1 . At this time, there are multiple existing technologies to complete the data change amount sequence, which is not limited in the embodiments of the present invention. In this example, the first-order difference p is used to complete [n 1 , m 1 , o 1 to obtain the data change amount sequence [n 1 , m 1 , o 1 , p]. Therefore, if the extracted first-order difference is n, the corresponding data change amount in the data change amount sequence can be obtained as n 1 . At this time, the data change amount function is the function obtained by fitting the data of [n, m], and the data change amount function is a linear function, and the slope of the data change amount function is used as the parameter of the initial hidden danger monitoring frequency control parameter calculation formula.

[0054] It is understandable that since each piece of data of the adjacent potential hazard points includes the location characteristics, displacement characteristics, deformation characteristics, and frequency domain characteristics of the potential hazard points, and one target data sequence corresponds to one characteristic, the total number of target data is equal to the number of environmental characteristics (e.g., location characteristics, displacement characteristics, deformation characteristics, and frequency domain characteristics of the potential hazard points) included in the adjacent potential hazard point data. Also, since an initial potential hazard monitoring frequency control parameter calculation formula can be calculated for each target data sequence, the number of initial potential hazard monitoring frequency control parameter calculation formulas is equal to the number of environmental characteristics included in the adjacent potential hazard point data. By combining all the initial potential hazard monitoring frequency control parameter calculation formulas corresponding to the adjacent potential hazard point data sequences, the obtained potential hazard monitoring frequency control parameter calculation formula synthesizes the environmental characteristics of the driving roadway during the adjacent historical potential hazard monitoring period and calculates the target monitoring moment based on the fluctuations of the environmental characteristics (e.g., first-order difference, data change amount, slope of the data change amount function), so as to increase the monitoring frequency when the collected data has large fluctuations and reduce the monitoring frequency when the data is relatively stable, thereby accurately monitoring the multi-dimensional data of the coal mine roadway on the basis of saving detection energy.

[0055] Further, obtaining the target monitoring moment based on the pre-constructed frequency conversion adjustment sequence and the potential hazard monitoring frequency control parameter includes: Obtain multi-source monitoring data, extract a reference mine roadway set from the multi-source monitoring data, and sequentially extract reference mine roadways from the reference mine roadway set, and perform the following operations on each of the extracted reference mine roadways: Obtain a reference frequency parameter set corresponding to the reference mine roadway, and calculate a reference regulation factor set corresponding to the reference frequency parameter set based on the potential hazard monitoring frequency control parameter calculation formula, where the reference frequency parameter and the reference regulation factor are in one-to-one correspondence; Construct a mapping relationship between the reference frequency parameter set and the reference regulation factor set to obtain an initial frequency-factor data set, and simplify the initial frequency-factor data set to obtain a frequency-factor set, where the frequency-factor set includes multiple frequency-factors, and the frequency-factor includes: a reference frequency parameter and a reference regulation factor; Summarize the frequency-factor set to obtain a frequency-factor set group corresponding to the reference mine roadway set; Perform clustering operation based on the reference frequency on the frequency-factor set group by using the pre-constructed clustering method and the preset number of clustering centers to obtain multiple frequency-factor clusters, where the clustering operation based on the reference frequency is a K-means clustering operation with the reference frequency as the variable, and the number of multiple frequency-factor clusters is equal to the number of clustering centers; Extract frequency-factor clusters from multiple frequency-factor clusters in sequence, identify the clustering frequency interval and clustering factor interval of the extracted frequency-factor clusters, calculate the mean of the clustering frequency interval, and obtain the fuzzy reference frequency; Associate the clustering factor interval with the fuzzy reference frequency to obtain a unit frequency conversion adjustment interval, summarize and integrate the unit frequency conversion adjustment intervals to obtain a frequency conversion adjustment sequence; Search for the unit frequency conversion adjustment interval where the hidden danger monitoring frequency control parameter is located in the frequency conversion adjustment sequence to obtain a target interval, confirm the fuzzy reference frequency corresponding to the target interval as the target frequency, and calculate the target monitoring moment based on the target frequency and the latest historical hidden danger monitoring moment.

[0056] It can be understood that the multi-source monitoring data is the data obtained from the monitoring devices in the driving headings in different regions. In the process of extracting the reference mine roadway set from the multi-source monitoring data, experts or technicians can screen out the driving headings that can be used as references for the driving headings in the embodiments of the present invention from the multi-source monitoring data to obtain the reference mine roadway set. It should also be noted that the number of the reference mine roadway set is greater than or equal to two. In the process of screening the reference mine roadways, comprehensive investigations can be carried out from multiple aspects such as geological conditions (such as rock hardness, compressive strength, groundwater conditions, etc.), roadheader parameters (such as cutterhead thrust, torque, rotation speed, etc.), and driving headings in the same mining area or adjacent strata, so as to screen out the reference mine roadways that have reference value for the driving headings in the embodiments of the present invention. The embodiments of the present invention do not limit this.

[0057] Further, the reference frequency parameter set is a set composed of the frequencies monitored by the microseismic monitoring unit in the reference mine roadway and the environmental characteristics in the reference mine roadway at the frequencies of the monitoring, including but not limited to: hidden danger point position characteristics, hidden danger point displacement characteristics, hidden danger point deformation characteristics, hidden danger point frequency domain characteristics, etc. The reference frequency is the frequency monitored by the microseismic monitoring unit in the reference mine roadway. In the reference regulation factor set corresponding to the reference frequency parameter set calculated based on the hidden danger monitoring frequency control parameter calculation formula, a corresponding reference regulation factor can be calculated according to a reference frequency parameter, which is consistent with the method of calculating the hidden danger monitoring frequency control parameter according to the hidden danger monitoring frequency control parameter calculation formula, the latest historical hidden danger monitoring moment, and the pre-constructed hidden danger monitoring frequency control parameter calculation formula in the embodiments of the present invention.

[0058] Further, the method for constructing the mapping relationship between the reference frequency parameter set and the reference regulation factor set to obtain the initial frequency-factor data set is: storing the reference frequency parameter and the corresponding reference regulation factor in the same data, and the data obtained at this time is the initial frequency-factor data.

[0059] Specifically, the present invention sequentially extracts the initial frequency-factor data from the initial frequency-factor dataset, extracts the reference frequency and the reference regulation factor in the initial frequency-factor data, correlates the reference frequency and the reference regulation factor to obtain the frequency-factor, and aggregates the frequency-factors to obtain the frequency-factor set. Since the relationship between the reference frequency parameter and the reference regulation factor was found using the hidden danger monitoring frequency control parameter calculation formula in the foregoing embodiments of the present invention, when analyzing subsequently, the frequency monitored by the microseismic monitoring unit in the reference frequency parameter is used as the reference frequency and stored together with the reference regulation factor, providing data support for confirming the target monitoring time according to the hidden danger monitoring frequency control parameter corresponding to the driving roadway.

[0060] It should be noted that the clustering method is K-means clustering, and the number of clustering centers can be set artificially. For example, the number of clustering centers is 5. The clustering operation based on the reference frequency is a K-means clustering operation with the reference frequency as a variable, and the K-means clustering operation with the reference frequency as a variable is a prior art and will not be elaborated herein.

[0061] Furthermore, a frequency-factor cluster is a cluster obtained after the clustering operation, and a frequency-factor cluster includes multiple frequency-factors. The clustering frequency interval is a continuous one-dimensional interval formed by the maximum reference frequency and the minimum reference frequency in the frequency-factor cluster, and the clustering factor interval is a continuous one-dimensional interval formed by the maximum reference regulation factor and the minimum reference regulation factor in the frequency-factor cluster. Calculating the mean value of the clustering frequency interval is a prior art, and the average value of the maximum reference frequency and the minimum reference frequency can be calculated to obtain the fuzzy reference frequency. The method for correlating the clustering factor interval with the fuzzy reference frequency to obtain the unit frequency conversion adjustment interval is: storing the fuzzy reference frequency and the clustering factor interval in one data, and this data is the unit frequency conversion adjustment interval.

[0062] It should be noted that in the process of summarizing and integrating the unit variable-frequency adjustment intervals to obtain the variable-frequency adjustment sequence, it may occur that directly putting all the clustering factor intervals in the unit variable-frequency adjustment intervals together cannot form a continuous interval. For example, if the first clustering factor interval is [0, a], the second clustering factor interval is [b, c], and a is greater than b, then there is an intersection [b, a] between the first clustering factor interval and the second clustering factor interval. The intersection part is corresponding to a higher-frequency fuzzy reference frequency, that is, the part [a, b] uses the clustering factor interval with a higher frequency between the first clustering factor interval and the second clustering factor interval as the fuzzy reference frequency of [a, b]. For example, if the fuzzy reference frequency corresponding to the second clustering factor interval is greater than the fuzzy reference frequency of the first clustering factor interval, then the fuzzy reference frequency corresponding to the second clustering factor interval is used as the fuzzy reference frequency of the intersection of the first clustering factor interval and the second clustering factor interval.

[0063] Also for example, assume that at this time a is less than b and not equal to b, then there is a reference regulation factor with an interval of [a, b] between the first clustering factor interval and the second clustering factor interval that cannot find a corresponding fuzzy reference frequency. At this time, the higher fuzzy reference frequency among the adjacent two clustering factor intervals is also used to correspond to it. Therefore, it is necessary to summarize and integrate the unit variable-frequency adjustment intervals to obtain the variable-frequency adjustment sequence.

[0064] It can be understood that each reference regulation factor in the reference regulation factor set can find a fuzzy reference frequency in the variable-frequency adjustment sequence, and for the values other than the reference regulation factors in the reference regulation factor set, a fuzzy reference frequency can also be found in the variable-frequency adjustment sequence. Therefore, in the embodiment of the present invention, the driving roadway that can be used as a reference for the driving roadway in the embodiment of the present invention is selected from multi-source monitoring data, and when the monitoring frequency of the known reference mine roadway is known, the reference regulation factor is calculated in reverse using the same hidden danger monitoring frequency control parameter calculation formula, so as to provide a basis for setting the frequency of the microseismic monitoring unit for the driving roadway under construction using the hidden danger monitoring frequency control parameter to calculate the target monitoring moment.

[0065] Furthermore, after knowing the target frequency and the latest historical hidden danger monitoring moment, the specific moment of the target monitoring moment for the next monitoring can be calculated. The specific calculation method is the prior art and will not be elaborated here.

[0066] S5. Summarize the real-time mine images according to the preset monitoring time sequence to obtain a mine image sequence.

[0067] It should be explained that the monitoring time sequence is a sequence sorted in the order from the earliest to the latest time within a preset time period. For example, the preset time period is 24 hours.

[0068] S6. Identify all safety hazard point identifiers in the mine image sequence to obtain a safety hazard point identifier sequence, and construct an identified safety hazard point dataset based on the mine monitoring signal set, the mine image sequence, and the safety hazard point identifier sequence. Among them, the safety hazard point data includes an identified hazard evolution graph sequence and an identified hazard evolution signal sequence.

[0069] Further, the construction of the identified safety hazard point dataset based on the mine monitoring signal set, the mine image sequence, and the safety hazard point identifier sequence includes: Perform a classification operation on the safety hazard point identifier sequence to obtain a hazard classification identifier sequence. Among them, the hazard classification identifier sequence includes multiple hazard classification identifiers, and each hazard classification identifier corresponds to one or more classified safety hazard point identifiers; Extract hazard classification identifiers from the hazard classification identifier sequence in turn to obtain target safety hazard points, and perform the following operations on all target safety hazard points: Extract all mine monitoring signal sets at the monitoring time sequence from the data acquisition unit, and identify the characteristic signals of the target safety hazard points in all mine monitoring signal sets at the monitoring time sequence to obtain an initial hazard signal sequence; Extract real-time mine images from the mine image sequence in turn, identify the safety hazard image area corresponding to the target safety hazard points from the extracted real-time mine images, and summarize the safety hazard image areas to obtain an initial safety hazard point evolution graph sequence corresponding to the target safety hazard points; Use the one or more classified safety hazard point identifiers to mark the initial safety hazard point evolution graph sequence and the initial hazard signal sequence respectively to obtain an identified hazard point evolution graph sequence and an identified hazard signal sequence, summarize the identified hazard point evolution graph sequence and the identified hazard signal sequence to obtain safety hazard point data; Summarize the safety hazard point data to obtain an identified safety hazard point dataset corresponding to the hazard classification identifier sequence.

[0070] It should be noted that in a real-time mine image, there can be one, zero, or multiple safety hazard point identifiers. However, for a certain hazard point, if there is one safety hazard point identifier in a real-time mine image, there will also be corresponding safety hazard point identifiers in one or more other real-time mine images in the mine image sequence. Therefore, it is necessary to classify the safety hazard point identifiers of the same hazard point in the driving roadway to facilitate observing the evolution of the same hazard point. Therefore, the invention embodiment performs a classification operation on the safety hazard point identifier sequence to obtain a hazard classification identifier sequence. Then, the hazard classification identifier represents the total identifier of the same hazard point, and the one or more classified safety hazard point identifiers corresponding to a hazard classification identifier represent the identifiers of all hazard points of the same hazard point in the mine image sequence.

[0071] Exemplarily, there is a hidden danger point, which is a karst collapse column, and its identification in a real-time mine image is D 1 , then in other real-time mine images in the mine image sequence, the karst collapse column will also appear. If the safety hazard points are respectively identified as D 2 、D 3 、D 24 , then in the classification operation of the safety hazard point identification sequence, D 1 、D 2 、D 3 、D 24 will be stored in a hazard classification identification. D 1 、D 2 、D 3 、D 24 are all the classified safety hazard point identifications. When subsequently identifying the characteristic signals of the target safety hazard point in all mine monitoring signal sets under the monitoring time sequence, the identified ones are the characteristic signals corresponding to D 1 、D 2 、D 3 、D 24 . The characteristic signals are the signals collected by the in-driving acquisition unit and the shutdown acquisition unit in the signal acquisition unit under the monitoring time sequence, which are used to characterize the karst collapse column corresponding to the hazard classification identification. The characteristic signals are arranged according to the monitoring time sequence to obtain an initial hazard signal sequence.

[0072] It should be noted that the safety hazard image area is the image area in the real-time mine image used to characterize the target safety hazard point. For example, if the target safety hazard point is a karst collapse column, the safety hazard image area is the image corresponding to the area of the karst collapse column in the real-time mine image, which can be achieved by intercepting the real-time mine image.

[0073] Further, the initial safety hazard point evolution diagram sequence is a sequence obtained by arranging safety hazard image regions according to the monitoring time sequence. It can be learned from the previous text of this example that the essence of the hazard classification identifier is extracted from real-time mine images, and the safety hazard image region is also extracted from real-time mine images. Therefore, it is easy to find which real-time mine image the classified safety hazard point identifier corresponds to in the detection image sequence, and then the safety hazard image region corresponding to the classified safety hazard point identifier in the real-time mine image can be found according to the real-time mine image corresponding to the classified safety hazard point identifier. At this time, using the classified hazard identifier point as text and marking it in the safety hazard image region can mark the initial safety hazard point evolution diagram sequence with the one or more classified safety hazard point identifiers to obtain the marked hazard point evolution diagram sequence. Similarly, the initial hazard signal sequence is identified according to the mine monitoring signal set. In the previous example of this text, it is a mine image sequence constructed according to the microseismic monitoring signal or the tunneling vibration signal in the mine monitoring signal set. Therefore, similar to using the multiple classified safety hazard point identifiers to mark the initial safety hazard point evolution diagram sequence, the one or more classified safety hazard point identifiers can also be used to mark the initial hazard signal sequence to obtain the marked hazard signal sequence. The implementation process only needs to find the corresponding relationship between the multiple classified hazard points and the initial hazard signal sequence, so it will not be elaborated here.

[0074] S7. Analyze the marked safety hazard point data set. If a safety warning instruction is generated based on the analyzed marked hazard data set, send the safety warning instruction to the initiator of the mine real-time environment monitoring instruction; otherwise, return to the step of obtaining the real-time monitoring moment to complete a real-time monitoring and warning of geological disasters based on the fusion of big data and environmental characteristics.

[0075] Further, the step of analyzing the marked safety hazard point data set, if a safety warning instruction is generated based on the analyzed marked hazard data set, send the safety warning instruction to the initiator of the mine real-time environment monitoring instruction; otherwise, return to the step of obtaining the real-time monitoring moment, includes: Perform the following operations on all the safety hazard point data in the marked safety hazard point data set: Analyze the safety hazard point data to obtain a hazard point analysis result; If the hazard point analysis result is a preset hazard result, send a safety warning instruction to the initiator of the mine real-time environment monitoring instruction; Otherwise, extract the historical hazard point data of a preset historical period from the pre-constructed historical evolution database based on the safety hazard point data, integrate the historical hazard point data and the safety hazard point data to obtain historical-real-time hazard point integration data, and analyze the historical-real-time hazard point integration data to obtain a historical-real-time hazard point analysis result; If the historical-real-time hidden danger point analysis result is the preset historical-real-time hidden danger result, a safety warning instruction is sent to the initiating end of the mine real-time environment monitoring instruction; Otherwise, summarize the hidden danger point analysis results to obtain the comprehensive data corresponding to the dataset identifying the safety hidden danger points at the monitoring time sequence. If the comprehensive data is the preset safety warning comprehensive data, a safety warning instruction is sent to the initiating end of the mine real-time environment monitoring instruction; If the comprehensive data is not the preset safety warning comprehensive data, extract the historical comprehensive data of the preset historical period from the historical evolution database. If the historical comprehensive data is not the preset historical safety warning comprehensive data, return to the step of obtaining the real-time monitoring moment.

[0076] It should be noted that the hidden danger point analysis result is the result after analyzing the safety hidden danger point data, and can be stored in the forms of charts, videos, texts, etc. The content and display form of the hidden danger point analysis result are arranged according to the needs of the monitoring personnel. For example, if the safety hidden danger point data is the initial safety hidden danger point evolution diagram sequence and the initial hidden danger signal sequence of a certain subsidence column, the analysis can be to fit the initial safety hidden danger point evolution diagram sequence into an evolution video using existing technologies, and the data features in the initial safety hidden danger point evolution diagram sequence (such as the position feature of the hidden danger point, the displacement feature of the hidden danger point, the deformation feature of the hidden danger point, and the frequency domain feature of the hidden danger point, etc.) can be constructed into a two-dimensional fluctuation curve, etc., and no more examples will be given here. The hidden danger result is the result that there may be hidden dangers in the artificially set hidden danger point analysis result. For example, when there is an area of a certain crack in the safety hidden danger point data, if the change value of the area of the certain crack exceeds a change value threshold set artificially, the hidden danger point analysis result can be confirmed as the hidden danger result. Therefore, the specific setting methods and standards of the hidden danger result can be determined in various ways according to expert opinions, empirical formulas, etc.

[0077] Further, the safety warning instruction is an instruction for warning the initiating end of the real-time mine environment monitoring instruction, including the hidden danger analysis result and the data with hidden dangers in the hidden danger analysis result. The historical evolution database is a database composed of the previous monitoring results of the current driving roadway. The historical time period is a manually set time period, which is used to limit the time range for extracting historical hidden danger point data from the historical evolution database. The historical hidden danger point data is the set of all data of the same hidden danger point corresponding to the hidden danger classification identifier of the safety hidden danger point data in the historical evolution database under the historical time period. The integration of the historical hidden danger point data and the safety hidden danger point data is as follows: The historical hidden danger point data is spliced together in the order of time occurrence according to the composition method of the safety hidden danger point data (the composition of the safety hidden danger point data includes: the initial safety hidden danger point evolution graph sequence and the initial hidden danger signal sequence). Therefore, the historical-real-time hidden danger point integration data is the data obtained after integrating the historical hidden danger point data and the safety hidden danger point data. Further, the process of analyzing the historical-real-time hidden danger point integration data to obtain the historical-real-time hidden danger point analysis result is similar to the process of analyzing the safety hidden danger point data to obtain the hidden danger point analysis result, and can achieve the same effect. Based on the fact that the hidden danger point analysis result is not the preset hidden danger result, the historical hidden danger point data is combined to analyze the representative hidden danger points corresponding to the hidden danger classification identifiers of the safety hidden danger point data.

[0078] It can be understood that if the historical-real-time hidden danger point analysis result is not the preset historical-real-time hidden danger result, it means that even if the historical hidden danger point data is combined and only the representative hidden danger points corresponding to the hidden danger classification identifiers of the safety hidden danger point data are analyzed, there are no hidden dangers. Therefore, in the embodiment of the present invention, the hidden danger point analysis results of the data set of safety hidden danger points marked in the monitoring time sequence are summarized to obtain comprehensive data, and it is judged whether the comprehensive data is safety warning comprehensive data. The safety warning comprehensive data is similar to the hidden danger result and is used to represent that there are hidden dangers in the comprehensive data.

[0079] Further, when the comprehensive data is not the preset safety warning comprehensive data, historical comprehensive data of a preset historical time period is extracted from the historical evolution database, and the historical comprehensive data is combined to analyze all the representative hidden danger points corresponding to multiple hidden danger classification identifiers of the data set marked with safety hidden danger points. Therefore, the historical comprehensive data is similar to the historical hidden danger point data and can achieve the same effect, which will not be elaborated here.

[0080] To solve the problems described in the background art, the present invention obtains the real-time monitoring moment. If the real-time monitoring moment is within the preset tunneling period, the preset tunneling acquisition period and the tunneling-accompanying acquisition unit are used to receive the tunneling vibration signal, and based on the tunneling vibration signal, a real-time mine image and a mine monitoring signal set are obtained. Among them, the tunneling vibration signal comes from the vibration of the roadheader. When tunneling, the present invention uses the tunneling-accompanying acquisition unit to detect the geological structure under the rock stratum, and approximately considers that the seismic source is equivalently generated by the roadheader, thereby reducing the dependence on the active seismic source. If the real-time monitoring moment is not within the tunneling period, the microseismic monitoring unit is used to obtain the real-time mine image and the mine monitoring signal set. Among them, the mine monitoring signal set is monitored by the microseismic monitoring unit. When outside the tunneling period, the present invention uses the microseismic monitoring technology to monitor the tunneling roadway to detect the geological structure under the rock stratum and realize the real-time monitoring of the tunneling roadway. The real-time mine images are summarized according to the preset monitoring time sequence to obtain a mine image sequence, and all safety hazard point identifiers in the mine image sequence are identified to obtain a safety hazard point identifier sequence. The present invention classifies the safety hazard point identifiers of the same hazard point in the tunneling roadway, so as to facilitate observing the evolution of the same hazard point. Based on the mine monitoring signal set, the mine image sequence and the safety hazard point identifier sequence, a labeled safety hazard point data set is constructed. Among them, the safety hazard point data includes a labeled hazard evolution graph sequence and a labeled hazard evolution signal sequence. In the embodiment of the present invention, the monitoring frequency is adjusted, increasing the monitoring frequency when the collected data has large fluctuations and reducing the monitoring frequency when the data is relatively stable, so as to accurately monitor the multi-dimensional data of the coal mine roadway on the basis of saving detection energy. The labeled safety hazard point data set is analyzed. If a safety warning instruction is generated based on the analyzed labeled hazard data set, the safety warning instruction is sent to the initiating end of the mine real-time environment monitoring instruction. Otherwise, the step of obtaining the real-time monitoring moment is returned to complete a real-time monitoring and warning of geological disasters based on the fusion of big data and environmental characteristics. On the basis that the parsing result of the hazard point is not the preset hazard result, the present invention combines the historical hazard point data, analyzes the representative hazard points corresponding to the hazard classification identifiers of the safety hazard point data, adopts a data analysis method of gradually increasing the dimension, and also combines the historical comprehensive data to analyze all the representative hazard points corresponding to multiple hazard classification identifiers of the labeled safety hazard point data set, so as to not only grasp the data hazard fluctuations point by point, but also be able to perform data analysis on the environmental characteristics of the current coal mine roadway based on big data and historical data, thereby monitoring the morphological features of the tunneling roadway and providing data support for judging whether a geological disaster occurs. Therefore, the present invention can use the tunneling-accompanying acquisition signal and the microseismic monitoring technology to monitor the environmental characteristics of the tunneling roadway in real time, and use big data to detect hazards in the environmental characteristics to realize the real-time monitoring and warning of safety hazards in the mine.

[0081] Such as Figure 2As shown, it is a functional module diagram of a real-time monitoring and early warning system for geological disasters based on the integration of big data and environmental characteristics provided by an embodiment of the present invention.

[0082] The real-time monitoring and early warning system 100 for geological disasters based on the integration of big data and environmental characteristics described in the present invention can be installed in an electronic device. According to the functions achieved, the real-time monitoring and early warning system 100 for geological disasters based on the integration of big data and environmental characteristics can include a coal mine detection environment module 101, a mining-with-driving acquisition module 102, a static acquisition module 103, and a monitoring feedback module 104. The modules described in the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0083] The coal mine detection environment module 101 is used to receive real-time mine environment monitoring instructions and confirm the coal mine detection environment based on the real-time mine environment monitoring instructions. Among them, the coal mine detection environment includes: a roadheader, a driving roadway, and a data acquisition unit. Among them, the data acquisition unit includes: a mining-with-driving acquisition unit and a shutdown acquisition unit. The mining-with-driving acquisition unit includes a plurality of mining-with-driving detectors, and the shutdown acquisition unit includes a plurality of static mine environment detectors and a microseismic monitoring unit; The mining-with-driving acquisition module 102 is used to obtain the real-time monitoring time. If the real-time monitoring time is within a preset driving period, then use the preset driving acquisition period and the mining-with-driving acquisition unit to receive the driving vibration signal, and obtain the real-time mine image and the mine monitoring signal set based on the driving vibration signal. Among them, the driving vibration signal comes from the vibration of the roadheader; The static acquisition module 103 is used to obtain the real-time mine image and the mine monitoring signal set by using the microseismic monitoring unit if the real-time monitoring time is not within the driving period. Among them, the mine monitoring signal set is monitored by the microseismic monitoring unit; The monitoring feedback module 104 is used to summarize the real-time mine images according to a preset monitoring time sequence to obtain a mine image sequence, identify all safety hazard point identifiers in the mine image sequence to obtain a safety hazard point identifier sequence, construct an identified safety hazard point data set based on the mine monitoring signal set, the mine image sequence, and the safety hazard point identifier sequence. Among them, the safety hazard point data includes an identified hazard evolution graph sequence and an identified hazard evolution signal sequence. Analyze the identified safety hazard point data set. If a safety early warning instruction is generated based on the analyzed identified hazard data set, then send a safety early warning instruction to the initiating end of the real-time mine environment monitoring instruction. Otherwise, return to the step of obtaining the real-time monitoring time to complete a real-time monitoring and early warning of geological disasters based on the integration of big data and environmental characteristics.

[0084] Specifically, when the modules in the real-time monitoring and early warning system 100 for geological disasters based on the fusion of big data and environmental characteristics in the embodiments of the present invention are used, they adopt the same technical means as those in the Figure 1 real-time monitoring and early warning method for geological disasters based on the fusion of big data and environmental characteristics described above, and can produce the same technical effects, which will not be elaborated here.

[0085] As Figure 3 shown, it is a schematic structural diagram of an electronic device for implementing the real-time monitoring and early warning method for geological disasters based on the fusion of big data and environmental characteristics provided by an embodiment of the present invention.

[0086] The electronic device 1 may include a processor 10, a memory 11, and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a program for the real-time monitoring and early warning method for geological disasters based on the fusion of big data and environmental characteristics.

[0087] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as the mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 1. Further, the memory 11 also includes the internal storage unit of the electronic device 1 and the external storage device. The memory 11 can not only be used to store application software installed on the electronic device 1 and various types of data, such as the code of the program for the real-time monitoring and early warning method for geological disasters based on the fusion of big data and environmental characteristics, but also be used to temporarily store data that has been output or will be output.

[0088] In some embodiments, the processor 10 may be composed of an integrated circuit. For example, it may be composed of a single packaged integrated circuit, or may be composed of multiple packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is the control core (Control Unit) of the electronic device, connecting various components of the entire electronic device through various interfaces and lines, and by running or executing programs or modules stored in the memory 11 (such as the program for real-time monitoring and early warning method of geological disasters based on the fusion of big data and environmental characteristics), and by calling the data stored in the memory 11, to execute various functions of the electronic device 1 and process data.

[0089] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is set to enable connection and communication between the memory 11 and at least one processor 10, etc.

[0090] Figure 3 Only the electronic device with components is shown. Those skilled in the art can understand that Figure 3 the shown structure does not constitute a limitation on the electronic device 1, and it may include fewer or more components than shown, or combine certain components, or have a different component arrangement.

[0091] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component. Preferably, the power source can be logically connected to the at least one processor 10 through a power management system, so as to implement functions such as charge management, discharge management, and power consumption management through the power management system. The power source may also include any components such as one or more DC or AC power sources, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may also include various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0092] Furthermore, the electronic device 1 may further include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the electronic device 1 and other electronic devices.

[0093] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visual user interface.

[0094] The program of the real-time geological disaster monitoring and early warning method based on the fusion of big data and environmental characteristics stored in the memory 11 of the electronic device 1 is a combination of multiple instructions, which can be implemented when running in the processor 10: Receive real-time mine environment monitoring instructions, and confirm the coal mine detection environment based on the real-time mine environment monitoring instructions. Among them, the coal mine detection environment includes: a roadheader, a driving roadway, and a data acquisition unit. Among them, the data acquisition unit includes: a driving acquisition unit and a shutdown acquisition unit. The driving acquisition unit includes a plurality of driving geophones, and the shutdown acquisition unit includes a plurality of static mine environment geophones and a microseismic monitoring unit; Obtain the real-time monitoring moment. If the real-time monitoring moment is within a preset driving period, use the preset driving acquisition period and the driving acquisition unit to receive driving vibration signals, and obtain real-time mine images and a mine monitoring signal set based on the driving vibration signals. Among them, the driving vibration signals come from the vibration of the roadheader; If the real-time monitoring moment is not within the driving period, use the microseismic monitoring unit to obtain real-time mine images and a mine monitoring signal set. Among them, the mine monitoring signal set is monitored by the microseismic monitoring unit; Summarize the real-time mine images according to a preset monitoring time sequence to obtain a mine image sequence, identify all safety hazard point identifiers in the mine image sequence to obtain a safety hazard point identifier sequence, and construct an identified safety hazard point data set based on the mine monitoring signal set, the mine image sequence, and the safety hazard point identifier sequence. Among them, the safety hazard point data includes an identified hazard evolution graph sequence and an identified hazard evolution signal sequence; Analyze the identified safety hazard point data set. If a safety early warning instruction is generated based on the analyzed identified hazard data set, send the safety early warning instruction to the initiating end of the real-time mine environment monitoring instruction. Otherwise, return to the step of obtaining the real-time monitoring moment to complete a real-time geological disaster monitoring and early warning based on the fusion of big data and environmental characteristics.

[0095] Specifically, for the specific implementation method of the above instructions by the processor 10, reference can be made to Figures 1 to 3 the descriptions of the relevant steps in the corresponding embodiments, which will not be elaborated here.

[0096] Furthermore, if the modules / units integrated in the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory).

[0097] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by the processor of the electronic device, it can implement: Receiving a real-time mine environmental monitoring instruction, and confirming the coal mine detection environment based on the real-time mine environmental monitoring instruction. Among them, the coal mine detection environment includes: roadheader, driving roadway and data acquisition unit. Among them, the data acquisition unit includes: a driving-along acquisition unit and a shutdown acquisition unit. The driving-along acquisition unit includes a plurality of driving-along detectors, and the shutdown acquisition unit includes a plurality of static mine environmental detectors and a microseismic monitoring unit; Obtaining the real-time monitoring moment. If the real-time monitoring moment is within a preset driving period, then use the preset driving acquisition period and the driving-along acquisition unit to receive driving vibration signals, and obtain real-time mine images and a mine monitoring signal set based on the driving vibration signals. Among them, the driving vibration signals come from the vibration of the roadheader; If the real-time monitoring moment is not within the driving period, use the microseismic monitoring unit to obtain real-time mine images and a mine monitoring signal set. Among them, the mine monitoring signal set is monitored by the microseismic monitoring unit; Summarize the real-time mine images according to a preset monitoring time sequence to obtain a mine image sequence, identify all safety hazard point identifiers in the mine image sequence to obtain a safety hazard point identifier sequence, and construct an identified safety hazard point data set based on the mine monitoring signal set, the mine image sequence and the safety hazard point identifier sequence. Among them, the safety hazard point data includes an identified hazard evolution graph sequence and an identified hazard evolution signal sequence; Analyze the identified safety hazard point data set. If a safety warning instruction is generated based on the analyzed identified hazard data set, then send the safety warning instruction to the initiating end of the mine real-time environmental monitoring instruction. Otherwise, return to the step of obtaining the real-time monitoring moment to complete a real-time monitoring and warning of geological disasters based on the fusion of big data and environmental characteristics.

[0098] In several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and there may be other partitioning methods in actual implementation.

[0099] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] In addition, in each embodiment of the present invention, the functional modules can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware, or in the form of a combination of hardware and software functional modules.

[0101] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A real-time monitoring and early warning method for geological disasters based on the fusion of big data and environmental characteristics, characterized in that: The method comprises: Receive a real-time mine environment monitoring instruction, and confirm a coal mine detection environment based on the real-time mine environment monitoring instruction, wherein the coal mine detection environment includes: a tunneling machine, a tunneling tunnel, and a data acquisition unit, wherein the data acquisition unit includes: an ongoing excavation acquisition unit and a shutdown acquisition unit, wherein the ongoing excavation acquisition unit includes a plurality of ongoing excavation geophones, and the shutdown acquisition unit includes a plurality of static mine environment geophones and a microseismic monitoring unit; Acquire the real-time monitoring time. If the real-time monitoring time is within the preset excavation period, use the preset excavation collection period and the excavation collection unit to receive the excavation vibration signal, and acquire the real-time mine image and the mine monitoring signal set based on the excavation vibration signal, wherein the excavation vibration signal comes from the vibration of the excavation machine; If the real-time monitoring time is not within the excavation period, a microseismic monitoring unit is used to obtain a real-time mine image and a mine monitoring signal set, wherein the mine monitoring signal set is obtained by monitoring the microseismic monitoring unit; Summarize the real-time mine images according to a preset monitoring time sequence to obtain a mine image sequence, identify all safety hazard point identifiers in the mine image sequence to obtain a safety hazard point identifier sequence, and construct an identified safety hazard point data set based on the mine monitoring signal set, the mine image sequence and the safety hazard point identifier sequence, wherein the safety hazard point data includes an identified hazard evolution graph sequence and an identified hazard evolution signal sequence; Parse and identify the safety hazard point data set. If a safety warning instruction is generated based on the parsed identified hazard data set, then send the safety warning instruction to the initiator of the mine real-time environmental monitoring instruction. Otherwise, return to the step of obtaining the real-time monitoring time to complete a real-time monitoring and early warning of geological disasters based on the fusion of big data and environmental characteristics.

2. The method for real-time monitoring and early warning of geological disasters based on the fusion of big data and environmental characteristics as claimed in claim 1, characterized in that: The method of acquiring a real-time mine image and a mine monitoring signal set based on the excavation vibration signal includes: The excavation vibration signal is fitted by using a pre-constructed seismic interferometry technology to obtain a virtual shot signal set, a low-pass filtering operation is performed on the virtual shot signal set to obtain a noise reduction signal, the noise reduction signal is analyzed by using a pre-constructed scattered wave imaging method, and the analyzed noise reduction signal is visualized to obtain a mine hidden danger detection image corresponding to the real-time monitoring time; Analyze the mine hidden danger detection image to obtain the real-time mine image containing the safety hidden danger point identification, and confirm the excavation vibration signal as the mine monitoring signal set.

3. The real-time monitoring and early warning method for geological disasters based on the fusion of big data and environmental characteristics as claimed in claim 2 is characterized in that: The method of obtaining a real-time mine image and a mine monitoring signal set by using a microseismic monitoring unit includes: Determine whether there is a mine static monitoring moment that is the same as the real-time monitoring moment in the pre-constructed mine static monitoring time sequence; If there is a static mine monitoring moment in the mine static monitoring sequence that is the same as the real-time monitoring moment, multiple static mine environment detectors are used to receive microseismic monitoring signals, analyze the microseismic monitoring signals, and obtain real-time mine images based on the microseismic monitoring signals, and confirm the microseismic monitoring signals as the mine monitoring signal set.

4. The method for real-time monitoring and early warning of geological disasters based on the fusion of big data and environmental characteristics as claimed in claim 3 is characterized in that: The determining whether there is a mine static monitoring moment that is the same as the real-time monitoring moment in the pre-constructed mine static monitoring time sequence includes: Based on the real-time monitoring moment, the adjacent historical hidden danger monitoring period is obtained, the latest historical hidden danger monitoring moment before the real-time monitoring moment is extracted from the adjacent historical hidden danger monitoring period, the hidden danger monitoring frequency control parameter is calculated based on the latest historical hidden danger monitoring moment and the pre-constructed hidden danger monitoring frequency control parameter calculation formula, the hidden danger monitoring frequency control parameter is used to obtain the target monitoring moment, and the target monitoring moment is imported into the pre-constructed initial mine static monitoring time sequence to obtain the mine static monitoring time sequence, wherein the mine static monitoring time sequence includes multiple mine static monitoring moments; Compare the target monitoring time with the real-time monitoring time. If the target monitoring time lags behind the real-time monitoring time, confirm that there is no mine static monitoring time in the mine static monitoring sequence that is the same as the real-time monitoring time. Otherwise, confirm that there is a mine static monitoring time in the mine static monitoring sequence that is the same as the real-time monitoring time.

5. The real-time monitoring and early warning method for geological disasters based on the fusion of big data and environmental characteristics as claimed in claim 4 is characterized in that: The method of constructing a data set of safety hazard points based on a mine monitoring signal set, a mine image sequence and a safety hazard point identification sequence includes: Performing a classification operation on the safety hazard point identification sequence to obtain a hazard classification identification sequence, wherein the hazard classification identification sequence includes multiple hazard classification identifications, and each hazard classification identification corresponds to one or more classified safety hazard point identifications; The hidden danger classification identifiers are extracted from the hidden danger classification identifier sequence in sequence to obtain the target safety hidden danger points, and the following operations are performed on the target safety hidden danger points: Extract all mine monitoring signal sets under the monitoring time sequence from the data acquisition unit, and identify the characteristic signals of the target safety hazard point in all mine monitoring signal sets under the monitoring time sequence to obtain an initial hazard signal sequence; Extracting real-time mine images from the mine image sequence in sequence, identifying the safety hazard image area corresponding to the target safety hazard point from the extracted real-time mine image, summarizing the safety hazard image area, and obtaining an initial safety hazard point evolution graph sequence corresponding to the target safety hazard point; Using the one or more classified safety hazard point identifiers to respectively mark the initial safety hazard point evolution graph sequence and the initial hazard signal sequence, obtain an identified hazard point evolution graph sequence and an identified hazard signal sequence, summarize the identified hazard point evolution graph sequence and the identified hazard signal sequence, and obtain safety hazard point data; The safety hazard point data are aggregated to obtain the identified safety hazard point data set corresponding to the hazard classification identification sequence.

6. The real-time monitoring and early warning method for geological disasters based on the fusion of big data and environmental characteristics as claimed in claim 5 is characterized in that: The step of parsing the identified safety hazard point data set, and if a safety warning instruction is generated based on the parsed identified safety hazard data set, sending the safety warning instruction to the initiator of the mine real-time environment monitoring instruction, otherwise, returning to the step of obtaining the real-time monitoring time, comprises: The following operations are performed on the potential safety hazard point data in the potential safety hazard point identification dataset: Analyze the potential safety hazard point data and obtain the potential safety hazard point analysis results; If the hidden danger point analysis result is the preset hidden danger result, a safety warning instruction is issued to the initiator of the mine real-time environment monitoring instruction; Otherwise, based on the safety hazard point data, historical hazard point data of a preset historical period is extracted from a pre-built historical evolution database, the historical hazard point data and the safety hazard point data are integrated to obtain historical-real-time hazard point integrated data, and the historical-real-time hazard point integrated data is analyzed to obtain historical-real-time hazard point analysis results; If the historical-real-time hidden danger point analysis result is the preset historical-real-time hidden danger result, a safety warning instruction is issued to the initiator of the mine real-time environment monitoring instruction; Otherwise, the hidden danger point analysis results are summarized to obtain the comprehensive data corresponding to the data set of the safety hidden danger points identified under the monitoring time sequence. If the comprehensive data is the preset safety warning comprehensive data, a safety warning instruction is issued to the initiator of the mine real-time environment monitoring instruction; If the comprehensive data is not the preset safety warning comprehensive data, then extract the historical comprehensive data of the preset historical period from the historical evolution database; if the historical comprehensive data is not the preset historical safety warning comprehensive data, then return to the step of obtaining the real-time monitoring time.

7. The real-time monitoring and early warning method for geological disasters based on the fusion of big data and environmental characteristics as claimed in claim 6 is characterized in that: The method of calculating the hidden danger monitoring frequency control parameter based on the latest historical hidden danger monitoring time and the pre-constructed hidden danger monitoring frequency control parameter calculation formula, and obtaining the target monitoring time using the hidden danger monitoring frequency control parameter, includes: Acquire a neighboring hidden danger point data sequence based on a neighboring historical hidden danger monitoring period, wherein the neighboring hidden danger point data sequence includes a plurality of neighboring hidden danger point data, and the plurality of neighboring hidden danger point data are sorted in a time-ordered order, and each of the plurality of neighboring hidden danger point data includes: a hidden danger point position feature, a hidden danger point displacement feature, a hidden danger point deformation feature, and a hidden danger point frequency domain feature; Extracting a target data sequence from a data sequence of adjacent potential danger points, digitizing the target data sequence, and obtaining a target value sequence, wherein the target data sequence includes a plurality of target data of the same type, and the type of the target data is one of a potential danger point position feature, a potential danger point displacement feature, a potential danger point deformation feature, and a potential danger point frequency domain feature; Extract target values ​​from the target value sequence in sequence, and perform the following operations on the extracted target values: Extracting the next target value that lags behind the target value from the target value sequence to obtain an adjacent value, calculating the difference between the target value and the adjacent value to obtain a first-order difference, summing up the first-order differences to obtain a first-order difference sequence; The first difference sequence is slidingly intercepted by using a preset sliding window and a preset sliding step size to obtain a sliding difference data sequence, sliding difference data are sequentially extracted from the sliding difference data sequence, and the variance of the extracted sliding difference data is calculated to obtain the data change amount corresponding to the sliding difference data; Summarize the data changes to obtain a data change sequence; Confirming the first adjustment coefficient and the second adjustment coefficient based on the data variation sequence and the primary difference sequence, and constructing a hidden danger monitoring frequency control parameter calculation formula according to the first adjustment coefficient and the second adjustment coefficient; Calculate the hidden danger monitoring frequency control parameters using the hidden danger monitoring frequency control parameter calculation formula and the latest historical hidden danger monitoring time; The target monitoring time is obtained based on the pre-built frequency conversion adjustment sequence and hidden danger monitoring frequency control parameters.

8. The real-time monitoring and early warning method for geological disasters based on the fusion of big data and environmental characteristics according to claim 7 is characterized in that: The hidden danger monitoring frequency control parameter calculation formula is constructed according to the first adjustment coefficient and the second adjustment coefficient, including: Extracting first-order differences from the primary difference sequence in sequence, and extracting data changes corresponding to the first-order differences from the data change sequence in sequence, and constructing a calculation formula for the initial hidden danger monitoring frequency control parameter based on the extracted first-order differences and the data changes corresponding to the first-order differences; All initial hidden danger monitoring frequency control parameter calculation formulas corresponding to the adjacent hidden danger point data sequences are combined to obtain the hidden danger monitoring frequency control parameter calculation formula, wherein the hidden danger monitoring frequency control parameter calculation formula is as follows: ， in, Indicates the hidden danger monitoring frequency control parameters, represents the first-order difference, and represent the first adjustment coefficient and the second adjustment coefficient respectively, and and are constants, Indicates the amount of data change. It represents the data variation function obtained by linear fitting of sliding differential data. The subscript representing the calculation formula of the initial hidden danger monitoring frequency control parameter, Indicates the total number of calculation formulas for the initial hidden danger monitoring frequency control parameters, It represents the calculation formula of the initial hidden danger monitoring frequency control parameters.

9. The method for real-time monitoring and early warning of geological disasters based on the fusion of big data and environmental characteristics as claimed in claim 8, characterized in that: The method of obtaining the target monitoring time based on the pre-built frequency conversion adjustment sequence and hidden danger monitoring frequency control parameters includes: Acquire multi-source monitoring data, extract a reference mine tunnel set from the multi-source monitoring data, and extract reference mine tunnels from the reference mine tunnel set in sequence, and perform the following operations on the extracted reference mine tunnels: Obtain a reference frequency parameter set corresponding to a reference mine tunnel, and calculate a reference control factor set corresponding to the reference frequency parameter set based on the hidden danger monitoring frequency control parameter calculation formula, wherein the reference frequency parameters correspond to the reference control factors one by one; Constructing a mapping relationship between the reference frequency parameter set and the reference control factor set to obtain an initial frequency-factor data set, simplifying the initial frequency-factor data set to obtain a frequency-factor set, wherein the frequency-factor set includes a plurality of frequency-factors, and the frequency-factor includes: a reference frequency parameter and a reference control factor; Summarize the frequency-factor sets to obtain the frequency-factor set group corresponding to the reference mine tunnel set; Using a pre-constructed clustering method and a preset number of cluster centers, a reference frequency-based clustering operation is performed on the frequency-factor set to obtain a plurality of frequency-factor clusters, wherein the reference frequency-based clustering operation is a K-means clustering operation with the reference frequency as a variable, and the number of the plurality of frequency-factor clusters is equal to the number of the cluster centers; Extracting frequency-factor clusters from multiple frequency-factor clusters in turn, identifying the clustering frequency interval and clustering factor interval of the extracted frequency-factor clusters, calculating the mean of the clustering frequency interval, and obtaining the fuzzy reference frequency; Associating the clustering factor interval with the fuzzy reference frequency to obtain a unit variable frequency adjustment interval, and summarizing and integrating the unit variable frequency adjustment interval to obtain a variable frequency adjustment sequence; The unit frequency conversion adjustment interval where the hidden danger monitoring frequency control parameter is located is searched in the frequency conversion adjustment sequence to obtain the target interval, the fuzzy reference frequency corresponding to the target interval is confirmed as the target frequency, and the target monitoring time is calculated based on the target frequency and the latest historical hidden danger monitoring time.

10. A real-time monitoring and early warning system for geological disasters based on the integration of big data and environmental characteristics, characterized in that: The system comprises: A coal mine detection environment module is used to receive a real-time mine environment monitoring instruction, and confirm the coal mine detection environment based on the real-time mine environment monitoring instruction, wherein the coal mine detection environment includes: a tunneling machine, a tunneling tunnel, and a data acquisition unit, wherein the data acquisition unit includes: an on-the-spot acquisition unit and a stop-work acquisition unit, wherein the on-the-spot acquisition unit includes a plurality of on-the-spot geophones, and the stop-work acquisition unit includes a plurality of static mine environment geophones and a microseismic monitoring unit; A collection module for acquisition of real-time monitoring time. If the real-time monitoring time is within a preset excavation period, the preset excavation collection period and the collection module for acquisition are used to receive the excavation vibration signal, and a real-time mine image and a mine monitoring signal set are acquired based on the excavation vibration signal, wherein the excavation vibration signal comes from the vibration of the excavator. A static acquisition module, used for obtaining a real-time mine image and a mine monitoring signal set by using a microseismic monitoring unit if the real-time monitoring moment is not within the excavation period, wherein the mine monitoring signal set is obtained by monitoring the microseismic monitoring unit; The monitoring feedback module is used to summarize the real-time mine images according to a preset monitoring time sequence to obtain a mine image sequence, identify all safety hazard point identifiers in the mine image sequence, obtain a safety hazard point identifier sequence, and construct an identified safety hazard point data set based on the mine monitoring signal set, the mine image sequence and the safety hazard point identifier sequence, wherein the safety hazard point data includes an identified hazard evolution graph sequence and an identified hazard evolution signal sequence, parse the identified safety hazard point data set, and if a safety warning instruction is generated based on the parsed identified hazard data set, send a safety warning instruction to the initiator of the mine real-time environmental monitoring instruction, otherwise, return to the step of obtaining the real-time monitoring time, and complete a real-time monitoring and early warning of geological disasters based on the fusion of big data and environmental characteristics.

Images