A method and system for identifying vibrations underground in coal mines

Abstract

A method and system for identifying vibrations underground in coal mines, which obtain various vibration data of each device and the appearance images of the devices in real time; record and store the working hours, load status, and historical operation parameters of each device, so as to calculate the weight of each device; extract vibration characteristics from the vibration data, and multiply all the vibration characteristics of each device by the corresponding weight of the device; identify the change of the feature point coordinates of the device through the Scale-Invariant Feature Transform (SIFT) algorithm for the collected appearance images as the image characteristics; obtain the historical vibration position data, and divide the underground area of the coal mine into multiple areas with different vibration risk levels through the Geographic Information System (GIS); fuse and splice the weighted vibration characteristics and the image characteristics of all devices to form a regional feature vector, and input the regional feature vector into a convolutional neural network for prediction. The present invention realizes the real-time monitoring and precise positioning of vibrations underground in coal mines and adapts to complex and changeable vibration environments.

Description

Technical Field

[0001] The present invention belongs to the technical field of vibration recognition, and more specifically, relates to a method and system for recognizing vibrations underground in coal mines. Background Art

[0002] The safe production of coal mines is a key concern in the industry, and underground vibration monitoring is crucial for preventing equipment damage and safety accidents. Traditional vibration monitoring methods relying on a single sensor have many limitations, such as incomplete information, inaccurate positioning, and limited vibration type recognition ability. With the progress of technology, the application of image recognition technology and GIS technology provides new perspectives and possibilities for coal mine vibration monitoring, but there is currently a lack of an effective method to combine these two technologies to achieve comprehensive and accurate recognition of vibrations underground in coal mines. Summary of the Invention

[0003] To solve the deficiencies in the prior art, the present invention provides a method and system for recognizing vibrations underground in coal mines.

[0004] The present invention adopts the following technical solutions.

[0005] In a first aspect of the present invention, a method for recognizing vibrations underground in coal mines is proposed, which is characterized by including:

[0006] By configuring a status sensor on each device, various vibration data of each device are obtained in real time, and the appearance images of the devices are collected in real time; the vibration data and the appearance images of the devices are preprocessed;

[0007] An operating parameter recording unit is established, which is connected to the status sensor and records and stores the working hours, load status, and historical operating parameters of each device;

[0008] The weight of each device is calculated based on the working hours, load status, and historical operating parameters;

[0009] Vibration features are extracted from the vibration data, and all vibration features of each device are multiplied by the corresponding weight of the device; the collected appearance images are used to extract feature points of the devices through the scale-invariant feature transform algorithm, the coordinate changes of the feature points of the devices are recognized, and all coordinate changes of the feature points are output in the form of a vector as image features;

[0010] Historical vibration position data are obtained, and the underground area of the coal mine is divided into multiple areas with different vibration risk levels by combining the vibration data and the vibration position data using the geographic information system GIS;

[0011] According to the divided regions, the weighted vibration characteristics and image characteristics of all devices in each region of each vibration risk level are fused and spliced to form a region feature vector, and the region feature vector is input into a trained convolutional neural network to predict the probability, type, and intensity of vibration in the region.

[0012] Preferably, a state sensor is configured on each device to obtain the vibration data of each device in real time, specifically:

[0013] The devices include a shearer, a roadheader, and a conveyor according to the device type; the vibration data includes vibration frequency, amplitude, vibration mode, and running acceleration change.

[0014] Preferably, the vibration data and the appearance image of the device are preprocessed, specifically:

[0015] The image is converted into a grayscale image, and then filtered to eliminate noise. The filtering formula is:

[0016]

[0017]

[0018] where k is the radius of the Gaussian kernel, is the pixel coordinate in the image, is the pixel coordinate of the pixel point after filtering, is the weight of the Gaussian kernel, is the element coordinate of the Gaussian kernel, is the pixel point with pixel coordinate in the original image; is the two-dimensional Gaussian function.

[0019] Preferably, the weight of each device is calculated through the working duration, load status, and historical operation parameters, specifically:

[0020]

[0021] where is the credibility weight of the working duration of the device, is the credibility weight of the load status of the device, is the credibility weight of the i-th historical operation parameter of the device; n is the number of historical operation parameters;

[0022]

[0023]

[0024]

[0025] Among them, , , are respectively the set working duration, load status, and weight coefficient of historical operation parameters; , , are respectively the thresholds of the set working duration, load status, and historical operation parameters; is the theoretical maximum working duration; is the maximum load value; is the maximum value of historical operation parameters; is the average value of historical operation parameters; , , are respectively the working duration, load status, and the i-th historical operation parameter of the device; is the step function, which is 1 when its independent variable is greater than or equal to 0, and 0 otherwise.

[0026] Preferably, various vibration characteristics include vibration waveform characteristics, vibration spectrum characteristics, and vibration energy distribution characteristics;

[0027] The extraction of vibration waveform characteristics is as follows:

[0028] All vibration amplitudes are arranged in chronological order to form a vibration amplitude sequence, and the curve function of this sequence is simulated as the vibration waveform, t is time, and the symmetry deviation of the vibration waveform and the derivatives at each set time point are calculated as the vibration waveform characteristics;

[0029] Symmetry deviation The calculation formula is:

[0030]

[0031] Among them, is the total number of set time points, is the time of the i-th set time point;

[0032] Preferably, the extraction of vibration waveform characteristics and vibration energy distribution characteristics is specifically as follows:

[0033] All vibration frequencies are arranged in chronological order to form a vibration frequency sequence, and using the fast Fourier transform FFT algorithm, the vibration frequency sequence is transformed into a spectrogram , f is frequency, and the peak value of the spectrogram is the vibration spectrum characteristic;

[0034] The vibration energy distribution characteristic is the vibration energy distribution within the set frequency range, and the calculation formula is:

[0035]

[0036] Among them, is the frequency corresponding to the peak of the spectrogram, f 1 - f 2 is the set frequency range; is the set frequency value.

[0037] Preferably, the historical vibration position data is obtained, and the vibration data is combined with the geographical information system GIS using the vibration position data to divide the underground coal mine area into multiple regions with different vibration risk levels, specifically:

[0038] According to the actual terrain near each device, a space with the device as the center and a set distance as the radius or a rectangular space with the device as the center point and set length and width is selected, and all the selected spaces are used as the objects for regional division, and other regions are merged into a risk-free region;

[0039] According to the historical vibration position data, calculate the vibration density of all unit area regions within the object. The formula is:

[0040]

[0041] Among them, is the vibration density of the v-th unit area region; m is the total number of historical vibration position data; h is the set smoothing parameter; K() is the Gaussian kernel function; is the position of the v-th unit area region; is the u-th historical vibration position data; and are both in the form of two-dimensional coordinates; is the Euclidean norm;

[0042] Set different vibration modes as digital indicators from 0 to 1; calculate the comprehensive vibration index according to the vibration density of the unit area region, the vibration mode of the equipment included in the unit area region, and the change in operating acceleration. The formula is:

[0043]

[0044] Among them, , , are the weights of vibration density, vibration mode, and change in operating acceleration respectively; is the average value of the vibration mode of the equipment in the v-th unit area region, is the average value of the change in operating acceleration of the equipment in the v-th unit area region;

[0045] Input the comprehensive vibration index of all unit - area regions into the GIS tool. Using the natural - break algorithm of GIS, divide all the comprehensive vibration indices into a set number of vibration risk levels; and through the GIS tool, integrate the unit - area regions with the same vibration risk level into one region and visualize it.

[0046] Preferably, calculate the weights of vibration density, vibration mode, and running acceleration change, specifically:

[0047] Normalize the vibration density, vibration mode, and running acceleration change;

[0048] Calculate the entropy value and weight of each index:

[0049]

[0050] Among them, a ={1, 2, 3}, when it is 1, 2, and 3, it represents vibration density, vibration mode, and running acceleration change respectively; is a the corresponding entropy value of vibration density, vibration mode setting, or running acceleration change, is the total number of unit - area regions in the division object; When a is 1, 2, and 3, it respectively represents after normalization , , ; When a is 1, 2, and 3, it respectively represents , , .

[0051] Preferably, according to the divided regions, fuse and splice the weighted vibration characteristics and image characteristics of all devices in each region with a vibration risk level to form a region - feature vector, and input the region - feature vector into a trained convolutional neural network to predict the probability, type, and intensity of vibration in this region, specifically:

[0052] For each weighted vibration characteristic and image characteristic of all devices in each region with a vibration risk level, calculate the average value of this characteristic and then splice them to form a region - feature vector;

[0053] Input it into a trained convolutional neural network, and output a three - dimensional vector. The three - dimensional vector respectively represents the probability of vibration in this region, the probability that the vibration in this region is of each vibration type, and the probability that the intensity of vibration in this region is of various intensities. The probability of vibration is 0 - 1. Each vibration type includes mechanical vibration caused by loose equipment parts, geological vibration caused by geological structure changes, and vibration generated by normal equipment operation. Each intensity includes weak, medium, and strong.

[0054] The second aspect of the present invention proposes an identification system for underground coal mine vibrations using the method described in the first aspect of the present invention, comprising a configuration status sensor, a camera device, an operating parameter recording unit, a weight calculation module, a feature extraction module, a region division module, and a prediction module, characterized in that:

[0055] Configuration status sensor: used to obtain various vibration data of each device in real time;

[0056] Camera device: used to collect the appearance images of the devices in real time; preprocess the vibration data and the appearance images of the devices;

[0057] Operating parameter recording unit: this unit is connected to the status sensor and is used to record and store the working hours, load status, and historical operating parameters of each device;

[0058] Weight calculation module: used to calculate the weight of each device based on the working hours, load status, and historical operating parameters;

[0059] Feature extraction module: extract vibration features according to the vibration data, and multiply all the vibration features of each device by the corresponding weight of the device; extract the feature points of the device from the collected appearance images through the scale-invariant feature transform algorithm, identify the coordinate changes of the feature points of the device, and output all the coordinate changes of the feature points in the form of a vector as the image feature;

[0060] Region division module: obtain the historical vibration position data, and use the geographic information system GIS in combination with the vibration data and the vibration position data to divide the underground coal mine area into multiple regions with different vibration risk levels;

[0061] Prediction module: according to the divided regions, fuse and splice the weighted vibration features and the image features of all the devices in each region with different vibration risk levels to form a region feature vector, input the region feature vector into the trained convolutional neural network, and predict the probability, type, and intensity of the vibration in this region.

[0062] The beneficial effects of the present invention are as follows. Compared with the prior art, by extracting the multi-dimensional features of the vibration data and combining the features extracted from the pictures, the accuracy and reliability of vibration identification are improved, and false alarms and missed alarms are reduced; the weights are calculated using the working hours, load status, and historical parameters, which can dynamically adapt to the prediction of device vibrations in different states; the GIS region division is carried out using the vibration data and the vibration position data, which can combine the physical location and the vibration data, and the region division is more scientific, and different risk-level regions are predicted and managed specifically. Finally, the real-time monitoring and precise positioning of underground coal mine vibrations are realized through the convolutional neural network, which can adapt to the complex and changeable vibration environment, improve the emergency handling efficiency, and provide data support for coal mine safety production. Brief Description of the Drawings

[0063] Figure 1 This is the flowchart of the method of the present invention. Detailed Embodiments

[0064] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. The embodiments described in this application are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the spirit of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0065] As Figure 1 shown, Embodiment 1 of the present invention proposes a method for identifying vibrations in underground coal mines, which is characterized by including:

[0066] By configuring state sensors on each device, various vibration data of each device are obtained in real time, and the appearance images of the devices are collected in real time; the vibration data and the appearance images of the devices are preprocessed;

[0067] A running parameter recording unit is established, which is connected to the state sensors and records and stores the working hours, load status and historical running parameters of each device;

[0068] Calculate the weight of each device based on the working hours, load status and historical running parameters;

[0069] Extract vibration characteristics according to the vibration data, and multiply all the vibration characteristics of each device by the corresponding weight of the device; extract the feature points of the device from the collected appearance images through the scale-invariant feature transform algorithm, identify the coordinate changes of the feature points of the device, and output all the coordinate changes of the feature points in the form of a vector as the image feature;

[0070] Obtain historical vibration position data, and combine the vibration data and the vibration position data to use the geographic information system GIS to divide the underground coal mine area into multiple areas with different vibration risk levels;

[0071] According to the divided areas, fuse and splice the weighted vibration characteristics and image features of all the devices in each area with different vibration risk levels to form an area feature vector, and input the area feature vector into a trained convolutional neural network to predict the probability, type and intensity of the vibration in the area.

[0072] Preferably, the configuration of state sensors on each device to obtain the vibration data of each device in real time is specifically:

[0073] The devices include coal shearers, roadheaders, and conveyors according to the device type; the vibration data includes vibration frequency, amplitude, vibration mode, and operating acceleration change.

[0074] Preferably, the preprocessing of the vibration data and the appearance image of the device is specifically as follows:

[0075] Normalize the vibration data, and the formula is:

[0076]

[0077] Where, is the original vibration data, is the mean value of the vibration data, is the standard deviation of the vibration data, is the vibration data after normalization;

[0078] Convert the image into a grayscale image, and then perform filtering to eliminate noise. The filtering formula is:

[0079]

[0080]

[0081] Where, k is the radius of the Gaussian kernel, is the pixel coordinate in the image, is the pixel coordinate of the pixel point after filtering, is the weight of the Gaussian kernel, is the element coordinate of the Gaussian kernel, is the pixel point with pixel coordinate in the original image; is the two-dimensional Gaussian function.

[0082] Preferably, the weight of each device is calculated by the working duration, load status, and historical operation parameters, specifically as follows:

[0083]

[0084] Where, is the credibility weight of the working duration of the device, is the credibility weight of the load status of the device, is the credibility weight of the i-th historical operation parameter of the device; n is the number of historical operation parameters;

[0085]

[0086]

[0087]

[0088] Among them, and and are the set working hours, load status, and historical operation parameter weight coefficients respectively; and and are the thresholds of the set working hours, load status, and historical operation parameters respectively; is the theoretical maximum working hours; is the maximum load value; is the maximum value of historical operation parameters; is the average value of historical operation parameters; and and are the working hours, load status, and the i-th historical operation parameter of the device respectively; is the step function, which is 1 when its independent variable is greater than or equal to 0, and 0 otherwise.

[0089] Preferably, various vibration characteristics include vibration waveform characteristics, vibration spectrum characteristics, and vibration energy distribution characteristics;

[0090] The extraction of vibration waveform characteristics is as follows:

[0091] All vibration amplitudes are arranged in a time sequence to form a vibration amplitude sequence, and the curve function of this sequence is simulated as the vibration waveform, t is the time, and the symmetry deviation of the vibration waveform and the derivatives at each set time point are calculated as the vibration waveform characteristics;

[0092] Symmetry deviation The calculation formula is:

[0093]

[0094] Among them, is the total number of set time points, is the time of the i-th set time point;

[0095] Preferably, the extraction of vibration waveform characteristics and vibration energy distribution characteristics is specifically as follows:

[0096] All vibration frequencies are arranged in a time sequence to form a vibration frequency sequence, and the fast Fourier transform (FFT) algorithm is used to convert the vibration frequency sequence into a spectrogram , f is the frequency, and the peak value of the spectrogram is the vibration spectrum characteristic;

[0097] The vibration energy distribution characteristic is the vibration energy distribution within the set frequency range, and the calculation formula is:

[0098]

[0099] Among them, is the frequency corresponding to the peak of the spectrogram, f 1 - f 2 is the set frequency range; is the set frequency value.

[0100] Preferably, the historical vibration position data is obtained, and the vibration data is combined with the vibration position data and the Geographic Information System (GIS) to divide the underground coal mine area into multiple areas with different vibration risk levels. Specifically:

[0101] According to the actual terrain near each device, a space with the device as the center and a set distance as the radius or a rectangular space with the device as the center point and set length and width is selected, and all the selected spaces are used as the objects for area division, and other areas are merged into a risk-free area;

[0102] Specifically, in this embodiment, the selected spaces are all spaces with the device as the center and a set distance as the radius, and the set distance is 5m.

[0103] According to the historical vibration position data, calculate the vibration density of all unit area regions within the object. The formula is:

[0104]

[0105] Among them, is the vibration density of the v-th unit area region; m is the total number of historical vibration position data; h is the set smoothing parameter; K() is the Gaussian kernel function; is the position of the v-th unit area region; is the u-th historical vibration position data; and are both in the form of two-dimensional coordinates; is the Euclidean norm;

[0106] Set different vibration modes as digital indicators from 0 to 1; calculate the comprehensive vibration index according to the vibration density of the unit area region, the vibration mode of the device included in the unit area region, and the change in operating acceleration. The formula is:

[0107]

[0108] Among them, , , are the weights of vibration density, vibration mode, and change in operating acceleration respectively; is the average vibration mode of the device in the v-th unit area region, is the average value of the change in the operating acceleration of the device in the v-th unit area region;

[0109] Input the comprehensive vibration indicators of all unit area regions into the GIS tool. Using the natural break algorithm of GIS, divide all the comprehensive vibration indicators into a set number of vibration risk levels; and integrate the unit area regions with the same vibration risk level into one region through the GIS tool and visualize it.

[0110] Preferably, calculate the weights of vibration density, vibration mode, and change in operating acceleration, specifically:

[0111] Normalize both vibration density, vibration mode, and change in operating acceleration;

[0112] Calculate the entropy value and weight of each indicator:

[0113]

[0114] Among them, a ={1, 2, 3}, when it is 1, 2, and 3, it represents vibration density, vibration mode, and change in operating acceleration respectively; is a the corresponding entropy value of vibration density, vibration mode setting, or change in operating acceleration, is the total number of unit area regions in the division object; At a when it is 1, 2, and 3, it represents respectively after normalization , , ; At a when it is 1, 2, and 3, it represents respectively , , .

[0115] Preferably, for the divided regions, fuse and splice the weighted vibration characteristics and image characteristics of all devices in each vibration risk level region to form a region feature vector, and input the region feature vector into a trained convolutional neural network to predict the probability, type, and intensity of vibration in this region, specifically:

[0116] For each weighted vibration characteristic and image characteristic of all devices in each vibration risk level region, calculate the average value of this characteristic and then splice them to form a region feature vector;

[0117] Input it into a trained convolutional neural network, and output a three-dimensional vector. The three-dimensional vector respectively represents the probability of vibration in this area, the probability that the vibration in this area is of each vibration type, and the probability that the intensity of the vibration in this area is of various intensities. The probability of vibration is between 0 and 1. Each vibration type includes mechanical vibration caused by loose equipment parts, geological vibration caused by geological structure changes, and vibration generated during normal equipment operation. Each intensity includes weak, medium, and strong.

[0118] Embodiment 2 of the present invention proposes an identification system for underground coal mine vibrations using the method described in Embodiment 1 of the present invention, including a configuration status sensor, a camera device, an operating parameter recording unit, a weight calculation module, a feature extraction module, a region division module, and a prediction module, characterized in that:

[0119] Configuration status sensor: used to obtain various vibration data of each device in real time;

[0120] Camera device: used to collect the appearance images of the equipment in real time; preprocess the vibration data and the appearance images of the equipment;

[0121] Operating parameter recording unit: This unit is connected to the status sensor and is used to record and store the working hours, load status, and historical operating parameters of each device;

[0122] Weight calculation module: used to calculate the weight of each device based on the working hours, load status, and historical operating parameters;

[0123] Feature extraction module: extract vibration features according to the vibration data, and multiply all the vibration features of each device by the corresponding weight of the device; extract the feature points of the equipment from the collected appearance images through the scale-invariant feature transform algorithm, identify the coordinate changes of the feature points of the equipment, and output all the coordinate changes of the feature points in the form of a vector as the image feature;

[0124] Region division module: obtain the historical vibration position data, and combine the vibration data and the vibration position data to use the geographic information system GIS to divide the underground coal mine area into multiple areas with different vibration risk levels;

[0125] Prediction module: according to the divided regions, fuse and splice the weighted vibration features and image features of all devices in each vibration risk level region to form a region feature vector, input the region feature vector into a trained convolutional neural network, and predict the probability, type, and intensity of vibration in this region.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: it is still possible to modify the specific implementation manners of the present invention or make equivalent substitutions, and any modification or equivalent substitution that does not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for identifying vibration in coal mines, characterized in that: include: By configuring status sensors on each device, various vibration data of each device can be obtained in real time, and the appearance image of the device can be collected in real time; Preprocessing vibration data and appearance images of equipment; Establish an operating parameter recording unit, which is connected to the status sensor to record and store the working hours, load status and historical operating parameters of each device; Calculate the weight of each device based on working hours, load status and historical operating parameters ; in, is the credibility weight of the working time of the equipment, is the credibility weight of the load status of the equipment, is the credibility weight of the i-th historical operating parameter of the equipment; n is the number of historical operating parameters; Extract vibration features based on vibration data, and multiply all vibration features of each device by the weight of the corresponding device; The acquired appearance image is used to extract the feature points of the device through a scale-invariant feature transformation algorithm, the coordinate changes of the feature points of the device are identified, and the coordinate changes of all feature points are output in the form of vectors as image features; Obtain historical vibration location data, and use the geographic information system (GIS) to combine the vibration data and vibration location data to divide the underground area of ​​the coal mine into multiple areas with different vibration risk levels; According to the divided areas, the weighted vibration features of all equipment in each vibration risk level area are fused and concatenated with the image features to form a regional feature vector. The regional feature vector is input into the trained convolutional neural network to predict the probability, type and intensity of vibration in the area.

2. A method for identifying vibration in underground coal mines according to claim 1, characterized in that: include: The state sensor is configured on each device to obtain the vibration data of each device in real time, specifically: Equipment includes coal mining machines, tunneling machines and conveyors according to equipment type; vibration data includes vibration frequency, amplitude, vibration mode, and operating acceleration changes.

3. A method for identifying vibration in coal mines according to claim 2, characterized in that: include: The vibration data and the appearance image of the device are preprocessed, specifically: The image is converted into a grayscale image, and then filtered to eliminate noise. The filtering formula is: in, k is the radius of the Gaussian kernel, is the pixel coordinate in the image, is the pixel coordinate The result after pixel filtering is is the weight of the Gaussian kernel, are the element coordinates of the Gaussian kernel, The pixel coordinates in the original image are Pixels of is a two-dimensional Gaussian function.

4. A method for identifying vibration in coal mines according to claim 1, characterized in that: include: The weight of each device is calculated by working time, load status and historical operating parameters, specifically: in, , , They are respectively the set working hours, load status and historical operating parameter weight coefficients; , , They are the thresholds of the set working hours, load status and historical operating parameters; The theoretical maximum working time; is the maximum load value; It is the maximum value of historical operating parameters; is the average value of historical operating parameters; , , are the working time, load status and the i-th historical operating parameter of the equipment respectively; It is a step function, which is 1 when its independent variable is greater than or equal to 0, and 0 otherwise.

5. A method for identifying vibration in underground coal mines according to claim 3, characterized in that: include: Various vibration characteristics include vibration waveform characteristics, vibration spectrum characteristics, and vibration energy distribution characteristics; The vibration waveform features are extracted as follows: All vibration amplitudes are arranged into a vibration amplitude sequence in time order, and the curve function of the sequence is simulated is the vibration waveform, t For time, the symmetry deviation of the vibration waveform and the derivatives of each set time point are calculated as vibration waveform features; Symmetry Deviation The calculation formula is: in, is the total number of time points set, The time of the I-th set time point.

6. A method for identifying vibration in underground coal mines according to claim 5, characterized in that: include: Extraction of vibration waveform characteristics and vibration energy distribution characteristics, specifically: All vibration frequencies are arranged into a vibration frequency sequence in chronological order, and the vibration frequency sequence is converted into a spectrum diagram using the fast Fourier transform FFT algorithm. , f is the frequency, and the peak of the spectrum is the vibration spectrum feature; The vibration energy distribution characteristic is the vibration energy distribution within the set frequency range, and the calculation formula is: in, is the frequency corresponding to the peak of the spectrum graph, f 1- f 2 is the set frequency range; is the set frequency value.

7. A method for identifying vibration in underground coal mines according to claim 3, characterized in that: include: The historical vibration location data is obtained, and the vibration location data and the geographic information system GIS are combined to divide the underground area of ​​the coal mine into multiple areas with different vibration risk levels, specifically: According to the actual terrain near each device, select a space with the device as the center and a set distance as the radius, or a rectangular space with the device as the center point and set length and width, divide all the selected spaces into regions, and merge other areas into a risk-free area; Based on the historical vibration position data, the vibration density of all unit areas within the object is calculated using the formula: in, is the vibration density of the vth unit area; m is the total number of historical vibration position data; h is the set smoothing parameter; K() is the Gaussian kernel function; is the position of the vth unit area; is the u-th historical vibration position data; and All are in the form of two-dimensional coordinates; is the Euclidean norm; Set different vibration modes as digital indicators ranging from 0 to 1; calculate the comprehensive vibration index based on the vibration density per unit area, the vibration mode of the equipment contained in the unit area, and the change in running acceleration. , the formula is: in, , , They are the weights of vibration density, vibration mode, and running acceleration changes; is the average value of the vibration mode of the device in the vth unit area, is the average value of the running acceleration change of the equipment in the vth unit area; The comprehensive vibration indicators of all unit area regions are input into the GIS tool, and the natural breakpoint algorithm of GIS is used to divide all the comprehensive vibration indicators into a set number of vibration risk levels; and the unit area regions with the same vibration risk level are integrated into one area through the GIS tool and visualized.

8. A method for identifying vibration in underground coal mines according to claim 6, characterized in that: include: Calculate the weights of vibration density, vibration mode, and running acceleration changes, specifically: The vibration density, vibration mode and running acceleration changes are all normalized; Calculate the entropy value and weight of each indicator: in, a ={1,2,3}, where 1, 2, and 3 represent the vibration density, vibration mode, and running acceleration changes respectively; for a The corresponding vibration density, vibration mode setting or entropy value of running acceleration change, is the total number of unit area regions in the partitioned object; exist a When it is 1, 2, or 3, it means after normalization. , , ; exist a When it is 1, 2, or 3, it means , , .

9. A method for identifying vibration in underground coal mines according to claim 6, characterized in that: include: According to the divided areas, the weighted vibration features of all devices in each vibration risk level area are fused and spliced ​​with the image features to form a regional feature vector, and the regional feature vector is input into the trained convolutional neural network to predict the probability, type and intensity of vibration in the area, specifically: For each weighted vibration feature and image feature of all equipment in the area of ​​each vibration risk level, the average value of the feature is calculated and then concatenated to form a regional feature vector; It is input into the trained convolutional neural network and outputs a three-dimensional vector. The three-dimensional vector represents the probability of vibration in the area, the probability of the vibration in the area being of each vibration type, and the probability of the vibration intensity in the area being of various intensities. The probability of vibration is 0-1. The various vibration types include mechanical vibration caused by loose equipment parts, geological vibration caused by changes in geological structure, and vibration caused by normal equipment operation. The various intensities include weak, medium, and strong.

10. A system for identifying underground vibration in a coal mine using the method according to any one of claims 1 to 9, comprising a configuration state sensor, a camera device, an operation parameter recording unit, a weight calculation module, a feature extraction module, a region division module and a prediction module, characterized in that: Configuration status sensor: used to obtain various vibration data of each device in real time; Camera device: used to collect the appearance image of the equipment in real time; Preprocessing vibration data and appearance images of equipment; Operation parameter recording unit: This unit is connected to the status sensor and is used to record and store the working hours, load status and historical operation parameters of each device; Weight calculation module: used to calculate the weight of each device based on working hours, load status and historical operating parameters; Feature extraction module: extract vibration features based on vibration data, multiply all vibration features of each device by the weight of the corresponding device; extract feature points of the device from the collected appearance image through the scale-invariant feature transformation algorithm, identify the coordinate changes of the feature points of the device, and output all feature point coordinate changes in the form of vectors as image features; Area division module: obtain historical vibration location data, and use the geographic information system GIS to divide the underground area of ​​the coal mine into multiple areas with different vibration risk levels by combining the vibration data and vibration location data; Prediction module: According to the divided areas, the weighted vibration features of all devices in each vibration risk level area are fused and concatenated with the image features to form a regional feature vector. The regional feature vector is input into the trained convolutional neural network to predict the probability, type and intensity of vibration in the area.

Images