Underground engineering rockburst detection device

Abstract

The underground engineering rockburst detection device comprises a machine body, a display is arranged on one side of the machine body, a stress detector and a plurality of color probes are arranged on the other side of the machine body, and a processor and a power source are further arranged on the machine body; the processor receives the colors detected by the color probes, integrates the colors into a rock mass image according to the position relation of the colors, judges the surrounding rock strength of the rock in the rock mass image in an image processing mode, and determines the probability of rock burst in combination with the stress detected by the stress detector; the occurrence probability of the rockburst is represented through the depth of the color, and finally the color corresponding to the occurrence probability of the rockburst is displayed on a display. According to the method, the surrounding rock strength is determined in an image processing mode, meanwhile, the stress is obtained through the stress detector, then the occurrence probability of rock burst is judged, and then rock burst detection and subsequent rock burst dredging work are conducted.

Description

Technical Field

[0001] The invention relates to the technical field of underground rockburst detection, and in particular to an underground engineering rockburst detection device. Background Art

[0002] Underground projects include hydropower underground projects (underground powerhouses of pumped storage power stations, three caverns, access tunnels, etc.), underground railways, highway tunnels, underwater tunnels, underground common trenches and underpasses. In the construction of underground projects, rock masses are usually crossed. The stress distribution of these rock masses is uneven. Rock bursts may occur in places where the stress is concentrated. Generally, rock bursts will cause injuries or even deaths to construction workers, and will also cause losses to the project. Therefore, during the construction of underground projects, the detection of rock bursts is very important. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide an underground engineering rockburst detection device in view of the deficiencies in the above-mentioned prior art, determine the surrounding rock strength through image processing, and obtain stress through a stress detector, thereby judging the probability of rockburst, and then detecting rockburst and subsequent rockburst relief work.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: an underground engineering rockburst detection device, comprising a body, a display is arranged on one side of the body, a stress detector and a plurality of color probes are arranged on the other side of the body, a processor and a power supply are also arranged on the body, the processor is respectively connected to the display, the stress detector and the color probe signal, and the power supply is respectively electrically connected to the processor, the display, the stress detector and the color probe;

[0005] The processor receives the colors detected by each color probe and integrates them into a rock image according to their positional relationship. The strength of the surrounding rock in the rock image is determined by image processing, and the probability of rock burst is determined in combination with the stress detected by the stress detector. The probability of rock burst is indicated by the depth of color, and finally the color corresponding to the probability of rock burst is displayed on the display.

[0006] Furthermore, the stress detector is arranged at the center of the side surface of the machine body, and the plurality of color probes are arranged on the side surfaces of the machine body around the stress detector.

[0007] Furthermore, a wireless communicator is also provided on the body, the wireless communicator is connected to the processor signal, and the wireless communicator is electrically connected to the power supply;

[0008] The processor transmits the probability of rock burst to an external client via a wireless communicator.

[0009] Furthermore, a hand-held portion is provided at the bottom of the body.

[0010] Furthermore, an anti-slip layer is provided on the handheld portion.

[0011] Further, the processor receives the colors detected by each color probe and integrates them into a rock mass image according to their positional relationship, including the following steps:

[0012] Receive the colors detected by each color probe multiple times;

[0013] The colors detected by each color probe received each time are combined into a sub-image;

[0014] A plurality of the sub-images are spliced ​​together to obtain a rock mass image.

[0015] Further, the method of determining the surrounding rock strength of the rock in the rock mass image by image processing includes the following steps:

[0016] Performing denoising and cleaning processing on the rock mass image;

[0017] Extract pixel values ​​of the rock mass image after denoising and cleaning, and establish a pixel matrix corresponding to the rock mass image;

[0018] Extract the pixel values ​​of each row of the pixel matrix to obtain the pixel sets of each row, and obtain the function sets corresponding to the pixel sets of each row according to the pixel values ​​of each row;

[0019] The function sets corresponding to the pixel sets of each row are summarized to obtain the function sets corresponding to the rock mass image;

[0020] The function set corresponding to the rock mass image is input into the pre-trained machine learning model to obtain the surrounding rock strength of the rock in the rock mass image;

[0021] The machine learning model is used to input a function set and output surrounding rock strength.

[0022] Furthermore, the stress detector detects stress by magnetic measurement.

[0023] Compared with the prior art, the present invention has the following advantages:

[0024] The present invention provides an underground engineering rockburst detection device, which determines a rock mass image by a color probe, judges the surrounding rock strength of the rock in the rock mass image by image processing, obtains stress by a stress detector, and further judges the probability of rockburst, predicts the probability of rockburst by displaying the depth of color, detects the specific situation of the project, thereby detecting rockburst and carrying out subsequent rockburst relief work.

[0025] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 The present invention provides an overall structural diagram of an underground engineering rockburst detection device.

[0027] Figure 2 Schematic diagram of the distribution of color probes and stress detectors in the present invention.

[0028] Description of reference numerals:

[0029] 1. Machine body; 2. Color probe; 3. Stress detector; 4. Anti-slip layer; 5. Handheld part; 6. Display; 7. Wireless communicator. DETAILED DESCRIPTION

[0030] like Figure 1-2 As shown, an underground engineering rockburst detection device provided by the present invention comprises a body 1, a display 6 is arranged on one side of the body 1, a stress detector 3 and a plurality of color probes 2 are arranged on the other side of the body 1, a processor and a power supply are also arranged on the body 1, the processor is respectively connected to the display 6, the stress detector 3 and the color probe 2 by signal, and the power supply is respectively electrically connected to the processor, the display 6, the stress detector 3 and the color probe 2;

[0031] The processor receives the colors detected by each color probe 2, and integrates them into a rock image according to their positional relationship, determines the surrounding rock strength of the rock in the rock image by image processing, and determines the probability of rock burst in combination with the stress detected by the stress detector 3, and indicates the probability of rock burst by the depth of color, and finally displays the color corresponding to the probability of rock burst on the display 6.

[0032] In actual engineering projects, construction workers hold the device at the construction site and point the side of the body 1 with the stress detector 3 and several color probes 2 toward the rock mass. At this time, with the support of the power supply, the processor controls the corresponding electronic components to work, and finally displays the color corresponding to the probability of rock burst on the display 6. The construction workers can view the results on the display 6 and finally determine whether to release the possible rock burst by drilling release or other methods.

[0033] When the display 6 is displaying, the depth of the color indicates the probability of rock burst. The darker the color, the smaller the probability of rock burst, and the lighter the color, the greater the probability of rock burst. The construction personnel judge it according to the actual construction situation and determine whether rock burst needs to be released.

[0034] In the present invention, for the calculation of rockburst probability, in addition to the traditional method of combining surrounding rock strength and stress, the present invention also introduces a neural network model for correcting the calculation results. The neural network model is trained based on a large amount of surrounding rock strength and stress and the corresponding rockburst probability as original data. After repeated corrections, the trained neural network model is applied. The present invention can input the surrounding rock strength and stress into the trained neural network model to finally obtain the rockburst probability.

[0035] In the present invention, the stress detector 3 can use the resistance strain gauge method to measure the stress, which can ensure high-precision stress measurement results and is suitable for stress measurement within 5 meters.

[0036] The product of the present invention can be further optimized in structure, the stress detector 3 is arranged at the center of the side of the body 1, and the plurality of color probes 2 are arranged around the stress detector 3 on the side of the body 1. This has the advantage that the stress result is surrounded by an image surround method, and the complete rock mass image and the stress located in the middle of the rock mass image are beneficial to the combination of surrounding rock strength and stress, and then the probability of rock burst is obtained.

[0037] For the convenience of construction, the present invention can also transmit the detected rock burst probability to an external client by means of data transmission. The body 1 is also provided with a wireless communicator 7, which is connected to the processor signal, and the wireless communicator 7 is electrically connected to the power supply; the processor transmits the rock burst probability to the external client through the wireless communicator 7. The external client can be a display located in the master control detection room, or can be a mobile phone client, a computer client, a web client, or other forms.

[0038] In order to facilitate construction, a hand-held portion 5 is provided at the bottom of the machine body 1, and the hand-held portion 5 is used by construction workers to hold it when in use. An anti-slip layer 4 is provided on the hand-held portion 5 to ensure the stability of the hand-held portion 5 when held.

[0039] Regarding the working process of the present invention, in the present invention, the processor receives the colors detected by each color probe 2 and integrates them into a rock mass image according to their positional relationship, including the following steps:

[0040] 1. Receive the colors detected by each color probe 2 multiple times;

[0041] 2. The colors detected by each color probe 2 are combined into a sub-image;

[0042] 3. Combine the multiple sub-images to obtain a rock mass image.

[0043] In the present invention, since the stress detector 3 is located at the center of the color probe 2, if the rock image detected from a single position has a gap in the middle, in order to compensate for this defect and also to improve the accuracy of stress detection, when the present invention is in use, the position of the hand is moved so that the device of the present invention can detect at multiple positions, so that the colors detected by each color probe 2 can be received multiple times, and the colors detected each time are received to form a sub-image, which is the image with a gap in the middle as mentioned above. Therefore, we splice multiple sub-images to obtain a rock image.

[0044] At the same time, since the device of the present invention detects at multiple positions, there will be multiple stresses and the positions corresponding to each stress. Based on this, we establish a stress matrix according to the position of each stress in a matrix manner. By analyzing and processing the stress matrix, we obtain the position and size of the final stress, and complete the correspondence with the above-mentioned rock mass image, which is convenient for subsequent data use.

[0045] Meanwhile, in the present invention, the method of judging the surrounding rock strength of the rock in the rock mass image by image processing comprises the following steps:

[0046] 1. De-noising and cleaning the rock mass image;

[0047] 2. Extract pixel values ​​from the denoised and cleaned rock mass image and establish a pixel matrix corresponding to the rock mass image;

[0048] 3. Extract the pixel values ​​of each row of the pixel matrix to obtain the pixel sets of each row, and obtain the function sets corresponding to the pixel sets of each row according to the pixel values ​​of each row;

[0049] 4. Summarize the function sets corresponding to the pixel sets in each row to obtain the function set corresponding to the rock mass image;

[0050] 5. Input the function set corresponding to the rock mass image into the pre-trained machine learning model to obtain the surrounding rock strength of the rock in the rock mass image;

[0051] The machine learning model is used to input a function set and output surrounding rock strength.

[0052] The present invention uses artificial intelligence to form experience through a large amount of data to correspond the surrounding rock strength and the corresponding rock mass image, thereby ensuring the accuracy of the surrounding rock strength obtained when in use.

[0053] At the same time, when the present invention processes the rock image, the data processing method used when processing the rock image, when processing the data, introduces a function to represent the correlation of the data. Compared with the traditional image processing method, it ensures that the rock image is accurately represented by data, and the rock image is digitized, ensuring the accuracy of the image entering the machine learning model, and laying the foundation for obtaining accurate surrounding rock strength in the subsequent process.

[0054] In the present invention, if there is no excessively high requirement for accuracy but the cost needs to be saved, the stress detector 3 of the present invention detects stress by magnetic measurement within 5 meters.

[0055] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any simple modification, change and equivalent structural change made to the above embodiment based on the technical essence of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An underground engineering rockburst detection device, characterized in that: The device comprises a body (1), a display (6) is arranged on one side of the body (1), a stress detector (3) and a plurality of color probes (2) are arranged on the other side of the body (1), a processor and a power supply are also arranged on the body (1), the processor is respectively connected to the display (6), the stress detector (3) and the color probe (2) by signals, and the power supply is respectively electrically connected to the processor, the display (6), the stress detector (3) and the color probe (2); The processor receives the colors detected by each color probe (2), and integrates them into a rock mass image according to their positional relationship, determines the surrounding rock strength of the rock in the rock mass image by image processing, and determines the probability of rock burst in combination with the stress detected by the stress detector (3), and indicates the probability of rock burst by the depth of the color, and finally displays the color corresponding to the probability of rock burst on the display (6).

2. An underground engineering rockburst detection device according to claim 1, characterized in that: The stress detector (3) is arranged at the center of the side of the machine body (1), and the plurality of color probes (2) are arranged on the side of the machine body (1) around the stress detector (3).

3. An underground engineering rockburst detection device according to claim 1, characterized in that: The body (1) is also provided with a wireless communicator (7), the wireless communicator (7) is signal-connected to the processor, and the wireless communicator (7) is electrically connected to the power supply; The processor transmits the probability of rock burst occurrence to an external client via a wireless communicator (7).

4. An underground engineering rockburst detection device according to claim 1, characterized in that: A hand-held portion (5) is provided at the bottom of the machine body (1).

5. An underground engineering rockburst detection device according to claim 4, characterized in that: The hand-held portion (5) is provided with an anti-slip layer (4).

6. An underground engineering rockburst detection device according to claim 1, characterized in that: The processor receives the colors detected by each color probe (2) and integrates them into a rock mass image according to their positional relationship, including the following steps: Receiving the colors detected by each color probe (2) multiple times; The colors detected by each color probe (2) received each time are combined into a sub-image; A plurality of the sub-images are spliced ​​together to obtain a rock mass image.

7. An underground engineering rockburst detection device according to claim 1, characterized in that: The method of judging the surrounding rock strength of the rock in the rock mass image by image processing includes the following steps: Performing denoising and cleaning processing on the rock mass image; Extract pixel values ​​of the rock mass image after denoising and cleaning, and establish a pixel matrix corresponding to the rock mass image; Extract the pixel values ​​of each row of the pixel matrix to obtain the pixel sets of each row, and obtain the function sets corresponding to the pixel sets of each row according to the pixel values ​​of each row; The function sets corresponding to the pixel sets of each row are summarized to obtain the function sets corresponding to the rock mass image; The function set corresponding to the rock mass image is input into the pre-trained machine learning model to obtain the surrounding rock strength of the rock in the rock mass image; The machine learning model is used to input a function set and output surrounding rock strength.

8. An underground engineering rockburst detection device according to claim 1, characterized in that: The stress detector (3) detects stress by means of magnetic measurement.

Images