CN113011434A - Coal mine underground safety explosion-proof method based on multi-sensor data acquisition - Google Patents

Coal mine underground safety explosion-proof method based on multi-sensor data acquisition Download PDF

Info

Publication number
CN113011434A
CN113011434A CN201911320356.2A CN201911320356A CN113011434A CN 113011434 A CN113011434 A CN 113011434A CN 201911320356 A CN201911320356 A CN 201911320356A CN 113011434 A CN113011434 A CN 113011434A
Authority
CN
China
Prior art keywords
image
coal mine
coal dust
underground
computer
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201911320356.2A
Other languages
Chinese (zh)
Inventor
不公告发明人
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201911320356.2A priority Critical patent/CN113011434A/en
Publication of CN113011434A publication Critical patent/CN113011434A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/30—Noise filtering
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
    • G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

The invention discloses a coal mine underground safety explosion-proof method based on multi-sensor data acquisition, which comprises the following steps: firstly, arranging a plurality of underground coal mine environment monitoring devices which are connected and communicated with a monitoring computer through a CAN bus at intervals on an underground coal mine working surface; secondly, acquiring and transmitting data of multiple sensors; thirdly, after the computer analyzes and processes the received data by adopting a multi-sensor data fusion method, judging whether to carry out safety alarm or not, and giving the alarmThe method for sending the short message by the coal mine underground safety control personnel sends out alarm information when alarming is needed. The invention can simultaneously treat coal dust particles, methane gas, C0 gas and O2Gas and CO2Gas concentration is collected, and through multi-sensor data fusion, the underground safety explosion-proof of many indexs can be realized, the coal mine safety accident that can effectively reduce or even avoid takes place, protection people's the security of the lives and property, excellent in use effect, convenient to popularize and use.

Description

Coal mine underground safety explosion-proof method based on multi-sensor data acquisition
Technical Field
The invention belongs to the technical field of coal mine safety, and particularly relates to a coal mine underground safety explosion-proof method based on multi-sensor data acquisition.
Background
China is a big coal producing country, and coal remains the main energy structure for a long time in the future. However, most of coal mines in China are mined by underground workers, unsafe factors are many, disaster accidents such as gas, coal dust and fire disasters frequently occur, the disaster accidents are serious in harm and many in harm, the production interruption time is long, and roadway engineering or production equipment is damaged. Therefore, how to strengthen the mine disaster prevention and treatment work, how to correctly process the relationship between safety and production, safety and benefit, how to accurately, real-timely and quickly fulfill the coal mine safety monitoring function, and ensure the efficient operation of rescue and relief work and safety rescue, become an important task of coal mine work.
Colliery safety explosion-proof in the pit among the prior art mainly relies on detecting gas concentration or dust concentration and realizes, adopts the individual detection, and the mode of reporting to the police alone does not carry out multisensor data acquisition, and data dispersion, and can only embody single index, and the practicality is relatively poor, and colliery incident still takes place occasionally, has caused very big harm to people's the lives and property.
Disclosure of Invention
The invention aims to solve the technical problem of providing a coal mine underground safety explosion-proof method based on multi-sensor data acquisition aiming at the defects in the prior art, which has the advantages of simple steps, novel and reasonable design, convenient realization and capability of simultaneously carrying out treatment on coal dust particles, methane gas, C0 gas and O2Gas and CO2Gas concentration is collected, and through multi-sensor data fusion, the underground safety explosion-proof of many indexs can be realized, the coal mine safety accident that can effectively reduce or even avoid takes place, protection people's the security of the lives and property, excellent in use effect, convenient to popularize and use.
In order to solve the technical problems, the invention adopts the technical scheme that: a coal mine underground safety explosion-proof method based on multi-sensor data acquisition comprises the following steps:
step one, arranging a plurality of underground coal mine environment monitoring devices which are connected and communicated with a monitoring computer through a CAN bus at intervals on an underground coal mine working face, wherein each underground coal mine environment monitoring device comprisesThe input end of the microprocessor is connected with an infrared camera for shooting dust images in the underground coal mine environment, a methane gas sensor for detecting the concentration of methane gas in the underground coal mine environment in real time, a C0 gas sensor for detecting the concentration of C0 gas in the underground coal mine environment in real time, and a power supply module for supplying power to all power utilization modules in the underground coal mine environment monitoring device, wherein the input end of the microprocessor is connected with the infrared camera for shooting dust images in the underground coal mine environment, the methane gas sensor for detecting the concentration of methane gas in the underground coal mine environment in real time, the C0 gas sensor for detecting2O for real-time detection of gas concentration2Gas sensor and method for measuring CO in coal mine underground environment2CO for real-time detection of gas concentration2The output end of the microprocessor is connected with a liquid crystal display screen;
step two, multi-sensor data acquisition and transmission, the concrete process is:
step 201, shooting a dust image in a coal mine underground environment by an infrared camera and transmitting the shot coal dust infrared image to a microprocessor, detecting the methane gas concentration in the coal mine underground environment in real time by a methane gas sensor and outputting a detected signal to the microprocessor, detecting the C0 gas concentration in the coal mine underground environment in real time by a C0 gas sensor and outputting the detected signal to the microprocessor, and outputting the detected signal to the microprocessor by an O-shaped camera2Gas sensor to O in coal mine underground environment2Detecting gas concentration in real time and outputting the detected signal to microprocessor, CO2Gas sensor 8 for CO in coal mine underground environment2The gas concentration is detected in real time and the detected signal is output to a microprocessor;
step 202, the microprocessor acquires the infrared image of the coal dust, the methane gas concentration, the C0 gas concentration and the O at the same time2Gas concentration and CO2Packing the gas concentration and sending to a computer;
thirdly, after analyzing and processing the received data by the computer by adopting a multi-sensor data fusion method, judging whether to alarm the safety, and sending alarm information when the alarm is needed by sending a short message to a safety control personnel under the coal mine; the specific process of analyzing and processing the received data by the computer by adopting a multi-sensor data fusion method comprises the following steps:
step 301, identifying a coal dust image, which comprises the following specific processes:
step 3011, image enhancement processing, which includes the specific process:
30111, the computer performs image enhancement processing on the coal dust infrared image based on Retinex theory;
30112, the computer performs image enhancement on the coal dust infrared image obtained through the processing in step 201 by using a histogram equalization algorithm;
step 3012, image segmentation processing: the computer adopts a region growing segmentation algorithm to perform image segmentation processing on the coal dust infrared image obtained through the enhancement processing in the second step;
3013, performing coal dust overlapping particle separation to identify coal dust particles, and the specific process is as follows:
30131, the computer performs binarization processing on the coal dust infrared image obtained in 3012 to obtain a binarized image;
30132, the computer extracts feature points of the binarized image obtained by the processing in the 30131 by using an SIFT algorithm, and extracts feature points of an edge curve of the coal dust overlapped particle image;
30133, the computer extracts, by using a module for extracting overlapped particle intersection points, overlapped particle intersection points in the feature points of the edge curve of the coal dust overlapped particle image extracted in 30132;
30134, the computer separates the coal dust overlapped particles by using a drosophila algorithm to identify the coal dust particles;
step 302, multi-sensor data fusion: computer for coal dust particle concentration, methane gas concentration, C0 gas concentration, O2Gas concentration and CO2And inputting the gas concentration into a pre-constructed deep learning network, and outputting a safety level by the deep learning network, wherein the safety level comprises a first safety level which does not need to be alarmed at all, a second level which needs to be early warned and a third level which needs to be alarmed.
In the method for safely preventing explosion in the underground coal mine based on multi-sensor data acquisition, the specific process of the computer for performing image enhancement processing on the infrared image of the coal dust based on the Retinex theory in the step 30111 is as follows:
step 301111, graying the coal dust infrared image, and then decomposing the coal dust infrared image S (x, y) into a reflection object image R (x, y) and an incident light image L (x, y) according to Retinex theory;
step 301112, separating the irradiated light component and the reflected light by logarithm method, and expressing the formula as:
S(x,y)＝log(R(x,y))+log(L(x,y)) (A1)
step 301113, performing convolution on the coal dust infrared image S (x, y) by adopting a Gaussian template to perform low-pass filtering to obtain a low-pass filtered image D (x, y), wherein the low-pass filtered image D (x, y) is expressed by a formula:
D(x,y)＝S(x,y)*F(x,y) (A2)
wherein F (x, y) represents a gaussian filter function;
step 301114 subtracts the low-pass filtered image D (x, y) from the original image R (x, y) in the logarithmic domain to obtain a high-frequency enhanced image G (x, y), which is expressed by the following formula:
G(x,y)＝R(x,y)-log(D(x,y)) (A3)
step 301115, taking the inverse logarithm of the high-frequency enhanced image G (x, y), to obtain an enhanced coal dust infrared image R' (x, y):
R′(x,y)＝exp(G(x,y)) (A4)。
in the above method for coal mine underground safety explosion prevention based on multi-sensor data acquisition, in step 30134, the computer performs coal dust overlapping particle separation by using a drosophila algorithm, and the specific process of identifying coal dust particles is as follows:
4041, randomly extracting 6 feature points between two adjacent intersection points of the overlapping regions, and performing ellipse fitting on the feature points between two adjacent intersection points of the overlapping regions to obtain an expression ax of an ellipse2+bxy+cy2+ dx + ey + h is a set of 6 parameters a, b, c, d, e, h in 0;
4042, initializing a fruit fly population position; the drosophila population position is a set of values of 6 parameters a, b, c, d, e, h in the expression of the ellipse obtained in step 401;
4043, giving the fruit fly individual a sense of smell to search for the random direction and distance of food;
step 4044, calculating the distance D from the origin, and then calculating the taste concentration determination value S;
step 4045, substituting S into the taste concentration determination function;
step 4046, finding the fruit fly with the highest taste concentration in the fruit fly population;
step 4047, recording the concentration value and X, Y coordinate value;
step 4048, determining whether the preset maximum iteration number is reached, and when the preset maximum iteration number is reached, ending the step, determining 6 parameters of the ellipse corresponding to the drosophila colony position determined by the last iteration as an expression ax of the ellipse finally subjected to ellipse fitting2+bxy+cy2+ dx + ey + h-0 with 6 parameters a, b, c, d, e, h; otherwise, returning to execute steps 4043-4048;
at step 301349, ellipses are drawn and the overlapping smut particles are separated by elliptic curves, each elliptic curve having an identified individual smut particle enclosed therein.
In the above method for coal mine underground safety explosion prevention based on multi-sensor data acquisition, in the binarized image in step 30131, the label of the target area is 1, and the label of the background area is 0.
In the method for the coal mine underground safety explosion prevention based on the multi-sensor data acquisition, in the step 30133, the specific process that the computer extracts the overlapped particle intersection point in the characteristic points of the coal dust overlapped particle image edge curve extracted in the step 30132 by calling the overlapped particle intersection point extraction module is as follows:
step 301331, let pc(xc,yc) As a current feature point, pc-1(xc-1,yc-1) For the current feature point pc(xc,yc) The previous feature point of (1), pc+1(xc+1,yc+1) For the current feature point pc(xc,yc) According to the formula:
Figure BDA0002326974020000051
calculating the edge curve of the coal dust overlapped particle image at the characteristic point pc(xc,yc) Curvature of C (p)c)；
Step 301332, according to the formula
Figure BDA0002326974020000052
Solving the current feature point pc(xc,yc) Current feature point pc(xc,yc) Is the previous feature point pc-1(xc-1,yc-1) And the current feature point pc(xc,yc) Is the latter characteristic point pc+1(xc+1,yc+1) The area I of the triangle;
step 301333, determining Condition
Figure BDA0002326974020000053
Whether or not it is true, when the condition is satisfied
Figure BDA0002326974020000054
When the current characteristic point p is established, the current characteristic point p is setc(xc,yc) Judging as the intersection point of the overlapped particles; wherein, ItAn area threshold is selected for the intersection.
In the coal mine underground safety explosion-proof method based on multi-sensor data acquisition, step 301333 is ItIs 0.7.
In the method for the coal mine underground safety explosion prevention based on the multi-sensor data acquisition, the preset maximum iteration time in the step 4048 is 200 times.
Compared with the prior art, the invention has the following advantages:
1. the method has the advantages of simple steps, novel and reasonable design and convenient implementation.
2. The invention can simultaneously treat coal dust particles, methane gas, C0 gas and O2Gas and CO2Gas concentration is collected, and through multi-sensor data fusion, the underground safety explosion prevention of multiple indexes can be realized, coal mine safety accidents can be effectively reduced or even avoided, and the life and property safety of people is protected.
3. When the coal dust image is identified, the characteristic points of the edge curve of the coal dust overlapped particle image are positioned, and then the overlapped particle intersection points in the characteristic points are extracted, so that the edge sensitivity is improved, the noise sensitivity is reduced, the number of points representing the edges of the coal dust particles is reduced through the positioning of the characteristic points, the calculation amount of subsequent intersection point extraction is also reduced, the real intersection points can be found, and the identification precision of the overlapped particles can be improved.
4. When the coal dust image is identified, the fruit fly algorithm is adopted to separate the coal dust overlapped particles, so that the coal dust overlapped particles can be reasonably separated, better robustness is obtained, and better effect can be obtained in binarization processing of the image with lower contrast; the recognition effect is good and stable, the speed is high, and the image compatibility is strong.
5. The invention has strong practicability, can be well applied to underground coal mine safety explosion prevention, has good use effect and is convenient to popularize and use.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a block diagram of the process flow of the present invention.
Detailed Description
As shown in FIG. 1, the coal mine underground safety explosion-proof method based on multi-sensor data acquisition comprises the following steps:
step one, arranging a plurality of underground coal mine environment monitoring devices which are connected with a monitoring computer through a CAN bus and communicate with the monitoring computer at intervals on an underground coal mine working surface, wherein each underground coal mine environment monitoring device comprises a microprocessor and a power supply module which supplies power to each power utilization module in the underground coal mine environment monitoring device, and the power supply modules are connected with the monitoring computer through the CAN bus and are communicated with the monitoring computer through the CAN busThe input end of the microprocessor is connected with an infrared camera for shooting dust images in the underground coal mine environment, a methane gas sensor for detecting the concentration of methane gas in the underground coal mine environment in real time, a C0 gas sensor for detecting the concentration of C0 gas in the underground coal mine environment in real time, and an O sensor for detecting the concentration of O in the underground coal mine environment2O for real-time detection of gas concentration2Gas sensor and method for measuring CO in coal mine underground environment2CO for real-time detection of gas concentration2The output end of the microprocessor is connected with a liquid crystal display screen;
step two, multi-sensor data acquisition and transmission, the concrete process is:
step 201, shooting a dust image in a coal mine underground environment by an infrared camera and transmitting the shot coal dust infrared image to a microprocessor, detecting the methane gas concentration in the coal mine underground environment in real time by a methane gas sensor and outputting a detected signal to the microprocessor, detecting the C0 gas concentration in the coal mine underground environment in real time by a C0 gas sensor and outputting the detected signal to the microprocessor, and outputting the detected signal to the microprocessor by an O-shaped camera2Gas sensor to O in coal mine underground environment2Detecting gas concentration in real time and outputting the detected signal to microprocessor, CO2Gas sensor 8 for CO in coal mine underground environment2The gas concentration is detected in real time and the detected signal is output to a microprocessor;
step 202, the microprocessor acquires the infrared image of the coal dust, the methane gas concentration, the C0 gas concentration and the O at the same time2Gas concentration and CO2Packing the gas concentration and sending to a computer;
thirdly, after analyzing and processing the received data by the computer by adopting a multi-sensor data fusion method, judging whether to alarm the safety, and sending alarm information when the alarm is needed by sending a short message to a safety control personnel under the coal mine; the specific process of analyzing and processing the received data by the computer by adopting a multi-sensor data fusion method comprises the following steps:
step 301, identifying a coal dust image, which comprises the following specific processes:
step 3011, image enhancement processing, which includes the specific process:
30111, the computer performs image enhancement processing on the coal dust infrared image based on Retinex theory;
30112, the computer performs image enhancement on the coal dust infrared image obtained through the processing in step 201 by using a histogram equalization algorithm;
step 3012, image segmentation processing: the computer adopts a region growing segmentation algorithm to perform image segmentation processing on the coal dust infrared image obtained through the enhancement processing in the second step;
3013, performing coal dust overlapping particle separation to identify coal dust particles, and the specific process is as follows:
30131, the computer performs binarization processing on the coal dust infrared image obtained in 3012 to obtain a binarized image;
30132, the computer extracts feature points of the binarized image obtained by the processing in the 30131 by using an SIFT algorithm, and extracts feature points of an edge curve of the coal dust overlapped particle image;
30133, the computer extracts, by using a module for extracting overlapped particle intersection points, overlapped particle intersection points in the feature points of the edge curve of the coal dust overlapped particle image extracted in 30132;
30134, the computer separates the coal dust overlapped particles by using a drosophila algorithm to identify the coal dust particles;
step 302, multi-sensor data fusion: computer for coal dust particle concentration, methane gas concentration, C0 gas concentration, O2Gas concentration and CO2And inputting the gas concentration into a pre-constructed deep learning network, and outputting a safety level by the deep learning network, wherein the safety level comprises a first safety level which does not need to be alarmed at all, a second level which needs to be early warned and a third level which needs to be alarmed.
In the method, the specific process of the computer in step 30111 for performing image enhancement processing on the coal dust infrared image based on the Retinex theory is as follows:
step 301111, graying the coal dust infrared image, and then decomposing the coal dust infrared image S (x, y) into a reflection object image R (x, y) and an incident light image L (x, y) according to Retinex theory;
step 301112, separating the irradiated light component and the reflected light by logarithm method, and expressing the formula as:
S(x,y)＝log(R(x,y))+log(L(x,y)) (A1)
step 301113, performing convolution on the coal dust infrared image S (x, y) by adopting a Gaussian template to perform low-pass filtering to obtain a low-pass filtered image D (x, y), wherein the low-pass filtered image D (x, y) is expressed by a formula:
D(x,y)＝S(x,y)*F(x,y) (A2)
wherein F (x, y) represents a gaussian filter function;
step 301114 subtracts the low-pass filtered image D (x, y) from the original image R (x, y) in the logarithmic domain to obtain a high-frequency enhanced image G (x, y), which is expressed by the following formula:
G(x,y)＝R(x,y)-log(D(x,y)) (A3)
step 301115, taking the inverse logarithm of the high-frequency enhanced image G (x, y), to obtain an enhanced coal dust infrared image R' (x, y):
R′(x,y)＝exp(G(x,y)) (A4)。
in the method, in step 30134, the computer performs coal dust overlapping particle separation by using a drosophila algorithm, and the specific process of identifying the coal dust particles is as follows:
4041, randomly extracting 6 feature points between two adjacent intersection points of the overlapping regions, and performing ellipse fitting on the feature points between two adjacent intersection points of the overlapping regions to obtain an expression ax of an ellipse2+bxy+cy2+ dx + ey + h is a set of 6 parameters a, b, c, d, e, h in 0;
4042, initializing a fruit fly population position; the drosophila population position is a set of values of 6 parameters a, b, c, d, e, h in the expression of the ellipse obtained in step 401;
4043, giving the fruit fly individual a sense of smell to search for the random direction and distance of food;
step 4044, calculating the distance D from the origin, and then calculating the taste concentration determination value S;
step 4045, substituting S into the taste concentration determination function;
step 4046, finding the fruit fly with the highest taste concentration in the fruit fly population;
step 4047, recording the concentration value and X, Y coordinate value;
step 4048, determining whether the preset maximum iteration number is reached, and when the preset maximum iteration number is reached, ending the step, determining 6 parameters of the ellipse corresponding to the drosophila colony position determined by the last iteration as an expression ax of the ellipse finally subjected to ellipse fitting2+bxy+cy2+ dx + ey + h-0 with 6 parameters a, b, c, d, e, h; otherwise, returning to execute steps 4043-4048;
at step 301349, ellipses are drawn and the overlapping smut particles are separated by elliptic curves, each elliptic curve having an identified individual smut particle enclosed therein.
In the present method, in the binarized image in step 30131, the label of the target region is 1, and the label of the background region is 0.
In the method, the specific process that the computer in step 30133 calls the overlapped particle intersection point extraction module to extract the overlapped particle intersection point in the feature points of the coal dust overlapped particle image edge curve extracted in step 30132 is as follows:
step 301331, let pc(xc,yc) As a current feature point, pc-1(xc-1,yc-1) For the current feature point pc(xc,yc) The previous feature point of (1), pc+1(xc+1,yc+1) For the current feature point pc(xc,yc) According to the formula:
Figure BDA0002326974020000101
calculating the edge curve of the coal dust overlapped particle image at the characteristic point pc(xc,yc) Curvature of C (p)c)；
Step 301332, according to the formula
Figure BDA0002326974020000102
Solving the current feature point pc(xc,yc) Current feature point pc(xc,yc) Is the previous feature point pc-1(xc-1,yc-1) And the current feature point pc(xc,yc) Is the latter characteristic point pc+1(xc+1,yc+1) The area I of the triangle;
step 301333, determining Condition
Figure BDA0002326974020000103
Whether or not it is true, when the condition is satisfied
Figure BDA0002326974020000104
When the current characteristic point p is established, the current characteristic point p is setc(xc,yc) Judging as the intersection point of the overlapped particles; wherein, ItAn area threshold is selected for the intersection.
In the method, step 301333 shows thattIs 0.7.
In the method, the preset maximum number of iterations in step 4048 is 200.
In conclusion, the invention can simultaneously treat coal dust particles, methane gas, C0 gas and O2Gas and CO2Gas concentration is collected, and through multi-sensor data fusion, the underground safety explosion-proof of many indexs can be realized, the coal mine safety accident that can effectively reduce or even avoid takes place, protection people's the security of the lives and property, excellent in use effect, convenient to popularize and use.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable one skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.

Claims (7)

1. A coal mine underground safety explosion-proof method based on multi-sensor data acquisition is characterized by comprising the following steps:
the method comprises the following steps that firstly, a plurality of underground coal mine environment monitoring devices which are connected with a monitoring computer through a CAN bus and are communicated with the monitoring computer are arranged on an underground coal mine working face at intervals, each underground coal mine environment monitoring device comprises a microprocessor and a power supply module which supplies power to each power utilization module in the underground coal mine environment monitoring device, the input end of the microprocessor is connected with an infrared camera used for shooting a dust image in the underground coal mine environment, a methane gas sensor used for detecting the concentration of methane gas in the underground coal mine environment in real time, a C0 gas sensor used for detecting the concentration of C0 gas in the underground coal mine environment in real time, and a sensor used for detecting the concentration of O0 gas in the underground coal mine environment2O for real-time detection of gas concentration2Gas sensor and method for measuring CO in coal mine underground environment2CO for real-time detection of gas concentration2The output end of the microprocessor is connected with a liquid crystal display screen;
step two, multi-sensor data acquisition and transmission, the concrete process is:
step 201, shooting a dust image in a coal mine underground environment by an infrared camera and transmitting the shot coal dust infrared image to a microprocessor, detecting the methane gas concentration in the coal mine underground environment in real time by a methane gas sensor and outputting a detected signal to the microprocessor, detecting the C0 gas concentration in the coal mine underground environment in real time by a C0 gas sensor and outputting the detected signal to the microprocessor, and outputting the detected signal to the microprocessor by an O-shaped camera2Gas sensor to O in coal mine underground environment2Detecting gas concentration in real time and outputting the detected signalGiven to a microprocessor, CO2Gas sensor 8 for CO in coal mine underground environment2The gas concentration is detected in real time and the detected signal is output to a microprocessor;
step 202, the microprocessor acquires the infrared image of the coal dust, the methane gas concentration, the C0 gas concentration and the O at the same time2Gas concentration and CO2Packing the gas concentration and sending to a computer;
thirdly, after analyzing and processing the received data by the computer by adopting a multi-sensor data fusion method, judging whether to alarm the safety, and sending alarm information when the alarm is needed by sending a short message to a safety control personnel under the coal mine; the specific process of analyzing and processing the received data by the computer by adopting a multi-sensor data fusion method comprises the following steps:
step 301, identifying a coal dust image, which comprises the following specific processes:
step 3011, image enhancement processing, which includes the specific process:
30111, the computer performs image enhancement processing on the coal dust infrared image based on Retinex theory;
30112, the computer performs image enhancement on the coal dust infrared image obtained through the processing in step 201 by using a histogram equalization algorithm;
step 3012, image segmentation processing: the computer adopts a region growing segmentation algorithm to perform image segmentation processing on the coal dust infrared image obtained through the enhancement processing in the second step;
3013, performing coal dust overlapping particle separation to identify coal dust particles, and the specific process is as follows:
30131, the computer performs binarization processing on the coal dust infrared image obtained in 3012 to obtain a binarized image;
30132, the computer extracts feature points of the binarized image obtained by the processing in the 30131 by using an SIFT algorithm, and extracts feature points of an edge curve of the coal dust overlapped particle image;
30133, the computer extracts, by using a module for extracting overlapped particle intersection points, overlapped particle intersection points in the feature points of the edge curve of the coal dust overlapped particle image extracted in 30132;
30134, the computer separates the coal dust overlapped particles by using a drosophila algorithm to identify the coal dust particles;
step 302, multi-sensor data fusion: computer for coal dust particle concentration, methane gas concentration, C0 gas concentration, O2Gas concentration and CO2And inputting the gas concentration into a pre-constructed deep learning network, and outputting a safety level by the deep learning network, wherein the safety level comprises a first safety level which does not need to be alarmed at all, a second level which needs to be early warned and a third level which needs to be alarmed.
2. The underground coal mine safety explosion-proof method based on multi-sensor data acquisition as claimed in claim 1, wherein: in step 30111, the specific process of the computer performing image enhancement processing on the coal dust infrared image based on the Retinex theory is as follows:
step 301111, graying the coal dust infrared image, and then decomposing the coal dust infrared image S (x, y) into a reflection object image R (x, y) and an incident light image L (x, y) according to Retinex theory;
step 301112, separating the irradiated light component and the reflected light by logarithm method, and expressing the formula as:
S(x,y)＝log(R(x,y))+log(L(x,y)) (A1)
step 301113, performing convolution on the coal dust infrared image S (x, y) by adopting a Gaussian template to perform low-pass filtering to obtain a low-pass filtered image D (x, y), wherein the low-pass filtered image D (x, y) is expressed by a formula:
D(x,y)＝S(x,y)*F(x,y) (A2)
wherein F (x, y) represents a gaussian filter function;
step 301114 subtracts the low-pass filtered image D (x, y) from the original image R (x, y) in the logarithmic domain to obtain a high-frequency enhanced image G (x, y), which is expressed by the following formula:
G(x,y)＝R(x,y)-log(D(x,y)) (A3)
step 301115, taking the inverse logarithm of the high-frequency enhanced image G (x, y), to obtain an enhanced coal dust infrared image R' (x, y):
R′(x,y)＝exp(G(x,y)) (A4)。
3. the underground coal mine safety explosion-proof method based on multi-sensor data acquisition as claimed in claim 1, wherein: in step 30134, the computer performs coal dust overlapping particle separation by using a drosophila algorithm, and the specific process of identifying the coal dust particles is as follows:
4041, randomly extracting 6 feature points between two adjacent intersection points of the overlapping regions, and performing ellipse fitting on the feature points between two adjacent intersection points of the overlapping regions to obtain an expression ax of an ellipse2+bxy+cy2+ dx + ey + h is a set of 6 parameters a, b, c, d, e, h in 0;
4042, initializing a fruit fly population position; the drosophila population position is a set of values of 6 parameters a, b, c, d, e, h in the expression of the ellipse obtained in step 401;
4043, giving the fruit fly individual a sense of smell to search for the random direction and distance of food;
step 4044, calculating the distance D from the origin, and then calculating the taste concentration determination value S;
step 4045, substituting S into the taste concentration determination function;
step 4046, finding the fruit fly with the highest taste concentration in the fruit fly population;
step 4047, recording the concentration value and X, Y coordinate value;
step 4048, determining whether the preset maximum iteration number is reached, and when the preset maximum iteration number is reached, ending the step, determining 6 parameters of the ellipse corresponding to the drosophila colony position determined by the last iteration as an expression ax of the ellipse finally subjected to ellipse fitting2+bxy+cy2+ dx + ey + h-0 with 6 parameters a, b, c, d, e, h; otherwise, returning to execute steps 4043-4048;
at step 301349, ellipses are drawn and the overlapping smut particles are separated by elliptic curves, each elliptic curve having an identified individual smut particle enclosed therein.
4. The underground coal mine safety explosion-proof method based on multi-sensor data acquisition as claimed in claim 1, wherein: in the binarized image in step 30131, the label of the target area is 1, and the label of the background area is 0.
5. The underground coal mine safety explosion-proof method based on multi-sensor data acquisition as claimed in claim 1, wherein: in step 30133, the specific process of the computer using the overlap particle intersection point extraction module to extract the overlap particle intersection point in the feature points of the coal dust overlap particle image edge curve extracted in step 30132 is as follows:
step 301331, let pc(xc,yc) As a current feature point, pc-1(xc-1,yc-1) For the current feature point pc(xc,yc) The previous feature point of (1), pc+1(xc+1,yc+1) For the current feature point pc(xc,yc) According to the formula:
Figure FDA0002326974010000041
calculating the edge curve of the coal dust overlapped particle image at the characteristic point pc(xc,yc) Curvature of C (p)c)；
Step 301332, according to the formula
Figure FDA0002326974010000042
Solving the current feature point pc(xc,yc) Current feature point pc(xc,yc) Is the previous feature point pc-1(xc-1,yc-1) And the current feature point pc(xc,yc) Is the latter characteristic point pc+1(xc+1,yc+1) The area I of the triangle;
step 301333, determining Condition
Figure FDA0002326974010000043
Whether or not it is true, when the condition is satisfied
Figure FDA0002326974010000044
When the current characteristic point p is established, the current characteristic point p is setc(xc,yc) Judging as the intersection point of the overlapped particles; wherein, ItAn area threshold is selected for the intersection.
6. The underground coal mine safety explosion-proof method based on multi-sensor data acquisition as claimed in claim 5, wherein: i in step 301333tIs 0.7.
7. The underground coal mine safety explosion-proof method based on multi-sensor data acquisition as claimed in claim 5, wherein: the preset maximum number of iterations in step 4048 is 200.
CN201911320356.2A 2019-12-19 2019-12-19 Coal mine underground safety explosion-proof method based on multi-sensor data acquisition Pending CN113011434A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911320356.2A CN113011434A (en) 2019-12-19 2019-12-19 Coal mine underground safety explosion-proof method based on multi-sensor data acquisition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911320356.2A CN113011434A (en) 2019-12-19 2019-12-19 Coal mine underground safety explosion-proof method based on multi-sensor data acquisition

Publications (1)

Publication Number Publication Date
CN113011434A true CN113011434A (en) 2021-06-22

Family

ID=76382293

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911320356.2A Pending CN113011434A (en) 2019-12-19 2019-12-19 Coal mine underground safety explosion-proof method based on multi-sensor data acquisition

Country Status (1)

Country Link
CN (1) CN113011434A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114577691A (en) * 2022-03-15 2022-06-03 中科海慧（北京）科技有限公司 Coal mine dust monitoring and simulation verification method
CN116050938A (en) * 2023-03-07 2023-05-02 济宁矿业集团有限公司霄云煤矿 Coal mine transportation safety supervision system based on data analysis

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114577691A (en) * 2022-03-15 2022-06-03 中科海慧（北京）科技有限公司 Coal mine dust monitoring and simulation verification method
CN116050938A (en) * 2023-03-07 2023-05-02 济宁矿业集团有限公司霄云煤矿 Coal mine transportation safety supervision system based on data analysis

Similar Documents

Publication Publication Date Title
CN109145742B (en) Pedestrian identification method and system
CN107176432A (en) A kind of anchor pole foreign matter and belt tearing detecting system based on machine vision
CN113012179A (en) Coal dust image identification method for coal mine underground explosion-proof detection
CN113011434A (en) Coal mine underground safety explosion-proof method based on multi-sensor data acquisition
CN105095829A (en) Face recognition method and system
CN109684976B (en) Door state monitoring method, device, equipment and system and storage medium
CN104077594A (en) Image recognition method and device
CN116642810A (en) Dust monitoring method and system based on Internet of things
CN106781195A (en) A kind of coal-mine fire smoke detection system
CN109873990A (en) A kind of illegal mining method for early warning in mine based on computer vision
CN104376322A (en) Intelligent detecting and evaluating method for container number preprocessing quality of containers
CN103577808A (en) Frogman recognition method
CN105512633A (en) Power system dangerous object identification method and apparatus
CN116682162A (en) Robot detection algorithm based on real-time video stream
CN111126192A (en) Underground coal mine object state recognition system based on deep learning
CN105973903A (en) System and method for detecting oral solution bottle caps
CN113011229A (en) Coal dust explosion early warning method for coal preparation plant based on visual information
CN109800686A (en) A kind of driver's smoking detection method based on active infrared image
CN202404694U (en) Adaptive disturbance signal identification module of distributing type optical fiber sensing application system
CN105718881B (en) The zero illumination environment monitoring smoke dust method based on infrared video gray level image
CN110210447B (en) Method and device for detecting moving target in underground dangerous area
Varshney et al. A deep learning based approach to detect suspicious weapons
CN112560658A (en) Early warning method and device, electronic equipment and computer readable storage medium
Ergasheva et al. Advancing Maritime Safety: Early Detection of Ship Fires through Computer Vision, Deep Learning Approaches, and Histogram Equalization Techniques
CN110399783A (en) Traffic action triggers platform, method and storage medium based on image analysis

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20210622