CN109918754B - Safety detection and early warning method and system for layered indexes of tailing pond - Google Patents
Safety detection and early warning method and system for layered indexes of tailing pond Download PDFInfo
- Publication number
- CN109918754B CN109918754B CN201910144179.0A CN201910144179A CN109918754B CN 109918754 B CN109918754 B CN 109918754B CN 201910144179 A CN201910144179 A CN 201910144179A CN 109918754 B CN109918754 B CN 109918754B
- Authority
- CN
- China
- Prior art keywords
- module
- tailing pond
- data
- monitoring
- early warning
- 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.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Alarm Systems (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to the technical field of tailing pond safety detection, and discloses a tailing pond layered index safety detection and early warning method and system, wherein the tailing pond layered index safety detection and early warning system based on big data analysis comprises: the dam crack monitoring system comprises a video monitoring module, a seepage line monitoring module, a dam crack monitoring module, a scale measuring module, a main control module, a big data processing module, a safety evaluation module, an early warning module, an emergency module and a display module. The scale of the tailing pond can be rapidly and effectively calculated through the scale measuring module, and the cost is low; meanwhile, the emergency module judges according to the grade of the alarm event, retrieves the alarm event in the plan, calls or generates a new emergency plan after matching, and applies the new emergency plan to emergency aid decision-making; and the information in the case base is reasonably utilized, and the accuracy of event judgment and processing is further improved.
Description
Technical Field
The invention belongs to the technical field of safety detection of tailing ponds, and particularly relates to a method and a system for safety detection and early warning of layered indexes of a tailing pond.
Background
The tailing pond is a place which is formed by building a dam to intercept a valley opening or enclosing the ground and is used for piling metal or nonmetal mines and discharging tailings or other industrial waste residues after ore sorting. The tailings pond is an artificial debris flow danger source with high potential energy, dam break danger exists, and major accidents are easily caused once the tailings pond is lost. The red mud storehouse formed by smelting waste residue, the waste residue storehouse formed by power generation waste residue should be managed according to the tailings storehouse. The tailings refer to ores mined from metal or nonmetal mines, and are discharged after valuable concentrate is selected by a concentrating mill. The tailings contain useful or harmful components which cannot be treated temporarily due to large quantity, and are discharged randomly, so that resource loss can be caused, farmlands or riverways are covered in a large area, and the environment is polluted. The tailings generated by the concentrating mill are not only large in quantity and fine in particle, but also contain various medicaments, and if the tailings are not treated, the environment around the concentrating mill is polluted seriously. The tailings are properly stored in a tailing pond, and the tailing water is clarified in the pond and then recycled, so that the environment can be effectively protected. However, the scale calculation speed of the existing tailing pond is slow, and meanwhile, when the monitoring tailing pond is abnormal, a response decision cannot be made quickly in time.
In summary, the problems of the prior art are:
the scale calculation speed of the existing tailing pond is low, and meanwhile, when the monitoring tailing pond is abnormal, a response decision cannot be made quickly in time.
In the prior art, the camera has poor focusing degree, cannot clearly shoot and record the site of the tailing pond, and is not beneficial to obtaining clear and accurate site video information of the tailing pond; in the prior art, dam body crack data cannot be accurately and rapidly monitored, and the smooth development of related work of a tailing pond is not facilitated; the alarm in the prior art has insufficient monitoring sensitivity on dangerous data, and cannot judge the accuracy of an alarm signal and delay alarm.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and a system for safely detecting and early warning the layering indexes of a tailing pond.
The invention is realized in this way, a method for safely detecting and early warning the hierarchical index of a tailing pond, which comprises the following steps:
firstly, shooting and recording the site of a tailing pond by a camera by adopting a cross gray image definition algorithm to obtain the site video information of the monitored tailing pond; monitoring tailing pond soaking line data by using a soaking line sensor;
secondly, monitoring dam crack data by using dam crack monitoring equipment through an optimal consistent approximation method; acquiring data of the total area, the total dam height and the total storage capacity of the tailing pond through a measurer;
thirdly, processing and analyzing the monitored data by using a cloud server to centralize large data resources;
fourthly, evaluating the safety of the tailing pond by utilizing evaluation software according to the monitoring data indexes;
monitoring data by using an alarm and adopting a PSO-BP algorithm, timely alarming when dangerous data is monitored, and selecting an optimal solution to deal with the dangerous state of the tailing pond through a pre-arranged database;
and sixthly, displaying the monitored site video, the saturation line, the water level, the crack and the safety evaluation data information of the tailings pond by using a display.
Further, the first step of using the camera to adopt the cross gray level image definition algorithm specifically comprises the following steps:
in the cross-hair gray image area, the maximum gray value B of the white pixelmax255, minimum grayscale value of black pixel BminThe maximum dynamic range of the pixel gray scale in the image is 0-255, and the gray scale median is (B)max-Bmin) 255/2-127.5; after normalization, the definition formulas of different gray values (255-:
the sharpness formula for the different gray values (0-127) of the black pixels is expressed as:
the sharpness algorithm for any gray value can be expressed as:
the cross-hair gray image area is composed of m X n pixels, and a pixel gray value matrix B (I, J), wherein I is more than or equal to 0 and less than or equal to m-1, J is more than or equal to 0 and less than or equal to n-1, and B (I, J) matrix represents:
then the sharpness of the reticle gray scale image area may represent:
further, in the second step, dam crack data is monitored by using dam crack monitoring equipment and adopting an optimal consistent approximation method, and the specific algorithm is as follows:
let f (x) be C [ a, b ]],pn(x) Is a set of polynomials of degree not exceeding n; if it is not
Then p x (x) is the best consistent approximation polynomial of f (x) over [ a, b ], also called the minimax polynomial;
solving an optimal polynomial by adopting a Rimidz algorithm; solving according to Chebyshev's theorem
Wherein: ak (k is 0,1, … n) is the polynomial coefficient to be solved; rho is the optimal approximation value; x is a radical of a fluorine atomiObtained by iterative correction.
Further, in the fifth step, the alarm is used for monitoring data by adopting a PSO-BP algorithm, so that the alarm can give an alarm to abnormal monitored data in time, and the specific steps are as follows:
(1) initialization: setting relevant parameters of a PSO-BP neural network; determining the number of layers of the neural network, the number of neurons in each layer and the dimension of particles to be optimized; wherein the total number of weight threshold values to be optimized by the PSO algorithm is as follows:
N＝(m+1)×n+(n+1)×t，
m is the number of input neurons, n is the number of hidden layer neurons, t is the number of output layer neurons, and the speed and the position of the particle are initialized randomly;
(2) calculating the fitness: calculating the sum of the absolute values of the errors of the network output and the expected sample output according to a fitness function;
(3) finding individual extrema and group extrema: comparing the fitness function value of each particle with the individual extreme value, and if the fitness function value is smaller, the fitness function value becomes a new individual extreme value; comparing the new individual extremum with the global optimal fitness value, and if the new individual extremum is smaller than the global optimal fitness value, taking the new individual extremum as the current group extremum;
(4) updating the position and velocity of the particles according to an ion packet algorithm;
in the formula: w is the inertial weight; k is the current iteration number; i is the velocity of the particle; d is the position of the particle; c. C1And c2C is selected by verification for learning factor, also called acceleration factor1＝c2Calculating as 2; and is between [0, 1 ]]A uniform random number in between;
(5) whether the global optimal fitness value is smaller than a set error or the iteration times are larger than the maximum iteration times is judged, and if the global optimal fitness value is not smaller than the set error or the iteration times are not larger than the maximum iteration times, the step (3) is returned; if the conditions are met, the output global optimal particle position is the optimal weight threshold of the BP neural network.
Another object of the present invention is to provide a tailing pond hierarchical index safety detection and early warning system based on big data analysis, which implements the tailing pond hierarchical index safety detection and early warning method, the tailing pond hierarchical index safety detection and early warning system based on big data analysis comprising:
the video monitoring module is connected with the main control module and is used for monitoring the field video information of the tailing pond through the camera;
the saturation line monitoring module is connected with the main control module and used for monitoring the data of the saturation line of the tailing pond through the saturation line sensor;
the dam body crack monitoring module is connected with the main control module and used for monitoring dam body crack data through dam body crack monitoring equipment;
the scale measuring module is connected with the main control module and is used for acquiring the data of the total area, the total dam height and the total reservoir capacity of the tailing reservoir through the measurer;
the main control module is connected with the video monitoring module, the saturation line monitoring module, the dam crack monitoring module, the scale measuring module, the big data processing module, the safety evaluation module, the early warning module, the emergency module and the display module and is used for controlling each module to normally work through the single chip microcomputer;
the big data processing module is connected with the main control module and used for processing and analyzing the monitored data by centralizing big data resources through the cloud server;
the safety evaluation module is connected with the main control module and used for evaluating the safety of the tailing pond according to the monitoring data indexes through evaluation software;
the early warning module is connected with the main control module and used for giving an alarm in time according to the monitored dangerous data through the alarm;
the emergency module is connected with the main control module and used for selecting an optimal solution to deal with the dangerous state of the tailing pond through the plan pond;
and the display module is connected with the main control module and used for displaying the monitored field videos, the saturation lines, the water levels, the cracks and the safety assessment data information of the tailing pond through the display.
The invention also aims to provide a tailing pond safety detection platform applying the tailing pond layered index safety detection and early warning method.
The invention has the advantages and positive effects that: the scale of the tailing pond can be rapidly and effectively calculated through the scale measuring module, and the cost is low; meanwhile, the emergency module judges according to the grade of the alarm event, retrieves the alarm event in the plan, calls or generates a new emergency plan after matching, and applies the new emergency plan to emergency aid decision-making; information in the case base is reasonably utilized to carry out auxiliary decision-making on abnormity and accident treatment of the tailing base, so that safe operation of the tailing base is guaranteed, and disaster loss of the tailing base is reduced to the maximum extent; the expanded Boolean model obtains the similarity of attributes in the emergency event, and the calculation is convenient and the accuracy is high; the attributes of the emergency events are described and measured by event names, types, positions, levels, influence degrees and specific descriptions, so that the accuracy of event retrieval and adaptation is improved; the method for generating the case by inference is simple and easy to operate, and the accuracy of judging and processing the event is further improved.
According to the invention, the camera adopts a cross gray image definition algorithm, so that the focusing power of the camera is effectively improved, the field shooting and recording definition of the tailings pond is improved, and clear and accurate field video information of the tailings pond is obtained; the dam crack monitoring equipment is used for monitoring the dam crack data by adopting an optimal consistent approximation method, so that the dam crack data can be accurately and quickly monitored, and the smooth development of related work of a tailing pond is ensured; the data are monitored by the alarm by adopting a PSO-BP algorithm, so that the monitoring sensitivity of dangerous data is effectively improved, the accuracy of judging alarm signals is improved, and the alarm can timely alarm abnormal data to be monitored.
Drawings
Fig. 1 is a flow chart of a method for detecting and warning safety of hierarchical indexes of a tailing pond according to an embodiment of the invention.
Fig. 2 is a structural block diagram of a tailing pond hierarchical index safety detection and early warning system based on big data analysis according to an embodiment of the present invention.
In fig. 2: 1. a video monitoring module; 2. a saturation line monitoring module; 3. a dam crack monitoring module; 4. a scale measurement module; 5. a main control module; 6. a big data processing module; 7. a security evaluation module; 8. an early warning module; 9. an emergency module; 10. and a display module.
Detailed Description
In order to further understand the contents, features and effects of the present invention, the following embodiments are illustrated and described in detail with reference to the accompanying drawings.
The structure of the present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the method for safely detecting and early warning the hierarchical indexes of the tailings pond provided by the invention comprises the following steps:
s101, shooting and recording the site of the tailing pond by using a camera through a cross gray image definition algorithm to obtain the site video information of the monitored tailing pond; monitoring tailing pond soaking line data by using a soaking line sensor;
s102, monitoring dam crack data by using dam crack monitoring equipment and adopting an optimal consistent approximation method; acquiring data of the total area, the total dam height and the total storage capacity of the tailing pond through a measurer;
s103, processing and analyzing the monitored data by utilizing the cloud server to centralize large data resources;
s104, evaluating the safety of the tailing pond by utilizing evaluation software according to the monitoring data indexes;
s105, monitoring data by using an alarm and adopting a PSO-BP algorithm, timely alarming when dangerous data is monitored, and selecting an optimal solution to deal with a dangerous state of the tailing pond through a pre-arranged database;
and S106, displaying the monitored site video, the saturation line, the water level, the crack and the safety evaluation data information of the tailing pond by using a display.
In step S101, the embodiment of the present invention provides a method for effectively improving the focusing power of a camera by using a cross gray image definition algorithm in the camera, improving the definition of on-site recording of a tailings pond, and facilitating to obtain clear and accurate on-site video information of the tailings pond, including the specific steps of:
in the cross-hair gray image area, the maximum gray value B of the white pixelmax255, minimum grayscale value of black pixel BminThe maximum dynamic range of the pixel gray scale in the image is 0-255, and the gray scale median is (B)max-Bmin) 255/2-127.5; after normalization, the definition formulas of different gray values (255-:
the sharpness formula for the different gray values (0-127) of the black pixels is expressed as:
the sharpness algorithm for any gray value can be expressed as:
the cross-hair gray image area is composed of m X n pixels, and a pixel gray value matrix B (I, J), wherein I is more than or equal to 0 and less than or equal to m-1, J is more than or equal to 0 and less than or equal to n-1, and B (I, J) matrix represents:
then the sharpness of the reticle gray scale image area may represent:
in step S102, the dam crack monitoring device provided in the embodiment of the present invention monitors the dam crack data by using the optimal consistent approximation method, which is beneficial to accurately and rapidly monitoring the dam crack data and ensuring smooth development of related work of the tailing pond, and the specific algorithm is as follows:
let f (x) be C [ a, b ]],pn(x) Is a set of polynomials of degree not exceeding n; if it is not
Then p x (x) is the best consistent approximation polynomial of f (x) over [ a, b ], also called the minimax polynomial;
solving an optimal polynomial by adopting a Rimidz algorithm; solving according to Chebyshev's theorem
Wherein: ak (k is 0,1, … n) is the polynomial coefficient to be solved; rho is the optimal approximation value; x is the number ofiObtained by iterative correction.
In step S105, the alarm provided in the embodiment of the present invention uses a PSO-BP algorithm to monitor data, so as to effectively improve the sensitivity of monitoring dangerous data and improve the accuracy of determining an alarm signal, so that the alarm can timely alarm abnormal data being monitored, and the specific steps are as follows:
(1) initialization: setting relevant parameters of a PSO-BP neural network; determining the number of layers of the neural network, the number of neurons in each layer and the dimension of particles to be optimized; wherein the total number of weight threshold values to be optimized by the PSO algorithm is as follows:
N＝(m+1)×n+(n+1)×t，
m is the number of input neurons, n is the number of hidden layer neurons, t is the number of output layer neurons, and the speed and the position of the particle are initialized randomly;
(2) calculating the fitness: calculating the sum of the absolute value of the error between the network output and the expected output of the sample according to a fitness function;
(3) finding individual extrema and group extrema: comparing the fitness function value of each particle with the individual extreme value, and if the fitness function value is smaller, the fitness function value becomes a new individual extreme value; comparing the new individual extremum with the global optimal fitness value, and if the new individual extremum is smaller than the global optimal fitness value, taking the new individual extremum as the current group extremum;
(4) updating the position and velocity of the particles according to an ion packet algorithm;
in the formula: w is the inertial weight; k is the current iteration number; i is the velocity of the particle; d is the position of the particle; c. C1And c2For learning factors, also called acceleration factors, by verifying c1＝c2Calculating as 2; and is between [0, 1]A uniform random number therebetween;
(5) whether the global optimal fitness value is smaller than a set error or the iteration times are larger than the maximum iteration times is judged, and if the global optimal fitness value is not smaller than the set error or the iteration times are not larger than the maximum iteration times, the step (3) is returned; if the conditions are met, the output global optimal particle position is the optimal weight threshold of the BP neural network.
As shown in fig. 2, the system for detecting and warning safety of hierarchical indexes of a tailing pond based on big data analysis provided by the embodiment of the present invention includes: the dam crack monitoring system comprises a video monitoring module 1, a seepage line monitoring module 2, a dam crack monitoring module 3, a scale measuring module 4, a main control module 5, a big data processing module 6, a safety evaluation module 7, an early warning module 8, an emergency module 9 and a display module 10.
The video monitoring module 1 is connected with the main control module 5 and is used for monitoring the field video information of the tailing pond through a camera;
the saturation line monitoring module 2 is connected with the main control module 5 and is used for monitoring the data of the saturation lines of the tailing pond through a saturation line sensor;
the dam crack monitoring module 3 is connected with the main control module 5 and used for monitoring dam crack data through dam crack monitoring equipment;
the scale measuring module 4 is connected with the main control module 5 and is used for acquiring the data of the total area, the total dam height and the total reservoir capacity of the tailing reservoir through a measurer;
the main control module 5 is connected with the video monitoring module 1, the seepage line monitoring module 2, the dam crack monitoring module 3, the scale measuring module 4, the big data processing module 6, the safety evaluation module 7, the early warning module 8, the emergency module 9 and the display module 10 and is used for controlling each module to normally work through a single chip microcomputer;
the big data processing module 6 is connected with the main control module 5 and used for processing and analyzing the monitored data by the cloud server centralized big data resources;
the safety evaluation module 7 is connected with the main control module 5 and used for evaluating the safety of the tailing pond according to the monitoring data indexes through evaluation software;
the early warning module 8 is connected with the main control module 5 and used for giving an alarm in time according to the monitored dangerous data through an alarm;
the emergency module 9 is connected with the main control module 5 and is used for selecting an optimal solution to deal with the dangerous state of the tailing pond through a plan pond;
and the display module 10 is connected with the main control module 5 and used for displaying the monitored field videos, the saturation lines, the water levels, the cracks and the safety assessment data information of the tailing pond through a display.
The scale measuring module 4 provided by the invention comprises the following steps:
(1) obtaining high-resolution remote sensing data of a tailing pond to be subjected to scale information extraction and original topographic data before the tailing pond is built;
(2) registering the high-resolution remote sensing data with the original terrain data;
(3) carrying out remote sensing identification on the plane features related to the scale of the tailing pond based on the high-resolution remote sensing data to obtain the plane features related to the tailing pond, wherein the plane features related to the tailing pond comprise the overall boundary range of the tailing pond, the boundary range of each level of dam body and key edge points of each level of dam body and the peripheral terrain;
(4) performing terrain analysis such as terrain profile and the like on the plane features related to the tailing pond by using the original terrain data to acquire elevation information of the key edge points in the longitudinal direction, and reconstructing a three-dimensional space structure constructed by the tailing pond by using the elevation information of the key edge points in the longitudinal direction;
(5) and calculating the total area, the total dam height and the total reservoir capacity of the tailings reservoir according to the hierarchical three-dimensional space structure of each level of dam body of the tailings reservoir based on the reconstructed three-dimensional space structure.
The emergency module 9 provided by the invention has the following emergency method:
1) acquiring a tailing pond case data set through a network, and establishing a case database;
2) inputting an emergency event;
3) analyzing and identifying the emergency event input in the step 2) and acquiring a description or measurement method of each attribute of the emergency event; if the emergency event is the same as the case in the case database, directly calling a plan scheme for auxiliary decision support; if the emergency event is different from the case in the case database, performing the next step;
4) calculating the respective similarity of each attribute in the emergency event;
5) calculating the total similarity of the emergency events and judging, wherein the judgment is as follows: comparing the total similarity of the emergency events with a set threshold, and if the total similarity of the emergency events is greater than or equal to the set threshold, directly calling a plan method for auxiliary decision support; if the total similarity of the emergency events is smaller than a set threshold value, reasoning based on a predetermined plan, wherein the specific method for reasoning based on the predetermined plan comprises the following steps: the calculated similarity of each attribute of the emergency event is sequenced, the case method with the maximum similarity of the attributes is used as an adaptive case method, and finally the case adaptation is achieved through local substitution and parameter adjustment.
The attributes of the emergency event provided by the invention comprise the name, type, position, level, influence degree, event reason, time and place of the event.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications, equivalent changes and modifications made to the above embodiment according to the technical spirit of the present invention are within the scope of the technical solution of the present invention.
Claims (4)
1. A safety detection and early warning method for layered indexes of a tailing pond is characterized by comprising the following steps:
firstly, shooting and recording a tailing pond on site by using a camera through a cross gray image definition algorithm to obtain the on-site video information of a monitored tailing pond; monitoring tailing pond soaking line data by using a soaking line sensor;
secondly, monitoring dam crack data by using dam crack monitoring equipment by adopting an optimal consistent approximation method; acquiring data of the total area, the total dam height and the total storage capacity of the tailing pond through a measurer;
the specific algorithm is as follows:
let f (x) epsilon C [ a, b)],pn(x) Is a set of polynomials of degree not exceeding n; if it is used
Then p x (x) is the best consistent approximation polynomial of f (x) over [ a, b ], also called the minimax polynomial;
wherein p (x) is a set composed of all polynomials, i is the degree, and n is a positive integer;
solving an optimal polynomial by adopting a Rimidz algorithm; solving according to Chebyshev's theorem
Wherein: ak is a polynomial coefficient to be solved, k is 0,1, … n; rho is the optimal approximation value; x is the number ofiObtaining by repeated correction method;
thirdly, processing and analyzing the monitored data by utilizing the cloud server to centralize large data resources;
fourthly, evaluating the safety of the tailing pond by utilizing evaluation software according to the monitoring data indexes;
monitoring data by using an alarm and adopting a PSO-BP algorithm, timely alarming when dangerous data is monitored, and selecting an optimal solution to deal with the dangerous state of the tailing pond through a pre-arranged database;
the method comprises the following specific steps:
(1) initialization: setting relevant parameters of a PSO-BP neural network; determining the number of layers of the neural network, the number of neurons in each layer and the dimension of particles to be optimized; wherein the total number of weight threshold values to be optimized by the PSO algorithm is as follows:
N＝(m+1)×n+(n+1)×t，
m is the number of input neurons, n is the number of hidden layer neurons, t is the number of output layer neurons, and the speed and the position of the particle are initialized randomly;
(2) calculating the fitness: calculating the sum of the absolute values of the errors of the network output and the expected sample output according to a fitness function;
(3) finding individual extrema and group extrema: comparing the fitness function value of each particle with an individual extreme value, and if the fitness function value is smaller, the fitness function value becomes a new individual extreme value; comparing the new individual extremum with the global optimal fitness value, and if the new individual extremum is smaller than the global optimal fitness value, taking the new individual extremum as the current group extremum;
(4) updating the position and velocity of the particles according to an ion packet algorithm;
in the formula: w is the inertial weight; k is the current iteration number; i is the velocity of the particle; d is the position of the particle; c. C1And c2Is a reason for studySub, also called acceleration factor, by verifying c1＝c2Calculating as 2; and is between [0, 1]A uniform random number in between; r is1And r2Air mass coefficients for the first day and the second day, respectively;
is the position of the particles and is,
is the particle velocity;
the number of the extreme values of the group is,
the value of the fitness function is used as the fitness function value,
is an individual extremum;
(5) whether the global optimal fitness value is smaller than a set error or the iteration times are larger than the maximum iteration times is judged, and if the global optimal fitness value is not smaller than the set error or the iteration times are not larger than the maximum iteration times, the step (3) is returned; if the conditions are met, the output global optimal particle position is the optimal BP neural network weight threshold;
and sixthly, displaying the monitored site video, the saturation line, the water level, the crack and the safety evaluation data information of the tailing pond by using a display.
2. The tailing pond layered index safety detection and early warning method of claim 1, wherein the first step of using a camera to adopt a cross gray image definition algorithm comprises the specific steps of:
in the cross-hair gray image area, the maximum gray value B of the white pixelmax255, minimum grayscale value of black pixel BminThe maximum dynamic range of the pixel gray scale in the image is 0-255, and the gray scale median is (B)max-Bmin) 255/2-127.5; normalizationAfter processing, the different gray values of the white pixels 255-128 definition formula is expressed as:
wherein, B is a pixel gray value matrix;
the definition formula of the black pixels with different gray values of 0-127 is expressed as follows:
the sharpness algorithm for any gray value can be expressed as:
the cross-hair gray image area is formed by m X n pixels, and a pixel gray value matrix B (I, J), wherein I is more than or equal to 0 and less than or equal to m-1, J is more than or equal to 0 and less than or equal to n-1, and B (I, J) matrix represents:
then the sharpness of the reticle gray scale image area may represent:
3. a tailing pond layered index safety detection and early warning system based on big data analysis for realizing the tailing pond layered index safety detection and early warning method of claim 1, wherein the tailing pond layered index safety detection and early warning system based on big data analysis comprises:
the video monitoring module is connected with the main control module and is used for monitoring the field video information of the tailing pond through the camera;
the saturation line monitoring module is connected with the main control module and used for monitoring the data of the saturation line of the tailing pond through the saturation line sensor;
the dam crack monitoring module is connected with the main control module and used for monitoring dam crack data through dam crack monitoring equipment;
the scale measuring module is connected with the main control module and is used for acquiring the data of the total area, the total dam height and the total reservoir capacity of the tailing reservoir through the measurer;
the main control module is connected with the video monitoring module, the saturation line monitoring module, the dam crack monitoring module, the scale measuring module, the big data processing module, the safety evaluation module, the early warning module, the emergency module and the display module and is used for controlling each module to normally work through the single chip microcomputer;
the big data processing module is connected with the main control module and used for processing and analyzing the monitored data by centralizing big data resources through the cloud server;
the safety evaluation module is connected with the main control module and used for evaluating the safety of the tailing pond according to the monitoring data indexes through evaluation software;
the early warning module is connected with the main control module and used for giving an alarm in time according to the monitored dangerous data through the alarm;
the emergency module is connected with the main control module and used for selecting an optimal solution to deal with the dangerous state of the tailing pond through the plan pond;
and the display module is connected with the main control module and used for displaying the monitored field videos, the saturation lines, the water level, the cracks and the safety assessment data information of the tailing pond through the display.
4. A safety detection platform of a tailings pond, which applies the safety detection and early warning method for the layering indexes of the tailings pond as claimed in any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910144179.0A CN109918754B (en) | 2019-02-27 | 2019-02-27 | Safety detection and early warning method and system for layered indexes of tailing pond |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910144179.0A CN109918754B (en) | 2019-02-27 | 2019-02-27 | Safety detection and early warning method and system for layered indexes of tailing pond |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109918754A CN109918754A (en) | 2019-06-21 |
| CN109918754B true CN109918754B (en) | 2022-06-03 |
Family
ID=66962501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910144179.0A Active CN109918754B (en) | 2019-02-27 | 2019-02-27 | Safety detection and early warning method and system for layered indexes of tailing pond |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109918754B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110285856A (en) * | 2019-07-10 | 2019-09-27 | 万桥信息技术有限公司 | A kind of Tailings Dam monitoring and warning emergency commanding platform based on GIS-Geographic Information System |
| CN111397685B (en) * | 2020-02-20 | 2021-10-29 | 石家庄铁道大学 | Intelligent prediction method based on online monitoring system tailing pond saturation line |
| CN113610397A (en) * | 2021-08-09 | 2021-11-05 | 宁波工程学院 | Petrochemical enterprise safety evaluation method based on PSO-BP neural network |
| CN115391472B (en) * | 2022-08-15 | 2023-05-05 | 中国安全生产科学研究院 | Production operation management system of non-colliery mountain tail ore deposit storehouse |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102202164A (en) * | 2011-05-20 | 2011-09-28 | 长安大学 | Motion-estimation-based road video stabilization method |
| CN103257644A (en) * | 2013-05-21 | 2013-08-21 | 青岛理工大学 | Tailing pond safety state online monitoring method |
| CN104281920A (en) * | 2014-09-29 | 2015-01-14 | 中南大学 | Tailing pond layered index safety assessment and early-warning method and system |
| CN106971044A (en) * | 2017-03-31 | 2017-07-21 | 青岛理工大学 | Tailing dam piping damage scene construction system and method |
| CN108615114A (en) * | 2018-04-28 | 2018-10-02 | 中国电建集团昆明勘测设计研究院有限公司 | Reservoir dam safety risk assessment method based on bowknot model |
| CN109341778A (en) * | 2018-11-23 | 2019-02-15 | 泉州装备制造研究所 | A kind of information-based intelligence control system and control method of security monitoring Tailings Dam |
-
2019
- 2019-02-27 CN CN201910144179.0A patent/CN109918754B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102202164A (en) * | 2011-05-20 | 2011-09-28 | 长安大学 | Motion-estimation-based road video stabilization method |
| CN103257644A (en) * | 2013-05-21 | 2013-08-21 | 青岛理工大学 | Tailing pond safety state online monitoring method |
| CN104281920A (en) * | 2014-09-29 | 2015-01-14 | 中南大学 | Tailing pond layered index safety assessment and early-warning method and system |
| CN106971044A (en) * | 2017-03-31 | 2017-07-21 | 青岛理工大学 | Tailing dam piping damage scene construction system and method |
| CN108615114A (en) * | 2018-04-28 | 2018-10-02 | 中国电建集团昆明勘测设计研究院有限公司 | Reservoir dam safety risk assessment method based on bowknot model |
| CN109341778A (en) * | 2018-11-23 | 2019-02-15 | 泉州装备制造研究所 | A kind of information-based intelligence control system and control method of security monitoring Tailings Dam |
Non-Patent Citations (4)
| Title |
|---|
| Quantitative Assessment Method Study Based on Weakness Theory of Dam Failure Risks in Tailings Dam;MEI Guodong;《Procedia Engineering》;20111230;第26卷;第1827-1834页 * |
| 基于十字线灰度图像清晰度模型的构建与应用;杜飞明 等;《计算技术与自动化》;20090915;第28卷(第3期);第83-85、105页 * |
| 尾矿库在线安全监测技术及其预警方法研究;肖圣博;《《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》》;20140415(第04期);第C037-63页 * |
| 浸润线地质雷达探测技术在某尾矿坝稳定性分析中的应用;何文 等;《有色金属工程》;20140215;第4卷(第1期);第68-70页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109918754A (en) | 2019-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109918754B (en) | Safety detection and early warning method and system for layered indexes of tailing pond | |
| CN110633690B (en) | Vehicle feature identification method and system based on bridge monitoring | |
| CN111915069B (en) | Deep learning-based detection method for distribution of lightweight toxic and harmful gases | |
| US11436712B2 (en) | Predicting and correcting vegetation state | |
| CN113496104A (en) | Rainfall forecast correction method and system based on deep learning | |
| Yu et al. | Pavement roughness index estimation and anomaly detection using smartphones | |
| CN116152863B (en) | Personnel information identification method and device, electronic equipment and storage medium | |
| CN112241844B (en) | Method and device for determining and updating environmental risk source background list of drinking water source area | |
| CN116989679A (en) | Highway high slope displacement integrated monitoring method based on image processing | |
| CN117133099A (en) | Automatic monitoring system for disaster of expressway high slope | |
| CN116612609A (en) | Disaster early warning method and system based on landslide hazard prediction | |
| CN117314157A (en) | Safety evaluation method, device, medium and equipment for mine slope stability | |
| CN114291025B (en) | Vehicle collision detection method and system based on data segmentation aggregation distribution | |
| Sutrisno et al. | Design of pothole detector using gray level co-occurrence matrix (GLCM) and neural network (NN) | |
| CN116563776A (en) | Method, system, medium and equipment for warning illegal behaviors based on artificial intelligence | |
| CN113295212B (en) | Landslide overall stability safety early warning system applying multi-monitoring point synergistic effect | |
| CN117671887A (en) | Intelligent security early warning management method and system based on big data | |
| TWI636276B (en) | Method of determining earthquake with artificial intelligence and earthquake detecting system | |
| CN114299231A (en) | Construction method of 3D model for river water pollution | |
| CN113808370A (en) | Landslide-oriented multi-index coupling monitoring and early warning method | |
| Al Murayziq et al. | Using case-based reasoning and artificial neural networks for the efficient prediction of dust storms | |
| CN116308828B (en) | Intelligent damage assessment method and system for vehicle with integrated and fused risk data | |
| Alburshaid et al. | Spatio-temporal land use analysis and urban growth dynamic prediction in the kingdom of Bahrain | |
| CN116739357B (en) | Multi-mode fusion perception city existing building wide area monitoring and early warning method and device | |
| CN116469013B (en) | Road ponding prediction method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |