CN109918754A - A method and system for safety detection and early warning of layered indicators in tailings pond - Google Patents
A method and system for safety detection and early warning of layered indicators in tailings pond Download PDFInfo
- Publication number
- CN109918754A CN109918754A CN201910144179.0A CN201910144179A CN109918754A CN 109918754 A CN109918754 A CN 109918754A CN 201910144179 A CN201910144179 A CN 201910144179A CN 109918754 A CN109918754 A CN 109918754A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- dam
- monitoring
- tailings dam
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000001514 detection method Methods 0.000 title claims abstract description 29
- 238000012544 monitoring process Methods 0.000 claims abstract description 68
- 238000011156 evaluation Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000005259 measurement Methods 0.000 claims abstract description 11
- 238000007405 data analysis Methods 0.000 claims abstract description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 29
- 239000002245 particle Substances 0.000 claims description 22
- 238000012806 monitoring device Methods 0.000 claims description 10
- 210000004209 hair Anatomy 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 210000002569 neuron Anatomy 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 239000012141 concentrate Substances 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 210000002364 input neuron Anatomy 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 210000004218 nerve net Anatomy 0.000 description 2
- 229910052755 nonmetal Inorganic materials 0.000 description 2
- 239000002893 slag Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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 Safety of Tailings Dam detection technique fields, a kind of Tailings Dam layering index safety detection and method for early warning and system are disclosed, the Tailings Dam layering index safety detection and early warning system based on big data analysis includes: video monitoring module, saturation monitoring modular, crack in dam body monitoring modular, scale measurement module, main control module, big data processing module, security evaluation module, warning module, emergency module, display module.The present invention can fast and effeciently calculate Tailings Dam scale by scale measurement module, and cost is relatively low；Meanwhile being determined by emergency module according to alert event grade, alert event in prediction scheme is retrieved, calls or generate new emergency preplan after matching, is applied to emergency aid decision；Rationally using the information in case library, the precision for judging event and handling is further increased.
Description
Technical field
The invention belongs to Safety of Tailings Dam detection technique field more particularly to a kind of Tailings Dam layering index safety detection and
Method for early warning and system.
Background technique
Tailings Dam, which refers to build a dam, intercepts what the mouth of a valley or exclosure were constituted, carries out mineral selection to store up metal or non-metal mine
Tailing or the place of other industrial residues is not discharged afterwards.Tailings Dam is the artificial mud-rock flow danger source with high potential energy, is deposited
In dam break danger, once accident, be easy to cause severe and great casualty.The red mud reservoir that melting waste slag is formed, power generation waste residue are formed useless
Slag library should be also managed by Tailings Dam.Tailing refers to the ore that metal or non-metal mine produce, and has selected through dressing plant
" waste residue " discharged after the concentrate of value.These tailings are since quantity is big, containing the useful or harmful components that cannot temporarily handle,
Arbitrarily discharge, it will cause resource loss, large area, which is annihilated, farmland or silts river up, pollutes environment.The tailing that dressing plant generates
Not only quantity is big, and particle is thin, and often contains various medicaments in tailing water, such as untreated, then must cause to select factory's ambient enviroment
Serious pollution.Tailing is properly stored in Tailings Dam, tailing water recycles after clarifying in library, can be effectively protected
Environment.However, existing Tailings Dam scale calculating speed is slow, meanwhile, when monitoring Tailings Dam notes abnormalities, cannot quickly it make in time
Cope with decision.
In conclusion problem of the existing technology is:
Existing Tailings Dam scale calculating speed is slow, meanwhile, when monitoring Tailings Dam notes abnormalities, it cannot quickly make and answer in time
To decision.
The degree of focus of image pick-up device is poor in the prior art, cannot clearly be shot with video-corder to Tailings Dam scene, be unfavorable for obtaining
Obtain clear and accurate Tailings Dam live video information；In the prior art, crack in dam body data cannot be accurately and rapidly monitored, no
Conducive to the smooth development of Tailings Dam related work；Alarm is insufficient for the monitoring sensitivity of risk data in the prior art, no
It can be for the accuracy that alarm signal is judged, delayed alarm.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of Tailings Dam layering index safety detection and the pre- police
Method and system.
The invention is realized in this way a kind of Tailings Dam layering index safety detection and method for early warning, the Tailings Dam point
Layer index safety detection and method for early warning include:
The first step is shot with video-corder Tailings Dam scene using cross gray level image definition algorithm using image pick-up device, is obtained
Monitor Tailings Dam live video information；Saturation line of tailings pond data are monitored using saturation sensor；
Second step monitors crack in dam body data using best uniformity approximation method using crack in dam body monitoring device；Pass through
The gross area, total height of dam and the aggregate storage capacity data of measuring appliance acquisition Tailings Dam；
Third step concentrates big data resource to carry out processing analysis to the data of monitoring using Cloud Server；
4th step assesses Safety of Tailings Dam according to monitoring data index using assessment software；
5th step is monitored data using PSO-BP algorithm using alarm, monitors that risk data carries out in time
Alarm, and optimal solution is chosen by prediction scheme storehouse and copes with Tailings Dam precarious position；
6th step utilizes Tailings Dam live video, the saturation, water level, crack, security evaluation of display display monitoring
Data information.
Further, the first step uses cross gray level image definition algorithm specific steps using image pick-up device are as follows:
In cross hairs gray level image region, the maximum gradation value B of white pixelmax=255, the minimum gradation value B of black pixelmin
=0, the maximum dynamic range of pixel grey scale is 0-255 in image, and gray scale intermediate value middle is (Bmax-Bmin)/2=255/2
=127.5；After normalized, white pixel difference gray value (255-128) clarity formula is indicated are as follows:
Black pixel difference gray value (0-127) clarity formula indicates are as follows:
The definition algorithm of any gray value may be expressed as:
Cross hairs gray level image region is made of m X n pixel, grey scale pixel value matrix B (I, J), wherein, 0≤I≤
M-1,0≤J≤n-1, B (I, J) matrix indicate:
So the clarity in cross hairs gray level image region can indicate:
Further, it is split using crack in dam body monitoring device using best uniformity approximation method monitoring dam body in the second step
Stitch data, specific algorithm are as follows:
If f (x) ∈ C [a, b], pn(x) set that all multinomials for being number no more than n are constituted；If
Then claiming p* (x) is optimal and uniform approximating polynomial of the f (x) on [a, b], also referred to as the very big multinomial of minimization；
Optimum polynomial is sought using Li meter Zi algorithm；It is solved according to chebyshev's theorem
Wherein: ak (k=0,1 ... it n) is multinomial coefficient to be asked；ρ is most preferably to approach value；xiIt is obtained with correction method repeatedly.
Further, in the 5th step, data are monitored using PSO-BP algorithm using alarm, so that alarm
It alarms in time the abnormal data of monitoring, specific steps are as follows:
(1) it initializes: the relevant parameter of setting PSO-BP neural network；Determine the number of plies of neural network, each layer of nerve
The number of member, and the particle dimension for needing to optimize；Wherein PSO algorithm needs the weight threshold total number optimized are as follows:
N=(m+1) × n+ (n+1) × t,
M is input neuron number, and n is hidden neuron number, and t is output layer neuron number, to the speed of particle
Random initializtion is carried out with position；
(2) it calculates fitness: calculating the sum of network output and sample desired output Error Absolute Value according to fitness function；
(3) individual extreme value and group's extreme value are found: the fitness function value of each particle is compared with individual extreme value,
If fitness function value is smaller, which becomes new individual extreme value；And by new individual extreme value and global
Optimal adaptation angle value is compared, if smaller, as current group's extreme value；
(4) according to the position and speed of cluster ion algorithm more new particle；
In formula: w is inertia weight；K is current iteration number；I is the speed of particle；D is the position of particle；c1And c2For
Studying factors, also referred to as acceleration factor select c by verifying1=c2=2 are calculated；Be uniform between [0,1]
Random number；
(5) see whether global optimum's fitness value is less than setting error or the number of iterations is greater than maximum number of iterations, if
It is unsatisfactory for condition, return step (3)；If meeting condition, the global optimum's particle position exported is optimal BP nerve net
Network weight threshold.
The Tailings Dam layering index safety detection and method for early warning are realized another object of the present invention is to provide a kind of
The Tailings Dam layering index safety detection and early warning system based on big data analysis, the Tailings Dam based on big data analysis
Layering index safety detection and early warning system include:
Video monitoring module is connect with main control module, for monitoring Tailings Dam live video information by image pick-up device；
Saturation monitoring modular, connect with main control module, for monitoring saturation line of tailings pond number by saturation sensor
According to；
Crack in dam body monitoring modular, connect with main control module, for monitoring crack in dam body by crack in dam body monitoring device
Data；
Scale measurement module, connect with main control module, for by measuring appliance acquire the gross area of Tailings Dam, total height of dam and
Aggregate storage capacity data；
Main control module, with video monitoring module, saturation monitoring modular, crack in dam body monitoring modular, scale measurement module,
Big data processing module, security evaluation module, warning module, emergency module, display module connection, for being controlled by single-chip microcontroller
Modules work normally；
Big data processing module, connect with main control module, for concentrating big data resource to monitoring by Cloud Server
Data carry out processing analysis；
Security evaluation module is connect with main control module, for by assessing software according to monitoring data index to Tailings Dam
Safety is assessed；
Warning module is connect with main control module, for passing through alarm according to the progress of monitoring risk data and alarm；
Emergency module, connect with main control module, chooses optimal solution reply Tailings Dam danger for passing through prediction scheme storehouse
State；
Display module is connect with main control module, for the Tailings Dam live video by display display monitoring, infiltration
Line, water level, crack, security evaluation data information.
Another object of the present invention is to provide a kind of application Tailings Dam layering index safety detection and method for early warning
Safety of Tailings Dam detection platform.
Advantages of the present invention and good effect are as follows: the present invention can fast and effeciently calculate tailing by scale measurement module
Library scale, and cost is relatively low；Meanwhile being determined by emergency module according to alert event grade, alert event in prediction scheme is retrieved,
New emergency preplan is called or generated after matching, and is applied to emergency aid decision；Rationally using the information in case library, to Tailings Dam
The exception and accident treatment of appearance carry out aid decision, ensure the safe operation of Tailings Dam, utmostly lower Tailings Dam calamity
Evil loss；The Boolean Model of extension obtains the similarity of attribute in emergency event, convenience of calculation and precision height；Emergency event
Attribute is described and is measured using event title, type, position, grade, influence degree and specific descriptions, is improved to event
Retrieval, the precision being adapted to；The method that reasoning generates case is simplified, and easily operated, is further increased and is judged event and locate
The precision of reason.
The present invention uses cross gray level image definition algorithm using image pick-up device, effectively improves the degree of focus of image pick-up device, mentions
The clarity that height shoots with video-corder Tailings Dam scene help to obtain clear and accurate Tailings Dam live video information；It is split using dam body
It stitches monitoring device and crack in dam body data is monitored using best uniformity approximation method, be conducive to accurately and rapidly monitor crack in dam body
Data guarantee the smooth development of Tailings Dam related work；Data are monitored using PSO-BP algorithm using alarm, effectively
The monitoring sensitivity for risk data is improved, the accuracy judged for alarm signal is improved, so that alarm is timely
It alarms the abnormal data of monitoring.
Detailed description of the invention
Fig. 1 is Tailings Dam layering index safety detection provided in an embodiment of the present invention and method for early warning flow chart.
Fig. 2 is the Tailings Dam layering index safety detection provided in an embodiment of the present invention based on big data analysis and early warning system
System structural block diagram.
In Fig. 2: 1, video monitoring module；2, saturation monitoring modular；3, crack in dam body monitoring modular；4, scale measures mould
Block；5, main control module；6, big data processing module；7, security evaluation module；8, warning module；9, emergency module；10, mould is shown
Block.
Specific embodiment
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and cooperate attached drawing
Detailed description are as follows.
Structure of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, Tailings Dam provided by the invention layering index safety detection and method for early warning the following steps are included:
S101 shoots with video-corder Tailings Dam scene using cross gray level image definition algorithm using image pick-up device, obtains prison
Control Tailings Dam live video information；Saturation line of tailings pond data are monitored using saturation sensor；
S102 monitors crack in dam body data using best uniformity approximation method using crack in dam body monitoring device；Pass through survey
The gross area, total height of dam and the aggregate storage capacity data of measuring device acquisition Tailings Dam；
S103 concentrates big data resource to carry out processing analysis to the data of monitoring using Cloud Server；
S104 assesses Safety of Tailings Dam according to monitoring data index using assessment software；
S105 is monitored data using PSO-BP algorithm using alarm, monitors that risk data is reported in time
It is alert, and optimal solution is chosen by prediction scheme storehouse and copes with Tailings Dam precarious position；
S106 utilizes Tailings Dam live video, the saturation, water level, crack, security evaluation number of display display monitoring
It is believed that breath.
It is provided in an embodiment of the present invention to use cross gray level image definition algorithm using image pick-up device in step S101, have
Effect improves the degree of focus of image pick-up device, improves the clarity shot with video-corder to Tailings Dam scene, help to obtain clear and accurate Tailings Dam
Live video information, specific steps are as follows:
In cross hairs gray level image region, the maximum gradation value B of white pixelmax=255, the minimum gradation value B of black pixelmin
=0, the maximum dynamic range of pixel grey scale is 0-255 in image, and gray scale intermediate value middle is (Bmax-Bmin)/2=255/2
=127.5；After normalized, white pixel difference gray value (255-128) clarity formula is indicated are as follows:
Black pixel difference gray value (0-127) clarity formula indicates are as follows:
The definition algorithm of any gray value may be expressed as:
Cross hairs gray level image region is made of m X n pixel, grey scale pixel value matrix B (I, J), wherein, 0≤I≤
M-1,0≤J≤n-1, B (I, J) matrix indicate:
So the clarity in cross hairs gray level image region can indicate:
It is provided in an embodiment of the present invention to use best uniformity approximation method using crack in dam body monitoring device in step S102
Crack in dam body data are monitored, are conducive to accurately and rapidly monitor crack in dam body data, guarantee smoothly opening for Tailings Dam related work
Exhibition, specific algorithm are as follows:
If f (x) ∈ C [a, b], pn(x) set that all multinomials for being number no more than n are constituted；If
Then claiming p* (x) is optimal and uniform approximating polynomial of the f (x) on [a, b], also referred to as the very big multinomial of minimization；
Optimum polynomial is sought using Li meter Zi algorithm；It is solved according to chebyshev's theorem
Wherein: ak (k=0,1 ... it n) is multinomial coefficient to be asked；ρ is most preferably to approach value；xiIt is obtained with correction method repeatedly.
It is provided in an embodiment of the present invention that data are monitored using PSO-BP algorithm using alarm in step S105,
The monitoring sensitivity for risk data is effectively improved, the accuracy judged for alarm signal is improved, so that alarm
It alarms in time the abnormal data of monitoring, specific steps are as follows:
(1) it initializes: the relevant parameter of setting PSO-BP neural network；Determine the number of plies of neural network, each layer of nerve
The number of member, and the particle dimension for needing to optimize；Wherein PSO algorithm needs the weight threshold total number optimized are as follows:
N=(m+1) × n+ (n+1) × t,
M is input neuron number, and n is hidden neuron number, and t is output layer neuron number, to the speed of particle
Random initializtion is carried out with position；
(2) it calculates fitness: calculating the sum of network output and sample desired output Error Absolute Value according to fitness function；
(3) individual extreme value and group's extreme value are found: the fitness function value of each particle is compared with individual extreme value,
If fitness function value is smaller, which becomes new individual extreme value；And by new individual extreme value and global
Optimal adaptation angle value is compared, if smaller, as current group's extreme value；
(4) according to the position and speed of cluster ion algorithm more new particle；
In formula: w is inertia weight；K is current iteration number；I is the speed of particle；D is the position of particle；c1And c2For
Studying factors, also referred to as acceleration factor select c by verifying1=c2=2 are calculated；Be uniform between [0,1]
Random number；
(5) see whether global optimum's fitness value is less than setting error or the number of iterations is greater than maximum number of iterations, if
It is unsatisfactory for condition, return step (3)；If meeting condition, the global optimum's particle position exported is optimal BP nerve net
Network weight threshold.
As shown in Fig. 2, it is provided in an embodiment of the present invention based on big data analysis Tailings Dam layering index safety detection and
Early warning system includes: video monitoring module 1, saturation monitoring modular 2, crack in dam body monitoring modular 3, scale measurement module 4, master
Control module 5, big data processing module 6, security evaluation module 7, warning module 8, emergency module 9, display module 10.
Video monitoring module 1 is connect with main control module 5, for monitoring Tailings Dam live video information by image pick-up device；
Saturation monitoring modular 2 is connect with main control module 5, for monitoring saturation line of tailings pond by saturation sensor
Data；
Crack in dam body monitoring modular 3 is connect with main control module 5, is split for monitoring dam body by crack in dam body monitoring device
Stitch data；
Scale measurement module 4 is connect with main control module 5, for acquiring the gross area, the total height of dam of Tailings Dam by measuring appliance
With aggregate storage capacity data；
Main control module 5 is measured with video monitoring module 1, saturation monitoring modular 2, crack in dam body monitoring modular 3, scale
Module 4, big data processing module 6, security evaluation module 7, warning module 8, emergency module 9, display module 10 connect, for leading to
Single-chip microcontroller control modules are crossed to work normally；
Big data processing module 6 is connect with main control module 5, for concentrating big data resource to monitoring by Cloud Server
Data carry out processing analysis；
Security evaluation module 7 is connect with main control module 5, for by assessing software according to monitoring data index to tailing
Library safety is assessed；
Warning module 8 is connect with main control module 5, for passing through alarm according to the progress of monitoring risk data and alarm；
Emergency module 9, connect with main control module 5, chooses optimal solution reply Tailings Dam danger for passing through prediction scheme storehouse
Dangerous state；
Display module 10 is connect with main control module 5, for by display display monitoring Tailings Dam live video,
Saturation, water level, crack, security evaluation data information.
4 method of scale measurement module provided by the invention is as follows:
(1) before the high-definition remote sensing data and Tailings Dam construction that obtain the Tailings Dam that pending size values extract
Initial land form data；
(2) the high-definition remote sensing data and initial land form data are registrated；
(3) the high-definition remote sensing data are based on, remote sensing is carried out to plane characteristic relevant to the Tailings Dam scale
Identification, obtains the relevant plane characteristic of Tailings Dam, wherein the relevant plane characteristic of the Tailings Dam includes that the Tailings Dam is overall
The crucial edge fit point of bounds, the bounds of dam body at different levels and dam body at different levels and periphery landform；
(4) landform such as topographic profile point are carried out to the relevant plane characteristic of the Tailings Dam using the initial land form data
Analysis is obtained the elevation information of the crucial edge fit point in the longitudinal direction, and is believed using the elevation of the crucial edge fit point in the longitudinal direction
Breath reconstructs the three-D space structure after the Tailings Dam construction；
(5) three-D space structure based on aforementioned reconstruct, according to the classification three-dimensional space of the dam bodys at different levels of the Tailings Dam
Structure calculates the gross area, total height of dam and aggregate storage capacity of the Tailings Dam.
9 emergency methods of emergency module provided by the invention are as follows:
1) Tailings Dam case data collection is obtained by network, establishes case database；
2) emergency event inputs；
3) analysis identification is carried out to the emergency event of step 2) input and obtains description or the degree of each attribute of emergency event
Amount method；If emergency event is identical as the case in case database, calls directly prediction scheme scheme and carry out aid decision support；
If emergency event and the case in case database be not identical, carry out in next step；
4) each respective similarity of attribute in emergency event is calculated；
5) calculate emergency event total similarity and judged, judgement is specifically: by total similarity of emergency event with
The threshold value of setting is compared, if total similarity of emergency event is more than or equal to the threshold value of setting, calls directly emergency planning method
Carry out aid decision support；If total similarity of emergency event is less than the threshold value of setting, made inferences based on prediction scheme, the base
It is in the specific method that prediction scheme makes inferences: first arranges the respective similarity of each attribute of the emergency event being calculated
Sequence, then using the maximum case method of the similarity of attribute as the case method of adaptation, finally by Part Substitution and parameter tune
The whole adaptation for reaching case.
The attribute of emergency event provided by the invention includes event title, type, position, grade, influence degree, event original
Cause, time and place.
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (6)
1. a kind of Tailings Dam layering index safety detection and method for early warning, which is characterized in that the Tailings Dam layering index safety
Detection and method for early warning include:
The first step shoots with video-corder Tailings Dam scene using cross gray level image definition algorithm using image pick-up device, obtains monitoring
Tailings Dam live video information；Saturation line of tailings pond data are monitored using saturation sensor；
Second step monitors crack in dam body data using best uniformity approximation method using crack in dam body monitoring device；Pass through measurement
The gross area, total height of dam and the aggregate storage capacity data of device acquisition Tailings Dam；
Third step concentrates big data resource to carry out processing analysis to the data of monitoring using Cloud Server；
4th step assesses Safety of Tailings Dam according to monitoring data index using assessment software；
5th step is monitored data using PSO-BP algorithm using alarm, monitors that risk data is alarmed in time,
And optimal solution is chosen by prediction scheme storehouse and copes with Tailings Dam precarious position；
6th step utilizes Tailings Dam live video, the saturation, water level, crack, security evaluation data of display display monitoring
Information.
2. Tailings Dam layering index safety detection as described in claim 1 and method for early warning, which is characterized in that the first step
Cross gray level image definition algorithm specific steps are used using image pick-up device are as follows:
In cross hairs gray level image region, the maximum gradation value B of white pixelmax=255, the minimum gradation value B of black pixelmin=0,
The maximum dynamic range of pixel grey scale is 0-255 in image, and gray scale intermediate value middle is (Bmax-Bmin)/2=255/2=
127.5；After normalized, white pixel difference gray value (255-128) clarity formula is indicated are as follows:
Black pixel difference gray value (0-127) clarity formula indicates are as follows:
The definition algorithm of any gray value may be expressed as:
Cross hairs gray level image region is made of m X n pixel, grey scale pixel value matrix B (I, J), wherein, 0≤I≤m-1,0
≤ J≤n-1, B (I, J) matrix indicate:
So the clarity in cross hairs gray level image region can indicate:
3. Tailings Dam layering index safety detection as described in claim 1 and method for early warning, which is characterized in that the second step
It is middle that crack in dam body data, specific algorithm are monitored using best uniformity approximation method using crack in dam body monitoring device are as follows:
If f (x) ∈ C [a, b], pn(x) set that all multinomials for being number no more than n are constituted；If
Then claiming p* (x) is optimal and uniform approximating polynomial of the f (x) on [a, b], also referred to as the very big multinomial of minimization；
Optimum polynomial is sought using Li meter Zi algorithm；It is solved according to chebyshev's theorem
Wherein: ak (k=0,1 ... it n) is multinomial coefficient to be asked；ρ is most preferably to approach value；xiIt is obtained with correction method repeatedly.
4. Tailings Dam layering index safety detection as described in claim 1 and method for early warning, which is characterized in that the 5th step
In, data are monitored using PSO-BP algorithm using alarm, so that alarm in time carries out the abnormal data of monitoring
Alarm, specific steps are as follows:
(1) it initializes: the relevant parameter of setting PSO-BP neural network；Determine the number of plies of neural network, each layer of neuron
Number, and the particle dimension for needing to optimize；Wherein PSO algorithm needs the weight threshold total number optimized are as follows:
N=(m+1) × n+ (n+1) × t,
M is input neuron number, and n is hidden neuron number, and t is output layer neuron number, speed and position to particle
Set carry out random initializtion；
(2) it calculates fitness: calculating the sum of network output and sample desired output Error Absolute Value according to fitness function；
(3) individual extreme value and group's extreme value are found: the fitness function value of each particle is compared with individual extreme value, if
Fitness function value is smaller, then the fitness function value becomes new individual extreme value；And it is new individual extreme value and the overall situation is best
Fitness value is compared, if smaller, as current group's extreme value；
(4) according to the position and speed of cluster ion algorithm more new particle；
In formula: w is inertia weight；K is current iteration number；I is the speed of particle；D is the position of particle；c1And c2For study
The factor, also referred to as acceleration factor select c by verifying1=c2=2 are calculated；Be uniformly random between [0,1]
Number；
(5) see whether global optimum's fitness value is less than setting error or the number of iterations is greater than maximum number of iterations, if discontented
Sufficient condition, return step (3)；If meeting condition, the global optimum's particle position exported is optimal BP neural network power
It is worth threshold value.
5. it is a kind of realize the layering index safety detection of Tailings Dam described in claim 1 and method for early warning based on big data analysis
Tailings Dam is layered index safety detection and early warning system, which is characterized in that the Tailings Dam layering based on big data analysis refers to
Mark safety detection and early warning system include:
Video monitoring module is connect with main control module, for monitoring Tailings Dam live video information by image pick-up device；
Saturation monitoring modular, connect with main control module, for monitoring saturation line of tailings pond data by saturation sensor；
Crack in dam body monitoring modular, connect with main control module, for monitoring crack in dam body data by crack in dam body monitoring device；
Scale measurement module, connect with main control module, for acquiring the gross area, total height of dam and the Zong Ku of Tailings Dam by measuring appliance
Hold data；
Main control module, with video monitoring module, saturation monitoring modular, crack in dam body monitoring modular, scale measurement module, big number
It is each for being controlled by single-chip microcontroller according to processing module, security evaluation module, warning module, emergency module, display module connection
Module works normally；
Big data processing module, connect with main control module, for concentrating big data resource to the data of monitoring by Cloud Server
Carry out processing analysis；
Security evaluation module is connect with main control module, for by assessing software according to monitoring data index to Safety of Tailings Dam
Property is assessed；
Warning module is connect with main control module, for passing through alarm according to the progress of monitoring risk data and alarm；
Emergency module, connect with main control module, chooses optimal solution reply Tailings Dam precarious position for passing through prediction scheme storehouse；
Display module is connect with main control module, for by display display monitoring Tailings Dam live video, saturation,
Water level, crack, security evaluation data information.
6. a kind of tailing using layering the index safety detection and method for early warning of Tailings Dam described in Claims 1 to 4 any one
Library safety detection platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910144179.0A CN109918754B (en) | 2019-02-27 | 2019-02-27 | A method and system for safety detection and early warning of layered indicators in tailings pond |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910144179.0A CN109918754B (en) | 2019-02-27 | 2019-02-27 | A method and system for safety detection and early warning of layered indicators in tailings pond |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109918754A true CN109918754A (en) | 2019-06-21 |
| CN109918754B 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 | A method and system for safety detection and early warning of layered indicators in tailings pond |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109918754B (en) |
Cited By (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 |
| CN111397685A (en) * | 2020-02-20 | 2020-07-10 | 石家庄铁道大学 | An intelligent prediction method for tailings pond infiltration line based on online monitoring system |
| 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 |
| CN115391472A (en) * | 2022-08-15 | 2022-11-25 | 中国安全生产科学研究院 | A production and operation management system for non-coal mine tailings pool |
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 | An information-based intelligent control system and control method for safety monitoring of tailings pond |
-
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 | An information-based intelligent control system and control method for safety monitoring of tailings pond |
Non-Patent Citations (4)
| Title |
|---|
| MEI GUODONG: "Quantitative Assessment Method Study Based on Weakness Theory of Dam Failure Risks in Tailings Dam", 《PROCEDIA ENGINEERING》 * |
| 何文 等: "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", 《有色金属工程》 * |
| 杜飞明 等: "基于十字线灰度图像清晰度模型的构建与应用", 《计算技术与自动化》 * |
| 肖圣博: "尾矿库在线安全监测技术及其预警方法研究", 《《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》》 * |
Cited By (5)
| 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 |
| CN111397685A (en) * | 2020-02-20 | 2020-07-10 | 石家庄铁道大学 | An intelligent prediction method for tailings pond infiltration line based on online monitoring system |
| CN111397685B (en) * | 2020-02-20 | 2021-10-29 | 石家庄铁道大学 | An intelligent prediction method for tailings pond infiltration line based on online monitoring system |
| 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 |
| CN115391472A (en) * | 2022-08-15 | 2022-11-25 | 中国安全生产科学研究院 | A production and operation management system for non-coal mine tailings pool |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109918754B (en) | 2022-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109918754A (en) | A method and system for safety detection and early warning of layered indicators in tailings pond | |
| Formetta et al. | Evaluating performance of simplified physically based models for shallow landslide susceptibility | |
| CN107742099A (en) | A kind of crowd density estimation based on full convolutional network, the method for demographics | |
| CN114021487B (en) | An early warning method, device, device and readable storage medium for hillside collapse | |
| CN115144548B (en) | Harmful gas composition real-time monitoring system and its monitoring method | |
| CN116245412A (en) | On-spot safety monitoring management system of building engineering | |
| CN117390938B (en) | High-pile wharf operation and maintenance period structure health monitoring method and system | |
| CN118171918B (en) | Air-space-ground landslide monitoring method and system based on multi-source data | |
| CN116384255B (en) | Park dangerous situation perception method and system based on multi-source data fusion | |
| CN112241844B (en) | Method and device for determining and updating environmental risk source background list of drinking water source area | |
| Foroutan et al. | Assessing impact of understory vegetation density on solid obstacle detection for off-road autonomous ground vehicles | |
| Dong et al. | CBAM-optimized automatic segmentation and reconstruction system for monocular images with asphalt pavement potholes | |
| CN117272840B (en) | Expressway bad weather early warning method and system | |
| CN115311574B (en) | Building monitoring method, equipment and medium | |
| CN118568621A (en) | Intelligent park management system based on digital twinning | |
| CN117584124A (en) | Inspection method and device based on intelligent robot | |
| EP2652675A1 (en) | Processing distributions of a population over a region of interest divided into a plurality of cells | |
| EP2466526A1 (en) | Predicting population distributions using measured values | |
| CN118387128B (en) | Special operation vehicle safety monitoring and early warning method and system | |
| CN118072106B (en) | Landslide hidden danger identification and susceptibility evaluation method | |
| CN118887791B (en) | Video real-time monitoring system and method for emergency disposal of barrier lake | |
| Rangnekar et al. | Learning representations to predict landslide occurrences and detect illegal mining across multiple domains | |
| CN118886232B (en) | A method and system for simulating organic matter migration analysis | |
| CN117992759B (en) | Dam monitoring method and system based on remote sensing data | |
| Sang et al. | Smartphone-Based IRI Estimation for Pavement Roughness Monitoring: A Data-Driven Approach |
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 |