CN111173565B - Mine monitoring data abnormal fluctuation early warning method and device - Google Patents
Mine monitoring data abnormal fluctuation early warning method and device Download PDFInfo
- Publication number
- CN111173565B CN111173565B CN202010015748.4A CN202010015748A CN111173565B CN 111173565 B CN111173565 B CN 111173565B CN 202010015748 A CN202010015748 A CN 202010015748A CN 111173565 B CN111173565 B CN 111173565B
- Authority
- CN
- China
- Prior art keywords
- early warning
- time
- real
- monitoring data
- monitoring
- 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
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
- E21F17/18—Special adaptations of signalling or alarm devices
Abstract
The invention discloses an early warning method and device for abnormal fluctuation of mine monitoring data, which is based on mine monitoring data and an abnormal fluctuation early warning index system, inquires historical monitoring data by connecting a mine end monitoring database, calculates a fitting function and a normal fluctuation range of monitoring values of various monitoring points, inquires real-time monitoring data to calculate a real-time deviation, configures different early warning analysis methods to calculate a comparison value between the real-time deviation and a reference standard difference, judges whether the monitoring data is abnormal fluctuation early warning and a corresponding early warning level by combining interval set values of multi-level early warning indexes, and can win precious time for safety risk identification and hidden danger troubleshooting and control, thereby reducing the probability of accidents.
Description
Technical Field
The invention belongs to the technical field of mine safety monitoring data abnormity monitoring, and particularly relates to a mine monitoring data abnormity fluctuation early warning method and device.
Background
Various monitoring data of a mine are important basis for visually reflecting the dynamic state of safety production, at present, various monitoring systems are mainly put in storage through data integration, data overrun alarming is realized by comparing a monitoring value with a data self-sensor limit value or setting an alarming limit value, no relevant calculation identification technology exists for abnormal fluctuation of data within the alarming limit value, the mode of setting the alarming limit value for a certain type of sensor triggers alarming more coarsely because of different normal values of the monitoring data of each sensor, risk identification is lagged, and abnormal fluctuation analysis within the alarming limit value and risk possibly occurring of early warning judgment cannot be carried out.
Disclosure of Invention
Aiming at the defects of the existing mine monitoring data alarm mode, the invention provides a mine monitoring data abnormal fluctuation early-warning method and device. The monitoring data abnormal fluctuation early warning method is characterized in that the abnormal fluctuation early warning function of monitoring data is achieved based on mine monitoring data and an abnormal fluctuation early warning index system, historical monitoring data are inquired through a monitoring and monitoring database connected with a mine end, a fitting function and a normal fluctuation range of monitoring values of various monitoring points are calculated, real-time monitoring data are inquired, real-time deviation is calculated, different early warning analysis methods are configured, a comparison value of the real-time deviation and a reference standard deviation is calculated, and whether abnormal fluctuation early warning exists or not and whether an early warning level corresponds to the abnormal fluctuation early warning is judged by combining interval set values of multi-stage early warning indexes. By adopting the GIS space map service, the real-time abnormal fluctuation condition of the monitoring data of each region can be visually displayed, the existence of risks can be identified through the abnormal fluctuation of the region monitoring, precious time is won for the management of the risk hidden dangers, and the probability of accidents is greatly reduced.
The method comprises the following specific steps:
in order to solve the above problems, the embodiment of the present invention discloses a method for early warning abnormal fluctuation of mine monitoring data, preferably, the method is based on the mine monitoring data and an abnormal fluctuation early warning index system, and the specific implementation method includes the following steps:
step 1: connecting a mine end monitoring database, and inquiring real-time monitoring data and historical monitoring data of various monitoring points of a mine; the monitoring points of the mine represent monitoring points with monitoring values of analog quantity;
step 2: performing exception filtering processing on the historical monitoring data in a base number value range according to an exception filtering coefficient to obtain a reference base number for normal monitoring;
and step 3: carrying out segmentation mean calculation on the reference base number according to the set base number granularity to generate a reference base number set, and calculating and generating a corresponding fitting function according to the reference base number set and an early warning fitting mode; wherein, the early warning fitting mode comprises: mean fitting, linear fitting and nonlinear fitting;
and 4, step 4: calculating the corresponding deviation of each element in the reference base number set according to the fitting function to generate a base number deviation set, and calculating and generating a reference standard deviation by using the base number deviation set to serve as a reference value of the normal fluctuation range of the monitoring data of the monitoring point;
and 5: calculating the real-time deviation of the real-time monitoring data according to a fitting function, calculating a comparison value of the real-time deviation and the reference standard deviation by combining an early warning analysis method, comparing the comparison value with an interval set value of a multi-stage early warning index, judging whether the real-time monitoring data is abnormal fluctuation or not, and judging an early warning level corresponding to the real-time monitoring data;
step 6: and displaying the fit line corresponding to the fit function, the reference basis number set, the real-time monitoring data and the reference standard deviation in the same coordinate system by adopting different colors and line shapes, and displaying the abnormal fluctuation real-time early warning condition of various measuring points of the whole mine in a point arrangement mode by combining with GIS space map service. Preferably, the step of determining whether the real-time monitoring data is abnormally fluctuating includes:
comparing the comparison value with a multi-stage early warning index interval set value, and judging whether the comparison value is in the early warning index interval;
if not, skipping to execute the step 2;
if yes, judging whether the state of the measuring point is a continuous early warning state or not; if yes, updating the real-time early warning state; if not, generating abnormal fluctuation real-time early warning data, marking the real-time monitoring data as abnormal monitoring data and storing the abnormal monitoring data, participating in data abnormal filtering calculation in the next calculation process, and skipping to execute the step 2.
Preferably, the method for obtaining a monitored normal reference base includes:
(1) when in use
In time, all abnormal data are filtered and removed to obtain the reference base number for normal monitoring, and the step 3 is executed;
(2) when in use
Then, the abnormal data is reserved, filtering processing is not carried out, the reference base number of the normal monitoring is obtained, and the step 3 is executed;
(3) when k is more than or equal to 0.5, regarding that the data abnormal rate in the value range of the current round is higher and can not be used for generating the normal fluctuation reference standard of the monitoring point, continuing to use the reference standard difference of the previous round as the reference standard value for normal monitoring, and skipping to execute the step 5;
wherein:
is an abnormal filtering coefficient; k is the anomaly rate.
Preferably, the method for inquiring the real-time monitoring data and the historical monitoring data of various monitoring points of the mine comprises the following steps:
acquiring historical monitoring data in the time range according to the set base number value range; and the base number value range represents the time length from the current time to a certain historical moment.
Preferably, the method for generating the reference base number set by performing a segmentation mean calculation on the reference bases according to the set base number granularity includes:
dividing the base number value range into a plurality of time periods according to the value set by the base number granularity, and taking the middle time point of each time period to form a fitting time set Ti(t1,t2,t3,t4......ti) And averaging the reference base numbers in each time period;
forming the average value into the reference base number set Ai{(t1,a1),(t2,a2),(t3,a3)......(ti,ai)}。
Preferably, the method for generating a reference standard deviation by using the radix deviation set includes:
bringing the fitting time set into the fitting function for calculation to obtain a standard fitting set corresponding to the reference basis number set;
obtaining the radix deviation set by utilizing the reference radix set and the standard fitting set;
calculating by using the radix deviation set to obtain the reference standard deviation; wherein the reference standard deviation is calculated as follows:
wherein: delta is the reference standard deviation, N is the number of elements in the reference radix set, aiAs fitting time tiCorresponding reference base, biAs fitting time tiThe corresponding standard fit calculated values.
Preferably, the early warning analysis method comprises two methods of real-time deviation/standard deviation and real-time deviation-standard deviation;
the calculation formula of the early warning analysis method is as follows:
x is s-delta or x is s/delta
Wherein: x is a comparison value of the real-time deviation and the reference standard deviation, delta is the reference standard deviation, and s is the real-time deviation of the real-time monitoring data.
Preferably, the method for judging the early warning level corresponding to the real-time monitoring data includes:
(1) setting a multi-stage early warning index Ii{(0,Ii],(Ii,Ii-1]......(I3,I2],(I2,I1],(I1,+∞)}。
(2) When the contrast value x is judged to belong to the early warning index IiAnd when the current time is within the ith interval, the early warning level is i level.
In a second aspect, in order to solve the above problem, an embodiment of the present invention discloses a mine monitoring data abnormal fluctuation early warning device, preferably, the device is based on mine monitoring data and an abnormal fluctuation early warning index system, and the device includes:
a database query module for step 1: connecting a mine end monitoring database, and inquiring real-time monitoring data and historical monitoring data of various monitoring points of a mine; the monitoring points of the mine represent monitoring points with monitoring values of analog quantity;
an exception filtering module for step 2: performing exception filtering processing on the historical monitoring data in a base number value range according to an exception filtering coefficient to obtain a reference base number for normal monitoring;
a fitting function calculation module for step 3: carrying out segmentation mean calculation on the reference base number according to the set base number granularity to generate a reference base number set, and calculating and generating a corresponding fitting function according to the reference base number set and an early warning fitting mode; wherein, the early warning fitting mode comprises: mean fitting, linear fitting and nonlinear fitting;
a reference standard deviation calculation module for step 4: calculating the corresponding deviation of each element in the reference base number set according to the fitting function to generate a base number deviation set, and calculating and generating a reference standard deviation by using the base number deviation set to serve as a reference value of the normal fluctuation range of the monitoring data of the monitoring point;
an abnormal fluctuation and early warning level judgment module used for the step 5: calculating the real-time deviation of the real-time monitoring data according to a fitting function, calculating a comparison value of the real-time deviation and the reference standard deviation by combining an early warning analysis method, comparing the comparison value with an interval set value of a multi-stage early warning index, judging whether the real-time monitoring data is abnormal fluctuation or not, and judging an early warning level corresponding to the real-time monitoring data;
a display module for step 6: and displaying the fit line corresponding to the fit function, the reference basis number set, the real-time monitoring data and the reference standard deviation in the same coordinate system by adopting different colors and line shapes, and displaying the abnormal fluctuation real-time early warning condition of various measuring points of the whole mine in a point arrangement mode by combining with GIS space map service.
Preferably, the abnormal fluctuation and early warning level determining module includes:
and the interval judgment submodule is used for comparing the comparison value with a multi-stage early warning index interval set value and judging whether the comparison value is in the early warning index interval.
Preferably, the anomaly filtering module includes:
a first exception filtering submodule for processing when
In time, all abnormal data are filtered and removed to obtain the reference base number for normal monitoring, and the step 3 is executed;
a second exception filtering submodule for processing when
Then, the abnormal data is reserved, filtering processing is not carried out, the reference base number of the normal monitoring is obtained, and the step 3 is executed;
a third anomaly filtering submodule, configured to, when k is greater than or equal to 0.5, regard that the data anomaly rate in the value range of the current round is high and cannot be used as the generation of the normal fluctuation reference standard of the monitoring point, continue to use the reference standard deviation of the previous round as the reference standard value for normal monitoring, and skip to execute the step 5;
wherein:
is an abnormal filtering coefficient; k is the anomaly rate.
Preferably, the database query module includes:
the acquisition submodule is used for acquiring historical monitoring data in the time range according to the set base number value range; and the base number value range represents the time length from the current time to a certain historical moment.
Preferably, the fitting function calculation module includes:
the average value obtaining submodule is used for dividing the base number value range into a plurality of time periods according to the value set by the base number granularity, and taking the middle time point of each time period to form a fitting time set Ti(t1,t2,t3,t4......ti) And averaging the reference base numbers in each time period;
a reference radix set composition submodule for composing the average value into the reference radix set Ai{(t1,a1),(t2,a2),(t3,a3)......(ti,ai)}。
Preferably, the reference standard deviation calculating module includes:
the standard fitting set calculation submodule is used for bringing the fitting time set into the fitting function to carry out calculation so as to obtain a standard fitting set corresponding to the reference basis number set;
a cardinal number deviation set obtaining sub-module, configured to obtain the cardinal number deviation set by using the reference cardinal number set and the standard fitting set;
and the reference standard deviation obtaining submodule is used for calculating by utilizing the radix deviation set to obtain the reference standard deviation.
Preferably, the early warning analysis method in the abnormal fluctuation and early warning level judgment module comprises two methods of real-time deviation/standard deviation and real-time deviation-standard deviation;
the calculation formula of the early warning analysis method is as follows:
x is s-delta or x is s/delta
Wherein: x is a comparison value of the real-time deviation and the reference standard deviation; δ is the reference standard deviation; and s is the real-time deviation of the real-time monitoring data.
Preferably, the abnormal fluctuation and early warning level determining module includes:
an early warning index setting submodule for setting a multilevel early warning index Ii{(0,Ii],(Ii,Ii-1]......(I3,I2],(I2,I1],(I1,+∞)}。
An early warning level judgment submodule for judging whether the contrast value x belongs to the early warning index IiAnd when the current time is within the ith interval, the early warning level is i level.
The invention provides a method and a device for early warning abnormal fluctuation of mine monitoring data, which are used for judging whether the real-time monitoring data of various monitoring points are abnormally fluctuated or not, visually displaying the real-time abnormal fluctuation condition of the monitoring data of each area through GIS space map service, identifying the existence of risks through the abnormal fluctuation of the area monitoring, winning precious time for treating hidden risks and greatly reducing the probability of accidents.
Drawings
Fig. 1 is a flowchart of a method for early warning abnormal fluctuation of mine monitoring data according to an embodiment of the present invention;
fig. 2 is a structural diagram of an abnormal fluctuation early warning device for mine monitoring data according to an embodiment of the present invention.
Detailed Description
In order to make the invention point of the embodiment of the present invention clearer, the following clearly and completely describes the early warning method in the embodiment of the present invention with reference to the flowchart of the embodiment of the present invention. The invention provides a method and a device for early warning abnormal fluctuation of mine monitoring data, and the embodiment selects certain type of monitoring data to describe the calculation process.
Referring to fig. 1, fig. 1 is a flowchart of a mine monitoring data abnormal fluctuation early warning method provided by an embodiment of the present invention. As shown in fig. 1, the method comprises the steps of:
step 1, collecting monitoring data of various sensors of a mine, storing the monitoring data in a server, wherein the monitoring data comprises types of monitoring data such as gas concentration, flow, wind speed, roof pressure, water level, water pressure, oxygen concentration, carbon monoxide concentration and the like, and storing the monitoring data in a real-time database and a historical database.
Step 2, configuring an abnormal fluctuation early warning index system, including a fluctuation early warning name, a monitoring data type, an early warning fitting mode, a base number value range, an early warning analysis method and an abnormal filtering coefficient
And the multi-stage early warning index value I and the base number granularity gamma.
(1) The fluctuation early warning name is used for describing the service description of the abnormal fluctuation early warning and is used as the unique identification of the judgment rule.
(2) The monitoring data type is configured to set an abnormal fluctuation monitoring object.
(3) The early warning fitting mode comprises a mean value fitting mode, a nonlinear fitting mode and a linear fitting mode.
(4) The base number value range represents the time length from the current time to a certain historical moment, and historical monitoring data in the time range are obtained according to the set base number value range in the data query process.
(5) Preferably, the early warning analysis method comprises two modes of real-time deviation/standard deviation and real-time deviation-standard deviation.
(6) Coefficient of abnormal filtering
And the reference index is used for filtering abnormal data in the reference value range.
(7) Taking the multi-stage early warning index value as a reference comparison standard for abnormal fluctuation early warning, setting a calculation result of an algorithm according to an early warning analysis method, and performing comparison analysis on the index value to generate early warning real-time data of a corresponding level1Orange secondary early warning I2Yellow three-level early warning I3Blue four-stage early warning I4。
(8) The base granularity gamma is used for determining the time division times of the reference base value range.
Step 3, connecting a mine end monitoring database, inquiring real-time monitoring data and historical monitoring data of various monitoring points of the mine, and acquiring a base number value range in the historical database and the historical monitoring data monitored by various sensors of the mine; and acquiring real-time monitoring data monitored by various sensors of the mine in the real-time database. Wherein various sensors in the step 1 are installed at various monitoring points of the mine, and the various monitoring points of the mine represent monitoring points with monitoring values of analog quantity.
And 4, performing exception filtering processing on the historical monitoring data in the base number value range according to the exception filtering coefficient to obtain a reference base number for normal monitoring. The abnormal filtering process is to compare the relation between the ratio k (abnormal rate) of the abnormal data volume to the total data volume in the base value range and the filtering coefficient alpha to determine whether to filter the abnormal data volume, and the specific judgment logic is as follows:
(1) when in use
And (5) filtering and removing all abnormal data to obtain the reference base number for normal monitoring, and executing the step.
(2) When in use
And (5) keeping abnormal data, not performing filtering processing, obtaining the reference base number of the normal monitoring, and executing the step 5.
(3) And when k is more than or equal to 0.5, regarding that the data abnormal rate in the value range of the current round is higher and can not be used for generating the normal fluctuation reference standard of the monitoring point, continuing to use the reference standard difference of the previous round as the reference standard value of the normal fluctuation range, and skipping to execute the step 8.
Wherein:
and k is an abnormal filtering coefficient, and is an abnormal rate, namely the ratio of the number of the monitoring data to the total monitoring data in the numeric range of the base number.
Step 5, dividing the base number value range into a plurality of time periods according to the value set by the base number granularity gamma, and taking the middle time point of each time period to form a fitting time set Ti(t1,t2,t3,t4......ti) And averaging the reference base numbers in each time period, wherein the average value set generated by calculation of each time period is called as a reference base number set Ai{(t1,a1),(t2,a2),(t3,a3)......(ti,ai)}。
Step 6, respectively calculating corresponding fitting functions of three modes of mean fitting, nonlinear fitting and linear fitting according to the reference basis number set and the set early warning fitting mode, and setting the fitting time set Ti(t1,t2,t3,t4.....iT) substituting the reference basis number set into the fitting function to calculate to obtain a standard fitting set B corresponding to the reference basis number seti{(t1,b1),(t2,b2),(t3,b3)......(ti,bi)}。
Step 7, calculating the corresponding deviation of each element in the reference base number set according to the fitting function to generate a base number deviation set Ci{(a1-b1),(a2-b2),(a3-b3)......(ai-bi) I.e. the true reference value AiSubtract the fitting value BiObtaining the corresponding deviation of each element, and forming the deviation into a deviation set. And calculating and generating standard deviation as a reference value of a normal fluctuation range by using a base number deviation set, namely historical monitoring data is simulatedThe normal range of line fluctuation is calculated as follows:
wherein: delta is the reference standard deviation, N is the number of elements in the reference radix set, aiReference base corresponding to fitting time, biCalculated values for the standard fit corresponding to the time of the fit.
Step 8, inquiring real-time monitoring data in the database, and calculating the real-time deviation of the real-time monitoring value by combining a fitting function, wherein the real-time deviation calculation process is as follows:
setting real-time monitoring data points R (t, v) and corresponding fitting standard points as Bt(t,bt) Then the real-time offset is calculated as follows:
s＝|ν-bt|
wherein: v is the value in the real-time monitoring data corresponding to the t time point, btAnd s is a real-time deviation corresponding to a numerical value in the real-time monitoring data at the t time point.
Step 9, calculating a comparison value of the real-time deviation and the reference standard deviation by combining an early warning analysis method to obtain a comparison value x, comparing the comparison value with the interval set value of the multi-stage early warning indexes, and judging whether the comparison value is in the early warning index interval or not;
if not, skipping to execute the step 3;
if yes, judging whether the state of the measuring point is a continuous early warning state or not; if so, updating the real-time early warning state, for example, the previous yellow three-level early warning, and the current contrast value is in a red first-level early warning interval, so that the early warning state is updated from the yellow three-level early warning to the red first-level early warning; if not, generating abnormal fluctuation real-time early warning data, marking the real-time monitoring data as abnormal monitoring data and storing the abnormal monitoring data, participating in data abnormal filtering calculation in the next calculation process, and skipping to execute the step 3;
wherein, the early warning analysis partyThe method comprises the following steps: the real-time deviation/standard deviation and the real-time deviation-standard deviation are two types, and the early warning level judgment interval comprises: red first-class warning [ I1Infinity), orange two-stage warning [ I2,I1) Yellow three-level early warning [ I)3,I2) Blue four-stage warning [ I ]4,I3)。
The specific calculation formula of the early warning analysis method is as follows:
x is s-delta or x is s/delta
Wherein: x is a comparison value of the real-time deviation and the reference standard deviation; δ is a reference standard deviation; and s is the real-time deviation of the current monitoring value.
In addition, the early warning level corresponding to the real-time monitoring data needs to be judged, and the method comprises the following steps:
(1) setting a multi-stage early warning index Ii{(0,Ii],(Ii,Ii-1]......(I3,I2],(I2,I1],(I1,+∞)}。
(2) When the contrast value x is judged to belong to the early warning index IiAnd when the current time is within the ith interval, the early warning level is i level.
The beneficial effects of this embodiment are as follows:
the invention provides a method and a device for early warning abnormal fluctuation of mine monitoring data, which are used for judging whether the real-time monitoring data of various monitoring points are abnormally fluctuated or not, visually displaying the real-time abnormal fluctuation condition of the monitoring data of each area through GIS space map service, identifying the existence of risks through the abnormal fluctuation of the area monitoring, winning precious time for treating hidden risks and greatly reducing the probability of accidents.
In another embodiment, referring to fig. 2, a structural diagram of an abnormal fluctuation early warning device for mine monitoring data according to the present invention is shown, and specifically includes the following modules:
a database query module 21, configured to perform the following steps: connecting a mine end monitoring database, and inquiring real-time monitoring data and historical monitoring data of various monitoring points of a mine; and the various monitoring points of the mine represent monitoring points with monitoring values of analog quantity.
In an optional implementation manner, the database query module 21 includes:
the acquisition submodule is used for acquiring historical monitoring data in the time range according to the set base number value range; and the base number value range represents the time length from the current time to a certain historical moment.
An exception filtering module 22 for step 2: and carrying out exception filtering processing on the historical monitoring data in the base number value range according to the exception filtering coefficient to obtain a reference base number for normal monitoring.
In an alternative implementation, the exception filtering module 22 includes:
a first exception filtering submodule for processing when
In time, all abnormal data are filtered and removed to obtain the reference base number for normal monitoring, and the step 3 is executed;
a second exception filtering submodule for processing when
Then, the abnormal data is reserved, filtering processing is not carried out, the reference base number of the normal monitoring is obtained, and the step 3 is executed;
a third anomaly filtering submodule, configured to, when k is greater than or equal to 0.5, regard that the data anomaly rate in the value range of the current round is high and cannot be used as the generation of the normal fluctuation reference standard of the monitoring point, continue to use the reference standard deviation of the previous round as the reference standard value for normal monitoring, and skip to execute the step 5;
wherein:
is an abnormal filtering coefficient; k is the anomaly rate.
A fitting function calculation module 23, configured to perform, in step 3: carrying out segmentation mean calculation on the reference base number according to the set base number granularity to generate a reference base number set, and calculating and generating a corresponding fitting function according to the reference base number set and an early warning fitting mode; wherein, the early warning fitting mode comprises: mean fit, linear fit, and nonlinear fit.
In an alternative implementation, the fitting function calculation module 23 includes:
the average value obtaining submodule is used for dividing the base number value range into a plurality of time periods according to the value set by the base number granularity, and taking the middle time point of each time period to form a fitting time set Ti(t1,t2,t3,t4......ti) And averaging the reference base numbers in each time period;
a reference radix set composition submodule for composing the average value into the reference radix set Ai{(t1,a1),(t2,a2),(t3,a3)......(ti,ai)}。
A reference standard deviation calculation module 24 for step 4: and calculating the corresponding deviation of each element in the reference base number set according to the fitting function to generate a base number deviation set, and calculating and generating a reference standard deviation by using the base number deviation set to serve as a reference value of the normal fluctuation range of the monitoring data of the monitoring point.
In an alternative implementation, the reference standard deviation calculation module 24 includes:
the standard fitting set calculation submodule is used for bringing the fitting time set into the fitting function to carry out calculation so as to obtain a standard fitting set corresponding to the reference basis number set;
a cardinal number deviation set obtaining sub-module, configured to obtain the cardinal number deviation set by using the reference cardinal number set and the standard fitting set;
and the reference standard deviation obtaining submodule is used for calculating by utilizing the radix deviation set to obtain the reference standard deviation.
An abnormal fluctuation and early warning level judgment module 25, configured to step 5: calculating the real-time deviation of the real-time monitoring data according to a fitting function, calculating a comparison value of the real-time deviation and the reference standard deviation by combining an early warning analysis method, comparing the comparison value with an interval set value of a multi-stage early warning index, judging whether the real-time monitoring data is abnormal fluctuation or not, and judging an early warning level corresponding to the real-time monitoring data.
In an optional implementation manner, the abnormal fluctuation and early warning level determining module 25 includes:
and the interval judgment submodule is used for comparing the comparison value with a multi-stage early warning index interval set value and judging whether the comparison value is in the early warning index interval.
In an optional implementation manner, the abnormal fluctuation and early warning level determining module 25 further includes:
the early warning analysis method in the abnormal fluctuation and early warning level judgment module comprises two methods of real-time deviation/standard deviation and real-time deviation-standard deviation;
the calculation formula of the early warning analysis method is as follows:
x is s-delta or x is s/delta
Wherein: x is a comparison value of the real-time deviation and the reference standard deviation; δ is the reference standard deviation; and s is the real-time deviation of the real-time monitoring data.
And a display module 26, configured to display the fit line corresponding to the fit function, the reference basis number set, the real-time monitoring data, and the reference standard deviation in the same coordinate system in different colors and line shapes in step 6, and display the abnormal fluctuation real-time early warning conditions of various measuring points in the whole mine in a point arrangement manner by combining with a GIS space map service.
The mine monitoring data abnormal fluctuation early warning method and the mine monitoring data abnormal fluctuation early warning device provided by the invention are introduced in detail, a specific example is applied in the method to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (9)
1. The mine monitoring data abnormal fluctuation early warning method is characterized by being based on a mine monitoring data and abnormal fluctuation early warning index system, and specifically comprises the following steps:
step 1: connecting a mine end monitoring database, and inquiring real-time monitoring data and historical monitoring data of various monitoring points of a mine; the monitoring points of the mine represent monitoring points with monitoring values of analog quantity;
step 2: performing exception filtering processing on the historical monitoring data in a base number value range according to an exception filtering coefficient to obtain a reference base number for normal monitoring;
and step 3: carrying out segmentation mean calculation on the reference base number according to the set base number granularity to generate a reference base number set, and calculating and generating a corresponding fitting function according to the reference base number set and an early warning fitting mode; wherein, the early warning fitting mode comprises: mean fitting, linear fitting and nonlinear fitting;
and 4, step 4: calculating the corresponding deviation of each element in the reference base number set according to the fitting function to generate a base number deviation set, and calculating and generating a reference standard deviation by using the base number deviation set to serve as a reference value of the normal fluctuation range of the monitoring data of the monitoring point;
and 5: calculating the real-time deviation of the real-time monitoring data according to a fitting function, calculating a comparison value of the real-time deviation and the reference standard deviation by combining an early warning analysis method, comparing the comparison value with an interval set value of a multi-stage early warning index, judging whether the real-time monitoring data is abnormal fluctuation or not, and judging an early warning level corresponding to the real-time monitoring data;
step 6: and displaying the fit line, the reference basis number set, the real-time monitoring data and the reference standard deviation corresponding to the fit function in the same coordinate system by adopting different colors and linear shapes, and displaying the abnormal fluctuation real-time early warning condition of various monitoring points of the mine in a point arrangement mode by combining with GIS space map service.
2. The method of claim 1, wherein the step of determining whether the real-time monitoring data is abnormally fluctuating comprises:
comparing the comparison value with a multi-stage early warning index interval set value, and judging whether the comparison value is in the early warning index interval;
if not, skipping to execute the step 2;
if yes, judging whether various monitoring points of the mine are in a continuous early warning state; if yes, updating the real-time early warning state; if not, generating abnormal fluctuation real-time early warning data, marking the real-time monitoring data as abnormal monitoring data and storing the abnormal monitoring data, participating in data abnormal filtering calculation in the next calculation process, and skipping to execute the step 2.
3. The method of claim 1, wherein the obtaining a monitored normal reference base comprises:
(1) when in use
In time, all abnormal data are filtered and removed to obtain the reference base number for normal monitoring, and the step 3 is executed;
(2) when in use
Then, the abnormal data is reserved, filtering processing is not carried out, the reference base number of the normal monitoring is obtained, and the step 3 is executed;
(3) when k is more than or equal to 0.5, regarding that the data abnormal rate in the value range of the current round is high and can not be used for generating the normal fluctuation reference standard of the monitoring point, continuing to use the reference standard difference of the previous round as the reference standard value for normal monitoring, and skipping to execute the step 5;
wherein:
is an abnormal filtering coefficient; k is the anomaly rate.
4. The method of claim 1, wherein the step of generating a reference radix set by performing a segmentation mean calculation on the reference radix by the set radix granularity comprises:
dividing the base number value range into a plurality of time periods according to the value set by the base number granularity, and taking the middle time point of each time period to form a fitting time set Ti(t1,t2,t3,t4......ti) And averaging the reference base numbers in each time period;
forming the average value into the reference base number set Ai{(t1,a1),(t2,a2),(t3,a3)......(ti,ai)}。
5. The method of claim 4, wherein the method of using the radix bias set to compute the generated reference standard deviation comprises:
the fitting time set is brought into the fitting function for calculation to obtain a standard fitting set B corresponding to the reference basis number seti{(t1,b1),(t2,b2),(t3,b3)......(ti,bi)}；
Obtaining the radix deviation set by utilizing the reference radix set and the standard fitting set;
calculating by using the radix deviation set to obtain the reference standard deviation; wherein the reference standard deviation is calculated as follows:
wherein: delta is the reference standard deviation, N is the number of elements in the reference radix set, aiAs fitting time tiCorresponding reference base, biAs fitting time tiThe corresponding standard fit calculated values.
6. The method of claim 1, wherein the early warning analysis method comprises both "real-time deviation/standard deviation" and "real-time deviation-standard deviation";
the calculation formula of the early warning analysis method is as follows:
x is s-delta or x is s/delta
Wherein: x is a comparison value of the real-time deviation and the reference standard deviation, delta is the reference standard deviation, and s is the real-time deviation of the real-time monitoring data.
7. The method according to claim 1 or 6, wherein the method for judging the early warning level corresponding to the real-time monitoring data comprises the following steps:
(1) setting a multi-stage early warning index Ii{(0,Ii],(Ii,Ii-1]......(I3,I2],(I2,I1],(I1,+∞)}；
(2) When the contrast value x is judged to belong to the early warning index IiAnd when the current time is within the ith interval, the early warning level is i level.
8. The utility model provides a mine monitoring data abnormal fluctuation early warning device which characterized in that, the device is based on mine monitoring data and abnormal fluctuation early warning index system, the device includes:
a database query module for step 1: connecting a mine end monitoring database, and inquiring real-time monitoring data and historical monitoring data of various monitoring points of a mine; the monitoring points of the mine represent monitoring points with monitoring values of analog quantity;
an exception filtering module for step 2: performing exception filtering processing on the historical monitoring data in a base number value range according to an exception filtering coefficient to obtain a reference base number for normal monitoring;
a fitting function calculation module for step 3: carrying out segmentation mean calculation on the reference base number according to the set base number granularity to generate a reference base number set, and calculating and generating a corresponding fitting function according to the reference base number set and an early warning fitting mode; wherein, the early warning fitting mode comprises: mean fitting, linear fitting and nonlinear fitting;
a reference standard deviation calculation module for step 4: calculating the corresponding deviation of each element in the reference base number set according to the fitting function to generate a base number deviation set, and calculating and generating a reference standard deviation by using the base number deviation set to serve as a reference value of the normal fluctuation range of the monitoring data of the monitoring point;
an abnormal fluctuation and early warning level judgment module used for the step 5: calculating the real-time deviation of the real-time monitoring data according to a fitting function, calculating a comparison value of the real-time deviation and the reference standard deviation by combining an early warning analysis method, comparing the comparison value with an interval set value of a multi-stage early warning index, judging whether the real-time monitoring data is abnormal fluctuation or not, and judging an early warning level corresponding to the real-time monitoring data;
a display module for step 6: and displaying the fit line, the reference basis number set, the real-time monitoring data and the reference standard deviation corresponding to the fit function in the same coordinate system by adopting different colors and linear shapes, and displaying the abnormal fluctuation real-time early warning condition of various monitoring points of the mine in a point arrangement mode by combining with GIS space map service.
9. The apparatus of claim 8, wherein the abnormal fluctuation and early warning level determination module comprises:
and the interval judgment submodule is used for comparing the comparison value with a multi-stage early warning index interval set value and judging whether the comparison value is in the early warning index interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010015748.4A CN111173565B (en) | 2020-01-07 | 2020-01-07 | Mine monitoring data abnormal fluctuation early warning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010015748.4A CN111173565B (en) | 2020-01-07 | 2020-01-07 | Mine monitoring data abnormal fluctuation early warning method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111173565A CN111173565A (en) | 2020-05-19 |
| CN111173565B true CN111173565B (en) | 2021-02-09 |
Family
ID=70652629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010015748.4A Active CN111173565B (en) | 2020-01-07 | 2020-01-07 | Mine monitoring data abnormal fluctuation early warning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111173565B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112185086B (en) * | 2020-10-12 | 2022-03-15 | 合肥弘恩机电科技有限公司 | Grain depot safety early warning system based on deviation analysis |
| CN112597144B (en) * | 2020-12-29 | 2022-11-08 | 农业农村部环境保护科研监测所 | Automatic cleaning method for production place environment monitoring data |
| CN113623005B (en) * | 2021-09-06 | 2024-03-26 | 中煤科工集团沈阳研究院有限公司 | Mixed gas recognition method for coal seam group exploitation |
| CN115471796B (en) * | 2022-11-14 | 2023-03-24 | 河北电力工程监理有限公司 | Power grid engineering supervision system and method based on machine vision |
| CN116205087B (en) * | 2023-05-05 | 2023-07-14 | 安徽中科大国祯信息科技有限责任公司 | Rain and sewage drainage pipe network anomaly analysis method and device based on edge computing gateway |
| CN116701731B (en) * | 2023-06-08 | 2024-04-05 | 费莱(浙江)科技有限公司 | Dynamic monitoring and early warning method for operation stability in life cycle of motor |
| CN116449761B (en) * | 2023-06-13 | 2023-10-13 | 中苏科技股份有限公司 | Intelligent pump station intelligent control system and method |
| CN117097639B (en) * | 2023-08-16 | 2024-01-30 | 广州尚全信息技术有限公司 | Real-time prompting method and system for network risk |
| CN116992390B (en) * | 2023-09-26 | 2023-12-05 | 北京联创高科信息技术有限公司 | Configuration and display method of abnormal data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SU1588876A1 (en) * | 1988-09-05 | 1990-08-30 | Специализированное Монтажно-Наладочное Управление Производственного Объединения "Гордормост" | Electronic diagnostic bench for checking operability of functional elements |
| CN105240052B (en) * | 2015-11-11 | 2017-07-04 | 中煤科工集团重庆研究院有限公司 | Coal mine gas disaster monitoring and early warning information acquisition system and acquisition method |
| CN108301872B (en) * | 2018-02-28 | 2020-03-31 | 山东科技大学 | Visual mine real-time monitoring alarm system and method based on data filtering |
| CN108829535A (en) * | 2018-06-08 | 2018-11-16 | 上海擎创信息技术有限公司 | Data processing method, terminal and computer readable storage medium |
| CN110377447B (en) * | 2019-07-17 | 2022-07-22 | 腾讯科技（深圳）有限公司 | Abnormal data detection method and device and server |
-
2020
- 2020-01-07 CN CN202010015748.4A patent/CN111173565B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111173565A (en) | 2020-05-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111173565B (en) | Mine monitoring data abnormal fluctuation early warning method and device | |
| CN109583680B (en) | Power stealing identification method based on support vector machine | |
| CN107169426B (en) | Crowd emotion abnormality detection and positioning method based on deep neural network | |
| WO2020063819A1 (en) | Real-time data analysis method for pipe network, and device | |
| CN113344133B (en) | Method and system for detecting abnormal fluctuation of time sequence behaviors | |
| CN112216071A (en) | Intelligent chemical monitoring and early warning platform based on big data | |
| CN111259334A (en) | Monitoring and early warning method for water use abnormity of large users of industrial enterprises | |
| CN110569248B (en) | Improved SPC (selective pressure control) residential water supply leakage monitoring and early warning method | |
| CN109947815B (en) | Power theft identification method based on outlier algorithm | |
| CN115358647A (en) | Hydrogen energy industry chain risk monitoring system and monitoring method based on big data | |
| CN106774187A (en) | The system and method for automatic monitoring production line beat | |
| CN112380599A (en) | Bridge intelligent online monitoring and early warning system based on big data analysis | |
| CN113534727B (en) | Early warning control system of refrigeration equipment for fishing boat based on artificial intelligence platform | |
| CN114925860A (en) | Fault diagnosis method and system for air separation equipment | |
| CN111312414A (en) | Fatigue evaluation method of nuclear power plant fatigue monitoring and life evaluation system | |
| CN107829780B (en) | A kind of gas false alarm recognition methods based on coal mine safety monitoring networked system | |
| CN108108665B (en) | Multivariable-based safety early warning method for gas pressure regulator | |
| CN117130332A (en) | Intelligent monitoring system for production line of military industry enterprise based on data analysis | |
| CN112149823A (en) | Combined implementation method for filtering alarm information | |
| CN113159503B (en) | Remote control intelligent safety evaluation system and method | |
| CN114969068A (en) | Method and system for analyzing real-time flow monitoring data of urban pressure pipe network | |
| CN116150239B (en) | Data mining method for gas stealing behavior | |
| CN117330896B (en) | Rapid early warning system for low-current grounding line selection alarm | |
| CN111271981B (en) | Metallurgical furnace temperature monitoring method and monitoring system | |
| CN117216694A (en) | Gas data anomaly detection method based on time sequence |
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 |