CN117605539A - Intelligent early warning system and method for monitoring coal mine water damage - Google Patents
Intelligent early warning system and method for monitoring coal mine water damage Download PDFInfo
- Publication number
- CN117605539A CN117605539A CN202311709753.5A CN202311709753A CN117605539A CN 117605539 A CN117605539 A CN 117605539A CN 202311709753 A CN202311709753 A CN 202311709753A CN 117605539 A CN117605539 A CN 117605539A
- Authority
- CN
- China
- Prior art keywords
- data
- coal mine
- target
- mine environment
- environment data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000003245 coal Substances 0.000 title claims abstract description 350
- 238000000034 method Methods 0.000 title claims abstract description 57
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 41
- 238000012544 monitoring process Methods 0.000 title claims abstract description 36
- 230000002159 abnormal effect Effects 0.000 claims abstract description 238
- 238000012937 correction Methods 0.000 claims abstract description 22
- 238000010276 construction Methods 0.000 claims abstract description 7
- 238000005070 sampling Methods 0.000 claims description 133
- 230000005856 abnormality Effects 0.000 claims description 86
- 230000007613 environmental effect Effects 0.000 claims description 36
- 230000008859 change Effects 0.000 claims description 28
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 4
- 238000012545 processing Methods 0.000 abstract description 2
- 230000002547 anomalous effect Effects 0.000 description 3
- 238000004880 explosion Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 239000011435 rock Substances 0.000 description 2
- 238000006424 Flood reaction Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mining & Mineral Resources (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Probability & Statistics with Applications (AREA)
- Geochemistry & Mineralogy (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to an intelligent early warning system and method for monitoring coal mine water damage, comprising the following steps: acquiring a coal mine environment data sequence; acquiring all target abnormal data of a coal mine environment data sequence; acquiring an anomaly score correction factor of each target anomaly data according to the comprehensive anomaly confidence coefficient of each target anomaly data in the coal mine environment data sequence; and acquiring all real abnormal data in the coal mine environment data sequence according to the abnormal score correction factors of each target abnormal data, and further monitoring the construction environment in the coal mine. The invention ensures that the early warning effect of the coal mine early warning system is more accurate.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an intelligent early warning system and method for monitoring coal mine water damage.
Background
In the construction and production processes of the coal mine, water seepage and water burst phenomena can be possibly generated underground. Ground water and underground water flow into the mine through various channels, and when the water flowing into the mine exceeds the normal water draining capacity of the mine, the mine floods are caused, so that normal production of the mine is affected, casualties are caused, and the damage is serious. Therefore, the method monitors hydrologic, geological, environmental and other data in the coal mine in real time, and adopts early warning measures for water damage accidents, which is an important link for ensuring the smooth progress of engineering. The monitoring of the environmental data such as humidity, temperature, gas concentration and the like in the coal mine can discover environmental abnormality in the mine in time, prevent water damage caused by water level rising, rock formation deformation, gas explosion and the like, and effectively prevent and reduce the occurrence of the water damage of the coal mine, so that the monitoring of the environmental data of the coal mine has important significance for preventing the water damage. When monitoring and analyzing the abnormality of the coal mine environment data, one common algorithm is an isolated forest algorithm, the algorithm is started from abnormal points, the abnormal points are divided by a formulated rule, and the abnormality scores of all the data are obtained according to a plurality of dividing times, so that the abnormal data are judged.
Noise data is generated in the coal mine environment data due to environmental factors and equipment problems in the coal mine, when the coal mine environment data is monitored and analyzed by using an isolated forest algorithm, whether the data are abnormal or not is judged according to the isolation degree of the data, the isolation degree of the noise data is always higher and even higher than that of real abnormal data, so that the abnormality scores of the noise data are higher, the real abnormal data and the noise data cannot be distinguished, the analysis and prediction of a system are deviated, and the system cannot timely send early warning through an alarm of a control system.
Disclosure of Invention
In order to solve the problems, the invention provides an intelligent early warning system and method for monitoring water damage of a coal mine.
The embodiment of the invention provides an intelligent early warning method for monitoring coal mine water damage, which comprises the following steps:
acquiring a coal mine environment data sequence, wherein the coal mine environment data sequence comprises coal mine environment data at a plurality of sampling moments, and the coal mine environment data at each sampling moment refers to coal mine temperature data, coal mine humidity data and coal mine gas concentration data at each sampling moment;
acquiring an abnormal score of the coal mine environment data at each sampling moment through an isolated forest algorithm, and screening the coal mine environment data according to the abnormal score to obtain all target abnormal data;
arranging all the target abnormal data according to the time sequence of the sampling moment to obtain a target abnormal data sequence; acquiring adjacent abnormal data segments of each target abnormal data in the target abnormal data sequence; acquiring adjacent range data segments of each target abnormal data in a coal mine environment data sequence; acquiring comprehensive anomaly confidence coefficient of each target anomaly data according to the anomaly score difference of each target anomaly data and other target anomaly data in the adjacent anomaly data segment and the coal mine humidity data difference of each target anomaly data and coal mine environment data at other sampling moments in the adjacent range data segment; acquiring an anomaly score correction factor of each target anomaly data according to the comprehensive anomaly confidence coefficient of each target anomaly data and the difference between each target anomaly data and coal mine environment data at other sampling moments in the adjacent range data segment;
correcting the abnormal score of each target abnormal data according to the abnormal score correction factors, and screening the coal mine environment data according to the corrected abnormal score to obtain all real abnormal data; and monitoring the construction environment in the coal mine according to the distribution of the real abnormal data in the coal mine environment data sequence.
Preferably, the method for screening the coal mine environment data according to the anomaly score to obtain all target anomaly data comprises the following specific steps:
a threshold T1 is preset, and if the abnormality score of the coal mine environment data at any sampling time in the coal mine environment data sequence is greater than or equal to T1, the coal mine environment data at the sampling time is recorded as target abnormality data of the coal mine environment data sequence, so that all target abnormality data of the coal mine environment data sequence are obtained.
Preferably, the method for acquiring the adjacent abnormal data segment of each target abnormal data in the target abnormal data sequence includes the following specific steps:
presetting a parameter a, and regarding the data segment formed by the first a target abnormal data of the ith target abnormal data and the last a target abnormal data of the ith target abnormal data in the target abnormal data sequence as the adjacent abnormal data segment of the ith target abnormal data.
Preferably, the method for acquiring the adjacent range data segment of each target abnormal data in the coal mine environment data sequence includes the following specific steps:
and regarding the kth target abnormal data in the coal mine environment data sequence, taking a data segment formed by the coal mine environment data of the first a sampling moments of the kth target abnormal data and the coal mine environment data of the last a sampling moments of the kth target abnormal data as a neighboring range data segment of the kth target abnormal data, wherein a is a preset parameter.
Preferably, the method for obtaining the comprehensive anomaly confidence coefficient of each target anomaly data according to the anomaly score difference between each target anomaly data and other target anomaly data in the adjacent anomaly data segment and the coal mine humidity data difference between each target anomaly data and coal mine environment data at other sampling moments in the adjacent range data segment comprises the following specific steps:
acquiring the abnormality degree of the adjacent area of each target abnormal data in the coal mine environment data sequence according to the abnormality score difference of each target abnormal data and other target abnormal data in the adjacent abnormal data segment; acquiring the range abnormality degree of each target abnormality data in the coal mine environment data sequence according to the coal mine humidity data difference of each target abnormality data and the coal mine environment data at other sampling moments in the adjacent range data segment;
and taking the product of the adjacent area abnormality degree of each target abnormality data in the coal mine environment data sequence and the range abnormality degree of each target abnormality data in the coal mine environment data sequence as the comprehensive abnormality confidence of each target abnormality data.
Preferably, the specific formula for obtaining the abnormality degree of the adjacent area of each target abnormal data in the coal mine environment data sequence according to the abnormality score difference between each target abnormal data and other target abnormal data in the adjacent abnormal data segment is as follows:
in the method, in the process of the invention,representing the degree of abnormality of the adjacent area of the ith target abnormal data of the coal mine environment data sequence; t is t i Representing the sampling moment corresponding to the ith target abnormal data of the coal mine environment data sequence; t is t i,j The sampling time corresponding to the j-th target abnormal data in the adjacent abnormal data segment of the i-th target abnormal data of the coal mine environment data sequence is represented; h is a i An anomaly score representing the ith target anomaly data of the coal mine environment data sequence; h is a i,j An anomaly score for the jth target anomaly data in a neighboring anomaly data segment representing the ith target anomaly data of the coal mine environmental data sequence; a is a preset parameter; the absolute value is taken; norm () represents a linear normalization function.
Preferably, the method for obtaining the range abnormality degree of each target abnormality data in the coal mine environment data sequence according to the coal mine humidity data difference between each target abnormality data and the coal mine environment data at other sampling moments in the adjacent range data segment includes the following specific steps:
regarding coal mine environment data at a v sampling moment in a data section of an adjacent range of the kth target abnormal data, taking the absolute value of the difference value of the coal mine humidity data of the coal mine environment data at the v sampling moment and the coal mine humidity data of the coal mine environment data at the v+1 sampling moment as the first-order difference degree of the humidity of the coal mine environment data at the v sampling moment; taking the absolute value of the difference value of the first-order difference degree of the humidity of the coal mine environment data at the v sampling moment and the first-order difference degree of the humidity of the coal mine environment data at the v+1th sampling moment as the second-order difference degree of the humidity of the coal mine environment data at the v sampling moment; the range abnormality degree calculation method of the kth target abnormality data of the coal mine environment data sequence comprises the following steps:
in the method, in the process of the invention,representing the range abnormality degree of the kth target abnormality data of the coal mine environment data sequence; ΔH2 k,v A first-order difference degree of the humidity of the coal mine environment data at the v sampling moment in the adjacent range data segment of the kth target abnormal data of the coal mine environment data sequence is represented; ΔH2 k,v A second-order difference degree of humidity of the coal mine environment data at a v-th sampling time in a data segment of an adjacent range of the kth target abnormal data of the coal mine environment data sequence is represented; a is a preset parameter; norm () represents a linear normalization function.
Preferably, the obtaining the abnormality score correction factor of each target abnormal data according to the comprehensive abnormal confidence coefficient of each target abnormal data and the differences between each target abnormal data and the coal mine environment data at other sampling moments in the adjacent range data segment includes the following specific methods:
for the kth target abnormal data in the coal mine environment data sequence, acquiring the environment data change speed and environment data change quantity of the kth target abnormal data in the coal mine environment data sequence; the calculation method of the anomaly score correction factor of the kth target anomaly data in the coal mine environment data sequence comprises the following steps:
in delta k An anomaly score correction factor representing kth target anomaly data in the coal mine environment data sequence; q (Q) k The environmental data change speed of the kth target abnormal data in the coal mine environmental data sequence is represented; w (W) k The environmental data variable quantity of the kth target abnormal data in the coal mine environmental data sequence is represented;representing the comprehensive anomaly confidence of the kth target anomaly data in the coal mine environment data sequence; norm () represents a linear normalization function.
Preferably, the method for acquiring the environmental data change speed and the environmental data change amount of the kth target abnormal data in the coal mine environmental data sequence comprises the following specific steps:
regarding the coal mine environment data of the v sampling moment in the adjacent range data segment of the kth target abnormal data in the coal mine environment data sequence, taking the absolute value of the difference value of the coal mine temperature data of the coal mine environment data of the v sampling moment and the coal mine temperature data of the coal mine environment data of the v+1 sampling moment as the first-order temperature difference degree of the coal mine environment data of the v sampling moment; taking the absolute value of the difference value of the first-order temperature difference of the coal mine environment data at the v sampling moment and the first-order temperature difference of the coal mine environment data at the v+1th sampling moment as the second-order temperature difference of the coal mine environment data at the v sampling moment; taking the absolute value of the difference value of the coal mine gas concentration data of the coal mine environment data at the v sampling moment and the coal mine gas concentration data of the coal mine environment data at the v+1th sampling moment as the first-order difference degree of the gas concentration of the coal mine environment data at the v sampling moment; taking the absolute value of the difference between the first-order difference of the gas concentration of the coal mine environment data at the v-th sampling moment and the first-order difference of the gas concentration of the coal mine environment data at the v+1th sampling moment as the second-order difference of the gas concentration of the coal mine environment data at the v-th sampling moment; the calculation method of the environmental data change speed and the environmental data change amount of the kth target abnormal data in the coal mine environmental data sequence comprises the following steps:
wherein DeltaH 1 k,v A first-order difference degree of the humidity of the coal mine environment data at the v sampling moment in the adjacent range data segment of the kth target abnormal data of the coal mine environment data sequence is represented; ΔH2 k,v A second-order difference degree of humidity of the coal mine environment data at a v-th sampling time in a data segment of an adjacent range of the kth target abnormal data of the coal mine environment data sequence is represented; ΔC1 k,v A first-order difference degree of gas concentration of the coal mine environment data at a v-th sampling time in a data segment of a neighboring range of the kth target abnormal data of the coal mine environment data sequence is represented; Δc2 k,v A second-order difference degree of gas concentration of the coal mine environment data at the v sampling moment in a data segment of a neighboring range of the kth target abnormal data of the coal mine environment data sequence is represented; Δf1 k,v A first-order temperature difference of the coal mine environment data at the v sampling moment in the adjacent range data segment of the kth target abnormal data of the coal mine environment data sequence is represented; Δf2 k,v A second-order temperature difference of the coal mine environment data at the v sampling moment in the adjacent range data segment of the kth target abnormal data of the coal mine environment data sequence is represented; a is a preset parameter; the absolute value is taken.
The invention also provides an intelligent early warning system for monitoring the water damage of the coal mine, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of any one of the intelligent early warning method for monitoring the water damage of the coal mine when executing the computer program.
The technical scheme of the invention has the beneficial effects that: according to the method, the abnormal score correction factors of each target abnormal data are obtained according to the comprehensive abnormal confidence coefficient of each target abnormal data and the differences of the coal mine environment data at other sampling moments in the data segments of the adjacent range, the corrected abnormal score of each target abnormal data is obtained according to the abnormal score correction factors of each target abnormal data, all real abnormal data are obtained by screening the coal mine environment data according to the corrected abnormal score, the real abnormal data and the noise data in the coal mine environment data sequence are distinguished, and the construction environment in the coal mine is monitored according to the distribution of the real abnormal data in the coal mine environment data sequence, so that the early warning effect of a coal mine early warning system is more accurate.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of an intelligent early warning method for monitoring coal mine water damage.
Detailed Description
In order to further explain the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of the intelligent early warning system and method for monitoring coal mine water damage according to the invention, which are provided by the invention, with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a concrete scheme of an intelligent early warning system and method for monitoring coal mine water damage, which are specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a step flow chart of an intelligent early warning method for monitoring coal mine water damage according to an embodiment of the invention is shown, and the method comprises the following steps:
step S001: and acquiring a coal mine environment data sequence.
It should be noted that, environmental data such as humidity, temperature, gas concentration in the monitored coal mine can discover in time that the environment in the mine is unusual, prevent that water damage's phenomenon from possibly causing such as rising of water level, rock stratum deformation, gas explosion from appearing, effectively prevent and alleviate colliery water damage's emergence, so colliery environmental data's monitoring has more important meaning to the prevention of water damage.
Specifically, in order to implement the intelligent early warning method for monitoring the water damage of the coal mine provided by the embodiment, a coal mine environment data sequence needs to be acquired at first, and the specific process is as follows:
the embodiment presets that each 3 minutes is a sampling time, and three dimensional data types, namely coal mine temperature data, coal mine humidity data and coal mine gas concentration data, are collected through a mining humidity sensor, a mining temperature sensor and a gas concentration detector in sequence each time, and the collection is carried out for 24 hours; and taking three dimensional data of coal mine temperature data, coal mine humidity data and coal mine gas concentration data at each sampling moment as a coal mine environment data sequence.
The coal mine environment data sequence comprises coal mine environment data of a plurality of sampling moments, wherein the coal mine environment data of each sampling moment refers to coal mine temperature data, coal mine humidity data and coal mine gas concentration data of each sampling moment.
So far, the coal mine environment data sequence is obtained through the method.
Step S002: and acquiring all target abnormal data of the coal mine environment data sequence.
When monitoring and analyzing the abnormality of the coal mine environment data, one common algorithm is an isolated forest algorithm, which is sent out from abnormal points, is divided by a set rule, and obtains the abnormality scores of all the data according to a plurality of division times, so as to judge and obtain the abnormal data.
A threshold T1 is preset, where the present embodiment is described by taking t1=0.75 as an example, and the present embodiment is not specifically limited, where T1 depends on the specific implementation.
Specifically, acquiring an abnormal score of coal mine environment data at each sampling moment in a coal mine environment data sequence through an isolated forest algorithm; and if the abnormality score of the coal mine environment data at any sampling time in the coal mine environment data sequence is greater than or equal to T1, the coal mine environment data at the sampling time is recorded as target abnormality data of the coal mine environment data sequence, so that all target abnormality data of the coal mine environment data sequence are obtained.
So far, all target abnormal data of the coal mine environment data sequence are obtained through the method.
Step S003: and acquiring an anomaly score correction factor of each target anomaly data according to the comprehensive anomaly confidence coefficient of each target anomaly data in the coal mine environment data sequence.
1. And acquiring the comprehensive abnormal confidence coefficient of each target abnormal data in the coal mine environment data sequence.
It should be noted that, for all target abnormal data of the coal mine environment data sequence, the target abnormal data may include real abnormal data and noise data in time sequence, and the target abnormal data may be distinguished from the following two angles: the real abnormal data often appear collectively, and the noise data appear singly or are few in number, so that the judgment can be carried out through the relation between adjacent abnormal data in time sequence; the change trend of the real abnormal data accords with the physical change rule, the change of the real abnormal data on the time sequence is gentle, the noise data has instability and irregularity, and the change of the noise data on the time sequence is usually severe, so that the judgment can be carried out through the change trend of the data on the time sequence. By utilizing the two characteristics, the confidence of the data anomaly score can be comprehensively obtained.
When analyzing the relationship between the target abnormal data, it is necessary to arrange all the target abnormal data in time sequence, and calculate the corresponding adjacent region abnormal degree by the difference value and time interval between several target abnormal data which are closer to the target abnormal data and the abnormal score thereof.
A parameter a is preset, where the embodiment is described by taking a=5 as an example, and the embodiment is not specifically limited, where a depends on the specific implementation.
Specifically, arranging all target abnormal data of the coal mine environment data sequence according to the time sequence of the sampling moment to obtain a target abnormal data sequence; for the ith target abnormal data in the target abnormal data sequence, taking a data segment formed by the first a target abnormal data of the ith target abnormal data and the last a target abnormal data of the ith target abnormal data as a neighboring abnormal data segment of the ith target abnormal data; the calculation method of the abnormality degree of the adjacent area of the ith target abnormality data of the coal mine environment data sequence comprises the following steps:
in the method, in the process of the invention,representing the degree of abnormality of the adjacent area of the ith target abnormal data of the coal mine environment data sequence; t is t i Representing the sampling moment corresponding to the ith target abnormal data of the coal mine environment data sequence; t is t i,j The sampling time corresponding to the j-th target abnormal data in the adjacent abnormal data segment of the i-th target abnormal data of the coal mine environment data sequence is represented; h is a i An anomaly score representing the ith target anomaly data of the coal mine environment data sequence; h is a i,j An anomaly score for the jth target anomaly data in a neighboring anomaly data segment representing the ith target anomaly data of the coal mine environmental data sequence; a is a preset parameter; the expression of absolute valuePairing values; norm () represents a linear normalization function.
If the number of all the target abnormal data before the ith target abnormal data is smaller than a, the number of all the target abnormal data before the ith target abnormal data is marked as b, and a data segment formed by the b target abnormal data before the ith target abnormal data and the 2a-b target abnormal data after the ith target abnormal data is used as a neighboring abnormal data segment of the ith target abnormal data; if the number of all the target abnormal data after the ith target abnormal data is smaller than a, the number of all the target abnormal data after the ith target abnormal data is marked as c, and a data segment formed by c target abnormal data after the ith target abnormal data and the previous 2a-c target abnormal data is used as an adjacent abnormal data segment of the ith target abnormal data; the adjacent anomalous data segment of the ith target anomalous data does not include the ith target anomalous data.
Thus, the degree of abnormality of the adjacent area of each target abnormality data of the coal mine environment data sequence is obtained.
It should be noted that, all the target abnormal data are known to be doped with noise data, the change of the noise data in time sequence is unstable and irregular, and the change of the real abnormal data in time sequence is relatively more stable and gentle, so that the corresponding range abnormality degree can be obtained through the change trend of the target abnormal data in time sequence.
Specifically, for the kth target abnormal data in the coal mine environment data sequence, a data segment formed by the coal mine environment data of the first a sampling moments of the kth target abnormal data and the coal mine environment data of the last a sampling moments of the kth target abnormal data is used as a neighboring range data segment of the kth target abnormal data.
Regarding coal mine environment data at a v sampling moment in a data section of an adjacent range of the kth target abnormal data, taking the absolute value of the difference value of the coal mine humidity data of the coal mine environment data at the v sampling moment and the coal mine humidity data of the coal mine environment data at the v+1 sampling moment as the first-order difference degree of the humidity of the coal mine environment data at the v sampling moment; taking the absolute value of the difference value of the first-order difference degree of the humidity of the coal mine environment data at the v sampling moment and the first-order difference degree of the humidity of the coal mine environment data at the v+1th sampling moment as the second-order difference degree of the humidity of the coal mine environment data at the v sampling moment; the range abnormality degree calculation method of the kth target abnormality data of the coal mine environment data sequence comprises the following steps:
in the method, in the process of the invention,representing the range abnormality degree of the kth target abnormality data of the coal mine environment data sequence; ΔH2 k,v A first-order difference degree of the humidity of the coal mine environment data at the v sampling moment in the adjacent range data segment of the kth target abnormal data of the coal mine environment data sequence is represented; ΔH2 k,v A second-order difference degree of humidity of the coal mine environment data at a v-th sampling time in a data segment of an adjacent range of the kth target abnormal data of the coal mine environment data sequence is represented; a is a preset parameter; norm () represents a linear normalization function.
The method comprises the steps of obtaining a data segment of a neighboring range of the kth target abnormal data by referring to an obtaining method of the neighboring abnormal data segment of the ith target abnormal data; the adjacent range data segment of the kth target abnormal data comprises the kth target abnormal data; the first-order humidity difference represents the change speed of the humidity data, and the second-order humidity difference represents the change amount of the change speed of the humidity data.
Further, the product of the adjacent area abnormality degree of each target abnormality data in the coal mine environment data sequence and the range abnormality degree of each target abnormality data is used as the comprehensive abnormality confidence degree of each target abnormality data.
Thus, the comprehensive anomaly confidence of each target anomaly data in the coal mine environment data sequence is obtained.
2. And acquiring an abnormal score correction factor of each piece of target abnormal data in the coal mine environment data sequence.
Since the change of the humidity data is associated with other environmental data such as temperature and gas concentration, the correction of the anomaly score is not only dependent on the confidence of the humidity, but also needs to comprehensively analyze other dimensional data at the same time. In the same coal mine environment, humidity, temperature and gas concentration are related to each other, and the stability of the environment is affected. Wherein humidity is generally inversely related to temperature, when the air humidity is increased, the temperature is reduced, and when the humidity is reduced, the temperature is increased; the humidity and the gas concentration are inversely related, when the humidity is increased, the air becomes more moist, the gas diffusion speed is reduced, and on the contrary, when the humidity is reduced, the gas concentration is increased. Therefore, when abnormality occurs in the humidity data, the temperature and the gas concentration often change.
Specifically, regarding the coal mine environment data of the v sampling moment in the adjacent range data segment of the kth target abnormal data in the coal mine environment data sequence, taking the absolute value of the difference value of the coal mine temperature data of the coal mine environment data of the v sampling moment and the coal mine temperature data of the coal mine environment data of the v+1th sampling moment as the first-order temperature difference degree of the coal mine environment data of the v sampling moment; taking the absolute value of the difference value of the first-order temperature difference of the coal mine environment data at the v sampling moment and the first-order temperature difference of the coal mine environment data at the v+1th sampling moment as the second-order temperature difference of the coal mine environment data at the v sampling moment; taking the absolute value of the difference value of the coal mine gas concentration data of the coal mine environment data at the v sampling moment and the coal mine gas concentration data of the coal mine environment data at the v+1th sampling moment as the first-order difference degree of the gas concentration of the coal mine environment data at the v sampling moment; taking the absolute value of the difference between the first-order difference of the gas concentration of the coal mine environment data at the v-th sampling moment and the first-order difference of the gas concentration of the coal mine environment data at the v+1th sampling moment as the second-order difference of the gas concentration of the coal mine environment data at the v-th sampling moment; the calculation method of the anomaly score correction factor of the kth target anomaly data in the coal mine environment data sequence comprises the following steps:
in delta k An anomaly score correction factor representing kth target anomaly data in the coal mine environment data sequence; q (Q) k The environmental data change speed of the kth target abnormal data in the coal mine environmental data sequence is represented; w (W) k The environmental data variable quantity of the kth target abnormal data in the coal mine environmental data sequence is represented;representing the comprehensive anomaly confidence of the kth target anomaly data in the coal mine environment data sequence; ΔH2 k,v A first-order difference degree of the humidity of the coal mine environment data at the v sampling moment in the adjacent range data segment of the kth target abnormal data of the coal mine environment data sequence is represented; ΔH2 k,v A second-order difference degree of humidity of the coal mine environment data at a v-th sampling time in a data segment of an adjacent range of the kth target abnormal data of the coal mine environment data sequence is represented; ΔC1 k,v A first-order difference degree of gas concentration of the coal mine environment data at a v-th sampling time in a data segment of a neighboring range of the kth target abnormal data of the coal mine environment data sequence is represented; Δc2 k,v A second-order difference degree of gas concentration of the coal mine environment data at the v sampling moment in a data segment of a neighboring range of the kth target abnormal data of the coal mine environment data sequence is represented; Δf1 k,v A first-order temperature difference of the coal mine environment data at the v sampling moment in the adjacent range data segment of the kth target abnormal data of the coal mine environment data sequence is represented; Δf2 k,v V in the adjacent range data segment of the kth target anomaly data representing the coal mine environment data sequenceThe second-order temperature difference of the coal mine environment data at each sampling moment; a is a preset parameter; the absolute value is taken; norm () represents a linear normalization function.
So far, the abnormal score correction factor of each target abnormal data in the coal mine environment data sequence is obtained.
Step S004: and acquiring all real abnormal data in the coal mine environment data sequence according to the abnormal score correction factors of each target abnormal data, and further monitoring the construction environment in the coal mine.
Two parameters N1, N2 are preset, where the present embodiment is described by taking n1=3 and n2=5 as examples, and the present embodiment is not specifically limited, where N1, N2 are according to the specific implementation.
Specifically, for any one target abnormal data in the coal mine environment data sequence, taking the product of the abnormal score of the target abnormal data and the abnormal score correction factor of the target abnormal data as the corrected abnormal score of the target abnormal data; if the corrected abnormal score of the target abnormal data is larger than T1, the target abnormal data is recorded as real abnormal data, and all real abnormal data in the coal mine environment data sequence are obtained.
Further, the coal mine environment data of 20 arbitrary continuous sampling moments in the coal mine environment data sequence are recorded as target data segments of the coal mine environment data sequence; if the real abnormal data appear continuously N1 times in the coal mine environment data sequence or more than N2 real abnormal data exist in any one target data segment of the coal mine environment data sequence, an alarm of the control system sends out early warning to remind a worker to check the construction environment in the coal mine in time.
Through the steps, the intelligent early warning method for monitoring the coal mine water damage is completed.
The invention also provides an intelligent early warning system for monitoring the water damage of the coal mine, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of any one of the intelligent early warning method for monitoring the water damage of the coal mine when executing the computer program.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. The intelligent early warning method for monitoring the coal mine water damage is characterized by comprising the following steps of:
acquiring a coal mine environment data sequence, wherein the coal mine environment data sequence comprises coal mine environment data at a plurality of sampling moments, and the coal mine environment data at each sampling moment refers to coal mine temperature data, coal mine humidity data and coal mine gas concentration data at each sampling moment;
acquiring an abnormal score of the coal mine environment data at each sampling moment through an isolated forest algorithm, and screening the coal mine environment data according to the abnormal score to obtain all target abnormal data;
arranging all the target abnormal data according to the time sequence of the sampling moment to obtain a target abnormal data sequence; acquiring adjacent abnormal data segments of each target abnormal data in the target abnormal data sequence; acquiring adjacent range data segments of each target abnormal data in a coal mine environment data sequence; acquiring comprehensive anomaly confidence coefficient of each target anomaly data according to the anomaly score difference of each target anomaly data and other target anomaly data in the adjacent anomaly data segment and the coal mine humidity data difference of each target anomaly data and coal mine environment data at other sampling moments in the adjacent range data segment; acquiring an anomaly score correction factor of each target anomaly data according to the comprehensive anomaly confidence coefficient of each target anomaly data and the difference between each target anomaly data and coal mine environment data at other sampling moments in the adjacent range data segment;
correcting the abnormal score of each target abnormal data according to the abnormal score correction factors, and screening the coal mine environment data according to the corrected abnormal score to obtain all real abnormal data; and monitoring the construction environment in the coal mine according to the distribution of the real abnormal data in the coal mine environment data sequence.
2. The intelligent early warning method for monitoring coal mine water damage according to claim 1, wherein the method is characterized in that the coal mine environment data is screened according to the abnormality score to obtain all target abnormality data, and comprises the following specific steps:
a threshold T1 is preset, and if the abnormality score of the coal mine environment data at any sampling time in the coal mine environment data sequence is greater than or equal to T1, the coal mine environment data at the sampling time is recorded as target abnormality data of the coal mine environment data sequence, so that all target abnormality data of the coal mine environment data sequence are obtained.
3. The intelligent early warning method for monitoring coal mine water damage according to claim 1, wherein the method for acquiring the adjacent abnormal data segment of each target abnormal data in the target abnormal data sequence comprises the following specific steps:
presetting a parameter a, and regarding the data segment formed by the first a target abnormal data of the ith target abnormal data and the last a target abnormal data of the ith target abnormal data in the target abnormal data sequence as the adjacent abnormal data segment of the ith target abnormal data.
4. The intelligent early warning method for monitoring coal mine water damage according to claim 1, wherein the method for acquiring the adjacent range data segment of each target abnormal data in the coal mine environment data sequence comprises the following specific steps:
and regarding the kth target abnormal data in the coal mine environment data sequence, taking a data segment formed by the coal mine environment data of the first a sampling moments of the kth target abnormal data and the coal mine environment data of the last a sampling moments of the kth target abnormal data as a neighboring range data segment of the kth target abnormal data, wherein a is a preset parameter.
5. The method for intelligent early warning of water damage monitoring in coal mine according to claim 1, wherein the method for acquiring the comprehensive anomaly confidence of each target anomaly data according to the anomaly score difference of each target anomaly data and other target anomaly data in the adjacent anomaly data segment and the coal mine humidity data difference of each target anomaly data and coal mine environment data at other sampling moments in the adjacent range data segment comprises the following specific steps:
acquiring the abnormality degree of the adjacent area of each target abnormal data in the coal mine environment data sequence according to the abnormality score difference of each target abnormal data and other target abnormal data in the adjacent abnormal data segment; acquiring the range abnormality degree of each target abnormality data in the coal mine environment data sequence according to the coal mine humidity data difference of each target abnormality data and the coal mine environment data at other sampling moments in the adjacent range data segment;
and taking the product of the adjacent area abnormality degree of each target abnormality data in the coal mine environment data sequence and the range abnormality degree of each target abnormality data in the coal mine environment data sequence as the comprehensive abnormality confidence of each target abnormality data.
6. The intelligent early warning method for monitoring coal mine water damage according to claim 5, wherein the specific formula for acquiring the abnormality degree of the adjacent area of each target abnormality data in the coal mine environment data sequence according to the abnormality score difference of each target abnormality data and other target abnormality data in the adjacent abnormality data segment is as follows:
in the method, in the process of the invention,representing the degree of abnormality of the adjacent area of the ith target abnormal data of the coal mine environment data sequence; t is t i Representing the sampling moment corresponding to the ith target abnormal data of the coal mine environment data sequence;t i,j the sampling time corresponding to the j-th target abnormal data in the adjacent abnormal data segment of the i-th target abnormal data of the coal mine environment data sequence is represented; h is a i An anomaly score representing the ith target anomaly data of the coal mine environment data sequence; h is a i,j An anomaly score for the jth target anomaly data in a neighboring anomaly data segment representing the ith target anomaly data of the coal mine environmental data sequence; a is a preset parameter; the absolute value is taken; norm () represents a linear normalization function.
7. The intelligent early warning method for monitoring coal mine water damage according to claim 5, wherein the acquiring the range abnormality degree of each target abnormality data in the coal mine environment data sequence according to the coal mine humidity data difference between each target abnormality data and the coal mine environment data at other sampling moments in the adjacent range data segment comprises the following specific steps:
regarding coal mine environment data at a v sampling moment in a data section of an adjacent range of the kth target abnormal data, taking the absolute value of the difference value of the coal mine humidity data of the coal mine environment data at the v sampling moment and the coal mine humidity data of the coal mine environment data at the v+1 sampling moment as the first-order difference degree of the humidity of the coal mine environment data at the v sampling moment; taking the absolute value of the difference value of the first-order difference degree of the humidity of the coal mine environment data at the v sampling moment and the first-order difference degree of the humidity of the coal mine environment data at the v+1th sampling moment as the second-order difference degree of the humidity of the coal mine environment data at the v sampling moment; the range abnormality degree calculation method of the kth target abnormality data of the coal mine environment data sequence comprises the following steps:
in the method, in the process of the invention,representing the range abnormality degree of the kth target abnormality data of the coal mine environment data sequence; ΔH2 k,v A first-order difference degree of the humidity of the coal mine environment data at the v sampling moment in the adjacent range data segment of the kth target abnormal data of the coal mine environment data sequence is represented; ΔH2 k,v A second-order difference degree of humidity of the coal mine environment data at a v-th sampling time in a data segment of an adjacent range of the kth target abnormal data of the coal mine environment data sequence is represented; a is a preset parameter; norm () represents a linear normalization function.
8. The method for intelligent early warning of water damage monitoring in coal mine according to claim 1, wherein the method for acquiring the abnormality score correction factor of each target abnormality data according to the comprehensive abnormality confidence of each target abnormality data and the differences of the coal mine environment data of each target abnormality data and other sampling moments in the adjacent range data segment comprises the following specific steps:
for the kth target abnormal data in the coal mine environment data sequence, acquiring the environment data change speed and environment data change quantity of the kth target abnormal data in the coal mine environment data sequence; the calculation method of the anomaly score correction factor of the kth target anomaly data in the coal mine environment data sequence comprises the following steps:
in delta k An anomaly score correction factor representing kth target anomaly data in the coal mine environment data sequence; q (Q) k The environmental data change speed of the kth target abnormal data in the coal mine environmental data sequence is represented; w (W) k The environmental data variable quantity of the kth target abnormal data in the coal mine environmental data sequence is represented;representing the comprehensive anomaly confidence of the kth target anomaly data in the coal mine environment data sequence; norm () represents a linear normalization function.
9. The intelligent early warning method for monitoring coal mine water damage according to any one of claims 7 and 8, wherein the method for acquiring the environmental data change speed and the environmental data change amount of the kth target abnormal data in the coal mine environmental data sequence comprises the following specific steps:
regarding the coal mine environment data of the v sampling moment in the adjacent range data segment of the kth target abnormal data in the coal mine environment data sequence, taking the absolute value of the difference value of the coal mine temperature data of the coal mine environment data of the v sampling moment and the coal mine temperature data of the coal mine environment data of the v+1 sampling moment as the first-order temperature difference degree of the coal mine environment data of the v sampling moment; taking the absolute value of the difference value of the first-order temperature difference of the coal mine environment data at the v sampling moment and the first-order temperature difference of the coal mine environment data at the v+1th sampling moment as the second-order temperature difference of the coal mine environment data at the v sampling moment; taking the absolute value of the difference value of the coal mine gas concentration data of the coal mine environment data at the v sampling moment and the coal mine gas concentration data of the coal mine environment data at the v+1th sampling moment as the first-order difference degree of the gas concentration of the coal mine environment data at the v sampling moment; taking the absolute value of the difference between the first-order difference of the gas concentration of the coal mine environment data at the v-th sampling moment and the first-order difference of the gas concentration of the coal mine environment data at the v+1th sampling moment as the second-order difference of the gas concentration of the coal mine environment data at the v-th sampling moment; the calculation method of the environmental data change speed and the environmental data change amount of the kth target abnormal data in the coal mine environmental data sequence comprises the following steps:
wherein DeltaH 1 k,v Coal mine loop representing the v sampling time in the adjacent range data segment of the kth target anomaly data of the coal mine environment data sequenceFirst-order difference degree of humidity of the environmental data; ΔH2 k,v A second-order difference degree of humidity of the coal mine environment data at a v-th sampling time in a data segment of an adjacent range of the kth target abnormal data of the coal mine environment data sequence is represented; ΔC1 k,v A first-order difference degree of gas concentration of the coal mine environment data at a v-th sampling time in a data segment of a neighboring range of the kth target abnormal data of the coal mine environment data sequence is represented; Δc2 k,v A second-order difference degree of gas concentration of the coal mine environment data at the v sampling moment in a data segment of a neighboring range of the kth target abnormal data of the coal mine environment data sequence is represented; Δf1 k,v A first-order temperature difference of the coal mine environment data at the v sampling moment in the adjacent range data segment of the kth target abnormal data of the coal mine environment data sequence is represented; Δf2 k,v A second-order temperature difference of the coal mine environment data at the v sampling moment in the adjacent range data segment of the kth target abnormal data of the coal mine environment data sequence is represented; a is a preset parameter; the absolute value is taken.
10. An intelligent early warning system for monitoring water damage in a coal mine, comprising a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the intelligent early warning method for monitoring water damage in a coal mine according to any one of claims 1-9 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311709753.5A CN117605539A (en) | 2023-12-13 | 2023-12-13 | Intelligent early warning system and method for monitoring coal mine water damage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311709753.5A CN117605539A (en) | 2023-12-13 | 2023-12-13 | Intelligent early warning system and method for monitoring coal mine water damage |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117605539A true CN117605539A (en) | 2024-02-27 |
Family
ID=89959781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311709753.5A Pending CN117605539A (en) | 2023-12-13 | 2023-12-13 | Intelligent early warning system and method for monitoring coal mine water damage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117605539A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117805932A (en) * | 2024-03-01 | 2024-04-02 | 肥城新查庄地质勘查有限公司 | Coal seam determining method based on coal mine exploration data |
| CN117979508A (en) * | 2024-03-05 | 2024-05-03 | 六班电气有限公司 | Intelligent lamplight regulation and control method based on underground environment sensing |
-
2023
- 2023-12-13 CN CN202311709753.5A patent/CN117605539A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117805932A (en) * | 2024-03-01 | 2024-04-02 | 肥城新查庄地质勘查有限公司 | Coal seam determining method based on coal mine exploration data |
| CN117805932B (en) * | 2024-03-01 | 2024-05-28 | 肥城新查庄地质勘查有限公司 | Coal seam determining method based on coal mine exploration data |
| CN117979508A (en) * | 2024-03-05 | 2024-05-03 | 六班电气有限公司 | Intelligent lamplight regulation and control method based on underground environment sensing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117605539A (en) | Intelligent early warning system and method for monitoring coal mine water damage | |
| CN110619587B (en) | Method and system for foundation pit monitoring intelligent early warning and data evidence storage | |
| CN111611751B (en) | Chemical process risk dynamic analysis method based on Bayesian and event tree | |
| CN105306439A (en) | Feature rule detection method based on decision tree self-repairing | |
| CN109507728A (en) | A kind of underground hazard method for early warning based on micro seismic monitoring | |
| CN113255783B (en) | Sensor fault detection method and device based on unsupervised learning | |
| CN110411572A (en) | Carry the infra-red radiation monitoring and pre-alarming method of coal petrography rupture | |
| CN117934248B (en) | Power plant safety management and control platform data analysis method and system | |
| US10635741B2 (en) | Method and system for analyzing process factors affecting trend of continuous process | |
| CN117556364A (en) | Mining ore pressure safety intelligent monitoring system | |
| CN112966017A (en) | Abnormal subsequence detection method with indefinite length in time sequence | |
| CN115499318B (en) | Tunnel monitoring data communication management and control method, system and terminal equipment | |
| CN116644975A (en) | Intelligent supervision method and system for anti-collision hidden engineering construction | |
| CN109555561B (en) | Mine pressure prediction method and system | |
| CN110414800A (en) | Construction of super highrise building accident risk source appraisal procedure and device | |
| CN115455791A (en) | Method for improving landslide displacement prediction accuracy rate based on numerical simulation technology | |
| CN106150491B (en) | Oil reservoir exploration method and device | |
| CN114060018B (en) | Reservoir dynamic reserve determination method, system, equipment and readable storage medium | |
| CN108319915B (en) | Multi-time-window simplified form identification method for dynamically adjusting rock burst signal threshold | |
| CN112214816A (en) | Digital twinning technology-based reverse control method and system for sliding instability of fault structure | |
| CN109681273B (en) | Underground environment early warning method | |
| CN117743988B (en) | Instant prediction method for pressure-bearing state of hydraulic support after initial support | |
| CN117536691B (en) | Fully-mechanized coal mining face equipment parameter monitoring method and system | |
| CN117421620B (en) | Interaction method of tension state data | |
| CN115951619B (en) | Development machine remote intelligent control system based on artificial intelligence |
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 |