CN118030189A - Method and system for monitoring natural ignition beam tube of coal mine - Google Patents
Method and system for monitoring natural ignition beam tube of coal mine Download PDFInfo
- Publication number
- CN118030189A CN118030189A CN202410309209.XA CN202410309209A CN118030189A CN 118030189 A CN118030189 A CN 118030189A CN 202410309209 A CN202410309209 A CN 202410309209A CN 118030189 A CN118030189 A CN 118030189A
- Authority
- CN
- China
- Prior art keywords
- data
- real
- time
- type
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000003245 coal Substances 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012544 monitoring process Methods 0.000 title claims abstract description 32
- 230000005856 abnormality Effects 0.000 claims abstract description 80
- 230000002159 abnormal effect Effects 0.000 claims abstract description 50
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- KJONHKAYOJNZEC-UHFFFAOYSA-N nitrazepam Chemical compound C12=CC([N+](=O)[O-])=CC=C2NC(=O)CN=C1C1=CC=CC=C1 KJONHKAYOJNZEC-UHFFFAOYSA-N 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 9
- 239000007789 gas Substances 0.000 description 4
- 230000035772 mutation Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000005303 weighing 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
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a method and a system for monitoring a natural ignition beam tube of a coal mine, comprising the following steps: acquiring real-time data of multiple types of data in a coal mine roadway, acquiring a real-time window of the real-time data of each type of data, calculating the reference abnormal degree of the real-time data of each type of data and the adjustment degree of each type of data, obtaining a first abnormal degree of the real-time data of each type of data, obtaining an adjustment coefficient of the first abnormal degree of each type of data according to the difference between the real-time data of the multiple types of data, finally obtaining the comprehensive abnormal degree of the real-time data at the current moment, and determining whether the real-time data at the current moment is abnormal or not by utilizing CABDDCG algorithm. According to the invention, different types of real-time data related to natural fire causes in the coal mine are analyzed to detect the abnormality, so that the accuracy of monitoring the natural fire beam tube of the coal mine is improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for monitoring a natural ignition beam tube of a coal mine.
Background
With the development of technology, an automatic monitoring system is beginning to be applied to coal mine safety management. These systems typically include temperature sensors, gas sensors, fiber optic sensors, etc. for monitoring critical parameters such as temperature, gas concentration, etc. within the mine in real time. Through analysis of a large amount of real-time data, the system can identify potential natural ignition risks and provide early warning, so that mine management personnel can take measures in time.
The natural fire of the coal mine is induced by different types of data, and when some types of data are far higher than other types of data, the change of the data graph structure of the natural fire of the coal mine is analyzed by CABDDCG algorithm (Clustering Algorithm Based on Dynamic Division of Connected Graph, chinese translation is a clustering algorithm based on dynamic splitting of a connected graph) to be biased to the dominant type of data, so that the monitoring result obtained by the different types of data is biased, the early warning of the analysis result of the natural fire of the coal mine is not facilitated, and the accuracy of monitoring the natural fire beam tube of the coal mine is reduced.
Disclosure of Invention
The invention provides a method and a system for monitoring a natural ignition beam tube of a coal mine, which are used for solving the existing problems.
The invention discloses a method and a system for monitoring a natural ignition beam tube of a coal mine, which adopts the following technical scheme:
The embodiment of the invention provides a method for monitoring a natural ignition beam tube of a coal mine, which comprises the following steps:
acquiring real-time data of various types of data in a coal mine roadway;
Acquiring a real-time window of real-time data of each type of data, and obtaining the reference abnormality degree and the reference abnormality degree of the real-time data of each type of data according to the difference between the data of the real-time window of the real-time data of each type of data
The degree of adjustment for each data type;
The product of the reference abnormality degree of the real-time data of each type of data and the adjustment degree of each type of data,
A first degree of anomaly of the real-time data noted as each type of data;
obtaining an adjustment coefficient of a first abnormality degree of each type of data according to the difference between the real-time data of the plurality of types of data;
obtaining the comprehensive abnormal degree of the real-time data at the current moment according to the first abnormal degree of the real-time data of all types of data and the adjustment coefficient of the first abnormal degree;
And determining whether the real-time data at the current moment is abnormal or not by utilizing CABDDCG algorithm according to the comprehensive abnormality degree of the current real-time data.
Further, the step of acquiring the real-time window of the real-time data of each type of data comprises the following specific steps:
In the real-time data of the type a data, starting from the real-time data at the current time, recording a sequence formed by the real-time data of b minutes as a real-time window in reverse time sequence; and b is a preset time range.
Further, the step of obtaining the reference abnormality degree of the real-time data of each type of data and the adjustment degree of each type of data according to the difference between the data of the real-time window of the real-time data of each type of data comprises the following specific steps:
Obtaining the reference abnormal degree of the real-time data of each type of data according to all the data in the real-time window of the real-time data of each type of data;
calculating the data in the real-time window of the real-time data of each type of data by using a first derivative method to obtain extreme points in the real-time window;
And obtaining the adjustment degree of each data type according to the extreme point in the real-time window of the real-time data of each type of data.
Further, the specific calculation formula corresponding to the reference abnormality degree of the real-time data of each type of data is obtained according to all the data in the real-time window of the real-time data of each type of data:
Wherein Q i represents a reference abnormality degree of real-time data of the i-th type data; n represents the number of data present in the real-time window of the real-time data of the i-th type of data; s i,n+1,1 denotes an absolute value of a difference value of the (n+1) th data and the first data within a real-time window of real-time data of the (i) th type of data; q i,1 denotes the 1 st data within the real-time window of the real-time data of the i-th type data; q i,n+1 denotes the n+1th data within the real-time window of the real-time data of the i-th type data.
Further, the specific calculation formula corresponding to the adjustment degree of each data type is obtained according to the extreme point in the real-time window of the real-time data of each data type, wherein the specific calculation formula is as follows:
Wherein W i represents the degree of adjustment of the ith data type; j represents the number of maximum points existing in the real-time data real-time window of the ith type of data; k represents a preset data quantity; deltaw i,j,k represents the difference between the jth maximum point data and the kth data on the left side of the jth maximum point of the real-time window of the real-time data of the ith type of data; deltaw' i,j,k represents the difference between the j-th maximum point data and the k-th data on the right side of the j-th maximum point of the real-time window of the real-time data of the i-th type data; q i,1 denotes the 1 st data of the real-time window of the real-time data of the i-th type of data; q' i,j denotes the jth extreme point data of the real-time window of the real-time data of the ith type of data; norm () is a linear normalization function.
Further, the method for obtaining the adjustment coefficient of the first degree of abnormality of each type of data according to the difference between the real-time data of the plurality of types of data comprises the following specific steps:
The maximum value in the Pelson correlation coefficients of the real-time data of the ith type of data and the real-time data of all other types of data is recorded as the strongest correlation coefficient of the ith type of data;
recording the maximum value in pearson correlation coefficients of the data in the real-time window of the real-time data of the ith type of data and the data in the real-time windows of the real-time data of all other types of data as the strongest correlation coefficient of the real-time window of the real-time data of the ith type of data;
and obtaining an adjustment coefficient of the first abnormality degree of the ith type of data according to the strongest correlation coefficient of the ith type of data and the strongest correlation coefficient of the real-time window of the real-time data of the ith type of data.
Further, the specific calculation formula corresponding to the adjustment coefficient of the first anomaly degree of the ith type of data according to the strongest correlation coefficient of the ith type of data and the strongest correlation coefficient of the real-time window of the real-time data of the ith type of data is:
Wherein R i represents an adjustment coefficient of the first degree of abnormality of the i-th type data; r' i is the strongest correlation coefficient for the i-th type of data; r i is the strongest correlation coefficient of the real-time window of the real-time data of the ith type of data; the |is an absolute value function, exp () is an exponential function based on a natural constant.
Further, the specific calculation formula corresponding to the comprehensive abnormal degree of the real-time data at the current time is obtained according to the first abnormal degree of the real-time data of all types and the adjustment coefficient of the first abnormal degree, and the specific calculation formula is as follows:
Wherein T represents the comprehensive abnormality degree of the real-time data at the current time; i represents the number of data types; e i represents a first degree of abnormality of real-time data of the i-th type of data; r i represents an adjustment coefficient of a first degree of abnormality of the i-th type data; norm () is a linear normalization function.
Further, the determining whether the real-time data at the current moment has abnormality by using CABDDCG algorithm according to the comprehensive abnormality degree of the current real-time data comprises the following specific steps:
obtaining the comprehensive abnormal degree of the real-time data at each moment in all types of data according to the acquisition mode of the comprehensive abnormal degree of the current real-time data;
In all types of data, the comprehensive abnormality degree of the real-time data at each moment is input into an algorithm CABDDCG, a plurality of clusters are output, the average value of all the data in the cluster where the comprehensive abnormality degree of the real-time data at the current moment is located is marked as a first average value, the average value of all the data in the cluster where the data quantity is maximum is marked as a second average value, and when the ratio of the first average value to the second average value is smaller than a preset judgment threshold value, the real-time data at the current moment is judged to be abnormal.
The invention also provides a coal mine natural ignition beam tube monitoring system, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program stored in the memory so as to realize the steps of the coal mine natural ignition beam tube monitoring system.
The technical scheme of the invention has the beneficial effects that:
In the embodiment of the invention, the real-time data of various types of data in the coal mine tunnel are acquired, and each type of data is acquired
Real-time window of real-time data of each type of data, reference abnormality degree of real-time data of each type of data is calculated
The adjustment degree of the data type is used for adjusting the reference abnormality degree according to the adjustment degree to obtain the accurate and reliable first abnormality degree of the real-time data of each type of data, thereby ensuring the accuracy of abnormality detection and obtaining a plurality of types of data
The difference between the real-time data of the type data, the adjustment coefficient of the first abnormality degree of each type data is obtained
The first abnormality degree is corrected, so that the accurate comprehensive abnormality degree is obtained, and the accuracy of abnormality detection is further ensured.
Up to this point, whether the real-time data at the current moment is abnormal or not is determined by utilizing CABDDCG algorithm, so that the natural ignition of the coal mine is improved
And (5) the accuracy of beam tube monitoring.
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 the steps of a method for monitoring a natural ignition beam tube of a coal mine.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of a specific implementation, structure, characteristics and effects of the method and system for monitoring the natural ignition beam tube of the coal mine according to the invention in combination with 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 method and a system for monitoring a natural ignition beam tube of a coal mine.
Referring to fig. 1, a flowchart of a method for monitoring a natural ignition beam tube of a coal mine according to an embodiment of the invention is shown, the method includes the following steps:
step S001: and acquiring real-time data of various types of data in the coal mine tunnel.
The key data information related to the natural fire disaster of different types of coal mines is obtained by arranging sensors of temperature, gas concentration and other related parameters in the coal mine tunnel.
Here, in the present embodiment, different types of data are acquired by related sensors such as a temperature sensor, a gas sensor, and the like for critical type data such as temperature, oxygen concentration, methane concentration, and the like. In the center position of the coal mine roadway, a plurality of sensors are fixed, each sensor can be arranged in a plurality, data errors caused by sensor faults are avoided, the preset acquisition frequency in the embodiment is once per second, the acquisition frequency is described by way of example, other values can be set in other embodiments, and the embodiment is not limited.
The method is characterized in that the method aims at a plurality of acquired real-time data of each sensor, averages the acquired real-time data, improves the accuracy of the data, and is used as the basis for the analysis of the subsequent data of various types.
Thereby acquiring real-time data of various types of data in the coal mine tunnel.
Step S002: and acquiring a real-time window of the real-time data of each type of data, and obtaining the reference abnormality degree of the real-time data of each type of data and the adjustment degree of each data type according to the difference between the data of the real-time window of the real-time data of each type of data.
Among the various critical data related to the natural fire induction of the coal mine, the natural fire of the coal mine can be caused by the anomalies of different types of data, and the final detection result is biased to the dominant data type when the anomalies are detected directly through CABDDCG algorithm. Therefore, the embodiment firstly analyzes the abnormal degree performance of various data in real time, adjusts the abnormal degree performance of various data through the relativity among different types of data, and finally carries out weighing and integration on the abnormal degree performance of various types of data after adjustment to determine real-time abnormal parameters.
When analyzing the abnormal representation of various types of data in real time, comparing the difference between the previous moments and the current real-time data on the whole, and determining the reference abnormal degree; and finding each maximum point in the previous data, analyzing the type (mutation type or slow variation type) of the maximum point, determining the referenceable value of each maximum point, taking the referenceable value as the weight for comparing the real-time data with the abnormality of the previous maximum data point, and adjusting the reference abnormality degree.
When real-time analysis is performed on each type of data, the real-time data at each moment is put in the previous 10min data for comparison analysis, the time is recorded as a real-time window, the preset time range b in this embodiment is 10min, and this is described by taking this as an example, other values can be set in other embodiments, this embodiment is not limited, and the current real-time data is specified as the first data of the real-time window, and the following is the same.
Taking the real-time data of the a-th type data as an example, the real-time window of the a-th type data is recorded as a sequence formed by sequentially reversing the time sequence of the b-minute real-time data from the real-time data at the current time in the real-time data of the a-th type data. And b is a preset time range.
In the above manner, a real-time window for each type of data is obtained.
And calculating the data in the real-time windows by using a first derivative method to obtain extreme points in each real-time window. The first derivative method is a known technique, and the specific method is not described here.
While the present embodiment marks each maximum data point of this real-time window for subsequent analysis to develop.
Q i represents the reference abnormality degree of the real-time data of the ith type of data, and is determined by comparing the real-time window in which the current real-time data is located; n represents the number of data present in the real-time window of the real-time data of the i-th type of data; s i,n+1,1 represents the absolute value of the difference between the (n+1) th data and the first data in the real-time window of the real-time data of the (i) th type of data, and represents the proximity of each real-time data to the first data; q i,1 denotes the 1 st data within the real-time window of the real-time data of the i-th type data; q i,n+1 denotes the n+1th data within the real-time window of the real-time data of the i-th type data.
In the formula (i),The real-time data is taken as the first data through the real-time window in which the real-time data is located, the real-time data and each data (except the real-time data) of the real-time window are compared one by one to determine the reference abnormal degree of the real-time data, and the embodiment focuses on the data which are more adjacent in time to the current real-time data because of the abnormal analysis of the real-time data, so that the adjacent degree of the data is reflected through S i,n+1,1.
The whole formula finally takes the average value accumulated by comparing the data one by one, and the average value is used as the reference abnormal degree of the real-time data, and the abnormal degree performance of the current real-time data is determined through the whole comparison.
Thereby obtaining the reference abnormality degree of the real-time data of various types of data.
However, this is only analyzed from the whole data, and the thus obtained reference abnormality degree of the real-time data is not accurate enough, so that the adjustment degree of the reference abnormality degree of the real-time data can be determined by comparing the real-time data with the maximum value data under the real-time window, and by comparing the maximum value data with the real-time data because each of the maximum value data may be suspected abnormality data.
Meanwhile, when the maximum value data are used as suspected abnormal data for comparison analysis, the credibility of the maximum value data can be considered. Since even the maximum point can be classified into two types of "mutation type" and "slow type" according to the data change characteristics, the degree of adjustment of the reference abnormality degree of the real-time data can be determined by the reliability of the maximum point and the difference between the maximum point data and the real-time data, and the specific procedure is as follows:
Wherein W i represents the adjustment degree of the ith data type, and refers to the adjustment degree of the corresponding reference abnormality degree; j represents the number of maximum points existing in a real-time window of real-time data of the ith type of data; deltaw i,j,k represents the difference between the jth maximum point data and the kth data on the left side of the jth maximum point of the real-time window of the real-time data of the ith type of data; deltaw' i,j,k represents the difference between the jth maximum point data and the kth data on the right of the jth maximum point within the real-time window of the real-time data of the ith type of data; q i,1 denotes the 1 st data of the real-time window of the real-time data of the i-th type of data; q' i,j denotes the jth extreme point data of the real-time window of the real-time data of the ith type of data; norm () is a linear normalization function, normalizes the data value of the comparison analysis result of each extreme point of the ith type of data to be within the interval of [0,1], where K is a preset data quantity, in this embodiment, K is 10, and this is described as an example, and other values may be set in other embodiments, which is not limited in this embodiment.
In the formula (i),The reliability of judging the extreme point is shown, because the larger the difference between the extreme point and the data in the adjacent range is, the greater the possibility that the extreme point is a mutation point is, so that the same quantity data comparison analysis is carried out on the extreme point and the left side and the right side, the reliability of the current extreme point is judged, namely the degree expression between the mutation type and the slow deformation type of the current extreme point is judged, and the reliability of the current extreme point is judgedThe larger the probability of being described as a mutant, the greater the concern for it, and the higher the confidence.
In the formula (i),The real-time data is compared with each extreme point data, the abnormal performance is determined by comparing the real-time data with each extreme point data, when the real-time data is larger than the extreme point data, the ratio of the real-time data to the extreme point data is larger than 1, and the extreme point data is suspected abnormal data, so that the abnormal performance of the current real-time data is judged by the comparison.
Thereby obtaining the adjustment degree of the reference abnormality degree of the real-time data of various types of data.
Step S003: the product of the reference abnormality degree of the real-time data of each type of data and the adjustment degree of each type of data is recorded as the first abnormality degree of the real-time data of each type of data.
The reference abnormality degree and the corresponding adjustment degree of the real-time data of various types of data are obtained through the above process, and the two can be combined to obtain the first abnormality degree of the real-time data of various types of data.
Ei＝Qi*Wi
Wherein E i represents a first degree of abnormality of real-time data of the i-th type of data; q i denotes a reference abnormality degree of real-time data of the i-th type data; w i represents the degree of adjustment of the ith data type.
Thereby, a first degree of abnormality of real-time data of various types of data is obtained.
Step S004: and obtaining an adjustment coefficient of the first abnormality degree of each type of data according to the difference between the real-time data of the plurality of types of data.
And determining another type of data with the strongest correlation with the data of each type by using the pearson correlation coefficient. Because the daily flow or steps may be different during coal mine operation, single type data changes may be different every day, but if the correlation between the two types of data is high, the data change ratio of the two types of data at the historical moment and the current real-time condition is also in a certain relationship. Therefore, the difference between the historical moment and the current real-time difference condition is analyzed, and the larger the difference is, the more abnormal the current is, and the larger the adjustment coefficient is.
And aiming at the historical data of each type of data, analyzing the correlation between the historical data and the historical data of other types of data through the Pearson correlation coefficient, and screening out the other type of data with the strongest correlation with each type of data. And comparing the correlation degree between the historical data of the two types of data with the correlation degree between the corresponding real-time windows of the real-time data of the two types of data.
And calculating the pearson correlation coefficient of the real-time data of the ith type of data and the real-time data of each other type of data, and recording the maximum pearson correlation coefficient as the strongest correlation coefficient of the ith type of data.
And calculating the pearson correlation coefficient of the data in the real-time window of the real-time data of the ith type of data and the data in the real-time window of the real-time data of each other type of data, and recording the maximum pearson correlation coefficient as the strongest correlation coefficient of the real-time window of the real-time data of the ith type of data.
The calculation formula of the adjustment coefficient of the first degree of abnormality of the i-th type data is:
Wherein R i represents an adjustment coefficient of the first degree of abnormality of the i-th type of data, which is determined based on the historical data and the real-time window data of the other data type having the strongest correlation with the i-th type of data; r' i is the strongest correlation coefficient for the i-th type of data; r i is the strongest correlation coefficient of the real-time window of the real-time data of the ith type of data. exp () is an exponential function based on a natural constant, and in this embodiment, exp (-) is used to represent an inverse proportion relation and normalization processing, and an implementer can set the inverse proportion function and the normalization function according to actual situations, and ||is an absolute value function.
In the formula, whenTime,/>Here, the reduced adjustment coefficient determined after the correlation between the type data history data and the real-time window data in the i-th is represented. Since the range of pearson correlation coefficients is [ -1,1], a reduced adjustment coefficient can be assigned to both if the comparison is negative or positive; exp (- |r' i-ri |) herein indicates the degree of decrease, and the smaller the difference in degree of correlation between the two, the better the correlation is considered, which means that the closer the correlation between the current real-time window and the history data is, the less the possibility of abnormality exists, and the larger the value of the adjustment coefficient thus determined after exp ().
In the formula (i),When the positive and negative correlation of the two are inconsistent, the method is described as followsThis represents the incremental adjustment factor determined after correlation of the i-th type of data history data with the real-time window data. Because both the time correlation positive and negative are changed, the time correlation positive and negative are naturally influenced by abnormality; the larger the correlation difference between the two, the greater the probability of abnormality, and thus the greater the value of the determined adjustment coefficient.
Thereby determining an adjustment coefficient for the first degree of abnormality of each type of data.
Step S005: and obtaining the comprehensive abnormal degree of the real-time data at the current moment according to the first abnormal degree of the real-time data of all types of data and the adjustment coefficient of the first abnormal degree.
According to the first degree of abnormality of the real-time data of various data types and the corresponding adjustment coefficient, the final degree of abnormality can be determined, and according to the performances of different types of degree of abnormality, the final degree of abnormality is obtained by weighting and integrating.
Wherein T represents the comprehensive abnormal degree of the real-time data at the current time and is comprehensively determined based on various data analysis; i represents the number of data types; e i represents a first degree of abnormality of real-time data of the i-th type of data; r i represents an adjustment coefficient of a first degree of abnormality of the i-th type data; norm () is normalized based on real-time (E i×Ri) calculations of various data types;
In the formula, norm (E i×Ri) represents that the whole normalization is carried out on each type of data by the adjusted first degree of abnormality; the degree of abnormal occupation (weight) of the data of each type, which is the overall data after the overall normalization of the adjusted first degree of abnormality, is represented.
For all types of data, acquiring real-time data at each moment after the current moment, and acquiring the comprehensive abnormality degree of the real-time data at each moment according to the mode.
Step S006: and determining whether the real-time data at the current moment is abnormal or not by utilizing CABDDCG algorithm according to the comprehensive abnormality degree of the current real-time data.
For all types of data, inputting the comprehensive abnormality degree of the real-time data at each moment into an algorithm CABDDCG, outputting a plurality of clusters, marking the average value of all data in the cluster where the comprehensive abnormality degree of the real-time data at the current moment is located as a first average value, marking the average value of all data in the cluster where the data quantity is maximum as a second average value, and judging that the real-time data at the current moment is abnormal when the ratio of the first average value to the second average value is smaller than a preset judgment threshold value, wherein the CABDDCG algorithm is a known technology, and a specific method is not described herein. The preset determination threshold value in this embodiment is 0.1, which is described as an example, and other values may be set in other embodiments, and this embodiment is not limited thereto.
What needs to be described is: the CABDDCG algorithm is a clustering algorithm based on dynamic splitting of the connected graph, and in this embodiment, clustering operation is performed by taking the comprehensive anomaly degree of real-time data of all types of data at each moment as a data point.
The present invention has been completed.
The invention also provides a coal mine natural ignition beam tube monitoring system, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program stored in the memory so as to realize the steps of the coal mine natural ignition beam tube monitoring method.
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 method for monitoring the natural ignition beam tube of the coal mine is characterized by comprising the following steps of:
acquiring real-time data of various types of data in a coal mine roadway;
Acquiring a real-time window of real-time data of each type of data, and obtaining a reference abnormal degree of the real-time data of each type of data and an adjustment degree of each data type according to the difference between the data of the real-time window of the real-time data of each type of data;
recording the product of the reference abnormality degree of the real-time data of each type of data and the adjustment degree of each data type as a first abnormality degree of the real-time data of each type of data;
obtaining an adjustment coefficient of a first abnormality degree of each type of data according to the difference between the real-time data of the plurality of types of data;
obtaining the comprehensive abnormal degree of the real-time data at the current moment according to the first abnormal degree of the real-time data of all types of data and the adjustment coefficient of the first abnormal degree;
And determining whether the real-time data at the current moment is abnormal or not by utilizing CABDDCG algorithm according to the comprehensive abnormality degree of the current real-time data.
2. The method for monitoring the natural ignition beam tube of the coal mine according to claim 1, wherein the real-time window for acquiring the real-time data of each type of data comprises the following specific steps:
In the real-time data of the type a data, starting from the real-time data at the current time, recording a sequence formed by the real-time data of b minutes as a real-time window in reverse time sequence; and b is a preset time range.
3. The method for monitoring the natural ignition beam tube of the coal mine according to claim 1, wherein the step of obtaining the reference abnormality degree of the real-time data of each type of data and the adjustment degree of each type of data according to the difference between the data of the real-time window of the real-time data of each type of data comprises the following specific steps:
Obtaining the reference abnormal degree of the real-time data of each type of data according to all the data in the real-time window of the real-time data of each type of data;
calculating the data in the real-time window of the real-time data of each type of data by using a first derivative method to obtain extreme points in the real-time window;
And obtaining the adjustment degree of each data type according to the extreme point in the real-time window of the real-time data of each type of data.
4. The method for monitoring a natural ignition beam tube of a coal mine according to claim 3, wherein the specific calculation formula corresponding to the reference abnormal degree of the real-time data of each type of data is obtained according to all the data in the real-time window of the real-time data of each type of data:
Wherein Q i represents a reference abnormality degree of real-time data of the i-th type data; n represents the number of data present in the real-time window of the real-time data of the i-th type of data; s i,n+1,1 denotes an absolute value of a difference value of the (n+1) th data and the first data within a real-time window of real-time data of the (i) th type of data; q i,1 denotes the 1 st data within the real-time window of the real-time data of the i-th type data; q i,n+1 denotes the n+1th data within the real-time window of the real-time data of the i-th type data.
5. The method for monitoring a natural ignition beam tube of a coal mine according to claim 3, wherein the specific calculation formula corresponding to the adjustment degree of each data type is obtained according to the extreme point in the real-time window of the real-time data of each data type, wherein the specific calculation formula is as follows:
Wherein W i represents the degree of adjustment of the ith data type; j represents the number of maximum points existing in the real-time data real-time window of the ith type of data; k represents a preset data quantity; deltaw i,j,k represents the difference between the jth maximum point data and the kth data on the left side of the jth maximum point of the real-time window of the real-time data of the ith type of data; deltaw' i,j,k represents the difference between the j-th maximum point data and the k-th data on the right side of the j-th maximum point of the real-time window of the real-time data of the i-th type data; q i,1 denotes the 1 st data of the real-time window of the real-time data of the i-th type of data; q' i,j denotes the jth extreme point data of the real-time window of the real-time data of the ith type of data; norm () is a linear normalization function.
6. The method for monitoring the natural ignition beam tube of the coal mine according to claim 1, wherein the method for obtaining the adjustment coefficient of the first abnormality degree of each type of data according to the difference between the real-time data of the plurality of types of data comprises the following specific steps:
The maximum value in the Pelson correlation coefficients of the real-time data of the ith type of data and the real-time data of all other types of data is recorded as the strongest correlation coefficient of the ith type of data;
recording the maximum value in pearson correlation coefficients of the data in the real-time window of the real-time data of the ith type of data and the data in the real-time windows of the real-time data of all other types of data as the strongest correlation coefficient of the real-time window of the real-time data of the ith type of data;
and obtaining an adjustment coefficient of the first abnormality degree of the ith type of data according to the strongest correlation coefficient of the ith type of data and the strongest correlation coefficient of the real-time window of the real-time data of the ith type of data.
7. The method for monitoring a natural ignition beam tube of a coal mine according to claim 6, wherein the specific calculation formula corresponding to the adjustment coefficient of the first abnormality degree of the ith type of data is obtained according to the strongest correlation coefficient of the ith type of data and the strongest correlation coefficient of the real-time window of the real-time data of the ith type of data, and is as follows:
Wherein R i represents an adjustment coefficient of the first degree of abnormality of the i-th type data; r' i is the strongest correlation coefficient for the i-th type of data; r i is the strongest correlation coefficient of the real-time window of the real-time data of the ith type of data; the |is an absolute value function, exp () is an exponential function based on a natural constant.
8. The method for monitoring the natural ignition beam tube of the coal mine according to claim 1, wherein the specific calculation formula corresponding to the comprehensive anomaly degree of the real-time data at the current moment is obtained according to the first anomaly degree of the real-time data of all types and the adjustment coefficient of the first anomaly degree, and is as follows:
Wherein T represents the comprehensive abnormality degree of the real-time data at the current time; i represents the number of data types; e i represents a first degree of abnormality of real-time data of the i-th type of data; r i represents an adjustment coefficient of a first degree of abnormality of the i-th type data; norm () is a linear normalization function.
9. The method for monitoring the natural ignition beam tube of the coal mine according to claim 1, wherein the method for determining whether the real-time data at the current moment is abnormal by utilizing CABDDCG algorithm according to the comprehensive degree of abnormality of the current real-time data comprises the following specific steps:
obtaining the comprehensive abnormal degree of the real-time data at each moment in all types of data according to the acquisition mode of the comprehensive abnormal degree of the current real-time data;
In all types of data, the comprehensive abnormality degree of the real-time data at each moment is input into an algorithm CABDDCG, a plurality of clusters are output, the average value of all the data in the cluster where the comprehensive abnormality degree of the real-time data at the current moment is located is marked as a first average value, the average value of all the data in the cluster where the data quantity is maximum is marked as a second average value, and when the ratio of the first average value to the second average value is smaller than a preset judgment threshold value, the real-time data at the current moment is judged to be abnormal.
10. A coal mine natural ignition beam tube monitoring system comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the computer program when executed by the processor performs the steps of a coal mine natural ignition beam tube monitoring method as claimed in any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410309209.XA CN118030189B (en) | 2024-03-19 | 2024-03-19 | Method and system for monitoring natural ignition beam tube of coal mine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410309209.XA CN118030189B (en) | 2024-03-19 | 2024-03-19 | Method and system for monitoring natural ignition beam tube of coal mine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118030189A true CN118030189A (en) | 2024-05-14 |
| CN118030189B CN118030189B (en) | 2024-08-16 |
Family
ID=90993337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410309209.XA Active CN118030189B (en) | 2024-03-19 | 2024-03-19 | Method and system for monitoring natural ignition beam tube of coal mine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118030189B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04203100A (en) * | 1990-11-30 | 1992-07-23 | Nohmi Bosai Ltd | Detector of abnormality in tunnel |
| JPH0636163A (en) * | 1992-02-25 | 1994-02-10 | Kokusai Gijutsu Kaihatsu Kk | Flame detection system |
| CN104832216A (en) * | 2015-05-08 | 2015-08-12 | 淄博祥龙测控技术有限公司 | Coal mine spontaneous fire fiber temperature detection beam tube monitoring system and method |
| CN216206155U (en) * | 2021-11-30 | 2022-04-05 | 中矿佳越科技(北京)有限公司 | Mining multi-point optical fiber roof monitoring device |
| CN114964661A (en) * | 2022-05-27 | 2022-08-30 | 武汉联讯光电技术有限公司 | Underground coal mine spontaneous combustion fire bundle pipe monitoring system based on artificial intelligence |
| US20230004551A1 (en) * | 2021-07-02 | 2023-01-05 | Viettel Group | Method of processing and storing data for real time anomaly detection problem |
| CN115929383A (en) * | 2022-12-22 | 2023-04-07 | 国能榆林能源有限责任公司 | Accurate monitoring of colliery conflagration and multiple prevention and control system |
| CN116624226A (en) * | 2023-04-10 | 2023-08-22 | 中煤科工集团重庆研究院有限公司 | Coal mine disaster data acquisition, analysis and visual display system |
| CN116738817A (en) * | 2023-04-24 | 2023-09-12 | 中煤科工集团重庆研究院有限公司 | Coal mine multi-disaster fusion natural fission early warning method and system |
| CN117314218A (en) * | 2023-08-28 | 2023-12-29 | 湖南科技大学 | Coal mine water damage real-time early warning method based on big data analysis |
-
2024
- 2024-03-19 CN CN202410309209.XA patent/CN118030189B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04203100A (en) * | 1990-11-30 | 1992-07-23 | Nohmi Bosai Ltd | Detector of abnormality in tunnel |
| JPH0636163A (en) * | 1992-02-25 | 1994-02-10 | Kokusai Gijutsu Kaihatsu Kk | Flame detection system |
| CN104832216A (en) * | 2015-05-08 | 2015-08-12 | 淄博祥龙测控技术有限公司 | Coal mine spontaneous fire fiber temperature detection beam tube monitoring system and method |
| US20230004551A1 (en) * | 2021-07-02 | 2023-01-05 | Viettel Group | Method of processing and storing data for real time anomaly detection problem |
| CN216206155U (en) * | 2021-11-30 | 2022-04-05 | 中矿佳越科技(北京)有限公司 | Mining multi-point optical fiber roof monitoring device |
| CN114964661A (en) * | 2022-05-27 | 2022-08-30 | 武汉联讯光电技术有限公司 | Underground coal mine spontaneous combustion fire bundle pipe monitoring system based on artificial intelligence |
| CN115929383A (en) * | 2022-12-22 | 2023-04-07 | 国能榆林能源有限责任公司 | Accurate monitoring of colliery conflagration and multiple prevention and control system |
| CN116624226A (en) * | 2023-04-10 | 2023-08-22 | 中煤科工集团重庆研究院有限公司 | Coal mine disaster data acquisition, analysis and visual display system |
| CN116738817A (en) * | 2023-04-24 | 2023-09-12 | 中煤科工集团重庆研究院有限公司 | Coal mine multi-disaster fusion natural fission early warning method and system |
| CN117314218A (en) * | 2023-08-28 | 2023-12-29 | 湖南科技大学 | Coal mine water damage real-time early warning method based on big data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118030189B (en) | 2024-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113255733B (en) | Unsupervised anomaly detection method under multi-modal data loss | |
| CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
| CN112284440B (en) | Sensor data deviation self-adaptive correction method | |
| CN116992322B (en) | Smart city data center management system | |
| CN118245920B (en) | Coal mine data optimized transmission method | |
| CN114417699A (en) | Pump valve fault detection method | |
| CN117889945B (en) | Highway bridge construction vibration testing method | |
| CN115877363B (en) | Robot obstacle avoidance evaluation method | |
| CN115858794B (en) | Abnormal log data identification method for network operation safety monitoring | |
| CN117235617A (en) | ML-RFKNN-based photovoltaic array fault diagnosis method in sand and dust weather | |
| CN118030189B (en) | Method and system for monitoring natural ignition beam tube of coal mine | |
| CN115423079A (en) | Self-integrated satellite anomaly detection method based on central constraint contrast learning feature transformation | |
| CN117591986B (en) | Real-time automobile data processing method based on artificial intelligence | |
| CN116757337B (en) | House construction progress prediction system based on artificial intelligence | |
| CN117470529A (en) | Static friction fault detection method and system for valve of process control system | |
| CN117807538A (en) | Fault detection method based on dynamic threshold and trend prediction | |
| CN116662800A (en) | Rolling bearing fault diagnosis method based on self-adaptive attention mechanism | |
| CN116311739A (en) | Multi-sensor fire detection method based on long-short-term memory network and environment information fusion | |
| CN117131456B (en) | Multi-sensor data management method for boat bridge electric control system | |
| CN117805932B (en) | Coal seam determining method based on coal mine exploration data | |
| CN116205365B (en) | Self-adaptive prediction method and system for residual life of mechanical equipment | |
| CN113821866B (en) | Method for predicting residual life of finger protection adhesive tape of urban rail door system | |
| CN118442125B (en) | Coal mine safety monitoring and early warning system based on Internet of things | |
| CN118395090B (en) | Tail gas monitoring and treating method of coating and recycling integrated machine | |
| CN115856465A (en) | Aero-engine anomaly detection method based on coding time domain convolution |
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 |