CN116644975A - Intelligent supervision method and system for anti-collision hidden engineering construction - Google Patents
Intelligent supervision method and system for anti-collision hidden engineering construction Download PDFInfo
- Publication number
- CN116644975A CN116644975A CN202310926699.3A CN202310926699A CN116644975A CN 116644975 A CN116644975 A CN 116644975A CN 202310926699 A CN202310926699 A CN 202310926699A CN 116644975 A CN116644975 A CN 116644975A
- Authority
- CN
- China
- Prior art keywords
- current
- data
- coal
- dust amount
- coal dust
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000010276 construction Methods 0.000 title claims abstract description 31
- 239000003245 coal Substances 0.000 claims abstract description 228
- 239000002817 coal dust Substances 0.000 claims abstract description 194
- 238000005553 drilling Methods 0.000 claims abstract description 151
- 230000002159 abnormal effect Effects 0.000 claims abstract description 116
- 230000005856 abnormality Effects 0.000 claims abstract description 109
- 238000001514 detection method Methods 0.000 claims abstract description 29
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 13
- 238000009826 distribution Methods 0.000 description 5
- 238000005520 cutting process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003475 lamination Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000005641 tunneling Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B49/00—Testing the nature of borehole walls; Formation testing; Methods or apparatus for obtaining samples of soil or well fluids, specially adapted to earth drilling or wells
- E21B49/005—Testing the nature of borehole walls or the formation by using drilling mud or cutting data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mining & Mineral Resources (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Geology (AREA)
- General Business, Economics & Management (AREA)
- Marine Sciences & Fisheries (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Game Theory and Decision Science (AREA)
- Fluid Mechanics (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Probability & Statistics with Applications (AREA)
- Environmental & Geological Engineering (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Pit Excavations, Shoring, Fill Or Stabilisation Of Slopes (AREA)
Abstract
The application relates to the field of data processing, and particularly provides an intelligent supervision method and system for anti-collision hidden engineering construction, comprising the following steps: performing anomaly detection on current coal dust amount data of a current coal bed in the current drilling based on historical coal dust amount data of the current drilling to obtain data anomaly degree; determining an abnormal possibility of the coal dust amount of the current coal seam in the current drilling hole based on the historical coal dust amount data and the current coal dust amount data; calculating the abnormal credibility of the coal dust amount of the current coal bed in the current drilling hole based on the coal dust amount of the coal beds drilled around the current drilling hole; determining the reliability of abnormal coal dust amount data of the current coal seam; based on the abnormality possibility, correcting the abnormality degree of the data by the abnormality reliability and the reliability to obtain the corrected abnormality degree of the data; and determining whether the coal pressure of the current coal bed in the current borehole is abnormal or not based on the corrected data abnormality degree. The safety and the reliability of coal pressure detection are improved, and the safety of construction workers is greatly ensured.
Description
Technical Field
The application relates to the field of data processing, in particular to an intelligent supervision method and system for anti-collision hidden engineering construction.
Background
The construction of the anti-impact engineering is an important ring in the safety production process of the rock burst mine, and the construction quality and the progress of the anti-impact engineering directly determine the progress of tunneling and stoping. Meanwhile, the safety of construction staff in the construction process is also required to be ensured, and the coal seam pressure in the construction process is detected by adopting a coal dust method at present, but the abnormality of the coal seam quantity cannot be accurately analyzed in the prior art because the coal seam pressure is abnormal or other conditions are abnormal.
Therefore, a method for monitoring and managing the environment of construction staff in the process of carrying out anti-impact hidden engineering construction is needed.
Disclosure of Invention
The application provides an intelligent supervision method and system for anti-collision hidden engineering construction. The safety and the reliability of coal pressure detection are improved, and the safety of construction workers is greatly ensured.
In a first aspect, the present application provides an intelligent supervision method for anti-impact hidden engineering construction, including: performing anomaly detection on current coal dust amount data of a current coal bed in the current drilling based on historical coal dust amount data of the current drilling to obtain data anomaly degree; determining an abnormal possibility of the coal dust amount of the current coal seam in the current drilling hole based on the historical coal dust amount data and the current coal dust amount data; calculating the abnormal credibility of the coal dust amount of the current coal bed in the current drilling hole based on the coal dust amount of the coal beds drilled around the current drilling hole; determining the reliability of abnormal coal dust amount data of the current coal seam; based on the abnormality possibility, correcting the abnormality degree of the data by the abnormality reliability and the reliability to obtain the corrected abnormality degree of the data; and determining whether the coal pressure of the current coal bed in the current borehole is abnormal or not based on the corrected data abnormality degree.
In an alternative embodiment, determining the likelihood of abnormality of the current coal seam in the current borehole based on the historical coal seam quantity data and the current coal seam quantity data comprises:
calculating the abnormal possibility of the coal dust amount of the current coal seam in the current drilling hole based on the quantity of the historical coal dust amount data, the correlation of the current coal dust amount data and each historical coal dust amount data and the data abnormality degree of the historical coal dust amount data.
In an alternative embodiment, calculating the abnormal possibility of the coal dust amount of the current coal seam in the current drill hole based on the number of the historical coal dust amount data, the correlation of the current coal dust amount data and each historical coal dust amount data, and the data abnormality degree of the historical coal dust amount data comprises:
calculating the likelihood of abnormality using the following formula (1):
（1）
where n represents the number of historical coal dust amount data,representing the correlation of the current coal dust amount data and the jth historical coal dust amount data, ++>The data abnormality degree of the coal dust amount data corresponding to the ith coal bed is shown, and h is the number of layers of the coal bed.
In an alternative embodiment, calculating the abnormal credibility of the coal dust amount of the current coal seam in the current drilling hole based on the coal dust amount of the coal seam drilled around the current drilling hole comprises:
determining a correlation index of the current drilling hole and surrounding drilling holes according to the current coal dust amount of the current drilling hole and the historical coal dust amount of the surrounding drilling holes;
and determining the abnormal credibility of the coal dust amount of the current coal bed in the current drilling hole based on the number of the surrounding drilling holes, the correlation index of the current drilling holes and the surrounding drilling holes, the distance between the surrounding drilling holes and the current drilling hole and the data abnormality degree of the corresponding depth of the surrounding drilling holes in the current drilling hole.
In an alternative embodiment, determining the correlation index of the current borehole and the surrounding boreholes according to the current coal dust amount of the current borehole and the historical coal dust amount of the surrounding boreholes comprises:
determining a correlation index of the current borehole and surrounding boreholes by using the following formula (2):
（2）
wherein ,representing the historical coal dust amount of the corresponding i th surrounding borehole at the j-th survey data, determining the similarity with the current coal dust amount data of the current borehole,/->A difference between the historical coal dust amount determination representing the ith surrounding borehole and the current coal dust amount data of the current borehole, n representing the amount of the historical coal dust amount data, +.>And (5) representing the index of the correlation of the ith surrounding borehole and the current borehole.
In an alternative embodiment, determining the abnormal credibility of the coal dust amount of the current coal seam in the current drilling hole based on the number of surrounding drilling holes, the correlation index of the current drilling hole and the surrounding drilling holes, the distance between the surrounding drilling holes and the current drilling hole, and the data abnormality degree of the corresponding depth of the surrounding drilling holes in the current drilling hole comprises:
determining the abnormal credibility of the coal dust amount of the current coal seam in the current drilling hole by using the following formula (3):
（3）
wherein m represents the number of boreholes for detection,index indicating the correlation of the ith surrounding borehole with the current borehole,/for>Indicating the distance of the ith surrounding borehole to the current borehole, +.>The degree of abnormality of the data indicating the depth of the i-th surrounding borehole corresponding to the current borehole.
In an alternative embodiment, determining the reliability of the coal dust amount data anomaly of the current coal seam includes:
acquiring the data abnormality degree of different drilling holes corresponding to each coal seam, and selecting coal dust amount data with the data abnormality degree larger than a first threshold value as data to be processed;
clustering the data to be processed to obtain a data anomaly center corresponding to each coal seam;
and calculating the reliability based on the distance between the data anomaly center of the current coal seam and the data anomaly centers of other coal seams and the distance between the data anomaly center of the current coal seam and the data anomaly center of other drilling holes corresponding to the current coal seam.
In an alternative embodiment, calculating the reliability based on a distance between a data anomaly center of a current coal seam and a data anomaly center of other coal seams and a distance between a data anomaly center of the current coal seam and a data anomaly center of other holes corresponding to the current coal seam includes:
the reliability is calculated using the following equation (4):
（4）
wherein S represents the distance between the data abnormal center of the current coal bed in the current drilling hole and the data abnormal centers of other drilling holes corresponding to the current coal bed,and B represents the deviation degree of the data anomaly centers of the coal beds, wherein the calculation mode of B is as follows:
wherein ,representing the Euclidean distance between the data anomaly center of the (u) th coal seam and the data anomaly center of the (u-1) th coal dust, and the difference between the Euclidean distance between the (u+1) th coal seam data anomaly center and the data anomaly center of the (u) th coal seam, and the difference between the (u+1) th coal seam data anomaly center and the data anomaly center of the (u) th coal seam data anomaly center, and the difference between the (u+1) th coal seam data anomaly center and the data anomaly center of the (u-1) th coal dust and the data anomaly center of>And the absolute value of the difference between the angle between the connecting line of the (u) th coal seam data abnormal center and the (u-1) th coal seam data abnormal center and the horizontal right direction and the angle between the connecting line of the (u+1) th coal seam data abnormal center and the (u) th coal seam data abnormal center and the horizontal right direction is represented, and h represents the layer number of the coal seam.
In an alternative embodiment, determining whether the coal pressure abnormality occurs in the current coal seam in the current borehole based on the corrected data abnormality degree includes:
and if the modified data abnormality degree is larger than a preset value, determining that the current coal seam coal pressure is abnormal.
In a second aspect, the present application provides an intelligent supervision system for impact protection and concealment engineering construction, comprising: the abnormality detection module is used for carrying out abnormality detection on the current coal dust amount data of the current coal seam in the current drilling hole based on the historical coal dust amount data of the current drilling hole to obtain the data abnormality degree;
the calculation module is used for determining the abnormal possibility of the coal dust amount of the current coal seam in the current drilling hole based on the historical coal dust amount data and the current coal dust amount data; calculating the abnormal credibility of the coal dust amount of the current coal bed in the current drilling hole based on the coal dust amount of the coal beds drilled around the current drilling hole; determining the reliability of abnormal coal dust amount data of the current coal seam;
the correction module is used for correcting the data abnormality degree based on the abnormality possibility, the abnormality reliability and the reliability to obtain a corrected data abnormality degree;
and the abnormality determining module is used for determining whether the coal pressure abnormality occurs in the current coal bed in the current drilling hole or not based on the corrected data abnormality degree.
The beneficial effects of the application are as follows: compared with the prior art, the intelligent supervision method for the anti-collision hidden engineering construction provided by the application comprises the following steps: performing anomaly detection on current coal dust amount data of a current coal bed in the current drilling based on historical coal dust amount data of the current drilling to obtain data anomaly degree; determining an abnormal possibility of the coal dust amount of the current coal seam in the current drilling hole based on the historical coal dust amount data and the current coal dust amount data; calculating the abnormal credibility of the coal dust amount of the current coal bed in the current drilling hole based on the coal dust amount of the coal beds drilled around the current drilling hole; determining the reliability of abnormal coal dust amount data of the current coal seam; based on the abnormality possibility, correcting the abnormality degree of the data by the abnormality reliability and the reliability to obtain the corrected abnormality degree of the data; and determining whether the coal pressure of the current coal bed in the current borehole is abnormal or not based on the corrected data abnormality degree. The safety and the reliability of coal pressure detection are improved, and the safety of construction workers is greatly ensured.
Drawings
FIG. 1 is a schematic flow diagram of one embodiment of an intelligent supervision method of the impact protection and concealment engineering construction of the present application;
FIG. 2 is a graph of borehole depth versus amount of coal fines;
fig. 3 is a schematic structural view of an embodiment of an intelligent supervision device for impact protection and concealment engineering construction according to the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The method is used for monitoring the construction environment and guaranteeing the safety of constructors when the anti-collision hidden engineering construction is carried out. The present application will be described in detail with reference to the accompanying drawings and examples.
Referring to fig. 1, a flow chart of a first embodiment of an intelligent supervision method for anti-collision hidden engineering construction according to the present application specifically includes:
step S11: and carrying out anomaly detection on the current coal dust amount data of the current coal seam in the current drilling hole based on the historical coal dust amount data of the current drilling hole to obtain the data anomaly degree.
Specifically, when carrying out scour protection hidden engineering construction, carry out real-time supervision through using the coal dust method to the construction environment, ensure the safety at the process of carrying out the pressure release to and adjust the pressure release degree that corresponds.
At a construction site, the amount of coal dust is obtained by using a drilling cutting method, and the pressure of the coal bed is detected according to the amount of the coal dust, namely, the amount of the coal dust is recorded as z. I.e. one set of data at a time is acquired and noted as Z { Z1, Z2, …, zh }, h representing the depth of the borehole, i.e. the number of coal seams. There are a plurality of test boreholes, the number of which is denoted as m. The data collected by each drill hole is plotted into a curve image by taking the coal dust amount as an ordinate and the collection depth, namely the coal seam amount as an abscissa, and particularly, refer to fig. 2.
Specifically, an existing data anomaly detection algorithm LOF algorithm is used for anomaly detection of acquired coal seam data and historical data thereof. It should be noted that, here, the historical data refers to the historical coal dust amount data in the current drill hole, and the historical coal dust amount data and the current coal dust amount data represent the coal dust amounts of different coal layers. And carrying out anomaly detection on the current coal dust amount data of the current coal seam in the current drilling hole based on the historical coal dust amount data of the current drilling hole to obtain the data anomaly degree.
For example, the historical coal dust amount data obtained by the current drilling includes Z { Z1, Z2, …, zh }, and then the current coal dust amount data of the current drilling is zh+1. And performing anomaly detection on Z { Z1, Z2, …, zh, zh+1} by using an anomaly detection algorithm, such as an LOF algorithm, so as to obtain a data anomaly result. And carrying out normalization processing on the data abnormal result, and further obtaining the data abnormal degree R of the current drilling corresponding to the current coal seam. It will be appreciated that using this method, the degree of data anomalies for each borehole at each coal seam can be calculated.
Step S12: determining an abnormal possibility of the coal dust amount of the current coal seam in the current drilling hole based on the historical coal dust amount data and the current coal dust amount data; calculating the abnormal credibility of the coal dust amount of the current coal bed in the current drilling hole based on the coal dust amount of the coal beds drilled around the current drilling hole; and determining the possibility that the abnormal coal dust quantity of the current coal bed is abnormal in coal pressure based on the current coal bed in the current drilling hole and other coal beds in the current drilling hole.
In an embodiment, the analysis is performed according to the current drilling hole, so that an abnormality index corresponding to each coal seam can be obtained, and specifically, the abnormality index includes an abnormality probability of the coal dust amount of the current coal seam in the current drilling hole, an abnormality reliability of the coal dust amount of the current coal seam in the current drilling hole, and a possibility that the coal dust amount of the current coal seam is abnormal as a coal pressure. Based on the abnormality index, it can be determined whether the current coal seam has abnormal coal pressure.
Specifically, for the same borehole, if the coal pressure of the current coal seam is abnormal in the same borehole, the abnormal coal pressure of other coal seams in the current borehole can be detected, and the abnormal coal pressure can be expressed as abnormal coal dust amount, so that whether the current coal seam coal dust amount is abnormal or not can be judged according to the correlation between the historical coal dust amount data based on the current borehole and the current coal dust amount data corresponding to the current coal seam and the abnormal degree of the coal dust of the corresponding coal seam. In a specific embodiment, the abnormal probability of the coal dust amount of the current coal seam in the current drilling hole is calculated based on the number of the historical coal dust amount data, the correlation of the current coal dust amount data and each historical coal dust amount data and the data abnormality degree of the historical coal dust amount data.
In one embodiment, the likelihood of anomaly is calculated using the following equation (1):
（1）
where n represents the number of historical coal dust amount data,representing the correlation of the current coal dust amount data and the jth historical coal dust amount data, ++>The data abnormality degree of the coal dust amount data corresponding to the ith coal bed is shown, and h is the number of layers of the coal bed.
Specifically, the correlation of the current coal dust amount data and the jth historical coal dust amount data can be obtained through the similarity of the curves drawn in fig. 2. The curve similarity is calculated by a shape context algorithm and is not described in detail here. That is, if the curves corresponding to the historical coal dust amount data of the current drilling hole are more similar, the corresponding coal dust amount data of each layer are more relevant, the corresponding coal bed data are abnormal, the current coal dust amount data can be more abnormal, namely, when the obtained coal dust amount data are obtainedThe larger the correspondence +.>The larger the analysis data is, the greater the abnormality possibility W of the current analysis data caused by abnormal coal pressure is.
According to analysis of different drilling positions, the drilling holes with the closer distance from the current drilling hole are closer to the coal seam distribution condition, so that the corresponding drilling hole coal dust amount is closer to the coal seam when the drilling holes are detected, and the abnormal credibility of the current coal dust amount in the current drilling hole can be determined according to the coal dust amount of the surrounding drilling hole coal seams of the current drilling hole. Specifically, the abnormal credibility of the coal dust amount of the current coal bed in the current drilling hole is calculated based on the coal dust amount of the coal beds drilled around the current drilling hole.
In a specific embodiment, determining a correlation index of the current drilling hole and surrounding drilling holes according to the current coal dust amount of the current drilling hole and the historical coal dust amount of the surrounding drilling holes; and determining the abnormal credibility of the coal dust amount of the current coal bed in the current drilling hole based on the number of the surrounding drilling holes, the correlation index of the current drilling holes and the surrounding drilling holes, the distance between the surrounding drilling holes and the current drilling hole and the data abnormality degree of the corresponding depth of the surrounding drilling holes in the current drilling hole.
In one embodiment, the correlation index of the current borehole with the surrounding boreholes is determined using equation (2) as follows:
（2）
wherein ,representing the historical coal dust amount of the corresponding i th surrounding borehole at the j-th survey data, determining the similarity with the current coal dust amount data of the current borehole,/->A difference between the historical coal dust amount determination representing the ith surrounding borehole and the current coal dust amount data of the current borehole, n representing the amount of the historical coal dust amount data, +.>A correlation index representing the ith surrounding borehole and the current borehole; that is, when the coal dust amount curves of each layer obtained in the history of the surrounding drilling holes are more similar to the coal dust amount curves of each layer obtained by the current drilling holes, and the difference of the coal dust amounts of the corresponding layers is smaller, the correlation between the current drilling holes and the surrounding drilling holes is stronger.
Drawing each drilling hole acquisition data by taking the coal dust amount as an ordinate and the drilling hole depth as an abscissa to form a drilling hole depth-coal dust amount image, calculating the similarity of curves in the drilling hole depth-coal dust amount image by using a shape context algorithm, and calculating the similarity of the obtained historical coal dust amount of the ith surrounding drilling hole and the current coal dust amount data of the current drilling hole。
Further, determining the abnormal credibility of the coal dust amount of the current coal seam in the current drilling hole by using the following formula (3):
（3）
wherein m represents the number of boreholes for detection,indicating the correlation index of the ith surrounding borehole and the current borehole, wherein the larger the correlation index is, the more reliable the corresponding data is, and the more reliable the corresponding data is>Indicating the distance from the ith surrounding borehole to the current borehole, i.e., when the closer the distance is, the more reliable the corresponding cuttings hole data is, the +.>The degree of abnormality of the data representing the depth corresponding to the ith surrounding borehole at the current borehole, i.e. when each borehole is found to be closer to the current borehole and the degree of abnormality of the corresponding data is greater, it is indicated that the current data abnormality is more likely to be an abnormality due to the change of the coal seam pressure.
Further, according to the analysis of the coal seam pressure, the depth of the drilling hole is found to be deeper, the corresponding pressure is higher, the current coal seam pressure is higher, the corresponding abnormality degree is also abnormal, an abnormality threshold is set, all the current abnormal layer numbers and the corresponding drilling positions are obtained, namely, even if the coal seam pressure is increased, the collected coal dust is changed, the drilling holes concentrated in the impact area are similar to the abnormality of the corresponding drilling layers, so that whether the abnormality of the coal seam data quantity of the current analysis drilling hole accords with the abnormality position distribution can be judged according to the abnormal coal dust quantity distribution condition, and the current data is more reliable if the abnormality accords with the abnormality. According to the method, all abnormal acquisition positions which are larger than the threshold value are analyzed according to the abnormal degree, firstly, drilling data acquisition points of which the abnormal degree of each layer is larger than the threshold value are acquired, the acquisition points are clustered by using a DBSCAN algorithm, and corresponding clustering centers are acquired. By using the method, the data of each layer of coal seam is analyzed, and then the abnormal center of the corresponding data abnormality of each layer is obtained. And acquiring the abnormal reliability of the coal dust amount data of the current coal seam by calculating the distance between the abnormal center of the layer where the current analysis data is located and the data abnormal centers of other layers and the distance between the current abnormal data and the data abnormal center corresponding to the layer.
Specifically, the possibility of coal pressure abnormality is calculated using the following formula (4):
（4）
wherein S represents the distance between the data abnormal center of the current coal bed in the current drilling hole and the data abnormal centers of other drilling holes corresponding to the current coal bed,and B represents the deviation degree of the data anomaly centers of the coal beds, wherein the calculation mode of B is as follows:
wherein ,representing the Euclidean distance between the data anomaly center of the (u) th coal seam and the data anomaly center of the (u-1) th coal dust, and the difference between the Euclidean distance between the (u+1) th coal seam data anomaly center and the data anomaly center of the (u) th coal seam, and the difference between the (u+1) th coal seam data anomaly center and the data anomaly center of the (u) th coal seam data anomaly center, and the difference between the (u+1) th coal seam data anomaly center and the data anomaly center of the (u-1) th coal dust and the data anomaly center of>And the absolute value of the difference between the angle between the connecting line of the (u) th coal seam data abnormal center and the (u-1) th coal seam data abnormal center and the horizontal right direction and the angle between the connecting line of the (u+1) th coal seam data abnormal center and the (u) th coal seam data abnormal center and the horizontal right direction is represented, and h represents the layer number of the coal seam. Namely, when the angle difference formed between adjacent layers of the abnormal data center points of all the layers is smaller, the distance difference is smaller, the possibility that the coal pressure abnormality occurs in the corresponding coal layer is indicated, and the possibility that the abnormal data is caused by the coal pressure abnormality is larger.
When the distance between the current analysis data and the abnormal center of the abnormal drill hole of the other drill hole data is smaller and the distance between the abnormal center of the drill hole of the layer and the abnormal center of the drill hole of the other layer is smaller, the current analysis data is more likely to be caused by the change of the lamination of the coal layer, namely the current acquired data is more reliable. Because the coal pressure change is concentrated in the coal seam, the abnormal centers of all layers are concentrated corresponding to the detection data of each layer, so that the abnormal data centers of all layers can be obtained, the adjacent abnormal data centers of all layers are calculated, and whether the current coal dust data abnormality of all the coal seams is caused by the coal pressure abnormality is judged according to the deviation degree of the abnormal data centers.
Step S13: and correcting the data abnormality degree based on the abnormality probability, the abnormality reliability and the reliability to obtain the corrected data abnormality degree.
According to the obtained indexes (anomaly possibility, anomaly reliability and reliability), the anomaly of the current data, namely the anomaly degree of the data is corrected, so that the anomaly degree of the current data can better correspond to the anomaly of the coal pressure change of the coal bed on the surface, and the anomaly of the data caused by other factors is reduced, and the correction method is as follows:
wherein 、/>For regulating parameters, in the present application +.>=0.6，/>=0.4，/>Representing the possibility that the current data abnormality is coal pressure abnormality according to the analysis of the other data of the current drilling, normalizing the possibility W of the abnormality to obtain +.>Representing the possibility that the current data obtained according to other borehole data analysis is abnormal in coal pressure, wherein corresponding parameters are obtained by normalizing the abnormal reliability Q and the reliability Y respectively, and the corresponding parameters are the following parameters>The abnormal detection of the current coal dust amount data is indicated to obtain the data abnormal degree.
Step S14: and determining whether the coal pressure of the current coal bed in the current borehole is abnormal or not based on the corrected data abnormality degree.
By using the method, the anomaly analysis and correction are carried out on each acquired data. And if the modified data abnormality degree is larger than a preset value, determining that the current coal seam coal pressure is abnormal. Setting a preset value lambda=0.7, i.e. when the data is abnormalWhen the current data is larger than the preset value, the current data can be considered to be abnormal.
And setting a neighborhood radius r=10 and a threshold value psi=15 through counting the abnormal number of data and abnormal data distribution, namely when the obtained abnormal data is distributed in the range of a circle with the radius r and the abnormal data is larger than the threshold value psi, the abnormal coal pressure of the coal bed in the current area can be considered, the number of holes in the area needs to be increased, and the detection of the coal bed pressure in the area is enhanced. And adjusting the pressure relief scheme according to the obtained coal dust amount. Specifically, when detecting, if there are more than 15 abnormal detection data in the detection area within the size range of 10×10 neighborhood, it is indicated that the current area has abnormal amount per layer. At the moment, the pressure relief scheme is required to be adjusted according to the amount of coal dust, so that the safety of construction workers is ensured.
When the LOF algorithm is used for carrying out anomaly analysis on the historical data and the current data, only the condition of the anomaly of the current data can be analyzed, but the condition that the anomaly of the current data is caused cannot be determined, so that further analysis on the data with the anomaly is needed, and further unnecessary waste of manpower and material resources caused by detecting the anomaly of the data is avoided. According to the application, the current drilling acquisition data is analyzed according to the drilling cuttings amount, drilling distribution and other conditions obtained by a plurality of drilling holes, so that the reliability of the abnormality of the current acquisition data as abnormal coal pressure is increased, the drilling cuttings acquisition amount of the area is increased, the safety and reliability of coal pressure detection are greatly increased, and the safety of construction workers is greatly ensured.
Referring to fig. 3, a schematic structural diagram of an embodiment of an intelligent supervision system for anti-collision hidden engineering construction according to the present application includes: an abnormality detection module 31, a calculation module 32, a correction module 33, and an abnormality determination module 34.
The abnormality detection module 31 is configured to perform abnormality detection on current coal dust amount data of a current coal seam in a current borehole based on historical coal dust amount data of the current borehole, so as to obtain a data abnormality degree. The calculation module 32 is configured to determine an anomaly likelihood for the current coal seam's coal dust amount in the current borehole based on the historical coal dust amount data and the current coal dust amount data; calculating the abnormal credibility of the coal dust amount of the current coal bed in the current drilling hole based on the coal dust amount of the coal beds drilled around the current drilling hole; and determining the reliability of abnormal coal dust amount data of the current coal seam. The correction module 33 is configured to correct the data anomaly degree based on the anomaly possibility, the anomaly reliability and the reliability, and obtain a corrected data anomaly degree. The abnormality determination module 34 is configured to determine whether a coal pressure abnormality occurs in the current coal seam in the current borehole based on the corrected degree of data abnormality.
The foregoing is only the embodiments of the present application, and therefore, the patent scope of the application is not limited thereto, and all equivalent structures or equivalent processes using the descriptions of the present application and the accompanying drawings, or direct or indirect application in other related technical fields, are included in the scope of the application.
Claims (10)
1. An intelligent supervision method for anti-collision hidden engineering construction is characterized by comprising the following steps:
performing anomaly detection on current coal dust amount data of a current coal bed in the current drilling based on historical coal dust amount data of the current drilling to obtain data anomaly degree;
determining an abnormal possibility of the coal dust amount of the current coal seam in the current drilling hole based on the historical coal dust amount data and the current coal dust amount data; calculating the abnormal credibility of the coal dust amount of the current coal bed in the current drilling hole based on the coal dust amount of the coal beds drilled around the current drilling hole; determining the reliability of abnormal coal dust amount data of the current coal seam;
based on the abnormality possibility, the abnormality credibility and the reliability correct the data abnormality degree to obtain a corrected data abnormality degree;
and determining whether the coal pressure of the current coal bed in the current borehole is abnormal or not based on the corrected data abnormality degree.
2. The method of claim 1, wherein determining an anomaly likelihood for a current coal seam coal level in a current borehole based on the historical coal level data and current coal level data comprises:
calculating the abnormal possibility of the coal dust amount of the current coal seam in the current drilling hole based on the quantity of the historical coal dust amount data, the correlation of the current coal dust amount data and each historical coal dust amount data and the data abnormality degree of the historical coal dust amount data.
3. The method of claim 2, wherein calculating the likelihood of abnormality of the coal dust amount of the current coal seam in the current borehole based on the number of the historical coal dust amount data, the correlation of the current coal dust amount data with each historical coal dust amount data, and the degree of data abnormality of the historical coal dust amount data, comprises:
calculating the likelihood of abnormality using the following formula (1):
（1）
where n represents the number of historical coal dust amount data,representing the correlation of the current coal dust amount data and the jth historical coal dust amount data, ++>The data abnormality degree of the coal dust amount data corresponding to the ith coal bed is shown, and h is the number of layers of the coal bed.
4. The method of claim 1, wherein calculating an abnormal confidence in the current amount of coal fines in the current coal seam in the current borehole based on the amount of coal fines in the coal seam in the borehole surrounding the current borehole, comprises:
determining a correlation index of the current drilling hole and surrounding drilling holes according to the current coal dust amount of the current drilling hole and the historical coal dust amount of the surrounding drilling holes;
and determining the abnormal credibility of the coal dust amount of the current coal bed in the current drilling hole based on the number of the surrounding drilling holes, the correlation index of the current drilling holes and the surrounding drilling holes, the distance between the surrounding drilling holes and the current drilling hole and the data abnormality degree of the corresponding depth of the surrounding drilling holes in the current drilling hole.
5. The method of claim 4, wherein determining a correlation indicator for the current borehole and the surrounding borehole based on the current amount of coal fines for the current borehole and the historical amount of coal fines for the surrounding borehole comprises:
determining a correlation index of the current borehole and surrounding boreholes by using the following formula (2):
（2）
wherein ,representing the historical coal dust amount of the corresponding i th surrounding borehole at the j-th survey data, determining the similarity with the current coal dust amount data of the current borehole,/->Determining a difference between historical coal dust amount representing an ith surrounding borehole and current coal dust amount data for a current boreholeDifferent, n represents the number of historical coal dust amount data, +.>A correlation index representing the ith surrounding borehole and the current borehole;
drawing each drilling hole acquisition data by taking the coal dust amount as an ordinate and the drilling hole depth as an abscissa to form a drilling hole depth-coal dust amount image, calculating the similarity of curves in the drilling hole depth-coal dust amount image by using a shape context algorithm, and calculating the similarity of the obtained historical coal dust amount of the ith surrounding drilling hole and the current coal dust amount data of the current drilling hole。
6. The method of claim 4, wherein determining the abnormal confidence of the coal fines amount of the current coal seam in the current borehole based on the number of surrounding boreholes, the correlation index of the current borehole to the surrounding borehole, the distance from the surrounding borehole to the current borehole, and the degree of data abnormality of the corresponding depth of the surrounding borehole in the current borehole, comprises:
determining the abnormal credibility of the coal dust amount of the current coal seam in the current drilling hole by using the following formula (3):
（3）
wherein m represents the number of boreholes for detection,indicating the index of the correlation of the ith surrounding borehole with the current borehole,indicating the distance of the ith surrounding borehole to the current borehole, +.>Represents the ith circumferenceThe degree of abnormality of the drill hole at the data of the depth corresponding to the current drill hole.
7. The method of claim 1, wherein determining the reliability of the current coal seam for the coal fines volume data anomaly comprises:
acquiring the data abnormality degree of different drilling holes corresponding to each coal seam, and selecting coal dust amount data with the data abnormality degree larger than a first threshold value as data to be processed;
clustering the data to be processed to obtain a data anomaly center corresponding to each coal seam;
and calculating the reliability based on the distance between the data anomaly center of the current coal seam and the data anomaly centers of other coal seams and the distance between the data anomaly center of the current coal seam and the data anomaly center of other drilling holes corresponding to the current coal seam.
8. The method of claim 7, wherein calculating the reliability based on a distance of a data anomaly center of a current coal seam from a data anomaly center of other coal seams and a distance of a data anomaly center of a current coal seam from a data anomaly center of other boreholes corresponding to the current coal seam comprises:
the reliability is calculated using the following equation (4):
（4）
wherein S represents the distance between the data abnormal center of the current coal bed in the current drilling hole and the data abnormal centers of other drilling holes corresponding to the current coal bed,and B represents the deviation degree of the data anomaly centers of the coal beds, wherein the calculation mode of B is as follows:
wherein ,representing the Euclidean distance between the data anomaly center of the (u) th coal seam and the data anomaly center of the (u-1) th coal dust, and the difference between the Euclidean distance between the data anomaly center of the (u+1) th coal seam and the data anomaly center of the (u) th coal seam,and the absolute value of the difference between the angle between the connecting line of the (u) th coal seam data abnormal center and the (u-1) th coal seam data abnormal center and the horizontal right direction and the angle between the connecting line of the (u+1) th coal seam data abnormal center and the (u) th coal seam data abnormal center and the horizontal right direction is represented, and h represents the layer number of the coal seam.
9. The method of claim 1, wherein determining whether a coal pressure anomaly has occurred in a current coal seam in the current borehole based on the corrected degree of data anomaly comprises:
and if the modified data abnormality degree is larger than a preset value, determining that the current coal seam coal pressure is abnormal.
10. An intelligent supervisory system for anti-collision hidden engineering construction, which is characterized by comprising:
the abnormality detection module is used for carrying out abnormality detection on the current coal dust amount data of the current coal seam in the current drilling hole based on the historical coal dust amount data of the current drilling hole to obtain the data abnormality degree;
the calculation module is used for determining the abnormal possibility of the coal dust amount of the current coal seam in the current drilling hole based on the historical coal dust amount data and the current coal dust amount data; calculating the abnormal credibility of the coal dust amount of the current coal bed in the current drilling hole based on the coal dust amount of the coal beds drilled around the current drilling hole; determining the reliability of abnormal coal dust amount data of the current coal seam;
the correction module is used for correcting the data abnormality degree based on the abnormality possibility, the abnormality reliability and the reliability to obtain a corrected data abnormality degree;
and the abnormality determining module is used for determining whether the coal pressure abnormality occurs in the current coal bed in the current drilling hole or not based on the corrected data abnormality degree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310926699.3A CN116644975B (en) | 2023-07-27 | 2023-07-27 | Intelligent supervision method and system for anti-collision hidden engineering construction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310926699.3A CN116644975B (en) | 2023-07-27 | 2023-07-27 | Intelligent supervision method and system for anti-collision hidden engineering construction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116644975A true CN116644975A (en) | 2023-08-25 |
| CN116644975B CN116644975B (en) | 2023-10-10 |
Family
ID=87623351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310926699.3A Active CN116644975B (en) | 2023-07-27 | 2023-07-27 | Intelligent supervision method and system for anti-collision hidden engineering construction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116644975B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116975768A (en) * | 2023-09-22 | 2023-10-31 | 山东爱福地生物股份有限公司 | Data anomaly detection method for fertilizer safety production |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180293336A1 (en) * | 2017-04-06 | 2018-10-11 | Qingfeng TAO | Forecasting ultimate recovery of oil and oil production for a multiply-fractured horizontal well |
| WO2021088190A1 (en) * | 2019-11-06 | 2021-05-14 | 山东科技大学 | Method for using multiple parameters and measurements while drilling to determine coal mass stress peak region and issue early warning |
| CN112882911A (en) * | 2021-02-01 | 2021-06-01 | 中电科网络空间安全研究院有限公司 | Abnormal performance behavior detection method, system, device and storage medium |
| US20220003108A1 (en) * | 2020-02-03 | 2022-01-06 | Landmark Graphics Corporation | Event prediction using state-space mapping during drilling operations |
| CN114320267A (en) * | 2021-11-24 | 2022-04-12 | 淮北矿业股份有限公司 | Database-managed drilling depth calculation method |
| CN114528190A (en) * | 2022-04-21 | 2022-05-24 | 云账户技术(天津)有限公司 | Single index abnormality detection method and device, electronic equipment and readable storage medium |
| CN116146282A (en) * | 2023-04-18 | 2023-05-23 | 枣庄矿业(集团)济宁七五煤业有限公司 | Intelligent supervision system for anti-collision hidden engineering construction |
-
2023
- 2023-07-27 CN CN202310926699.3A patent/CN116644975B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180293336A1 (en) * | 2017-04-06 | 2018-10-11 | Qingfeng TAO | Forecasting ultimate recovery of oil and oil production for a multiply-fractured horizontal well |
| WO2021088190A1 (en) * | 2019-11-06 | 2021-05-14 | 山东科技大学 | Method for using multiple parameters and measurements while drilling to determine coal mass stress peak region and issue early warning |
| US20220003108A1 (en) * | 2020-02-03 | 2022-01-06 | Landmark Graphics Corporation | Event prediction using state-space mapping during drilling operations |
| CN112882911A (en) * | 2021-02-01 | 2021-06-01 | 中电科网络空间安全研究院有限公司 | Abnormal performance behavior detection method, system, device and storage medium |
| CN114320267A (en) * | 2021-11-24 | 2022-04-12 | 淮北矿业股份有限公司 | Database-managed drilling depth calculation method |
| CN114528190A (en) * | 2022-04-21 | 2022-05-24 | 云账户技术(天津)有限公司 | Single index abnormality detection method and device, electronic equipment and readable storage medium |
| CN116146282A (en) * | 2023-04-18 | 2023-05-23 | 枣庄矿业(集团)济宁七五煤业有限公司 | Intelligent supervision system for anti-collision hidden engineering construction |
Non-Patent Citations (3)
| Title |
|---|
| JINGLONG LIU等: "Underground Coal Fire Detection and Monitoring Based on Landsat-8 and Sentinel-1 Data Sets in Miquan Fire Area, XinJiang", REMOTE SENSING, pages 1 - 24 * |
| 崔洪庆;朱加锋;: "基于瓦斯抽采钻孔的瓦斯地质异常勘探", 煤炭科学技术, no. 02, pages 16 - 19 * |
| 张巨峰等: "基于动态数据驱动的煤矿瓦斯异常涌出风险预警系统设计", 《中 国 安 全 生 产 科 学 技 术》, vol. 18, pages 100 - 105 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116975768A (en) * | 2023-09-22 | 2023-10-31 | 山东爱福地生物股份有限公司 | Data anomaly detection method for fertilizer safety production |
| CN116975768B (en) * | 2023-09-22 | 2023-12-19 | 山东爱福地生物股份有限公司 | Data anomaly detection method for fertilizer safety production |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116644975B (en) | 2023-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116644975B (en) | Intelligent supervision method and system for anti-collision hidden engineering construction | |
| CA3091766C (en) | Enhanced surveillance of subsurface operation integrity using microseismic data | |
| US8965701B2 (en) | System and method for automatic detection and analysis of borehole breakouts from images and the automatic generation of alerts | |
| US20120188090A1 (en) | System and method for generation of alerts and advice from automatically detected borehole breakouts | |
| WO2020163040A1 (en) | Enhanced surveillance of subsurface operation integrity using neural network analysis of microseismic data | |
| WO2013112398A1 (en) | System and method for generation of alerts and advice from automatically detected borehole breakouts | |
| CN115455791B (en) | Method for improving landslide displacement prediction accuracy based on numerical simulation technology | |
| CN109902265B (en) | Underground early warning method based on hidden Markov model | |
| CN117489413B (en) | Advanced detection and early warning method for abnormal gas emission of coal bed | |
| CN111914419B (en) | Saturated silt standard penetration liquefaction judgment method | |
| NO20220852A1 (en) | Methods for estimating a position of a well path within a subsurface formation | |
| CN117423213A (en) | Landslide hazard monitoring system and method | |
| CN116341370A (en) | TBM tunneling rock mass quality rapid determination method | |
| CN115492639A (en) | Coal roadway driving working face coal and gas outburst early warning method | |
| CN112664186B (en) | Method for early warning and identifying other high-voltage source by using methane carbon isotope data | |
| CN106353794A (en) | Method for correcting micro-seismic velocity models on basis of relative first arrival matching errors | |
| CN108413927B (en) | Method and system for monitoring geological settlement of water-soluble mining salt well | |
| CN112698424A (en) | Method for obtaining fault rock displacement pressure based on rock debris | |
| CN117780249B (en) | Investigation site safety monitoring system and method based on artificial intelligence | |
| CN111814115B (en) | Method for correcting reliability-containing safe drilling fluid density window of fractured lost formation | |
| CN117805932B (en) | Coal seam determining method based on coal mine exploration data | |
| CN117148430B (en) | Shale oil fracturing microseism monitoring method | |
| CN117350543A (en) | Underground water permeability accident prediction method based on AI algorithm and distributed hydrological sensor | |
| CN118008479A (en) | Digital forecasting and early warning method for tunnel geological disasters in high-risk karst areas | |
| CN118517256A (en) | Intelligent control system of directional drilling equipment |
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 |