CN113987095A - GIS (geographic information System) space-time data model for underground illegal mining identification - Google Patents
GIS (geographic information System) space-time data model for underground illegal mining identification Download PDFInfo
- Publication number
- CN113987095A CN113987095A CN202111156453.XA CN202111156453A CN113987095A CN 113987095 A CN113987095 A CN 113987095A CN 202111156453 A CN202111156453 A CN 202111156453A CN 113987095 A CN113987095 A CN 113987095A
- Authority
- CN
- China
- Prior art keywords
- geological
- model
- space
- mining
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Abstract
The invention discloses a GIS (geographic information system) spatiotemporal data model facing underground illegal mining identification, which comprises a geometric element model layer, a spatiotemporal process model layer, a spatiotemporal inversion model layer and an illegal identification model layer, wherein the expressions of spatiotemporal processes of mine geological objects such as ore bodies, roadways, rock masses, mining right ranges, underground mining surfaces, goafs and the like under multiple time granularities and multiple spatial scales can be comprehensively supported through the mutual correlation and interaction of the four model layers, and the fusion of multi-level source to ground observation data and the response of multi-level illegal mining events are realized; the method is characterized in that a GIS (geographic information System) space-time data model facing underground illegal mining identification is established by simulating and describing the time-space change process of the mining subsidence on the basis of analyzing and expressing the time-space change of the mining subsidence in combination with the actual demand of underground illegal mining real-time monitoring, and platform guarantee is provided for the identification and monitoring of subsequent different types of illegal mining events.
Description
Technical Field
The invention relates to the technical field of illegal mining identification, in particular to a GIS (geographic information system) space-time data model for underground illegal mining identification.
Background
During underground mining of the mine, along with continuous propulsion of the underground mining surface, geological objects such as rock strata, ore bodies, earth surfaces and the like of the mine are influenced to a certain extent to generate displacement and deformation, even the inherent attribute information of the geological objects is changed, the dynamic process of underground mining of the mine has the space-time change characteristics of multiple sources, multiple dimensions and multiple granularities, and mining subsidence and earth surface deformation are caused when underground mining of the mine reaches a certain extent;
during the spatial movement of mining subsidence, the mining subsidence is continuously propelled by an underground working face to cause deformation of surrounding rocks of a mine, bending of overlying rocks, collapse of rock mass, gliding of collapsed rocks and uplift of floor rock stratum, and finally the mining subsidence is affected to the ground surface from the interior of the rock mass to generate movement deformation, thereby causing huge geological disasters and damage to the ecological environment of a mining area; the ground surface moving deformation is related to various geological mining conditions such as mining depth, mining thickness, roof management method, coal bed occurrence, mining area geometric shape and the like, and various ground information such as ground building distribution, water conservancy facility distribution, land cultivation condition, agricultural layout condition, traffic condition and the like;
therefore, in the underground mining process of the mine, the time-space change process of mining subsidence is accurately simulated and described, platform guarantee can be effectively provided for identification and monitoring of different types of illegal mining events in the later period, economic loss and casualties caused by underground illegal mining of the mine are reduced, a mine model constructed by a traditional information system of mine informatization is difficult to support dynamic digital expression of the time-space process of underground mining, and geological phenomena and dynamic processes caused by underground mining of the mine cannot be accurately reflected.
Disclosure of Invention
Aiming at the existing problems, the invention aims to provide a GIS space-time data model facing underground illegal mining identification, which is established by simulating and describing the time-space change process of mining subsidence on the basis of analyzing and expressing the time-space change of mining subsidence by combining the actual requirements of underground illegal mining real-time monitoring, and provides platform guarantee for the identification and monitoring of subsequent different types of illegal mining events.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a GIS (geographic information system) spatio-temporal data model for underground illegal mining identification comprises a geometric element model layer, a spatio-temporal process model layer, a spatio-temporal inversion model layer and an illegal identification model layer;
the geometric element model layer is a basic part of spatial data integration and expansion model, can abstract the whole geological geometric space into four spatial entity objects of points, lines, surfaces and bodies according to the geometric element expression requirements of the above-ground and underground models, the indoor models and the outdoor models, simultaneously carries out geometric expression on the geological entity objects in space and form, and can also provide support for data compatibility and bottom layer operation of related models to form a geometric element unified expression model;
the space-time process model layer is mainly composed of a dynamic GIS space-time data model and is a core component of an extended model, and on the basis of the dynamic GIS space-time data model, a geological event multi-factor driving model is combined to integrate the space-time process, a geographic object, an event type, a state and observation related elements into one space-time data model to form a space-time process unified expression model;
the space-time inversion model layer is based on a geometric element unified expression model and a space-time process unified expression model, a multi-space-time and multi-scale multi-dimensional geological space-time model supporting geological space-time objects is constructed according to the internal requirements of underground illegal mining identification, on the basis, a mining subsidence mechanism and a probability integration method are utilized, a Quantum Genetic Algorithm (QGA) and a quantum annealing method (QA) are introduced at the same time, and an underground mining inversion model for inverting new underground mining events and underground goaf space positions and ranges is constructed;
the illegal recognition model layer is used for analyzing the multi-dimensional geological space-time model and the underground mining inversion model, expressing the change of the spatial characteristics and the thematic attribute characteristics of the geological objects along the time axis, then performing space-time analysis on the related geological objects at different moments, and comprehensively considering or utilizing thematic monitoring data and underground data to establish a discrimination model between legal mining and illegal mining.
Preferably, the geometric element model layer can observe and measure natural geographic phenomena in the region by using a plurality of sensors or space-sky-ground observation means, form dynamic space-time information and special attributes in the whole geological geometric space of the region, and send the formed space-time information and special attributes to the space-time inversion model layer;
wherein: the air-space-ground observation means refer to radar SAR, optical remote sensing, unmanned aerial vehicles, GPS and leveling means.
Preferably, the spatiotemporal process model layer comprises a settlement data observation module, an event library pool and a spatiotemporal layer;
the settlement data observation module is used for dynamically recording ground surface settlement data in the underground mining process to obtain dynamic variable input of different geological objects, forming different event libraries according to ground surface settlement conditions, and sending events to different agent objects according to event types in the event libraries to form a time-space map layer containing a plurality of agent objects;
the spatio-temporal layer creates different geological events according to different proxy objects, forms an event pool containing multiple data, and establishes a geological event multi-factor driving model according to the event pool; integrating data of relevant elements such as the spatio-temporal process, geographic objects, events, event types, states, observation and the like processed by the spatio-temporal process model layer into a spatio-temporal data model to form a spatio-temporal process unified expression model, and sending the spatio-temporal process unified expression model into the spatio-temporal inversion model layer;
wherein: the agent object is mainly responsible for processing specific events generated by the geological event multi-factor driving model object, not only can receive corresponding response events of a general geological object, but also can process output of corresponding results in a geological simulation process; the map layer is the most basic element in the map, namely the data is divided into a plurality of files according to attributes, each file data has a set object class with common structure and characteristics, and the map layer class is loaded into a geological space-time process and can be used for responding to geological events; the event library is stored with a plurality of different geological event types, wherein the geological event types comprise constraint conditions for geological objects to generate geological events of the type or constraint conditions for driving the geological events to drive the geological events to change ground objects; in the geological space-time data model, geological event types need to be registered in corresponding geological objects according to different purposes, a plurality of different geological objects are formed, and a geological event multi-factor driving model is formed.
Preferably, the process of establishing the underground mining inversion model comprises
S1, establishing a probability integral parameter inversion model based on QA;
and S2, constructing a probability integral parameter inversion model based on the QGA.
Preferably, the specific steps of establishing the QA-based probability integral parametric inversion model in step S1 include:
s101, setting the actually measured subsidence and horizontal movement of the earth surface movement observation point above the working surface as W respectivelyai、UaiThe predicted sinking value and the horizontal movement value of the observation point during the ith iteration are respectively Wpi、UpiAnd calculating to obtain energy under a certain state by taking the minimum sum of squares of the differences between the predicted value and the observed value as a criterion:
Ei＝fi＝∑((Wpi-Wai)2+(Upi-Uai)2) (1)
the Hamilton amount without external force in the QA algorithm is: h0＝Ei+1-Ei＝fi+1-fi；
S102, according to the QA algorithm principle, the main calculation flow of the probability integration method parameter inversion method based on QA is as follows:
(1) preparing data: giving a goaf space geometric characteristic parameter: coal seam thickness m, coal seam dip angle alpha, working face inclination azimuth angle theta, mining depth H, working face strike length D3Tendency to be long D1Coordinate (X) with the center point0，Y0) Initial value B)0＝[m,α,θ,H,D3,D1,X0,Y0]Determining the temperature and lateral field variation function:
(i.e. the temperature and lateral field decrease by the same amount at the same time), T represents the number of iterations, and the minimum temperature Tmin＝Γmin(ii) a Given the fluctuation range ± Δ B ═ Δ m, Δ α, Δ θ, Δ H, Δ D for each probability integration parameter3,ΔD1,ΔX0,ΔY0]The parameter maximum allowable step size and the internal cycle number M;
(2) calculating an objective function: according to the formula (1), obtaining a calculation formula for inverting the ith iteration of the objective function of the goaf space geometric characteristic parameter model by the probability integration method of fusing QA: f. ofi＝∑((Wpi-Wai)2+(Upi-Uai)2)；
(3) Inner loop iteration: randomly generating a random number rand (j) between (0,1), and calculating a parameter value B after the (i + 1) th iteration of each parameteri+1The calculation formula is Bi+1(j)＝Bi(j) (2, rand (j) -1), scale (j), (where j is 1: N, N is the number of parameters, and N is 8) to determine whether the parameters after the (i + 1) th iteration are within the parameter fluctuation range: if not, then take Bi+1(j)＝Bi(j) (ii) a Otherwise, after the iteration is finished, calculating the objective function f of the (i + 1) th iterationi+1And (4) proceeding to step;
(4) judging a sentence: calculating Δ f ═ fi+1-fi，
Due to the complexity of the relationships between particles, it can be considered as a constant C; if Δ f < 0, or Δ f > 0 and
selecting the parameter value of the (i + 1) th time to replace the parameter value of the ith time; otherwise, still selecting the ith parameter value; in addition, whether the internal cycle times M are met is judged, if not, the step (3) is carried out, otherwise, the step (5) is carried out;
(5) an outer loop statement: judging whether the precision requirement is met, if so, jumping out of the cycle; otherwise, judging whether the temperature T and the transverse field gamma are in an allowable range, if so, reducing the temperature and the transverse field, repeating the steps (2) to (4), otherwise, jumping out of the cycle, and outputting an optimal parameter solution.
Preferably, the process of constructing the QGA-based probability integral parametric inversion model in step S2 includes:
s201, quantum coding and generation of an initial population: according to the predicted parameters of the known underground working face probability integral method, determining the initial values and the constraint values of the geometrical parameters of the underground working face by combining the existing geological mining data, and carrying out binary coding by using a quantum coding method to generate an initial population;
s202, decoding and evaluating individual fitness of population: decoding the binary coding population by using a decoding formula in combination with the setting form of each parameter in the south of the model, calculating all individual fitness values in the population, and recording the optimal individual fitness value of the current population;
s203, judging whether a termination condition is met: in the model, error precision and iteration times in fitting are used as judgment conditions, and the optimal individual of the current population is decoded and output when the precision requirement is met or the maximum genetic algebra is reached, namely the optimal inversion parameter; otherwise, entering the step (4);
s204, updating the population by the quantum revolving door: taking the optimal individuals in the step S202 as an evolution target, comparing the binary codes of all the individuals of the parents with the binary codes of the optimal individuals of the current population, generating the qubit codes of the filial population by using the quantum revolving gate, and finally generating the binary codes of the filial population according to the qubit codes;
s205, repeating the steps S202 to S204, and performing iterative computation; jumping out of the loop when the requirement of the termination condition in the step S203 is met, and outputting an optimal probability integral inversion parameter;
wherein: the number of initial population set in the model is 100, and the maximum genetic algebra is 100.
Preferably, the illegal recognition model layer comprises a time domain recognition model, a space domain recognition model and an attribute domain recognition model of the geological object;
time domain identification model: the method comprises an address time scale unit, a time density unit, a time structure unit, a geological event unit, a geological state unit, a geological process unit and a temporal topology unit, wherein each geological state records a snapshot of a variable attribute part of the geological object at a certain moment, so that when the geological state changes, the change of the geological object can be used for determining the change of the geological object, and the process of illegal mining identification can be judged by using one data set as follows, namely:
in the formula (2), DxFor the length of the mine in the direction of the face, DyMining width along the face inclination direction, H being mining depth, T being mining time, data set gn(Dx,DYH, T) is data such as mining right boundary range, mining depth and the like,
a data set referring to illegal mining identification results; f refers to an expression of some algorithm on the argument in parentheses;
a spatial domain identification model: the underground mining area modeling method comprises a space structure unit, a space topology unit, a space direction unit and a space measurement unit, wherein in the underground mining process, the underground mining condition is reflected according to recorded surface subsidence data, so that the underground mining area is modeled, and whether the underground mining area exceeds the mining right range or not is judged;
attribute domain identification model: the geological process unit comprises a geological facility unit, a geological unit, a comprehensive geological body unit, a geological environment unit, a geological process unit, a stratigraphic rock body unit and other geological body units.
The invention has the beneficial effects that: the invention discloses a GIS (geographic information System) space-time data model for underground illegal mining identification, which is improved in the following aspects compared with the prior art:
the invention establishes a GIS (geographic information System) space-time data model facing underground illegal mining identification, and in the underground mining process of a mine, aiming at geological phenomena and dynamic processes induced by underground mining of the mine, the GIS data model supporting the dynamic expression of the geological space-time process is designed by combining the actual requirements of underground illegal mining real-time monitoring and simulating and describing the time-time change process of mining subsidence on the basis of analyzing and expressing the time-time change of mining subsidence, so that platform guarantee is provided for the identification and monitoring of subsequent illegal mining events of different types, and the GIS space-time data model has the advantages of strong practicability and capability of avoiding excessive mining of resources and real-time monitoring.
Drawings
FIG. 1 is a frame diagram of a GIS spatiotemporal data model oriented to underground illegal mining identification.
FIG. 2 is a block diagram of a geologic event multi-factor driven process model in accordance with the present invention.
FIG. 3 is a block diagram of a model of a surface deformation spatiotemporal process in accordance with the present invention.
FIG. 4 is a block diagram of a state representation of a geological object of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the following further describes the technical solution of the present invention with reference to the drawings and the embodiments.
Referring to the attached figures 1-4, the GIS spatio-temporal data model facing underground illegal mining identification comprises a geometric element model layer, a spatio-temporal process model layer, a spatio-temporal inversion model layer and an illegal identification model layer;
1. geometric element model layer: the geometric element model layer is the most basic part of spatial data integration and expansion model, and can abstract the whole geological geometric space into four spatial entity objects of points, lines, surfaces and bodies according to the geometric element expression requirements of the above-ground and underground models, the indoor models and the outdoor models, so that the geometric entity objects are geometrically expressed in space and form, support can be provided for data compatibility and bottom layer operation of related models, and a geometric element unified expression model is formed;
the model layer mainly utilizes a plurality of sensors or space-ground observation means to observe and measure natural geographic phenomena (external forms and surface characteristics of a bottom layer) in an area, forms dynamic space-time information and special attributes in the whole geological geometric space of the area, and sends the formed space-time information and special attributes to a space-time inversion model layer, wherein the space-ground observation means refers to radar SAR, optical remote sensing, unmanned aerial vehicles, GPS, leveling and the like;
the time-space information refers to dynamic time-space data in a geological time-space process, a geological time-space process value is in a time period, a certain geological object or a geological object set evolves along a time axis in a process, and the process is an event and a response event generated by the interaction of geological objects with multiple dimensions and multiple time granularities to change thematic attributes or spatial forms, so that the essence of the geological time-space process is the change process of the space and thematic attribute information of the geological object along a time sequence, for different degrees of surface deformation existing in a mine area, the occurrence of the surface time-space change means the change of the state of the geological object, the change is usually caused by geological related events, generally, the actions and events generated by the surface deformation information of the mine area can be divided into artificial events such as underground water extraction, industrial and mining excavation, surface water infiltration, and the like, Natural events such as geological structure activity, erosion, and the like;
the special attribute is the attribute of different geological event types, the geological event type refers to the constraint condition that geological events are generated by geological objects in the geological event type or the constraint condition that the geological events drive the ground object to change, in a geological space-time data model, the geological event type needs to be registered in the corresponding geological object according to different purposes, and the geological event type registration is divided into two types, one type is used for determining which type of geological events can be generated by the geological objects, and the other type is used for judging which type of geological events can drive the geological objects to generate space-time change;
the method is characterized in that the geological entity object is geometrically expressed in space and form, support can be provided for data compatibility and bottom layer operation of related models, and the process of forming the geometric element unified expression model comprises the following steps:
spatio-temporal process model layer: the space-time process model layer is mainly composed of a dynamic GIS space-time data model and is a core component of an extended model, and on the basis of the dynamic GIS space-time data model, a geological event multi-factor driving model is combined to integrate the space-time process, a geographic object, an event type, a state and observation related elements into one space-time data model to form a space-time process unified expression model;
the model layer comprises a settlement data observation module, an event library pool and a spatio-temporal layer; the settlement data observation module is used for dynamically recording ground surface settlement data in the underground mining process to obtain dynamic variable input of different geological objects, forming different event libraries according to ground surface settlement conditions, and sending events to different agent objects according to event types in the event libraries to form a time-space map layer containing a plurality of agent objects (mainly responsible for processing specific events generated by a geological event multi-factor driving model object, not only receiving corresponding response events of a general geological object, but also processing output of corresponding results in the geological simulation process);
the spatio-temporal layer creates different geological events according to different proxy objects, forms an event pool containing multiple data, and establishes a geological event multi-factor driving model according to the event pool;
integrating data of relevant elements such as the spatio-temporal process, geographic objects, events, event types, states, observation and the like processed by the spatio-temporal process model layer into a spatio-temporal data model to form a spatio-temporal process unified expression model, and sending the spatio-temporal process unified expression model into the spatio-temporal inversion model layer;
wherein: the agent object is mainly responsible for processing specific events generated by the geological event multi-factor driven model object, not only can receive corresponding response events of a general geological object, but also can process output of corresponding results in a geological simulation process; the map layer is the most basic element in the map, namely data is divided into a plurality of files according to certain attributes, each file data is enabled to have a set object class with common structure and characteristics, and the map layer class is loaded into a geological space-time process and can be used for responding to geological events; the event library is stored with a plurality of different geological event types, wherein the geological event types comprise constraint conditions for geological objects to generate geological events of the type or constraint conditions for driving the geological events to drive the geological events to change ground objects; in the geological space-time data model, geological event types need to be registered in corresponding geological objects according to different purposes, a plurality of different geological objects are formed, and a geological event multi-factor driving model is formed.
Model layer of space-time inversion: the space-time inversion model layer is based on a geometric element unified expression model and a space-time process unified expression model, a multi-space-time and multi-scale multi-dimensional geological space-time model supporting geological space-time objects is constructed according to the internal requirements of underground illegal mining identification, on the basis, a mining subsidence mechanism and a probability integration method are utilized, a Quantum Genetic Algorithm (QGA) and a quantum annealing method (QA) are introduced at the same time, and an underground mining inversion model for inverting new underground mining events and underground goaf space positions and ranges is constructed;
the geometric element unified expression model adopts a mining subsidence mechanism and a probability integration method, a Quantum Genetic Algorithm (QGA) and a quantum annealing method (QA) to construct an underground mining inversion model:
s1, a probability integral parameter inversion model establishing process based on QA, wherein the establishing process comprises the following specific steps:
s101, setting the actually measured subsidence and horizontal movement of the earth surface movement observation point above the working surface as W respectivelyai、UaiThe predicted sinking value and the horizontal movement value of the observation point during the ith iteration are respectively Wpi、UpiAnd calculating to obtain energy under a certain state by taking the minimum sum of squares of the differences between the predicted value and the observed value as a criterion:
Ei＝fi＝∑((Wpi-Wai)2+(Upi-Uai)2) (1)
the Hamilton amount without external force in the QA algorithm is: h0＝Ei+1-Ei＝fi+1-fi；
S102, according to the QA algorithm principle, the main calculation flow of the probability integration method parameter inversion method based on QA is as follows:
(1) preparing data: giving a goaf space geometric characteristic parameter: thickness m, dip of coal seamAngle alpha, working face inclination azimuth theta, mining depth H, working face strike length D3Tendency to be long D1Coordinate (X) with the center point0，Y0) Initial value B)0＝[m,α,θ,H,D3,D1,X0,Y0]Determining the temperature and lateral field variation function:
(i.e. the temperature and lateral field decrease by the same amount at the same time), T represents the number of iterations, and the minimum temperature Tmin＝Γmin(ii) a Given the fluctuation range ± Δ B ═ Δ m, Δ α, Δ θ, Δ H, Δ D for each probability integration parameter3,ΔD1,ΔX0,ΔY0]The parameter maximum allowable step size and the internal cycle number M;
(2) calculating an objective function: according to the formula (1), obtaining a calculation formula for inverting the ith iteration of the objective function of the goaf space geometric characteristic parameter model by the probability integration method of fusing QA: f. ofi＝∑((Wpi-Wai)2+(Upi-Uai)2)；
(3) Inner loop iteration: randomly generating a random number rand (j) between (0,1), and calculating a parameter value B after the (i + 1) th iteration of each parameteri+1The calculation formula is Bi+1(j)＝Bi(j) (2, rand (j) -1), scale (j), (where j is 1: N, N is the number of parameters, and N is 8) to determine whether the parameters after the (i + 1) th iteration are within the parameter fluctuation range: if not, then take Bi+1(j)＝Bi(j) (ii) a Otherwise, after the iteration is finished, calculating the objective function f of the (i + 1) th iterationi+1And (4) proceeding to step;
(4) judging a sentence: calculating Δ f ═ fi+1-fi，
Due to the complexity of the relationships between particles, it can be considered as a constant C; if Δ f < 0, or Δ f > 0 and
the parameter value of the (i + 1) th time is selected to replace the parameter of the (i) th timeA numerical value; otherwise, still selecting the ith parameter value; in addition, whether the internal cycle times M are met is judged, if not, the step (3) is carried out, otherwise, the step (5) is carried out;
(5) an outer loop statement: judging whether the precision requirement is met, if so, jumping out of the cycle; otherwise, judging whether the temperature T and the transverse field gamma are in an allowable range, if so, reducing the temperature and the transverse field, repeating the steps (2) to (4), otherwise, jumping out of the circulation, and outputting an optimal parameter solution;
s2, a construction process of a probability integral parameter inversion model based on the QGA, wherein the specific construction process comprises the following steps:
s201, quantum coding and generation of an initial population: according to the predicted parameters of the known underground working face probability integral method, determining the initial values and the constraint values of the geometrical parameters of the underground working face by combining the existing geological mining data, and carrying out binary coding by using a quantum coding method to generate an initial population;
s202, decoding and evaluating individual fitness of population: decoding the binary coding population by using a decoding formula in combination with the setting form of each parameter in the south of the model, calculating all individual fitness values in the population, and recording the optimal individual fitness value of the current population;
s203, judging whether a termination condition is met: in the model, error precision and iteration times in fitting are used as judgment conditions, and the optimal individual of the current population is decoded and output when the precision requirement is met or the maximum genetic algebra is reached, namely the optimal inversion parameter; otherwise, entering the step (4);
s204, updating the population by the quantum revolving door: taking the optimal individuals in the step S202 as an evolution target, comparing the binary codes of all the individuals of the parents with the binary codes of the optimal individuals of the current population, generating the qubit codes of the filial population by using the quantum revolving gate, and finally generating the binary codes of the filial population according to the qubit codes;
s205, repeating the steps S202 to S204, and performing iterative computation; jumping out of the loop when the requirement of the termination condition in the step S203 is met, and outputting an optimal probability integral inversion parameter;
wherein: the number of initial population set in the model is 100, and the maximum genetic algebra is 100.
The space-time process unified expression model utilizes the space-time geological object and the LOD space-time object to establish a multi-dimensional geological space-time model.
Illegal recognition model layer: the illegal recognition model layer is used for analyzing the multidimensional geological space-time model and the underground mining inversion model through the semantics of geological objects in a time domain, a space domain and an attribute domain, expressing the change of the space characteristics and the special attribute characteristics of the geological objects along a time axis, then performing space-time analysis on the related geological objects at different moments, and comprehensively considering or utilizing special monitoring data and underground data to establish a discrimination model for legal mining and illegal mining.
The discrimination model comprises a time domain identification model, a space domain identification model and an attribute domain identification model of the geological object;
time domain identification model: the method comprises an address time scale unit, a time density unit, a time structure unit, a geological event unit, a geological state unit, a geological process unit and a temporal topology unit, wherein each geological state records a snapshot of a variable attribute part of the geological object at a certain moment, so that when the geological state changes, the change of the geological object can be used for determining the change of the geological object, and the process of illegal mining identification can be judged by using one data set as follows, namely:
in the formula (2), DxFor the length of the mine in the direction of the face, DyMining width along the face inclination direction, H being mining depth, T being mining time, data set gn(Dx,DYH, T) is data such as mining right boundary range, mining depth and the like,
a data set referring to illegal mining identification results; f refers to an expression of some algorithm on the argument in parentheses;
a spatial domain identification model: the underground mining area modeling method comprises a space structure unit, a space topology unit, a space direction unit and a space measurement unit, wherein in the underground mining process, the underground mining condition is reflected according to recorded surface subsidence data, so that the underground mining area is modeled, and whether the underground mining area exceeds the mining right range or not is judged;
attribute domain identification model: the geological process unit comprises a geological facility unit, a geological unit, a comprehensive geological body unit, a geological environment unit, a geological process unit, a stratigraphic rock body unit and other geological body units.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. A GIS space-time data model facing underground illegal mining identification is characterized in that: the system comprises a geometric element model layer, a space-time process model layer, a space-time inversion model layer and an illegal recognition model layer;
the geometric element model layer is a basic part of spatial data integration and expansion model, can abstract the whole geological geometric space into four spatial entity objects of points, lines, surfaces and bodies according to the geometric element expression requirements of the above-ground and underground models, the indoor models and the outdoor models, simultaneously carries out geometric expression on the geological entity objects in space and form, and can also provide support for data compatibility and bottom layer operation of related models to form a geometric element unified expression model;
the space-time process model layer is mainly composed of a dynamic GIS space-time data model and is a core component of an extended model, and on the basis of the dynamic GIS space-time data model, a geological event multi-factor driving model is combined to integrate the space-time process, a geographic object, an event type, a state and observation related elements into one space-time data model to form a space-time process unified expression model;
the space-time inversion model layer is based on a geometric element unified expression model and a space-time process unified expression model, a multi-space-time and multi-scale multi-dimensional geological space-time model supporting geological space-time objects is constructed according to the internal requirements of underground illegal mining identification, and on the basis, an underground mining inversion model for inverting new underground mining events and underground goaf space positions and ranges is constructed by utilizing a mining subsidence mechanism and a probability integration method and introducing a quantum genetic algorithm and a quantum annealing method at the same time;
the illegal recognition model layer is used for analyzing the multi-dimensional geological space-time model and the underground mining inversion model, expressing the change of the spatial characteristics and the thematic attribute characteristics of the geological objects along the time axis, then performing space-time analysis on the related geological objects at different moments, and comprehensively considering or utilizing thematic monitoring data and underground data to establish a discrimination model between legal mining and illegal mining.
2. The GIS spatiotemporal data model for underground illegal mining identification according to claim 1, characterized in that: the geometric element model layer can observe and measure natural geographic phenomena in the region by utilizing a plurality of sensors or space-sky-ground observation means, form dynamic space-time information and special attributes in the whole geological geometric space of the region, and send the formed space-time information and special attributes to the space-time inversion model layer;
wherein: the air-space-ground observation means refer to radar SAR, optical remote sensing, unmanned aerial vehicles, GPS and leveling means.
3. The GIS spatiotemporal data model for underground illegal mining identification according to claim 1, characterized in that: the space-time process model layer comprises a settlement data observation module, an event library pool and a space-time layer;
the settlement data observation module is used for dynamically recording ground surface settlement data in the underground mining process to obtain dynamic variable input of different geological objects, forming different event libraries according to ground surface settlement conditions, and sending events to different agent objects according to event types in the event libraries to form a time-space map layer containing a plurality of agent objects;
the spatio-temporal layer creates different geological events according to different proxy objects, forms an event pool containing multiple data, and establishes a geological event multi-factor driving model according to the event pool; integrating data of relevant elements such as the spatio-temporal process, geographic objects, events, event types, states, observation and the like processed by the spatio-temporal process model layer into a spatio-temporal data model to form a spatio-temporal process unified expression model, and sending the spatio-temporal process unified expression model into the spatio-temporal inversion model layer;
wherein: the agent object is mainly responsible for processing specific events generated by the geological event multi-factor driving model object, not only can receive corresponding response events of a general geological object, but also can process output of corresponding results in a geological simulation process; the map layer is the most basic element in the map, namely the data is divided into a plurality of files according to attributes, each file data has a set object class with common structure and characteristics, and the map layer class is loaded into a geological space-time process and can be used for responding to geological events; the event library stores a plurality of different geological event types, wherein the geological event types comprise constraint conditions for geological objects to generate geological events of the type or constraint conditions for geological events to drive the geological object to change; in the geological space-time data model, geological event types need to be registered in corresponding geological objects according to different purposes, a plurality of different geological objects are formed, and a geological event multi-factor driving model is formed.
4. The GIS spatiotemporal data model for underground illegal mining identification according to claim 1, characterized in that: the process of establishing the underground mining inversion model comprises
S1, establishing a probability integral parameter inversion model based on QA;
and S2, constructing a probability integral parameter inversion model based on the QGA.
5. The GIS spatiotemporal data model for underground illegal mining identification according to claim 4, characterized in that: the specific steps of establishing the QA-based probability integral parameter inversion model described in step S1 include:
s101, setting the actually measured subsidence and horizontal movement of the earth surface movement observation point above the working surface as W respectivelyai、UaiThe predicted sinking value and the horizontal movement value of the observation point during the ith iteration are respectively Wpi、UpiAnd calculating to obtain energy under a certain state by taking the minimum sum of squares of the differences between the predicted value and the observed value as a criterion:
Ei＝fi＝∑((Wpi-Wai)2+(Upi-Uai)2) (1)
the Hamilton amount without external force in the QA algorithm is: h0＝Ei+1-Ei＝fi+1-fi；
S102, according to the QA algorithm principle, the main calculation flow of the probability integration method parameter inversion method based on QA is as follows:
(1) preparing data: giving a goaf space geometric characteristic parameter: coal seam thickness m, coal seam dip angle alpha, working face inclination azimuth angle theta, mining depth H, working face strike length D3Tendency to be long D1Coordinate (X) with the center point0，Y0) Initial value B)0＝[m,α,θ,H,D3,D1,X0,Y0]Determining the temperature and lateral field variation function:
(i.e. the temperature and lateral field decrease by the same amount at the same time), T represents the number of iterations, and the minimum temperature Tmin＝Γmin(ii) a Given the fluctuation range ± Δ B ═ Δ m, Δ α, Δ θ, Δ H, Δ D for each probability integration parameter3,ΔD1,ΔX0,ΔY0]The parameter maximum allowable step size and the internal cycle number M;
(2) calculating an objective function: obtaining a probability integration method for fusing QA to invert the goaf space according to a formula (1)The calculation formula of the ith iteration of the geometric characteristic parameter model target function is as follows: f. ofi＝∑((Wpi-Wai)2+(Upi-Uai)2)；
(3) Inner loop iteration: randomly generating a random number rand (j) between (0,1), and calculating a parameter value B after the (i + 1) th iteration of each parameteri+1The calculation formula is Bi+1(j)＝Bi(j) (2, rand (j) -1), scale (j), (where j is 1: N, N is the number of parameters, and N is 8) to determine whether the parameters after the (i + 1) th iteration are within the parameter fluctuation range: if not, then take Bi+1(j)＝Bi(j) (ii) a Otherwise, after the iteration is finished, calculating the objective function f of the (i + 1) th iterationi+1And (4) proceeding to step;
(4) judging a sentence: calculating Δ f ═ fi+1-fi，
Due to the complexity of the relationships between particles, it can be considered as a constant C; if Δ f < 0, or Δ f > 0 and
selecting the parameter value of the (i + 1) th time to replace the parameter value of the ith time; otherwise, still selecting the ith parameter value; in addition, whether the internal cycle times M are met is judged, if not, the step (3) is carried out, otherwise, the step (5) is carried out;
(5) an outer loop statement: judging whether the precision requirement is met, if so, jumping out of the cycle; otherwise, judging whether the temperature T and the transverse field gamma are in an allowable range, if so, reducing the temperature and the transverse field, repeating the steps (2) to (4), otherwise, jumping out of the cycle, and outputting an optimal parameter solution.
6. The GIS spatiotemporal data model for underground illegal mining identification according to claim 4, characterized in that: the construction process of the QGA-based probability integral parameter inversion model in step S2 includes:
s201, quantum coding and generation of an initial population: according to the predicted parameters of the known underground working face probability integral method, determining the initial values and the constraint values of the geometrical parameters of the underground working face by combining the existing geological mining data, and carrying out binary coding by using a quantum coding method to generate an initial population;
s202, decoding and evaluating individual fitness of population: decoding the binary coding population by using a decoding formula in combination with the setting form of each parameter in the south of the model, calculating all individual fitness values in the population, and recording the optimal individual fitness value of the current population;
s203, judging whether a termination condition is met: in the model, error precision and iteration times in fitting are used as judgment conditions, and the optimal individual of the current population is decoded and output when the precision requirement is met or the maximum genetic algebra is reached, namely the optimal inversion parameter; otherwise, entering the step (4);
s204, updating the population by the quantum revolving door: taking the optimal individuals in the step S202 as an evolution target, comparing the binary codes of all the individuals of the parents with the binary codes of the optimal individuals of the current population, generating the qubit codes of the filial population by using the quantum revolving gate, and finally generating the binary codes of the filial population according to the qubit codes;
s205, repeating the steps S202 to S204, and performing iterative computation; jumping out of the loop when the requirement of the termination condition in the step S203 is met, and outputting an optimal probability integral inversion parameter;
wherein: the number of initial population set in the model is 100, and the maximum genetic algebra is 100.
7. The GIS spatiotemporal data model for underground illegal mining identification according to claim 1, characterized in that:
the illegal recognition model layer comprises a time domain recognition model, a space domain recognition model and an attribute domain recognition model of the geological object;
time domain identification model: the method comprises an address time scale unit, a time density unit, a time structure unit, a geological event unit, a geological state unit, a geological process unit and a temporal topology unit, wherein each geological state records a snapshot of a variable attribute part of the geological object at a certain moment, so that when the geological state changes, the change of the geological object can be used for determining the change of the geological object, and the process of illegal mining identification can be judged by using one data set as follows, namely:
in the formula (2), DxFor the length of the mine in the direction of the face, DyMining width along the face inclination direction, H being mining depth, T being mining time, data set gn(Dx,DYH, T) is data such as mining right boundary range, mining depth and the like,
a data set referring to illegal mining identification results; f refers to an expression of some algorithm on the argument in parentheses;
a spatial domain identification model: the underground mining area modeling method comprises a space structure unit, a space topology unit, a space direction unit and a space measurement unit, wherein in the underground mining process, the underground mining condition is reflected according to recorded surface subsidence data, so that the underground mining area is modeled, and whether the underground mining area exceeds the mining right range or not is judged;
attribute domain identification model: the geological process unit comprises a geological facility unit, a geological unit, a comprehensive geological body unit, a geological environment unit, a geological process unit, a stratigraphic rock body unit and other geological body units.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111156453.XA CN113987095A (en) | 2021-09-30 | 2021-09-30 | GIS (geographic information System) space-time data model for underground illegal mining identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111156453.XA CN113987095A (en) | 2021-09-30 | 2021-09-30 | GIS (geographic information System) space-time data model for underground illegal mining identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113987095A true CN113987095A (en) | 2022-01-28 |
Family
ID=79737346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111156453.XA Pending CN113987095A (en) | 2021-09-30 | 2021-09-30 | GIS (geographic information System) space-time data model for underground illegal mining identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113987095A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115795774A (en) * | 2022-05-30 | 2023-03-14 | 中核第四研究设计工程有限公司 | Uranium resource dynamic variation calculating and displaying method based on space-time model |
-
2021
- 2021-09-30 CN CN202111156453.XA patent/CN113987095A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115795774A (en) * | 2022-05-30 | 2023-03-14 | 中核第四研究设计工程有限公司 | Uranium resource dynamic variation calculating and displaying method based on space-time model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| USRE49507E1 (en) | Faulted geological structures having unconformities | |
| CA2985743C (en) | Geologic stratigraphy via implicit and jump functions | |
| Eshkalak et al. | Geomechanical properties of unconventional shale reservoirs | |
| EP3371629B1 (en) | Representing structural uncertainty in a mesh representing a geological environment | |
| Vardakos et al. | Parameter identification in numerical modeling of tunneling using the Differential Evolution Genetic Algorithm (DEGA) | |
| US10571601B2 (en) | Geologic fault representation for flow simulation | |
| EP2629123A2 (en) | Simulation model optimization | |
| US20130317798A1 (en) | Method and system for field planning | |
| US11249208B2 (en) | Geologic structural model generation | |
| CN108842821B (en) | Calculation method for reasonable buried depth of submarine tunnel constructed by drilling and blasting method | |
| WO2022078514A1 (en) | Three-dimensional speed geological modeling method capable of random distribution of structures and wave speeds | |
| CN112904419A (en) | Microseism imaging method and terminal equipment | |
| CN113987095A (en) | GIS (geographic information System) space-time data model for underground illegal mining identification | |
| CN115293316A (en) | Prediction method for deep-buried thick coal seam water flowing fractured zone based on SSA-ELMAN | |
| Guo et al. | Parameter inversion of probability integral method based on improved crow search algorithm | |
| WO2023130074A1 (en) | Geologic modeling framework | |
| Wang et al. | Multi-source data integration and multi-scale modeling framework for progressive prediction of complex geological interfaces in tunneling | |
| CN112292714B (en) | Grid partition based on fault radiation | |
| Zeng et al. | Local coupled Markov chain model for simulating varied stratigraphy | |
| Bescoby et al. | Enhanced interpretation of magnetic survey data using artificial neural networks: a case study from Butrint, southern Albania | |
| Wang et al. | Development of a Hybrid Method to Predict the Slope Surface Deformation Utilizing the Time Series and GA-Elman Models | |
| Nikakhtar et al. | Performance Comparison of Particle Swarm Optimization and Genetic Algorithm for Back-analysis of Soil Layer Geotechnical Parameters | |
| Hajian et al. | Prior applications of neural networks in geophysics | |
| CN108897061B (en) | Method, device and system for determining sand body proportion of reservoir | |
| CN117852416A (en) | Multimode grouting precontrolled analysis method and system based on digital geological model |
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 |