CN113077082A - Mining area mining subsidence prediction method based on improved crow search algorithm - Google Patents
Mining area mining subsidence prediction method based on improved crow search algorithm Download PDFInfo
- Publication number
- CN113077082A CN113077082A CN202110323901.4A CN202110323901A CN113077082A CN 113077082 A CN113077082 A CN 113077082A CN 202110323901 A CN202110323901 A CN 202110323901A CN 113077082 A CN113077082 A CN 113077082A
- Authority
- CN
- China
- Prior art keywords
- crow
- search algorithm
- strategy
- improved
- value
- 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
- 238000010845 search algorithm Methods 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000005065 mining Methods 0.000 title claims abstract description 45
- 238000004364 calculation method Methods 0.000 claims abstract description 9
- 230000006872 improvement Effects 0.000 claims abstract description 5
- 230000008569 process Effects 0.000 claims description 14
- 241001137251 Corvidae Species 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 12
- 235000013305 food Nutrition 0.000 claims description 8
- 238000006073 displacement reaction Methods 0.000 claims description 7
- 230000008447 perception Effects 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 4
- 238000009827 uniform distribution Methods 0.000 claims description 3
- 235000009967 Erodium cicutarium Nutrition 0.000 claims 2
- 230000010354 integration Effects 0.000 abstract description 14
- 238000004422 calculation algorithm Methods 0.000 description 19
- 238000004088 simulation Methods 0.000 description 9
- 238000005457 optimization Methods 0.000 description 8
- 238000000050 ionisation spectroscopy Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 239000003245 coal Substances 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 206010040954 Skin wrinkling Diseases 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000019637 foraging behavior Effects 0.000 description 1
- 230000000246 remedial effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Molecular Biology (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Physics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a mining area mining subsidence prediction method based on an improved crow search algorithm, which comprises the following steps of: s1, introducing a Levy flight strategy, a leader strategy and a replacement crow strategy into the crow search algorithm for improvement based on the crow search algorithm to obtain an improved crow search algorithm; and S2, introducing the improved crow search algorithm into probability integral parameter inversion to establish a probability integral parameter inversion model based on the improved crow search algorithm, and performing settlement prediction calculation through the model to obtain a settlement probability predicted value. According to the mining area mining subsidence prediction method based on the improved crow search algorithm, on the basis of the crow search algorithm, a Levy flight strategy, a leader strategy and a replacement crow strategy are introduced, a probability integration method parameter inversion model based on the improved crow search algorithm is constructed, the probability integration method parameter inversion model is superior to a CAS in the aspects of relative errors of control parameters and errors in fitting, and the probability integration method has a certain random error resistance.
Description
Technical Field
The invention belongs to the technical field of mining subsidence prediction in a mining area, and particularly relates to a mining subsidence prediction method based on an improved crow search algorithm, wherein the mining subsidence prediction method is based on an improved crow search algorithm and is used for inverting probability integral parameters.
Background
At present, coal is the main energy source in China. Large-scale mining of coal resources can result in large-scale ground subsidence and disastrous effects on the natural environment. Surface subsidence caused by underground mining activities is a serious engineering, economic and environmental problem. In a broad sense, surface subsidence is the inevitable consequence of underground mining activities, reflecting the state of motion of the mine. Ground subsidence has a serious impact on ground structure, service and communications. In the development of construction sites in ground subsidence areas, extensive remedial measures or special building designs are often required. Therefore, mining subsidence prediction has become the focus of attention of scholars at home and abroad.
In the 50 s of the 20 th century, the Polish student J.Litteringzyn (J.Litwiniszyn) introduced the random medium theory into rock formation mobility research, and then the Chinese student Liubao et al continued to develop the theory into probability integration. In China, the probability integration method is one of the most mature and widely applied settlement prediction methods. Parametric errors and model errors are the main sources of error in probability integration applications. The key for improving the prediction precision of the probability integration method is to reduce model errors and parameter errors. The model error mainly comes from the basic assumption of the method and is difficult to improve, so the meaning of reducing the parameter error is more obvious. Accurate mining subsidence prediction should be based on obtaining accurate parameters. The prediction parameter inversion method of the probability integration method roughly goes through the processes of a linear approximation method, a step acceleration method, an intelligent algorithm and an optimization algorithm. The linear approximation parameter method linearizes probability integral by using the idea of linear approximation, and then calculates parameters according to the least square principle. The initial values are orthogonally designed, and then the real values of the parameters are quickly approximated in a small amount of experiments by utilizing a linear approximation parameter method. However, the method is complicated in calculation process and difficult to popularize. The GE applies a model vector method (step acceleration method) to obtain prediction parameters of mining subsidence. The method solves the problems of acquiring parameters by utilizing the actual measurement data of the mining of the working face with any shape and utilizing the dynamic measurement data. The solving process of the step-size acceleration method can be trapped in a local extreme value trap, and the local optimal solution can be mistaken as the global optimal solution. A probability integral parameter inversion model based on a genetic algorithm is constructed, and certain accuracy, reliability and stability are achieved in parameter calculation. The particle swarm optimization algorithm is proposed to invert the parameters of the probability integration method, and the method has the advantages of high search speed, high efficiency, simple algorithm and the like.
Through analysis of research results, it can be found that when the search range of the algorithm is not sufficient, the genetic algorithm and the particle swarm optimization algorithm are both in local optimization to a certain extent, so that the algorithm is early and converged.
Disclosure of Invention
The invention aims to solve the problems and provide a mining area mining subsidence prediction method based on an improved crow search algorithm.
The invention realizes the purpose through the following technical scheme:
a mining area mining subsidence prediction method based on an improved crow search algorithm comprises the following steps:
s1, introducing a Levy flight strategy, a leader strategy and a replacement crow strategy into the crow search algorithm for improvement based on the crow search algorithm to obtain an improved crow search algorithm;
s2, introducing the improved crow search algorithm into probability integral parameter inversion to establish a probability integral parameter inversion model based on the improved crow search algorithm, and performing settlement prediction calculation through the model to obtain a settlement probability predicted value;
the specific process of introducing the improved crow search algorithm into the probability integral parameter inversion is as follows:
1) setting the maximum number of iterations tmaxPerception probability AP, flight radius riGiving a center value X of a probability integral parameter0=[q,tanβ,b,θ,s1,s2,s3,s4]And the fluctuation range DeltaX ═ Deltaq, Deltatanβ,Δb,Δs1,Δs2,Δs3,Δs4]Generating an initial crow populationAnd recording the initial crow group position as the memory position M of the crow groupi;
2) Setting a fitness function for judging whether the crow position is good or bad:
wherein T is the number of observation stations, Wj、UjAre each XiAs the expected sinking and horizontal displacement values of the probability integral parameters at observation station j,respectively an actually measured sinking value and an actually measured horizontal displacement value on an observation station j;
3) updating the positions of the crows, and searching each crow in the population according to a crow searching formula after introducing a Levy flight strategy and a leader strategy;
4) generating a substitute crow according to a crow search formula after introducing a substitute crow strategy, replacing the crow position beyond a solution space, and updating the crow position;
5) calculating the fitness of the updated crow memory position, and updating the memory position of the crow according to a crow memory position updating formula;
6) and repeating the steps 3) to 5) until the maximum iteration times are reached or the precision condition is met, and outputting the fitness function optimal value in the crow memory value as a result.
As a further optimization scheme of the present invention, the crow search algorithm specifically comprises: assuming that N crows fly in a defined D-dimension search range, the position of food is searched, and a better fitness function value f (X) of the position of the food is foundi,t) Low, where the position of crow i in the t iteration is:
wherein i ∈ [1, N ]],t∈[1,tmax],tmaxRepresenting the maximum number of iterations;
the best position found by the t iteration of the crow i, namely the memory position of the crow is as follows:
in the searching process, the crow has two different modes to update the position of the crow, the crow i randomly follows the crow j, the memory position of the crow j is tried to be found, the crow j has certain perception probability to find that the crow j is tracked, if the crow j is not found, the memory position of the crow j is obtained by the crow i, the state is a first state, if the crow j is found, the crow i is taken to a random position, the state is a second state, and the expression formula of the searching process is as follows:
wherein the flight radius riObeying the uniform distribution between 0 and 1, wherein AP represents the perception probability of the crow j, and pl is the flight distance;
after the search is finished, the fitness of the new position of the crow i is compared with the fitness of the memory value of the crow i, the memory position of the crow is updated, and the expression formula is as follows:
and after the iteration is finished, taking the crow memory value with the minimum fitness function value as the optimal parameter solution for output.
As a further optimization scheme of the invention, a Levy flight strategy introduced when improving based on a crow search algorithm is specifically as follows:
σv=1
wherein the value of beta is 1.5;
the crow search formula introduced in the Levy flight strategy is as follows:
as a further optimization scheme of the invention, a leader strategy introduced when improving based on a crow search algorithm is specifically as follows: randomly selecting N/2 crows, and taking the memory value of the crows with the optimal fitness as the position M of the leaderleader,tWhen the execution state is one, selecting a leader position for tracking;
the crow search formula after introducing the Levy flight strategy and the leader strategy is as follows:
as a further optimization scheme of the invention, a replacement crow strategy introduced when improving based on a crow search algorithm is specifically as follows: when a crow position outside a solution space range is generated in the searching process, a new crow position is randomly generated in the solution space to replace the position to participate in the next iterative calculation;
the crow search formula after introducing the replacement crow strategy is as follows:
the invention has the beneficial effects that:
1) on the basis of a crow search algorithm, a Levy flight strategy, a leader strategy and a replacement crow strategy are introduced, a probability integration method parameter inversion model based on an improved crow search algorithm is constructed, a simulation test is designed to discuss the inversion capability of the model, and the results of the simulation test show that: relative errors of ICAS inversion parameters q, tan beta, b and theta are respectively 0.12%, 0.39%, 0.54% and 0.15%, relative errors of inflection point offset distance are not more than 2.8% at most, and comparative analysis proves that ICAS is superior to CAS in the aspects of relative errors of control parameters and errors in fitting; (ii) a
2) The invention designs an observed value with random errors to verify the anti-interference capability of the model, and the result shows that: under the interference of random errors, although the relative errors of the parameter fitting results and the errors in fitting are increased slightly, the accuracy and precision are still kept at a higher level, which shows that the parameter inversion model introduced based on the improved crow search algorithm has certain random error resistance.
Drawings
FIG. 1 is a flow chart of the improved crow search algorithm inverting probability integral parameters of the present invention;
FIG. 2 is a Levy flight trajectory diagram of the invention;
FIG. 3 is a diagram of a simulation experiment working surface of the present invention;
FIG. 4 is a diagram of the absolute error analysis data of ICAS and CAS predicted values of the present invention.
Detailed Description
The present application will now be described in further detail with reference to the drawings, it should be noted that the following detailed description is given for illustrative purposes only and is not to be construed as limiting the scope of the present application, as those skilled in the art will be able to make numerous insubstantial modifications and adaptations to the present application based on the above disclosure.
Example 1
As shown in fig. 1-2, a mining area mining subsidence prediction method based on an improved crow search algorithm includes the following steps:
s1, introducing a Levy flight strategy, a leader strategy and a replacement crow strategy into the crow search algorithm for improvement based on the crow search algorithm to obtain an improved crow search algorithm;
s2, introducing the improved crow search algorithm into probability integral parameter inversion to establish a probability integral parameter inversion model based on the improved crow search algorithm, and performing settlement prediction calculation through the model to obtain a settlement probability predicted value;
the probability integration method is used for calculating the expected value of mining subsidence and the horizontal movement value of any point A (x, y) on the earth's surface according to the following formula:
wherein the content of the first and second substances,
W0=mq cosα
in the formula, D1And D3Respectively the inclined length and the strike length of a mining working face, m is the average mining thickness of the working face, q is a sinking coefficient, alpha is the inclination angle of the working face, tan beta is the main influence angle tangent, H, H1、H2Respectively including the mining depth at the main broken line position, the mining depth at the upper boundary and the mining depth at the lower boundary of the working face3Calculating the length, l, for the working face run3=D3-S3-S4,l1The length is calculated for the working face trend,wherein S is1、S2、S3、S4The inflection point offset distance of the rising mountain, the inflection point offset distance of the falling mountain, the inflection point offset distance of the open-cut eye and the inflection point offset distance of the stoping line are respectively.
Arbitrary point A (x, y) of the earth's surface(angular value of positive counterclockwise of x-axis to specified direction) horizontal displacement in direction:
wherein r is the major influence radius, b is the horizontal shift coefficient,to sink W (x, y) inThe directional derivative of direction, i.e.
The method is characterized in that a crow searching algorithm proposed by simulating foraging behavior of crow is assumed to have four points, wherein one point is that the crow lives in a social form, the other point is that the crow hides own food and remembers the position of the crow, the third point is that the crow tracks other crow and tries to find the food position of other crow, and the fourth point is that the crow senses that the crow is tracked by a certain probability and brings a tracker to a random position.
The crow search algorithm based on the four-point hypothesis specifically comprises the following steps: assuming that N crows fly in a defined D-dimension search range, the position of food is searched, and a better fitness function value f (X) of the position of the food is foundi,t) Low, where the position of crow i in the t iteration is:
wherein i ∈ [1, N ]],t∈[1,tmax],tmaxRepresenting the maximum number of iterations;
the best position found by the t iteration of the crow i, namely the memory position of the crow is as follows:
in the searching process, the crow has two different modes to update the position of the crow, the crow i randomly follows the crow j, the memory position of the crow j is tried to be found, the crow j has certain perception probability to find that the crow j is tracked, if the crow j is not found, the memory position of the crow j is obtained by the crow i, the state is a first state, if the crow j is found, the crow i is taken to a random position, the state is a second state, and the expression formula of the searching process is as follows:
wherein the flight radius riObeying the uniform distribution between 0 and 1, wherein AP represents the perception probability of the crow j, and pl is the flight distance;
after the search is finished, the fitness of the new position of the crow i is compared with the fitness of the memory value of the crow i, the memory position of the crow is updated, and the expression formula is as follows:
and after the iteration is finished, taking the crow memory value with the minimum fitness function value as the optimal parameter solution for output.
The Levy flight strategy introduced when improving based on the crow search algorithm is specifically as follows:
σv=1
wherein the value of beta is 1.5;
the crow search formula introduced in the Levy flight strategy is as follows:
the leader strategy introduced when improving based on the crow search algorithm is specifically as follows: randomly selecting N/2 crows, and taking the memory value of the crows with the optimal fitness as the position M of the leaderleader,tWhen the execution state is one, selecting a leader position for tracking;
the crow search formula after introducing the Levy flight strategy and the leader strategy is as follows:
the replacement crow strategy introduced when improving based on the crow search algorithm is specifically as follows: when a crow position outside a solution space range is generated in the searching process, a new crow position is randomly generated in the solution space to replace the position to participate in the next iterative calculation;
the crow search formula after introducing the replacement crow strategy is as follows:
when the improved crow search algorithm is introduced into the probability integral parameter inversion, the method specifically comprises the following steps:
1) setting the maximum number of iterations tmaxPerception probability AP, flight radius riGiving a center value X of a probability integral parameter0=[q,tanβ,b,θ,s1,s2,s3,s4]And a fluctuation range Δ X ═ Δ q, Δ tan β, Δ b, Δ s1,Δs2,Δs3,Δs4]Generating an initial crow populationAnd recording the initial crow group position as the memory position M of the crow groupi;
2) Setting a fitness function for judging whether the crow position is good or bad:
wherein T is the number of observation stations, Wj、UjAre each XiAs the expected sinking and horizontal displacement values of the probability integral parameters at observation station j,respectively an actually measured sinking value and an actually measured horizontal displacement value on an observation station j;
3) updating the positions of the crows, and searching each crow in the population according to a crow searching formula after introducing a Levy flight strategy and a leader strategy;
4) generating a substitute crow according to a crow search formula after introducing a substitute crow strategy, replacing the crow position beyond a solution space, and updating the crow position;
5) calculating the fitness of the updated crow memory position, and updating the memory position of the crow according to a crow memory position updating formula;
6) and repeating the steps 3) to 5) until the maximum iteration times are reached or the precision condition is met, and outputting the fitness function optimal value in the crow memory value as a result.
Experimental example 1
In order to verify the feasibility and the inversion accuracy of the improved crow algorithm and verify the feasibility and the inversion accuracy of the improved crow algorithm, a simulation experiment is designed, and the working surface of the simulation experiment is established as follows: rectangular working face trend length D3800m, inclined mining length D1The average mining thickness m of the coal seam is 3.0m, the dip angle alpha of the coal seam is 5 degrees, the average mining depth H is 400m, a roof is managed by adopting a caving method, and monitoring points (E1-E51) are arranged on a main section of the strike at intervals of 30m in a simulated mode; monitoring points (N52-N92) are arranged on the inclined main section at intervals of 30m simulation. The prediction parameters of the probability integration method are respectively as follows: the subsidence coefficient q is 0.8, the horizontal movement coefficient b is 0.3, the main influence tangent tan β is 2.0, the mining influence propagation angle θ is 87 °, the inflection offset S1 is S2, S3, S4 is 0.1H.
The simulated work surface is shown in figure 3.
And generating a simulated sinking observation value and a simulated horizontal movement value by using the set probability integral parameters, respectively inverting the probability integral parameters by using an original crow searching algorithm and an improved crow searching algorithm, and comparing the relative error and the medium error of the inversion result. Setting the size N of the crow population as 100, the maximum iteration times as 100, and the flight radius riThe perception probabilities AP are 0.1(CAS) and 0.5(ICAS), respectively, at 1. The results of 10 separate runs are shown in Table 1.
TABLE 1 comparison analysis of stability and accuracy of original crow's feet search algorithm and improved crow's feet search algorithm
The experimental results in table 1 show that:
in the aspect of parameter relative errors, the relative error of the inversion parameters of the original crow searching algorithm is not more than 8.7%, the relative error of the inversion parameters of the improved crow searching algorithm is controlled within 2.8%, and the relative errors of the parameters inverted by the improved crow searching algorithm are all smaller than those of the original crow searching algorithm.
In the aspect of errors in parameter fitting, except that the errors in fitting of the horizontal movement coefficient b and the horizontal movement coefficient b are not large, the errors in fitting of other improved crow search algorithm inversion parameters are better than those of the original crow search algorithm, the errors in parameter fitting of the original crow search algorithm are not more than 6.12, and the errors in parameter fitting of the improved crow search algorithm are not more than 5.46, so that the improved crow search algorithm is high in parameter precision, and the obtained result is reliable. Simulation experiment results show that compared with the original crow search algorithm, the improved crow search algorithm has more accurate predicted parameters of the inversion probability integration method and higher accuracy of the inversion parameters.
The average value of the 10 times inversion results is used for calculating the expected sinking value and the expected horizontal movement value on each observation station, the absolute error between the expected value and the measured value of the two algorithms is compared, and as can be seen from fig. 4, the absolute error between the expected value and the measured value calculated by the probability integration parameters obtained by ICAS inversion is smaller, and the expected result is more accurate.
In order to research the random error resistance of the improved crow search algorithm probability integral inversion model, on the basis of 3.2 simulation experiments, accidental errors obeying normal distribution N (0,4) and N (0,10) are added to a simulation observation value respectively, 10 times of experiments are carried out in each case, and the experimental results are shown in table 2.
TABLE 2 improved crow search algorithm analysis of random error resistance
As can be seen from the data in table 2: after accidental errors of N (0,4) and N (0,10) which obey normal distribution are added, the maximum values of relative errors of the parameters respectively do not exceed 2.8% and 3.5%, and the maximum values of errors in parameter fitting respectively do not exceed 5.5 and 5.8, which shows that under the interference of random errors, although the errors of the parameter fitting results are increased, the precision and the accuracy are still kept at a higher level, and the ICAS parameter inversion model has certain random error resistance.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention.
Claims (5)
1. A mining area mining subsidence prediction method based on an improved crow search algorithm is characterized by comprising the following steps of:
s1, introducing a Levy flight strategy, a leader strategy and a replacement crow strategy into the crow search algorithm for improvement based on the crow search algorithm to obtain an improved crow search algorithm;
s2, introducing the improved crow search algorithm into probability integral parameter inversion to establish a probability integral parameter inversion model based on the improved crow search algorithm, and performing settlement prediction calculation through the model to obtain a settlement probability predicted value;
the specific process of introducing the improved crow search algorithm into the probability integral parameter inversion is as follows:
1) setting the maximum number of iterations tmaxPerception probability AP, flight radius riGiving a center value X of a probability integral parameter0=[q,tanβ,b,θ,s1,s2,s3,s4]And a fluctuation range Δ X ═ Δ q, Δ tan β, Δ b, Δ s1,Δs2,Δs3,Δs4]Generating an initial crow populationAnd recording the initial crow group position as the memory position M of the crow groupi;
2) Setting a fitness function for judging whether the crow position is good or bad:
wherein T is the number of observation stations, Wj、UjAre each XiEstimated dip as a probability integral parameter at observation station jValue and horizontal displacement value, Wj 0、Respectively an actually measured sinking value and an actually measured horizontal displacement value on an observation station j;
3) updating the positions of the crows, and searching each crow in the population according to a crow searching formula after introducing a Levy flight strategy and a leader strategy;
4) generating a substitute crow according to a crow search formula after introducing a substitute crow strategy, replacing the crow position beyond a solution space, and updating the crow position;
5) calculating the fitness of the updated crow memory position, and updating the memory position of the crow according to a crow memory position updating formula;
6) and repeating the steps 3) to 5) until the maximum iteration times are reached or the precision condition is met, and outputting the fitness function optimal value in the crow memory value as a result.
2. The mining area mining subsidence prediction method based on the improved crow search algorithm is characterized in that the crow search algorithm specifically comprises the following steps: assuming that N crows fly in a defined D-dimension search range, the position of food is searched, and a better fitness function value f (X) of the position of the food is foundi,t) Low, where the position of crow i in the t iteration is:
wherein i ∈ [1, N ]],t∈[1,tmax],tmaxRepresenting the maximum number of iterations;
the best position found by the t iteration of the crow i, namely the memory position of the crow is as follows:
in the searching process, the crow has two different modes to update the position of the crow, the crow i randomly follows the crow j, the memory position of the crow j is tried to be found, the crow j has certain perception probability to find that the crow j is tracked, if the crow j is not found, the memory position of the crow j is obtained by the crow i, the state is a first state, if the crow j is found, the crow i is taken to a random position, the state is a second state, and the expression formula of the searching process is as follows:
wherein the flight radius riObeying the uniform distribution between 0 and 1, wherein AP represents the perception probability of the crow j, and pl is the flight distance;
after the search is finished, the fitness of the new position of the crow i is compared with the fitness of the memory value of the crow i, the memory position of the crow is updated, and the expression formula is as follows:
and after the iteration is finished, taking the crow memory value with the minimum fitness function value as the optimal parameter solution for output.
3. The mining area mining subsidence prediction method based on the improved crow search algorithm as claimed in claim 2, wherein the Levy flight strategy introduced when the improvement is carried out based on the crow search algorithm is specifically as follows:
σv=1
wherein the value of beta is 1.5;
the crow search formula introduced in the Levy flight strategy is as follows:
4. the mining area mining subsidence prediction method based on the improved crow search algorithm as claimed in claim 2, characterized in that the leader strategy introduced when improving based on the crow search algorithm is specifically: randomly selecting N/2 crows, and taking the memory value of the crows with the optimal fitness as the position M of the leaderleader,tWhen the execution state is one, selecting a leader position for tracking;
the crow search formula after introducing the Levy flight strategy and the leader strategy is as follows:
5. the mining area mining subsidence prediction method based on the improved crow's foot search algorithm as claimed in claim 2, characterized in that the replacement crow strategy introduced when improving based on the crow's foot search algorithm is specifically: when a crow position outside a solution space range is generated in the searching process, a new crow position is randomly generated in the solution space to replace the position to participate in the next iterative calculation;
the crow search formula after introducing the replacement crow strategy is as follows:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110323901.4A CN113077082B (en) | 2021-03-26 | 2021-03-26 | Mining area mining subsidence prediction method based on improved crow search algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110323901.4A CN113077082B (en) | 2021-03-26 | 2021-03-26 | Mining area mining subsidence prediction method based on improved crow search algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113077082A true CN113077082A (en) | 2021-07-06 |
CN113077082B CN113077082B (en) | 2022-09-23 |
Family
ID=76610382
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110323901.4A Active CN113077082B (en) | 2021-03-26 | 2021-03-26 | Mining area mining subsidence prediction method based on improved crow search algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113077082B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113807011A (en) * | 2021-09-13 | 2021-12-17 | 安徽理工大学 | Coal mining settlement prediction model parameter inversion method based on whale optimization algorithm |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108549402A (en) * | 2018-03-19 | 2018-09-18 | 哈尔滨工程大学 | Unmanned aerial vehicle group method for allocating tasks based on quantum crow group hunting mechanism |
CN108717580A (en) * | 2018-03-23 | 2018-10-30 | 安徽理工大学 | The method for seeking probability integral parameter based on invasive weed optimization algorithm |
CN108733621A (en) * | 2018-05-14 | 2018-11-02 | 安徽理工大学 | The inversion method of probability integral Model Parameter based on BFGS algorithms |
CN111476965A (en) * | 2020-03-13 | 2020-07-31 | 深圳信息职业技术学院 | Method for constructing fire detection model, fire detection method and related equipment |
US20200285900A1 (en) * | 2019-03-06 | 2020-09-10 | Wuhan University | Power electronic circuit fault diagnosis method based on optimizing deep belief network |
CN111832645A (en) * | 2020-07-09 | 2020-10-27 | 广西大学 | Classification data feature selection method based on discrete crow difference collaborative search algorithm |
CN112150059A (en) * | 2020-06-23 | 2020-12-29 | 国网天津市电力公司电力科学研究院 | Metering appliance intelligent warehouse scheduling optimization method based on crow algorithm |
-
2021
- 2021-03-26 CN CN202110323901.4A patent/CN113077082B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108549402A (en) * | 2018-03-19 | 2018-09-18 | 哈尔滨工程大学 | Unmanned aerial vehicle group method for allocating tasks based on quantum crow group hunting mechanism |
CN108717580A (en) * | 2018-03-23 | 2018-10-30 | 安徽理工大学 | The method for seeking probability integral parameter based on invasive weed optimization algorithm |
CN108733621A (en) * | 2018-05-14 | 2018-11-02 | 安徽理工大学 | The inversion method of probability integral Model Parameter based on BFGS algorithms |
US20200285900A1 (en) * | 2019-03-06 | 2020-09-10 | Wuhan University | Power electronic circuit fault diagnosis method based on optimizing deep belief network |
CN111476965A (en) * | 2020-03-13 | 2020-07-31 | 深圳信息职业技术学院 | Method for constructing fire detection model, fire detection method and related equipment |
CN112150059A (en) * | 2020-06-23 | 2020-12-29 | 国网天津市电力公司电力科学研究院 | Metering appliance intelligent warehouse scheduling optimization method based on crow algorithm |
CN111832645A (en) * | 2020-07-09 | 2020-10-27 | 广西大学 | Classification data feature selection method based on discrete crow difference collaborative search algorithm |
Non-Patent Citations (3)
Title |
---|
JAIN: "An improved Crow Search Algorithm for high-dimensional problems", 《2017 JOURNAL OF INTELLIGENT & FUZZY SYSTEM》 * |
李焰华等: "基于莱维飞行的乌鸦搜索算法", 《智能计算机与应用》 * |
林涛等: "基于改进乌鸦搜索算法的云计算任务调度研究", 《微电子学与计算机》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113807011A (en) * | 2021-09-13 | 2021-12-17 | 安徽理工大学 | Coal mining settlement prediction model parameter inversion method based on whale optimization algorithm |
CN113807011B (en) * | 2021-09-13 | 2023-06-27 | 安徽理工大学 | Parameter inversion method for coal mining subsidence prediction model based on whale optimization algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN113077082B (en) | 2022-09-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | Multi-objective optimization for limiting tunnel-induced damages considering uncertainties | |
CN111666621B (en) | Method for determining safe support pressure interval of excavation face of tunnel in clay stratum | |
CN113077082B (en) | Mining area mining subsidence prediction method based on improved crow search algorithm | |
CN111932387B (en) | Mining subsidence prediction method based on improved Boltzmann function | |
CN113221462A (en) | Foundation pit soil parameter inversion method combining PSO-DE algorithm and neural network | |
Dai et al. | Firefly Optimization Algorithm for the Prediction of Uplift due to High‐Pressure Jet Grouting | |
Cui et al. | Research on deformation prediction of foundation pit based on PSO‐GM‐BP model | |
CN115688607A (en) | Band-shaped cross-sea quasi-geoid refinement method based on multi-channel spectrum combination | |
Rop et al. | An updated numerical model of the Greater Olkaria geothermal system, Kenya | |
Guo et al. | Parameter inversion of probability integral method based on improved crow search algorithm | |
Deng et al. | Implementation of imrrt path planning algorithm for mobile robot | |
Niu et al. | An intelligent prediction method of the karst curtain grouting volume based on support vector machine | |
Wei et al. | A novel probability integral method segmental modified model for subsidence prediction applicable to thick loose layer mining areas | |
CN114139432A (en) | Fractured reservoir CO using neural network technology2Flooding simulation method | |
Guo et al. | Back‐Analysis of Parameters of Jointed Surrounding Rock of Metro Station Based on Random Forest Algorithm Optimized by Cuckoo Search Algorithm | |
Xu et al. | Prediction of the Height of Water Flowing Fractured Zone Based on the MPSO‐BP Neural Network Model | |
Jiang et al. | Prediction of BlastInduced Ground Vibration (BIGV) of Metro Construction Using Difference Evolution AlgorithmOptimized Gaussian Process (DE‐GP) | |
Xu et al. | A Path Optimization Algorithm for the Mobile Robot of Coal Mine Based on Ant Colony Membrane Algorithm | |
Liu et al. | Curve forming prediction of coal mine roadway based on RBF interpolation | |
Jingxian et al. | Research on the establishment of a mining subsidence prediction model under thick loose layer and its parameter inversion method | |
CN110610017B (en) | Mining subsidence prediction parameter solving method based on improved firework algorithm | |
Abediniangerabi et al. | Early-Stage Advisory System for Energy-Conscious Design of Building Façade Systems | |
Zhou et al. | An intelligent resilience evaluation model for the development of urban underground space with safety concern of surrounding existing built environment | |
CN116882106A (en) | Mine multielement scene self-adaptive ventilation network calculation method | |
Du et al. | Deformation Prediction and Analysis of Soft Rock Roadway with High Altitude and Large Buried Depth Based on Particle Swarm Optimization LSTM 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |