CN110889249A - Resistivity karst cave identification method based on population evolution algorithm - Google Patents
Resistivity karst cave identification method based on population evolution algorithm Download PDFInfo
- Publication number
- CN110889249A CN110889249A CN201911082582.1A CN201911082582A CN110889249A CN 110889249 A CN110889249 A CN 110889249A CN 201911082582 A CN201911082582 A CN 201911082582A CN 110889249 A CN110889249 A CN 110889249A
- Authority
- CN
- China
- Prior art keywords
- karst cave
- solution
- population
- objective function
- evolution algorithm
- 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
Images
Classifications
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a resistivity karst cave identification method based on a population evolution algorithm, which mainly comprises the following steps: s1, constructing a karst cave finite element model, and solving potential distribution data of a structural measurement point by using an electric impedance method positive problem correlation formula; s2, constructing a target function of the karst cave structure, namely the target function to be optimized; and S3, continuously and iteratively optimizing the target function by using a population evolution algorithm, and storing the optimal solution after meeting the stopping criterion so as to identify the karst cave position. Compared with the traditional sensitivity or gradient matrix method, the method can accurately detect the positions of various karst caves without initial values and gradient information and is insensitive to noise. The effectiveness and robustness of the method are illustrated through two embodiments of a single karst cave and a plurality of karst caves, and compared with a particle swarm algorithm, the method has better detection precision even under certain measurement noise and good engineering application capability.
Description
Technical Field
The invention relates to a resistivity karst cave identification method based on a population evolution algorithm, and belongs to the technical field of underground karst cave detection.
Background
At present, in the area where the limestone underground karst cave develops, the underground karst cave of a construction engineering field is often positioned below an underground water level, each building party aims at ensuring the safety of the building foundation, and a large amount of manpower, financial resources and time are invested to carry out the exploration work of the limestone underground karst cave of the construction engineering field in the limestone area. The underground karst cave can cause certain dangers to buildings, subways and the like, the underground karst cave is detected and processed in time, and the method has important significance to safety in construction, use and the like of the structure.
The resistivity method for detecting the karst cave problem is an optimization problem in the identification research of inverse problems, and the basic idea is as follows: the detection area, the electrode scheme and the karst cave are determined, the measured electric potential distribution data are changed, and the karst cave position can be positioned by using the changes in response to the change of the apparent resistivity of the soil layer. Namely, the method is realized by defining an objective function related to the karst cave structure and then utilizing various optimization methods to detect the position of the karst cave. The traditional resistivity cavern detection method introduces a regularization method, adopts sensitivity or a gradient matrix to identify the position of the cavern, and has the following defects: the method is sensitive to initial values and noise, and is easy to fall into a local optimal solution, so that the identification effect is poor.
Disclosure of Invention
The invention aims to provide a cross-hole resistivity karst cave identification method with practicability, effectiveness and accuracy, which can accurately detect the positions of various karst caves, is not sensitive to noise and has good engineering application capability.
The technical scheme of the invention is as follows: a cross-hole resistivity karst cave identification method comprises the following steps:
the method comprises the following steps: establishing a finite element model of a karst cave soil layer, determining an electrode scheme, and obtaining potential distribution data of a measuring point by using an electrical impedance method;
step two: constructing an objective function of the karst cave structure, namely an optimized objective function, wherein the objective function is as follows:
c=[c1;c2;...;cm](1)
where g (c) is the objective function, | () | represents the 2 norm of the vector, i.e.c is the apparent resistivity of each cell, Su represents the data on the set of measured potential points,is the potential distribution data measured by the ith set of electrode schemes,is the potential distribution data identified by the ith electrode scheme,is a matrix formed by s sets of measurement data, and R (c) is a matrix formed by s sets of identification data;
step three: and continuously optimizing the objective function by using a population evolution algorithm, and finally obtaining the identification position of the karst cave after meeting the stop criterion.
In the third step of the method, the specific process of optimizing the objective function by using the population evolution algorithm is as follows:
s1, population parameters and initialization: the control parameters include the maximum number of iterations ItermaxNumber of seed groups Np, number of decision variables n, upper bound X of decision variablesmaxAnd lower bound Xmin:
Xp,q=Xmin+r and·(Xmax-Xmin),p=1,2,...,Np,q=1,2,...,n (1)
Wherein rand is in [0,1 ]]Uniformly distributed random numbers in the range, and the adaptive value f ═ of the candidate solution (f ═ f)1,f2,...,fNp) Calculated according to the following objective function:
fp=obj(Xp,1,Xp,2,…,Xp,n),p=1,2,…,Np (2)
s2, new position generation stage: at this stage, the population candidate solution is considered to move around its own initial position to a better position, for candidate solution p, another candidate solution 1 is randomly selected from the population (p ≠ 1) for generating potential search directions, and the positions are updated according to the distance between the old and new positions of the candidate solution p by the following two models:
(i) model 1: the new position of the candidate solution p is directly learned to the candidate solution 1, and the exploration radius dynamically changes along with iteration:
(ii) model 2: a new position of the solution candidate p is generated around the home position:
s3, spatial search enhancement stage: to further enhance the in-depth search for each dimension, the following steps are taken for each iteration: (i) finding the best and worst candidate solutions in the population; (ii) by changing the value of one dimension while maintaining the values of the other dimensions; (iii) comparing the newly generated solution with the fitness value of the original solution, and reserving a better solution; (iv) repeating steps (ii) and (iii) for other aspects, respectively, the newly created solution being generated by the following formula:
s4, stop criterion stage: saving the current optimal solution, and if the maximum iteration times are met, terminating the algorithm; otherwise, steps S2 and S3 will be repeated.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that: the method constructs the target function through the potential distribution data of the karst cave structure measuring points, utilizes the metaheuristic algorithm to identify the karst cave position, is insensitive to initial values and noise, is not easy to fall into a local optimal solution, and has better efficiency and precision.
Drawings
FIG. 1 is a flow chart of a solution cavity identification problem normalized to an optimization problem;
FIG. 2 is a schematic diagram of a flow chart of an implementation of a population evolution algorithm;
FIG. 3 is a finite element model of a single karst cave in example 1 of the present invention;
FIG. 4 is a finite element model of a plurality of karsts in embodiment 2 of the present invention;
FIG. 5 shows the result of the detection in the absence of noise by the method of the present invention in example 1 of the present invention;
FIG. 6 shows the results of the detection in the presence of 0.1% noise in example 1 of the present invention;
FIG. 7 is a detection result of the particle swarm optimization under the noise-free condition in embodiment 1 of the present invention;
FIG. 8 is a graph showing the detection result of the particle swarm optimization in the presence of 0.1% noise in example 1 of the present invention;
FIG. 9 is a comparison graph of the convergence curves of the algorithm for a single cave with 0.1% noise in example 1 of the present invention.
FIG. 10 shows the result of the detection in the absence of noise by the method of the present invention in example 2 of the present invention;
FIG. 11 shows the results of the detection in the presence of noise by the method of the present invention in example 2 of the present invention;
FIG. 12 shows the detection result of the particle swarm optimization in the noise-free case in embodiment 2 of the present invention;
FIG. 13 shows the detection results of the particle swarm optimization in the presence of 0.1% noise in example 2 of the present invention;
FIG. 14 is a comparison graph of the convergence curves of the algorithm for multiple caverns with 0.1% noise in example 2 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and examples.
Referring to fig. 1, the specific process of the resistivity karst cave identification method based on the population evolution algorithm of the invention comprises two steps:
(1) objective function
The karst cave model is simplified into a rectangular detection area. The current points are not identical to the potential points, but are equal in number. The positive problem solution is performed using finite elements, as follows:
Ku=f
wherein u ═ u1;u2;…;un]Comprises all thatMeasuring node potential, f ═ f1;f2;…;fn]The current vector is characterized, different electrode schemes, and f is different. K is a stiffness matrix and the apparent resistivity c of each unit is ═ c1;c2;…;cm]Is linearly related to where KjIs a matrix of cell stiffness at unit resistivity.
When no karst cave exists in the soil layer, the apparent resistivity of all the units is taken as c0When the solution holes appear, the apparent resistivity of the unit is reduced, and the apparent resistivity of the unit with the solution holes is 3, namely cjThat is, 3( j 1,2, 3.., m) indicates that the jth unit has a cavity. By the formula of the finite element, c has a functional relation with u, and the electric potential distribution data calculated by c can be identified
The objective function constructed based on the potential distribution data is as follows:
c=[c1;c2;...;cm](2)
where c is the apparent resistivity of each cell, Su represents the data on the set of measured potential points,is the potential distribution data measured by the ith set of electrode schemes,is the number of potential distributions identified by the ith group of electrode schemesAccording to the above-mentioned technical scheme,is a matrix of s sets of measured data, and R (c) is a matrix of s sets of calculated data. When the measured potential distribution data and the identified potential distribution data are completely matched, the numerical value is minimum, the karst cave identification problem is equivalent to an optimization problem, a certain individual position of the population is an apparent resistivity distribution condition, and when the objective function reaches a minimum value, the position of the karst cave can be reflected through the identified apparent resistivity c, namely an optimal solution.
(2) And optimizing the target function by using a population evolution algorithm to obtain a recognition result.
Referring to fig. 2, the population evolution algorithm can be divided into the following 7 stages:
stage 1: population parameters and initialization: the control parameters include the maximum number of iterations ItermaxGroup size number Np, decision variable number n, upper bound X of decision variablesmaxAnd lower bound Xmin. These parameters are given at the start of the algorithm. Similar to other naturally inspired metaheuristic optimization algorithms, the initial population positions are randomly generated as follows:
Xp,q=Xmin+r and·(Xmax-Xmin),p=1,2,...,Np,q=1,2,...,n (1)
wherein rand is in [0,1 ]]Uniformly distributed random numbers within the range. The adaptive value f ═ f (f) of the solution candidates1,f2,...,fNp) Calculated according to the following objective function:
fp=obj(Xp,1,Xp,2,...,Xp,n),p=1,2,...,Np (2)
and (2) stage: and a new position generation stage: at this stage, the population candidate solution is considered to move around its initial position to a better position. For a candidate solution p, another candidate solution l is randomly selected from the population (p ≠ l) for generating potential search directions. According to the distance between the new position and the old position of the candidate solution p, the positions are updated through the following two models:
(i) model 1: the new position of the candidate solution p is directly learned to the candidate solution l, and the exploration radius dynamically changes along with iteration:
(ii) model 2: a new position of the solution candidate p is generated around the home position:
in the two models, the purpose of the model 1 is to explore a solution in a feasible space, so that the exploration capability of the algorithm is improved, and the situation that the solution falls into a local optimal solution is avoided; the model 2 is used for improving the convergence performance of the algorithm, so that the development capability of the algorithm is enhanced. During each iteration, in order to balance the exploration and development capabilities of the algorithm in the search process, the two models are randomly invoked.
If the fitness value of the new location is better than the old location, the location of the candidate solution is updated, otherwise the old location is retained:
and (3) stage: and (3) a spatial search enhancement stage: during the search, all dimensions of each candidate solution are updated simultaneously. However, the variation of one-dimensional variables may have a negative effect on other dimensional variables, resulting in poor convergence performance for each dimension. To further enhance the in-depth search for each dimension, the following steps are taken for each iteration: (i) finding the best and worst candidate solutions in the population; (ii) generating another solution from the best candidate by changing the value of one dimension while maintaining the values of the other dimensions; (iii) comparing the newly generated solution with the fitness value of the original solution, and reserving a better solution; (iv) (iv) repeating steps (ii) and (iii) separately for other aspects. The newly generated solution is generated by the following formula:
and (4) stage: a stopping criterion stage: if the maximum number of iterations is met, the algorithm will terminate: otherwise, the two processes of the stage 2 and the stage 3 are repeated, and a new position and an enhanced dimension search are generated.
As the population evolution algorithm belongs to a population intelligent algorithm, the population evolution algorithm can be used for solving a nonlinear problem, and the resistivity method for detecting the karst cave problem is a typical nonlinear problem. In combination with a population evolution algorithm, firstly, a finite element model of a karst cave is identified according to a resistivity method of a detection area, the corresponding karst cave position is calibrated according to the apparent resistivity of a unit, the set input and output currents (an electrode scheme) are solved according to a positive problem formula, the potential distribution of the detection area is solved, in the practical engineering, only the potential distribution condition can be obtained, but the apparent resistivity distribution is solved according to the potential distribution, the problem is nonlinear, therefore, the apparent resistivity distribution condition of the detection area is solved by combining the population evolution algorithm, the position of the karst cave is obtained (an objective function is established according to the potential distribution condition obtained by the positive problem, a certain body position of a population is the apparent resistivity distribution condition, parameters such as the initial position of the individual, the number of the individual and the like are set, then, the continuous iteration of the algorithm is carried out, after the stopping criterion is met, the resulting optimal individual location is the identified apparent resistivity profile).
Example 1: single karst cave model location identification
And establishing a single karst cave finite element model as shown in FIG. 3, dividing the rectangular detection area into 64 units, and detecting by adopting an underground karst cave model with 64 units. The length and width of the rectangular detection area are 4m by 4m, and each side is uniformly divided into 8 units; and detecting the underground karst cave by adopting an electrical impedance imaging method. Assuming that cell number 28 is equivalent to 3 in apparent resistivity, the parameters in the algorithm are set: maximum number of iterations ItermaxThe number of population sizes Np and the number of decision variables n are respectively 200, 250 and64. the noise levels were 0% and 0.1%, respectively.
As can be seen from FIGS. 5-8, the position of the karst cave can be detected by the population evolution algorithm, and the particle swarm algorithm gives a lot of wrong identifications. The karst cave position can be accurately identified by a population evolution algorithm, and the relative error of actual data and identification data is extremely small. Even under the influence of artificial noise, the relative error is within 1.3 percent; as can be seen from the convergence curve of the algorithm in FIG. 9, the convergence rate of the population evolution algorithm is significantly faster than that of the particle swarm algorithm, and the final convergence value is much smaller.
Example 2: multiple karst cave model position identification
As shown in FIG. 4, in the present embodiment, for multi-unit cavern detection, an electrical impedance imaging method is used to detect the underground cavern. Assuming that cells 12 and 47 are equivalent to 3 in apparent resistivity, the parameters in the algorithm are set: maximum number of iterations ItermaxThe population size number Np and the decision variable number n are 200, 250 and 64, respectively. The noise levels were 0% and 0.1%, respectively.
As can be seen from FIGS. 10-13, the population evolution algorithm can accurately identify the karst cave position in the absence of noise. In contrast, particle swarm optimization cannot detect efficiently; it can be seen from the convergence curve of the algorithm in fig. 14 that the convergence rate of the population evolution algorithm is significantly faster than that of the particle swarm algorithm, and the final convergence value is much smaller, although the number of the recognition units is larger, the population evolution algorithm is still feasible and accurate in the aspect of karst cave detection and is insensitive to noise.
It should be understood that the above-described embodiments of the present invention are only examples for clearly illustrating the present invention, and those skilled in the art can modify the forms of the present invention based on the above description, such as expanding the detection range, changing the location of the cavern, etc., and are not exhaustive herein. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (2)
1. A resistivity karst cave identification method based on a population evolution algorithm is characterized by comprising the following steps:
the method comprises the following steps: establishing a finite element model of a karst cave soil layer, determining an electrode scheme, and obtaining potential distribution data of a measuring point by using an electrical impedance method;
step two: constructing an objective function of the karst cave structure, namely an optimized objective function, wherein the objective function is as follows:
where g (c) is the objective function, | () | represents the 2 norm of the vector, i.e.c is the apparent resistivity of each cell, Su represents the data on the set of measured potential points,is the potential distribution data measured by the ith set of electrode schemes,is the potential distribution data identified by the ith group of electrode schemes,is a matrix formed by s sets of measurement data, and R (c) is a matrix formed by s sets of identification data;
step three: and continuously optimizing the objective function by using a population evolution algorithm, and finally obtaining the identification position of the karst cave after meeting the stop criterion.
2. The resistivity-cave identification method based on the population evolution algorithm according to claim 1, characterized in that: the specific process of optimizing the objective function by using the population evolution algorithm in the third step is as follows:
s1, population parameters and initialization: the control parameters include iterative optimizationLarge number ItermaxGroup size number Np, decision variable number n, upper bound X of decision variablesmaxAnd lower bound Xmin:
Xp,q=Xmin+rand·(Xmax-Xmin),p=1,2,...,Np,q=1,2,...,n (1)
Wherein rand is in [0,1 ]]Uniformly distributed random numbers in the range, and the adaptation value f ═ of the solution candidate (f ═ f)1,f2,...,fNp) Calculated according to the following objective function:
fp=obj(Xp,1,Xp,2,…,Xp,n),p=1,2,…,Np (2)
s2, new position generation stage: at this stage, the population candidate solution is considered to move around its initial position to a better position, for candidate solution p, another candidate solution l is randomly selected from the population (p ≠ l) for generating potential search directions, and the position is updated according to the distance between the old and new positions of the candidate solution p by the following two models:
(i) model 1, learning the new position of the candidate solution p directly to the candidate solution l, and dynamically changing the exploration radius along with iteration:
(ii) model 2 New positions that produce candidate solutions p near the original position:
s3, spatial search enhancement stage: to further enhance the in-depth search for each dimension, the following steps are taken for each iteration: (i) finding the best and worst candidate solutions in the population; (ii) by changing the value of one dimension while maintaining the values of the other dimensions; (iii) comparing the newly generated solution with the fitness value of the original solution, and reserving a better solution; (iv) repeating steps (ii) and (iii) for other aspects, respectively, the newly created solution is generated by the following formula:
s4, stop criterion stage: saving the current optimal solution, and if the maximum iteration times are met, terminating the algorithm; otherwise, steps S2 and S3 will be repeated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911082582.1A CN110889249B (en) | 2019-11-07 | 2019-11-07 | Method for identifying resistivity karst cave based on population evolution algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911082582.1A CN110889249B (en) | 2019-11-07 | 2019-11-07 | Method for identifying resistivity karst cave based on population evolution algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110889249A true CN110889249A (en) | 2020-03-17 |
CN110889249B CN110889249B (en) | 2023-07-25 |
Family
ID=69747026
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911082582.1A Active CN110889249B (en) | 2019-11-07 | 2019-11-07 | Method for identifying resistivity karst cave based on population evolution algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110889249B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112083253A (en) * | 2020-09-18 | 2020-12-15 | 西南交通大学 | Soil electrical parameter state inversion method under direct current |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102508303A (en) * | 2011-11-23 | 2012-06-20 | 山东大学 | Advanced detection method for focusing chromatography induced polarization of underground engineering |
CN106199700A (en) * | 2016-06-30 | 2016-12-07 | 马克 | A kind of underground water seal oil storage cave depot micro seismic monitoring method and system |
CN107045147A (en) * | 2017-04-05 | 2017-08-15 | 浙江省水利河口研究院 | A kind of multidimensional detecting device and method for detecting river course solution cavity |
US20180216932A1 (en) * | 2015-10-06 | 2018-08-02 | Bridger Photonics, Inc. | High-sensitivity gas-mapping 3d imager and method of operation |
CN109024569A (en) * | 2018-08-22 | 2018-12-18 | 中国建筑第四工程局有限公司 | A kind of beading solution cavity pretreatment construction method |
CN109636671A (en) * | 2018-12-18 | 2019-04-16 | 中南大学 | A kind of wind electricity digestion optimisation strategy considering multi-level market linkage type |
CN109870909A (en) * | 2019-03-01 | 2019-06-11 | 中国人民解放军陆军装甲兵学院 | A kind of Artificial Immune Algorithm based on RBF neural and adaptable search |
-
2019
- 2019-11-07 CN CN201911082582.1A patent/CN110889249B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102508303A (en) * | 2011-11-23 | 2012-06-20 | 山东大学 | Advanced detection method for focusing chromatography induced polarization of underground engineering |
US20180216932A1 (en) * | 2015-10-06 | 2018-08-02 | Bridger Photonics, Inc. | High-sensitivity gas-mapping 3d imager and method of operation |
CN106199700A (en) * | 2016-06-30 | 2016-12-07 | 马克 | A kind of underground water seal oil storage cave depot micro seismic monitoring method and system |
CN107045147A (en) * | 2017-04-05 | 2017-08-15 | 浙江省水利河口研究院 | A kind of multidimensional detecting device and method for detecting river course solution cavity |
CN109024569A (en) * | 2018-08-22 | 2018-12-18 | 中国建筑第四工程局有限公司 | A kind of beading solution cavity pretreatment construction method |
CN109636671A (en) * | 2018-12-18 | 2019-04-16 | 中南大学 | A kind of wind electricity digestion optimisation strategy considering multi-level market linkage type |
CN109870909A (en) * | 2019-03-01 | 2019-06-11 | 中国人民解放军陆军装甲兵学院 | A kind of Artificial Immune Algorithm based on RBF neural and adaptable search |
Non-Patent Citations (2)
Title |
---|
LI CHANGHONG: "coupling analysis and application of strata information and exploration information of AGI high-density resistivity measurement system", vol. 261, pages 1379 - 1385 * |
王荣伟;高正红;: "基于改进粒子群算法的翼型多目标优化研究", no. 03 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112083253A (en) * | 2020-09-18 | 2020-12-15 | 西南交通大学 | Soil electrical parameter state inversion method under direct current |
CN112083253B (en) * | 2020-09-18 | 2021-07-02 | 西南交通大学 | Soil electrical parameter state inversion method under direct current |
Also Published As
Publication number | Publication date |
---|---|
CN110889249B (en) | 2023-07-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109145464B (en) | Structural damage identification method integrating multi-target ant lion optimization and trace sparse regularization | |
CN107256237A (en) | The LOF cluster datas abnormal point detecting method and detecting system optimized based on dynamic grid | |
CN111415379B (en) | Three-dimensional point cloud data registration method based on cuckoo optimization | |
CN106886980B (en) | Point cloud density enhancement method based on three-dimensional laser radar target identification | |
Xin et al. | Deep community detection in topologically incomplete networks | |
CN110110434B (en) | Initialization method for probability load flow deep neural network calculation | |
CN105118090A (en) | Adaptive point-cloud filtering method for complex terrain structure | |
CN115496144A (en) | Power distribution network operation scene determining method and device, computer equipment and storage medium | |
CN116578551A (en) | GRU-GAN-based power grid data restoration method | |
CN110889249A (en) | Resistivity karst cave identification method based on population evolution algorithm | |
CN110850477A (en) | Resistivity karst cave identification method based on squirrel search algorithm | |
CN111507591B (en) | Power system state determination method, device, computer medium and storage medium | |
CN110188830B (en) | SAR image change detection method based on multi-core graph cut | |
CN109861220B (en) | Method for constructing tensor input of deep convolutional neural network for power system analysis | |
CN108898527B (en) | Traffic data filling method of generative model based on destructive measurement | |
Guo et al. | Data mining and application of ship impact spectrum acceleration based on PNN neural network | |
CN115793456A (en) | Lightweight sensitivity-based power distribution network edge side multi-mode self-adaptive control method | |
CN114221334A (en) | Rapid state estimation method based on graph neural network | |
Wang et al. | Enhancing Diversity by Local Subset Selection in Evolutionary Multiobjective Optimization | |
CN111211559A (en) | Power grid impedance estimation method based on dynamic step length firefly algorithm | |
Hassan et al. | Optimizing photovoltaic models: A leader artificial ecosystem approach for accurate parameter estimation of dynamic and static three diode systems | |
CN116611267B (en) | All-constraint configuration method for priori boundary structure in geophysical prospecting data regularized inversion | |
CN108267106A (en) | A kind of Cylindricity error evaluation of fast steady letter | |
KR102328879B1 (en) | Method and device for unsupervised learning to be used for detecting anomalistic web log under circumstance of unbalanced training data, and testing method and testing device using the same | |
Salar et al. | Improving genetic algorithm performance in multi-classification using simplex method |
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 |