CN112733438A - Sponge city planning model parameter optimization method based on ant colony algorithm - Google Patents

Sponge city planning model parameter optimization method based on ant colony algorithm Download PDF

Info

Publication number
CN112733438A
CN112733438A CN202011602277.3A CN202011602277A CN112733438A CN 112733438 A CN112733438 A CN 112733438A CN 202011602277 A CN202011602277 A CN 202011602277A CN 112733438 A CN112733438 A CN 112733438A
Authority
CN
China
Prior art keywords
parameter
value
sponge city
ant colony
optimized
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
Application number
CN202011602277.3A
Other languages
Chinese (zh)
Inventor
马丽娜
李运东
禹雅洁
田禹
梁恒
李俐频
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Harbin Institute of Technology
Original Assignee
Harbin Institute of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Harbin Institute of Technology filed Critical Harbin Institute of Technology
Priority to CN202011602277.3A priority Critical patent/CN112733438A/en
Publication of CN112733438A publication Critical patent/CN112733438A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • 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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A sponge city planning model parameter optimization method based on an ant colony algorithm belongs to the technical field of city planning. The method solves the problems of low efficiency, high interference degree by human factors and high resource consumption in the artificial calibration adopted for sponge city model parameter optimization. According to the method, a target function and parameters to be optimized are set according to a sponge city model to be optimized; setting a value range of a parameter to be optimized according to a historical parameter and a parameter empirical value of a sponge city model to be optimized; and obtaining the optimal value range of each parameter by using the ant colony algorithm according to the value range of each parameter to be optimized. The method is suitable for parameter optimization of the sponge city planning model.

Description

Sponge city planning model parameter optimization method based on ant colony algorithm
Technical Field
The invention belongs to the technical field of urban planning.
Background
The sponge city has the functions of source emission reduction, process control and tail end treatment, and is an effective means for systematically improving the urban water environment and preventing and treating rainfall flood and waterlogging disasters. The sponge city planning model is established, the type selection and the construction position layout of sponge city construction facilities can be guided, the effect of a sponge construction scheme is evaluated, and the sponge city planning model is a key link for sponge city construction. The sponge city planning model parameters are optimized, the model prediction precision can be improved, and the method has important significance for improving the sponge city construction efficiency.
However, at present, a manual calibration method is usually adopted for parameter optimization of sponge city models, but the sponge city models have numerous related parameters and complex relationships, and part of the parameters are difficult to measure through experiments and only depend on empirical judgment of experts in related fields, so that the prediction result is interfered by human factors to a higher degree. Meanwhile, the manual calibration efficiency is limited by the working time, and the consumption of engineering manpower and capital resources is large.
Disclosure of Invention
The invention aims to solve the problems of low efficiency, high interference degree by human factors and high resource consumption in the artificial calibration adopted for sponge city model parameter optimization, and provides an ant colony algorithm-based sponge city planning model parameter optimization method.
The invention relates to a sponge city planning model parameter optimization method based on an ant colony algorithm, which comprises the following specific steps:
step one, setting a target function and parameters to be optimized according to a sponge city model to be optimized;
setting a value taking range of the parameter to be optimized according to the historical parameter and the parameter empirical value of the sponge city model to be optimized;
and thirdly, carrying out iterative computation on the objective function by using the ant colony algorithm according to the value range of each parameter to be optimized until the threshold value or the upper limit of the iteration times of the objective function is reached, and obtaining the optimal value range of each parameter.
Further, the third step is a specific method of obtaining the optimal value range of each parameter by using the ant colony algorithm by using the value range of each parameter to be optimized, and the specific method comprises the following steps:
step A1, dispersing the value range of each parameter to be optimized into N equal parts, and obtaining N value intervals of each parameter;
step A2, initializing an ant colony algorithm; setting the endpoints of the N value intervals of each parameter as N +1 nodes of the parameter;
step A3, randomly placing all ants in the ant colony on N +1 nodes of a first parameter; step a31 is executed;
step A31, calculating the transfer probability of each ant from the node of the current parameter to the node of the next parameter; step A4 is executed;
step A4, distributing all ants of the ant colony to the N +1 nodes of the next parameter according to the transition probability, and executing step A41; wherein N is a positive integer;
step A41, judging whether the next parameter is the last parameter to be optimized of the iteration, if so, executing step A5, otherwise, executing step A31;
step A5, calculating the objective function value of the iteration, and judging whether the objective function value reaches a function threshold value, if so, executing step A7, otherwise, executing step A6;
step A6, judging whether the current iteration number reaches the upper limit of the iteration number, if so, executing step A7, otherwise, executing step A61;
step A61, calculating the transfer probability of each ant from the node of the current parameter to the node of the first parameter; return to performing step a 4;
step A7, calculating the pheromone intensity of N +1 nodes of each parameter, obtaining an optimal path according to the pheromone intensity of the nodes of each parameter, and obtaining the optimal value interval of each parameter according to the optimal path.
Further, the parameters to be optimized in the first step include: rainwater runoff and pollutant concentration in urban catchment areas.
Further, the ant colony algorithm is initialized in the fourth step as follows: setting an upper limit of iteration times and an initial value of a node information intensity element; and setting the total number of ants in the ant colony and setting a target function threshold value.
Further, the specific formula for calculating the pheromone strength of each parameter N +1 nodes in step eight is as follows:
τij(t+n)＝ρ·τij(t)+Δτij
Δτij＝∑m/k＝1Δτijk
τij(t) represents the residual quantity of pheromone on the route ij at time t, ρ represents the residual quantity of pheromone, Δ τijk represents the information amount of the kth ant left on the path ij in the current cycle, and delta tauijRepresents the increment of the amount of information left on the path by all ants that have undergone path ij in this cycle.
Further, the calculation method for calculating the objective function value of the iteration in step a5 is as follows: the formula is adopted:
Figure BDA0002869131270000021
and (3) realizing calculation, wherein N is the group number of data output by the iteration sponge city model, and Q issimThe data value Q of the iteration sponge city modelobsAnd QsimThe corresponding actual observed value is compared with the actual observed value,
Figure BDA0002869131270000031
is the average of the actual observed data; the NSE value is closer to 1, the fitting effect of the simulation value and the measured value is better, the NSE value is small, the reliability of the result is low, the evaluation value is larger, the reliability is higher, and the model optimization has high precision.
The invention provides an ant colony algorithm-based sponge city planning model parameter optimization method, which corrects the situation that the traditional water science model has errors in actual urban water environment simulation to a certain extent and has important significance in evaluating the current situation of the sponge urban water environment. The existing model correction method is not only very complex, but also only suitable for a linear input and output hydrological model with a relatively simple structure. Compared with manual calibration, the ant colony algorithm analysis means provided by the invention has the advantages of universality, high convergence speed and the like, and can quickly and accurately obtain the prediction result, so that the sponge city design model can more accurately and effectively reflect real city ecological characteristics. In addition, the ant colony algorithm has the advantages of strong self-learning, self-adaptability, strong fault tolerance and the like, is different from the fact that manual calibration is limited by professional knowledge and poor in anti-interference performance, and users can directly apply to the optimization research of model core parameters without the need of a principle equation of smart model input and output, so that the parameter rate calibration efficiency is effectively improved, the interference degree of human factors is small, and the resource waste is reduced.
The difference value between the predicted value and the actual value of the sponge city design model optimized by the method is obviously reduced, the Nash-Sutcliffe efficiency coefficient of the original model fluctuates between 0.3 and 0.6, and the optimized model is basically stabilized to about 0.8. The sponge city design model has good applicability to hydrological environment simulation of an actual city, and research results also show that the comprehensive hydrological model optimized by the ant colony algorithm improves the problems of parameter optimization and result output in the hydrological model to a certain extent, and greatly improves the practicability of the model.
Drawings
Fig. 1 is a flowchart of the present invention for obtaining the optimal value interval of each parameter by using the ant colony algorithm.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
The first embodiment is as follows: the sponge city planning model parameter optimization method based on the ant colony algorithm in the embodiment comprises the following specific steps:
step one, setting a target function and parameters to be optimized according to a sponge city model to be optimized;
setting a value taking range of the parameter to be optimized according to the historical parameter and the parameter empirical value of the sponge city model to be optimized;
and thirdly, carrying out iterative computation on the objective function by using the ant colony algorithm according to the value range of each parameter to be optimized until the threshold value or the upper limit of the iteration times of the objective function is reached, and obtaining the optimal value range of each parameter.
Further, referring to fig. 1, the specific method for obtaining the optimal value range of each parameter by using the ant colony algorithm using the value range of each parameter to be optimized in step three is as follows:
step A1, dispersing the value range of each parameter to be optimized into N equal parts, and obtaining N value intervals of each parameter;
step A2, initializing an ant colony algorithm; setting the endpoints of the N value intervals of each parameter as N +1 nodes of the parameter;
step A3, randomly placing all ants in the ant colony on N +1 nodes of a first parameter; step a31 is executed;
step A31, calculating the transfer probability of each ant from the node of the current parameter to the node of the next parameter; step A4 is executed;
step A4, distributing all ants of the ant colony to the N +1 nodes of the next parameter according to the transition probability, and executing step A41; wherein N is a positive integer;
step A41, judging whether the next parameter is the last parameter to be optimized of the iteration, if so, executing step A5, otherwise, executing step A31;
step A5, calculating the objective function value of the iteration, and judging whether the objective function value reaches a function threshold value, if so, executing step A7, otherwise, executing step A6;
step A6, judging whether the current iteration number reaches the upper limit of the iteration number, if so, executing step A7, otherwise, executing step A61;
step A61, calculating the transfer probability of each ant from the node of the current parameter to the node of the first parameter; return to performing step a 4;
step A7, calculating the pheromone intensity of N +1 nodes of each parameter, obtaining an optimal path according to the pheromone intensity of the nodes of each parameter, and obtaining the optimal value interval of each parameter according to the optimal path.
The invention develops an automatic sponge city model parameter calibration method based on an ant colony model algorithm. The ant colony algorithm is inspired by foraging behaviors of ants, and is characterized in that ants are indirectly communicated through traces of semiochemicals, so that the shortest path between a nest hole and food is found. In the method, the model parameters are used as food points on the ant colony advancing path, an equation relation between the model prediction precision and the ant colony path total distance is established, and the parameter assignment with the highest prediction precision is screened by optimizing the ant colony shortest path, so that the model prediction precision is improved. The parameter optimization algorithm relies on computer iterative solution, the automation degree is greatly enhanced, the defect of high dependence of model construction on professionals is overcome, and the model prediction precision and the parameter optimization speed are remarkably improved. The algorithm provides a brand-new solution for the optimization of each parameter in the sponge city planning design model.
Further, the parameters to be optimized in the first step include: rainwater runoff and pollutant concentration in urban catchment areas.
Further, the ant colony algorithm is initialized in the fourth step as follows: setting an upper limit of iteration times and an initial value of a node information intensity element; and setting the total number of ants in the ant colony and setting a target function threshold value.
Further, the specific formula for calculating the pheromone strength of each parameter N +1 nodes in step eight is as follows:
τij(t+n)＝ρ·τij(t)+Δτij
Δτij＝∑m/k＝1Δτijk
τij(t) represents the residual quantity of pheromone on the route ij at time t, ρ represents the residual quantity of pheromone, Δ τijk represents the information amount of the kth ant left on the path ij in the current cycle, and delta tauijRepresents the increment of the amount of information left on the path by all ants that have undergone path ij in this cycle.
Further, in step a5, the calculation method for calculating the objective function value of the iteration is as follows: the formula is adopted:
Figure BDA0002869131270000051
and (3) realizing calculation, wherein N is the group number of data output by the iteration sponge city model, and Q issimThe output value, Q, of the iterative modelobsAnd QsimThe corresponding actual observed value is compared with the actual observed value,
Figure BDA0002869131270000052
is the average of the observed data; the more NSE value approaches 1, the better the fitting effect of the simulation value and the measured value is shown, the small NSE value shows that the reliability of the result is low, and the larger the evaluation value means that the reliability is higher, and the model optimization has high precision.
The specific embodiment is as follows:
the method is successfully applied to the city A, and the intelligent model for planning and designing the sponge city after optimizing the core parameters is used for simulating the rainwater runoff of the urban catchment area of the city A, and the specific process is as follows:
(1) and collecting and arranging data of the intelligent model for the sponge city planning design, wherein the data comprises the rainwater runoff and the pollutant concentration of the urban catchment area. And (3) taking the Nash-Sutcliffe efficiency coefficient as a target function to evaluate the fitting degree of the predicted value and the actual value.
(2) Determining parameters needing to be optimized by the model as the permeability of the storage regulating layer, the balance infiltration rate of sandy soil is 29.97-120.40, the soil is 1.02-10.92 and the clay is 0.254-0.51;
(3) dividing the value range of the permeability of the regulation and storage layer into ten equal parts, wherein the number of the value ranges is eleven; the sand is 29.97, 39.01, 48.05, 57.10, 66.14, 75.18, 84.23, 93.27, 102.31, 111.35 and 120.40; the loam is: 1.02, 2.01, 3.00, 3.99, 4.98, 5.97, 6.96, 7.95, 8.94, 9.93, 10.92; the clay is 0.254, 0.280, 0.305, 0.331, 0.356, 0.382, 0.408, 0.433, 0.459, 0.484, 0.510.
(4) Assigning the same initial value to the information intensity among all the point positions of all the variables, determining the visibility, determining the cycle number and starting iterative computation, wherein an information heuristic factor alpha is 0.9, an expected heuristic factor beta is 1.0;
(5) respectively setting the number m of ants belonging to {8,9,10,11,12,13 and 14}, calculating the transition probability, randomly placing m ants on the point position of the first parameter, and transferring to each node of the next variable according to the calculated transition probability;
(6) updating the intensity of pheromones of paths which have been traveled by ants, thereby correcting the probability of selecting each variable path by the ants;
(7) and (4) continuing iteration until the maximum iteration frequency is reached for 50 times, basically stabilizing the data when the iteration is carried out for forty times, and obtaining the optimal values of all variables, namely sandy soil 120.3963, loam 3.3021 and clay 0.25423 after calculation.
(8) And outputting an iteration result, and calculating Nash-Sutcliffe efficiency coefficients of the rainwater runoff of the urban catchment area to be 0.78, 0.76, 0.70, 0.73 and 0.74 respectively.
After the main parameters of the sponge city design model are optimized, the simulated urban catchment area rainwater runoff before and after the ant colony algorithm optimization is compared with the measured value, and the result is shown in table 1.
TABLE 1 Nash efficiency coefficient for optimizing rainwater runoff of urban catchment area before and after optimization
Figure BDA0002869131270000061
From the nash efficiency coefficients of table 1, the nash efficiency coefficient of the rainwater runoff of the urban catchment area before optimization is 0.56 at most and 0.35 at least, and the nash efficiency coefficient after optimization is 0.78 at most and 0.70 at least. After optimization, the fitting degree of the predicted value and the measured value is greatly improved, and the maximum fitting degree is improved by about 40%.
Although the invention herein has been described with reference to particular embodiments, it is to be understood that these embodiments are merely illustrative of the principles and applications of the present invention. It is therefore to be understood that numerous modifications may be made to the illustrative embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that the features described in the various dependent claims and herein may be combined in a manner different from that described in the original claim. It is also to be understood that features described in connection with individual embodiments may be used in other described embodiments.

Claims (6)

1. The sponge city planning model parameter optimization method based on the ant colony algorithm is characterized by comprising the following specific steps:
step one, setting a target function and parameters to be optimized according to a sponge city model to be optimized;
step two, setting the value range of the parameter to be optimized according to the historical parameter and the parameter empirical value of the sponge city model to be optimized;
and thirdly, carrying out iterative computation on the objective function by using the ant colony algorithm according to the value range of each parameter to be optimized until the threshold value or the upper limit of the iteration times of the objective function is reached, and obtaining the optimal value range of each parameter.
2. The method for optimizing the parameters of the sponge city planning model based on the ant colony algorithm according to claim 1, wherein the specific method for obtaining the optimal value range of each parameter by using the ant colony algorithm by using the value ranges of the parameters to be optimized in the third step is as follows:
step A1, dispersing the value range of each parameter to be optimized into N equal parts, and obtaining N value intervals of each parameter;
step A2, initializing an ant colony algorithm; setting the endpoints of the N value intervals of each parameter as N +1 nodes of the parameter;
step A3, randomly placing all ants in the ant colony on N +1 nodes of a first parameter; step a31 is executed;
step A31, calculating the transfer probability of each ant from the node of the current parameter to the node of the next parameter; step A4 is executed;
step A4, distributing all ants of the ant colony to the N +1 nodes of the next parameter according to the transition probability, and executing step A41; wherein N is a positive integer;
step A41, judging whether the next parameter is the last parameter to be optimized of the iteration, if so, executing step A5, otherwise, executing step A31;
step A5, calculating the objective function value of the iteration, and judging whether the objective function value reaches a function threshold value, if so, executing step A7, otherwise, executing step A6;
step A6, judging whether the current iteration number reaches the upper limit of the iteration number, if so, executing step A7, otherwise, executing step A61;
step A61, calculating the transfer probability of each ant from the node of the current parameter to the node of the first parameter; returning to execute the step A4;
step A7, calculating the pheromone strength of N +1 nodes of each parameter, obtaining an optimal path according to the pheromone strength of the nodes of each parameter, and obtaining the optimal value interval of each parameter according to the optimal path.
3. The method for optimizing sponge city planning model parameters based on ant colony algorithm according to claim 1 or 2, wherein the parameters to be optimized in step one comprise: rainwater runoff and pollutant concentration in urban catchment areas.
4. The method for optimizing sponge city planning model parameters based on ant colony algorithm according to claim 2, wherein the ant colony algorithm is initialized in step a2 as follows: setting an upper limit of iteration times and an initial value of a node information intensity element; and setting the total number of ants in the ant colony and setting a target function threshold value.
5. The method for optimizing sponge city planning model parameters based on ant colony algorithm according to claim 2 or 4, wherein the specific formula for calculating the pheromone strength of each parameter N +1 nodes in step A7 is as follows:
τij(t+n)＝ρ·τij(t)+Δτij
Δτij＝∑m/k＝1Δτijk
τij(t) represents the residual quantity of pheromone on the route ij at time t, ρ represents the residual quantity of pheromone, Δ τijk represents the information amount of the kth ant left on the path ij in the current cycle, and delta tauijRepresenting the increment of the amount of information left on the path by all ants in the current cycle that have traversed the path ij.
6. The method for optimizing sponge city planning model parameters based on ant colony algorithm according to claim 5, wherein the calculation method for calculating the iterative objective function value in step A5 is as follows: the formula is adopted:
Figure FDA0002869131260000021
and (3) realizing calculation, wherein N is the group number of data output by the iteration sponge city model, and Q issimData value, Q, output by the iterative sponge city modelobsAnd QsimThe corresponding actual observed value is compared with the actual observed value,
Figure FDA0002869131260000022
is the average of the actual observed data.
CN202011602277.3A 2020-12-29 2020-12-29 Sponge city planning model parameter optimization method based on ant colony algorithm Pending CN112733438A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011602277.3A CN112733438A (en) 2020-12-29 2020-12-29 Sponge city planning model parameter optimization method based on ant colony algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011602277.3A CN112733438A (en) 2020-12-29 2020-12-29 Sponge city planning model parameter optimization method based on ant colony algorithm

Publications (1)

Publication Number Publication Date
CN112733438A true CN112733438A (en) 2021-04-30

Family

ID=75610552

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011602277.3A Pending CN112733438A (en) 2020-12-29 2020-12-29 Sponge city planning model parameter optimization method based on ant colony algorithm

Country Status (1)

Country Link
CN (1) CN112733438A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113947301A (en) * 2021-10-13 2022-01-18 广东巍智科技有限公司 Sponge city project evaluation method and device, terminal equipment and storage medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104766358A (en) * 2015-04-08 2015-07-08 浙江大学 Optimization method of flying insect moving model parameters based on statistic estimation
CN109033517A (en) * 2018-06-21 2018-12-18 浙江大学 A kind of Engineering Optimizational Method improving Storm Sewer Network design scheme applicability

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104766358A (en) * 2015-04-08 2015-07-08 浙江大学 Optimization method of flying insect moving model parameters based on statistic estimation
CN109033517A (en) * 2018-06-21 2018-12-18 浙江大学 A kind of Engineering Optimizational Method improving Storm Sewer Network design scheme applicability

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
M.H. AFSHAR: "A parameter free Continuous Ant Colony Optimization Algorithm for the optimal design of storm sewer networks: Constrained and unconstrained approach", 《ADVANCES IN ENGINEERING SOFTWARE》 *
孙会航等: "基于多目标优化与综合评价的海绵城市规划设计", 《环境科学学报》 *
岳佳佳等: "蚁群算法在黑河上游VIC模型参数校正中的应用", 《北京师范大学学报（自然科学版）》 *
熊梦思等: "变化环境下水文模型时变参数的识别及函数型式构建", 《水资源研究》 *
王晓路: "基于蚁群算法优化SVM的瓦斯涌出量预测", 《煤炭技术》 *
陈洪涛: "蚁群算法在排水管网系统优化设计中的应用研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113947301A (en) * 2021-10-13 2022-01-18 广东巍智科技有限公司 Sponge city project evaluation method and device, terminal equipment and storage medium
CN113947301B (en) * 2021-10-13 2022-09-13 广东巍智科技有限公司 Sponge city project evaluation method and device, terminal equipment and storage medium

Similar Documents

Publication Publication Date Title
Fallah-Mehdipour et al. Real-time operation of reservoir system by genetic programming
CN107067091B (en) Urban ecological land space planning model based on ant colony optimization algorithm
CN105701571A (en) Short-term traffic flow prediction method based on nerve network combination model
CN105512767A (en) Flood forecasting method of multiple forecast periods
CN107705556A (en) A kind of traffic flow forecasting method combined based on SVMs and BP neural network
CN103077247B (en) The method for building up of friends transmission tree in a kind of social networks
CN105260607A (en) Serial connection and parallel connection coupling multi-model hydrological forecasting method
CN109697512B (en) Personal data analysis method based on Bayesian network and computer storage medium
CN110162807B (en) Ammunition storage reliability assessment method based on improved ant colony optimization BP neural network
CN108614915B (en) Hydrological model free construction strategy method based on scene driving
CN112907970B (en) Variable lane steering control method based on vehicle queuing length change rate
CN107766694A (en) Hydro-Model Parameter Calibration Technology method of estimation based on FCM NSGA II
CN115759499A (en) Path planning method, device, equipment and medium based on optimization algorithm
CN113435630B (en) Basin hydrological forecasting method and system with self-adaptive runoff yield mode
CN117556775B (en) Multi-target chip circuit parameter optimization design method
CN108681751A (en) Determine the method and terminal device of event influence factor
CN113919107A (en) Power grid reliability evaluation method based on maximum entropy principle and cross entropy important sampling
CN107704426A (en) Water level prediction method based on extension wavelet-neural network model
CN111859733A (en) Automobile exhaust system reliability optimization method based on ant colony algorithm
CN107609717A (en) A kind of model transfer amount Forecasting Methodology based on Kalman filter in social networks
CN112733438A (en) Sponge city planning model parameter optimization method based on ant colony algorithm
CN113409576B (en) Bayesian network-based traffic network dynamic prediction method and system
CN105045967A (en) Group degree based sorting method and model evolution method for important nodes on complex network
CN113393051A (en) Power distribution network investment decision method based on deep migration learning
CN114298270A (en) Pollutant concentration prediction method fusing domain knowledge and related equipment thereof

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20210430

RJ01 Rejection of invention patent application after publication