In order to solve some function optimization problems, Population Dynamics optimizationalgorithm under Microbial Control in Contaminated Environment (PDO-MCCE) is proposed by adopting a population dynamics model with...
详细信息
In order to solve some function optimization problems, Population Dynamics optimizationalgorithm under Microbial Control in Contaminated Environment (PDO-MCCE) is proposed by adopting a population dynamics model with microbial treatment in a polluted environment. In this algorithm, individuals are automatically divided into normal populations and mutant populations. The number of individuals in each category is automatically calculated and adjusted according to the population dynamics model, it solves the problem of artificially determining the number of individuals. There are 7 operators in the algorithm, they realize the information exchange between individuals the information exchange within and between populations, the information diffusion of strong individuals and the transmission of environmental information are realized to individuals, the number of individuals are increased or decreased to ensure that the algorithm has global convergence. The periodic increase of the number of individuals in the mutant population can greatly increase the probability of the search jumping out of the local optimal solution trap. In the iterative calculation, the algorithm only deals with 3/500 similar to 1/10 of the number of individual features at a time, the time complexity is reduced greatly. In order to assess the scalability, efficiency and robustness of the proposed algorithm, the experiments have been carried out on realistic, synthetic and random benchmarks with different dimensions. The test case shows that the PDO-MCCE algorithm has better performance and is suitable for solving some optimization problems with higher dimensions.
In this study, the K feedback gain vector parameters that are used for the control of three degree of freedom four rotor quadcopter system (3 DOF Hover) are optimized with the Enhanced Equilibrium optimization Algorit...
详细信息
ISBN:
(纸本)9780791885437
In this study, the K feedback gain vector parameters that are used for the control of three degree of freedom four rotor quadcopter system (3 DOF Hover) are optimized with the Enhanced Equilibrium optimizationalgorithm ((EO)-O-2). The (EO)-O-2 algorithm is proposed with using parameters obtained from fractional order chaotic oscillator models instead of random variables. The Basic EO algorithm is inspired by volume- mass balance. In EO algorithm, each particle is called a motion that searches a parameter vector space. However, random coefficients derived from uniform distribution are used in the parameters updating process or in the generation of the initial population. The (EO)-O-2 algorithm was proposed by using vectors obtained from fractional order chaotic oscillators instead of stochastic coefficients in the basic Equilibrium optimizationalgorithm. Genesio Tesi, Rossler, Lotka Volterra fractional-order chaotic oscillator models were used in the (EO)-O-2 algorithm to optimize K feedback gain vector of 3 DOF Hover. The order and initial conditions the fractional chaotic oscillator models were experimentally adjusted for the control of 3 DOF problem. Thus, suitable fractional-order chaotic models for the problem were obtained. The (EO)-O-2 algorithm results are compared with the Stochastic Multi Parameter optimization (SMDO) and Discreet Stochastic optimization (DSO) algorithms for the system's pitch, roll and yaw angles.
The application of swarmoptimizationalgorithm in WSNs has become a new research hotspot of scholars at home and abroad. Aiming at the problem that the spotted hyena optimizationalgorithm is easy to fall into local ...
详细信息
ISBN:
(纸本)9781450396899
The application of swarmoptimizationalgorithm in WSNs has become a new research hotspot of scholars at home and abroad. Aiming at the problem that the spotted hyena optimizationalgorithm is easy to fall into local optimum, which leads to low optimization accuracy, an improved spotted hyena optimizationalgorithm is proposed. On the basis of the original algorithm, Sine chaotic map and elite reverse learning strategy are embedded to reduce the probability of falling into local optimum and improve the global search ability of spotted hyena optimizationalgorithm. In addition, the adaptive inertia weight is introduced to balance the global search and local development capabilities of the spotted hyena optimizationalgorithm. The experimental results show that compared with the original spotted hyena optimizationalgorithm, sine and cosine algorithm, multiverse optimizationalgorithm, differential evolution algorithm and particle swarmoptimizationalgorithm, the improved algorithm has significant performance advantages in optimization ability and stability.
This study proposed and compared several novel hybrid models that combined swarmintelligencealgorithms and Deep Learning Neural Network for flood susceptibility mapping. Lai Chau, a province in the northwest mountai...
详细信息
This study proposed and compared several novel hybrid models that combined swarmintelligencealgorithms and Deep Learning Neural Network for flood susceptibility mapping. Lai Chau, a province in the northwest mountainous region of Vietnam was chosen as a case study since it had recently undergone severe flashflood in 2018. For this purpose, numerical predictor variables such as topographically derived factors (Digital Elevation Model, Aspect, Slope, Curvature, Topographic Wetness Index), climatic variables (Rain), and hydrological variables (stream density, stream power index, distance to river) and multiple remote sensing indices (Normalized Difference Vegetation Index, Normalized Difference Buildup Index) were used. These predictor variables were selected because they are globally collectible and reproducible. The performances of these models were evaluated by using common statistical indicators, namely Root Mean Square Error, Mean Absolute Error, Overall Accuracy and Area under Receiving Operating Characteristics, and the statistical test of differences. The results showed that the proposed swarmintelligence models outperformed benchmarked methods, namely Particle swarmoptimization, Support Vector Machine, Random Forest in almost all comparing indicators. It is suggested that proposed models are more robust than the classifiers, which were used for benchmarking and they are good alternatives for flood susceptibility mapping given the availability of dataset.
After studying the migratory and foraging behavior of flamingos, this paper proposes a new swarm intelligence optimization algorithm: flamingos search algorithm. At the same time, in order to verify the optimization e...
详细信息
ISBN:
(纸本)9781450384087
After studying the migratory and foraging behavior of flamingos, this paper proposes a new swarm intelligence optimization algorithm: flamingos search algorithm. At the same time, in order to verify the optimization effect and stability of FSA, this paper conducts tests and comparisons on 20 different benchmark functions, and standard deviation of the proposed FSA outperformed the other algorithms with regard to 20 test functions and path planning applications. Finally, this paper applies FSA to the path optimization problem, and the test results show that FSA has good engineering application potential, especially in the solution of path planning problems with good optimization performance. Experimental code for this article can be obtained from this website: https://***/18280426650/FSA.
Target assignment for unmanned aerial vehicle (UAV) swarm has been a research hotspot in academic and industry communities. The current methods mainly focus on multiple targets assignment in planes or few targets assi...
详细信息
Target assignment for unmanned aerial vehicle (UAV) swarm has been a research hotspot in academic and industry communities. The current methods mainly focus on multiple targets assignment in planes or few targets assignment in solids. However, they ignore three-dimensional scenarios for UAV swarm and multiple targets characteristics for assignment problem. To solve these issues, we propose a multi-target intelligent assignment model. Firstly, we introduce damage cost and time cost to evaluate the system performance of swarm and time performance in three-dimensional scenarios. Then, we design a bio-inspired swarm intelligence optimization algorithm to find the optimal multiple targets assignment and to balance the two costs and multiple constraints simultaneously. This algorithm regards UAVs as several parallel biological sub-populations, which adopts the multi-layered optimization strategy to select the suitable assignment sequence. The simulation results demonstrate that the proposed method is effective for multi-target assignment in three-dimensional scenarios.
Wind energy is an increasing concern for wind farm administrators. Effective wind energy potential analysis and accurate forecasting can reduce the operating cost of wind farms. However, many previous studies have bee...
详细信息
Wind energy is an increasing concern for wind farm administrators. Effective wind energy potential analysis and accurate forecasting can reduce the operating cost of wind farms. However, many previous studies have been restricted to analyses of wind energy potential analysis and wind speed forecasting, which may result in poor decisions and inaccurate power scheduling for wind farms. This study develops a wind energy decision system based on swarmintelligenceoptimization and data preprocessing, which includes two modules: wind energy potential analysis and wind speed forecasting. In the wind energy potential analysis module, the parameters of the Weibull distribution are optimized by a multiple swarm intelligence optimization algorithm, which can provide better wind energy assessment results. In the wind speed forecasting module, the data preprocessing method can effectively eliminate the noise of the original wind speed time series, maintain the characteristics of the wind speed data, and improve the accuracy of the forecasting model. The numerical results show that the wind energy decision system not only provides an effective wind energy assessment, but can also satisfactorily approximate the actual wind speed forecasting. Therefore, it can serve as an effective tool for wind farm management and decision-making. (C) 2018 Published by Elsevier Ltd.
Mine water inrush is one of the most threatening natural disasters in the process of mine construction and production. Once mine water inrush occurs, how to quickly determine the cause of water inrush and find out the...
详细信息
Mine water inrush is one of the most threatening natural disasters in the process of mine construction and production. Once mine water inrush occurs, how to quickly determine the cause of water inrush and find out the source of water inrush is the key to solve and further prevent the water inrush disaster. Because hydrochemical data is the most essential feature of groundwater, it is fast, accurate and economical to discriminate the source of mine water inrush from water quality data. Starting from the frontier disciplines of artificial intelligence, bionics, chaos theory, mathematical statistics and computer programming language, BP neural network with nonlinear mapping function was introduced into the discrimination of groundwater hydration characteristic components. At the same time, particle swarmoptimization（PSO） intelligent optimizationalgorithm was used to globally optimize the initial weight and threshold of neural network, it could improve the convergence speed, avoid over-fitting and improve the generalization of neural network in the training process of neural network. In order to overcome the "premature" convergence of PSO, an improved particle swarmoptimizationalgorithm（MPSO） was proposed by improving the parameters of inertia weight, cognitive coefficient and social coefficient, random mutation operator and so on. Adaptive chaotic particle swarmoptimization（ACPSO） was proposed by introducing the "premature" judgment mechanism and chaotic mapping principle into PSO. MATLAB software was used to design and compile the program, four kinds of nonlinear water inrush source discrimination models, BP, PSO-BP, MPSO-BP and ACSO-BP, were constructed. The application results show that the neural network based on swarmintelligenceoptimization improves the discrimination accuracy of mine water inrush source, but compared with each other, ACPSO-BP is better than MPSO-B, MPSO-BP is better than PSO-BP, PSO-B is better than BP in convergence speed, accuracy and g
Inversion of geophysical logging data is one of the most important tasks in oil and gas exploration. Ambiguity is usually inherent for the solutions, especially for formation with complex lithology. The optimum log in...
详细信息
ISBN:
(纸本)9781509040933
Inversion of geophysical logging data is one of the most important tasks in oil and gas exploration. Ambiguity is usually inherent for the solutions, especially for formation with complex lithology. The optimum log interpretation technique can effectively reduce the ambiguity of the interpretation results. Therefore, the Glowworm swarmoptimization (GSO), one of the swarm intelligence optimization algorithms, is introduced into the log interpretation to obtain the optimal solution by virtue of its strong ability both in local and global optimization. Moreover, in order to solve the problem of slow convergence speed in the later iteration process, adaptive step is integrated into glowworm swarmoptimization to form the Variation Step Adaptive Glowworm swarmoptimization (VSAGSO) algorithm, which improves the accuracy and efficiency of optimizing. VSAGSO algorithm is applied for test in the tuffaceous sandstone reservoir in a certain oilfield. Comprehensively considering all kinds of errors and constraints, it could directly working-out the optimized results of reservoir parameters such as tuff content, shale content, skeleton mineral content and porosity in well accordance with the core data.
暂无评论