artificial bee colony algorithm

Estimation  of  the  load  carrying  capacity  of  pile  foundation  is  one  of  the  most  sought  after  research  areas  in geotechnical   engineering.   Static   equilibrium   and   other dynamic equations are used to predict  the  axial  load  capacity  of  pile.  The  prediction  of lateral  load  capacity  of  piles,  used  in  tall  and  offshore structures is more complex and requires solution of non-linear differential equations. The elastic analysis adopting Winkler   soil   model is   not suitable for the non-linear soil behavior.  Estimating the load capacity of such piles using experimental methods is always associated with error and makes the modeling result far from reality. Today, intelligent methods have shown a high capability in predicting and estimating unknown variables and can replace experimental and analytical methods. In this research, we tried to accurately predict the lateral load capacity of piles in clay soils by creating an intelligent hybrid model called optimized relevant vector regression with the artificial bee colony algorithm. The relevant vector regression is a probabilistic method based on Bayesian approach. The relevant vector regression does not need to predict the error/margin tradeoff parameter C, which can decrease the time and the kernel function, does not need to satisfy the Mercer condition. For those relevant vector regression advantages compared with the support vector regression approach, relevant vector regression model is successfully applied in regression prediction problems. In this method, relevant vector regression is used as a predictive model and artificial bee colony algorithm is used to optimize the parameters of relevant vector regression method. The artificial bee colony algorithm is a swarm based meta-heuristic algorithm for optimizing numerical problems. It was inspired by the intelligent foraging behavior of honey bees. The algorithm is specifically based on the model for the foraging behavior of honey bee colonies. The model consists of three essential components: employed and unemployed foraging bees, and food sources. The first two components, employed and unemployed foraging bees, search for rich food sources, which is the third component, close to their hive. The model also defines two leading modes of behavior which are necessary for self-organizing and collective intelligence: recruitment of foragers to rich food sources resulting in positive feedback and abandonment of poor sources by foragers causing negative feedback.  In artificial bee colony, a colony of artificial forager bees (agents) search for rich artificial food sources (good solutions for a given problem). To apply artificial bee colony, the considered optimization problem is first converted to the problem of finding the best parameter vector which minimizes an objective function. Then, the artificial bees randomly discover a population of initial solution vectors and then iteratively improve them by employing the strategies: moving towards better solutions by means of a neighbor search mechanism while abandoning poor solutions.In this modeling, the data used are related to a laboratory data set of small-scale pile load capacity. Various statistical indicators were used to evaluate the modeling accuracy. Finally, the results showed that the combined relevant vector regression with the artificial bee colony algorithm for test data with R2 = 0.975 and RMSE = 0.001, has a high ability to predict the lateral load capacity of spark plugs. In addition, the sensitivity analysis performed in this study showed that the variables of eccentricity of load and the length of pile are more important and effective compared to other parameters.

In recent years, the damage identification of structures becomes more attractive for researchers in order to assess ‎the quantify condition of structural system during service life. Moreover, identifying the damage location and ‎severity is very important after disaster such as earthquake and terrorist attak. Structures can be also damaged by ‎normal activity such as corrosion, aging, fatique, wind, waveload etc. Therefore the structural health monitoring is ‎an emerging field to ensure the continues and periodic performance of structures. In this paper, identification of the ‎extent and location of damages in structures are studied by analytical method using artificial bee colony ‎optimization (ABC). In the analytical method, the mass and stiffness matrices of structure could be determine by ‎the finite element procedure. Considering the stiffness matrix of healthy structure and that of the damage structure, ‎the location and severity of the damage could be determined. It is assumed that the global mass matrix remains ‎unchanged after the damage occures in the structure. The natural frequencies and mode shapes of damaged ‎structure can be obtained by measurement. In the study, the damage characteristics are known. Then by applying ‎the eigenvalue equation, the stiffness matrix is determined for damaged structure. Finding the extent and location ‎of damage is introduced as an inverse problem. Using the conventional methods are very expensive and time ‎consuming, while metaheuristic evolutionary computing method is capable to solve complex combinational ‎optimization problems. Swarm intelligence algorithm introduces the collactive behavior of social insects colonies ‎to solve optimization problems. Artificial bee colony algoritm is an evolutionary computing method, which is ‎developed, based on the intelligent foraging behavior of honeybee swarm. Each food source is considered as a ‎possible solution. The location and quality of the nectar from the flower is related to the damage properties and ‎fitness function, respectively. The dimension of every artificial employed bee is equal to the number of member of ‎the structure. Then quality value of the food source is evaluated by the fitness function. The best fitness value is ‎memorized in each search. When the fitness value denote improved after a predefined iterative, the new possible ‎solution will be considered. In the ABC process, the number of food source, the limit and the maximum cycle ‎number are three control parameters. In the optimization problem, applying a proper objective function is one of ‎the indispesable part of the process. Since the structural damage detection is a highly nonlinear problem, a proper ‎objective function can detect the damage accurately and quackly. There are various methods for damage detection, ‎which generaly can be classified into two categories, static and dynamic method. Because of the efficiency of the ‎dynamic method, the objective function is selected based on the dynamic technique, which utilize the eigenvalue ‎problem. In the mathematical equation of the objective function, the mass and stiffness matrix of healthy structure ‎is defined by finite element method. The natural frequencies and mode shapes obtained by the measurement. The ‎stiffness matrix of damaged structure is determined with the optimization algorithm to minimize the objective ‎function. In a measurement test, the used sensors cannot detect all of the degrees freedom of a structure, therefore ‎the obtained information in measurement include a limited number of frequencies or mode shapes. In addition, to ‎avoid a time consuming process, it may be decided to utilize only a limit number of frequencies obtained by the ‎measurement. The system equivalent reduction expansion process (SEREP), which is an accurate and efficient ‎technique of model reduction, is utilized in the paper. Moreover, the damage detection is examined through three ‎numerical examples, plane and space truss and palne frame, each one has two damage scenarios, which include ‎noisy measurement data. The results indicate that the proposed method is a powerfull procedure to detect damages ‎in structures.‎

In the design of seismically base-isolated structures, it is expected that the isolator will experience nonlinear behavior while the superstructure still behaves linearly. Therefore for modeling these systems, a linear behavior is assumed for superstructure and different nonlinear models are used for isolator. But there are special conditions such as strong ground motions in which superstructure behave nonlinearly. In this study, the nonlinear behavior of seismically base-isolated structures is more accurately investigated. This is done using nonlinear time history analysis of structures using ground motions. Two sets of ground motions are selected which represent earthquakes with 475 and 2475 years return period. OpenSees software is used for modeling these structures. The effective parameters on the response of seismically base isolated structure which are investigated are: response modification factor of the superstructure, stiffness of the isolator, damping ratio of the isolator, stiffness of the superstructure and damping ratio of the superstructure. Studies of this paper are divided into two parts. In the first part, two-degree freedom model with viscoelastic isolator has been used to investigate the effect of superstructure nonlinearity. Also a sensitivity analysis is done to find important parameters which have more effects on the systems response. Results of this part show that, nonlinear behavior of superstructure increases system ductility demand drastically. It is concluded that the period of isolator and superstructure have the most effect on the ductility demand. In the second part, the effect of different parameters and higher mode effects on the response of seismically base-isolated structures is investigated using muti-degree of freedom models sited on isolator with bilinear behavior. Results obtained in this part also confirm the increase in the response of the system when the superstructure has low strength. Likewise in this condition, the isolator deformation decreases. Distribution of ductility demand in the height of structure is also non-uniform in this condition and lower stories are more vulnerable. Isolators with a lower fundamental period and also isolators with a lower yield force lead to the least amount of isolator deformation and ductility demand of superstructure. By increasing damping in the isolator, ductility demand of superstructure will increase. A stiffer superstructure with nonlinear behavior has a much more ductility demand rather than similar structure which is more flexible. But when the superstructure behaves linearly, the fundamental period of superstructure and isolator deformation increase or decrease together. Finally, due to the intensive increase in the ductility demand of the superstructure when it behaves nonlinearly, a solution is proposed with the aim of simultaneous optimization of the superstructure and isolator systems. This strategy uses a combination of uniform ductility theory and a modified artificial bee colony algorithm. By applying this method and using ductilities of superstructure and isolator simultaneously, it is possible to obtain the desirable ductility in the isolator, in addition to achieve a more economical choice for the superstructure. If there is no constraint around the structure for movement, by increasing the target ductility of the superstructure, the weight of the superstructure can be reduced by reducing its yield force.

The development of effective decision support tools that can be adopted in the transportation industry is vital since it can lead to substantial cost reduction and efficient resource consumption. However, vehicles moving on our roads contribute to congestion, noise¡ pollution, and accidents. So route planning and transport management, using optimization tools, can help reduce transport costs by cutting mileage and improving driver and vehicle usage. In addition, it can improve customer service, cut carbon emissions, improve strategic decision making and reduce administration costs.
Due to the simultaneous pick-up and delivery postal service and delivery time importance of those parcels, this study focuses on the pick-up and delivery problems. The pick-up and delivery problems are important types of vehicle routing problem (VRP). VRP is the core of scientific research on the distribution and transport of people and goods. Unlike the classical VRP, in which all customers require the same services, in the pick-up and delivery problem basic it is considered that two different types of services can be found in one place, in fact there's a pick up or delivery. PDP has several applications in the transportation of pick-up and delivery parcel post. The purpose of this research is to find the most optimal route to transport postal service. It is performed by imposing a series of conditions to the pick-up and delivery problems using meta-heuristic algorithms for the simulation data. It is followed by brief explanation of present metaheuristic algorithms including bee colony algorithm and genetic algorithms and their features. Finally the results of the algorithms are compared on the basis of the accuracy, repeatability, speed of convergence. It is necessary to note that the results are not ideal, but the best case is considered. The results showed the performance of the bee algorithm are better than genetic. Based on the results obtained in each run, genetic algorithms and Bee were 84% and 93% are possible to achieve the best solution.

Unmanned aerial systems (UAS) are one of the latest technologies utilized in the hazard management and remote sensing. Nowadays, tendency in the development of UAS is toward autonomous navigation or hybrid tasks. In this context, development of comprehensive, efficient methodologies for path planning, control and navigation of UAS can be regarded as one of the fundamental steps for the development of autonomous systems. Up to now, different planning algorithms have been proposed in the specialized literature in order to enrich the framework of autonomous navigation of unmanned aerial systems. However, few efforts have been devoted to design new chaotic path planners for determining the optimal trajectories of these aerial systems in urban areas. An effective path planning technique can attain mission aims with respect to various restrictions of the UAS and less computational time.Chaos theory is one of the most studied theories with different applications in engineering and technology. Most of the natural processes demonstrate chaotic behavior such as black hole and clouds. Past researchers showed that if an evolutionary algorithm be hybridized with chaos, its performance will have improved, considerably. However, most of the evolutionary algorithms are inspired from nature, but all of their steps are random based motions. But nature is not either completely random based or chaotic. Hence, the combination of these theories should be more realistic. With this regard, evolution and chaos are related to each other narrowly in most of the complex natural systems. It is evidenced that some of the chaotic signals can alleviate the premature convergence problem of the evolutionary algorithms in tackling optimization problems.In this article, first, UAS path planning is modeled as a 3D constrained optimization problem. In this modeling, the aim is the optimization of path, fuel and safety with respect to different restrictions. After scheming and suggesting of general planning framework, UAS path planning problem is investigated by comparative study with regard to the studied scenario. For this aim, evolutionary planner is implemented in order to minimize the flight height, path length and energy consumption considering different restrictions such as safe altitude, turning angle, climbing slope, gliding slope, no fly zones and mission map limits. Then, a comprehensive model is employed to describe route-planning task, and then, based on the hybridization of chaos theory with evolutionary computing, four new evolutionary optimizers are developed. Hence, this paper developed four chaotic optimizers including particle swarm optimization, differential evolution, imperialist competitive algorithm and artificial bee colony technique based on 14 chaotic signals.In the rest of this paper, analyses, and extensive performance evaluation of the designed trajectory-planning approaches are performed according to the success rate results, precision and quality of the results, CPU running times, and convergence speed. The results show that the proposed framework can be utilized in represented scenario as an effective path planner. Proposed strategies are capable to compute the optimal paths more efficiently in comparison with the standard algorithms. From the results it is known that the chaotic differential evolution with logistic map can outperform the other compared algorithms.