Abstract:

Abstract:

Abstract:

Abstract: The core idea of swarmintelligence (swarmintelligence) is that several simple individuals form a group, through cooperation, competition, interaction and learning mechanisms to show advanced and complex functions, in the absence of local information and models, still able to complete the solution of complex problems.The solution process is to initialize the variable randomly, and calculate the output value of the objective function after iterative solution.Swarm intelligent optimization algorithm is not dependent on gradient information, and it is not continuous and derivable to solve problems, which makes it suitable for both continuous numerical optimization and discrete combinational optimization.At the same time, the potential parallelism and distributed characteristics of swarm intelligence optimization algorithm make it have significant advantages in dealing with big data.

Abstract: As an evolutionary computation (EC) technique, Genetic programming (GP) has been widely applied to image analysis in recent decades. However, there was no comprehensive and systematic literature review in this area. To provide guidelines for the state-of-the-art research, this paper presented a survey of the literature in recent years on GP for image analysis, including feature extraction, image classification, edge detection, and image segmentation. In addition, this paper summarised the current issues and challenges, such as computationally expensive, generalisation ability and transfer learning, on GP forimage analysis, and pointd out promising research directions for future work.

Abstract: A new swam intelligent optimization algorithm named Whale Swarm Algorithm (WSA) was studied. The principle and essential procedures of WSA were introduced, and the characteristics of WSA were presented through comparison with other classical swam intelligent optimization algorithms. For multimodal optimization, the iteration rule of WSA was improved, two parameters namely stability threshold and fitness threshold are introduced, and thus WSA with Iterative Counter (WSA-IC) was developed. The experimental results demonstrate that WSA-IC showed good performance in terms of the number and quality of optimal solutions and convergence speed. Then WSA-IC was applied to the steelmaking continuous casting scheduling problem, and proved to have good optimization ability and strong stability through the experiments. Finally, with the above research results, it was summarized that WSA has much value in practice, and further research of WSA can be carried out in theoretical study and practical application.

Abstract: Constrained optimization algorithm adopted the similav evolutionary strategy to deal with solutions located on the Pareto edge and solutions with poor function values, which could lead to poor search results. Aiming to solve this problem, a constrained optimization algorithm with teo-stage and three-archive was proposed. The algorithm was divided into two stages. In the first stage, the population was divided into three archives according to the £(t) value. These archives were non-dominated solution archives, dominant solution archives, and non-dominated feasible solution archives, respectively. The dual optimization of hybird strtegy is applied to the non-dominated  solution archives. It could not only aviod being trapped in local optimum, but also accelerate the convergence of solutions near the frontier. The dominant solution archives focused on the global search, which was benefical for the algorithm to search better feasible solution. The non-dominated solution archives and the dominant solution archives were evolved using different optimization strategies to improve the optimization capability of algorithm. In the second stage, non-dominated sorting was performed on individuals when the first stage reached the certain generation. These individuals were concentrated from each generation to the non-dominated feasible solution archives. The selected N individuals were the optimal solution. Finally, the proposed algorithm was compared with other constrained multi-objective evolutionary algorithms on the three classical constraint test functions. The simulation results showed that the proposed algorithm had advantages in different kind of constraints.

Abstract: A multi-swarm Artificial Bee Colony（MABC）algorithm based on the segmentation of population was proposed in this paper. It was applied to function optimization to overcome the drawbacks of slow convergence and low computational accuracy of conventional ABC algorithm.  In this algorithm， K-means clustering algorithm based on Euclidean distance was introduced to divide the bee colony. In the subpopulation,  a method was introduced to update the location of nectar based on global communication to accelerate the convergence of the algorithm;and the fitness function based on local communication was introduced to expand the diversity of the solution. The simulation results of six standard functions show that the MABC algorithm can attain significant improvement on convergence rate and solution accuracy， and show better performance in function optimization problems when compared with the ABC algorithm.

Abstract: There were some problems in the Artificial Bee Colony (ABC) algorithm, such as the slow convergence speed, low solution precision and easy to fall in local optimum. Inspired by particle swarm optimization algorithm, multi-elitist artificial bee colony algorithm for real-parameter optimization use of global best solution and an elitist randomly selected from the elitist set were adopted to enhance the exploitation of the global best solution. In this paper, we the elitist to guide the nectar search during the employed bee process was introduced. And the selection probability formula of food source was reconstructed by using the quality of food source. In the onlooker bee stage, the best food source was selected to guide the swarm to enhance the exploitation of the global best solution, and the and the neighbor food source was selected to be the optimally directional choice. As the same time, a simplex method was used on elitist solution set to balance the exploration and exploitation ability of the algorithm. The numerical experiment results showed that the proposed algorithm had higher searching precision and faster convergence speed.

Abstract: Aiming at the low efficiency and easy trap into local optimum for the basic krill herd algorithm, a new quantum behave krill herd algorithm was proposed. It was named as cooperative evolution quantum krill herd algorithm (CEQKHA) based on cooperative evolution and quantum computation. The population could be divided into two parts, such as main population and sub-population, which could evolve independently and exchange fine individuals. The position of krill herd could be updated by using quantum activity. The best position of krill herd could be set as the center of potential well of delta potential well, and the position of krill herd in the different population can evolve in different way. The convergence of the algorithm was also deduced. Simulation of benchmark functions proved that CEQKHA could get better results and perform well than other algorithms

Abstract: Aiming at the optimization of the energy in microgrid, a bi-objective optimization model for economic and environmental operations of the microgrid systems was proposed. Then this model was assessed based on the evaluation results of the dispatching system. To be specific, in order to optimize this model, a novel multi-objective artificial bee colony algorithm called ICABC was decised, based on crowding-distance with performance indicators. This algorithm incorporated an external archive (EA) to preserve non-dominated solutions; and a novel crowding-distance method called DICC was used to maintain the diversity of solutions. DICC was essentially a updated version of traditional crowding-distance strategy in NSGA-II. It amied to avoid the removal of elite individuals in dense areas effectively while enhance the diversity of obtained non-dominated solutions, With rigor expermental evaluations on a set of benchmark problems, it showed that ICABC had more powerful performance compared with NSCA-II and MOCLPSO. Then, ICABC was applied to resolve the proposed model for dynamic dispatching of microgrid with muliple distributed generations. Simulation results exhibited that the proposed method and model effectively reduced the total system cost by rationally arranging the output of the distributed generations.

Abstract:

An Improved General Particle Swarm Optimization (IGPSO) algorithm was proposed for process planning problem based on the GPSO model and the characteristics of procwss planning problem. Crossover operations were utilized to achieve the particles to obtain updated information from individual extreme library and population extreme library. Variable Neighborhood Search was intaoduced as a local search strategy for particles. A set of instances have been conducted to examine the proposed algorithm and the comparisons among other algorithms appeared in current literature were also presented. The experimental results showed the proposed algorithm had higher efficiency and better stability in solving process planning problems.

undefined

Abstract: Activated carbon (AC) prepared from residue of desilicated rice husk (DRH) was investigated for the removal of antibiotic enrofloxacin (ENR) from aqueous solution. The operating variables including contact time, adsorbent dosage, ENR concentration and solution pH were optimized using central composite design (CCD) under response surface methodology (RSM) approach. The better conditions for ENR adsorption were found out to be 355.3 min contact time, 0.40·g L-1 adsorbent dosage, 350.0 mg·L-1 ENR concentration, pH 7.69 with predicted adsorption uptake of 429.4 mg·g-1. The experimental equilibrium data agreed well with the Langmuir adsorption model and Koble-Corrigan model. The maximum monolayer adsorption capacity of AC was found to be 444.2 mg·g-1 at 298K. This study indicated that AC based on DRH was a promising candidate because of the lower cost and larger adsorption capacity for the removal of ENR from aqueous solution.

Abstract: Mass transfer passage was used inside the packed bed of enchance steam generation efficiency in a novel adsorption heat pump by utilizing a direct-contact heat exchange method. Ratios of the passage to inner diameter of the packed bed were 10% and 20%. Experimental results from 10% passage showed that the maximum generated steam temperature reached 236℃, which increased by 23ºc compared to that without passage. Meanwhile the mass of steam mass increased by 26%, mass ratio of steam to dry zeolite(m_s,_out/mz) increased by 14%, and steam generation time increased by 1.8%. Experimental results from 20% passage showed that the maximum steam temperature only increased by 11ºc; steam mass increased by 5.6%, m_s,_out/mzn was almost unchanged; steam generation time increased by 25.3%. Superheated steam generation rate was faster for large passage, while the maximum temperature and mass of generated steam were higher for small passage.

Abstract: Three periodic models with different installation angles of the blade baffle heat exchanger were established by the CFD analysis software Fluent. The installion angles were 30°, 45°, 60°, respectively. And the performance of heat exchanger with different installation angles was investigated. Results showed that in the diversion of the baffle, the shell-side flow became sideling flow, which could restrain the flow induced vibration effectively. The velocity of the fluid in the near wall region was higher than that of the central region. With the increase of the installation angle, the shell-side pressure drop decreased, the comprehensive performance of the heat transfer coefficient of the exchanger increased. When the installation angle was 30° the heat transfer coefficient was larger than the other two.

Abstract: In this study, the adsorption capacity of modified grapefruit peel to ciprofloxacin hydrochloride (CIP) was investigated in the fixed-bed column technique. The effects of initial  CIP ciprofloxacin, flow rate, and column height on the breakthrough characteristics of the adsorption system were studied. With the increase of adsorption column height or decrease of initial concentration and flow rate, the breakthrough time were increased. The Thomas model was applied to the experimental data to determine the characteristic parameters of the column that were useful for process design.The R² of Thomas model was more than 0.9500 and the experimental values q_exp was similar to theoretical values q_e. It was indicated that Thomas model is suitable for describe the dynamic adsorption. The bed depth service time( BDST) model was applied to predict the breakthrough time and saturated time under different conditions. The results showed that BDST model could predict breakthrough time accurately and maximum error were less than 1.32%. The theoretical breakthrough curve according to mass transfer model was accordance with experimental breakthrough curve in the column process.

Abstract: The surface morphology and the different mechanical properties between crystalline region and amorphous region of the stereocomplex crystal were studied in this paper. The same mass ratio of Poly (L-lactic acid) (PLLA) and poly (D-lactic acid) (PDLA) stereocomplex was prepared by solution blending. Differential Scanning Calorimetry, Polarizing Microscope, Atomic Force Microscopy, Confocal Laser Scanning Microscope and Nano Indentation Tester were used to list the surface morpholigy of PLA stereocomplex crystal and the diversification of mechanical properties. The result showed  that a high degree of stereo-tacticity of PLLA/PDLA blend could be achieved from the mass ratio of 1/1 for sample.The research also showed that obviously depression phenomenon on the surface of crystal was formed due to the contraction of the molecular chain. Furthermore, the hardness and modulus of crystalline region were improved compared to the amorphous region.

Abstract: This paper focused on the problem on the problem of MPPT control for PV arrays. Under the solar irradiance levels from 0 to 1200W/m² and the ambient temperatures from 0 to 100ºC. The short circuit and open circuit voltage of PV array have been measured using PSCAD/EMTDC software. And the result showed that in the condition of constant temperature, the open circuit voltage and short circuit current increased with the increase of illumination intensity; in the condition of constant light intensity, the open circuit voltage decreased and the short-circult current increased with the increase of temperature. The hysteresis loop was used to generate the control pulse. The MPPT control method based on conductance increment method has been improved from the two aspects of tracking speed and accuracy. A simulation model of system was built to achieve MPPT control. Finally, the experimental result showed that the maximum output power of the PV array increased with the increase of illumination intensity.

Abstract: This study aimed to study of forearm movement direction based on non-invasive brain machine interface technology. An autonomic movement expermental paradigm and was desighed, the EEG (electroencephalograph) signal of two stages of autonomous motion planning and execution was anaused. Method that combines the WPD (wavelet packet decomposition) and CSP (common spatial patterns) was used to extract characteristics. The SVM (support vector machine) was further used to classify multidimensional characteristics. Experiment on subjects withness the average 80% accuracy of three classifications (left, right and static) .The results showed that the combined method could effectively resolve direction information of EEG.