In order to improve the modeling efficiency of RBF neural network, an Artificial Fish Swarm Algorithm (AFSA) training algorithm with an adaptive mechanism is proposed. In the training algorithm, the search step size and visible domain of AFSA algorithm can be adjusted dynamically according to the convergence characteristics of artificial fish swarm, and then the improved AFSA algorithm is used to optimize the parameters of RBF neural network. The example shows that, the proposed model is a better approximation performance for the nonlinear function.

Staircases in Reinforced Concrete (RC) frame structures suffered severe damages in recent earthquakes although they are regarded as critically important passages during emergencies. Staircases act as the first line of defense in earthquakes, and therefore they first yield and fail. Then they lose the action of safe passages so that the anticipated seismic performance objectives cannot be satisfied. To make sure that staircases work as safe passages in strong earthquakes, the current Chinese code for seismic design of buildings claims special requirements on the design of staircases. At first, the influence of staircases on the structural behavior of a typical RC frame structure is studied by the comparison of internal force in the structural members considering and neglecting the effect of staircases under frequent earthquakes. Besides, the effect of staircases on the yielding and failing mechanism of the frame structure is investigated through static elasto-plastic analyses. From this study the reason of the damages suffered by cast-in-site staircases in RC frame structures under earthquakes can be understood.

Temporal distribution phytoplankton community structure in a shallow lake, Lake Taihu, China, was investigated from 2010 to 2011 on a monthly basis at 9 sampling stations. The results showed that phytoplankton communities primarily consist of cyanobacteria, chlorophyta and bacillariophyta in Lake Taihu. A significant change in phytoplankton community was observed in both years: cyanobacteria hold an overwhelming dominance in summer and autumn, chloraphyta and bacillariophyta occupied the certain proportion only when the cyanobacterial bloom was declined in winter and early spring. The maximum abundance value of cyanobacteria, chlorophyta and bacillariophyta appeared at June, 2010, July, 2011 and Feb, 2011, respectively. The present study is a continuation and complement in long-term research of Lake Taihu, which provides scientific foundation for further research of the lake.

To improve the optimization design of Radial Basis Function (RBF) neural network, a RBF neural network based on a hybrid Genetic Algorithm (GA) is proposed. First the hierarchical structure and adaptive crossover probability is introduced into the traditional GA algorithm for the improvement, and then the hybrid GA algorithm is used to optimize the structure and parameters of the network. The simulation indicates that the proposed model has a good modeling performance.

For the aerodynamic modeling problem from measured flight data for aircraft stall, a WNN aerodynamic modeling method is proposed. According to the aerodynamic modeling flow from flight data for aircraft stall, WNN is introduced to establish the aerodynamic model of aircraft for stall phenomenon. Experiment shows that the method can improve the modeling ability of WNN, and is suitable for actual aerodynamic modeling for aircraft stall.