Papers by Author: Wei Gao

Abstract: The flow in a single-stage fan is analyzed through numerical simulation. The results indicate that there exists a best prewhirl angle which can make flow loss minimal at a given flow rate. So we can improve the internal flow field structure by changing the prewhirl angle, thus the fan efficiency can be raised. In addition, the flow separation on the suction surface is sensitive to the variation of the prewhirl angle. The range of the separation on suction surface increases with the decrease of the prewhirl angle, and expands to the central area of the blades.

Abstract: Ant Colony Algorithm is a new bionics optimization algorithm from mimic the swarm intelligence of ant colony behavior. And it is a very good combination optimization method. To extend the ant colony algorithm, and to improve the searching performance, from the connections of continuous optimization and searching process of ant colony algorithm, one new Continuous Ant Colony Algorithm is proposed. To verify the new algorithm, the typical functions, such as Schaffer function and “Needle-in-a-haystack” function, are all used. And then, the results of new algorithm are compared with that of immunized evolutionary programming proposed by author.

Abstract: The evolutionary neural network can be generated combining the evolutionary optimization algorithm and neural network. Based on analysis of shortcomings of previously proposed evolutionary neural networks, combining the continuous ant colony optimization proposed by author and BP neural network, a new evolutionary neural network whose architecture and connection weights evolve simultaneously is proposed. At last, through the typical XOR problem, the new evolutionary neural network is compared and analyzed with BP neural network and traditional evolutionary neural networks based on genetic algorithm and evolutionary programming. The computing results show that the precision and efficiency of the new neural network are all better.