Neural Network: Besed on the classical Neural Networks, including BP Neural Network, Radial Basis Function Neural Network, exploit the theories advantages of complex value and fractional order, design innovative Neural Networks,analyze the properties of convergence, robustness, fault tolerance and uniform approximation ability, further apply to feature selection, system identification, TSP optimization and other fields.
Fuzzy System: Research type one and type two models of fuzzy system, which sre studied for the design of neural network and the theoretical analysis of its sensitivity and fault tolerance.
Evolutionary Computing: Combine the memory characteristics of fractional order theory with traditional evolutionary algorithms such as Particle Swarm Optimization and Ant Colony Algorithm to find the global strategy of the algorithm, which can be applied to feature selection and dynamic multi-objective optimization.
Engineering Field: Based on the above theoretical research, solve practical problems such as Interwell Connectivity and historical matching in petroleum engineering.