Differential Evolution Algorithm Base On Eugenic Strategy And Application To Chemical Engineering

Accurate models are important to the research and application of chemical engineering. However, most problems in chemical engineering are complex and we know little about their principles. So it is difficult to build accurate models directly by the first principles. On the other hand, although the whole experimental model can be built without the principles, it completely replies on sample data. When sample data are not enough, or contain noises or aberrant data, they cannot reflect the properties of the object to be modeled very well. Thus the model's performances are degraded. The models built by the combination of principles and observation data can overcome the disadvantages of the above two methods. One side, simple models are built by their principles; On the other side, observation data are obtained by experiments or other ways. Then more reliable models are created by the above information via optimizing. In this paper, we mainly discuss the differential evolution algorithm base on eugenic strategy and application to chemical engineering, including the following parts:1. A eugenic evolution strategy was proposed to improve the efficiency of the conventional simple differential evolution algorithm (SDEA) searching. The differential eugenic evolution algorithm (DEEA) collects the population information along the evolution of children generations and constructs a deterministic optimization algorithm, which will be embedded in the evolution process at appropriate stage to speed up the local searching. For the possible deterministic searching methods, the Simple Searching method was found to be feasible in integrating with the differential evolution algorithm. Besides, offering Afresh Distribution operation to escape premature is effectively modified the SDEA. Two typical examples indicated the good performance of the proposed method. Finally, the DEEA was successfully applied to the nonlinear parameter estimation of two models in chemical engineering.2. A kind of mathematic function is created to estimate the diversity ofpopulation in order to avoid premature. At the same time, a oversimplified Simple formed by only three point is offered. It can solve the difficulty of find the real Simple in multidimention in the Simple Searching method. 3. Analyzing the influence of the two operations (the precision of Simple Searching method and minimal diversity of population for Afresh Distribution) using Two-Factor analysis of variance. As a result, different parameters should be set in optimizing different function with Differential Eugenic Evolution algorithm. In the end of this paper, we make a summary and describe the future works: thedifferential evolution algorithm should be combined with neural network, expertsystem and other kinds of intelligent agents.