Wen-Jun Zhang

Dissipative particle swarm optimization

A dissipative particle swarm optimization is developed according to the self-organization of dissipative structure. The negative entropy is introduced to construct an opening dissipative system that is far-from-equilibrium so as to driving the irreversible evolution process with better fitness. The testing of two multimodal functions indicates it improves the performance effectively.

Adaptive particle swarm optimization on individual level

An adaptive particle swarm optimization (PSO) on individual level is presented. By analyzing the social model of PSO, a replacement criterion, based on the diversity of fitness between the current particle and the best historical experience, is introduced to maintain the social attribution of swarm adaptively by taking off inactive particles. The testing of three benchmark functions indicates that it improves the average performance effectively.

Hybrid particle swarm optimizer with mass extinction

A hybrid particle swarm optimizer with mass extinction, which has been suggested to be an important mechanism for evolutionary progress in the biological world, is presented to enhance the capacity in reaching an optimal solution. The tested results of three benchmark functions indicate this method improves the performance effectively.

Handling boundary constraints for numerical optimization by particle swarm flying in periodic search space

The periodic mode is analyzed together with two conventional boundary handling modes for particle swarm. By providing an infinite space that comprises periodic copies of original search space, it avoids possible disorganizing of particle swarm that is induced by the undesired mutations at the boundary. The results on benchmark functions show that particle swarm with periodic mode is capable of improving the search performance significantly, by compared with that of conventional modes and other algorithms.

Social cognitive optimization for nonlinear programming problems

Social cognitive optimization (SCO) for solving nonlinear programming problems (NLP) is presented based on human intelligence with the social cognitive theory (SCT). Experiments comparing SCO with genetic algorithms on some benchmark functions show that the former can produce high-quality solutions efficiently, even with only one learning agent.

SWAF: Swarm Algorithm Framework for Numerical Optimization

A swarm algorithm framework (SWAF), realized by agent-based modeling, is presented to solve numerical optimization problems. Each agent is a bare bones cognitive architecture, which learns knowledge by appropriately deploying a set of simple rules in fast and frugal heuristics. Two essential categories of rules, the generate-and-test and the problem-formulation rules, are implemented, and both of the macro rules by simple combination and subsymbolic deploying of multiple rules among them are also studied. Experimental results on benchmark problems are presented, and performance comparison between SWAF and other existing algorithms indicates that it is efficiently.

Solving Engineering Design Problems by Social Cognitive Optimization

Swarm systems are products of natural evolution. The complex collective behavior can emerge from a society of N autonomous cognitive entities [2], called as agents [5]. Each agent acquires knowledge in socially biased individual learning [4]. For human, the extrasomatic arbitrary symbols that manipulated by language allows for cognition on a grand scale [3], since agent can acquire social information that is no longer limited to direct observation to other agents. The individual learning then only plays secondary role due to the ubiquity and efficiency of social learning [1].

Handling equality constraints by adaptive relaxing rule for swarm algorithms

The adaptive constraints relaxing rule for swarm algorithms to handle with the problems with equality constraints is presented. The feasible space of such problems may be similiar to ridge function class, which is hard for applying swarm algorithms. To enter the solution space more easily, the relaxed quasi feasible space is introduced and shrinked adaptively. The experimental results on benchmark functions are compared with the performance of other algorithms, which show its efficiency.

Application of neural network method for process synthesis

Process synthesis is a top-down design methodology and can effectively reduce the process design time. In the paper the general method and the neural network (NN) package used for process synthesis are discussed. Then the characteristics of synthesizing some key process modules, including ion implantation and well formation, are analyzed, based on which the training set used to build the NN is generated. After that the NN model used for process modules synthesis is constructed and trained. Test results show that this model can fulfill the process modules synthesis.