Wu Qidi

Ant system algorithm for optimization in continuous space

An ant system (AS) algorithm is introduced into an optimization problem solving in a continuous field. A corresponding algorithm is defined and good simulation results are derived in examples of the global optimum value searching of a multi-minimum continuous function and a nonlinear continuous function.

A modified adaptive particle swarm optimization algorithm

It is effective to avoid falling into local optimums at the original stage of the computation that the knowledge of multi-optimum distribution state is introduced into general programming of the particle swarm movement in particle swarm optimization. But if the proportion factor of multi-optimum programming cannot be dynamic adjusted in the optimization process, the performance of the algorithm will be limited. In this paper, a modified adaptive particle swarm optimization algorithm based on fuzzy and adaptive programming of multi-optimum was put forward and simulated. In the modified algorithm derived in this paper, proportion factor of multi-optimum programming can be dynamic adjusted in the optimization process, and simulation results show that it has well general convergence character.

Hopfield neural networks approach for job shop scheduling problems

A new method based on Hopfield neural networks for solving job-shop scheduling problems (JSP) is proposed. All constraints of job-shop scheduling problems and its permutation matrix express are developed. A new calculation energy function included all constraints of job-shop scheduling problems is given. A corresponding new Hopfield neural network construction and its weights of job-shop scheduling problems are given. To avoid Hopfield neural network to converge to local minimum volume, and to produce some non-feasible scheduling solutions for JSP, simulated annealing algorithm is applied to Hopfield neural network. Hopfield neural network converging to minimum volume 0, can keep the steady outputs of neural networks as feasible solution for job-shop scheduling problem. This paper improved existing method based on Hopfield neural network for solving job-shop scheduling problems. Compared with the method, modified method can keep the steady outputs of neural networks as feasible solutions for job-shop scheduling problems.

Linear system parameters identification based on ant system algorithm

An ant system algorithm is introduced into the system parameter identification problem in continuous space. A corresponding algorithm is defined and good simulation results are derived in the example of linear system parameters identification.

Application of adaptive fuzzy logic system to model for greenhouse climate

In this paper, the greenhouse climate model based on adaptive fuzzy logic system is presented. Greenhouse climate system is a nonlinear system with the various climate factors being coupled. Due to its capability to handle both numerical data and linguistic information, it is feasible to apply adaptive fuzzy logic system to model for greenhouse climate, and then provide prediction for greenhouse climate control.

Further example study on ant system algorithm based continuous space optimization

In the paper, the ant system (AS) optimization algorithm in continuous space is under further study and used for other examples of optimum value searching of a multi-minimum continuous function and a linear continuous function. The multi-minimum function of the Rosenbrock function is chosen. In the paper, the general optimization error function for algorithm evaluation is modified. The applicability characteristics of AS application in continuous space optimization problems are summarized at the end of the paper.

Neural network based parameters identification and adaptive speed control of AC drive system

In this paper, a Hopfield neural network (HNN) based open-loop and closed-loop AC drive system parameter identification scheme is derived. Then an autotuned AC drive system which has the ability of online parameter tracking is designed. Simulation results have proved the validity of the HNN based AC drive system identification scheme and its adaptive control.

Colored Petri net based hierarchical scheduling model for semiconductor production line

In this paper a kind of scheduling model and its modeling approach are studied for reentrant semiconductor production line. By introducing multi-dimensional color sets and machine group oriented hierarchy, a kind of colored Petri net based hierarchical scheduling model is proposed. Then, a case study of the proposed model is illustrated with an example semiconductor production line, which includes 5 machines and 6 steps. The modeling approach is combined top-down structure modeling and bottom-up parameter definition. At last, some further discussion about the application of the proposed Petri net model are given.

Multi-optimum programming based particle swarm optimization algorithm and its application in multi-dimensional & multi-modal function optimization

In this paper, the knowledge of multi-optimum distribution state is introduced into general programming of the particle swarm movement to avoid falling into local optimums at the original stage of the computation. The algorithm is improved based on the modified particle algorithm and used to optimize the multi-dimensional and multi-optimum function. Simulation results show that, the general convergence character of the algorithm derived in this paper has better performance than the results derived based on the modified particle algorithm.

Hybrid algorithm for job-shop scheduling problem

A hybrid algorithm of a genetic algorithm and tabu search is proposed to solve the job-shop scheduling problem in this paper. Tabu search acts as the mutation of the genetic algorithm, and implements the optimal process on individuals independently before the crossover operator operates them. A performance comparison of the proposed method with the better genetic algorithm and other heuristics is adopted to prove its efficiency based on the famous job-shop benchmark problem. The numerical experiments have shown its better optimal performance.