Research On RNA Genetic Algorithms And Applications In Overhead Cranes

Genetic algorithm(GA)is a kind of intelligent optimization algorithm,which is simple and easy to use.And it has strong robustness,parallel ability and large room for expansion.It simulates the natural law of biological evolution "survival of the fittest",and due to genetic algorithm has no continuous or differential requirements for optimization problems,it is widely used in scientific research and engineering fields.RNA-GA is a new kind of genetic algorithm inspired by RNA molecule operation.Based on previous research work,this thesis focuses on improvements of RNA-GA and its applications in overhead crane.The main contents of this thesis are as follows:(1)This thesis briefly reviews the development and research status of genetic algorithms,and the research works of modeling and control of overhead cranes.(2)The RNA genetic algorithm inspired by fish swarm behavior(fsRNA-GA)is proposed.In the algorithm,a neighborhood evolve operation is designed to measure the degree of congestion between individuals by defining the crowding factor of the fitness values.Therefore,the more potential individuals are found in the local space.To the problem with many parameters,the matrix coding is used to replace the chain coding in RNA-GA.With some typical test functions,the performance tests of fsRNA-GA are conducted for both low and high dimension unconstrained optimization problems.Then fsRNA-GA is used to optimize the center of the Radial Basis Function neural network(RBF-NN).With the data acquired by the overhead crane platform,the RBF neural network model of the crane position and swing angle is established.The simulation results show the effectiveness of the RBF-NN model.(3)The RNA genetic algorithm with the highest bit codon selection operation(csRNA-GA)is proposed.The highest bit codon selection operation can increase the probability of the elite genes entering the next generation in the evolution process,which increases the diversity of the population.With some typical test functions,the numerical experiment results show that the csRNA-GA has better global search ability and convergence precision.The csRNA-GA is used to optimize the two PID controller parameters of the overhead crane system.And the simulation results show that the PID controllers have good performance of responding quickly,without overshoot and with small swing amplitude.