摘要
研究气垫船航向优化控制问题,航向受到多种影响,具有非线性、时变等特点,常规PID难以建立精确的控制模型,控制精度低,影响航向控制。为了提高气垫船航向控制精度,提出一种粒子群优化算法、最小二乘支持向量机和常规PID相融合的气垫船航向控制算法(PSO-LSSVM-PID)。采用粒子群算法对气垫船PID参数进行在线整定,同时采用最小二乘支持向量机对航向变化进行预测,然后PID根据预测结果对气垫船航向进行超前控制。仿真结果表明,PSO-LSSVM-PID提高了气垫船航向控制精度,克服了常规PID控制算法存的缺陷,环境适应能力更强,可以保证气垫船安全航行。
Air cushion vehicle is affect by many factors, such as nonlinear and time - varying characteristics, it is difficult for the traditional PID to establish accurate control model, so the control precision is low. In order to improve the control precision of the air cushion vehicle, this paper put forward a course control algorithm which combines par- ticle swarm optimization algorithm, least squares support vector machine with conventional PID （ PSO - LSSVM - PID）. The particle swarm optimization algorithm was used to tune the PID parameters on - line while the least square support vector machine was used to predict the change of course, and then PID controled the air cushion vehicle course according to the predicted results. The simulation results show that PSO - LSSVM - PID improves the control precision of the air cushion vehicle course, and overcomes the defects of traditional PID control algorithm. The proposed algorithm has good environmental adaptability and can ensure the safety navigation of air cushion vehicle.
出处
《计算机仿真》
CSCD
北大核心
2013年第6期361-365,共5页
Computer Simulation
关键词
气垫船
航向控制
最小二乘支持向量机
粒子群优化算法
Air cushion vehicle
Course control
Least squares support vector machine
Particle swarm algorithm
