高技术通讯Issue(10)：130-138,9.DOI:10.3772/j.issn.10020470.2014.10.014
船舶发电机组转速神经网络模型参考自适应控制研究
Neural network based model reference adaptive control of the speed of a marine generator set
摘要
Abstract
The neural network based model reference adaptive control (NNMRAC) was used as a control tractics to investigate the control of the nonlinear, time varying rotation speed of a marine generator set to achieve the better control quality. In this study, a second order transfer function model was established for the diesel generator set. The multilayer feed forward topological structure was adopted in both the neural network identifier and controller of the model reference adaptive control (MRAC). The scaled conjugate gradient back propagation algorithm was used to optimize the performance of the learning algorithm. After the learning process, the NNMRAC controller and the conventional PID controller conducted their parallel control for the marine generator set. The simulation results showed that both the rapidity and sensitivity of the speed control system of the marine generator set were all improved. <br> model reference adaptive control (MRAC). The scaled conjugate gradient back propagation algorithm was used to optimize the performance of the learning algorithm. After the learning process, the NNMRAC controller and the conventional PID controller conducted their parallel control for the marine generator set. The simulation results showed that both the rapidity and sensitivity of the speed control system of the marine generator set were all improved.关键词
船舶发电机组/神经网络/模型参考自适应控制(MRAC)/转速控制/量化共轭梯度算法Key words
marine generator set/neural network/model reference adaptive control (MRAC)/speed control/scaled conjugate gradient algorithm引用本文复制引用
张威,施伟锋,许丽霞..船舶发电机组转速神经网络模型参考自适应控制研究[J].高技术通讯,2014,(10):130-138,9.基金项目
高等学校博士学科点专项科研基金(20123121110003)和上海海事大学研究生创新基金(2014ycx056)资助项目。 （20123121110003）
