【摘要】 水下运输系统在运输载荷时会受到水的不确定非线性和其他外部扰动影响。针对水下运输系统的运行控制问题，以核电厂燃料组件的水下运输系统为对象，设计了基于径向基函数（RBF）神经网络的非奇异终端滑模控制方法。首先，根据牛顿第二定律和Morison方程建立了系统的运动微分方程并推导其状态空间方程；其次，设计非奇异终端滑模控制器，并用RBF神经网络对未知非线性作用进行估计并在控制器中补偿，由Lyapunov稳定性理论推导了网络权值的自适应更新律；通过Lyapunov稳定性理论证明了所提控制策略可以实现对未知非线性估计的渐进收敛和对给定指令跟踪的有限时间收敛；分别对带载上行和空载下行两种工况进行仿真验证，仿真结果表明了所设计的控制器性能良好。更多还原

【Abstract】 The underwater transportation system will be affected by the uncertain nonlinearity of water and other external disturbance when transporting loads. Aiming at the operational control of underwater transportation system, a non-singular terminal sliding mode control method based on radial basis function(RBF) neural network is designed for the underwater transport process of nuclear power plant fuel assembly. Firstly, according to Newton’s second law and Morison’s equation, the kinetic differential equation of the system is established and its state-space equation is derived. Secondly, a non-singular terminal sliding mode controller is designed, and the unknown nonlinear effect is estimated by RBF neural network and compensated in the controller. The adaptive updating law of network weight is derived by Lyapunov stability theory. The Lyapunov stability theory proves that the proposed control strategy can achieve asymptotic convergence for unknown nonlinear estimation and finite-time convergence for given instruction tracking.Simulations is carried out for the two conditions of upgoing with load and downgoing without load respectively, and the results verify that the controller designed has good performance.更多还原