Fault tolerant control based on stochastic distributions via MLP neural networks
Fault tolerant control based on stochastic distributions via MLP neural networks
复制标题
DOI：
10.1016/j.neucom.2006.10.030
复制
发表时间：
2007
期刊：
影响因子：
6
通讯作者：
Yumin Zhang;Lei Guo;Haisheng Yu;K. Zhao
中科院分区：
文献类型：
--
作者：
Yumin Zhang;Lei Guo;Haisheng Yu;K. Zhao
针对一般随机连续时间系统，研究了一种基于输出概率密度函数的最优容错控制方案。与经典的FTC问题不同，测量信息是系统输出的随机分布而不是其值。控制的目标是利用输出PDF设计控制方案，可以补偿故障和抑制干扰。采用多层感知器（MLP）神经网络逼近输出PDF，并利用非线性主元分析（NLPCA）降低模型阶数。针对所建立的具有扰动和不确定性的连续时间加权系统，提出了一种基于LMI的可行FTC方法，以保证故障能够得到很好的测量和补偿，并优化了不确定误差系统的H∞性能指标。
An optimal fault tolerant control (FTC) scheme using output probability density functions (PDFs) is studied for the general stochastic continuous time systems. Being different from the classical FTC problems, the measured information is the stochastic distribution of the system output rather than its value. The control objective is to use the output PDFs to design control schemes that can compensate the fault and attenuate the disturbance. A multi-layer perceptron (MLP) neural network is applied to approximate the output PDFs, with which nonlinear principal component analysis (NLPCA) can be used to reduce the model order. For the established continuous-time weighting system with disturbances and uncertainties which is used to link the input and the weights, an LMI-based feasible FTC method is presented to assure that the fault can be well measured and compensated, where the H∞performance index for the uncertain error systems is optimized.