基于交互容积卡尔曼的随机切换系统故障诊断

Fault Diagnosis of Stochastic Switched Systems Based on Interactive Multiple Model and Cubature Kalman Filter

中文关键词:  随机切换非线性系统  交互式容积卡尔曼滤波  故障检测  故障估计

英文关键词:stochastic switched nonlinear systems  IMM-CKF  fault detection  fault estimation

中文摘要:

      针对一类随机切换非线性系统的故障检测和故障估计问题，提出了一种基于交互式多模型和容积卡尔曼滤波（IMM CKF）的系统状态估计算法。该算法利用容积卡尔曼滤波（CKF）在不同时刻对每个子系统进行状态估计，把不同子系统状态估计结果融合得到最终的状态估计，实现对系统真实状态的估计。针对一类随机切换非线性系统发生执行器故障，采用IMM CKF估计系统状态；然后分析了IMM CKF算法的稳定性；根据状态估计结果，构造残差信号，设计残差评价函数，检测故障发生。当检测到故障发生时，设计增广系统，对故障幅值进行估计。通过仿真实验验证提出算法的有效性，结果表明该算法可以较为准确地诊断系统故障。

英文摘要:

      In order to solve the problem of fault detection and fault estimation for a class of stochastic switched nonlinear systems,a system state estimation algorithm based on interactive multiple model and cubature Kalman filter (IMM-CKF) is proposed.The cubature Kalman filter(CKF) is used to estimate the state of each subsystem at different time points,then the state estimation results of different subsystems are fused to obtain the final state estimation to realize the true real estimation state of the system.For a class of stochastic switched nonlinear systems with actuator failure,IMM-CKF was used to estimate the system state.Then the stability of the IMM-CKF algorithm was analyzed.Based on the results of the state estimation,residual and residual evaluation functions were established to detect the actuator fault.When a fault is detected,an augmentation system is designed to estimate the magnitude of the fault.Finally,simulation experiments validate the proposed algorithm.The results show that the algorithm can diagnose system faults more accurately.