Fault detection and isolation for linear structured systems

基于动态对称性的四旋翼飞行器神经网络故障检测与识别

Neural Network-based Fault Detection and Identification for Quadrotors using Dynamic Symmetry

本文提出一种基于LSTM的无模型四旋翼飞行器故障检测与隔离框架，利用动力学对称性仅对单个电机故障进行训练即可预测任意电机故障，实验表明其对部分和完全故障的预测准确率超过90%，且对模型不确定性和数据分布偏移具有鲁棒性。

基于未知输入观测器的容错控制分配方法

Fault-Tolerant Control Allocation: an Unknown Input Observer based approach

本文重点研究了在过驱动系统中，利用未知输入观测器检测和隔离执行器和执行器故障，并进行控制重构。控制分配积极地使用输入冗余，以使相关的故障可观察。过驱动船舶的案例研究支持理论的发展。

通过凸松弛实现模型辨识和故障检测的输入设计

Input Design for Model Discrimination and Fault Detection via Convex Relaxation

本文提出通过凸松弛方法设计输入信号以区分动态系统模型，用于故障检测。通过随机搜索算法求解非凸优化问题，并分析子最优解的准确性。

Robust Fault Diagnosis for Pipelines

This paper presents the design of a diagnosis system for the detection, identification and reconstruction of faults in pipelines. The design of such diagnosis system is based on redundant relations and nonlinear observers, taking into account faults in sensors, damages in pumps, and unknown extractions. The proposed algorithm is developed based on a model described by nonlinear equations of the fluid behavior in a pipeline, considering the principles of conservation of mass and momentum. In order to distinguish among different types of faults and to reconstruct their behavior, the diagnosis sy…