State and fault estimation for nonlinear recurrent neural network systems: Experimental testing on a three‐tank system

Abstract

An observer is presented for the simultaneous estimation of the system state and actuator and sensor faults of a discrete recurrent neural network (RNN) system. The presented approach enables disturbance attenuation and guarantees observer convergence. First, the discrete RNN is converted to a discrete linear parameter varying (LPV) model. Then, the LPV model is further transformed into a descriptor system by extending the system state and sensor fault. Next, an H ∞ observer is presented for the simultaneous estimation of the extended state and actuator fault of the descriptor system. Finally, the problem of observer design is translated into solving a linear matrix inequality. Experimental tests on a three-tank system have validated the effectiveness and correctness of the presented method.

Fault-Tolerant Control Based on Virtual Actuator and Sensor for Discrete-Time Descriptor Systems

“…These faults may degrade the performance, leading to unsatisfactory behavior, or in the worst-case to instability, thus bearing catastrophic consequences for the system itself and for the safety of living beings around them. Motivated by the increasing need for safety and reliability, fault diagnosis and fault tolerant control (FTC) techniques have attracted a lot of interest in the control community, since they allow to maintain the system performance close to the desired one while preserving stability in spite of the faults [9]- [11]. Following a well-established nomenclature, the existing FTC techniques can be classified into passive and active [12].…”

Deep Cost Adaptive Convolutional Network: A Classification Method for Imbalanced Mechanical Data

“…Mechanical intelligent fault diagnosis methods are used to extract the hidden fault characteristics from the monitoring signals [4], [5] and automatically identify the health condition of machinery through intelligent algorithm, which are current researched hotspot in the field of fault diagnosis. Since Hinton [6] first proposed the concept of ''deep learning'' in 2006, deep learning has become an emerging researched hotspot in The associate editor coordinating the review of this manuscript and approving it for publication was Youqing Wang . academia and industry, and deep neural networks have also been successfully applied in different engineering fields, such as image recognition [7], text analysis [8], speech recognition [9], fault diagnosis [10]- [12] and remaining useful life prediction [13]- [15]. Jing et al [10] proposed a fault diagnosis method based on convolutional neural network, which learns features from the frequency domain data of the original vibration signals.…”

Distributed semi‐cooperative filter for a nonlinear multi‐agent system with heterogeneous and homologous unknown inputs

“…The estimation of states and unknown inputs (UIs) is important in fault diagnosis and dynamic system control. [1][2][3][4][5] This problem is frequently encountered in power system exciters, [6,7] chemical processes, [8][9][10] state estimation of a battery, [11][12][13] navigation, [14,15] and earthquake damage estimation. [16] Over the last decade, many methods have been proposed for the simultaneous estimation of the UIs and states in a linear discrete-time system, [17][18][19][20][21][22] among which Gillijns and De Moor [22] present a valuable overview.…”

“…The estimation of states and unknown inputs (UIs) is important in fault diagnosis and dynamic system control. [ 1–5 ] This problem is frequently encountered in power system exciters, [ 6,7 ] chemical processes, [ 8–10 ] state estimation of a battery, [ 11–13 ] navigation, [ 14,15 ] and earthquake damage estimation. [ 16 ]…”