https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

A review on machinery diagnostics and prognostics implementing condition-based maintenance

This book is downloadable from http://www.irisa.fr/sisthem/kniga/. Many monitoring problems can be stated as the problem of detecting a change in the parameters of a static or dynamic stochastic system. The main goal of this book is to describe a unified framework for the design and the performance analysis of the algorithms for solving these change detection problems. Also the book contains the key mathematical background necessary for this purpose. Finally links with the analytical redundancy approach to fault detection in linear systems are established. We call abrupt change any change in the parameters of the system that occurs either instantaneously or at least very fast with respect to the sampling period of the measurements. Abrupt changes by no means refer to changes with large magnitude; on the contrary, in most applications the main problem is to detect small changes. Moreover, in some applications, the early warning of small - and not necessarily fast - changes is of crucial interest in order to avoid the economic or even catastrophic consequences that can result from an accumulation of such small changes. For example, small faults arising in the sensors of a navigation system can result, through the underlying integration, in serious errors in the estimated position of the plane. Another example is the early warning of small deviations from the normal operating conditions of an industrial process. The early detection of slight changes in the state of the process allows to plan in a more adequate manner the periods during which the process should be inspected and possibly repaired, and thus to reduce the exploitation costs.

Detection of abrupt changes: theory and application

There is an increasing demand for dynamic systems to become safer and more reliable This requirement extends beyond the normally accepted safety-critical systems such as nuclear reactors and aircraft, where safety is of paramount importance, to systems such as autonomous vehicles and process control systems where the system availability is vital It is clear that fault diagnosis is becoming an important subject in modern control theory and practice Robust Model-Based Fault Diagnosis for Dynamic Systems presents the subject of model-based fault diagnosis in a unified framework It contains many important topics and methods; however, total coverage and completeness is not the primary concern The book focuses on fundamental issues such as basic definitions, residual generation methods and the importance of robustness in model-based fault diagnosis approaches In this book, fault diagnosis concepts and methods are illustrated by either simple academic examples or practical applications The first two chapters are of tutorial value and provide a starting point for newcomers to this field The rest of the book presents the state of the art in model-based fault diagnosis by discussing many important robust approaches and their applications This will certainly appeal to experts in this field Robust Model-Based Fault Diagnosis for Dynamic Systems targets both newcomers who want to get into this subject, and experts who are concerned with fundamental issues and are also looking for inspiration for future research The book is useful for both researchers in academia and professional engineers in industry because both theory and applications are discussed Although this is a research monograph, it will be an important text for postgraduate research students world-wide The largest market, however, will be academics, libraries and practicing engineers and scientists throughout the world

Robust Model-Based Fault Diagnosis for Dynamic Systems

Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy—a survey and some new results

Provides a perspective on the state of the art in robust approaches to fault-tolerant control and gives some indication of ways in which the research may best proceed. Key themes are the individual robustness properties of fault detection, fault isolation and controllers used as elements in a fault-tolerant system. Comparisons between active and passive approaches are made and emphasis is placed on the overall robustness properties of the fault-tolerant control system.<
 >

Robustness issues in fault-tolerant control

Given the linear state-space representation of a dynamic system, a method for computing allowable eigenvector subspaces using singular value decomposition for both real and complex eigenvalues is illustrated. Once these spaces have been determined, it is possible to assign the eigenvectors in two ways: one which performs desirable weightings of the system states for each mode permitting system decoupling, and the second which assigns eigenvectors iteratively, to make the corresponding eigenvalues as insensitive to perturbations inthe system matrices as possible. A computational procedure for each of these techniques is described. The work is illustrated using the stability augmentation system control design problem for the lateral motion model of a nonlinear aircraft system. The modal requirements for this problem are well known, and this enables acomparison of the two methods to be made.

Analysis of the technique of robust eigenstructure assignment with application to aircraft control

Robust FDI applied to thruster faults of a satellite system

Summary
This paper proposes an integrated fault estimation and fault-tolerant control (FTC) design for Lipschitz non-linear systems subject to uncertainty, disturbance, and actuator/sensor faults. A non-linear unknown input observer without rank requirement is developed to estimate the system state and fault simultaneously, and based on these estimates an adaptive sliding mode FTC system is constructed. The observer and controller gains are obtained together via H∞ optimization with a single-step linear matrix inequality (LMI) formulation so as to achieve overall optimal FTC system design. A single-link manipulator example is given to illustrate the effectiveness of the proposed approach. Copyright © 2016 John Wiley & Sons, Ltd.

Integrated fault estimation and fault-tolerant control for uncertain Lipschitz nonlinear systems

A new method of analyzing faults in the m measurements of an nth-order system is presented. The proposed approach uses the estimation error space of each observer in a bank of observers to detect and isolate sensor faults. The designs are applied to a nonlinear model of an unmanned aircraft that has been described in previous publications. The reconfigurability of the aircraft sensor system is demonstrated, and the results show rapid recovery from a faulty sensor. The use of the observation error eliminates the need for state-space computations, thus producing an effective real-time fault monitor for fly-by-wire aircraft. N an earlier paper,1 a comparison of two techniques of instrument fault diagnosis (IFD) was made. This work is an extension of Patton and Willcox's idea of using analytical redundancy to design a match between m components of the observation error space instead of using state estimates di- rectly as discussed by Clark,3'4 Clark and Setzer,5 Frank and Keller,6 and Watanabe and Himmelblau.7 IFD in dynamic systems has received a significant amount of attention recently.2"11 Most methods described in the liter- ature discuss the analytical redundancy approach in prefer- ence to the use of redundant hardware. Analytical redundancy provides redundant (estimate) information from different measurements of a process, usually with observer or Kalman filter schemes. The commonly discussed state estimate solu- tion to IFD is based on the principle of generating estimates of part or all of the system state vector from subsets of the measurements, which when compared with similar estimates from other observers can be used to monitor the health of an instrument. The problem with the state estimate solution to IFD arises as the observer requires a good linear model of the process, and it must also be assumed that the disturbances on the system are well modeled or else have an insignificant effect on plant parameter variations. These limitations cause the state estimate approach to be inadequate for many real en- gineering applications. Sensitivity to input-induced parameter variations causes uncertain errors between redundant state estimate vectors, and in an IFD scheme these errors could cause false signaling of an instrument fault. It becomes clear that the bandwidth of uncertain signals should be estimated prior to the IFD system design. The use of frequency domain sensitivity information in this way enables a robust approach to the observer design to be made. The conjecture used is that the "innovations" or prediction error signals contain all the information concerning the parameter variations of the pro- cess being identified and controlled. Attention is thus turned toward the use of an innovations-based approach to system fault diagnosis that has wide potential applications. By using a weighting of the measurement estimation error as a parity

Ron J. Patton

Papers

Robustness issues in fault-tolerant control

Analysis of the technique of robust eigenstructure assignment with application to aircraft control

Robust FDI applied to thruster faults of a satellite system

Integrated fault estimation and fault-tolerant control for uncertain Lipschitz nonlinear systems

Parameter-Insensitive Technique for Aircraft Sensor Fault Analysis