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

This work suggests a design approach building on past results in the area of adaptive Neural Network (NN) based reconfigurable flight control which has been successfully utilized for a variety of aerospace applications, while incorporating recent advances in the areas of output feedback and NN adaptation algorithms. The paradigm is based on feedback linearization and synthesis of a fixed-gain dynamic compensator, whilst incorporating a neural network by using concurrent update information to compensate for model uncertainties, system faults and external disturbances. The concurrent learning networks update law is simplified and restructured for better and easy use during applications. The stability and reconfigurable ability of the improved control system based on the concurrent learning algorithm is validated with simulation performances of the nonlinear Machan UAV.

Reconfigurable flight control using feedback linearization with online Neural Network adaption

Given the linear state-space representation of a dynamic system, a method for computing allowable eigenvector sub-spaces 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 in the system matrices as possible. A computational procedure for each of these techniques is descrioed. The work is illustrated using the stability augmentation system control design problem for the lateral motion model of a non-linear aircraft system. The modal requirements for this problem are well known and this enables a comparison of the two methods to be made. Conclusions can then be drawn about the robustness of general control system design using eigenstructure assignment.

A Comparison of Two Techniques for Eigenstructure Assignment

The tensor product (TP) based models have been applied widely in approximation theory and approximation techniques. Recently, a controller design framework working on dynamic systems has also been established based on TP model transformation combined with linear matrix inequalities (LMI) within parallel distributed compensation (PDC) framework. The effectiveness of the control design framework strongly depends on the approximation property of the TP model used. Therefore, the primary aim of this paper is to investigate the approximation capabilities of dynamic TP model. It is shown that the set of functions that can be approximated arbitrarily well by TP forms with bounded number of components lies no-where dense in the set of continuous functions. This drawback necessitates the application of trade-off techniques between accuracy and complexity of TP form. Such requirements are very difficult to consider in the analytical framework, but TP model transformation offers an easy way to deal with them.

On the approximation properties of TP model forms

The authors use a model-following VSCS (variable structure control system) design approach to provide an aircraft control system which exhibits parameter insensitivity with good disturbance rejection while enabling the pilot to perform an advanced aircraft maneuver. Eigenstructure assignment is used to define a model with these response characteristics. The authors also consider a definition and practical measures of the robustness of such a model-following VSCS. The VSCS technique is illustrated by considering the design of a lateral translational/yaw pointing control scheme for a conventional combat aircraft which has been augmented with a chin-fin to provide the required sideforce control. Analysis of the performance of this control scheme when subjected to a range of flight conditions is used to demonstrate application of the robustness criteria developed. >

An assessment of robustness of variable structure control systems for advanced aircraft manoeuvres

This paper is concerned with the assignment of a desired eigenstructure to linear parameter-varying (LPV) systems as an extended version of the corresponding eigenstructure assignment problem for linear time-invariant systems. Based on a complete parametric solution of parametric generalized Sylvester matrix equation, a controller design method is proposed to guarantee a low sensitivity of the closed-loop eigenvalues. The observer state feedback structure is considered for output feedback control design. An example of control for a satellite attitude system is used to demonstrate the usefulness of the proposed approach.

Ron J. Patton

Papers

Reconfigurable flight control using feedback linearization with online Neural Network adaption

A Comparison of Two Techniques for Eigenstructure Assignment

On the approximation properties of TP model forms

An assessment of robustness of variable structure control systems for advanced aircraft manoeuvres

Low eigenvalue sensitivity eigenstructure assignment to linear parameter varying systems