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 paper is concerned with low sensitive and robust control design via output-feedback eigenstructure assignment for linear multivariable systems. A parametric expression of closed-loop eigenvectors and generalized eigenvectors is developed. It also considers the case where the closed-loop eigenvalues are multiple and/or the same as the open-loop ones so that the system to be designed can be uncontrollable and/or unobservable. The controller designed via output-feedback eigenstructure assignment is expressed by new proposed parameter vectors. The freedom provided by output-feedback eigenstructure assignment is used to optimize some performance functions which are used to measure the sensitivity of the closed-loop matrix and the robustness of the closed-loop system.

Low sensitive and robust control design via output feedback eigenstructure assignment

Asymmetrical Load Mitigation of Wind Turbine Pitch Actuator Faults using Unknown Input-based Fault-tolerant Control

Prediction or forecasting of the wave excitation force (WEF) is required for implementing a power ef ciency maximisation control of wave energy converters (WECs) due to the inherent non-causality of required power take-off (PTO) force. WEF prediction is a non-trivial challenge, depending on WEF (i) estimation and (ii) forecasting. In this study, an observer-based unknown input estimator (OBUIE) is used to estimate the wave excitation force, then a Gaussian Process (GP) model is adopted to forecast the wave excitation force. A new strategy for combined OBUIE and GP forecasting is presented and the performance of the new scheme is validated on a simulation model of the Wavestar WEC system, considering six different sea states. The simulation results indicate the accuracy and feasibility of the proposed method.

Wave Excitation Force Estimation and Forecasting for WEC Power Conversion Maximisation

This paper proposes a systematic adaptive sliding mode controller design for the decentralized system with nonlinear interactions and unmatched uncertainties. An adaptive tuning approach is developed to deal with unknown but bounded uncertainties/interactions. The sliding surface is designed which obviates the use of regular transformation, by solving a simple LMI-based optimization problem. The feasibility of the LMIs is also discussed in this paper. Finally, a numerical example is used to illustrate this method.

An adaptive sliding mode approach to decentralized control of uncertain systems

In Chapter 3, various approaches for generating robust residual via unknown input observers have been introduced. The underlying principle of these approaches is to make the state estimation error be independent of disturbances (or unknown inputs). The residual is defined as the (weighted) output estimation error which is a linear transformation of the state estimation error. The residual generated by UIOs is also independent of disturbances, if the disturbance term does not appear in the output equation or the disturbance term in the output equation has been nulled. In model-based FDI, the state estimation is not necessarily needed, because the required information is the diagnostic signal - residual. Hence, it is not necessary to de-couple the state estimation error from disturbances in model-based FDI. A direct approach to design disturbance de-coupled residuals is then required. In this approach, the residual itself is de-coupled from disturbances, however the state estimation error may not be. It can be expected that existing conditions for such a direct approach could be relaxed compared with those required for UIOs.

Ron J. Patton

Papers

Low sensitive and robust control design via output feedback eigenstructure assignment

Asymmetrical Load Mitigation of Wind Turbine Pitch Actuator Faults using Unknown Input-based Fault-tolerant Control

Wave Excitation Force Estimation and Forecasting for WEC Power Conversion Maximisation

An adaptive sliding mode approach to decentralized control of uncertain systems

Robust Residual Generation by the Assignment of Observer Eigenstructure