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

Formulates the design procedure and illustrates the technique using a pitch-pointing/vertical translation manoeuvre for a combat aircraft as developed by Sobel and Shapiro (1985) and Andry et al. (1983). A fully nonlinear simulation incorporating wind turbulence in the form of a Dryden spectrum as in Gault and Gunter (1968) is used to assess the performance of the controller. The performance of the variable structure control systems is compared with the performance of the purely linear control used to define the model dynamics. Conclusions are drawn about the advantages with regard to performance of the nonlinear structure against the disadvantages of having such a control type. >

Variable structure control laws for aircraft manoeuvres


 This article presents a data-efficient learning approach for the complex-conjugate control of a wave energy point absorber. Particularly, the Bayesian Optimization algorithm is adopted for maximizing the extracted energy from sea waves subject to physical constraints. The algorithm learns the optimal coefficients of the causal controller. The simulation model of a Wavestar Wave Energy Converter (WEC) is selected to validate the control strategy for both the regular and irregular waves. The results indicate the efficiency and feasibility of the proposed control system. Less than 20 function evaluations are required to converge towards the optimal performance of each sea state. Additionally, this model-free controller can adapt to variations in the real sea state and be insensitive and robust to the WEC modeling bias.

Learning a Predictionless Resonating Controller for Wave Energy Converters

Several energy maximization control approaches for point-absorber wave-energy converter (PAWEC) systems require knowledge of the wave excitation force (WEF) that is not measurable during the PAWEC operation. Many WEF estimators have been proposed based on stochastic PAWEC modeling using the Kalman filter (KF), extended KF (EKF), or receding-horizon estimation. Alternatively, a deterministic WEF estimator is proposed here based on the fast unknown input estimation (FUIE) concept. The WEF is estimated as an unknown input obviating the requirement to represent its dynamics. The proposed observer-based unknown input estimator (OBUIE) inherits the capability of estimating fast-changing signals from the FUIE, which is important when considering irregular wave conditions. Unlike preceding methods, the OBUIE is designed based on a PAWEC model, including the nonlinear viscous drag force. It has been shown that the nonlinear viscous drag force is essential for accurate PAWEC model description, within the energy maximization control role. The performance of the proposed estimator is evaluated in terms of PAWEC conversion efficiency in a single degree-of-freedom PAWEC device operating in regular and irregular waves. Simulation results are obtained using MATLAB to evaluate the estimator under different control methods and subject to parametric uncertainty.

/pdf/observer-based-unknown-input-estimator-of-wave-excitation-4mrf5hjpgx.pdf

Observer-Based Unknown Input Estimator of Wave Excitation Force for a Wave Energy Converter

This paper aims at solving the conflicts of the computational needs of building tensor product (TP) based control models having high approximation accuracy and practical aspects of their applicability w.r.t. system stability and feasibility. Therefore first we propose a HOSVD (higher order singular value decomposition) based methodology capable of implementing any differential equation systems of a dynamic model in TP model form with specific basis functions whereupon the linear matrix inequalities (LMI) based controller design techniques and stability analysis can be executed. Second, we intend to find a tradeoff between the TP modelling accuracy, hence system performance, and the controller complexity which is bounded by the available real time computation power at hand. As an example a detailed control design is given.

Design methodology of tensor product based control models via HOSVD and LMIs

The concept of combining robust fault estimation within a controller system to achieve active Fault Tolerant Control (FTC) has been the subject of considerable interest in the recent literature. The current study is motivated by the need to develop model-based FTC schemes for systems that have no unique equilbria and are therefore difficult to linearise. Linear Parameter Varying (LPV) strategies are well suited to model-based control and fault estimation for such systems. This contribution involves pole-placement within suitable LMI regions, guaranteeing both stability and performance of a multi-fault LPV estimator employed within an FTC structure. The proposed design strategy is illustrated using a non-linear two-link manipulator system with friction forces acting simultaneously at each joint. The friction forces, considered as a special case of actuator faults, are estimated and their effect compensated within a polytope controller system, yielding a robust form of active FTC that is easy to apply to real robot systems.

/pdf/an-lpv-pole-placement-approach-to-friction-compensation-as-53q2bs5wlr.pdf

Ron J. Patton

Papers

Variable structure control laws for aircraft manoeuvres

Learning a Predictionless Resonating Controller for Wave Energy Converters

Observer-Based Unknown Input Estimator of Wave Excitation Force for a Wave Energy Converter

Design methodology of tensor product based control models via HOSVD and LMIs

An LPV pole-placement approach to friction compensation as an FTC problem