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 proposes an approach to active fault tolerant control (AFTC) of a variable-speed wind turbine subject to single or simultaneous multiple sensor faults. Both analytical and hardware redundancies are used in this approach. A fault estimation observer is proposed for the pitch and generator subsystems. A Takagi-Sugeno (T-S) fuzzy observer is designed as the fault detection and isolation (FDI) unit for the nonlinear drive train subsystem. Meanwhile, a control scheme combining model predictive control (MPC) with T-S fuzzy modeling is proposed to control the nonlinear wind turbine system and take into account the system constraints.

Active fault tolerant control of a wind turbine via T-S fuzzy model predictive control

There have been several proposals and suggestions of benchmark studies for evaluating the performance of fault detection and isolation (FDI) methods allied to real industrial plant. The main aim of these benchmarks is to provide a training facility for the engineering community (both industry and academia) to gain an understanding and "feel" for the way in which various FDI methods can perform in a realistic control engineering application setting. This is deemed an essential step in the process of transferring the technology (often gained in the academic community) into real application. This presentation would provide the description and application of a benchmark scheme based on an intelligent electro-pneumatic valve actuator with in-situ (in the loop) testing and fault signalling in a sugar factory evaporisation process. The overall application would also be outlined and this involves on-line FDI and monitoring of the sensors and several actuators of a sugar juice evaporisation plant, providing overall monitoring of the plant under closed-loop control. The study was conducted within the Research Training Network "Development and Application of Methods for Actuator Diagnosis in Industrial Control Systems " DAMADICS {www.eng.hull.ac.uk/research/control}, funded by the European Commission in the Human Improvement Programme of Framework 5. The FDI benchmark is method-independent and based on an in-depth study of the phenomena that can lead to likely faults in valve actuator systems. The work to be presented uses a detailed consideration of the physical and electro-mechanical properties (and their modelling requirements) of an intelligent industrial actuator. The presentation would also include the typical engineering requirements of an actuator valve operating under challenging process conditions, together with the setting up of suitable performance indices for evaluating the FDI results. The results to be described correspond to real in the loop testing and FDI evaluation with injected fault signals.

A benchmark study approach to fault diagnosis of industrial process control systems

The contribution addressed by this paper refers to the development of a new dynamic neuro-fuzzy system and its application to fault detection and isolation of an evaporation station. Hybrid learning based on the fuzzy c-means clustering and steepest-descent method algorithms are used to train the neuro-fuzzy system. The experimental case study refers to the sensor and actuator fault diagnosis of an evaporation station from a sugar factory. An extended neuro-fuzzy generalised observer scheme is used to generate the residuals (symptoms) in the form of the one-step-ahead prediction errors. These are then analysed by a neural classifier in order to take the appropriate decision regarding the actual behaviour of the process.

A New Dynamic Neuro-Fuzzy System Applied to Fault Diagnosis of an Evaporation Station

The problems of fault detection and isolation of dynamic systems has been studied intensively in the recent years and many successful industrial applications have been reported. In the main these studies have been restricted to model based techniques, with few reports of successful implementation of data driven approaches. These data driven approaches have been range from the application of linear regression techniques, to neuro-fuzzy systems. This paper reports on application of, Multivariate Statistical Process Control (MSPC) methodologies, which can provide a diagnostic tool for the on-line or real time monitoring and detection of the process malfunction is proposed. Finally the effectiveness of Partial Least Squares (PLS) in FDI of the Three-Tank system are represented and discussed through simulation results.

Ron J. Patton

Papers

Active fault tolerant control of a wind turbine via T-S fuzzy model predictive control

A benchmark study approach to fault diagnosis of industrial process control systems

A New Dynamic Neuro-Fuzzy System Applied to Fault Diagnosis of an Evaporation Station

PLS-based FDI of a Three-Tank laboratory system

Fault-tolerant consensus control of multi-agent systems under actuator/sensor faults and channel noises: A distributed anti-attack strategy