Autonomous systems are those that evolve over time, and through learning, can make intelligent decisions when faced with unidentified and unknown situations. Artificial Neural Networks (ANN) has been applied to an increasing number of real-world problems with considerable complexity. Due to their learning abilities, ANN-based systems have been increasingly attracting attention in applications where autonomy is critical and where identification of possible fault scenarios is not exhaustive before hand. We have proposed a methodology in which the learning rules that a trained network has adapted can be extracted and refined using rule extraction and rule refinement techniques, respectively, and then these refined rules are subsequently formally specified and verified against requirements specification using formal methods. The effectiveness of the proposed approach has been demonstrated using a case study of an attitude control subsystem of a satellite.

This book provides advanced techniques for precision compensation and fault diagnosis of precision motion systems and rotating machinery. Techniques and applications through experiments and case studies for intelligent precision compensation and fault diagnosis are offered along with the introduction of machine learning and deep learning methods. Machine Learning-Based Fault Diagnosis for Industrial Engineering Systems discusses how to formulate and solve precision compensation and fault diagnosis problems. The book includes experimental results on hardware equipment used as practical examples throughout the book. Machine learning and deep learning methods used in intelligent precision compensation and intelligent fault diagnosis are introduced. Applications to deal with relevant problems concerning CNC machining and rotating machinery in industrial engineering systems are provided in detail along with applications used in precision motion systems. Methods, applications, and concepts offered in this book can help all professional engineers and students across many areas of engineering and operations management that are involved in any part of Industry 4.0 transformation.

This comprehensive work presents the status and likely development of fault diagnosis, an emerging discipline of modern control engineering. It covers fundamentals of model-based fault diagnosis in a wide context, providing a good introduction to the theoretical foundation and many basic approaches of fault detection.

“Fault Detection and Isolation: Multi-Vehicle Unmanned System” deals with the design and development of fault detection and isolation algorithms for unmanned vehicles such as spacecraft, aerial drones and other related vehicles. Addressing fault detection and isolation is a key step towards designing autonomous, fault-tolerant cooperative control of networks of unmanned systems. This book proposes a solution based on a geometric approach, and presents new theoretical findings for fault detection and isolation in Markovian jump systems. Also discussed are the effects of large environmental disturbances, as well as communication channels, on unmanned systems. The book proposes novel solutions to difficulties like robustness issues, as well as communication channel anomalies. “Fault Detection and Isolation: Multi-Vehicle Unmanned System” is an ideal book for researchers and engineers working in the fields of fault detection, as well as networks of unmanned vehicles.

"Education, arts and social sciences, natural and technical sciences in the United States and Canada".

This book considers two popular topics: fault detection and isolation (FDI) and flight data estimation using flush air data sensing (FADS) systems. Literature surveys, comparison tests, simulations and wind tunnel tests are performed. In both cases, a UAV platform is considered for demonstration purposes. In the first part of the book, FDI is considered for sensor faults where a neural network approach is implemented. FDI is applied both in academia and industry resulting in many publications over the past 50 years or so. However few publications consider neural networks in comparison to traditional techniques such as observer based, parameter estimations and parity space approaches. The second part of this book focuses on how to estimate flight data (angle of attack, airspeed) using a matrix of pressure sensors and a neural network model. In conclusion this book can serve as an introduction to FDI and FADS systems, a literature survey, and a case study for UAV applications.