Download or read book Safe and Efficient Aircraft Guidance and Control Using Neural Networks written by Kyle David Julian and published by . This book was released on 2020 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt: Autonomous systems have the potential to reduce costs and increase safety for a variety of applications, including aviation. Whereas automation is used for problems with limited scope, autonomous systems must reason about complex scenarios, including low-probability safety-critical events, where the correct behavior cannot be enumerated. As a result, autonomous systems use computers to reason and make decisions. One method for computing decisions uses a form of optimization called dynamic programming, but the curse of dimensionality leads to large representations of the decision-making policy. One approach to reduce the representation size is to approximate the decision logic. This thesis presents a neural network compression method that trains an accurate neural network approximation of decision logic score tables. Rather than storing the score table in memory, only the neural network parameters need to be stored, reducing the representation size by a factor of 1000 or more. Experiments with Monte Carlo simulations and flight testing indicate that a neural network representation can perform as well as the original policy. Although simulations and flight testing can instill confidence, a finite number of simulations does not guarantee that the neural network behaves correctly in all possible scenarios, as neural networks are well known to behave in unexpected ways. Verifying that the neural network issues safe actions in all scenarios is necessary before they can be used in safety-critical systems. This thesis presents two methods that reason about the weights of the neural networks and the dynamics of the state variables describing the scenario to determine if the neural network makes safe decisions in all scenarios. The first method analyzes the dynamics to compute a region of state variables for each action where that action cannot be safely given. Then, analysis of the network weights determines if any input variables could result in the neural network giving an unsafe action. If these neural network properties are verified, then the neural network is guaranteed to behave safely in all scenarios. If the properties do not hold and the neural network gives an action in its unsafe region, the system as a whole is not necessarily unsafe. If prior neural network actions prevent the system from reaching states where unsafe actions are given, then the neural network may still be safe. This thesis presents a reachability method to determine if unsafe states can be reached using the neural network actions. Beginning with a set of initial states, the reachability method uses the neural network policy and system dynamics to compute the set of states that could be reached at the next time step. The analysis can be repeated to compute the set of states that can be reached over time, ending when the reachable set includes an unsafe state or converges to a steady-state safe set. The reachability method guarantees that the neural network behaves safely if no unsafe states are reachable from the initial set. The two methods described previously verify safety when using a neural network controller, but these methods do not scale well with the dimensionality of the state space. For neural networks with high-dimensional inputs, such as images, these verification methods are intractable. This thesis presents an approach to validate a neural network controller by searching for small input disturbances that cause the neural network controller to reach an unsafe state. The validation method combines reinforcement learning algorithms with analysis of the neural network weights to find the most likely sequence of input disturbances that causes the system to fail. The method scales well for image-based neural networks, and inspection of the failure sequence either reveals system weaknesses or validates that the system requires unrealistic disturbances to fail.

Download or read book Advances in Aerospace Guidance Navigation and Control written by Joël Bordeneuve-Guibé and published by Springer. This book was released on 2015-04-04 with total page 730 pages. Available in PDF, EPUB and Kindle. Book excerpt: The two first CEAS (Council of European Aerospace Societies) Specialist Conferences on Guidance, Navigation and Control (CEAS EuroGNC) were held in Munich, Germany in 2011 and in Delft, The Netherlands in 2013. ONERA The French Aerospace Lab, ISAE (Institut Supérieur de l’Aéronautique et de l’Espace) and ENAC (Ecole Nationale de l’Aviation Civile) accepted the challenge of jointly organizing the 3rd edition. The conference aims at promoting new advances in aerospace GNC theory and technologies for enhancing safety, survivability, efficiency, performance, autonomy and intelligence of aerospace systems. It represents a unique forum for communication and information exchange between specialists in the fields of GNC systems design and operation, including air traffic management. This book contains the forty best papers and gives an interesting snapshot of the latest advances over the following topics: l Control theory, analysis, and design l Novel navigation, estimation, and tracking methods l Aircraft, spacecraft, missile and UAV guidance, navigation, and control l Flight testing and experimental results l Intelligent control in aerospace applications l Aerospace robotics and unmanned/autonomous systems l Sensor systems for guidance, navigation and control l Guidance, navigation, and control concepts in air traffic control systems For the 3rd CEAS Specialist Conference on Guidance, Navigation and Control the International Program Committee conducted a formal review process. Each paper was reviewed in compliance with standard journal practice by at least two independent and anonymous reviewers. The papers published in this book were selected from the conference proceedings based on the results and recommendations from the reviewers.

Download or read book Autonomous Safety Control of Flight Vehicles written by Xiang Yu and published by CRC Press. This book was released on 2021-02-12 with total page 200 pages. Available in PDF, EPUB and Kindle. Book excerpt: Aerospace vehicles are by their very nature a crucial environment for safety-critical systems. By virtue of an effective safety control system, the aerospace vehicle can maintain high performance despite the risk of component malfunction and multiple disturbances, thereby enhancing aircraft safety and the probability of success for a mission. Autonomous Safety Control of Flight Vehicles presents a systematic methodology for improving the safety of aerospace vehicles in the face of the following occurrences: a loss of control effectiveness of actuators and control surface impairments; the disturbance of observer-based control against multiple disturbances; actuator faults and model uncertainties in hypersonic gliding vehicles; and faults arising from actuator faults and sensor faults. Several fundamental issues related to safety are explicitly analyzed according to aerospace engineering system characteristics; while focusing on these safety issues, the safety control design problems of aircraft are studied and elaborated on in detail using systematic design methods. The research results illustrate the superiority of the safety control approaches put forward. The expected reader group for this book includes undergraduate and graduate students but also industry practitioners and researchers. About the Authors: Xiang Yu is a Professor with the School of Automation Science and Electrical Engineering, Beihang University, Beijing, China. His research interests include safety control of aerospace engineering systems, guidance, navigation, and control of unmanned aerial vehicles. Lei Guo, appointed as "Chang Jiang Scholar Chair Professor", is a Professor with the School of Automation Science and Electrical Engineering, Beihang University, Beijing, China. His research interests include anti-disturbance control and filtering, stochastic control, and fault detection with their applications to aerospace systems. Youmin Zhang is a Professor in the Department of Mechanical, Industrial and Aerospace Engineering, Concordia University, Montreal, Québec, Canada. His research interests include fault diagnosis and fault-tolerant control, and cooperative guidance, navigation, and control (GNC) of unmanned aerial/space/ground/surface vehicles. Jin Jiang is a Professor in the Department of Electrical & Computer Engineering, Western University, London, Ontario, Canada. His research interests include fault-tolerant control of safety-critical systems, advanced control of power plants containing non-traditional energy resources, and instrumentation and control for nuclear power plants.

Download or read book Advances in Aerospace Guidance Navigation and Control written by Qiping Chu and published by Springer Science & Business Media. This book was released on 2013-11-18 with total page 773 pages. Available in PDF, EPUB and Kindle. Book excerpt: Following the successful 1st CEAS (Council of European Aerospace Societies) Specialist Conference on Guidance, Navigation and Control (CEAS EuroGNC) held in Munich, Germany in 2011, Delft University of Technology happily accepted the invitation of organizing the 2nd CEAS EuroGNC in Delft, The Netherlands in 2013. The goal of the conference is to promote new advances in aerospace GNC theory and technologies for enhancing safety, survivability, efficiency, performance, autonomy and intelligence of aerospace systems using on-board sensing, computing and systems. A great push for new developments in GNC are the ever higher safety and sustainability requirements in aviation. Impressive progress was made in new research fields such as sensor and actuator fault detection and diagnosis, reconfigurable and fault tolerant flight control, online safe flight envelop prediction and protection, online global aerodynamic model identification, online global optimization and flight upset recovery. All of these challenges depend on new online solutions from on-board computing systems. Scientists and engineers in GNC have been developing model based, sensor based as well as knowledge based approaches aiming for highly robust, adaptive, nonlinear, intelligent and autonomous GNC systems. Although the papers presented at the conference and selected in this book could not possibly cover all of the present challenges in the GNC field, many of them have indeed been addressed and a wealth of new ideas, solutions and results were proposed and presented. For the 2nd CEAS Specialist Conference on Guidance, Navigation and Control the International Program Committee conducted a formal review process. Each paper was reviewed in compliance with good journal practice by at least two independent and anonymous reviewers. The papers published in this book were selected from the conference proceedings based on the results and recommendations from the reviewers.

Download or read book Aircraft Trajectory Control Using Artificial Neural Networks written by Sreehari R. Chanda and published by . This book was released on 1996 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Fault tolerant Flight Control and Guidance Systems written by Guillaume J. J. Ducard and published by Springer Science & Business Media. This book was released on 2009-05-14 with total page 268 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book offers a complete overview of fault-tolerant flight control techniques. Discussion covers the necessary equations for the modeling of small UAVs, a complete system based on extended Kalman filters, and a nonlinear flight control and guidance system.

Download or read book Nonlinear Flight Control Using Neural Networks written by Byoung Soo Kim and published by . This book was released on 1993 with total page 360 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Automated Systems in the Aviation and Aerospace Industries written by Shmelova, Tetiana and published by IGI Global. This book was released on 2019-03-22 with total page 486 pages. Available in PDF, EPUB and Kindle. Book excerpt: Air traffic controllers need advanced information and automated systems to provide a safe environment for everyone traveling by plane. One of the primary challenges in developing training for automated systems is to determine how much a trainee will need to know about the underlying technologies to use automation safely and efficiently. To ensure safety and success, task analysis techniques should be used as the basis of the design for training in automated systems in the aviation and aerospace industries. Automated Systems in the Aviation and Aerospace Industries is a pivotal reference source that provides vital research on the application of underlying technologies used to enforce automation safety and efficiency. While highlighting topics such as expert systems, text mining, and human-machine interface, this publication explores the concept of constructing navigation algorithms, based on the use of video information and the methods of the estimation of the availability and accuracy parameters of satellite navigation. This book is ideal for aviation professionals, researchers, and managers seeking current research on information technology used to reduce the risk involved in aviation.

Download or read book Aircraft Position Prediction Using Neural Networks written by Anuja Doshi and published by . This book was released on 2005 with total page 144 pages. Available in PDF, EPUB and Kindle. Book excerpt: The Federal Aviation Administration (FAA) has been investigating early warning accident prevention systems in an effort to prevent runway collisions. One system in place is the Airport Movement Area Safety System (AMASS), developed under contract with the FAA. AMASS uses a linear prediction system to predict the position of an aircraft 5 to 30 seconds in the future. The system sounds an alarm to warn air traffic controllers if it foresees a potential accident. However, research done at MIT and Volpe National Transportation Systems Center has shown that neural networks more accurately predict the future position of aircraft. Neural networks are self-learning, and the time required for the optimization of safety logic will be minimized using neural networks. More accurate predictions of aircraft position will deliver earlier warnings to air traffic controllers while reducing the number of nuisance alerts. There are many factors to consider in designing an aircraft position prediction neural network, including history length, types of inputs and outputs, and applicable training data. This document chronicles the design, training, performance, and analysis of a position prediction neural network, and the presents the resulting optimal neural network for the AMASS System. Additionally, the neural network prediction model is then compared other prediction models, including a constant speed, linear regression, and an auto regression model. In this analysis, neural networks present themselves as a superior model for aircraft position prediction.

Download or read book Direct Adaptive Aircraft Control Using Dynamic Cell Structure Neural Networks written by and published by . This book was released on 1997 with total page 24 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Nonlinear Flight Control Using Adaptive Critic Based Neural Networks written by Sergio Esteban Roncero and published by . This book was released on 2002 with total page 204 pages. Available in PDF, EPUB and Kindle. Book excerpt: "Ultimately the purpose of the nonlinear flight control system developed in this work is to pave the way for an adaptive reconfigurable nonlinear controller that would make aviation a safe way of transportation even in the presence of control failures and/or damaged aerodynamic surfaces."--Abstract, p. iii.

Download or read book Knowledge Based Aircraft Automation written by National Aeronautics and Space Administration (NASA) and published by Createspace Independent Publishing Platform. This book was released on 2018-07-08 with total page 86 pages. Available in PDF, EPUB and Kindle. Book excerpt: The ultimate goal of this report was to integrate the powerful tools of artificial intelligence into the traditional process of software development. To maintain the US aerospace competitive advantage, traditional aerospace and software engineers need to more easily incorporate the technology of artificial intelligence into the advanced aerospace systems being designed today. The future goal was to transition artificial intelligence from an emerging technology to a standard technology that is considered early in the life cycle process to develop state-of-the-art aircraft automation systems. This report addressed the future goal in two ways. First, it provided a matrix that identified typical aircraft automation applications conducive to various artificial intelligence methods. The purpose of this matrix was to provide top-level guidance to managers contemplating the possible use of artificial intelligence in the development of aircraft automation. Second, the report provided a methodology to formally evaluate neural networks as part of the traditional process of software development. The matrix was developed by organizing the discipline of artificial intelligence into the following six methods: logical, object representation-based, distributed, uncertainty management, temporal and neurocomputing. Next, a study of existing aircraft automation applications that have been conducive to artificial intelligence implementation resulted in the following five categories: pilot-vehicle interface, system status and diagnosis, situation assessment, automatic flight planning, and aircraft flight control. The resulting matrix provided management guidance to understand artificial intelligence as it applied to aircraft automation. The approach taken to develop a methodology to formally evaluate neural networks as part of the software engineering life cycle was to start with the existing software quality assurance standards and to change these standards to include neural network dev...

Download or read book Flight Control Law Synthesis Using Neural Network Theory written by and published by . This book was released on 1990 with total page 21 pages. Available in PDF, EPUB and Kindle. Book excerpt: A commonly used technique for advanced fighter aircraft control law development involves a lengthy process of linearizing the aircraft model and calculating many control system gains via conventional linear methods. This process must be repeated for a number of trim points within the flight envelope to achieve the aircraft stability and flying qualities mandated by various military specifications. Neural networks have been used extensively in many applications such as pattern recognition and optimization because of their ability to create nonlinear mappings of continuous valued inputs through supervised learning. This report outlines a concept which incorporates emerging neural network technology with present-day control theory to produce a system by which optimal controller gains can be automatically generated. The research completed to date and the results contained in this report are intended to provide a proof of concept by applying the neural network synthesis technique to some simplified linear and nonlinear examples.

Download or read book Direct Adaptive Aircraft Control Using Dynamic Cell Structure Neural Networks written by National Aeronautics and Space Administration (NASA) and published by Createspace Independent Publishing Platform. This book was released on 2018-08-17 with total page 36 pages. Available in PDF, EPUB and Kindle. Book excerpt: A Dynamic Cell Structure (DCS) Neural Network was developed which learns topology representing networks (TRNS) of F-15 aircraft aerodynamic stability and control derivatives. The network is integrated into a direct adaptive tracking controller. The combination produces a robust adaptive architecture capable of handling multiple accident and off- nominal flight scenarios. This paper describes the DCS network and modifications to the parameter estimation procedure. The work represents one step towards an integrated real-time reconfiguration control architecture for rapid prototyping of new aircraft designs. Performance was evaluated using three off-line benchmarks and on-line nonlinear Virtual Reality simulation. Flight control was evaluated under scenarios including differential stabilator lock, soft sensor failure, control and stability derivative variations, and air turbulence. Jorgensen, Charles C. Ames Research Center NASA-TM-112198, A-976719A, NAS 1.15:112198 RTOP 519-30-12...

Download or read book Fully Tuned Radial Basis Function Neural Networks for Flight Control written by N. Sundararajan and published by Boom Koninklijke Uitgevers. This book was released on 2002 with total page 182 pages. Available in PDF, EPUB and Kindle. Book excerpt: Fully Tuned Radial Basis Function Neural Networks for Flight Control presents the use of the Radial Basis Function (RBF) neural networks for adaptive control of nonlinear systems with emphasis on flight control applications. A Lyapunov synthesis approach is used to derive the tuning rules for the RBF controller parameters in order to guarantee the stability of the closed loop system. Unlike previous methods that tune only the weights of the RBF network, this book presents the derivation of the tuning law for tuning the centers, widths, and weights of the RBF network, and compares the results with existing algorithms. It also includes a detailed review of system identification, including indirect and direct adaptive control of nonlinear systems using neural networks. Fully Tuned Radial Basis Function Neural Networks for Flight Control is an excellent resource for professionals using neural adaptive controllers for flight control applications.

Download or read book Efficient Predictive Guidance and Control for Aircraft Applications written by Eran Dimantha Bandara Medagoda and published by . This book was released on 2011 with total page 578 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Results on Using Neural Networks for Cost Effective Fault Detection and Identification in Digital Flight Control Systems written by Oded M. Golan and published by . This book was released on 2000 with total page 68 pages. Available in PDF, EPUB and Kindle. Book excerpt: