Название: Developing Digital RF Memories and Transceiver Technologies for Electromagnetic Warfare
Автор: Phillip E. Pace
Издательство: Artech House
Год: 2022
Страниц: 919
Язык: английский
Формат: pdf (true)
Размер: 15.5 MB

This book provides a comprehensive resource and thorough treatment in the latest development of Digital RF Memory (DRFM) technology and their key role in maintaining dominance over the electromagnetic spectrum. Part I discusses the use of advanced technology to design transceivers for spectrum sensing using unmanned systems to dominate the electromagnetic spectrum. Part II uses artificial intelligence and machine learning to enable modern spectrum sensing and detection signal processing for electronic support and electronic attack. Another key contribution is examination of counter-DRFM techniques. DRFM and transceiver design details and examples are provided along with the MATLAB software allowing the reader to construct their own embedded DRFM transceivers for unmanned systems. It examines the design trade-offs in developing multiple, structured, false target synthesis DRFM architectures and aids in developing counter-DRFM techniques and distinguish false target from real ones. Written by an expert in the field, and including MATLAB design software, this is the only comprehensive book written on the subject of DRFM.

Along with the explosion in unmanned air, land and sea vehicles, these on-board microdata centers are pushing the bounds of size, weight, and power consumption while their size continues to shrink. The on-board processors must handle the massive amounts of data from the sensors to avoid collision and perform the surveillance and reconnaissance mission – transforming the raw sensor data into the required decision-level knowledge, all while, for example, navigating an ingress for suppression. The biggest news item nevertheless, is Artificial Intelligence (AI), autonomous weapons, and Machine Learning (ML), grabbing the headlines and they will continue to do so into the foreseeable future. Being able to easily handle the complex Big Data problems as a response management server and friendly copilot system deserves special attention! However, the topic of autonomous weapons, with its many ethical implications, demands some formal inquiry and doctrine especially for unmanned airborne systems (UAS). With a network of UAS, AI, and highly capable DRFM transceivers, a flexible design can be realized for any desired mission.

Unmanned platforms (space, air, surface, subsurface) and AI are now commanding center stage in any discussion of future military requirements and objectives. Current (TTPs) must now incorporate AI with each mission objective giving each platform its own unique capabilities. Unmanned movement (e.g., flight) is one matter; however, autonomous or automatic movement (or flight) is quite another. Full autonomy requires the use of a AI and is a major technology challenge replete with its own controversies–not only technologically, but also ethically, morally, and legally. In the Chapter 9, AI is presented as an electromagnetic technology method of EMS exploration and exploitation. Understanding the difference between deep learning and machine learning is emphasized with applications to automatic sensing, detection, and classification of emitters, including unknown emitters that have not previously been encountered. We also walk through how to construct a feature vector from a radar and/or communication signal’s (T-F) and bifrequency (B-F) detection image. The use of principal component analysis is used to reduce the size of the feature vector. Machine Learning classification algorithms are used to identify, recognize, and specify the particular emitter. A detailed description of a perceptron and a multilayer perceptron classification nonlinear neural network (NN) representing the human brain is given.