Bbn Technologies Corporation

Bbnt Solutions Llc.

Andrew Charles Coon

Gary Dana Butler

Ernest Scott Stickels

Robert Warren Kanyuck

Howard Allen Lazoff

Richard Phillip Taschler

Genetically adaptive neural network systems and methods provide environmentally adaptable classification algorithms for use, among other things, in multi-static active sonar classification. Classification training occurs in-situ with data acquired at the onset of data collection to improve the classification of sonar energy detections in difficult littoral environments. Accordingly, in-situ training sets are developed while the training process is supervised and refined. Candidate weights vectors evolve through genetic-based search procedures, and the fitness of candidate weight vectors is evaluated. Feature vectors of interest may be classified using multiple neural networks and statistical averaging techniques to provide accurate and reliable signal classification.

Genetically adaptive neural network classification systems and methods

Shells fired from the gun of a ship create an underwater explosion that is used to drive a sonar system. Sonobuoys &lsqb; &rsqb; and/or a ship-towed array measure acoustic signals caused by the underwater explosion. A ship processing component &lsqb; &rsqb; analyzes the signals and locates reflections of objects &lsqb; &rsqb; in the signals. In addition to controlling the location at which to fire a shell, an adjustable fuze on the shell may be set to thereby control the depth at which the shell explodes. The low-frequency impulsive nature of the explosion makes it particularly suited for detecting objects in a littoral environment.

Projectile sonar

Growing community of inventors

Columbia, MD, United States of America

Andrew Charles Coon