Prospects for further implementation: will be continued as applied.
Research level: no analogues in the world.
Availability of a patent: no.
What additional actions requires further research: Implementation requires further funding.
Brief characteristics, advantages, further application perspective.
A prototype of a new optical infrasound sensor has been created, in which the feedback is calculated by an integrated microprocessor. A set of optimal algorithms that implement the gradient descent method, the neural network method and the Kalman adaptive filtering method for the functioning of the acoustic reconnaissance signal system have been determined. An algorithm and software for the acoustic pattern recognition procedure have been created, where an artificial neural network with three layers is used. The input vector is a line enveloping the spectra of the amplitude-frequency characteristics of signals from the infrasound sensors, which are part of the acoustic reconnaissance-signaling system (ARSS). It is shown that the use of digital sensors of infrasound predetermines the possibility of using only one digital communication channel (wired, wireless or combined) in the ARSS, which significantly reduces its cost and reduces the installation time. The accuracy of determining the parameters (distance, azimuth to the source and time) of the event by the experimental group (acoustic antenna) is sufficient for location. It has been established that the indicated technical means record both signals of natural and technogenic origin with sufficient quality in determining the parameters of disturbances. It is shown that sensors that distort input signals to a lesser extent provide significantly better performance of algorithms for detection, location, recognition and tracking of targets. It was found that for the task of locating objects in on-line mode, it is advisable to use the projectile solutions, which has significant advantages in the speed of algorithm execution than the statistical method according to Fisher’s criterion. It was found that Kohonen’s neural grid with one hidden layer is able to effectively recognize acoustic and seismic characteristics beyond the envelope of the vibration spectrum. According to experimental data, the efficiency is approximately 95%, which meets the modern requirements of reconnaissance and signal systems for the needs of the army and security structures. The directions and measures for the creation of miniature precision sensors of mechanical vibrations for the needs of the army, security systems and geophysical research have been determined. New ultrasound sensors created within the framework of the project with improved amplitude-frequency characteristics (AFC) and digital transmission and processing of data can significantly increase the efficiency of ARSS in location, tracking and target identification at low altitudes in comparison with existing systems. Using precision calculations of the feedback signal using a microcontroller and adding it to the input signal, sensors have been created with significantly improved characteristics in the infrasonic region.
IF YOU ARE INTERESTED IN THIS DEVELOPMENT, PLEASE,
WRITE TO US