FIELD: hydro acoustics.
SUBSTANCE: invention relates to underwater acoustics and can be used to build intelligent automated systems for classifying marine targets, detected by the signs of amplitude-phase modulation of low-frequency signals of the pumping of the marine environment by radiation and fields of objects. Intelligent system for detecting and classifying marine targets contains a working zone of non-linear interaction and parametric conversion of pump and information waves formed in the marine environment. Length of the working area is equal to the length of the controlled section of the marine environment, for which the radiating and receiving transducers are located at opposite boundaries of the section. Input of the radiating transducer is connected by a submarine cable to the output path of the radiation of pump signals, which contains series-connected pump signals of a stabilized frequency, a power amplifier and a unit for matching its output with a submarine cable. Output of the receiving transducer is connected by a submarine cable to the input of a path for receiving, processing and recording information signals, which contains a series-connected broadband amplifier, a time-frequency converter, a spectrum analyzer and a recorder functionally associated with it. Principal difference from the prototype is that the path of neural network recognition and classification is additionally introduced, containing a target class recognition unit based on amplitude-frequency characteristics covered by feedback from the learning unit. Output of the spectrum analyzer of the reception, processing and recording wave of information waves is connected to the input of the target class recognition unit according to the amplitude-frequency characteristics of the neural network recognition and classification path, at the output of which a signal is generated according to the type of target according to the degree of belonging of the studied spectral region to the object of classification. Technical result is achieved by applying computational operations of neural networks and an operatively updated library of mathematically processed spectrogram images of marine targets.
EFFECT: automation of the process of recognizing classes of offshore targets (surface or underwater object) detected by the signs of amplitude-phase modulation of low-frequency signals of the pumping of the marine environment by radiation and fields of objects.
1 cl, 5 dwg
