A Signal Recognition Method for Airport Optical Fiber Perimeter Early Warning System

Abstract

The invention relates to a signal identification method of a fiber perimeter early-warning system of an airport. The method comprises the following steps: (1) signal acquisition; to be specific, collecting a light signal by a perimeter early-warning system and converting the signal into an original electric signal X(n); (2), pretreatment; to be specific, carrying out processing like filtering and amplification on the original electric signal X(n) to obtain an electric signal X' (n); (3), downsampling; to be specific, carrying out downsampling on a disturbing signal to obtain an x(n); (4), time-frequency characteristic obtaining at a zero level; to be specific, carrying out processing on the signal x(n) after downsampling according to a formula to obtain a time-frequency characteristic; (5) characteristic extraction; to be specific, extracting a maximum value M, a zero-crossing frequency number K, frequency deviation D, a frequency sample entropy S, and a total signal energy amount E; and (6), intrusion classification; to be specific, inputting five typical characteristics into probabilistic neural networks of five input layers and determining an intrusion type based on comparison of output layers. With the method, a problem that the signal identification precision are affected by the non-stable characteristic of the output signal and the similarity of the intrusion signal and the false-alarm signal of the fiber perimeter early-warning system of the airport can be solved; different disturbance types can be identified effectively; and the real-time performance and practicability are high.

Description

technical field [0001] The invention relates to an early warning pattern recognition technology for an airport perimeter system, in particular to a signal identification method for an airport optical fiber perimeter early warning system. Background technique [0002] The existing types of perimeter security systems at home and abroad mainly include: video surveillance, microwave field, infrared radiation, electronic fence, etc., but they have disadvantages such as small application range, low sensitivity, easy to be affected by the environment, high false alarm rate and expensive price. restrict its development. The optical fiber perimeter warning system uses optical fiber as a sensor to perceive changes in external signals. It has high sensitivity, strong anti-interference ability, strong environmental adaptability, low cost and long life. It has become the main development technology in the field of perimeter security. This system adopts the principle of Mach-Zehnder opti...

AI Technical Summary

Problems solved by technology

[0004] The invention aims at the problem that the non-stationary characteristics of the output signal of the M-Z interferometer type airport optical fiber perimeter early warning system and the similarity between the intrusion signal and the false alarm signal seriously affect the accuracy of signal recognition, and provides a signal based on derivative analysis at zero level recognition methods

Images