Cable hidden danger identification method and device based on MFCC and diffusion Gaussian mixture model

Abstract

The invention provides a cable hidden danger identification method and device based on an MFCC and a diffusion Gaussian mixture model, and relates to the technical field of cable hidden danger identification, and the method comprises the steps: obtaining first sound data, and carrying out the preprocessing of the first sound data after low-pass filtering noise reduction, so as to obtain second sound data; performing frequency domain transformation on the second sound data to obtain third sound data; dividing the third sound data into a third sound data test set and a third sound data training set, constructing a diffused Gaussian mixture model classifier, and training the constructed diffused Gaussian mixture model classifier by using the third sound data test set so as to optimize parameters of the diffused Gaussian mixture model classifier; and testing the diffusive Gaussian mixture model classifier with optimized parameters by using the third sound data training set. According to the invention, the technical problem that it is difficult to detect the sounding time of external breaking factors or collect a large amount of invalid sound data in the prior art can be solved.

Description

technical field [0001] The invention relates to the technical field of cable hidden danger identification, in particular to a cable hidden danger identification method and device based on MFCC and a diffused Gaussian mixture model. Background technique [0002] With the rapid development of urban construction, urban construction continues to expand and accelerate, and major municipal projects are also rolled out, mainly involving municipal key projects, subways, bridges, roads, real estate development and urban supporting pipe network water supply, heat, gas, communications Construction, etc., always threaten the safety of underground cables. The traditional method of preventing external cable breakage adopts the methods of regular inspections and on-site nursing. This method is not only extremely inefficient, but also cannot detect hidden dangers in time due to the existence of the inspection cycle, and then carry out countermeasures. Therefore, at this stage, underground ...

AI Technical Summary

Problems solved by technology

However, due to the randomness and low loudness of excavators and pipe pulling machines, and the cable channels are mostly built on the roadside, and the background interference from cars and other backgrounds is large, it is difficult to detect the sounding time of external factors or collect a large number of them in actual work. invalid sound data

Images