Urban rail neighborhood construction monitoring method and system based on deep neural network

Abstract

The invention relates to the technical field of urban rail transit safety, and particularly discloses an urban rail neighborhood construction monitoring method and system based on a deep neural network. The method comprises the following steps: receiving a sound time domain signal from a preset position, judging the sound time domain signal through a trained first deep neural network, further judging whether the drilling sound is sent in a protection neighborhood at the preset position when the drilling sound exists, if so, triggering an alarm, and the recognition accuracy of the trained first deep neural network on the drilling sound is up to 99.6%. By integrating the subsequent steps, the method can effectively detect the illegal construction situation in the urban rail protection neighborhood, and has the benefits of timeliness, comprehensiveness, manpower saving and the like. According to the monitoring system, the effects of the method can be achieved by arranging the sound sensing and judging module, the communication module and the server side, and in addition, the system is easy to build, low in cost and capable of being conveniently fused in an existing urban rail management system.

Description

technical field [0001] The invention relates to the technical field of urban rail transit safety, in particular to a method and system for monitoring construction in urban rail neighborhoods based on a deep neural network. Background technique [0002] Urban rail transit (also referred to as urban rail transit) is more often used to refer to various medium and short-distance passenger railway systems newly built in economically developed areas. [0003] From the perspective of the industrial chain, urban rail transit investment is divided into three stages, namely engineering design, engineering construction and post-operation management. Among them, engineering construction is the most critical link. The mechanical and electrical equipment in the engineering construction accounts for 20% of the total cost of rail transit construction, and the signal system accounts for 13.87% of the cost of the mechanical and electrical equipment. Assuming that the 3,000-kilometer urban ra...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a construction monitoring method and system in urban rail neighborhoods based on a deep neural network. The technical problem to be solved is: how to timely, comprehensively and accurately monitor whether there is illegal construction in urban rail neighborhoods, and if there is, conduct automatic alarm

Images