Water supply system inspection method and system based on machine vision unit neural network

Abstract

The invention discloses a water supply system inspection method and system based on a machine vision unit neural network. The water supply system inspection method comprises the following steps that S1, a unit neural network is composed of a plurality of sensors, a plurality of cameras and a plurality of execution subsystems, and equipment and an environment standard image library are established;S2, the water supply system runs, and the operation data of the water supply system is collected in real time by the plurality of sensors; S3, the real-time collected operation data is calculated according to the balance condition of the water supply system and whether a leakage condition is likely to occur in the water supply system is judged, If not, go back to execute S2, if yes, S4 is executed; and S4, the plurality of camera inspection is triggered, the plurality of cameras enter a machine vision inspection mode to acquire a real-time image and compare and analyze the real-time image with a standard image library. The water supply system inspection method and system is real-time or short-period and rapid detection, hardware resources and software resources and network resources are optimized, the false alarm rate of the information and the error rate of personnel are reduced, and the safety of the equipment and the personal safety are guaranteed technically.

Description

technical field [0001] The invention belongs to the field of machine vision, image processing and analysis, and industrial production network neural technology, and in particular relates to a water supply system patrol inspection method and system based on machine vision unit neural network. Background technique [0002] Vision enables humans to perceive and understand the existing objective world. Accordingly, the goal of machine vision is to replicate the effects of human vision through electronic perception and understanding of images. Machine vision has applications in transportation, medical care, imaging and other fields, but for energy development and production systems or power systems, there are the following disadvantages: a. The application is less and relatively elementary, and it is limited to the camera to observe some inherent point; b. does not involve or involves less image processing and analysis technology; c. does not form a joint, independent and systema...

AI Technical Summary

Problems solved by technology

Machine vision has applications in transportation, medical care, imaging and other fields, but for energy development and production systems or power systems, there are the following disadvantages: a. The application is less and relatively elementary, and it is limited to the camera to observe some inherent point; b. does not involve or involves less image processing and analysis technology; c. does not form a joint, independent and systematic structure with the actual production site, and the observation of actual production stays at the superficial stage; d. has no foothold On-site production is actually targeted to establish a certain standard comparison mechanism, and the development of camera functions is relatively shallow

[0003] The neural network unit is a complete set of real-time monitoring and tracking system established for a specified object and specific system. This unit has the characteristics of real-time and coverage, but has the following defects: a. The data only comes from the collection of electronic and electrical equipment. If the measuring device or sensing device fails or is damaged, the source of the data is unreliable; b. There is no trigger screen that can match the real-time production situation on site, and the source of information is relatively single. Only by going to the actual location to check and check item by item can a judgment be made, and the emergency response effect is poor; c. There is no clear and objective comparison mechanism and supervision mechanism technically, and only comparison within the system can easily cause hazy and uncertain illusions Not conducive to accurate analysis of equipment status

Images