Escalator fault prediction and health management method and system based on multi-dimensional monitoring

Abstract

The invention discloses an escalator failure prediction and health management method and system for multi-dimensional monitoring. By acquiring long-term monitoring sample data of an escalator, the long-term monitoring sample data includes multi-dimensional monitoring data of multiple components, By constructing a deep iterative neural network learning model for real-time fault judgment and real-time health status judgment, using the machine learning model and looping feedback to improve the efficiency of data analysis, and analyze the monitoring data and fault status values ​​in the data model relationship to solve the problem of false positives in single-dimensional monitoring faults.

Description

technical field [0001] The invention belongs to the technical field of comprehensive monitoring of underground infrastructure, and in particular relates to a multi-dimensional monitoring escalator fault prediction and health management method and system. Background technique [0002] At present, escalators are used to transport passengers up or down between different floors of buildings, and are widely used in train stations, subway stations, bus stations, shopping malls, airports and other crowded places. The working principle of the escalator is a chain-type circular conveyor belt, which is a forced drive, so once it gets stuck, it may cause damage to the equipment, and its moving parts are exposed and in direct contact with people, posing a huge safety hazard. The main feature of its work is: open type, so the involvement of foreign matter in the gap is the main danger of personal injury and equipment damage. There are many types of escalator failures in the rail transit...

AI Technical Summary

Problems solved by technology

[0004] In view of the above defects or improvement needs of the prior art, the present invention provides a multi-dimensional monitoring escalator fault prediction and health management method and system, which constructs a deep iterative neural network by acquiring long-term monitoring sample data of the escalator The learning model is used for real-time fault judgment and real-time health status judgment, using the machine learning model and looping feedback to improve the efficiency of data analysis, and analyze the numerical relationship between monitoring data and fault status in the data model to solve single-dimensional monitoring faults The problem of false positives

Images