Elevator Equipment Fault Prediction Method Based on Deep Learning

Abstract

The present invention is an elevator equipment failure prediction method based on deep learning, which belongs to the technical field of elevator failure prediction; the technical problem to be solved is to provide a timely and accurate method for predicting elevator failure type and elevator failure time; in order to solve the above technical problems, this The specific steps of the invention are summarized as follows: first collect the elevator fault record information, and establish a real-time elevator fault information database; then process the elevator fault information into an event sequence and a time sequence; The iterative training of the neural network obtains the output embedding of the two sequences; and then combines the two output embeddings through the joint layer to train the background knowledge of the intensity function and the nonlinear representation of the historical influence; finally, according to the characterization results of the intensity function, the elevator fault type and time; the present invention can assist elevator maintenance personnel to take relevant preventive measures as early as possible to avoid the occurrence of failure events.

Description

technical field [0001] The invention discloses a method for predicting faults of elevator equipment based on deep learning, and belongs to the technical field of fault prediction of elevators. Background technique [0002] With the continuous increase of high-rise buildings, the quality of elevators has attracted people's attention. Elevators that fail to stop, run poorly or even have accidents have affected people's daily life. To reduce the failure rate of elevators, the method of timely and accurate detection and troubleshooting needs further research. The current elevator fault diagnosis and detection methods mostly combine the elevator structure and principle, and propose detection methods for the elevator's mechanical system, electrical control system and safety protection system, but this requires a lot of analysis time. Contents of the invention [0003] The present invention overcomes the deficiencies existing in the prior art, and the technical problem to be so...

AI Technical Summary

Problems solved by technology

Most of the current elevator fault diagnosis and detection methods combine the structure and principle of the elevator, and propose detection methods for the mechanical system, electrical control system and safety protection system of the elevator, but this requires a lot of analysis time

Images