Elevator fault judgment method and system based on big data feature analysis

Abstract

The invention discloses an elevator fault judgment method and system based on big data feature analysis, and the method comprises the steps: firstly obtaining a vibration signal of an elevator car, carrying out the preprocessing and fast Fourier transform of the vibration signal, converting the vibration signal into a feature map, carrying out the graying and normalization processing of the feature map, and carrying out the recognition of the vibration signal; the method comprises the following steps: firstly, processing a feature map, then taking the processed feature map as a training sample which comprises a normal sample and a fault sample, inputting the training sample into a CNN (Convolutional Neural Network) for learning and training, enabling a model to have a better fault diagnosis effect by optimizing parameters, and realizing real-time judgment on a signal by utilizing the trained CNN so as to quickly and accurately diagnose an elevator fault.

Description

technical field [0001] This application belongs to the technical field of elevator data analysis, and specifically relates to an elevator fault judgment method and system based on big data feature analysis, especially a method based on FFT (Fast Fourier Transform, Fast Fourier Transform) and CNN (Convolutional Neural Networks, Convolutional neural network) elevator fault judgment method and system. Background technique [0002] With the increasing popularity of elevators in recent years, the comfort and safety factor of elevators has also received more and more attention. At the same time, precisely because of the large-scale popularization of elevators, various types of elevator failure problems have emerged in an endless stream. The car of the elevator is an important part of the elevator as a whole, and the safety status of the car has a direct impact on the safety of the elevator. [0003] The elevator car can be said to be the main part of the elevator. It is the elev...

AI Technical Summary

Problems solved by technology

Although the commonly used method of wavelet decomposition plus support vector machine has good results, improper selection of the wavelet base and the number of decomposition layers of wavelet decomposition will cause large errors in the results, and it needs to rely on expert experience

This makes it difficult to diagnose elevator faults based on elevator car vibration signals.

Images