《机电工程》杂志社科技期刊核心期刊论文投稿机电一体化机械、仪表电工自动化、计算机浙江大学主办

Introduction

International Standard Serial Number:

ISSN 1001-4551

Sponsor:

Zhejiang University;

Zhejiang Machinery and Electrical Group

Edited by:

Editorial of Journal of Mechanical & Electrical Engineering

Chief Editor:

ZHAO Qun

Vice Chief Editor:

TANG ren-zhong,

LUO Xiang-yang

Tel:

86-571-87041360,87239525

Fax:

86-571-87239571

Add:

No.9 Gaoguannong,Daxue Road,Hangzhou,China

P.C:

310009

E-mail:

meem_contribute@163.com

Prediction method of elevator wire rope slippage based on POA-CNN-REGST model

Published:2023-08-14 author:ZHU Xi-shan, LUO Zhen, YI Can-can, et al. Browse: 402 Check PDF documents

Prediction method of elevator wire rope slippage based on

POA-CNN-REGST model

ZHU Xi-shan1, LUO Zhen1, YI Can-can2, YOU Guang-hui2, XUE Jia-cheng2

(1.Guangxi Special Equipment Inspection and Research Institute, Nanning 530299, China; 2.School of Machinery and Automation,

Wuhan University of Science and Technology, Wuhan 430081, China)

Abstract: Aiming at the problem that excessive slip between elevator traction sheave and wire rope may lead to important accidents, a prediction method of slip of elevator wire rope based on pelican optimization algorithm-convolutional neural network-stacked regression (POA-CNN-REGST) was proposed. Firstly, the data production function was used to generate samples, and the Gaussian white noise was added to the samples. The POA-CNN-REGST, support vector machine (SVM), relevance vector machine (RVM) models were used to train and learn the simulation data respectively. Then, the relevant data such as elevator slip collected by the experimental base was normalized, and the POA-CNN-REGST was used to predict the elevator wire rope slip. Finally, the results were compared with the traditional statistical models SVM and RVM. The research results show that when using the same training set and testing set, the root mean square error of simulation data analysis is 0.049 6, while in the real data analysis, the root mean square error and average absolute percentage error are as low as 0.066 1 and 0.073 3. Whether it is simulation data analysis or real data analysis, the prediction accuracy of the model is much higher than that of SVM and RVM, which shows that it has high reliability in the measurement of elevator wire rope slip.

Key words: traction elevator; wire rope; slip amount; pelican optimization algorithm(POA); convolutional neural network(CNN); stacked regression(REGST) model

Advanced Search

Online Office System

Chinese Core Periodicals
Chinese Sci-tech Core Periodicals
SA, INSPEC Indexed
CSA: T Indexed
UPD:Indexed