| Author Name | Affiliation | | Xunsheng Ji | School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, Jiangsu, China | | Dazhi Wang | School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, Jiangsu, China | | Kun Jiang | School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, Jiangsu, China |
|
| Abstract: |
| In this paper, an improved two-dimensional convolution neural network (2DCNN) is proposed to monitor and analyze elevator health, based on the distribution characteristics of elevator time series data in two-dimensional images. The current and effective power signals from an elevator traction machine are collected to generate gray-scale binary images. The improved two-dimensional convolution neural network is used to extract deep features from the images for classification, so as to recognize the elevator working conditions. Furthermore, the oscillation criterion is proposed to describe and analyze the active power oscillations. The current and active power are used to synchronously describe the working condition of the elevator, which can explain the co-occurrence state and potential relationship of elevator data. Based on the improved integration of local features of the time series, the recognition accuracy of the proposed 2DCNN is 97.78%, which is better than that of a one-dimensional convolution neural network. This research can improve the real-time monitoring and visual analysis performance of the elevator maintenance personnel, as well as improve their work efficiency. |
| Key words: elevator condition current active power two-dimensional convolution network (2DCNN) |
| DOI：10.11916/j.issn.1005-9113.21062 |
| Clc Number:TU857 |
| Fund: |
|
| Descriptions in Chinese: |
| 电流与有功功率二维图像的电梯状态识别 吉训生，王大智，江昆 （江南大学 物联网工程学院，江苏 无锡214122） 摘要：本文基于电梯时间序列数据在二维图像中的分布特征，提出一种改进的二维卷积神经网络（2DCNN）来监测和分析电梯的健康状况。收集来自电梯曳引机的电流和有效功率信号以生成灰度二值图像，基于改进的二维卷积神经网络从图像中提取深层特征进行分类，以识别电梯的工作状态。此外，提出振荡判据来描述和分析有功功率振荡。电流和有功功率用于同步描述电梯的工作状态，可以解释电梯数据的同现状态和电位关系。基于时间序列局部特征的改进集成，所提出的2DCNN的识别准确率为97.78%，优于一维卷积神经网络。本研究可以提高电梯维保人员的实时监控和可视化分析能力，提高工作效率。 关键词：电梯工况，电流，有功功率，二维卷积神经网络（2D-CNN） |
