基于LSTM的工业互联网设备工作状态预测

doi:10.3969/j.issn.1006-2475.2020.01.001

计算机与现代化

• 人工智能 • 下一篇

基于LSTM的工业互联网设备工作状态预测

（中国石油大学（华东）计算机与通信工程学院，山东青岛266580）

收稿日期:2019-03-05 出版日期:2020-02-13 发布日期:2020-02-13
作者简介:李兆桐(1995-)，男，山东青州人，硕士研究生，研究方向：深度学习,数据挖掘，E-mail: 768109309@qq.com；张卫山(1970-)，男，上海四平人，教授，硕士生导师，博士，研究方向：人工智能及其应用，大数据处理，数据挖掘；郭武武(1993-)，男，湖北潜江人，研究方向：时间序列分析，深度学习。
基金资助:
国家自然科学基金资助项目（61309024）；山东省重点科研项目（2017GGX10140）；山东省自然科学基金资助项目（F020509，F060604）

LSTM-based Working State Prediction of Industrial Internet Equipment

(School of Computer and Communication Engineering, China University of Petroleum (East China), Qingdao 266580, China)

Received:2019-03-05 Online:2020-02-13 Published:2020-02-13

摘要/Abstract

摘要： 随着工业互联网技术的发展，工业互联网设备的工作状态预测对于提升设备的可靠性具有重要意义。在实际的工业场景中，由于设备数据高度离散且在多个时间段内相互重合，简单的单信号预测和阈值方法是无效的。本文提出一种基于LSTM（长短时记忆）神经网络的设备工作状态预测模型。首先使用SMOTE算法进行数据倾斜处理，利用PCA算法进行数据降维，之后基于LSTM神经网络构建设备工作状态预测模型，最后利用F1分数值进行模型评估。本文基于真实的空调压缩机数据进行实验验证，实验结果表明了本文方法的有效性。

关键词: 长短时记忆神经网络, 时间序列预测, 工业互联网设备

Abstract: With the development of industrial Internet technology, working state prediction of industrial Internet equipment is of great significance for improving the reliability of equipment. In practical industrial scenarios, simple single-signal prediction and threshold methods are ineffective because the data is highly discrete and coincides over multiple time periods. This paper presents a working state prediction model of industrial Internet equipment based on LSTM (Long Short-Term Memory) neural network. Firstly, this paper uses the SMOTE algorithm for data skew processing and the PCA algorithm for data dimensionality reduction, then builds the working state prediction model of industrial Internet equipment based on LSTM neural network. Finally the model is evaluated by F1-Score. This paper is based on real air conditioning compressor data for experimental verification. The experimental results show the effectiveness of the proposed method.

Key words: LSTM neural network, time series prediction, industrial Internet equipment

中图分类号:

TP277
TP18

李兆桐，张卫山，郭武武. 基于LSTM的工业互联网设备工作状态预测[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2020.01.001.

LI Zhao-tong, ZHANG Wei-shan, GUO Wu-wu. LSTM-based Working State Prediction of Industrial Internet Equipment[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2020.01.001.

参考文献

［1］周剑飞,刘晨. 基于LSTM的设备故障在线检测方法［J/OL］. 计算机工程与应用:1-9［2019-03-05］. http://kns.cnki.net/kcms/detail/11.2127.TP.20181225.2104.005.html.
［2］ DRAGOMIR O E, GOURIVEAU R, DRAGOMIR F, et al. Review of prognostic problem in condition-based maintenance［C］// 2009 IEEE European Control Conference. 2009:1587-1592.
［3］ CHANDOLA V, BANERJEE A, KUMAR V. Anomaly detection: A survey［J］. ACM Computing Surveys (CSUR), 2009,41(3):Article No.15.
［4］ SIPOS R, FRADKIN D, MOERCHEN F, et al. Log-based predictive maintenance［C］// Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2014:1867-1876.
［5］ RAWAT S, RAWAT S. Multi-sensor data fusion by a hybrid methodology: A comparative study［J］. Computers in Industry, 2016,75(C):27-34.
［6］ ZHANG K, XU J, MIN M R, et al. Automated IT system failure prediction: A deep learning approach［C］// 2016 IEEE International Conference on Big Data. 2016:1291-1300.
［7］ ZHU X, HUANG Z, YANG Y, et al. Self-taught dimensionality reduction on the high-dimensional small-sized data［J］. Pattern Recognition, 2013,46(1):215-229.
［8］ QIU X, FU D, FU Z. An efficient dimensionality reduction approach for small-sample size and high-dimensional data modeling［J］. Journal of Computers, 2014,9(3):576-581.
［9］ SHARMA N, SAROHA K. A novel dimensionality reduction method for cancer dataset using PCA and feature ranking［C］// 2015 IEEE International Conference on Advances in Computing, Communications and Informatics (ICACCI). 2015:2261-2264.
［10］ABULIGAH L M, KHADER A T, AI-BETAR M A, et al. Text feature selection with a robust weight scheme and dynamic dimension reduction to text document clustering［J］. Expert Systems with Applications, 2017,84:24-36.
［11］陈志平,汪赞,张国安,等. 基于大数据的电梯故障诊断与预测研究［J］. 机电工程, 2019,36(1):90-94.
［12］范李平,张晓辉,苏伟. 基于大数据挖掘的变电设备故障预警研究及应用［J］. 电力大数据, 2019(1):1-7.
［13］王桂兰,赵洪山,米增强. XGBoost算法在风机主轴承故障预测中的应用［J］. 电力自动化设备, 2019,39(1):73-77.
［14］LEAHY K, HU R L, KONSTANTAKOPOULOS I C, et al. Diagnosing wind turbine faults using machine learning techniques applied to operational data［C］// 2016 IEEE International Conference on Prognostics and Health Management. 2016:1-8.
［15］HINTON G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks［J］. Science, 2006,313(5786):504-507.
［16］ASSENDORP J P. Deep Learning for Anomaly Detection in Multivariate Time Series Data［D］. Hochschule für Angewandte Wissenschaften Hamburg, 2017.
［17］〖JP2〗MALHOTRA P, TV V, RAMAKRISHNAN A, et al. Multi-sensor prognostics using an unsupervised health index based on LSTM encoder-decoder［C］//The 1st ACM SIGKDD Workshop on Machine Learning for Prognostics Health Management. 2016.
［18］INCE T, KIRANYAZ S, EREN L, et al. Real-time motor fault detection by 1-D convolutional neural networks［J］. IEEE Transactions on Industrial Electronics, 2016,63(11):7067-7075.
［19］JOLLIFFE I. Principal Component Analysis［M］. Springer Berlin Heidelberg, 2011.
［20］FAWCETT T, PROVOST F. Adaptive fraud detection［J］. Data Mining and Knowledge Discovery, 1997,1(3):291-316.
［21］〖JP+1〗LEWIS D D, CATLETT J. Heterogeneous uncertainty sampling for supervised learning［C］// Proceedings of the 11th International Conference on Machine Learning. 1994:148-156.
［22］JAPKOWICZ N, MYERS C, GLUCK M. A novelty detection approach to classification［C］// International Joint Conference on Artificial Intelligence. 1995, 1: 518-523.
［23］CHAWLA N V, BOWYER K W, HALL L O, et al. SMOTE: Synthetic minority over-sampling technique［J］. Journal of Artificial Intelligence Research, 2002,16: 321-357.
［24］HOCHREITER S, SCHMIDHUBER J. Long short-term memory［J］. Neural Computation, 1997,9(8):1735-1780.

[1]	刘瑞雪, 李文, 刘芳, 杜守国. 用于具有缺失值的时间序列预测的张量自回归补全算法[J]. 计算机与现代化, 2023, 0(09): 51-58.
[2]	孙子雨, 任燃, 魏曦哲. 基于DTW-TCN的股票分类及预测研究[J]. 计算机与现代化, 2023, 0(08): 31-37.
[3]	石志伟, 武志峰, 张哲. 纠正学习策略下LightGBM-GRU模型的股票波动率预测[J]. 计算机与现代化, 2023, 0(01): 95-102.
[4]	周昌野, 李程. 基于GS-LSTM模型的铁路货运量预测[J]. 计算机与现代化, 2022, 0(10): 24-28.
[5]	郭成, 王宵, 王波, 王加富. 基于多层融合神经网络模型的短期电力负荷预测方法[J]. 计算机与现代化, 2021, 0(10): 94-99.
[6]	王志平,郑宝友,刘仪伟. 一种改进的LSTM模型在图像标题生成中的应用[J]. 计算机与现代化, 2020, 0(04): 37-.
[7]	张诗林. 基于Bi-LSTM和CRF的中文网购评论中商品属性提取[J]. 计算机与现代化, 2019, 0(02): 93-.

基于LSTM的工业互联网设备工作状态预测

LSTM-based Working State Prediction of Industrial Internet Equipment

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

本文评价