Fault Diagnosis of Laminar Cooling Roller Motor Based on Morphological Combination Patterns Mining of Multi-Current Features

MA Tian-yu; LIU Si-ya; LIU Jin-ping; ZHENG Zhi-wei; LI Zhi-peng

doi:10.12263/DZXB.20211596

您当前的位置：

首页 >

文章列表页 >

Fault Diagnosis of Laminar Cooling Roller Motor Based on Morphological Combination Patterns Mining of Multi-Current Features

PAPERS | 更新时间：2025-12-08

- Fault Diagnosis of Laminar Cooling Roller Motor Based on Morphological Combination Patterns Mining of Multi-Current Features
- ACTA ELECTRONICA SINICA Vol. 51, Issue 4, Pages: 870-878(2023)
- 作者机构：
  
  1.湖南师范大学物理与电子科学学院，湖南长沙 410006
  2.湖南师范大学信息科学与工程学院，湖南长沙 410006
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(61971188)
- DOI：10.12263/DZXB.20211596
  CLC： TP277
- Received：29 November 2021，
  
  Revised：2022-08-31，
  
  Published：25 April 2023
- 稿件说明：
移动端阅览
马天雨,刘思亚,刘金平等.基于多电流特征形态组合模式挖掘的层冷辊电机故障诊断[J].电子学报,2023,51(04):870-878.

MA Tian-yu,LIU Si-ya,LIU Jin-ping,et al.Fault Diagnosis of Laminar Cooling Roller Motor Based on Morphological Combination Patterns Mining of Multi-Current Features[J].ACTA ELECTRONICA SINICA,2023,51(04):870-878.
马天雨,刘思亚,刘金平等.基于多电流特征形态组合模式挖掘的层冷辊电机故障诊断[J].电子学报,2023,51(04):870-878. DOI： 10.12263/DZXB.20211596.

MA Tian-yu,LIU Si-ya,LIU Jin-ping,et al.Fault Diagnosis of Laminar Cooling Roller Motor Based on Morphological Combination Patterns Mining of Multi-Current Features[J].ACTA ELECTRONICA SINICA,2023,51(04):870-878. DOI： 10.12263/DZXB.20211596.

摘要

针对人工点检层冷辊电机存在过度维修和故障漏报的问题，本文提出一种基于多电流特征形态组合模式挖掘的故障诊断方法.该方法选取与故障相关的六种关键电流特征，计算各特征的上下分位数形成边界，采用Bayes-L-BFGS（Bayes Limited-memory Broyden-Fletcher-Goldfarb-Shanno）算法自动拟合出各特征的边界形态；针对形态样本少的问题，本文提出一种用于形态识别的SCNN（Spetial Convolutional Neural Network）-Transformer模型. 通过训练Siamese-CNN准确识别边界形态，并训练Transformer识别边界时序关系与形态变化程度，融合两个模型的识别结果确定边界形态类型；以边界形态类型作为基因片段，采用遗传算法挖掘出不同故障对应的多电流特征形态组合模式，形成用于故障类型匹配的形态组合模式库.在某钢厂层冷辊电机上对本文方法进行在线验证，准确率超过90%，无关键故障漏报与误报.

Abstract

Aiming at the problems of excessive maintenance and fault omission of laminar cooling roller motor in the manual inspection layer

this paper proposes a fault diagnosis method based on morphological combination patterns mining of multi-current features. This method selects six key current features related to the fault

calculates each upper and lower quantiles of the features to form the boundary

and the Bayes-L-BFGS (Bayes Limited-memory Broyden-Fletcher-Goldfarb-Shanno) algorithm is used to automatically fit the boundary morphology of each feature. For the problem of few morphological samples

a SCNN (Spetial Convolutional Neural Network)-Transformer model for morphological recognition is proposed. By training Siamese-CNN

the model accurately identifies the boundary morphology

and trains Transformer to identify the boundary timing relationship and the degree of morphological change

and combines the recognition results of the two models to determine the morphological type. The paper uses the morphological type as the gene segment

and the genetic algorithm is used to mine the morphological combination patterns of multi-current features corresponding to different faults. The fault morphological combination patterns is used to form a morphological combination patterns library for fault type matching. The proposed method is verified online on laminar cooling roller motors in a steel mill

and the accuracy rate exceeds 90% with no missing or false alarm of key faults.

关键词

Keywords

references

郑昌琼 . 简明材料词典 [Z ] . 北京 : 科学出版社 , 2002: 311 .

ZHENG Changqiong . Concise Material Dictionary [Z ] . Beijing : Science Press , 2002: 311 . (in Chinese)

那宝魁 . 钢铁企业标准化管理体系 [M ] . 北京 : 冶金工业出版社 , 2015 : 106 .

NA Baokui . Standardized Management System of Iron and Steel Enterprises [M ] . Beijing : Metallurgical Industry Press , 2015 : 106 . (in Chinese)

刘金平 , 王杰 , 唐朝晖 , 等 . 基于自适应滑窗递归稀疏主成分分析的工业过程故障监测 [J ] . 电子学报 , 2020 , 48 ( 9 ): 1795 - 1803 .

LIU Jinping , WANG Jie , TANG Chaohui , et al . Industrial process fault monitoring based on adaptive sliding window-recursive sparse principal component analysis [J ] . Acta Electronica Sinica , 2020 , 48 ( 9 ): 1795 - 1803 . (in Chinese)

沈政 . 热轧层冷电机负载电流在线监控技术及其应用 [J ] . 科技经济市场 , 2020 , 11 ( 6 ): 18 - 20 .

SHEN Zheng . Online monitoring technology of load current of layer cooling motor in hot rolling and its application [J ] . Science, Technology and Economic Market , 2020 , 11 ( 6 ): 18 - 20 . (in Chinese)

董云飞 . 基于知识的电动机故障诊断专家系统 [J ] . 中国科技博览 , 2014 , 16 ( 10 ): 277 .

DONG Yunfei . Motor fault diagnosis expert system based on knowledge [J ] . China Science and Technology Expo , 2014 , 16 ( 10 ): 277 . (in Chinese)

蔡少辉 . 基于振动信号分析的电机故障诊断应用研究 [J ] . 电子测试 , 2021 , 23 ( 6 ): 95 - 96 .

CAI Shaohui . Application research of motor fault diagnosis based on vibration signal analysis [J ] . Electronic Testing , 2021 , 23 ( 6 ): 95 - 96 . (in Chinese)

KUMAR P , HATI A S . Review on machine learning algorithm based fault detection in induction motors [J ] . Archives of Computational Methods in Engineering , 2021 , 28 ( 3 ): 1929 - 1940 .

赵慧敏 . 基于智能优化方法的SVM电机故障诊断模型研究 [J ] . 大连交通大学学报 , 2016 , 37 ( 1 ): 92 - 96 .

ZHAO Huimin . Research on motor fault diagnosis model for support vector machine based on intelligent optimization methods [J ] . Journal of Dalian Jiaotong University , 2016 , 37 ( 1 ): 92 - 96 . (in Chinese)

王训训 , 陈天 , 刘正杰 , 等 . 粒子群优化融合随机森林的电机故障诊断方法 [J ] . 微特电机 , 2019 , 47 ( 10 ): 42 - 45 .

WANG Xunxun , CHEN Tian , LIU Zhengjie , et al . Motor fault diagnosis method based on particle swarm optimization and random forest [J ] . Small ＆ Special Electrical Machines , 2019 , 47 ( 10 ): 42 - 45 . (in Chinese)

谢丰 , 付文鹏 , 李阳 , 等 . 基于贝叶斯决策模型的热轧卷筒电机故障诊断 [J ] . 中国冶金 , 2021 , 31 ( 4 ): 68 - 73 .

XIE F , FU W P , LI Y , et al . Fault diagnosis of reel motor in hot continuous rolling based on Bayesian decision [J ] . China Metallurgy , 2021 , 31 ( 4 ): 68 - 73 . (in Chinese)

张行 , 朱树先 . 改进的神经网络分类法在异步电机故障诊断中的应用 [J ] . 自动化与仪器仪表 , 2018 ,( 4 ): 214 - 218 .

ZHANG X , ZHU S X . Improved neural network classification method used in fault diagnosis of asynchronous motor [J ] . Automation ＆ Instrumentation , 2018 ,( 4 ): 214 - 218 . (in Chinese)

丁石川 , 厉雪衣 , 杭俊 , 等 . 深度学习理论及其在电机故障诊断中的研究现状与展望 [J ] . 电力系统保护与控制 , 2020 , 48 ( 8 ): 172 - 187 .

DING S C , LI X Y , HANG J , et al . Deep learning theory and its application to fault diagnosis of an electric machine [J ] . Power System Protection and Control , 2020 , 48 ( 8 ): 172 - 187 . (in Chinese)

孙文君 . 基于深度学习模型的感应电机故障诊断方法研究 [D ] . 南京 : 东南大学 , 2017 : 4 - 5 .

SUN W J . Induction Motor Fault Diagnosis Based on Deep Learning Models [D ] . Nanjing : Southeast University , 2017 : 4 - 5 . (in Chinese)

JIANG W , WANG C , et al . Application of deep learning in fault diagnosis of rotating machinery [J ] . Processes , 2021 , 9 ( 6 ): 919 .

SHAO S Y , SUN W J , YAN R Q , et al . A deep learning approach for fault diagnosis of induction motors in manufacturing [J ] . Chinese Journal of Mechanical Engineering , 2017 , 30 ( 6 ): 1347 - 1356 .

郝鹏永 . 基于深度信念网络的异步电机典型故障的诊断方法及其实验研究 [D ] . 秦皇岛 : 燕山大学 , 2019 : 2 - 3 .

HAO Pengyong . Diagnosis Method and Experimental Research of Typical Faults of Asynchronous Motor Based on Deep Belief Network [D ] . Qinhuangdao : Yanshan University , 2019 : 2 - 3 . (in Chinese)

WANG B , et al . Turn‐to‐turn short circuit of motor stator fault diagnosis in continuous state based on deep auto‐encoder [J ] . IET Electric Power Applications , 2019 , 13 ( 10 ): 1598 - 1606 .

XIAO D Y , HUANG Y X , ZHANG X D , et al . Fault diagnosis of asynchronous motors based on LSTM neural network [C ] // 2018 Prognostics and System Health Management Conference (PHM-Chongqing) . Piscataway : IEEE , 2018 : 540 - 545 .

SHAO S , WANG P , YAN R . Generative adversarial networks for data augmentation in machine fault diagnosis [J ] . Computers in Industry , 2019 , 106 : 85 - 93 .

JIAO J , ZHAO M , LIN J , et al . A comprehensive review on convolutional neural network in machine fault diagnosis [J ] . Neurocomputing , 2020 , 417 : 36 - 63 .

LEE J H , PACK J H , et al . Fault diagnosis of induction motor using convolutional neural network [J ] . Applied Sciences , 2019 , 9 ( 15 ): 2950 .

XIANG L , WANG P , YANG X , et al . Fault detection of wind turbine based on SCADA data analysis using CNN and LSTM with attention mechanism [J ] . Measurement , 2021 , 175 ( 8 ): 109094 .

邱大伟 , 刘子辰 , 周一青 , 等 . 基于Transformer神经网络的滚动轴承故障类型识别 [J ] . 高技术通讯 , 2021 , 31 ( 1 ): 1 - 11 .

QIU D W , LIU Z C , ZHOU Y Q , et al . A novel fault type detection method of rolling bearing using Transformer neural networks [J ] . Chinese High Technology Letters , 2021 , 31 ( 1 ): 1 - 11 . (in Chinese)

ZHANG A , LI S , CUI Y , et al . Limited data rolling bearing fault diagnosis with few-shot learning [J ] . IEEE Access , 2019 , 7 : 110895 - 110904 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A CatBoost Optimization-Based Fault Diagnosis Model for Photovoltaic Arrays

Zero Sample Fault Diagnosis Based on Transfer Learning

Fault Diagnosis of Railway Point Machine Based on Improved Time- Domain Multiscale Dispersion Entropy and Support Vector Machine

Research on Fault Diagnosis of Grounding Grid Based on Magnetic Field Distribution Characteristics

Fault Diagnosis Method Based on Test Set Reordering Combined with Structural Features

Related Author

PENG Zi-ran

XU Huai-shun

XIAO Shen-ping

WU Tian-shu

YIN Hong-peng

ZHAO Dan-dan

CAI Li

CAO Yuan

Related Institution

Hunan Provincial Key Laboratory of Electric Drive Control and Intelligent Equipment

School of Electrical and Information Engineering, Hunan University of Technology

Chongqing University

State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University

National Engineering Research Center of Rail Transportation Operation and Control System, Beijing Jiaotong University

⁰