2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS)最新文献_第8页

Remaining Useful Life Prediction of Rolling Bearings Using Correlation Coefficient Based Long Short-Term Memory Neural Network 基于相关系数的长短期记忆神经网络滚动轴承剩余使用寿命预测

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858400

Chenyang Wang, Chaolin Yin, Shan-shan Bai, Yongming Han

{"title":"Remaining Useful Life Prediction of Rolling Bearings Using Correlation Coefficient Based Long Short-Term Memory Neural Network","authors":"Chenyang Wang, Chaolin Yin, Shan-shan Bai, Yongming Han","doi":"10.1109/DDCLS55054.2022.9858400","DOIUrl":"https://doi.org/10.1109/DDCLS55054.2022.9858400","url":null,"abstract":"Rolling bearings play a crucial component for machinery equipment, which affects the operation efficiency and safety of the machinery equipment. The remaining useful life (RUL) prediction of rolling bearings is helpful for intelligent maintenance of the mechanical equipment. Therefore, an improved correlation coefficient based long short-term memory (LSTM) neural network model is presented in this paper to realize the RUL prediction of rolling bearings. First, the time domain, frequency domain and time-frequency domain features are extracted from the rolling bearing vibration data. Meanwhile, the noise reduction and normalization of the extracted features are conducted. Then, some important features that represent the bearing degradation trend are selected as the training data set through the correlation coefficient method to construct the RUL prediction model of online rolling bearings. Finally, the superiority of the presented RUL prediction model is validated baesd on the XJTU-SY rolling bearing data. Results on the experimental data indicate that the presented RUL prediction model has high generalization ability and high accuracy.","PeriodicalId":412672,"journal":{"name":"2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127659990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Performance Analyses of Discrete-Time RNN for Solving Discrete-Form Time-Variant Matrix Inversion with Different Selection Parameters 离散时间RNN求解不同选择参数下离散形式时变矩阵反演的性能分析

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858472

Yang Shi, Shengshen Fu, Chenling Ding, Jian Li, Dimitrios Gerontitis

引用次数: 0

Direct and Indirect Technique Routes of Convergence Analysis for Discrete-time Iterative Learning Control 离散时间迭代学习控制收敛分析的直接和间接技术路线

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858461

Jian Liu, Changqing Jia

引用次数: 0

Integral Sliding Mode Control for Partially Unknown T-S Fuzzy Systems Based on Reinforcement Learning Method 基于强化学习方法的部分未知T-S模糊系统积分滑模控制

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858419

Xingjian Sun, Min Shi, Nan Chen, Juping Gu

引用次数: 0

Data-based Adaptive Integral Sliding-mode Secure Control for Cyber-physical Power Systems with Disturbance under Bias Injection Attacks 基于数据自适应积分滑模安全控制的网络物理电力系统注入偏置攻击

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858354

Xinyu Han, Xin Huang

引用次数: 0

Architecture Growth of Dynamic Feedforward Neural Network Based on the Growth Rate Function 基于增长率函数的动态前馈神经网络结构增长

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858492

Xiaoping Zhang, Tianhang Yang, Li Wang, Shida Liu, Jiaqing Yan, Zhonghe He

引用次数: 0

A Prototypical Networks-based Multi-task Model for Few-shot Fault Diagnosis 基于原型网络的多任务小故障诊断模型

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858586

Zhihao Huo, Xiaoyu Yang, T. Yang, Huijin Fan, Housheng Su, Ying Zheng

{"title":"A Prototypical Networks-based Multi-task Model for Few-shot Fault Diagnosis","authors":"Zhihao Huo, Xiaoyu Yang, T. Yang, Huijin Fan, Housheng Su, Ying Zheng","doi":"10.1109/DDCLS55054.2022.9858586","DOIUrl":"https://doi.org/10.1109/DDCLS55054.2022.9858586","url":null,"abstract":"Due to the powerful classification performance, Prototypical Networks is widely used in few-shot fault diagnosis. However, insufficient feature extraction ability and negligence of inter-class distance in the Prototypical Networks may lead to the decrease of diagnosis accuracy. To solve the above problems, a Prototypical Networks-based multi-task model (PNBMTM) is proposed in this paper. Firstly, a convolutional autoencoder is built based on the feature extraction network of the Prototypical Networks, in which the optimization of the reconstruction loss is taken as a new task to obtain more efficient features. Secondly, a channel attention module (CAM) is designed to be applied to each layer of the encoder, which focuses on important features and suppresses useless features. Thirdly, relative distance loss is introduced while considering the effect of intra-class distance and inter-class distance to make inter-class distance larger and intra-class distance smaller, which helps to improve the quality of the features. And the optimization of relative distance loss is consequently taken as a new task to constitute a multi-task fault diagnosis model. Finally, a mechanical fault simulation experiment platform is built to verify the validity of the proposed model. The experimental results show that the proposed model has superior performance compared with other models.","PeriodicalId":412672,"journal":{"name":"2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114894442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fault Root Diagnosis of Industrial Process Based on Random Forest-Partial Symbol Transfer Entropy 基于随机森林-部分符号传递熵的工业过程故障根源诊断

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858493

Yunwei Zhu, Jianguo Wang, Jing-Ru Su, Liu-Wei Zhang, Y. Yao, He-Lin Chen

引用次数: 0

Quantized Iterative Learning Control for Nonlinear Switched Discrete- Time Systems with Actuator Saturation 具有执行器饱和的非线性开关离散时间系统的量化迭代学习控制

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858432

Shu-Ting Sun, Xiao-dong Li

引用次数: 1

On the Structure Model of Knowledge Manufacturing and Service System of Smart Library Based on Super-Network 基于超级网络的智能图书馆知识制造与服务系统结构模型研究

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858543

Qiongqiong Wei, Yanshuo Zhu

引用次数: 0