Research on Fault Prediction Method of Elevator Door System Based on Transfer Learning

被引:5
作者
Pan, Jun [1 ]
Shao, Changxu [1 ]
Dai, Yuefang [2 ]
Wei, Yimin [1 ]
Chen, Wenhua [1 ]
Lin, Zheng [1 ]
机构
[1] Zhejiang Sci Tech Univ, Zhejiang Prov Key Lab Reliabil Technol Mech & Elec, Hangzhou 310018, Peoples R China
[2] Hangzhou Xizi Iparking Co Ltd, Hangzhou 311103, Peoples R China
关键词
fault prediction; elevator door; GNN; LSTM; transfer learning; NETWORK;
D O I
10.3390/s24072135
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
The elevator door system plays a crucial role in ensuring elevator safety. Fault prediction is an invaluable tool for accident prevention. By analyzing the sound signals generated during operation, such as component wear and tear, the fault of the system can be accurately determined. This study proposes a GNN-LSTM-BDANN deep learning model to account for variations in elevator operating environments and sound signal acquisition methods. The proposed model utilizes the historical sound data from other elevators to predict the remaining useful life (RUL) of the target elevator door system. Firstly, the opening and closing sounds of other elevators is collected, followed by the extraction of relevant sound signal characteristics including A-weighted sound pressure level, loudness, sharpness, and roughness. These features are then transformed into graph data with geometric structure representation. Subsequently, the Graph Neural Networks (GNN) and long short-term memory networks (LSTM) are employed to extract deeper features from the data. Finally, transfer learning based on the improved Bhattacharyya Distance domain adversarial neural network (BDANN) is utilized to transfer knowledge learned from historical sound data of other elevators to predict RUL for the target elevator door system effectively. Experimental results demonstrate that the proposed method can successfully predict potential failure timeframes for different elevator door systems.
引用
收藏
页数:20
相关论文
共 29 条
[1]   The role of the Bhattacharyya distance in stochastic model updating [J].
Bi, Sifeng ;
Broggi, Matteo ;
Beer, Michael .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2019, 117 :437-452
[2]   Fault Diagnosis of Elevator Doors Using Control State Information [J].
Chae, Hyun ;
Lee, Jae Eung ;
Oh, Ki-Yong .
IEEE ACCESS, 2022, 10 :7207-7222
[3]   Research on prediction model of tractor sound quality based on genetic algorithm [J].
Chen, Pushuang ;
Xu, Liangyuan ;
Tang, Qiansheng ;
Shang, Lili ;
Liu, Wei .
APPLIED ACOUSTICS, 2022, 185
[4]   Health indicator construction for degradation assessment by embedded LSTM-CNN autoencoder and growing self-organized map [J].
Chen, Zhipeng ;
Zhu, Haiping ;
Wu, Jun ;
Fan, Liangzhi .
KNOWLEDGE-BASED SYSTEMS, 2022, 252
[5]   Deep transfer learning based on dynamic domain adaptation for remaining useful life prediction under different working conditions [J].
Cheng, Han ;
Kong, Xianguang ;
Wang, Qibin ;
Ma, Hongbo ;
Yang, Shengkang ;
Chen, Gaige .
JOURNAL OF INTELLIGENT MANUFACTURING, 2023, 34 (02) :587-613
[6]   Remaining useful lifetime prediction via deep domain adaptation [J].
da Costa, Paulo Roberto de Oliveira ;
Akcay, Alp ;
Zhang, Yingqian ;
Kaymak, Uzay .
RELIABILITY ENGINEERING & SYSTEM SAFETY, 2020, 195
[7]  
Ganin Y, 2017, ADV COMPUT VIS PATT, P189, DOI 10.1007/978-3-319-58347-1_10
[8]   A transferable neural network method for remaining useful life prediction [J].
He, Rui ;
Tian, Zhigang ;
Zuo, Mingjian .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2023, 183
[9]   Critical evaluation and comparison of psychoacoustics, acoustics and vibration features for gear fault correlation and classification [J].
Kane, P., V ;
Andhare, A. B. .
MEASUREMENT, 2020, 154
[10]   Margin-Maximized Hyperspace for Fault Detection and Prediction: A Case Study With an Elevator Door [J].
Kim, Minjae ;
Son, Seho ;
Oh, Ki-Yong .
IEEE ACCESS, 2023, 11 :128580-128595