A Weighted Deep Domain Adaptation Method for Industrial Fault Prognostics According to Prior Distribution of Complex Working Conditions

Wu, Zhenyu; Yu, Shuyang; Zhu, Xinning; Ji, Yang; Pecht, Michael

doi:10.1109/access.2019.2943076

Cited by 40 publications

(12 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method was compared with other existing RUL estimation methods, which are HDNN [31], CNN-LSTM [32], The best result of each column is red and the second-best result is blue. [33], DCNN [15], BLSTM-ED [21], and LSTM-BS [34].…”

Section: ) Comparison With State-of-the-arts Methodsmentioning

confidence: 99%

Attention-Based Bidirectional LSTM-CNN Model for Remaining Useful Life Estimation

Song

Park

Hong

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

In many industries, prognostic health management (PHM) technology has become important as a key technology to increase reliability and operational efficiency. Recently, several methods using a deep learning architecture to estimate the remaining useful life (RUL) as a part of the PHM have been presented. However, the limitation of existing methods is that they do not explicitly capture the relationship among different time sequences, which reduces the accuracy of RUL estimation. This paper proposes a novel RUL estimation algorithm using the attention mechanism to solve this problem. The proposed method applies scaled dot product attention to the encoder and the decoder consisting of long short-term memory, convolutional neural network and fully connected layer. The encoder applies self-attention to extract the association between time sequences, and the decoder extracts the association between the target RUL value and the time sequences using the representative vector of the RUL. Therefore, the proposed model has better performance to capture the long-term dependency in the sequence data and outperforms other state-of-the-art models in the experimental results. In addition, the extracted attention map shows that our model has better interpretability for RUL estimation.

show abstract

Section: ) Comparison With State-of-the-arts Methodsmentioning

confidence: 99%

Attention-Based Bidirectional LSTM-CNN Model for Remaining Useful Life Estimation

Song

Park

Hong

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

show abstract

“…CNN and LSTM can be cascaded in a sequential manner, e.g., CNN-LSTM [34] put CNN in the first stage, while BLCNN [21] reversed the order. In addition, HDNN [20] combined both the features from CNN and LSTM to generate the final predictions.…”

Section: A Experimental Datamentioning

confidence: 99%

Attention-based sequence to sequence model for machine remaining useful life prediction

Ragab

Chen²,

Wu³

et al. 2021

Neurocomputing

View full text Add to dashboard Cite

“…The unsupervised domain adaptation focuses on minimizing the domain discrepancy and learning the feature representation that can map the source and target data into the same feature space. These works assume the existence of sufficiently labeled source data and unlabeled target data 34–40 . The widely discussed domain adaptation schemes mainly include maximum mean discrepancy (MMD) minimization 36–38 and adversarial training 39,40 .…”

Section: Introductionmentioning

confidence: 99%

“…These works assume the existence of sufficiently labeled source data and unlabeled target data. [34][35][36][37][38][39][40] The widely discussed domain adaptation schemes mainly include maximum mean discrepancy (MMD) minimization [36][37][38] and adversarial training. 39,40 Yang et al 38 proposed a deep multi-layer domain adaptation network with MMD minimization for health monitoring and diagnosis of bearings used in real-case machines.…”

mentioning

confidence: 99%

Cross‐machine intelligent fault diagnosis of gearbox based on deep learning and parameter transfer

Han

Zhou

Xiang

et al. 2021

Structural Contr & Hlth

View full text Add to dashboard Cite

With the rapid development of artificial intelligence technologies, data-driven methods have significantly contributed to the intelligent monitoring and diagnosis of mechanical systems. However, the state-of-the-art approaches, especially the deep learning-based ones, implicitly assume the availability of large amounts of labeled fault data for supervised training, which is often infeasible due to the highly reliable system design in the field. In this research, a deep transfer convolutional neural network (CNN) scheme is proposed to enhance the diagnosis performance when dealing with insufficient training data in the target domain. By utilizing transfer learning, rich but relevant feature representation can be learnt from massive data in the source domain. The learnt weights and biases in the source domain are transferred to the target task as the initial parameter values. Then, the transferred parameters are properly fine-tuned with the small labeled datasets in the target domain. To avoid overfitting in the case of scarcely labeled samples in the target domain, global average pooling (GAP) is introduced to replace the fully-connected layers, and the traditional architecture in CNN is modified, to reduce the number of trainable parameters. Finally, by fully considering the transfer scenarios between diverse operating conditions and diverse machines, the cross-machine transfer experiments are designed with three gearbox datasets provided by the Prognostic and Health Management (PHM) 2009 conference, the Tsinghua University, and the University of Alberta. The results demonstrate the effectiveness of the proposed method with scarce labeled samples in the target domain. K E Y W O R D S convolutional neural network, deep transfer learning, gearbox fault diagnosis, global average pooling, scarcely labeled samples 1 | INTRODUCTION Machinery condition monitoring and fault diagnosis is a classic problem in the manufacturing industry. 1-4 Generally, the machinery fault diagnosis methods can be categorized into three classes, including model-based methods, knowledge-based methods, and data-driven methods. The model-based methods, such as finite element simulation and system identification, can perform fault diagnosis by monitoring the consistency between the real-time variables of the practical machine and the model-predicted values. However, due to the complex structure and working mechanism,

show abstract

A Weighted Deep Domain Adaptation Method for Industrial Fault Prognostics According to Prior Distribution of Complex Working Conditions

Cited by 40 publications

References 31 publications

Attention-Based Bidirectional LSTM-CNN Model for Remaining Useful Life Estimation

Attention-Based Bidirectional LSTM-CNN Model for Remaining Useful Life Estimation

Attention-based sequence to sequence model for machine remaining useful life prediction

Cross‐machine intelligent fault diagnosis of gearbox based on deep learning and parameter transfer

Contact Info

Product

Resources

About