Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Huaitao Shi et al.
Summary: This article introduces a Wasserstein distance based multi-scale adversarial domain adaptation method for accurate remaining useful life (RUL) prediction of complex machinery. Experimental results demonstrate the reliable prediction capability of the proposed method in unlabeled target domains, with better performance compared to other methods and models.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Yifei Ding et al.
Summary: This paper introduces a domain generalization (DG) approach for predicting the remaining useful life (RUL) of bearings under unseen operating conditions. It proposes an adversarial out-domain augmentation (AOA) framework to generate pseudo-domains and increase the diversity of available samples. The framework includes manifold and semantic regularization to ensure consistency. Experimental results validate the effectiveness and superiority of the proposed approach.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Engineering, Industrial
Shaojiang Dong et al.
Summary: This study proposes a novel method for remaining useful life (RUL) prediction with more refined transfer by adding failure behavior judgment. A failure behavior judgment method is proposed using the convolutional autoencoder (CAE) and Pearson correlation coefficient. Then, a multi-channel transfer network is proposed for extracting multi-scale features of bearing degradation, and a domain adaptive structure is added to reduce the difference in feature distribution between training and test bearing data.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Industrial
Jianhai Yan et al.
Summary: This paper proposes a multitask deep learning model for simultaneously assessing the health state and predicting the remaining useful life of a machine. The model consists of four modules: a shared module, a multigate mixture-of-experts layer, a health state module, and a remaining useful life module. The proposed model outperforms the state-of-the-art benchmark models and is validated on a public dataset of engines.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Industrial
Jiaxian Chen et al.
Summary: In this study, an intelligent RUL prediction approach is proposed for aero-engine by integrating multimodal data fusion methodology and ensemble transfer learning technology. The approach dynamically selects sensing data and makes robust RUL prediction under cross-working conditions. Comparative experiments on the N-CMAPSS dataset released in 2021 demonstrate that the proposed method outperforms other state-of-the-art RUL prediction methods.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Industrial
Jiusi Zhang et al.
Summary: Most supervised learning-based approaches assume that offline data and online data should have a similar distribution, which is difficult to satisfy in realistic remaining useful life prediction. To overcome this issue, a new transfer learning method called domain adaptation learning-oriented transfer learning (TL) is proposed. The method, called VLSTM-LWSAN, uses a local weighted deep sub-domain adaptation network to align fine-grained features between different degenerate stages, reducing the discrepancy between the target and source domains. Experimental results on an aircraft turbofan engine dataset demonstrate that VLSTM-LWSAN outperforms deep learning approaches without transfer learning and conventional transfer learning methods.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Industrial
Yong Zhang et al.
Summary: Prognostics and health management (PHM) is crucial for ensuring the reliable operation of industrial equipment. This paper proposes a dual-task network structure that simultaneously evaluates the health status and predicts the remaining useful life of the equipment. The use of bidirectional gated recurrent unit and multigate mixture-of-experts enhances prediction accuracy and efficiency through information extraction and weighted decision making.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Automation & Control Systems
Yiming Xiao et al.
Summary: This article proposes a novel joint transfer network for unsupervised bearing fault diagnosis from the simulation domain to the experimental domain. It uses bearing simulation data to construct the source domain, an improved loss function to achieve alignment across domains, and a weight allocation mechanism to suppress negative transfer.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Automation & Control Systems
Jichao Zhuang et al.
Summary: Traditional health assessment models face challenges in dealing with domain shifts between different tasks. This study proposes an adversarial domain generalization framework to enhance the diversity of sample distribution and mitigate feature drift and semantic divergence for health assessment.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Automation & Control Systems
Yang Li et al.
Summary: The article proposes a test selection method based on conditional joint distribution, utilizes a deep Copula function to describe the dependencies among tests, and introduces an improved discrete binary particle swarm optimization algorithm to handle the test selection problem. Application to an electrical circuit illustrates the efficiency of the proposed method over existing methods.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Computer Science, Artificial Intelligence
Zhiyao Zhang et al.
Summary: Our study addresses the challenges in RUL prediction by incorporating operational condition features and the MOC-based Normalization method, resulting in improved prognostic model performance.
APPLIED SOFT COMPUTING
(2022)
Article
Engineering, Industrial
Jichao Zhuang et al.
Summary: A metric adversarial domain adaptation approach (MADA) is proposed to evaluate the bearing RULs under multiple working conditions, which includes an adversarial domain adaptation architecture and a dual self-attention module for optimizing the prediction of bearing RULs.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Engineering, Industrial
Wanxiang Li et al.
Summary: In this paper, a RUL prediction method based on a transfer multi-stage shrinkage attention temporal convolutional network under variable working conditions is proposed. The method addresses the problems of disparate distribution of degradation features and difficulties in obtaining corresponding labels by designing a shrinkage attention module, a multi-stage shrinkage attention temporal convolution block, and an unsupervised domain adaptation strategy.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Engineering, Electrical & Electronic
Xue Wang et al.
Summary: This article proposes a decoupling network-based method for infrared and visible image fusion, which effectively retains the texture details and luminance information of the source images while preserving the high-contrast regions. Extensive experiments demonstrate that the proposed method generates fused images with saliency objects and clear details, outperforming other state-of-the-art methods.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Computer Science, Artificial Intelligence
Tae San Kim et al.
Summary: The research proposes a multi-task learning method based on convolution neural networks to better reflect the relationship between remaining useful life estimation and health status detection process, and it shows superior performance to existing baseline models in experiments using the C-MAPSS dataset for aero-engine unit prognostics.
JOURNAL OF INTELLIGENT MANUFACTURING
(2021)
Article
Engineering, Industrial
Song Fu et al.
Summary: The study investigates an effective UDA method called DIDRLSTM, which uses DRLSTM as a feature extractor and integrates domain adaptation and domain confusion modules to improve prognostic performance in RUL prediction.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Engineering, Industrial
Lei Xiao et al.
Summary: This paper proposes a new RUL prediction method by intentionally adding noise to an LSTM network and conducting correlation analysis among sensory measurements to improve prediction performance and construct new degradation features. The method is validated on an aero-engine lifetime dataset and compared to other techniques.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Automation & Control Systems
Mohamed Ragab et al.
Summary: This article introduces a novel contrastive adversarial domain adaptation (CADA) method for cross-domain RUL prediction, which combines adversarial domain adaptation architecture with contrastive loss to effectively consider target-specific information.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Automation & Control Systems
Weiting Zhang et al.
Summary: This article proposes a self-attention based Perception and Prediction framework, called DeepHealth, for instant IPdM. The framework consists of two submodels for health perception and sequence prediction. Experimental results demonstrate that the proposed solution achieves good prediction accuracy for instant IPdM on the automatic washing equipment and Case Western Reserve University datasets.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Artificial Intelligence
Ke Zhao et al.
Summary: This paper developed a joint distribution adaptation network with adversarial learning to address fault diagnosis challenges. By constructing a deep convolutional neural network to extract features, and using an improved joint maximum mean discrepancy and adversarial domain adaptation to match feature distributions and extract features, precise distribution matching and domain-invariant features extraction were achieved.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Xiang Li et al.
KNOWLEDGE-BASED SYSTEMS
(2020)
Article
Computer Science, Artificial Intelligence
Yanrui Jin et al.
KNOWLEDGE-BASED SYSTEMS
(2020)
Article
Engineering, Multidisciplinary
Xiaohui Chen et al.
EKSPLOATACJA I NIEZAWODNOSC-MAINTENANCE AND RELIABILITY
(2019)
