相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Automation & Control Systems
Mingming Yan et al.
Summary: This paper proposes a method for bearing prognostics using degradation regression models to estimate the remaining useful life of bearings. Key steps such as detecting elbow point and smoothing are introduced, and the effectiveness of the method is validated through experiments.
Article
Engineering, Multidisciplinary
Yisheng Zou et al.
Summary: This study focuses on the prediction of remaining useful life (RUL) of rolling bearings. By incorporating transfer learning and adversarial networks, a method that can improve the prediction accuracy is proposed.
Article
Engineering, Industrial
Mengqi Miao et al.
Summary: This study proposes a sparse domain adaption network (SDAN) to address the domain shift problem in bearing remaining useful life (RUL) prediction. SDAN employs an adaptive selection mechanism to select important input features and employs an adaptively convolutional neural network (ACNN) to extract essential information. Furthermore, SDAN utilizes a sparse feature selection layer to suppress noise and remove ineffective features. By integrating domain-adversarial learning and unsupervised sparse domain alignment, SDAN solves the problem of data distribution shift and provides transferable RUL prediction performance.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Engineering, Mechanical
Hongqiu Zhu et al.
Summary: This article proposes a method based on dynamic feature construction to predict the remaining useful life of bearings with fatigue failure, using improved convolutional neural networks and long short-term memory networks to achieve prediction.
INTERNATIONAL JOURNAL OF FATIGUE
(2022)
Article
Engineering, Multidisciplinary
Xianjun Du et al.
Summary: This paper proposes an attention mechanism based multiscale convolutional neural network prediction model for predicting the degradation trend and remaining useful life of rolling bearings, enabling effective preventive maintenance of rotating machinery. Continuous wavelet transform is used to transform the vibration signal into a time-frequency spectral feature map, and multi-scale convolutional neural network is employed for deep feature extraction. The proposed model achieves better performances than other algorithms, improving prediction accuracy and generalization performance.
Article
Engineering, Industrial
Han Wang et al.
Summary: This paper proposes a PSLOC method for bearing RUL prediction, which improves the prediction accuracy by addressing key issues in existing methods.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(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
Information Science & Library Science
Naman Bhoj et al.
Summary: With the rapid advancements in technology, there is an increasing trend in using IoT devices to monitor electrical energy consumption. Clean and green energy has become a priority for policymakers and businesses around the world, with a focus on reducing carbon footprint. Research comparing different models for predictive energy consumption in smart homes found that the CNN-GRU architecture outperformed other models.
TELEMATICS AND INFORMATICS
(2022)
Article
Computer Science, Interdisciplinary Applications
L. L. Shi et al.
Summary: A deep learning method based on LSTM is proposed in this study to predict the deformation of rock materials under different loading conditions. Unlike traditional methods, this approach does not require the determination of effective tangent stiffness tensor and can accurately predict the mechanical behavior of rock materials with strong strain-softening.
COMPUTERS AND GEOTECHNICS
(2022)
Proceedings Paper
Automation & Control Systems
Jangwon Lee et al.
Summary: Rotating machines, such as pumps and compressors, are critical components in refinery and chemical plants. Estimating the remaining useful life (RUL) of bearings is crucial for reducing production losses and avoiding machine damage. Data-driven approaches have been widely used due to the complexity and stochastic nature of bearing failure mechanisms.
Article
Engineering, Multidisciplinary
Jianwen Guo et al.
Summary: This paper proposes a method combining error fusion of multiple sparse auto-encoders with long short-term memory for predicting mechanical fault time series. The experimental results show the accuracy and superiority of this method in predicting mechanical fault time series.
Article
Engineering, Multidisciplinary
Lu Liu et al.
Summary: In recent years, data-driven approaches for remaining useful life (RUL) prognostics have gained widespread attention. This paper explores the degradation process of bearings and proposes an enhanced encoder-decoder framework for accurately predicting the remaining useful life of bearings by using trigonometric functions and cumulative operations to enhance the quality of health indicators. The experimental results demonstrate the superiority and feasibility of the proposed method compared to several state-of-the-art methods.
Article
Engineering, Multidisciplinary
Han Cheng et al.
Summary: This study proposes a transferable convolutional neural network (TCNN) to accurately predict the remaining useful life (RUL) of bearings under various failure behaviors. By integrating multiple-kernel maximum mean discrepancies into the optimization objective, it reduces distribution discrepancies and improves the performance of the prediction model.
Article
Computer Science, Artificial Intelligence
Milad Malekipirbazari et al.
Summary: This study investigates the challenge of deploying feature reduction methods on datasets with massive number of instances and finds that selecting a smaller random subset of instances can achieve similar performance levels. This provides empirical evidence for drastically reducing the amount of data needed for training a classifier.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Yaoxiang Yu et al.
Summary: This paper proposes a new method for recognizing control chart patterns, utilizing feature fusion and convolutional auto-encoder for feature extraction, and GACLN model for recognition. Genetic algorithm is used to search for optimal hyper-parameters. The results show that the performance of this method is superior to previous techniques.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Engineering, Multidisciplinary
Hua Ding et al.
Summary: This paper proposes a new method to predict the remaining useful life of bearings based on convolutional neural networks (CNN), which includes steps such as denoising, removing outliers, and using stratified sampling for data partitioning. A deep CNN model is constructed to avoid feature loss, and experimental results demonstrate the effectiveness of the proposed method.
Article
Engineering, Industrial
Yudong Cao et al.
Summary: The study introduces a new deep learning framework TCN-RSA for predicting the remaining useful life of mechanical systems, and demonstrates its superiority in experiments.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Computer Science, Artificial Intelligence
Mohsen Motahari-Nezhad et al.
Summary: This paper discusses the estimation of the remaining useful life of angular contact ball bearings using time-domain signal processing methods, introducing 60 time-domain features for fault detection and utilizing the IDE method for feature dimensionality reduction. The KNN algorithm is used for bearing classification based on selected features, with results showing high precision in fault detection. The study validates the performance of the KNN classifier with performance indices, highlighting the importance of features such as kurtosis in achieving high accuracy, precision, and specificity in bearing classification.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Engineering, Industrial
Cheng-Geng Huang et al.
Summary: This study introduces a novel deep convolutional neural network-bootstrap integrated prognostic approach for predicting the remaining useful life (RUL) of rolling bearings. The method combines 1D time series and 2D image feature representations for comprehensive degradation characterization and quantifies the RUL prediction interval effectively.
JOURNAL OF MANUFACTURING SYSTEMS
(2021)
Article
Automation & Control Systems
Mingming Yan et al.
Article
Automation & Control Systems
Melih Kuncan et al.
Article
Computer Science, Artificial Intelligence
Yuanhang Chen et al.
APPLIED SOFT COMPUTING
(2020)
Article
Engineering, Industrial
Wasim Ahmad et al.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2019)
Article
Automation & Control Systems
Min Xia et al.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2019)
Article
Engineering, Industrial
Xiang Li et al.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2019)
Article
Automation & Control Systems
Cheng-Geng Huang et al.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2019)
Review
Computer Science, Interdisciplinary Applications
Ryan J. Urbanowicz et al.
JOURNAL OF BIOMEDICAL INFORMATICS
(2018)
Article
Engineering, Mechanical
Yuning Qian et al.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2017)
Article
Computer Science, Information Systems
Yilmaz Kaya et al.
SECURITY AND COMMUNICATION NETWORKS
(2016)
