Showing papers in "Measurement in 2020"

TL;DR: This paper aims at systematically and comprehensively summarizing current large-scale wind turbine bearing failure modes and condition monitoring and fault diagnosis achievements, followed by a brief summary of future research directions for wind turbine Bearing fault diagnosis.

TL;DR: This paper proposes a deep learning-based fault diagnosis method to address the imbalanced data problem by explicitly creating additional training data and validated that the data-driven methods can significantly benefit from the data augmentation.

TL;DR: An adaptive deep transfer learning method for bearing fault diagnosis is proposed, a long-short term memory recurrent neural network model based on instance-transfer learning is constructed, and grey wolf optimization algorithm is introduced to adaptively learn key parameters of joint distribution adaptation.

TL;DR: Enhanced deep transfer auto-encoder is proposed for fault diagnosis of bearing installed in different machines using scaled exponential linear unit and target training samples with limited labeled information to improve the quality of the mapped vibration data collected from bearing.

TL;DR: The experimental results successfully demonstrate that the multi-CNN fusion model is very suitable for providing a classification method with high accuracy and low complexity on the NSL-KDD dataset and its performance is also superior to those of traditional machine learning methods and other recent deep learning approaches for binary classification and multiclass classification.

TL;DR: The proposed method has a higher fault diagnosis accuracy than existing deep learning diagnosis methods and the use of hierarchical regularization to obtain better training results.

TL;DR: Few-shot transfer learning method is constructed utilizing meta-learning for few-shot samples diagnosis in variable conditions using a unified 1D convolution network for many-shot diagnosis of three datasets.

TL;DR: A systematic review of state-of-the-art deep learning-based PHM frameworks emphasizes on the most recent trends within the field and presents the benefits and potentials of state of theart deep neural networks for system health management.

TL;DR: A fault diagnosis for rolling bearings, based on Generalized Refined Composite Multiscale Sample Entropy, Supervised Isometric Mapping, and Grasshopper Optimization Algorithm based Support Vector Machine, which improves the classification accuracy to 100%.

TL;DR: An insight into various defects that generally occur in gears is provided and a state-of-the-art review is provided on the latest and most widely used diagnosis methods for gearbox condition monitoring.

TL;DR: The comparison and analysis results indicate that the integrated framework is applicable to track the tool wear evolution and predict its RUL with the average prediction accuracy reaching up to 90%.

TL;DR: A novel method to realize the selection of the optimal IMF(s) of VMD which containing abundant fault information based on frequency band entropy (FBE) is introduced.

TL;DR: A multiscale local feature learning method based on back-propagation neural network (BPNN) for rolling bearings fault diagnosis is proposed, which is used to locally learn meaningful and dissimilar features from signals of different scales, thus improving the fault diagnosis accuracy.

TL;DR: A novel and high-accuracy fault detection approach named WT-GAN-CNN for rotating machinery is presented based on Wavelet Transform, Generative Adversarial Nets and convolutional neural network and its result in the stability of testing accuracy is also quite excellent.

TL;DR: This research presents a comprehensive review to study state-of-the-art challenges and recommended technologies for enabling data analysis and search in the future IoT presenting a framework for ICT integration in IoT layers.

TL;DR: A deep graph convolutional network (DGCN) based on graph theory is applied to deliver acoustic-based fault diagnosis of roller bearings, in which the collected acoustic signals are first transformed into graphs with geometric structures to improve classification accuracy of the deep learning methods applied.

TL;DR: The experimental results show the prognostic performances are promising both for the multi-steps-ahead predictions and long-horizon SOH estimations.

TL;DR: The proposed adaptive variational mode decomposition and Teager energy operator method (AVMD-TEO) can effectively reduce signal noise and extract incipient fault feature of rolling bearings.

TL;DR: Several Convolutional Neural Networks were trained to classify x-ray images into two classes viz., pneumonia and non-pneumonia, by changing various parameters, hyperparameters and number of convolutional layers.

TL;DR: An end-to-end solution with one-dimensional convolutional long short-term memory (LSTM) networks is presented, where both the spatial and temporal features of multisensor measured vibration signals are extracted and then jointed for better bearing fault diagnosis.

TL;DR: The improved VMD method after parameter optimization can extract the early failure characteristics of rolling bearing more distinctly, and the fault diagnosis model based on this method has higher accuracy and application value.

TL;DR: A novel method is presented for Polarimetric Synthetic Aperture Radar image segmentation, in which there is no need for any parameter initialization and the results prove the superiority of the proposed method as it improves both the performance and the noise resistance.

TL;DR: The proposed DLapAE algorithm with Laplacian regularization can improve the generalization performance of this fault diagnosis framework and make it more suitable for feature learning and classification of imbalanced data.

TL;DR: A new online detection method of incipient fault based on deep transfer learning based ondeep transfer learning is proposed, which shows the comparative performance of the proposed method on the bearing dataset of IEEE PHM Challenge 2012.

TL;DR: In this article, the optimization of material and machining parameters for surface finish and Material Removal Rate (MRR) enhancements while turning Aluminium/Rock dust composite through Taguchi and Grey Relational Analysis (GRA).

TL;DR: A novel integrated model based on deep learning and multi-sensor feature fusion is proposed that can achieve multisensory feature fusion to overcome the first weakness and show that the proposed model is more robust and accurate.

TL;DR: The experimental results show that the fault diagnosis of rolling bearing based on SIRCNN can effectively identify the type and severity of bearing fault under different noise environments, improve the diagnostic efficiency and reduce the performance requirements for the diagnostic equipment.

TL;DR: In this paper, a microwave sensor based on the split ring resonator has been proposed to detect the real part of the dielectric constant of the liquid sample, which has two purposes: (1) Measurement of the permittivity of one sample under test in two frequency bands (multi-band), and (2) dual samples under test for simultaneous dielectrics detection (multi sensing).

TL;DR: In this article, the machinability performance during dry longitudinal turning of Ti-6Al-4V-ELI titanium alloy using Taguchi Experimental Design (TED) and full factorial design (FFD) was investigated.

TL;DR: In this article, a nonlinear Lamb wave detection system was used to detect aluminum alloy plates with different depth cracks and aluminum alloy plate with different tensile load cycles, and the acquired time domain waveforms were analyzed by Fast Fourier Transform (FFT) and the influence of two kinds of defects on the nonlinear effects of Lamb waves was obtained.