Simulation-Driven Deep Learning Approach for Wear Diagnostics in Hydrodynamic Journal Bearings

2020 ◽  
pp. 1-26
Author(s):  
Ozhan Gecgel ◽  
Joao Paulo Dias ◽  
Stephen Ekwaro-Osire ◽  
Diogo Alves ◽  
Tiago H. Machado ◽  
...  
Keyword(s):  
Deep Learning ◽  
Condition Monitoring ◽  
Learning Algorithm ◽  
Journal Bearings ◽  
Operating Conditions ◽  
Intelligent Machines ◽  
The Past ◽  
Deep Learning Algorithm ◽  
Promising Tool ◽  
Rotating Systems

Abstract Early diagnosis in rotating machinery has been a challenge when looking towards the concept of intelligent machines. A crucial and critical component in these systems is the lubricated journal bearing, subjected to wear fault by abrasive removing of material in its inner wall, mainly during run-ups and run-downs. In extreme conditions, wear faults can cause unexpected shutdowns in rotating systems. Consequently, advanced condition monitoring is an essential procedure in the wear diagnosis of journal bearings. Although an increasing number of data-driven condition monitoring approaches for rotating machines have been proposed in the past decade, they mostly rely on substantial amounts of experimental data for training, which is expensive and time-consuming to obtain. The objective of this work is to develop a framework using a deep learning algorithm to classify wear faults in hydrodynamic journal bearings using simulated vibrations signals. Numerically simulated datasets under different wear severity levels and operating conditions were used to train and test the diagnostics framework. The results show that the proposed framework can be a promising tool to wear fault diagnostics in journal bearings.

scholarly journals Integrating Physics and Data Driven Cyber-Physical System for Condition Monitoring of Critical Transmission Components in Smart Production Line

2021 ◽  
Vol 11 (19) ◽  
pp. 8967
Author(s):  
Lin Song ◽  
Liping Wang ◽  
Jun Wu ◽  
Jianhong Liang ◽  
Zhigui Liu
Keyword(s):  
Signal Processing ◽  
Deep Learning ◽  
Condition Monitoring ◽  
Physical System ◽  
Production Line ◽  
Learning Algorithm ◽  
Data Driven ◽  
Equation Modeling ◽  
Cyber Physical System ◽  
Deep Learning Algorithm

In response to the lack of a unified cyber–physical system framework, which combined the Internet of Things, industrial big data, and deep learning algorithms for the condition monitoring of critical transmission components in a smart production line. In this study, based on the conceptualization of the layers, a novel five-layer cyber–physical systems framework for smart production lines is proposed. This architecture integrates physics and is data-driven. The smart connection layer collects and transmits data, the physical equation modeling layer converts low-value raw data into high-value feature information via signal processing, the machine learning modeling layer realizes condition prediction through a deep learning algorithm, and scientific decision-making and predictive maintenance are completed through a cognition layer and a configuration layer. Case studies on three critical transmission components—spindles, bearings, and gears—are carried out to validate the effectiveness of the proposed framework and hybrid model for condition monitoring. The prediction results of the three datasets show that the system is successful in distinguishing condition, while the short time Fourier transform signal processing and deep residual network deep learning algorithm is superior to that of other models. The proposed framework and approach are scalable and generalizable and lay the foundation for the extension of the model.

scholarly journals Progress in developing a hybrid deep learning algorithm for identifying and locating primary vertices

2021 ◽  
Vol 251 ◽  
pp. 04012
Author(s):  
Simon Akar ◽  
Gowtham Atluri ◽  
Thomas Boettcher ◽  
Michael Peters ◽  
Henry Schreiner ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Efficiency ◽  
Learning Algorithm ◽  
Learning Model ◽  
Operating Conditions ◽  
Proton Collision ◽  
Proton Proton ◽  
Deep Learning Algorithm ◽  
Proton Proton Collision ◽  
Deep Learning Model

The locations of proton-proton collision points in LHC experiments are called primary vertices (PVs). Preliminary results of a hybrid deep learning algorithm for identifying and locating these, targeting the Run 3 incarnation of LHCb, have been described at conferences in 2019 and 2020. In the past year we have made significant progress in a variety of related areas. Using two newer Kernel Density Estimators (KDEs) as input feature sets improves the fidelity of the models, as does using full LHCb simulation rather than the “toy Monte Carlo” originally (and still) used to develop models. We have also built a deep learning model to calculate the KDEs from track information. Connecting a tracks-to-KDE model to a KDE-to-hists model used to find PVs provides a proof-of-concept that a single deep learning model can use track information to find PVs with high efficiency and high fidelity. We have studied a variety of models systematically to understand how variations in their architectures affect performance. While the studies reported here are specific to the LHCb geometry and operating conditions, the results suggest that the same approach could be used by the ATLAS and CMS experiments.

scholarly journals Bearing Fault Diagnosis under Variable Working Conditions Based on Deep Residual Shrinkage Networks and Transfer Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Xinyu Yang ◽  
Fulin Chi ◽  
Siyu Shao ◽  
Qiang Zhang
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Transfer Learning ◽  
Learning Algorithm ◽  
Operating Conditions ◽  
Mean Deviation ◽  
Variable Load ◽  
Vibration Data ◽  
Deep Learning Algorithm ◽  
Load Variable

Nowadays, deep learning has made great achievements in the field of rotating machinery fault diagnosis. But in the practical engineering scenarios, when facing a large number of unlabeled data and variable operating conditions, only using a deep learning algorithm may reduce the performance. In order to solve the above problem, this paper uses a method of combining transfer learning with deep learning. First, the deep shrinkage residual network is constructed by adding soft thresholds to extract the characteristics of bearing vibration data under noise redundancy. Then, the joint maximum mean deviation (JMMD) criterion and conditional domain adversarial (CDA) learning domain adapting network are used to align the source and target domains. At the same time, adding transferable semantic augmentation (TSA) regular items improves alignment performance between classes. Finally, the proposed model is verified by three experiments: variable load, variable speed, and variable noise, which overcomes the shortcomings of traditional deep learning and shallow transfer learning algorithms.

scholarly journals Study on Radar Echo-Filling in an Occlusion Area by a Deep Learning Algorithm

2021 ◽  
Vol 13 (9) ◽  
pp. 1779
Author(s):  
Xiaoyan Yin ◽  
Zhiqun Hu ◽  
Jiafeng Zheng ◽  
Boyong Li ◽  
Yuanyuan Zuo
Keyword(s):  
Deep Learning ◽  
Loss Function ◽  
Learning Algorithm ◽  
Weather Radar ◽  
Loss Functions ◽  
Training Dataset ◽  
Echo Intensity ◽  
Common Mean ◽  
Deep Learning Algorithm ◽  
Radar Beam

Radar beam blockage is an important error source that affects the quality of weather radar data. An echo-filling network (EFnet) is proposed based on a deep learning algorithm to correct the echo intensity under the occlusion area in the Nanjing S-band new-generation weather radar (CINRAD/SA). The training dataset is constructed by the labels, which are the echo intensity at the 0.5° elevation in the unblocked area, and by the input features, which are the intensity in the cube including multiple elevations and gates corresponding to the location of bottom labels. Two loss functions are applied to compile the network: one is the common mean square error (MSE), and the other is a self-defined loss function that increases the weight of strong echoes. Considering that the radar beam broadens with distance and height, the 0.5° elevation scan is divided into six range bands every 25 km to train different models. The models are evaluated by three indicators: explained variance (EVar), mean absolute error (MAE), and correlation coefficient (CC). Two cases are demonstrated to compare the effect of the echo-filling model by different loss functions. The results suggest that EFnet can effectively correct the echo reflectivity and improve the data quality in the occlusion area, and there are better results for strong echoes when the self-defined loss function is used.

Sign in / Sign up

Export Citation Format

Share Document