Research on Fault Diagnosis Method of Train Wheelset Based on Deep Learning and Big Data Analysis

2020 ◽  
pp. 180-192
Author(s):  
WanQing OuYang ◽  
Jian Zhang ◽  
Rongchao Fang ◽  
HengBo Jiang ◽  
Yujie Luo ◽  
...  
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Data Analysis ◽  
Fault Diagnosis ◽  
Big Data Analysis ◽  
Diagnosis Method

scholarly journals Research on Pump Product Intelligent Fault Diagnosis System Based on Dig Data

2021 ◽  
Vol 2121 (1) ◽  
pp. 012024
Author(s):  
Yimei Xu ◽  
Xiaoqing Xu
Keyword(s):  
Big Data ◽  
Data Analysis ◽  
Fault Diagnosis ◽  
Manufacturing Industry ◽  
Big Data Analysis ◽  
Identification Accuracy ◽  
Analysis Method ◽  
Data Analysis Method ◽  
Diagnosis Method ◽  
Fault Diagnosis System

Abstract With the integration of information technology and manufacturing industry and the improvement of equipment monitoring data and computer computing ability, equipment fault diagnosis has entered the era of “big data”. Using big data analysis method for fault diagnosis, the fault diagnosis model can learn its own characteristics and complete fault identification, so that the fault diagnosis is more intelligent and automatic on the basis of high identification accuracy. This paper mainly studies the application of fault diagnosis method and big data analysis method in pump product fault diagnosis.

scholarly journals Deep learning neural network seismic big-data analysis of earthquake correlations in distinct seismic regions

2021 ◽  
Vol 8 (84) ◽  
Author(s):  
Antonios Konstantaras ◽  
Nikolaos S. Petrakis ◽  
Theofanis Frantzeskakis ◽  
Emmanouil Markoulakis ◽  
Katerina Kabassi ◽  
...  
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Deep Learning ◽  
Data Analysis ◽  
Big Data Analysis ◽  
Seismic Regions ◽  
Deep Learning Neural Network

Research on O2O Platform and Promotion Algorithm of Sports Venues Based on Deep Learning Technique

2018 ◽  
Vol 13 (3) ◽  
pp. 73-84
Author(s):  
Kaiyan Han ◽  
Qin Wang
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Data Analysis ◽  
Joint Distribution ◽  
Big Data Analysis ◽  
Practical Significance ◽  
Hidden Variable ◽  
Optimal Value ◽  
Learning Technique ◽  
Sports Venues

In the era of big data, intelligent sports venues have a practical significance to provide personalized service for users and build up a platform for stadium management. This article proposes a new parallel big data promotion algorithm based on the latest achievements of big data analysis. The proposed algorithm calculates the optimal value by using the observed variables Y, the hidden variable data Z, the joint distribution P (Y, Z | θ) and distribution conditions P (Z | Y | θ). The experimental results show that the proposed algorithm has higher accuracy of big data analysis, and can serve the intelligent sports venues better.

scholarly journals Prediction of Passenger Flow in Urban Rail Transit Based on Big Data Analysis and Deep Learning

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 142272-142279 ◽  
Author(s):  
Kaer Zhu ◽  
Ping Xun ◽  
Wei Li ◽  
Zhen Li ◽  
Ruochong Zhou
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Data Analysis ◽  
Big Data Analysis ◽  
Urban Rail Transit ◽  
Rail Transit ◽  
Passenger Flow ◽  
Urban Rail

Application of Deep Learning in Biological Big Data Analysis

2021 ◽  
pp. 117-148
Author(s):  
Rohit Shukla ◽  
Arvind Kumar Yadav ◽  
Tiratha Raj Singh
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Data Analysis ◽  
Data Extraction ◽  
Basic Structure ◽  
Big Data Analysis ◽  
Biological Data ◽  
Omics Data ◽  
Hidden Information ◽  
Continuous Development

The meaningful data extraction from the biological big data or omics data is a remaining challenge in bioinformatics. The deep learning methods, which can be used for the prediction of hidden information from the biological data, are widely used in the industry and academia. The authors have discussed the similarity and differences in the widely utilized models in deep learning studies. They first discussed the basic structure of various models followed by their applications in biological perspective. They have also discussed the suggestions and limitations of deep learning. They expect that this chapter can serve as significant perspective for continuous development of its theory, algorithm, and application in the established bioinformatics domain.

Sign in / Sign up

Export Citation Format

Share Document