Abstract
This paper aims to apply techniques of Big Data Analytics including K-Means Clustering to diagnose potential problems for offshore rotating machinery. The innovative methods are attempted in both Batch K-Means and Streaming K-Means. Their performances are compared with the conventional signal analysis method. Both KMeans models have a better performance on detecting significant mechanical faults as anomalies for offshore rotating machinery which can be considered as appropriate method for machine operational maintenance.
Original language | English |
---|---|
Title of host publication | ICBDR 2019 - Proceedings of the 2019 3rd International Conference on Big Data Research |
Publisher | Association for Computing Machinery |
Pages | 30-36 |
Number of pages | 7 |
ISBN (Electronic) | 9781450372015 |
DOIs | |
Publication status | Published - 20 Nov 2019 |
Event | 3rd International Conference on Big Data Research, ICBDR 2019 - Cergy-Pontoise, France Duration: 20 Nov 2019 → 21 Nov 2019 |
Publication series
Name | ACM International Conference Proceeding Series |
---|
Conference
Conference | 3rd International Conference on Big Data Research, ICBDR 2019 |
---|---|
Country/Territory | France |
City | Cergy-Pontoise |
Period | 20/11/19 → 21/11/19 |
Keywords
- Anomaly detection
- Big data
- K-means clustering
- Real-time processing
- Streaming K-means clustering
- Trouble diagnose
Fingerprint
Dive into the research topics of 'Anomaly detection for machinery by using Big Data Real-Time processing and clustering technique'. Together they form a unique fingerprint.Cite this
Wang, Z., Zhou, Y., & Li, G. (2019). Anomaly detection for machinery by using Big Data Real-Time processing and clustering technique. In ICBDR 2019 - Proceedings of the 2019 3rd International Conference on Big Data Research (pp. 30-36). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3372454.3372480