Big Data Analytics Framework for System Health Monitoring
Authors:
- Brian XuBXBrian Xu
- Sathish Alampalayam KumarSKSathish Alampalayam Kumar
- 1 June 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 23797703,p. 401-408
Abstract
In this paper, we present our Machine Learning (ML) based big data analytics framework that we tested to improve the quality and performance of Auxiliary Power Units (APU) health monitoring services. We are motivated to develop and apply practical and useful big data analytics technologies for industrial applications in aerospace and aviation. Key contributions of our work include the development and use of our ML algorithms that have been tested and used to analyze multiple data sources and to provide useful insights and increase the ability to predict (1) APU wear from 39%to 56% and (2) APU shutdown events from 19% to 60%. Such system health monitoring can be integrated with the widely used condition based maintenance (CBM) services. Users can use this cloud based analytic toolset and access the big data through any devices (PCs, Tablets, smart phones) anytime and anywhere.Keywords
This publication has 16 references indexed in Scilit:
- Predictive analysis of engine health for decision supportACM SIGKDD Explorations Newsletter, 2014
- Research on Big Data Architecture, Key Technologies and Its Measures2013
- Curating and Mining (Big) Data2013
- Big Data-as-a-Service: Definition and architecture2013
- Strategic Alignment of Cloud-Based Architectures for Big Data2013
- Cloud Based Architecture for Enabling Intuitive Decision Making2013
- Live Traffic Monitoring with Tstat: Capabilities and ExperiencesLecture Notes in Computer Science, 2010
- Predictive security model using data mining2005
- The ganglia distributed monitoring system: design, implementation, and experienceParallel Computing, 2004
- Toward formally-based design of message passing programsIEEE Transactions on Software Engineering, 2000