Vol. 7 No. 4 (2016): IJPHM Special Issue on Big Data and Advanced Analytics for PHM

The International Journal of Prognostics and Health Management (IJPHM) is the premier online open access journal related to multidisciplinary research on Prognostics, Diagnostics, and System Health Management. This special issue is focused on research advances in Big Data and Advanced Analytics pushing the envelop of machine intelligence in the digital industrial world.

The past ten years have witnessed a revolution in computer science and statistics. Neural networks have risen from obscurity as a collection of innovative new techniques known as Deep Learning, and are achieving human-level performance in image recognition and game playing. New hardware configurations and novel approaches, collectively known as Big Data, have been developed to effectively deal with the torrent of data from nearly ubiquitous sensors.

The Cloud Computing business model has arisen, making shared, configurable, and elastic computing resources available on demand as needed. Finally, a niche discipline of Industrial Analytics has emerged, characterized by predictive analytics and optimization for fleets of similar assets – e.g., aircraft engines, subsea oil pumps, computed tomography scanners. One challenge lies in combining irregularly occurring free-text maintenance and repair records and usage logs with regularly sampled but intermittent time series of control system, environmental, and usage data.

These four trends – Deep Learning, Big Data, Cloud Computing, and Industrial Analytics – will undoubtedly have a profound effect on the research and application of PHM, and people already doing work in this area are truly on the cutting edge of the science. This CFP solicits papers advancing Deep Learning, Cloud Computing, Big Data, and Industrial Analytics for PHM. Papers describing both novel applications of these techniques and related theory are encouraged.

Published: 2016-12-02

Technical Papers

Wearable EEG-based Activity Recognition in PHM-related Service Environment via Deep Learning

Soumalya Sarkar, Kishore Reddy, Alex Dorgan, Cali Fidopiastis, Michael Giering
Abstract 417 | PDF Downloads 357 | DOI https://doi.org/10.36001/ijphm.2016.v7i4.2459

A Hybrid Approach for Fusing Physics and Data for Failure Prediction

Prashanth Pillai, Anshul Kaushik, Shivanand Bhavikatti, Arjun Roy, Virendra Kumar
Abstract 596 | PDF Downloads 597 | DOI https://doi.org/10.36001/ijphm.2016.v7i4.2463

A SOM based Anomaly Detection Method for Wind Turbines Health Management through SCADA Data

Mian Du, Lina Bertling Tjernberg, Shicong Ma, Qing He, Lin Cheng, Jianbo Guo
Abstract 298 | PDF Downloads 291 | DOI https://doi.org/10.36001/ijphm.2016.v7i4.2464

An Approach To Mode and Anomaly Detection with Spacecraft Telemetry Data

Gautam Biswas, Hamed Khorasgani, Gerald Stanje, Abhishek Dubey, Somnath Deb, Sudipto Ghoshal
Abstract 537 | PDF Downloads 494 | DOI https://doi.org/10.36001/ijphm.2016.v7i4.2467

A Methodology for Updating Prognostic Models via Kalman Filters

Venkatesh Rajagopalan, Arun Subramaniyan
Abstract 213 | PDF Downloads 209 | DOI https://doi.org/10.36001/ijphm.2016.v7i4.2525