Find out how we can help your digital transformation. Contact us to learn more.
Planes, Trains, and Automobiles - A Data Scientist’s Guide to Modeling Engine Degradation
With the growth of connected “things”, industries are presented with huge opportunities to leverage sensor data to improve their operations, products, and services. With the proliferation of these devices, competitive advantages will develop from appropriate leveraging of the deluge of data. From connected appliances to jet engines, industries are already undergoing massive transformations. Critical to success is the ability to not only collect data from sensors, but to also leverage big data technologies and data science expertise to extract actionable insights from the data.
It is critical to be able to model degradation of a machine to prevent catastrophic events and to adjust maintenance scheduling. This is true in industries including oil and gas, transportation, and even consumer products.
In this latest Data Science Central webinar, members of the Pivotal Data Science team presents a data-driven approach to detecting and tracking jet-engine degradation using simulated sensor data.
In particular, we will focus on:
- data integration and cleansing
- transformation of time series data from sensors into meaningful features for modeling
- the algorithms used to build models to identify engine degradation patterns
Sarah Aerni is a Principal Data Scientist at Pivotal leading the San Francisco practice. She executes projects with customers from pharmaceutical companies and healthcare providers to financial institutions. Before Pivotal, Sarah obtained her PhD from Stanford University in Biomedical Informatics, performing research at the interface of biomedicine and machine learning. She focused her efforts on building computational models enabling research for a broad range of fields in biomedicine. In addition to academic research, she has experience in co-founding a company offering expert services in informatics for both academic and industry settings and consulting. Beyond her interests in biomedical informatics, she is passionate about education and fostering interdisciplinary collaboration.
April's experience ranges from building predictive models to developing applications as part of a cross-functional team. She has recently worked on a variety of IoT use cases; analyzing time series of smart meters, identifying anomalies in propulsion systems, and inventory optimization in oil & gas equipment parts. Her previous projects include clickstream analysis, a music recommender, and topic modeling. She has interest in all things connected, speaks three languages, and holds a B.S. in Applied Mathematics and a minor in Industrial Engineering/Operations Research from UC Berkeley.
Bill is the Editorial Director for Data Science Central and the President and Chief Data Scientist at Data-Magnum, providing predictive analytics and big data infrastructure projects as a service. Bill has been an active commercial predictive modeler since 2001.