This talk is targeted to data scientists, students, researchers, and non-technical professionals who are interested in data-driven predictive maintenance applications in the IT industry. At the end of the talk, the audience will get a clear picture of the landscape and challenges of predictive maintenance applications, including problem coverage, various applicable predictive models based on data available, and knowledge about what data should be collected.
Predictive maintenance is a technique to predict when an in-service machine will fail so that maintenance can be planned in advance. In a broader sense, it covers a variety of topics, including but not limited to: failure prediction, failure diagnosis, failure type classification, and recommendation of maintenance actions after failure.
Data-driven predictive maintenance, in particular, is gaining increased attention in the industry along with the emerging demand of Internet of Things applications and the maturity of supporting technologies. With the objective of being able to generate, transmit, store, and analyze big data, these technologies include innovations in hardware (e.g. sensor instruments, memory technologies), network technologies (wireless communication protocols), software architectures (pipeline to process streaming data and/or unstructured data in the cloud), and advanced analytics (e.g. problem formulation, machine learning modeling).
In the context of predictive maintenance applications, this talk will focus on the big data analytics aspect of the above mentioned four innovation areas. We review the predictive maintenance problems from two perspectives: from the view of the traditional reliability-centered maintenance field, and from the view of the IoT applications. We’ll emphasize bridging the data-driven approach with the problem-driven approach, by articulating which types of data are requested for different predictive maintenance applications. We strive to bring the attention of IoT industry leaders to the necessary data acquisition required before conducting effective predictive maintenance applications. A real-world example will be discussed by showing how a predictive maintenance problem is formulated into three related questions via different machine learning models.
The audience will learn hands-on experience about how to formulate a predictive maintenance problem into three different machine learning models (regression, binary classification, and multi-class classification) through a real-world example. This is illustrated by showing a step-by-step procedure of data input, data preprocessing, data labeling, and feature engineering to prepare the training/testing data from the raw data. Last, we illustrate how different types of learning models can be trained and compared with different algorithms.
Yan Zhang is a senior data scientist with the algorithm and data science team of the Data Group within Cloud and Enterprise at Microsoft. She builds predictive analytics models and generalizes machine learning solutions on the cloud machine learning platform. Her recent research includes cost prediction and fraud claim detection in the healthcare domain, predictive maintenance in IoT applications, customer segmentation, and text mining. Previously, she was a research faculty member at Syracuse University. Yan earned her PhD in data mining from the Computer Science Department at the University of Vermont. She’s the author of 23 publications, including journal articles, conference papers, and blog posts. Her first paper won the best paper award at the 17th IEEE International Conference on tools with artificial intelligence. She’s one of the reviewers for the book Predictive Analytics with Microsoft Azure Machine Learning, second edition, published in September 2015.
Comments on this page are now closed.
©2015, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • email@example.com
Apache Hadoop, Hadoop, Apache Spark, Spark, and Apache are either registered trademarks or trademarks of the Apache Software Foundation in the United States and/or other countries, and are used with permission. The Apache Software Foundation has no affiliation with and does not endorse, or review the materials provided at this event, which is managed by O'Reilly Media and/or Cloudera.