One challenge when dealing with manufacturing sensor data analysis is to formulate an efficient model of the underlying physical system. Rajesh Sampathkumar shares his experience working with sensor data at scale to model a real-world manufacturing subsystem with simple techniques, such as moving average analysis, and advanced ones, like VAR, applied to the problem of predictive maintenance.
Rajesh begins by exploring product sensor data, using aggregate statistical methods that do not consider the time element of the data in the analysis. These methods are effective in certain classes of problems where the failure modes are well defined, despite their obvious deficiency of not incorporating the time dimension. Rajesh then explores classification- and regression-based machine-learning approaches respectively, according to the hypotheses set up from the data. After validating the scope and usefulness of aggregate statistical modeling approaches, Rajesh incorporates the time dimension into the analysis and discusses various relevant algorithms. Rajesh concludes by sharing practical experiences running through this gamut of options and outlining some best practices relevant for anybody else embarking on the same journey.
Rajesh Sampathkumar is senior consultant at the Data Team, a strategy consulting organization focused on big data, data analytics, and data science, where he works with clients in diverse industries to provide data science expertise relevant to their business and decision making. Rajesh has many years of experience in consulting, design, and engineering at a number of reputed organizations.
©2016, 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. • firstname.lastname@example.org
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.