Aka "How to recognize the early signs of disruption"
On November 11 at 13.00 CET Rosaria Silipo and Iris Adä, KNIME, will be presenting a webinar on BrightTALK all about detecting anomalies in predictive maintenance with KNIME.
With the advent of the Internet of Things, system and monitoring applications are producing humongous amounts of data which undergo evaluation to optimise costs and benefits, predict future events, classify behaviours, implement quality control, and more.
The newest challenge lies in predicting the “unknown”, i.e. an anomaly. An anomaly is an event that is not part of the system past, an event that cannot be found in the system’s historical data. In the case of network data, an anomaly can be an intrusion, in medicine a sudden pathological status, in sales or credit card businesses a fraudulent payment, and, finally, in machinery a mechanical piece breakdown.
The problem here is: how can we predict something we have never seen, an event that is not in the historical data?
We need to change our analytical perspective: learn to reproduce normal functioning (because those are the data we have) and define criteria to recognize when our predictions and the underlying system are not in sync anymore.
This presentation deals with the recognition of early signs of anomalies in the sensor signals monitoring a working rotor. Here, auto-regressive models are trained on historical data to reproduce the rotor normal functioning over time, and therefore making possible the recognition of early signs of disruption.
Register for free here
Rosaria Silipo is the Principal Data Scientist at KNIME and works at our new office in Konstanz. She has been a researcher in applications of data mining and machine learning for many years already. Her application fields include biomedical systems and data analysis, financial time series, risk analysis and automatic speech processing. At KNIME her specialties include reporting, machine learning and the management and development of data mining groups.
Iris Adä is a Data Scientist at KNIME.com and is based in Heidelberg. Her research focus lies in event detection in time series data. She has gained many years of experience in teaching from basic computer science to advanced data mining courses at the University of Konstanz. In addition she is responsible for the data generation and many of the time series nodes.