Industrial companies typically have large amounts of sensor data from operating equipment such as turbines, pumps and compressors. The sensor data may represent pressure, vibrations, heat etc. over time. In order to use machine learning to predict equipment failures before they occur, it is necessary to obtain training data about past incidents from historical maintenance logs. Due to the large volume of such data from different companies, we seek to automate parts of this process by training an NLP algorithm on a subset of the logs and let it label the remaining.
The project is a collaboration with Cognite, a newly established company in Oslo. Cognite aims to build the leading Industrial Internet of Things (IIoT) data platform, enabling customers in various industries to create value from their sensor data. Their mission is to "Optimize the real world". Some traveling to Oslo may be necessary.