Browse Prior Art Database

Real Time & Proactive Plant Event Management through text mining & automatic classification Disclosure Number: IPCOM000246855D
Publication Date: 2016-Jul-07
Document File: 1 page(s) / 56K

Publishing Venue

The Prior Art Database

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 53% of the total text.

Page 01 of 1

Real Time & Proactive Plant Event Management through text mining & automatic classification

A comprehensive Central Event Processing System (CEPS) is connected to the plant operation so that the CEPS:

 on the one hand, receives, compiles, collects in digital log books, text mines, structures and analyzes warnings coming from the plants, and

 on the other hand, sends instructions for prescriptive actions back to the plant or its operator so as to enable the plant or plant operator to react as fast as possible to the warning based on extensive knowledge of past warnings, incidents and repairs/remedies reported in digital log books over time at a central level.

1. The CEPS creates and constantly updates a structured database from the historical text data stream coming from the plant operations (unstruct).

2. When an anomaly/incident/accident is emitted by a plant or plant operator, the CEPS applies automatic classification and similarity based techniques to relate the event to the right class of equipment/process/external factor types.

3. As soon as the automatic classification is performed, the CEPS generates a potential set of course of events (consequences, impacts, costs…) that occurred to equivalent equipments and in equivalent situations to be proposed to the plant/plant operator with associated probabilities based on scoring algorithms
4. The CEPS then communicates the best reactive actions to the plant or plant operator including prescriptive actions for the prevention of an expected failure, the most efficient repair actions to perform with regards to given incidents/accidents…

Text mining software solutions are largely used for web mining, sentiment analysis on social networks and more generally speaking for structuring web data in order to provide insights on trends, impacts of brands, names… They can also be used for classification purp...