OXILATE - Operational eXcellence by Integrating Learned information into AcTionable Expertise

OXILATE

OXILATE aims at enhancing intelligent services on complex systems, integrated in the customer’s operating context, reacting to the emerging customer needs for operationalized expertise in an agile manner. This will be achieved by development and use of flexible data-driven tools, methods, processes, models and platforms fusing expert knowledge with data analytics on operational data.
Funders
Image
Oxilate main image with touchscreen

Project information

Project duration

-

Funded by

Business Finland

Project coordinator

Other university or unit

Contact information

Contact person

Project description

The Finnish consortium involves two mid-cap companies working on software solutions (M-Files, Intopalo Digital), one SME (Atostek) extending its own solutions, and two large companies contributing an ecosystem to develop realistic and robust services (Valmet Automation, CP Kelco). The research partner is University of Oulu with groups of Emprical Software Engineering (M3S) and Control Engineering (ECE). The Finnish consortium focuses on developing Industry 4.0 process automation support, enhancement of data and knowledge capture to form virtual plant models and agile development of intelligent knowledge and data-intensive solutions for diagnostics, field services, and process optimization. Acquired knowledge and data form a digital twin of an industrial process, which becomes a data-intensive ecosystem for developing new applications for data analytics and intelligent interfaces to boost industry operations and services. Data intensive service support releases R & D resources from technical service support tasks to innovation activities.

Our research activities in this project aim to find flexible pre-processing, process identification and modeling methods enabling efficient use of both the operational data and outputs from the digital twins. The developed models act as digital assistants e.g. for the process operators and supervisors in applications such as predictive maintenance, real-time process performance monitoring and prediction, as well as root-cause analyses.