CREATION OF AN INDUSTRIAL DATA PLATFORM FOR ASSET MAINTENANCE
Many industrial companies have faced the challenge of implementing predictive maintenance programs. Mature machine learning tools are already available, and inflated marketing expectations have increased senior management sponsorship. But the harsh reality is that predictive maintenance projects have still shown very little impact on companies’ manufacturing environments.
The big barrier to achieving the expected results is the problem of data integration. Different equipment and assets require different predictive maintenance approaches that must be properly orchestrated. Beyond the issue of asset diversity, predictive maintenance solutions must integrate with the overall legacy maintenance process and systems.
HOW WE HELP
Galeo has worked with several clients to successfully design and consolidate predictive maintenance programs into the appropriate data platform infrastructure. Our work with them has been based on a modular approach based on the reuse and integration of information. This includes:
- Data capture infrastructure – including sensors and gateways – with appropriate abstraction layers for data management and data flows.
- Governance and data explorationwith automatic catalog capability. This component enabled the exploration and discovery of data for eventual reuse, making operational data available to predictive systems in a fully contextualized manner.
- Establish integration mechanismsto rapidly prototype complex asset maintenance systems by combining different specialized puzzle pieces: A prediction system for rotating equipment can be combined with a corrosion prediction system for chemical process plants, for example.
The modular approach we followed, whose main functionality was oriented to the integration of information and the modular combination of predictive solutions, has confirmed the possibility of accelerating the delivery of a predictive maintenance program. Systems development gains traction as pieces of the puzzle shorten time to value, improve agility to pivot failed approaches, and eliminate duplication of low-value efforts related to data infrastructure engineering.