The project aimed to build a system to monitor real-time performance of equipment at a chemical plant, in São Paulo, Brazil. The system helped reducing corrective and preventive maintenance orders, increase productivity, and improve plant reliability.
The system was built using the PI System and custom hybrid AI models to calculate performance indicators and identify failures in 173 pieces of equipment (pumps, centrifugal compressors, liquid ring compressors, fans, cooling tower and a turbo generator).
PI System tools were used to model the equipment variables, build KPIs, configure notifications, notify the maintenance team about potential abnormal conditions, and present the information through user-friendly dashboards.
Solvay expects to reduce emergency work from 16% (2018 report) to 5% by the end of 2023. In addition to that, Solvay also noted a better integration between maintenance, operations, and engineering teams.