Case Study: a global chemical manufacturer achieves 15% more effective operating time with STX Next predictive maintenance

A STX Next Case Study

Preview of the Global Chemical Manufacturer Case Study

Global Chemical Manufacturer boosts operating time by 15% with STX Next

A global chemical manufacturer faced the challenge of scheduling furnace cleanings based on fixed historical averages, which did not account for the varying condition of individual units. This approach led to premature cleanings that reduced uptime or delayed cleanings that risked equipment damage. STX Next was engaged to develop a solution using machine learning and predictive maintenance.

STX Next built a condition-based scheduler using Python and Azure ML to forecast when each unit would require cleaning. This solution provided a live operational view and integrated maintenance planning, which helped increase effective operating time by approximately 15% at the first site. The results included fewer unplanned outages, lower fuel consumption per ton produced, and more efficient shift handovers and site-wide planning.


View this case study…

STX Next

49 Case Studies