Equipment maintenance is usually done after a specific number of hours or cycles of operation.
However, this is often based on an average and not on sensor data of operational parameters.
Sometimes operational parameters lead to unplanned downtime of equipment in a production line, which can lead to major unforeseen costs.
Designed and built a Machine Learning model to predict equipment time to failure.
Optimized maintenance scheduling by minimizing the planned downtime.
Determined which factors have the highest impact on equipment time to failure by analyzing the importance of model features.
Minimized planned downtime due to optimized maintenance scheduling.
Reduced unplanned downtime of equipment and production lines.
Increased equipment lifetime by improving operational conditions based on understanding factors impacting equipment time to failure.