
Industrials
In the project the customer needed to develop a predictive maintenance platform using Big Data technologies to detect failing components before they break, enabling better visualization and analysis of maintenance issues, contacting customers for warranty replacements, and significantly reducing repair costs. synvert created a time-dependent ML model to predict potential problems with confidence intervals for increased interpretability.
Initial situation
The customer collected a large amount of manufacturing and maintenance data and was struggling to make sense of it.
The vision was to develop a predictive maintenance platform to save costs by reducing expensive repairs.
This can be achieved by detecting failing components before they break.
Architecture
The entire pipeline has been developed using Big Data technologies (Spark, Hadoop, Python) and is completed with a dashboard for visualization in Tableau.
After the production rollout, he project has been handed over to the operations team.
Generated benefits
The customer is able to better visualize and analyze maintenance issues.
Multiple customers can be contacted to replace specific components while still under warranty.
The operations teams are also able to identify patterns and significantly reduce high repair costs.
Services accomplished by synvert
synvert has developed a prediction model based on a time-dependent training set.
The ML model is able to predict potential problems for a given machine based on many different characteristics (when it was manufactured, when it was sold, components, etc.).
For each prediction, a confidence interval for the prediction is also provided to increase the interpretability of the model.