Manufacturing today considers data-drive business operations at different levels leading to the growth of various paradigms in manufacturing, of which emerged smart manufacturing.
However data can be used to predict equipment failure rates, streamline and optimize inventory management and prioritize processes.
The use of parameter tuning and optimization, grid-search, cross-validation, to predict the best performing machine learning algorithm. This research work evaluates the time potential failure-rates, against the lines which peaks and drops depending on its components RUL(Remaining Useful Life). The accuracy of the machine learning algorithms that are employed in this studies, are hence subjected to some metrics for evaluation, these are : MCC and AUC-ROC.
This study has analyzed and evaluated some annoymized dataset from a manufacturing company, using some metrics and machine learning algorithms for performance prediction of their production lines using unsupervised learning. This study would served as a good reference for anyone wanting to use the best performance model, for further research work.