A Fault Detection Strategy for an ePump During EOL Tests based on a Knowledge-based Vibroacoustic Tool and Supervised Machine Learning Classifiers

This paper presents a methodology for identifying faulty components in an electric pump during the end-of-line test based on accelerations and pressure pulsation data used to train an ensem- ble learning algorithm based on supervised machine learning classifiers. Despite various quality control measures in pump manufacturing, some out-of-tol- erance components can pass through and end up on the assembly line, potentially leading to premature failure or abnormal noise during real-field operation. Because of the high impact, it is very important to put in place actions to mitigate the risk of delivering non-conform units, even if properly working in terms of pressure-flow rate performances. In this paper, an innovative knowledge-based vibroacoustic tool together with a machine learning built-in Python® library have been used to post-process acceleration and pressure pulsations data to generate features, which are then used to train, and test several super- vised machine learning algorithms. The ensemble learning algorithm combines the best classifiers to identify healthy electric pump units with high accu- racy, achieving above 95% accuracy in an experi- mental test campaign carried out on eighty electric pumps. Results are compared using principal compo- nent analysis for dimensionality reduction, and a sen- sor sensitivity study is conducted.