← Back to all news
arXiv Machine Learning By Seshu K. Damarla, Xiuli Zhu

Contrastive Siamese Representation Learning for Predictive Maintenance of Electrical Submersible Pumps

Read the original on arXiv Machine Learning →

The paper introduces a fault‑diagnosis framework for electrical submersible pumps that uses Siamese contrastive representation learning to handle class imbalance and a prior‑corrected k‑nearest neighbor classifier for robust fault classification. It extracts discriminative vibration‑domain features, trains a Siamese network to cluster same‑fault samples, and applies a distance‑weighted KNN to mitigate imbalance. Validation with a Leave‑One‑ESP‑Out strategy shows consistent performance across unseen pump units, indicating potential for reliable predictive maintenance in offshore oil production.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 20

Multi-Class Electrical and Mechanical Fault Classification Using Random Convolutional Kernels

The paper evaluates SelF‑Rocket, a random convolutional kernel-based method, for multi‑class diagnosis of mechanical and electrical faults in rotating machinery. It introduces a multivariate extension of SelF‑Rocket and compares it with leading ROCKET‑based methods on two public benchmarks, MaFaulDa and ITSC‑UDG. Results show SelF‑Rocket achieves the best accuracy‑latency trade‑off, excelling on MaFaulDa and remaining competitive on the more challenging ITSC‑UDG dataset.

By Mouhamadou Mansour Lo, Mouad Talbaoui, Gildas Morvan, Mathieu Rossi, Fabrice Morganti, David Mercier
benchmarks
More like this →