Machine Fault Classification using Hamiltonian Neural Networks

by   Jeremy Shen, et al.
University of Michigan
UNC Charlotte
University of South Carolina

A new approach is introduced to classify faults in rotating machinery based on the total energy signature estimated from sensor measurements. The overall goal is to go beyond using black-box models and incorporate additional physical constraints that govern the behavior of mechanical systems. Observational data is used to train Hamiltonian neural networks that describe the conserved energy of the system for normal and various abnormal regimes. The estimated total energy function, in the form of the weights of the Hamiltonian neural network, serves as the new feature vector to discriminate between the faults using off-the-shelf classification models. The experimental results are obtained using the MaFaulDa database, where the proposed model yields a promising area under the curve (AUC) of 0.78 for the binary classification (normal vs abnormal) and 0.84 for the multi-class problem (normal, and 5 different abnormal regimes).


page 4

page 6


Hamiltonian Neural Networks with Automatic Symmetry Detection

Recently, Hamiltonian neural networks (HNN) have been introduced to inco...

Universal Approximation Properties of Neural Networks for Energy-Based Physical Systems

In Hamiltonian mechanics and the Landau theory, many physical phenomena ...

Symplectic Learning for Hamiltonian Neural Networks

Machine learning methods are widely used in the natural sciences to mode...

The Impact of Feature Causality on Normal Behaviour Models for SCADA-based Wind Turbine Fault Detection

The cost of wind energy can be reduced by using SCADA data to detect fau...

Unsupervised Synthesis of Anomalies in Videos: Transforming the Normal

Abnormal activity recognition requires detection of occurrence of anomal...

Multiclass Model for Agriculture development using Multivariate Statistical method

Mahalanobis taguchi system (MTS) is a multi-variate statistical method e...

Health Monitoring of Industrial machines using Scene-Aware Threshold Selection

This paper presents an autoencoder based unsupervised approach to identi...

Please sign up or login with your details

Forgot password? Click here to reset