Fully Unsupervised Feature Alignment for Critical System Health Monitoring with Varied Operating Conditions

by   Gabriel Michau, et al.

The failure of a complex and safety critical industrial asset can have extremely high consequences. Close monitoring for early detection of abnormal system conditions is therefore required. Data-driven solutions to this problem have been limited for two reasons: First, safety critical assets are designed and maintained to be highly reliable and faults are rare. Fault detection can thus not be supervised. Second, complex industrial systems usually have long lifetime and face very different operating conditions. Collecting a representative training dataset would require long observation periods, and delay the monitoring of the system. In this paper, we propose a methodology to monitor the systems in their early life. To do so, we enhance the training dataset with other units from a fleet, for which longer observations are available. Since each unit has its own specificity, we propose to extract features made independent of their origin by three unsupervised feature alignment techniques. First, using a variational encoder, we impose a shared latent space for both units. Second, we introduce a new loss designed to conserve inter-point spacial relationships between the input and the latent spaces. Last, we propose to train in an adversarial manner a discriminator on the origin of the features. Once aligned, the features are fed to a one-class classifier to monitor the health of the system. By exploring the different combinations of the proposed alignment strategies, and by testing them on a real case study, a fleet composed of 112 power plants operated in different geographical locations and under very different operating regimes, we demonstrate that this alignment is necessary and beneficial.


page 1

page 2

page 3

page 4


Unsupervised Fault Detection in Varying Operating Conditions

Training data-driven approaches for complex industrial system health mon...

Transferring Complementary Operating Conditions for Anomaly Detection

In complex industrial systems, the number of possible fault types is unc...

A Comparison of Residual-based Methods on Fault Detection

An important initial step in fault detection for complex industrial syst...

Federated Learning with Uncertainty-Based Client Clustering for Fleet-Wide Fault Diagnosis

Operators from various industries have been pushing the adoption of wire...

Contrastive Feature Learning for Fault Detection and Diagnostics in Railway Applications

A railway is a complex system comprising multiple infrastructure and rol...

Dictionary learning approach to monitoring of wind turbine drivetrain bearings

Condition monitoring is central to the efficient operation of wind farms...

Please sign up or login with your details

Forgot password? Click here to reset