Repository logo
 

Secure and communications-efficient collaborative prognosis

Accepted version
Peer-reviewed

Type

Article

Change log

Authors

Dhada, M 
Jain, AK 
Herrera, M 
Hernandez, MP 
Parlikad, AK 

Abstract

Collaborative prognosis is a technique that is used to enable assets to improve their ability to predict failures by learning from the failures of similar other assets. This is typically made possible by enabling the assets to communicate with each other. The key enabler of current collaborative prognosis techniques is that they require assets to share their sensor data and failure information between each other, which might be a major constraint due to commercial sensitivities, especially when the assets belong to different companies. This paper uses Federated Learning to address this issue, and examines whether this technique will enable collaborative prognosis while ensuring sensitive operational data is not shared between organisational boundaries. An example implementation is demonstrated for prognosis of a simulated turbofan fleet, where Federated Averaging algorithm is used as an alternative for the data exchange step. Its performance is compared with conventional collaborative prognosis that involves failure data exchange. The results confirm that Federated Averaging retains the performance of conventional collaborative prognosis, while eliminating the exchange of failure data within assets. This removes a critical hinderance in industrial adoption of collaborative prognosis, thus enhancing the potential of predictive maintenance.

Description

Keywords

electronic data interchange, maintenance engineering, groupware, fault diagnosis, failure analysis, conventional collaborative prognosis, failure data exchange, communications-efficient collaborative prognosis, current collaborative prognosis techniques, sensor data, failure information, sensitive operational data, data exchange step

Journal Title

IET Collaborative Intelligent Manufacturing

Conference Name

Journal ISSN

2516-8398
2516-8398

Volume Title

2

Publisher

Institution of Engineering and Technology (IET)

Rights

All rights reserved
Sponsorship
Engineering and Physical Sciences Research Council (EP/R004935/1)
EPSRC (via Lancaster University) (Unknown)