CASE STUDY

Orbital: Decentralised Deep Learning sets New State of the Art benchmark in asset failure prediction by 52%

12 Jun 2024

12 Jun 2024

Goals

Demonstrate that a decentralised deep learning approach for asset failure prediction can be achieved while maintaining data privacy, security, and reduced operational costs.

Develop and evaluate this approach in a digital twin environment for pipeline failure prediction up to 96 hours before onset.

Energy Intensity Index (EII) prediction & root-cause analysis

Benchmark and compare this approach to current machine learning methods deployed via Cloud in the industry on the following metrics: Model Accuracy, False Positive Prediction and Prediction performance

Energy Intensity Index (EII) prediction & root-cause analysis

Results

0

%

Overall Accuracy

Overall Accuracy

0

%

higher accuracy at each day of prediction

higher accuracy at each day of prediction

0

%

earlier predictions compared to other models

earlier predictions compared to other models

STAY UP TO DATE

Sign up for news and updates

© Kashmir Intelligence 2024

Kashmir Intelligence is a remote first company headquartered in London, UK

© Kashmir Intelligence 2024

Kashmir Intelligence is a remote first company headquartered in London, UK

© Kashmir Intelligence 2024

Kashmir Intelligence is a remote first company headquartered in London, UK