The purpose of the OBIGGS is to reduce the amount of oxygen in the fuel tank to a 'safe' level to significantly reduce the possibility of ignition of fuel vapors. There are circumstances where equipment of OBIGGS like ASMs, Ozone Converter Catalysts, etc. gets degraded earlier than the provided MTBF.This paper studies the present conventional systems limitations, like due to memory constraints only the faults and limited shop data are being recorded, hence there is no provision to store/report the stream of data margins with which we can pass/fail the performance tests.This paper also explains how a new design of the Connected concept achieves access to real-time data from the system and how the data is pushed to the cloud network. A connected solution for the OBIGGS is the technology to access real-time data (Systems LRUs Performance data and Custom data Parameters) from the Systems controller data bus, this data is further applied to AI/ML methods for predictive/prognostics features to compare why the performance of the ASMs in some systems may degrade quicker than others and to inform of when equipment of OBIGGS may need to be inspected/tested/replaced.VOCs related to ASMs degradation, FQIS field issues, sensors, valves, and other equipment's data parameters can be monitored over time that would be of value and an interest in more details for the Suppliers, Manufacturers, and Customers side.
Connected On-Board Inert Gas Generation System with Real-Time Data Access & Machine Learning Approach for Predictive / Prognostics Maintenance
Sae Int. J. Adv. and Curr. Prac. in Mobility
AeroCON 2022 ; 2022
Sae International Journal of Advances and Current Practices in Mobility ; 5 , 2 ; 762-767
2022-05-26
6 pages
Conference paper
English
On-Board Predictive Maintenance with Machine Learning
SAE Technical Papers | 2019
|Connected Vehicle Data – Prognostics and Monetization Opportunity
SAE Technical Papers | 2023
|A Generic Bayesian Approach to Real-Time Structural Health Prognostics
British Library Conference Proceedings | 2008
|Machine learning methods for vehicle predictive maintenance using off-board and on-board data
BASE | 2014
|