Journal
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
Volume 85, Issue -, Pages 590-606Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.engappai.2019.07.013
Keywords
Multi agent systems; Distributed systems; Recurrent neural networks; Prognostics; Networks; Asset management
Categories
Funding
- Fundacio la Caixa [LCF/BQ/EU17/11590049]
- Next Generation Converged Digital Infrastructure project - Engineering and Physical Sciences Research Council [EP/R004935/1]
- BT
- Centre for Digital Built Britain
- EPSRC [EP/L010917/1, EP/N021614/1, EP/I019308/1, EP/R004935/1, EP/K000314/1] Funding Source: UKRI
Ask authors/readers for more resources
Despite increasing interest, real-time prognostics (failure prediction) is still not widespread in industry due to the difficulties of existing systems to adapt to the dynamic and heterogeneous properties of real asset fleets. In order to address this, we present an Industrial Multi Agent System for real-time distributed collaborative prognostics. Our system fulfils all six core properties of Advanced Multi Agent Systems: Distribution, Flexibility, Adaptability, Scalability, Leanness, and Resilience. Experimental examples of each are provided for the case of prognostics using the C-MAPPS engine degradation data set, and data from a fleet of industrial gas turbines. Prognostics are performed using the Weibull Time To Event-Recurrent Neural Network algorithm. Collaboration is achieved by sharing information between agents in the system. We conclude that distributed collaborative prognostics is especially pertinent for systems with presence of sensor faults, limited computing capabilities or significant fleet heterogeneity.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available