indin_2019 (1).pdf (313.61 kB)
Measuring system entropy with a deep recurrent neural network model
conference contribution
posted on 2021-08-04, 08:24 authored by Miguel Martinez-GarciaMiguel Martinez-Garcia, Eve ZhangEve Zhang, Kenji Suzuki, Yudong ZhangIn this paper, a methodology for assessing the unpredictability of systems with memory was developed. The proposed approach consists in approximating the probability distribution exhibited by the response of a system, understood as a stochastic process, with a deep recurrent neural network; such networks offer increased forecasting capability by exploiting an accumulative register of previous system states. Once the probability distribution is computed, the uncertainty or entropy of the underlying process is measured. This measure determines the degree of regularity in the system, and identifies how atypical the system dynamics are. The proposed model was validated by identifying industrial gas turbine engine faults from recorded sensor data.
Funding
EPSRC Grant EVES (EP/R029741/1)
History
School
- Aeronautical, Automotive, Chemical and Materials Engineering
Department
- Aeronautical and Automotive Engineering
Published in
2019 IEEE 17th International Conference on Industrial Informatics (INDIN)Pages
1253 - 1256Source
2019 IEEE 17th International Conference on Industrial Informatics (INDIN)Publisher
IEEEVersion
- AM (Accepted Manuscript)
Rights holder
© IEEEPublisher statement
© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.Publication date
2020-01-30Copyright date
2019ISBN
9781728129273eISSN
2378-363XPublisher version
Language
- en