A data-driven fuzzy approach for predicting the remaining useful life in dynamic failure scenarios of a nuclear system

By Enrico Zio, Francesco Di Maio. Reliability Engineering & System Safety, 2010

320 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/8847c2f1541ab9789531d7a3c3aba6630044716c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Jooho Choi
2. A. K. Qin
3. Kay Chen Tan
4. Dawn An
5. Chong Zhang
6. Nam-Ho Kim
7. Pin Lim

In Control and Systems Engineering

1. Jooho Choi
2. A. K. Qin
3. Kay Chen Tan
4. Dawn An
5. Noureddine Zerhouni
6. Chong Zhang
7. Qin Wang
8. Olga Fink

Citations in the corpus

• Practical options for selecting data-driven or physics-based prognostics algorithms with reviews (2015, methodology): “The data-driven approaches are generally divided into two categories: (1) the artificial intelligence approaches that include neural network (NN) [21–23] and fuzzy logic [24,25]; and (2) the statistical approaches that include the Gaussian process (GP) regression [26,27], relevance/support vector ma”
• Direct Remaining Useful Life Estimation Based on Support Vector Regression (2017, methodology): “tained by the linear regression [27]–[29], unsupervised kernel regression modeling [30], fuzzy model [31], [32], or by polygons”
• Remaining Useful Lifetime Prediction via Deep Domain Adaptation (2019, unknown): “In particular, authors have proposed several methods that attempt to extract the relationships of acquired sequential data and RUL prediction, such as linear regression [23], Support Vector Regression (SVR) [8], fuzzy-logic systems [24] and neural networks [25].”
• Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics (2017, methodology): “sion [12], fuzzy similarity-based methods [11], [13], and Kalman filter (KF) [10], usually involves a grid search to seek”
• Potential, challenges and future directions for deep learning in prognostics and health management applications (2020, methodology): “…or design parameters of the units (e.g. average operating regimes) in order to find sub-fleets, possibly with clustering, defined by similar characteristics based on the selected parameters; subsequently using the data of each of the sub-fleets to train the algorithms (Zio and Di Maio, 2010).”