A systematic review of data-driven approaches to fault diagnosis and early warning

P Jieyang, A Kimmig, W Dongkun, Z Niu, F Zhi… - Journal of Intelligent …, 2023‏ - Springer
As an important stage of life cycle management, machinery PHM (prognostics and health
management), an emerging subject in mechanical engineering, has seen a huge amount of …

[HTML][HTML] Electricity price forecasting: A review of the state-of-the-art with a look into the future

R Weron - International journal of forecasting, 2014‏ - Elsevier
A variety of methods and ideas have been tried for electricity price forecasting (EPF) over the
last 15 years, with varying degrees of success. This review article aims to explain the …

Deep learning, explained: Fundamentals, explainability, and bridgeability to process-based modelling

S Razavi - Environmental Modelling & Software, 2021‏ - Elsevier
Recent breakthroughs in artificial intelligence (AI), and particularly in deep learning (DL),
have created tremendous excitement and opportunities in the earth and environmental …

Learning long-term dependencies with gradient descent is difficult

Y Bengio, P Simard, P Frasconi - IEEE transactions on neural …, 1994‏ - ieeexplore.ieee.org
Recurrent neural networks can be used to map input sequences to output sequences, such
as for recognition, production or prediction problems. However, practical difficulties have …

Deep learning: Evolution and expansion

R Wason - Cognitive Systems Research, 2018‏ - Elsevier
This paper historically attempts to map the significant success of deep neural networks in
notably varied classification problems and application domains with near human-level …

Learning long-term dependencies in NARX recurrent neural networks

T Lin, BG Horne, P Tino, CL Giles - IEEE transactions on neural …, 1996‏ - ieeexplore.ieee.org
It has previously been shown that gradient-descent learning algorithms for recurrent neural
networks can perform poorly on tasks that involve long-term dependencies, ie those …

Computational capabilities of recurrent NARX neural networks

HT Siegelmann, BG Horne… - IEEE Transactions on …, 1997‏ - ieeexplore.ieee.org
Recently, fully connected recurrent neural networks have been proven to be computationally
rich-at least as powerful as Turing machines. This work focuses on another network which is …

The problem of learning long-term dependencies in recurrent networks

Y Bengio, P Frasconi, P Simard - IEEE international conference …, 1993‏ - ieeexplore.ieee.org
The authors seek to train recurrent neural networks in order to map input sequences to
output sequences, for applications in sequence recognition or production. Results are …

Long-term wind speed and power forecasting using local recurrent neural network models

TG Barbounis, JB Theocharis… - IEEE Transactions …, 2006‏ - ieeexplore.ieee.org
This paper deals with the problem of long-term wind speed and power forecasting based on
meteorological information. Hourly forecasts up to 72-h ahead are produced for a wind park …

Input-output HMMs for sequence processing

Y Bengio, P Frasconi - IEEE Transactions on Neural Networks, 1996‏ - ieeexplore.ieee.org
We consider problems of sequence processing and propose a solution based on a discrete-
state model in order to represent past context. We introduce a recurrent connectionist …