Access the full text.
Sign up today, get DeepDyve free for 14 days.
Imrus Salehin, Iftakhar Talha, Md. Hasan, Sadia Dip, M. Saifuzzaman, Nazmun Moon (2020)
An Artificial Intelligence Based Rainfall Prediction Using LSTM and Neural Network2020 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE)
Issam Abed, N. Kacem, N. Bouhaddi, M. Bouazizi (2016)
Multi-modal vibration energy harvesting approach based on nonlinear oscillator arrays under magnetic levitationSmart Materials and Structures, 25
Jianming Hu, Jianzhou Wang, Kailiang Ma (2015)
A hybrid technique for short-term wind speed predictionEnergy, 81
L. Dai, M. Singh (1997)
Diagnosis of periodic and chaotic responses in vibratory systemsJournal of the Acoustical Society of America, 102
Shun Chen, Liya Zhao (2023)
A quasi-zero stiffness two degree-of-freedom nonlinear galloping oscillator for ultra-low wind speed aeroelastic energy harvestingApplied Energy
L. Dai (2008)
Nonlinear Dynamics Of Piecewise Constant Systems And Implementation Of Piecewise Constant Arguments
Yann LeCun, L. Bottou, Yoshua Bengio, P. Haffner (1998)
Gradient-based learning applied to document recognitionProc. IEEE, 86
Neither labor jobs regarding the collecting and sorting of the raw measured data nor prior knowledge domains of physics and mathematics are required during the training and testing processes
Zhou Jiaming, Longlei Dong, GuangFu Wei, Jian Yan (2019)
Impact load identification of nonlinear structures using deep Recurrent Neural NetworkMechanical Systems and Signal Processing
K. Jaseena, Binsu Kovoor (2021)
Decomposition-based hybrid wind speed forecasting model using deep bidirectional LSTM networksEnergy Conversion and Management, 234
Yong Yu, Xiaosheng Si, Changhua Hu, Jian-xun Zhang (2019)
A Review of Recurrent Neural Networks: LSTM Cells and Network ArchitecturesNeural Computation, 31
Luyao Wang, Liming Dai (2021)
Vibro-acoustical responses of a sandwich panel consist of aluminum honeycomb core and fabric-reinforced graphite facingsJournal of Sandwich Structures and Materials, 24
Repeat the same data preparation work described in step one of establishment of conventional benchmarks part
Felix Gers, Jürgen Schmidhuber (2001)
LSTM recurrent networks learn simple context-free and context-sensitive languagesIEEE transactions on neural networks, 12 6
W. Szemplinska-Stupnicka (1990)
The Behavior of Nonlinear Vibrating Systems
Z. Abdallah, Lan Du, Geoffrey Webb (2010)
Data Preparation
Yoshua Bengio, P. Simard, P. Frasconi (1994)
Learning long-term dependencies with gradient descent is difficultIEEE transactions on neural networks, 5 2
Yushu Chen, A. Leung (1998)
Bifurcation and Chaos in Engineering
The proposed CNN-BLSTM data-driven model is still able to achieve accurate prediction and keep relative stability even © 2023
Luyao Wang, Liming Dai, Gang Hu (2021)
Low-frequency vibro-acoustic response of an optimized fiber-reinforced graphite truss sandwich panel filled with wood-based materialJournal of Low Frequency Noise, Vibration and Active Control, 40
I. Kovacic, M. Brennan (2011)
The Duffing Equation: Nonlinear Oscillators and their Behaviour
(2011)
Processing Applications
Wanda Szemplinska-Stupnika (2014)
The behaviour of nonlinear vibrating systems vol. 2
Yu Wang (2017)
A new concept using LSTM Neural Networks for dynamic system identification2017 American Control Conference (ACC)
A. Sagheer, Mostafa Kotb (2019)
Time series forecasting of petroleum production using deep LSTM recurrent networksNeurocomputing, 323
(2016)
DeepLearning
Qingqing Nie, D. Wan, Rui Wang (2021)
CNN-BiLSTM water level prediction method with attention mechanismJournal of Physics: Conference Series, 2078
A. Geens, Y. Rolain (2000)
Noise figure measurements on nonlinear devicesProceedings of the 17th IEEE Instrumentation and Measurement Technology Conference [Cat. No. 00CH37066], 2
N. Andrianov (2018)
A Machine Learning Approach for Virtual Flow Metering and ForecastingArXiv, abs/1802.05698
J. Hernández-Orallo, Peter Flach, C. Ferri (2011)
Proceedings of the 28th International Conference on Machine Learning
S. Hochreiter, J. Schmidhuber (1997)
Long Short-Term MemoryNeural Computation, 9
Wen Yu, Jesus Gonzalez, Xiaoou Li (2021)
Fast training of deep LSTM networks with guaranteed stability for nonlinear system modelingNeurocomputing, 422
Katherine Reichl, D. Inman (2017)
Lumped mass model of a 1D metastructure for vibration suppression with no additional massJournal of Sound and Vibration, 403
(2021)
Nonlinear Mechanics of Complex StructuresAdvanced Structured Materials
S. Kiranyaz, Onur Avcı, Osama Abdeljaber, T. Ince, M. Gabbouj, D. Inman (2019)
1D Convolutional Neural Networks and Applications: A SurveyArXiv, abs/1905.03554
Kai-Chao Miao, Qiang Hua, Huifeng Shi (2021)
Short‐term load forecasting based on CNN‐BiLSTM with Bayesian optimization and attention mechanismConcurrency and Computation: Practice and Experience, 35
L. Dai, XiaojieĀ Wang, Changping Chen (2015)
Accuracy and Reliability of Piecewise-Constant Method in Studying the Responses of Nonlinear Dynamic SystemsJournal of Computational and Nonlinear Dynamics, 10
D. Musielak, Z. Musielak, J. Benner (2005)
Chaos and routes to chaos in coupled Duffing oscillators with multiple degrees of freedomChaos Solitons & Fractals, 24
L. Dai, Guoqing Wang (2008)
Implementation of Periodicity Ratio in Analyzing Nonlinear Dynamic Systems : A Comparison With Lyapunov ExponentJournal of Computational and Nonlinear Dynamics, 3
(2021)
arXiv:2112.13444 2021
L. Dai, R. Jazar (2012)
Nonlinear Approaches in Engineering Applications
The current work proposes a hybrid data‐driven model—Convolutional bidirectional long–short term memory (CNN‐BLSTM) for predicting chaotic behavior of three‐coupled Duffing oscillator nonlinear system, in which the CNN is for efficiently extracting the more robust and informative representations of chaotic sequences while the BLSTM is for holding the long‐term dependencies combining the past and future contexts. Different from traditional analytical and numerical approaches, the proposed prediction model features the benefit of focusing on the measured data solely without extensive professional domain knowledge. Additionally, three more recurrent neural network (RNN) models, including simple RNNs, stack LSTMs, and BLSTM, are built and comparisons of generalization performances to the CNN‐BLSTM are conducted. From the findings so far, the CNN‐BLSTM is able to learn the pattern of chaotic time sequence data with less training time and apply the acquired knowledge to the unseen dataset with lower errors. Moreover, the current work decently demonstrates that the proposed model outperforms other three models in terms of stability at different noise levels from two evaluation criteria. The CNN‐BLSTM provides useful guidance for the consideration of predicting multi‐dimensional nonlinear chaotic behavior.
Advanced Theory and Simulations – Wiley
Published: Aug 1, 2023
Keywords: bidirectional long–short term memory; chaos; Convolutional Neural Network; multi‐dimensional nonlinear system
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.