33,492 Hits in 5.8 sec

Unsteady aerodynamic identification based on recurrent neural networks

Jinglong Han, Bo Zhang, Tuanyuan Zhang, Ruiqun Ma
2020 Journal of Vibroengineering  
Finally, the aerodynamic parameters of a group of composite sinusoidal motion signals different from the training signals are predicted by the trained neural networks model and compared with the CFD results  ...  A group of sinusoidal chirp signals with variable amplitude and frequency are adopted as the excitation signals, and the obtained data are used to train the recurrent neural networks, and the ROM of the  ...  Acknowledgements This work was supported by National Natural Science Foundation of China (Grant No. 11472133).  ... 
doi:10.21595/jve.2020.21612 fatcat:gxvlaexzhvdihp357bqe5ww5yi

Behavioural pattern identification and prediction in intelligent environments

Sawsan Mahmoud, Ahmad Lotfi, Caroline Langensiepen
2013 Applied Soft Computing  
To build the prediction model, different dynamic recurrent neural networks are investigated.  ...  Recurrent neural networks have shown a great ability in finding the temporal relationships of input patterns.  ...  Much research has used ANNs in modelling and prediction of time series data. Most of the reported research has focused on using feed forward neural networks [20] [21] .  ... 
doi:10.1016/j.asoc.2012.12.012 fatcat:c6lk7wyauvarxn6br7n7xi75ju

Quantitative object motion prediction by an ART2 and Madaline combined neural network: Concepts and experiments

Qiuming Zhu, Ahmed Y. Tawfik
1995 Engineering applications of artificial intelligence  
An ART2 and a Madaline combined neural network is applied to predicting object motions in dynamic environments.  ...  The identified patterns are directed to the Madaline network to generate a quantitative prediction of the future motion states.  ...  Elsner and the others (4, 5, 6] have studied the use of artificial neural networks to predict time series, a problem very close to the motion prediction.  ... 
doi:10.1016/0952-1976(95)00034-x fatcat:zvj4ie7pojghpnx35bcizoeqt4

Magnetic Angular Rate and Gravity Sensor Based Supervised Learning for Positioning Tasks

Balázs Nagy, János Botzheim, Péter Korondi
2019 Sensors  
During the learning phase, the position estimated by sensor fusion is compared with position data of a motion capture system.  ...  These classical methods can be used for disturbance and noise reduction and extracting hidden information from it as well.  ...  Different neural network layer types are capable of filtering or modelling time series data [20] .  ... 
doi:10.3390/s19245364 pmid:31817428 fatcat:j535dsfuurelxk3c5gfjkzzhba

Real-Time Voluntary Motion Prediction and Parkinson's Tremor Reduction using Deep Neural Networks

Anas Ibrahim, Yue Zhou, Mary E. Jenkins, Ana Luisa Trejos, Michael D. Naish
2021 IEEE transactions on neural systems and rehabilitation engineering  
To address these issues, this work proposes a deep neural network model that learns the correlations and nonlinearities of tremor and voluntary motion, and is capable of multi-step prediction with minimal  ...  The average future voluntary motion prediction percentage accuracy with 10, 20, 50, and 100 steps ahead was 97.0%, 94.0%, 91.6%, and 89.9%, respectively, with prediction time as low as 1.5 ms for 100 steps  ...  Acknowledgment The authors would like to acknowledge José Guillermo Collí Alfaro who helped support this work, as well as all of the people who participated in the trials.  ... 
doi:10.1109/tnsre.2021.3097007 fatcat:qli5p64xznbehn52omzofki3iu

Prediction of Above-elbow Motions in Amputees, based on Electromyographic(EMG) Signals, Using Nonlinear Autoregressive Exogenous (NARX) Model

Ali Akbar Akbari, Mahdi Talasaz
2014 Iranian Journal of Medical Physics  
Recurrent neural network (RNN) models are not only applicable for the prediction of time series, but are also commonly used for the control of dynamical systems.  ...  Results Performance of NARX model is verified for several chaotic time series, which are applied as input for the neural network.  ...  Acknowledgment The authors would like to express their sincere gratitude to Dr Hosseini, physiotherapist at Mashhad Ghaem Hospital, for his suggestions about arm motions and Dr H.R.  ... 
doi:10.22038/ijmp.2014.3095 doaj:c97fe77857624d0ba9788f09cb709295 fatcat:tksqtklgerephes7gmdhnyalfm

Research on Ship Motion Prediction Algorithm Based on Dual-pass Long Short-Term Memory Neural Network

Xiong Hu, Boyi Zhang, Gang Tang
2021 IEEE Access  
The simulation of ship heave motion was carried out on the ship motion simulation platform, and the real-time datas which are measured by the INS are inputted to the trained dual-pass LSTM netural network  ...  Compared with conventional LSTM networks, the dual-pass LSTM network is more targeted and has better adaptability in the field of ship-motion prediction, and this network restores the motion prediction  ...  In order to verify the prediction effect of LSTM neural network on absolute sensor data and relative sensor data, the ship motion simulation platform is used to simulate the ship deck motion, the absolute  ... 
doi:10.1109/access.2021.3055253 fatcat:3nuscmei7veybcxvmqxjd7fgue

Application of time-delay neural and recurrent neural networks for the identification of a hingeless helicopter blade flapping and torsion motions

F. D. Marques, L. de F. Rodrigues de Souza, D. C. Rebolho, A. S. Caporali, E. M. Belo, R. L. Ortolan
2005 Journal of the Brazilian Society of Mechanical Sciences and Engineering  
A time delay neural networks (TDNN) for response prediction and a typical recurrent neural networks (RNN) are used for the identification.  ...  An analysis in frequency of the signals from simulated and the emulated models are presented.  ...  Acknowledgements The authors wish to acknowledge the financial support of the Brazilian Research Agencies FAPESP, CNPq and CAPES, during the tenure of this research work.  ... 
doi:10.1590/s1678-58782005000200001 fatcat:pxxb6nalzvhr7pmnb4gefhtpnu

Neural Network Approach for Nonlinear Aeroelastic Analysis

Ovidiu Voitcu, Yau Shu Wong
2003 Journal of Guidance Control and Dynamics  
Time Series Prediction by Using a Connectionist Network by Parallel Neural Networks.” /ntc ent Data Ana Vol. 5, Ne with Internal Delay Lines.”  ...  The continuous line represents the simulated pitch motion, and the dashed line represents the neural network prediction.  ... 
doi:10.2514/2.5019 fatcat:g3hceypwhfbk7flflcrhrp3psi

Time-Continuous Energy-Conservation Neural Network for Structural Dynamics Analysis [article]

Yuan Feng, Hexiang Wang, Han Yang, Fangbo Wang
2020 arXiv   pre-print
The proposed model uses the system energy as the last layer of the neural network and leverages the underlying automatic differentiation graph to incorporate the system energy naturally, which ultimately  ...  Although the basic neural network provides an alternative approach for structural dynamics analysis, the lack of physics law inside the neural network limits the model accuracy and fidelity.  ...  Acknowledgments The earthquake records used in this paper are from the PEER NGA online ground motion database.  ... 
arXiv:2012.14334v1 fatcat:wvv67zbn7babbmyyxedssxcieu

Volterra Kernels Assessment via Time-Delay Neural Networks for Nonlinear Unsteady Aerodynamic Loading Identification

Natália C. G. de Paula, Flávio D. Marques, Walter A. Silva
2019 AIAA Journal  
A generic expression is derived for the kernel function of p th -order from the internal parameters of a time-delay neural network.  ...  All aerodynamic data used for the construction of the reduced-order models are obtained from computational fluid dynamics (CFD) simulations of the NACA 0012 airfoil using the Euler equations.  ...  Marques acknowledge the financial support of the National Council for Scientific and Technological Development (CNPq) under grant numbers 131493/2016-7 and 307658/2016-3, and the São Paulo Research Foundation  ... 
doi:10.2514/1.j057229 pmid:31534261 pmcid:PMC6750029 fatcat:uj4edpj7cjb67dxnnch2hka6e4

A Novel Adaptive Joint Time Frequency Algorithm by the Neural Network for the ISAR Rotational Compensation

Zisheng Wang, Wei Yang, Zhuming Chen, Zhiqin Zhao, Haoquan Hu, Conghui Qi
2018 Remote Sensing  
Prediction results of the ANN estimator is used to directly compensate distorted ISAR images.  ...  In this paper, a coefficient estimator based on the artificial neural network (ANN) is firstly developed to solve the time-consuming rotational motion compensation (RMC) polynomial phase coefficient estimation  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs10020334 fatcat:at7j6qfrwvgrzcdjcgos43h3n4

Recurrent-type Neural Networks for Real-time Short-term Prediction of Ship Motions in High Sea State [article]

Danny D'Agostino, Andrea Serani, Frederick Stern, Matteo Diez
2021 arXiv   pre-print
The prediction capability of recurrent-type neural networks is investigated for real-time short-term prediction (nowcasting) of ship motions in high sea state.  ...  Time series of incident wave, ship motions, rudder angle, as well as immersion probes, are used as variables for a nowcasting problem. The objective is to obtain about 20 s ahead prediction.  ...  Specifically, recurrent neural network, long-short term memory, and gated recurrent units have been assessed and compared for real-time short-term prediction of wave elevation, ship motions, rudder angle  ... 
arXiv:2105.13102v1 fatcat:ibtwczugknbsbno4jbwlwe3pg4


D D'Agostino, A Serani, F Stern, M Diez
2022 The 9th Conference on Computational Methods in Marine Engineering (Marine 2021)  
The prediction capability of recurrent-type neural networks is investigated for realtime short-term prediction (nowcasting) of ship motions in high sea state.  ...  Time series of incident wave, ship motions, rudder angle, as well as immersion probes, are used as variables for a nowcasting problem. The objective is to obtain about 20 s ahead prediction.  ...  Specifically, recurrent neural network, longshort term memory, and gated recurrent units have been assessed and compared for real-time short-term prediction of wave elevation, ship motions, rudder angle  ... 
doi:10.2218/marine2021.6851 fatcat:dizklgryuzb7db4rpqmdph55zy

A Deep Learning Approach to Detect and Isolate Thruster Failures for Dynamically Positioned Vessels Using Motion Data

Peihua Han, Guoyuan Li, Robert Skulstad, Stian Skjong, Houxiang Zhang
2020 IEEE Transactions on Instrumentation and Measurement  
A convolutional neural network (CNN) is introduced to learn the mapping from the logged motion sequence to the status of the thruster.  ...  In this paper, thruster failure detection and isolation are considered as a time series classification problem.  ...  motion data is used in neural network for thruster FDI.  ... 
doi:10.1109/tim.2020.3016413 fatcat:bpyspynb5zbazlo72ngdomtygq
« Previous Showing results 1 — 15 out of 33,492 results