scholarly journals Adaptive Vibration Control of Structure-AMD Coupled System Using Multi-layer Neural Networks

2000 ◽  
Vol 3 ◽  
pp. 427-438 ◽  
Author(s):  
Bin XU ◽  
Zhishen WU ◽  
Koichi YOKOYAMA
Keyword(s):  
Neural Networks ◽  
Vibration Control ◽  
Coupled System ◽  
Adaptive Vibration Control

scholarly journals Adaptive vibration control of the electromagnet-track coupled high frequency resonance for an urban maglev system

2018 ◽  
Vol 4 (2) ◽  
pp. 92-106 ◽  
Author(s):  
Danfeng Zhou ◽  
Peichang Yu ◽  
Jie Li ◽  
Peng Cui ◽  
Mengxiao Song
Keyword(s):  
Vibration Control ◽  
Adaptive Filter ◽  
High Frequency ◽  
Control Algorithm ◽  
Coupled System ◽  
Maglev Train ◽  
Frequency Resonance ◽  
Special Cases ◽  
High Frequency Resonance ◽  
Adaptive Vibration Control

This paper is a study of the electromagnet-track coupled high frequency resonance that frequently occurs in the urban maglev systems, it includes the following points: Aim: The purpose of this study is to investigate the principle underlying the high frequency resonance occurs between the maglev train and the track, and to develop an appropriate vibration control algorithm which can be applied in the levitation controller, such that the resonance can be eliminated when the maglev train travels along the track. Materials and methods of the studies: In this paper, the model of the electromagnet-track coupled system is firstly established, in which some special cases, which correspond to the situations when the screws that fasten the F-rail to the sleepers are fatigue, or the stiffness of the rubber plates beneath the sleepers weaken for temperature reasons, are studied; and the reason that leads to the coupled resonance are explained as well. Secondly, an adaptive vibration control algorithm, which consists of a vibration observer and a tunable adaptive filter, is designed to suppress the high frequency electromagnet-track coupled resonance. Results: Using this algorithm, when the train arrives at the spots where the coupled resonance may occur, the vibration observer will detect the occurring of the vibration and estimates its frequency, and then activate the adaptive filter and tune it to absorb the vibration. Conclusion: The test indicates that this algorithm is capable of tuning itself to handle the unpredictable coupled resonance that occurs along the track, and it is simple and can be easily integrated into the levitation control code in a digital levitation control system.

Modal Filters and Neural Networks for Adaptive Vibration Control

2000 ◽  
Vol 6 (4) ◽  
pp. 631-648 ◽  
Author(s):  
Albert Bosse ◽  
Tae W. Lim ◽  
Stuart Shelley
Keyword(s):  
Neural Networks ◽  
Vibration Control ◽  
Modal Filters ◽  
Adaptive Vibration Control

Searching for new physics: Using explainable AI to understand deep learned parameterizations of turbulent heat fluxes

2021 ◽  
Author(s):  
Andrew Bennett ◽  
Bart Nijssen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Coupled System ◽  
Hydrologic Model ◽  
Heat Fluxes ◽  
Turbulent Heat ◽  
Phase Lag ◽  
Geophysical Research ◽  
Turbulent Heat Fluxes

<p>Machine learning (ML), and particularly deep learning (DL), for geophysical research has shown dramatic successes in recent years. However, these models are primarily geared towards better predictive capabilities, and are generally treated as black box models, limiting researchers’ ability to interpret and understand how these predictions are made. As these models are incorporated into larger models and pushed to be used in more areas it will be important to build methods that allow us to reason about how these models operate. This will have implications for scientific discovery that will ensure that these models are robust and reliable for their respective applications. Recent work in explainable artificial intelligence (XAI) has been used to interpret and explain the behavior of machine learned models.</p><p>Here, we apply new tools from the field of XAI to provide physical interpretations of a system that couples a deep-learning based parameterization for turbulent heat fluxes to a process based hydrologic model. To develop this coupling we have trained a neural network to predict turbulent heat fluxes using FluxNet data from a large number of hydroclimatically diverse sites. This neural network is coupled to the SUMMA hydrologic model, taking imodel derived states as additional inputs to improve predictions. We have shown that this coupled system provides highly accurate simulations of turbulent heat fluxes at 30 minute timesteps, accurately predicts the long-term observed water balance, and reproduces other signatures such as the phase lag with shortwave radiation. Because of these features, it seems this coupled system is learning physically accurate relationships between inputs and outputs. </p><p>We probe the relative importance of which input features are used to make predictions during wet and dry conditions to better understand what the neural network has learned. Further, we conduct controlled experiments to understand how the neural networks are able to learn to regionalize between different hydroclimates. By understanding how these neural networks make their predictions as well as how they learn to make predictions we can gain scientific insights and use them to further improve our models of the Earth system.</p>

Robust adaptive vibration control for a string with time-varying output constraint

2018 ◽  
Vol 28 (17) ◽  
pp. 5213-5231 ◽  
Author(s):  
Wei He ◽  
Zhe Jing ◽  
Xiuyu He ◽  
Jin-Kun Liu ◽  
Changyin Sun
Keyword(s):  
Vibration Control ◽  
Time Varying ◽  
Robust Adaptive ◽  
Adaptive Vibration Control ◽  
Output Constraint

scholarly journals Experimental implementation of artificial neural network-based active vibration control & chatter suppression

2021 ◽  
Author(s):  
Yong Xia
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Control System ◽  
Vibration Control ◽  
Control Strategies ◽  
Active Vibration Control ◽  
Chatter Suppression ◽  
Active Vibration ◽  
Artificial Neural

Vibration control strategies strive to reduce the effect of harmful vibrations such as machining chatter. In general, these strategies are classified as passive or active. While passive vibration control techniques are generally less complex, there is a limit to their effectiveness. Active vibration control strategies, which work by providing an additional energy supply to vibration systems, on the other hand, require more complex algorithms but can be very effective. In this work, a novel artificial neural network-based active vibration control system has been developed. The developed system can detect the sinusoidal vibration component with the highest power and suppress it in one control cycle, and in subsequent cycles, sinusoidal signals with the next highest power will be suppressed. With artificial neural networks trained to cover enough frequency and amplitude ranges, most of the original vibration can be suppressed. The efficiency of the proposed methodology has been verified experimentally in the vibration control of a cantilever beam. Artificial neural networks can be trained automatically for updated time delays in the system when necessary. Experimental results show that the developed active vibration control system is real time, adaptable, robust, effective and easy to be implemented. Finally, an experimental setup of chatter suppression for a lathe has been successfully implemented, and the successful techniques used in the previous artificial neural network-based active vibration control system have been utilized for active chatter suppression in turning.

Energy-Harvesting Adaptive Vibration Damping in High-Speed Train Suspension using Electromagnetic Dampers

2021 ◽  
pp. 2140002
Author(s):  
Qinlin Cai ◽  
Yingyu Hua ◽  
Songye Zhu
Keyword(s):  
Energy Harvesting ◽  
Vibration Control ◽  
Output Power ◽  
High Speed ◽  
Vibration Damping ◽  
Numerical Results ◽  
Dual Function ◽  
High Speed Train ◽  
Adaptive Vibration Control ◽  
Electromagnetic Damper

Electromagnetic damper cum energy harvester (EMDEH) is an emerging dual-function device that enables simultaneous energy harvesting and vibration control. This study presents a novel energy-harvesting adaptive vibration control application of EMDEH on the basis of the past EMDEH development in passive control. The proposed EMDEH comprises an electromagnetic damper connected to a specifically designed energy harvesting circuit (EHC), wherein the EHC is a buck–boost converter with a microcontroller unit (MCU) and a bridge rectifier. The effectiveness of the energy-harvesting adaptive vibration damping is validated numerically through a high-speed train (HST) model running at different speeds. MCU-controlled adaptive duty cycle adjustment in the EHC enables the EMDEHs to adaptively offer the optimal damping coefficients that are highly dependent on train speeds. In the meantime, the harvested power can be stored in rechargeable batteries by the EHC. Numerical results project the average output power ranging from 40.5[Formula: see text]W to 589.8[Formula: see text]W from four EMDEHs at train speed of 100–340[Formula: see text]km/h, with a maximum output power efficiency of approximately 35%. In comparison to energy-harvesting passive vibration control and a pure viscous damper, the proposed energy-harvesting adaptive control strategy can improve vibration reductions by approximately 40% and 27%, respectively, at a speed of 340[Formula: see text]km/h. These numerical results clearly demonstrate the benefit and prospect of the proposed energy-harvesting adaptive vibration control in HST suspensions.

Sign in / Sign up

Export Citation Format

Share Document