Adaptive control for vibration suppression by using self-organization map

Honda, Shinya; Narita, Yoshihiro; Kida, Naohiro

doi:10.1109/ascc.2015.7244696

Cited by 2 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yang et al performed vibration control of smart structures using multi-neural networks [3]. Honda et al conducted adaptive vibration control using self-organizing maps [4].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Vibration Control of Smart Structure Using Deep Reinforcement Learning

Honda,

Imura,

Sasaki

et al. 2022

EPI-IJE

View full text Add to dashboard Cite

In this research, the authors developed an adaptive control method using deep reinforcement learning which is a kind of machine learning to suppress the vibration of smart structures. This method just requires information about the control response and input, and don’t require numerical models for the controlled object to design the controller. We experimented to verify the effectiveness of this method. In this experiment, a smart structure fabricated by an aluminum plate and a piezoelectric actuator was used as a controlled object. Three kinds of reinforcement learning algorithms are employed, Deep Q Network (DQN), Deep Deterministic Policy Gradient (DDPG), and Twin Delayed DDPG (TD3), and the control performance is compared. As a result, we succeeded in reducing the norm of the frequency response to impulse disturbance by up to about 40 dB compared to the uncontrolled case. This demonstrates the applicability of the control method using deep reinforcement learning to adaptive vibration control.

show abstract

“…Yang et al performed vibration control of smart structures using multi-neural networks [3]. Honda et al conducted adaptive vibration control using self-organizing maps [4].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Vibration Control of Smart Structure Using Deep Reinforcement Learning

Honda,

Imura,

Sasaki

et al. 2022

EPI-IJE

View full text Add to dashboard Cite

show abstract

“…The self-organizing map (SOM) proposed by Kohonen is a highly intelligent information processing method that forms a topologically ordered mapping from the high-dimensional data space to a low-dimensional representation space [1]. It has already found wide applications in such areas as pattern recognition [2]- [4], data mining [5]- [8], automatic control [9]- [10] and failure detection [11]- [12] and so on.…”

Section: Introductionmentioning

confidence: 99%

3D SOM Neighborhood Algorithm

Li¹,

Cheng

Wang

et al. 2016

Proceedings of the 2016 International Conference on Intelligent Control and Computer Application

View full text Add to dashboard Cite

Neighborhood algorithm is an important part of 3D SOM algorithm. We proposed three kinds of neighborhood shape and two kinds of neighborhood decay function for threedimensional self-organizing feature maps (3D SOM) algorithm and applied them to three-dimensional image compression coding. Experimental results show that the 3D orthogonal cross neighborhood shape and exponential function algorithm have better peak signal to noise ratio (PSNR) and subject quality than others.

show abstract

Adaptive control for vibration suppression by using self-organization map

Cited by 2 publications

References 4 publications

Adaptive Vibration Control of Smart Structure Using Deep Reinforcement Learning

Adaptive Vibration Control of Smart Structure Using Deep Reinforcement Learning

3D SOM Neighborhood Algorithm

Contact Info

Product

Resources

About