A neural network-based direct inverse control for active control of vibrations of mechanical systems

Abreu, G.C.M. De; Teixeira, R.L.; Ribeiro, José Francisco Ferreira

doi:10.1109/sbrn.2000.889722

Cited by 19 publications

(11 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea of using ANNs for nonlinear feedforward control problems was first proposed by K. S. Narendra and K. Parthasarathy [21], and then, the investigations into it by some other people have been reported (see, for example, [7,17,[22][23][24][25]). Generally, multilayer feedforword neural networks adapted using some extensions of the standard gradient descent backpropagation algorithm has received the most attention from the control community as a potential nonlinear filtering tool [6].…”

Section: Ann Applications In Avcmentioning

confidence: 99%

“…The significant idea of [25] to solve this problem is by defining the target as the sum of control signal and tip acceleration (NNI output, which is desired to be zero for vibration suppression). The error is the difference between the In another example, the simplest concept called "Direct Inverse Control" is implemented in an ANN-based AVC [24]. The principle of "Direct Inverse Control" is that if a process can be described by a function dependent on the past states of the system that may be dependent on past inputs and outputs, a network is trained as the inverse of the process since that plant can be approximated by an inverse function.…”

Section: Ann Applications In Avcmentioning

confidence: 99%

“…The inverse model is subsequently applied as the controller for the process by inserting the desired output. [24].…”

Section: Ann Applications In Avcmentioning

confidence: 99%

See 2 more Smart Citations

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

Xia¹

2021

Preprint

View full text Add to dashboard Cite

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.

show abstract

Section: Ann Applications In Avcmentioning

confidence: 99%

Section: Ann Applications In Avcmentioning

confidence: 99%

See 1 more Smart Citation

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

Xia¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition actuator selection, there have been many papers presenting research on control method, such as PID control, adaptive control, and neural network etc. [9][10][11][12] Generally, the fundamental resonance can be actively controlled without reducing the high-frequency performance by using an active control system in combination with a passive isolator. Unfortunately, it's very difficult and expensive to develop this active vibration isolation system for such heavy machine with more than 5 tons weight.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Filtered-X LMS algorithm for active vibration control on micron positioning stage

Liu

Lee

2012

2012 International Conference on Control, Automation and Information Sciences (ICCAIS)

View full text Add to dashboard Cite

The objective of this study is to develop an active vibration control (AVC) system to suppress the relative displacement between lens set and granite platform using a micron positioning stage, installed between lens set and gantry. This control system applies Filtered-X LMS adaptive algorithm as the controller, and uses the vibration signal measured by accelerometer as input signal to generate a control signal that drives piezoelectric actuator to produce anti-force to suppress vibration of the micron positioning stage. The goal of this study is to reduce 50% amplitude of the horizontally relative displacement between the lens set and granite platform under a frequency range of 1 ~ 10Hz. Through the experiments of active control, it was verified that the vibration of stage is effectively decreased to 2 ~ 4μm from 12 ~ 20μm after control under the proposed frequency range.

show abstract

“…In addition to actuator selection, there have been many papers presenting research on control methods such as PID control, adaptive control, and neural networks etc. [9][10][11][12] The purpose of this research is to suppress micro-vibrations from the environment. In general, the sources of vibration can be divided into two categories: vibrations from the environment and vibrations produced inside the system.…”

Section: Introductionmentioning

confidence: 99%

Application of a Proportional Feedback Controller for Active Control of a Vibration Isolator

Liu

2005

Journal of Low Frequency Noise, Vibration and Active Control

View full text Add to dashboard Cite

This paper proposes the application of a proportional controller to active vibration control incorporated with a passive vibration isolator to suppress its resonant oscillation at its natural frequency. Vibration acceleration acquired from an accelerometer is fed to the controller as a feedback signal. The processed signal from the controller is transmitted to the voice coil actuator in order to control the vibration. Firstly, based on the theoretical equations which govern the vibrational system, the physical mechanism of active control in the total system is studied. Then, vibration on a stiff foundation and passive isolator is measured in order to understand the efficiency of the traditional vibration control method. Finally, an experiment on active vibration control is performed to study the suppression efficiency of the oscillation of the passive vibration isolator. The experiment results show that 99% of the vibration energy can be cancelled by active control.

show abstract

A neural network-based direct inverse control for active control of vibrations of mechanical systems

Cited by 19 publications

References 6 publications

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

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

Adaptive Filtered-X LMS algorithm for active vibration control on micron positioning stage

Application of a Proportional Feedback Controller for Active Control of a Vibration Isolator

Contact Info

Product

Resources

About