Neural network‐based adaptive control of piezoelectric actuators with unknown hysteresis

Xie, Wenfang; Fu, Jun; Yan, Han; Su, Chun‐Yi

doi:10.1002/acs.1042

Cited by 37 publications

(28 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A neural network-based dynamic pre-inversion compensator is designed to cancel out the effect of the hysteresis. The results obtained from the simulation study are described; however, the experimental verification is required [20]. The complicated non-linear dynamics of PEA including hysteresis, creep, drift, and time delay are treated as a black box system by S. Yu et al A neural network is built to compensate these behaviors to improve the beam positioning/tracking stability and accuracy.…”

Section: Background and Related Workmentioning

confidence: 99%

“…The PEA exhibits inherent non-linearities such as creep and hysteresis [19][20][21]26]. The zero-friction piezo drives and flexure guidance allow sub-nanometer resolution and sub-microradian angular resolution.…”

Section: Fsoc Experimental Test-bed Configuration and Control Strategmentioning

confidence: 99%

“…The zero-friction piezo drives and flexure guidance allow sub-nanometer resolution and sub-microradian angular resolution. The hysteresis characteristics and step response of PEAs are generally nonlinear and usually unknown [20,26]. This non-linear behavior limits system performance via undesirable oscillations and instability.…”

Section: Fsoc Experimental Test-bed Configuration and Control Strategmentioning

confidence: 99%

“…The non-linear static input-output mapping of the system is not one-to-one [16]. Therefore, it is difficult to operate at an accurate trajectory using conventional controllers and a feed-forward neural network is put forward to resolve it [19][20][21]. Further, the conventional controllers could not be sufficient and the neural controller can be used for improving non-linear input-output mapping through which the beam wandering is mitigated and is the main contribution in this paper.…”

Section: Fsoc Experimental Test-bed Configuration and Control Strategmentioning

confidence: 99%

“…The complexities of a beam ATP controller design for the beam wandering mitigation process is increased due to inherent non-linearity and hysteresis of opto-electronic components involved in the beam steering process, thereby making the control of a non-linear system non-trivial [19][20][21]. The Artificial Neural Network (ANN) is the most popular intelligent tool especially for non-linear function approximation and control applications due to its high ability of learning from sample data and yielding better results to the new data [20][21][22]. A new design approach is introduced in this paper for the hardware implementation of a neural controller in a field-programmable gate array (FPGA) to operate the beam ATP process at a faster rate and also in parallel.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Intensity feedback-based beam wandering mitigation in free-space optical communication using neural control technique

Raj¹,

Selvi

Durai

et al. 2014

J Wireless Com Network

View full text Add to dashboard Cite

Over the last two decades, free-space optical communication (FSOC) has become more and more interesting as an adjacent and/or alternative to radio frequency (RF) and optical fiber communications. The optical wave propagation in the FSOC channel is severely affected by atmospheric parameters, and it leads to the degradation of the data transmission quality and reliability. Among the various atmospheric effects, the beam wandering is the main cause of major power loss and cannot be solved without the incorporation of the beam centroid stabilization system. Therefore, designing a suitable opto-electronic assembly with a beam wandering mitigation system becomes significant to improve the performance of the FSOC system. A FSOC experimental setup is developed for the link range of 0.5 km in the college campus. A neural controller is designed for beam wandering mitigation. The neural controller processed the beam pointing (beam location) information obtained from an opto-electronic position detector (OPD) and then generated the necessary control outputs to the fast steering mirror (FSM) to steer the beam in the counter-direction to mitigate the beam wander at the receiver station. New design approach and architecture development for the implementation of the designed neural controller in the field-programmable gate array (FPGA) to mitigate the beam wandering are presented. The investigations on the performance of the neural controller in aiming a laser beam to be at a particular point on the detector plane are tested under dynamic disturbances generated at the transmitter in addition to the atmospheric effects through which the maximum correction capability of the developed neural controller is examined. Evidence of the suitability and the effectiveness of the proposed neural controller is evaluated in terms of beam centroid displacement, power spectral density (PSD), radial displacement on a 2D plane, effective scintillation index (ESI), Q-factor, and bit error rate (BER). The beam wandering range of −0.13 to +0.16 mm, maximum of 55 dB disturbance band attenuation with a frequency range of 0 Hz through 2 kHz, ESI of 0 to 0.15, Q-factor of 6, and BER of 6.45 × 10 −9 are achieved due to the incorporation of the developed neural controller in different real-world environmental conditions.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Section: Fsoc Experimental Test-bed Configuration and Control Strategmentioning

confidence: 99%

Section: Fsoc Experimental Test-bed Configuration and Control Strategmentioning

confidence: 99%

Section: Fsoc Experimental Test-bed Configuration and Control Strategmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Intensity feedback-based beam wandering mitigation in free-space optical communication using neural control technique

Raj¹,

Selvi

Durai

et al. 2014

J Wireless Com Network

View full text Add to dashboard Cite

show abstract

Robust adaptive output‐feedback control for a class of nonlinear systems with hysteresis compensation controller

Zhang

Zhi

et al. 2017

Adaptive Control & Signal

View full text Add to dashboard Cite

In this paper, a robust adaptive output-feedback dynamic surface control scheme is proposed for a class of single-input single-output nonlinear systems preceded by unknown hysteresis with the following features: (1) a hysteresis compensator is designed in the control signal to compensate the hysteresis nonlinearities with only the availability of the output of the control system; (2) by estimating the norm of the unknown parameter vector and the maximum value of the hysteresis density function, the number of the estimated parameters is reduced, which implies that the computational burden is greatly reduced; (3) by introducing the initializing technique, the initial conditions of the state observer and adaptive laws of unknown parameters can be properly chosen, and the arbitrarily small  ∞ norm of the tracking error is achieved. It is proved that all the signals in the closed-loop system are ultimately uniformly bounded and can be arbitrarily small. Simulation results show the validity of the proposed scheme.

show abstract

Decentralized robust adaptive neural dynamic surface control for multi‐machine excitation systems with static var compensator

Zhang

Wang

Zhu

et al. 2018

Adaptive Control & Signal

View full text Add to dashboard Cite

Focusing on solving the control problem of the multimachine excitation systems with static var compensator (SVC), this paper proposes a decentralized neural adaptive dynamic surface control (DNADSC) scheme, where the radial basis function neural networks are used to approximate the unknown nonlinear dynamics of the subsystems and compensate the unknown nonlinear interactions. The main advantages of the proposed DNADSC scheme are summarized as follows: (1) the strong nonlinearities and complexities are mitigated when the SVC equipment are introduced to the multimachine excitation systems and the explosion of complexity problem of the backstepping method is overcome by combining the dynamic surface control method with neural networks (NNs) approximators; 2) the tracking error of the power angle can be kept in the prespecified performance curve by introducing the error transformed function; (3) instead of estimating the weighted vector itself, the norm of the weighted vector of the NNs are estimated, leading to the reduction of the computational burden. It is proved that all the signals in the multimachine excitation system with SVC are semiglobally uniformly ultimately bounded. KEYWORDS adaptive control, decentralized control, error transformation function, multimachine excitation systems with SVC 92

show abstract

Neural network‐based adaptive control of piezoelectric actuators with unknown hysteresis

Cited by 37 publications

References 37 publications

Intensity feedback-based beam wandering mitigation in free-space optical communication using neural control technique

Intensity feedback-based beam wandering mitigation in free-space optical communication using neural control technique

Robust adaptive output‐feedback control for a class of nonlinear systems with hysteresis compensation controller

Decentralized robust adaptive neural dynamic surface control for multi‐machine excitation systems with static var compensator

Contact Info

Product

Resources

About