Practical implementation of a neural network controller in a hard disk drive

Herrmann, Guido; Ge, Shuzhi Sam; Guo, Guoxiao

doi:10.1109/tcst.2004.838567

Cited by 38 publications

(21 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…46th IEEE CDC, New Orleans, USA, Dec. [12][13][14]2007 ThC18.3 To compare the performance of the VCM actuator before and after the NN compensation in frequency domain, swept sinusoidal signals from 10Hz to 200Hz generated by DSA was injected into the closed-loop as reference signals. The frequency responses for the VCM actuator plant before and after compensation, and the sensitivity before and after compensation are plotted in Fig.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…The off-line training may not be adequate, however, as the hysteresis nonlinearity is not only position/velocity dependent, but also time-varying. As an alternative, neural networks (NNs) can be used as the parameterized approximator of the nonlinearity, incorporated by the adaptive control for on-line parameters tuning [11] [12].…”

Section: Introductionmentioning

confidence: 99%

“…in Lemma 1, it follows that[d u − ǫ(Z)]2r T PB ≤ [|d u | + |ǫ(Z)|] ·|2r T PB| ≤ ( µ * · Ŝ ′T µŴ + η * · Ŝ ′T ηŴ + W * · Ŝ ′ µμ + W * · Ŝ ′ ηη + W * 1 + |ǫ(Z)|) ·|2r T PB|46th IEEE CDC, New Orleans, USA, Dec [12][13][14]. 2007 ThC18 3.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Adaptive neural network compensation of pivot nonlinearity in hard disk drives

Fan

Hredzak

et al. 2007

2007 46th IEEE Conference on Decision and Control

View full text Add to dashboard Cite

In this paper we propose an adaptive NN control design to compensate for the pivot nonlinearity. To capture the time-varying uncertainties and nonlinearity, the adaptive tuning scheme is employed for NN weights, receptive center and width. The simulation and experimental results shows the effectiveness of the proposed scheme.Index Terms-Hard disk drive, adaptive neural networks, pivot nonlinearity compensation.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive neural network compensation of pivot nonlinearity in hard disk drives

Fan

Hredzak

et al. 2007

2007 46th IEEE Conference on Decision and Control

View full text Add to dashboard Cite

show abstract

“…However, these parameters are not consistent for different tracks, thus the performance of using feedforward compensation with these models is limited. To address the uncertainties, intelligent algorithms using neural networks (NNs) were derived in [6] [7]. The convergence rate of the estimation of NN weights especially when there exists measurement noise limits its practical application.…”

Section: Introductionmentioning

confidence: 99%

Modeling of nonlinear dynamics at low frequencies in hard disk drive and its adaptive compensation

Zhang

Fan

et al. 2009

2009 IEEE International Conference on Control and Automation

View full text Add to dashboard Cite

In hard disk drive servo system, the rejection of disturbances at low frequencies is degraded due to the nonlinearities of pivot friction and flex-cable bias. In this paper, a novel parametrized dynamic model is proposed with the parameters being functions of position. The proposed model provides good matching in both time domain and frequency domain. Based on this nonlinear parametrized model, a feedforward controller with adaptive gain is designed and implemented. The simulation and experimental results show that the proposed method can improve the servo performance effectively.

show abstract

“…Several representative works [3][4][5][6][7][8][9][10] on this topic are available in the literature. Among these, in [4], the continuous-time sliding mode control (CSMC) law was designed and applied to VCM for disk drives. In [5], an adaptive sliding mode control scheme was also developed for disk drives actuator control.…”

Section: Introductionmentioning

confidence: 99%

Improved Integral Sliding Mode Controller with Phase Lead Peak Filter for Hard Disk Drives

Xie

Wang

et al. 2007

2007 IEEE 22nd International Symposium on Intelligent Control

View full text Add to dashboard Cite

An integral-type sliding mode control scheme is developed that explicitly takes into account mismatched disturbances provided their bounds are known in this study. By using an integral sliding surface, the dynamics of the sliding mode is analytically obtained which does not have any reaching phase by using the integral sliding surface. To reconstruct estimates of the system states for use in a full information sliding mode control law, an asymptotic observer is also employed and the fulfillment of sliding condition, including the case when estimated states are used, is also verified. In addition, the proposed control scheme integrated with a phase leak peak filter (PLPF) is also investigated for better rejection of disturbance of narrow-band type at mid-frequency ranges in hard disk drives (HDDs). Simulation studies on track-following in HDDs are conducted to illustrate the feasibility and effectiveness of the proposed sliding mode control. They also demonstrate that the proposed scheme provides better performance than the conventional sliding mode and PID control methods.

show abstract

Practical implementation of a neural network controller in a hard disk drive

Cited by 38 publications

References 23 publications

Adaptive neural network compensation of pivot nonlinearity in hard disk drives

Adaptive neural network compensation of pivot nonlinearity in hard disk drives

Modeling of nonlinear dynamics at low frequencies in hard disk drive and its adaptive compensation

Improved Integral Sliding Mode Controller with Phase Lead Peak Filter for Hard Disk Drives

Contact Info

Product

Resources

About