Search

In this paper, neural networks (NNs) and adaptive robust control design method are integrated to design a performance oriented control law with only output feedback for a class of single-input-single-output nth order nonlinear systems in a normal form. The nonlinearities in the system include repeatable unknown nonlinearities and nonrepeatable unknown nonlinearities such as external disturbances. In addition, unknown nonlinearities can exist in the control input channel as well. A high-gain observer is employed to estimate the states of system. All unknown but repeatable nonlinear functions are approximated by the outputs of multilayer neural networks with the estimated states as inputs to achieve a better model compensation. All NN weights are tuned on-line. In order to avoid possible divergence of on-line tuning, discontinuous projections with fictitious bounds are used in the weight adjusting law to make sure that all the weights are adapted within a prescribed range. Theoretically, the resulting controller achieves a guaranteed output tracking transient performance and a guaranteed final tracking accuracy in general. Certain robust control terms is then constructed to effectively attenuate various model uncertainties and estimate errors. Furthermore, if all the states are available and the unknown nonlinear functions are in the functional ranges of the neural networks, an asymptotic output tracking is also achieved to retain the perfect learning capability of NNs in the ideal situation provided that the ideal NN weights fall within the prescribed range. The output feedback neural network adaptive robust control is then applied to the control of a linear motor drive system. Experiments are carried out to show the effectiveness of the proposed algorithm and the excellent output tracking performance.

In this paper, the recently proposed neural network adaptive robust control (NNARC) design axe generalized to synthesize performance oriented control laws for a class of nonlinear systems transformable to the semi-strict feedback forms through the incorporation of backstepping design techniques. All unknown but repeatable nonlinearities in system are approximated by outputs of multi-layer neural networks to achieve a better model compensation and an improved performance. Through the use of discontinuous projections with fictitious bounds, a controlled on-line training of all NN weights is achieved. Robust control terms can then be constructed to attenuate various model uncertainties effectively for a guaranteed output tracking transient performance and a guaranteed final tracking accuracy.

In this paper, neural networks (NNs) and adaptive robust control (ARC) design philosophy are integrated to design performance-oriented control laws for a class of single-input–single-output (SISO) nth-order non- linear systems. Both repeatable (or state dependent) unknown non-linearities and non-repeatable unknown non-linearities such as external disturbances are considered. In addition, unknown non-linearities can exist in the control input channel as well. All unknown but repeatable non-linear functions are approximated by outputs of multi-layer neural networks to achieve a better model compensation for an improved performance. All NN weights are tuned on-line with no prior training needed. In order to avoid the possible divergence of the on-line tuning of neural network, discontinuous projection method with fictitious bounds is used in the NN weight adjusting laws to make sure that all NN weights are tuned within a prescribed range. By doing so, even in the presence of approximation error and non-repeatable non-linearities such as disturbances, a controlled learning is achieved and the possible destabilizing effect of on-line tuning of NN weights is avoided. Certain robust control terms are constructed to attenuate various model uncertainties effectively for a guaranteed output tracking transient performance and a guaranteed final tracking accuracy in general. In addition, if the unknown repeatable model uncertainties are in the functional range of the neural networks and the ideal weights fall within the prescribed range, asymptotic output tracking is also achieved to retain the perfect learning capability of neural networks in the ideal situation. The proposed neural network adaptive control (NNARC) strategy is then applied to the precision motion control of a linear motor drive system to help to realize the high-performance potential of such a drive technology. NN is employed to compensate for the effects of the lumped unknown non-linearities due to the position dependent friction and electro-magnetic ripple forces. Comparative experiments verify the high-performance nature of the proposed NNARC. With an encoder resolution of 1 µm, for a low-speed back-and-forth movement, the position tracking error is kept within ±2 µm during the most execution time while the maximum tracking error during the entire run is kept within ±5.6 µm. Copyright © 2001 John Wiley & Sons, Ltd.

In this paper, an indirect neural network adaptive robust control (INNARC) scheme is developed for the precision motion control of linear motor drive systems. The proposed INNARC achieves not only good output tracking performance but also excellent identifications of unknown nonlinear forces in system for secondary purposes such as prognostics and machine health monitoring. Such dual objectives are accomplished through the complete separation of unknown nonlinearity estimation via neural networks and the design of baseline adaptive robust control (ARC) law for output tracking performance. Specifically, recurrent neural network (NN) structure with NN weights tuned on-line is employed to approximate various unknown nonlinear forces of the system having unknown forms to adapt to various operating conditions. The design is actual system dynamics based, which makes the resulting on-line weight tuning law much more robust and accurate than those in the tracking error dynamics based direct NNARC designs in implementation. With a controlled learning process achieved through projection type weights adaptation laws, certain robust control terms are constructed to attenuate the effect of possibly large transient modelling error for a theoretically guaranteed robust output tracking performance in general. Experimental results are obtained to verify the effectiveness of the proposed INNARC strategy. For example, for a typical point-to-point movement, with a measurement resolution level of ±1μm, the output tracking error during the entire execution period is within ±5μm and mainly stays within ±2μm showing excellent output tracking performance. At the same time, the outputs of NNs approximate the unknown forces very well allowing the estimates to be used for secondary purposes such as prognostics.Copyright © 2002 by ASME