Adaptive Control Using Neural Networks

In direct inverse control, (Figure 12.2), the neural network is used to compute an inverse model of the system to be controlled ]Levin et al., 1991 Nordgren and Meckl, 1993]. In classical linear control techniques, one would find a linear model of the system then analytically compute the inverse model. Using neural networks, the network is trained to perform the inverse model calculations, that is, to map system outputs to system inputs. Biomedical applications of this type of approach include the control of arm movements using electrical stimulation [Lan et al., 1994] and the adaptive control of arterial blood pressure [Chen et al, 1997]. 

Narendra, K.S. 1992. Adaptive control of dynamical systems using neural networks. In Handbook of Intelligent Control Neural, Fuzzy and Adaptive Approaches. D.A. White and D. A. Sofge, Eds. pp. 141-184. Van Nostrand Reinhold, New York. 

Rao, V. Damle, R. Tebbe, C. Kern, F. The Adaptive Control of Smart Structures using Neural Networks. Smart Materials and Structures, No. 3 (1994), pp. 354-366... 

Chen, F. Khalil, H.K. Adaptive Control of Nonlinear Systems using Neural Networks - A Dead-Zone Approach. Proc. Amer. Control Conf (1990), pp. 667-... 

A. Karakasoglu, and M.K. Sundareshan, Identification and decentralized adaptive control using dynamical neural networks with application to robotic manipulators, IEEE Trans, on neural networks, Vol. 4, No. 6, (1993), pp. 919-930. 

The classical adaptive control scheme is shown in Figure 2.58. Its goal is to use online identification through artificial intelligence (Al), neural networks, and fuzzy logic to adapt the model to the actual process. Al and model predictive control (MPC) can tolerate inaccuracy and uncertainty in the model, and online training can continuously improve the model. 

Chapter 12 introduces the use of neural network techniques and their application in modeling physiological control systems. As their name imphes, neural networks are computational algorithms based upon the computational structure of the nervous system, and are characterized as distributed processing and adaptive. Neural networks have been used to describe the control of arm movements with electrical stimulation and the adaptive control of arterial blood pressure. 

Neural networks have also been used in model reference adaptive control (MRAC) structures (Figure 12.4) [Naranedra and Parthasarathy, 1990 Narendra, 1992]. This approach builds upon established techniques for adaptive linear control and incorporates neural networks to address the problem of controlling nonlinear systems. The MRAC approach is directed at adapting the controlled system such... 

A biomedical control system that utilizes a neurophysiologically-based approach has been developed for use in Functional Neuromuscular Stimulation (FNS) systems [Abbas, 1995 Abbas and Chizeck, 1995). FNS is a rehabilitation engineering technique that uses computer-controlled electrical stimuli to activate paralyzed muscle. The task of a control system is to determine appropriate stimulation levels to generate a given movement or posture. The neural network control system utilizes a block diagram structure that is based on hierarchical models of the locomotor control system. It also utilizes a heterogenous network of neurons, some of which are capable of endogenous oscillation. This network has been shown to provide rapid adaptation of the control system parameters [Abbas and Chizeck, 1995 Abbas and Triolo, 1997] and has been shown to exhibit modulation of reflex responses [Abbas, 1995]. 

Having successfully implemented conventional MRAC techniques, the next logical step was to try to incorporate the MRAC techniques into a neural network-based adaptive control system. The ability of multilayered neural networks to approximate linear as well as nonlinear functions is well documented and has foimd extensive application in the area of system identification and adaptive control. The noise-rejection properties of neural networks makes them particularly useful in smart structure applications. Adaptive control schemes require only limited a priori knowledge about the system to be controlled. The methodology also involves identification of the plant model, followed by adaptation of the controller parameters based on a continuously updated plant model. These properties of adaptive control methods makes neural networks ideally suited for both identification and control aspects [7-11]. 

After successful implementation of conventional model-reference adaptive controllers on smart structures, the next logical step was to investigate the possibility of using a neural network for adaptive control implementations. The linear and nonlinear mapping properties of neural networks have been extensively utilized in the design of multilayered feed-forward neural networks for the implementation of adaptive control algorithms [10]. 

A schematic diagram of the neural network-based adaptive control technique is shown in Fig. 4.9. A neural network identification model is trained using a static backpropagation algorithm to generate p(fc + 1), given past values of y and u. The identification error is then used to update the weights of the neural identification model. The control error is used to update the... 

Various neural network-based adaptive control techniques were discussed in this study. A major problem in implementing neural network-based MRACs is the translation of the output error between the plant and the reference model so as to train the neural controller. A technique called iterative inversion, which inverts the neural identification model of the plant for calculating neural controller gains, has been used. Due to the real-time computer hardware limitations, the performance of neural network-based adaptive control systems is verified using simulation studies only. These results show that neural-network based MRACs can be designed and implemented on smart structures. 

---