In this paper, we propose a design method of LQI servo systems under digital control. There are few studies about digital servo systems that treated the state feedback case. In this paper, we study the output feedback case and give the optimal design method of an observer, as well as the state feedback gains. The LQI servo system obtained by this method is a two-degree-of-freedom optimal control system such that the reference tracking characteristics and disturbance rejection characteristics are both optimized with respect to separate quadratic performance indices. We apply the design method to the positioning control of a pneumatic servo cylinder, and demonstrate the effectiveness of the design method through experiments.
In applying neural networks it is an important but difficult problem to determine the number of parameters in the networks. As the number of parameters increases, overfitting problems may arise, with devastating effects on the generalization performance. In this paper we propose an Unbiasedness Criterion using Distorter (UCD) which is a heuristic model selection criterion, and apply it to determination of the number of hidden units of RBF networks. The new criterion is defined as the difference between outputs of two RBF networks; the one trained to minimize the ordinary training error and the other trained to minimize the error between the training data and output of the network transformed by the distorter. We compare the performance of the proposed criterion with others criteria such as AIC and NIC by applying to the model selection of Neurofuzzy Tomography which is a specific application of RBFN.
A supervisor has a robustness in the sense that it achieves the desirable behavior for more than one discrete event system in general. This robustness is useful when a supervisor controls the system with model uncertainty. This paper studies the robust finite state supervisor in the case that the desirable behavior is specified as a closed language. Given an arbitrary supervisor, we characterize all systems for which the desirable behavior is achieved by the supervisor. By using this characterization, we show that there exists the robust finite state supervisor which maximizes the class of systems for which the supervisor achieves the desirable behavior.
Error back-propagation (BP) is one of the most popular ideas used in learning algorithms for multilayer neural networks. In particular, the on-line BP has been applied to various problems in practice because of its simplicity of implementation. However, an efficient implementation of the on-line BP usually requires an ad hoc rule for determining the learning rate of the algorithm. Recently, we proposed a new learning algorithm called the successive projection method (SPM) that was based on an iteration method for solving a system of nonlinear inequalities. In this paper, we improve the SPM by modifying the sub-problem for each input pattern and the sigmoid output function of the hidden layers. The improved SPM (ISPM) updates the weights associated with the arcs in the network adaptively by solving a quadratic programming sub-problem for each input pattern. Some simulation results on pattern classification problems indicate that the proposed algorithm is more effective and robuster than the standard on-line BP and the original SPM.
This paper proposes a new model-free control input design method for systems with input saturation by using a convex programming technique. This method yields the optimal control input sequence, which achieves approximate trajectory tracking subject to input saturation, from input-output data without using any plant model. Furthermore, we extend the method to the two-degree-of-freedom control case in order to enjoy the merits of feedback control. The effectiveness of the proposed method is demonstrated by numerical examples.