In this paper, the authors propose a recognition method of hand written Hangeul. Hangeul characters are basically classified to 6 patterns by the positions of their elements. Using these characteristics of Hangeul, the pattern of the given character is determined by its peripheral distribution and the other features, and the character is resolved into its elements which are the vowels and the consonants. They are recognized by the optimized neural network. To optimize the neural network, we discuss optimization of the neural network parameters, such as the inclination of the sigmoid function, the numbers of the input layer's units and the hidden layer's units. The constructed recognition system is applied to non-learning Hangeul written by some Korean peoples, and recognition rate of 97.6 % is obtained.
Though a pneumatic actuator is widely used in industrial applications, it is not easy to control due to the nonlinearity in the valve, compliance variation and generating force. In this paper, we apply a method of feedback linearization for a pneumatic actuator system to handle the nonlinearity. It is shown that SISO pneumatic systems with a linearizable load and an isothermal pneumatic actuator are linearizable. In addition, linearizing control is reformulated so that existing linear controllers can be used without modification. Experiments with a rubber artificial muscle actuator is carried out and the following results are obtained. (1) It is verified that linearizing control is effective for pneumatic systems. (2) The model used here is appropriate for linearizing control. (3) In the linearizing control, there exists the term of estimated value of acceleration based on the model. It is shown that by replacing the estimated value by measured value, effect of model uncertainty can be reduced.
This paper proposes an iterative design method of robust controllers which achieve robust stability as well as low sensitivity based on the experimental data. In this method we redesign the controller based on the knowledge of the plant modeling error which is obtained from the experiment. The effectiveness of the proposed method is shown by the experiment of positioning of a vibration system.
In this paper, we consider an analysis and design method for the robust controller of magnetic levitation systems with parameter perturbations. First, an expression of the uncertain plant is given by taking account of the physical parameter variations directly. Then, based on this result, an analysis/design method for robust controller is given in the framework of μ, where the unmodeled dynamics and the sensitivity performance are also taken into consideration. Second, the effectiveness of the proposed method is evaluated by experiments.
In this paper, two kinds of the Degree Of Freedom in Constraint State (CSDOF) are defined for motion of an object in contact with an immobile environment, and then application to planning of assembly tasks is discussed. The CSDOF of the first kind is defined as the number of independent directions in which the object can move keeping the current contact conditions of contact state. The CSDOF of the second kind is defined as the number of independent derections in which the object can move freely when it is allowed to break the current contact conditions and to go away from the current contact state. Then we discuss the difficulty of state transition by considering the two kinds of CSDOF as well as the Degree Of Constraint in Constraint State (CSDOC) and give a criterion function for state transitions. Lastly, we show some applications of the two kinds of CSDOF to the planning of contact state transitions in assembly operations.