Yutaka Nakano

Evaluating the quality of pellet component by using image processing technique with neural networks

A new method is proposed to evaluate the quality of pellet component. Unlike other methods which only rely on the binarized image to solve this problem, ours rely on both the binarized image for measuring and other features of the image. In this paper, first of all, a model is constructed. The size of the model depends on the designed requirement of dimension and its allowable tolerance. By using this model, the sizes of the component are inspected roughly. Then, we propose the backpropagation (BP) neural networks for evaluating the ring of central part based on the features of the tested component. Because there are measurement errors such as systematic and random errors, so the dimension of the component has to be measured several times. Finally, the final decision method is proposed. This method can evaluate the quality of pellet component more precisely than the traditional methods.

Measurement of the tribo-charge values on the surface of a spherical toner particle

The present paper describes a new method for calculating the tribo-charge distribution of a spherical toner particle. The forces which act on the particle adhered on the inner surface of the parallel electrodes connected to the power supply are the adhesion, the gravity and the Coulomb forces. By the movement of the toner particle under these conditions, the tribo-charge can be calculated by the following equation:q=(8πσgd/3)/(V1-V2)where V1 V2 d, σ, g and r are the voltage applied across the upper and the lower electrodes in the case that the toner particle put on the lower electrode is lifted toward the upper one, the voltage in the case that the toner particle gets back again to the lower one, the air gap distance between the two electrodes, the density of the toner particle, the acceleration of gravity and the radius of a toner particle, respectively. By using this method, the charge amounts of the toner particle can be easily obtained.