Abstract: An image forming apparatus is disclosed which, by using a neural network to have preliminarily learned input conditions for a number of characteristic originals and having only the coupling coefficient after the learning and the output calculating portion to make calculations when necessary for the controlling in the apparatus itself, is capable of automatically performing an optimum copying control corresponding to various conditions of each of various originals.

Abstract: An image forming apparatus includes a developing unit for toner-developing a latent image formed on a photoreceptor, and a dual-component developer consisting of carrier particles and toner particles is contained in the developing unit. A toner concentration in the developing unit is sensed by a magnetic sensor. An output voltage of the magnetic sensor is applied to a microcomputer through an analog-to-digital converter. The microcomputer sets a toner supply time in accordance with a fuzzy inference based on the output voltage of the magnetic sensor and a change amount of the output voltage of the magnetic sensor. A toner supply motor is driven for the set time. Consequently, the toner supply roller supplies toner particles to the developing unit from a toner box.