AUTOMATED TUNING OF AN ELECTRONIC-CIRCUIT BOARD USING THE ARTIFICIAL NEURAL-NETWORK APPROACH

Manufacturing of electronic circuits for microwave communication board s often requires tuning of different circuit characteristics by manual adjustment of several trimmer components, including the trimmer's res istance and capacitance. This manual tuning process was automated by a pplying the artificial neural network modeling approach. In the consid ered tuning process, which required manual adjustment of a set of trim mers, multiple specification criteria had to be satisfied by several t rimmer rotations. The tuning process was described in terms of three i ndependent steps: the circuit output measurement, trimmer selection, a nd trimmer rotation. The trimmer selection was performed by a semi-sup ervised neural network, which learned the patterns of circuit characte ristics and the deviations between the ideal and practical outputs. An other network was developed for determination of trimmer rotation rate . The results, based on computer simulation of the tuning process, sho wed that the developed system improved performance of the tuning proce ss, allowing for automation of the microwave circuit board tuning task in a real manufacturing environment.