機械学習の枠組みに基づく能動型探索アルゴリズムのサーボパラメータ調整問題への適用性の検討;機械学習の枠組みに基づく能動型探索アルゴリズムのサーボパラメータ調整問題への適用性の検討;Applicability Study of the Active Search Algorithm Based on Machine Learning Scheme in the Case of Servo Tuning Problems

Optimization task of the control parameters of industrial positioning systems is a daily occurrence. It is necessary to explore unknown response landscape of the system by performing plural sampling of “control parameters and output combination” if the request specification is severe. Skilled operators have been conducting such tasks based on their experience and knowledge. The challenge is “The Optimization of Unknown Objective Function”. In their study, the authors have proposed their original optimization algorithm as a solution. This paper reports applicability study of their algorithm. Experimental results discovered that the algorithm found the optimal control parameter in 100 combination data set for seven times trial with some required specifications.