Akademik Veri Yönetim Sistemi
2nd Engineering International Conference on Electrical, Energy, and Artificial Intelligence(EICEEAI) 2023, Az-Zarqa, Ürdün, 27 - 28 Aralık 2023, ss.1-6
Induction machines are widely preferred for uncomplicated structures that have minimal maintenance in plants. In order to achieve efficient control of its operation, it is crucial to possess information about its parameters. For this purpose, neural network algorithms can be employed to estimate parameters. Nevertheless, the majority of studies undertaken for parameter estimation were inadequate in accurately representing the network architectures’ performance or achieving the desired precision. This was mostly owing to the low amount of available data and reliance on data from a single experimental setting. Thus, this study aims to address these weaknesses by evaluating a recurrent neural network with a concise and flexible structure. This evaluation involves using a substantial dataset and optimizing the network parameters to achieve the most efficient network structure. Upon completion of the study, the proposed approach demonstrated promising results with high correlation levels and minimal error rates.