A Brain Emotional Learning - Based Speed Control Strategy for DC Motors

Intelligent control models are considerably crucial in optimizing the operation and efficiency of power systems and power electronics. Relatively, to bridge existing gaps in achieving smooth and faster optimal control, this paper presents a new approach of Brain Emotional Learning Based Intelligent Controller (BELBIC) with a Bidirectional Long Short-Term Memory (BiLSTM) model that is applied on speed regulation of a DC motor. The BELBIC module receives real-time feedback from the motor's speed output, it dynamically adjusts to changing conditions, actively controlling the motor's speed. In addition, the BiLSTM model operates by accurately forecasting the future output of the system through stepwise forecasts. After the execution, key performance indicators (KPIs), such as MAE, MSE, RMSE, and ${{R}^2}$ , are calculated to evaluate the accuracy and prediction capacities of the system. As well, comprehensive results, utilizing KPIs to evaluate the developed BELBIC-BiLSTM system's efficiency are taken to account.