Key points are not available for this paper at this time.
This article presents an effective approach for acquiring energy consumption data of induction motors (IMs) in the context of Industry 4.0. A shadow model of the IM is developed based on its efficiency, incorporating the double cage model with iron loss resistance. The real-time simulation is employed to compute motor losses using an adaptive neuro-fuzzy inference system (ANFIS) algorithm. The proposed ANFIS MATLAB model is trained using operational data from a 1.5 KW, 400/230V, 50 Hz squirrel cage induction motor (SCIM). The mean of the root mean square error (RMSE) values for training and testing are respectively 1.64E-04 and 0.776075. The validity of the proposed method is established through an offline simulation in MATLAB, utilizing experimental data from the mentioned motor under two different load profiles. The errors in efficiency estimation, compared to the measured efficiency at rated conditions, yield an RMSE of 7.98e-04 and 0.0014, respectively, for linear and nonlinear load profiles. These results demonstrate the feasibility of implementing the proposed model in the industry to monitor the machine's efficiency and losses.
Adamou et al. (Wed,) studied this question.