Estimation of the Double-Cage Model for Three-Phase Induction Machines Using Decision Tree-Based Algorithms

Abstract

This article presents a novel methodology for estimating the double-cage model (DCM) for three-phase induction machines (TIMs) using decision tree-based algorithms. Validated on a diverse dataset of 860 machines spanning a power range from 0.12 to 370 kW, the proposed method stands out by requiring fewer input parameters than traditional techniques like the modified Newton method. Moreover, the proposed approach remains effective even when the input data exhibits statistical deviations, a common challenge in practical scenarios. The main contributions of this work are the reduction of the number of parameters necessary for the estimation of the DCM equivalent circuit and employing three distinct decision tree-based algorithms, whose effectiveness was confirmed through simulations and experimental tests, thereby providing an accurate representation of the dynamics of real TIMs. The results indicate that by using only basic and readily available data from machine nameplates, such as nominal current, power, speed, voltage, and torque, the proposed methodology provides a reliable and efficient framework for incorporating the real dynamics of TIMs into computational models.