Support vector machine optimization via an improved elephant herding algorithm for motor energy efficiency rating

Accurate evaluation of motor energy efficiency under off-condition operation can provide an important basis for an energy-saving upgrade of the motor and the elimination of backward motors. By considering the power quality, motor characteristics and load characteristics, a motor energy efficiency evaluation system with seven indexes and 10 grades was constructed. An improved elephant herding optimization method combined with a support vector machine rating model is proposed, it achieved an accuracy higher than 98%. Considering the slow convergence speed and low convergence precision of the standard elephant herding optimization (EHO) method, it is easy to fall into the local optimum problem. To improve population initialization, chaotic mapping and adversarial learning were used to achieve EHO with population diversity and global search capability. Group learning and elite retention have been added to improve the local development ability of the algorithm. The improved EHO has been compared with other intelligent optimization algorithms by using 12 benchmark functions, and the results show that the improved algorithm has better optimization performance.