ANFIS Supervised PID Controlled SAPF for Harmonic Current Compensation at Nonlinear Loads

Abstract

ABSTRACT The smart devices comprise extensive embedding of small-size AC power-driven power electronics components. This improves the smart automation in the majority of applications in the industry and home system. But, the nonlinear characteristics of such component introduces several higher-order harmonics and generates possible deviation in performance measures. The long-term persistence of harmonic distortions in the current distribution may result in system failure and depreciation in system efficiency. This paper presents a soft computing technique for reactive power compensation of harmonic current using adaptive neural fuzzy interface system (ANFIS). The smart ANFIS supervises the PID controller for adequate gate signaling to shunt active power filter (SAPF) by hysteresis current control. The neural network is trained by adaptive data set of error and deviation in error with respect to hysteresis current control. The nonlinear load model is subjected to transformer-less SAPF to avoid the presence of insertion losses and improves the system compatibility. The proposed system reduces the harmonic distortion from 92.23 to 0.49% in the nonlinear power converter model with improved 0.99 power factor. Additionally, the proposed system is absolutely feasible and novel for real-time application in smart devices with adequate transient and regression response. The proposed system is realized for individual effects of PID, ANN and ANFIS to justify the candidature of the soft computing technique in real-time applications as per IEEE 519 standard.