Adaptive Neuro-Fuzzy Inference System-Based Grey Time-Varying Sliding Mode Control for Power Conditioning Applications

In this paper, an adaptive neuro-fuzzy inference system-based grey time-varying sliding mode control (TVSMC) is proposed, and applied for power conditioning systems. The proposed methodology combines the merits of TVSMC, grey prediction (GP), and adaptive neuro-fuzzy inference system (ANFIS). Compared with classic sliding mode control (SMC), the TVSMC can shorten the reaching phase and ensure the occurrence of the sliding mode from an arbitrary initial state. However, when the loading is a severe nonlinear condition, the TVSMC may suffer from chattering, and steady-state error problems, thus deteriorating the performance of the PCS. The GP is thus devoted to alleviate the chattering when the system uncertainty bounds are overestimated and to reduce the steady-state error when the system uncertainty bounds are underestimated. Also, the control gains of the TVSMC with GP can optimally be tuned by the use of the ANFIS for achieving more precise tracking. With the proposed methodology, the robustness of the power conditioning system (PCS) can be enhanced expectably, and a high-quality PCS sinusoidal output voltage with low voltage harmonics and fast dynamic response can be obtained even under nonlinear loading. The theoretical analysis, design procedure, and digital signal processing (DSP)-based experimental implementation for PCS are presented to verify the efficacy of the proposed methodology.