Improved Sliding Mode Observer with Adaptive Fuzzy Logic Control for Efficient PMSM Sensorless Speed Regulation

Speed control of Permanent Magnet Synchronous Motors (PMSMs) in industrial applications often relies on Hall and encoder sensors. However, these sensors usually increase system maintenance costs, and their performance is susceptible to industrial environmental factors such as electromagnetic interference (EMI) and mechanical vibrations. To overcome these issues, this study proposes an improved Sliding Mode Observer (SMO) with an adaptive fuzzy logic controller to regulate the speed of PMSMs without relying on Hall and encoders. The proposed method adopts a hyperbolic tangent function instead of the conventional signum function. This results in smoother control transitions, which reduce chattering effects and improve noise tolerance. In addition, the adaptive fuzzy logic controller dynamically adjusts the SMO control gain based on feedback from the estimated speed and its error, which improves control efficiency under various operating conditions. In principle, the improved SMO controller uses a hyperbolic tangent function with updated gain in real time to estimate the alpha and beta components of the back‐electromotive voltage. These components are then used to calculate the rotor position and speed. By adjusting the control gain in real time, the proposed method improves the control performance compared to the conventional SMO method. Simulation results with various scenarios have shown improvements in start‐up response, settling time, and overshoot reduction. The PMSM experimental system has further confirmed the effectiveness of the proposed method, which highlights its applicability in practice. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.