Abstract Shaft resolver is widely used in many industrial applications, such as robotics and machine automation applications. Because the performance of the system depends on measurement accuracy, in order to… Click to show full abstract
Abstract Shaft resolver is widely used in many industrial applications, such as robotics and machine automation applications. Because the performance of the system depends on measurement accuracy, in order to perform an accurate position control, the absolute position data measured by the shaft resolver must be nearly as error-free as possible. In this study, an Artificial Neural Network (ANN)-based measurement method was proposed to reduce the errors of the shaft position calculated by using the high-frequency signals. 3-inputs, 10-neurons in hidden layer, and 2-outputs were taken for developed ANN. The proposed method was prepared to operate in a Field Programmable Gate Array (FPGA). Simulation with FPGA hardware was performed in MATLAB/Simulink environment by using FPGA-in-the loop feature. The proposed method was compared with conventional methods. It was seen that the error rate of the proposed method was very low compared to the other methods.
               
Click one of the above tabs to view related content.