A rotary actuator that employs hydraulic oil as the power source has a direct rotary structure. It is an important structure and has been widely utilized in aircrafts and ships because of its advantages, including large torque/quality ratio, simple compact structure, and fast dynamic response. Huge damage may be caused when a rotary actuator breaks down during operation. However, only a few studies have focused on fault detection and performance assessment for rotary actuators. In this study, a method that detects the fault in and assesses the performance of the rotary actuator based on residual analysis is proposed. The data in normal state are utilized to build an observer with two radial basis function (RBF) neural networks. One RBF neural network is employed to estimate the expected output required to generate the residuals. The self-adaptive thresholds are obtained through the other RBF neural network. The residual is then inputted into the self-organizing mapping neural network trained by the residual values in normal state to normalize the performance of the rotary actuator into confidences values between 0 and 1. Finally, the detection and assessment of two typical faults of the rotary actuator are simulated. Results verify the efficiency of the proposed method.
A Novel Positioning Algorithm Based on Self-adaptive Algorithm of RBF Network
