Meng Zhijun

An active wind gust rejection controller for an autonomous helicopter

This paper proposes a novel wind gust rejection controller for a model helicopter with uncertain parameters. A hybrid of backstepping and active disturbance rejection controller is designed to achieve attitude tracking. The analysis and inclusion of the nature of wind gust disturbances and rotor dynamics yield more practical and reliable disturbance observation. The disturbances are eliminated to the best extent due to real time estimation and compensation, and the robustness against model uncertainties is guaranteed through proper state transformation. The simulation results validate the performance and robustness of proposed controller.

Application of Expert System Fuzzy BP Neural Network in Fault Diagnosis of Piston Engine

Due to the limitation of BP neural network in fault diagnosis, an improved fault diagnosis method based on Expert System, Fuzzy Theory and improved BP neural network is presented in this paper. And then it is applied in the fault diagnosis of one piston engine. Firstly, a fault database of the piston engine is established by using Expert System, Secondly, the fault symptom is pre-processed with Fuzzy Theory to obtain training samples for neural network, in the end, simulations of fault diagnosis based on BP neural network and improved BP neural network are accomplished by employing the MATLAB software. The simulation results indicate that this method maintains fast convergence, high diagnostic accuracy and it can diagnosis engine failure effectively.

Helicopter engine performance prediction based on cascade-forward process neural network

In view of the difficulty of predicting engine performance effectively in traditional methods, a prediction method based on CFPNN (Cascade-Forward Process Neural Network) is proposed. By introducing a set of appropriate orthogonal basis functions into the input space, the input functions and weight functions are expanded. The time aggregation operation of the process neurons is simplified by this way. The RBP (Resilient Back-Propagation) learning algorithm based on orthogonal basis function expansion is proposed. The CFPNN based on RBP learning algorithm is compared with FFPNN (Feed-Forward Process Neural Network) based on RBP learning algorithm and CFPNN based on ABP (Adaptive Back-Propagation) learning algorithm respectively. The results show that the CFPNN based on RBP learning algorithm possesses good convergence and high accuracy. It provides an effective way for helicopter engine performance prediction.

The experimental study of Backstepping Active Disturbance Rejection Controller of helicopter

This paper proposes the experimental study of a novel method of Backstepping Active Disturbance Rejection Controller of helicopter, which estimates and compensates the environmental disturbances and nonlinear aerodynamic forces in real time with little reliance on accurate system model. A reduced-order controller is designed and applied in flight tests. The attitude tracking and disturbance rejection experiment demonstrated its utility in attitude tracking and disturbance rejection.