Neural Network Predictive Control For Piezoelectric Smart Structures

In recent years, piezoelectric smart structures including active vibration control technique has been a powerful means for suppressing undesired vibration of flexible structures. However, these structures coupling structural and electric fields are complex systems characterized by model uncertainties, distributed sensors and actuators, nonlinearity and parameter variations with time, it is difficult to build the explicit and accurate mathematical model, and the conventional vibration control approaches rely on the mathematical model of structures, whose control results are not satisfactory.Considering this problem, this paper introduces the nonlinear predictive control algorithm based on neural network predictive model into piezoelectric smart structure. Because of the difficulties of building the mathematical model and extracting dynamic data from experiment, the finite element software (ANSYS) is employed to analyze and obtain the dynamic response data of piezoelectric smart structure through modal analysis and transient analysis. Neural network predictive model of structure is built through off-line training on the basis of the data. The nonlinear generalized predictive control based on neural network has a better ability to solve complex nonlinear problem. Then the author introduces the neural network identification toolbox (NNSYSID) and neural network control toolbox (NNCTRL), which are two special toolboxes for designing neural network control system and can save lots of time for designers who can commit themselves to sixty-four-dollar question. At last, the author shows the method through a case. A cantilever beam which surface is boned piezoelectric patches used for sensor and actuator respectively is analyzed by ANSYS and controlled by the neural network predictive control algorithm on the platform of NNSYSID and NNCTRL. This is a simple and effective method for designers to solve the control problem of piezoelectric smart structure.Through researching on active vibration control of piezoelectric smart structure, the thesis completed its nonlinear self-adapted predictive control based on neural network predictive model. Besides, the thesis introduces the NNSYSID and NNCTRL. It is a simple and effective method for designers to solve the control problem of piezoelectric smart structure on the platform of NNSYSID and NNCTRL. So the thesis has an important engineering practical value.