A Neural Network Based Output Control Method for Piezoelectric Ceramic Actuators

Abstract

The invention relates to a neural network-based piezoelectric ceramic driver output control method, belonging to the field of wind tunnel model test vibration suppression, and relates to a neural network-based piezoelectric ceramic driver output control method suitable for wind tunnel active vibration suppression struts. The method first installs the piezoelectric ceramic driver data acquisition hardware system, collects the experimental data of the input voltage and output force of the piezoelectric ceramic driver, establishes the neural network model of the piezoelectric ceramic driver, uses the experimental data as the input and output of the neural network model, and selects Appropriate initial parameters are used to train the neural network model of the system, and finally the trained neural network model is called for application in the project. Compared with the traditional linear control method, this method avoids the nonlinear error on the control model, and makes the control result more accurate and with higher precision. In addition, this method is highly adaptable and can be applied to all systems containing piezoelectric ceramic actuators.

Description

technical field [0001] The invention belongs to the field of vibration suppression for wind tunnel model tests, and relates to a neural network-based piezoelectric ceramic driver output control method suitable for active vibration suppression struts in wind tunnels. Background technique [0002] In wind tunnel tests, the most commonly used support method for the model is the tail support, but the tail support form will lead to low system stiffness, and the natural frequency of the system will be coupled with the pulsating airflow in the wind tunnel, resulting in low-frequency vibration of the system. This will seriously affect the accuracy of the wind tunnel data, and will cause a great safety hazard to the wind tunnel test. Among the vibration suppression methods of the wind tunnel strut system, the most effective and popular method is to use the driver to actively control the vibration suppression. The piezoelectric ceramic driver structurally connects the piezoelectric ce...

AI Technical Summary

Problems solved by technology

The neural network model is used to indirectly realize the control of the output force, which avoids the problem that in the actual system, the force sensor cannot be installed due to the structure being too large, so that the output force value of the piezoelectric ceramic driver cannot be obtained, and at the same time, nonlinear factors such as the hysteresis of the piezoelectric ceramic driver are considered. , which is more accurate and effective than the linear control method

Images