Propulsion motor model-free adaptive prediction control method of neural network observer

Abstract

The invention discloses a model-free self-adaptive prediction control method for a propulsion motor based on a neural network observer. The model-free self-adaptive prediction control method is used for solving the problems of unmodeled dynamics and load disturbance of a pod propulsion motor of a semi-submerged ship under complex sea conditions. The method comprises the following steps: establishing a pod propulsion motor discrete dynamics model; according to the discrete dynamics model, establishing a dynamic linearization data model and a multi-step prediction equation of the system; estimating a nonlinear disturbance term by using a neural network observer, and feeding back an estimation result to a control law for disturbance compensation; and determining a control scheme according to the propulsion motor model-free adaptive prediction control method based on the neural network observer. The control performance and robustness of the pod propulsion motor control system are effectively improved by introducing the input information at the future moment.

Description

technical field [0001] The invention belongs to the technical field of ship electric propulsion control, and uses a neural network and a model-free self-adaptive prediction method to design a pod propulsion motor speed vector control scheme. Background technique [0002] With the rapid development of society and economy, the problem of energy depletion caused by the rapid consumption of petroleum energy on land has become increasingly serious. In this context, more and more countries and companies are paying attention to the development and utilization of marine resources. In the 1950s and 1960s, the United States first proposed Dynamic Positioning (DP) technology for offshore oil development. The DP system refers to maintaining the fixed position of ships and oil development platforms only by propellers. After more than 60 years of development, the basic principle of the DP system has not undergone major changes, but with the advancement of science and technology, a pod pr...

AI Technical Summary

Problems solved by technology

However, the working environment of the pod propulsion motor is harsh, and it is easily affected by unknown factors such as sea waves and sea wind. The system model established based on mechanism modeling often has problems with unmodeled dynamics and other uncertain factors.

[0004] Therefore, it is very urgent to study a new control method to solve the problems of unmodeled dynamics and poor anti-disturbance ability in the current pod propulsion motor controller design.

Images