基于AFSA的高速无人艇操纵模型参数辨识

Parameter Identification of Maneuvering Response Model for High-speed USV Based on AFSA

摘要:

为了对高速无人艇的操纵性能进行预报，提升其操控性能，准确地建立无人艇操纵运动模型十分关键。针对传统模型试验求解模型参数较为复杂的问题，提出一种基于人工鱼群算法(AFSA)的高速无人艇操纵响应模型参数辨识方法。通过差分将操纵响应模型离散化处理，变换构造相应的辨识模型，然后基于 AFSA 对状态向量寻优求解，辨识得到无人艇操纵响应模型参数。仿真实例表明：基于 AFSA 所得到的响应模型具有良好的泛化能力，以及该辨识方法的有效性，能够更好地对高速无人艇进行操纵运动控制及预报。

Abstract:

In order to predict the maneuverability of high-speed USV and improve its control performance，it is of great significance to accurately establish the maneuvering response model for USVs. Aiming at the problem that the model parameter solving in traditional model experiment is complex，an AFSA-based parameter identification method for the control response model of high-speed USVs is proposed. The control response model is discretized by difference，and then transformed into the corresponding identification model. Then based on AFSA，the state vector is optimized and solved，and the parameters of the USV response model are identified. The simulation results show that the identification model based on AFSA has good generalization ability，and this identification method is effective，which can better control and predict the maneuvering motion of high-speed USVs.