Fuzzy-Control-Aided ZNN for Minimum Energy Consumption Scheme of Redundant Manipulator
提出一种模糊控制辅助的零化神经网络模型，通过动态调整采样间隔，在保证跟踪精度的同时降低冗余机械臂的能耗，适用于机器人控制领域。
Redundant manipulators have shown great potential in the application of robots. These manipulators possess additional degrees of freedom beyond what is essential for completing specific tasks, presenting an opportunity to optimize energy usage. However, the existence of additional degrees of freedom also brings control challenges. Due to the ability to address problems of time-varying tracking, zeroing neural network (ZNN) is gradually widely used in the control of redundant manipulators. Discrete models are often used in engineering, and the sampling gap selected during discretization is an important factor that affects the tracking precision. Large sampling gaps require less computational consumption but yield lower tracking precision, whereas small sampling gaps result in higher precision but at a greater computational cost. In this article, a minimum energy consumption scheme (MECS) for the time-varying tracking control task of redundant manipulators is presented first. By applying the ZNN design formula, the continuous ZNN (CZNN) model is established to solve the MECS. Subsequently, Euler discretization formula is utilized to transform the CZNN model into its discrete form, known as the discrete ZNN (DZNN) model. Then a dual-input–single-output fuzzy control system is designed to obtain suitable sampling gaps. The fuzzy-control-aided ZNN (FCAZNN) model enables redundant manipulators to track desired paths with the expected precision. Finally, a series of experiments are carried out in this article to demonstrate the advantages of FCAZNN model, including both computer simulations and physical experiments.