Online Learning Control of Hydraulic Excavators Based on Echo-State Networks
Note to Practitioners-Motivated by the fact that obtaining useful mathematical models of hydraulic excavators may be impractical or too costly, this paper proposes an online learning control technique for the position control of hydraulic excavators. The proposed control technique uses remote control valve (RCV) signals and measurements of the joint angles to learn the dynamics of the excavator in an online manner, and the RCV inputs required to track the desired trajectory are generated simultaneously. As a result of online learning, the controller compensates for the changes in the plant dynamics over time, caused by factors, such as fluid temperature change or component wear. In this paper, we have implemented and validated the proposed controller on a 21-ton class hydraulic excavator. The proposed online learning control framework can also be applied to a wide range of control applications, where a mathematical model of the plant is absent or impractical to obtain.
원문복사신청을 하시면, 일부 해외 인쇄학술지의 경우 외국학술지지원센터(FRIC)에서
무료 원문복사 서비스를 제공합니다.
NDSL에서는 해당 원문을 복사서비스하고 있습니다. 위의 원문복사신청 또는 장바구니 담기를 통하여 원문복사서비스 이용이 가능합니다.
- 이 논문과 함께 출판된 논문 + 더보기