Online Learning Control of Hydraulic Excavators Based on Echo-State Networks

In some of recent advances in automation of construction equipment, much research has been conducted on the control of hydraulic excavators in both industry and academia for the benefit of safety and efficiency. However, most relevant works have employed model-based control approaches that require a mathematical representation of the target plant. For hydraulic excavators, obtaining a useful dynamic model for control can be challenging due to the nonlinearity of the hydraulic servo system. With this in mind, this paper investigates the feasibility of an online learning control framework based on echo-state networks (ESNs) to the position control of hydraulic excavators. While ESNs are a class of recurrent neural networks, the training of ESNs corresponds to solving a linear regression problem, thus making it suitable for online implementation. By exploiting the dynamic properties of ESNs, the deployed control framework uses the input and output signals of the plant to learn an inverse model, which is then used to simultaneously generate control inputs to track the desired trajectory. Experiments conducted on a 21-ton class hydraulic excavator show the promising results in that accurate tracking is achieved even in the absence of a dynamic model.

[1]  Nariman Sepehri,et al.  On quantitative feedback design for robust position control of hydraulic actuators , 2010 .

[2]  Shuzhi Sam Ge,et al.  Adaptive tracking control of uncertain MIMO nonlinear systems with input constraints , 2011, Autom..

[3]  Frank L. Lewis,et al.  Neural network compensation control for mechanical systems with disturbances , 2009, Autom..

[4]  Benjamin Schrauwen,et al.  The spectral radius remains a valid indicator of the Echo state property for large reservoirs , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[5]  Fei-Yue Wang,et al.  Agent-based control for fuzzy behavior programming in robotic excavation , 2004, IEEE Transactions on Fuzzy Systems.

[6]  Johan A. K. Suykens,et al.  NLq theory: checking and imposing stability of recurrent neural networks for nonlinear modeling , 1997, IEEE Trans. Signal Process..

[7]  Gregory L. Plett,et al.  Adaptive inverse control of linear and nonlinear systems using dynamic neural networks , 2003, IEEE Trans. Neural Networks.

[8]  Shuzhi Sam Ge,et al.  Adaptive Neural Network Tracking Control of MIMO Nonlinear Systems With Unknown Dead Zones and Control Directions , 2009, IEEE Transactions on Neural Networks.

[9]  Jing Na,et al.  Adaptive neural dynamic surface control for servo systems with unknown dead-zone , 2011 .

[10]  L. F. Abbott,et al.  Generating Coherent Patterns of Activity from Chaotic Neural Networks , 2009, Neuron.

[11]  Clarence W. de Silva,et al.  Tracking control of an electrohydraulic manipulator in the presence of friction , 1998, IEEE Trans. Control. Syst. Technol..

[12]  Stefan J. Kiebel,et al.  Re-visiting the echo state property , 2012, Neural Networks.

[13]  Karsten Berns,et al.  Simulation and control of an autonomous bucket excavator for landscaping tasks , 2010, 2010 IEEE International Conference on Robotics and Automation.

[14]  Frank L. Lewis,et al.  2009 Special Issue: Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems , 2009 .

[15]  Kyoung Kwan Ahn,et al.  Self-tuning of quantitative feedback theory for force control of an electro-hydraulic test machine , 2009 .

[16]  Pyung Hun Chang,et al.  A straight-line motion tracking control of hydraulic excavator system , 2002 .

[17]  Cheng Guan,et al.  Adaptive sliding mode control of electro-hydraulic system with nonlinear unknown parameters , 2008 .

[18]  Shaocheng Tong,et al.  Adaptive NN Tracking Control of Uncertain Nonlinear Discrete-Time Systems With Nonaffine Dead-Zone Input , 2015, IEEE Transactions on Cybernetics.

[19]  Kazuo Fujishima,et al.  Digging control system for hydraulic excavator , 2001 .

[20]  Jeongju Choi.  Tracking Control of Hydraulic Excavator Using Time Varying Sliding Mode Controller with Fuzzy System , 2012 .

[21]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[22]  Juhng-Perng Su,et al.  Sliding mode control with varying boundary layers for an electro-hydraulic position servo system , 2005 .

[23]  George T.-C. Chiu,et al.  Adaptive robust motion control of single-rod hydraulic actuators: Theory and experiments , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[24]  C. Chung,et al.  Output feedback nonlinear control for electro-hydraulic systems , 2012 .

[25]  Benjamin Schrauwen,et al.  Feedback Control by Online Learning an Inverse Model , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[26]  Hugh Durrant-Whyte,et al.  Impedance control of a hydraulically actuated robotic excavator , 2000 .

[27]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[28]  Pyung Hun Chang,et al.  Control of a heavy-duty robotic excavator using time delay control with integral sliding surface , 2002 .

[29]  Chih-Lyang Hwang,et al.  Neural-network-based variable structure control of electrohydraulic servosystems subject to huge uncertainties without persistent excitation , 1999 .

[30]  Joshua A. Marshall,et al.  Toward Autonomous Excavation of Fragmented Rock: Full-Scale Experiments , 2008, IEEE Transactions on Automation Science and Engineering.

[31]  Vladimir B. Bajic,et al.  New model and sliding mode control of hydraulic elevator velocity tracking system , 2002, Simul. Pract. Theory.

[32]  Young-Bum Kim,et al.  Utilizing online learning based on echo-state networks for the control of a hydraulic excavator , 2014 .

[33]  Suwat Kuntanapreeda,et al.  Observer-based backstepping force control of an electrohydraulic actuator , 2009 .

[34]  Frank L. Lewis,et al.  Disturbance compensation for servo-control applications using a discrete adaptive neural network feedforward method , 2007, 2007 46th IEEE Conference on Decision and Control.

[35]  Fernando José Von Zuben,et al.  An extended echo state network using Volterra filtering and principal component analysis , 2012, Neural Networks.