Research on PID Neural Network Decoupling Control Among Joints of Hydraulic Quadruped Robot

Bingwei       Gao; Yongtai       Ye; Guihua	      Han

doi:10.2174/2212797612666190819161320

Abstract

Background: Hydraulic quadruped robot is a representative of the redundant transmission. This is a great challenge for multi-joints coordinated movement of the robot, because of the movement coupling with several freedom degrees among kinematic chains. Therefore, there is an urgent need to realize the decoupling among the joints of the hydraulic quadruped robot.

Objective: The purpose of this study is to provide an overview of controller design from many studies and patents, and propose a novel controller to realize the decoupling control among joints of a hydraulic quadruped robot.

Methods: For the coupling problems between the thigh and calf of a hydraulic quadruped robot, based on the Lagrangian method, dynamics model of the robot’s leg is established. The influence of driven system is considered. The model of the hydraulic servo driven system is built, so as to obtain the coupling relationship between thigh and calf of hydraulic quadruped robot. Based on the multivariable decoupling theory, a PID neural network decoupling controller is designed.

Results: The researches on experiments are executed. The PID neural network decoupling control method is compared with the control that does not use any decoupling method. The decoupling effect of the proposed algorithm is verified on the thigh and the calf of the hydraulic quadruped robot.

Conclusion: The designed PID neural network decoupling control method reduces the crosscoupling between thigh and calf of the hydraulic quadruped robot, and has obvious effect to improve the dynamic characteristics of single joint of robot's leg.

Keywords: Cross-coupling, decoupling control, hydraulic quadruped robot, multi-joints coordinated movement, neural network, PID.

« Previous Next »

[1] 
Ding YS, Liu B. An intelligent bi-cooperative decoupling control approach based on modulation mechanism of internal environment in body. IEEE T Contr Syst T  2011; 19(3): 692-8.
[http://dx.doi.org/10.1109/TCST.2010.2047944] 
[2] 
Chi RN, Hu YM, Hu ZX. Real-time trajectory tracking of nonholonomic mobile robot based on decoupling control techniques. Robot  2001; 23(3): 256-60.
[3] 
Chiang MH, Yeh YP, Yang FL, Chen YN. Integrated control of clamping force and energy-saving in hydraulic injection moulding machines using decoupling fuzzy sliding-mode control. Int J Adv Manuf Tech  2005; (27): 53-62.
[http://dx.doi.org/10.1007/s00170-004-2138-z] 
[4] 
Nguyen HT, Su SW. Conditions for triangular decoupling control. Int J Control  2009; 82(9): 1575-81.
[http://dx.doi.org/10.1080/00207170802566614] 
[5] 
Duan YB, Gao BK, Liu CS, Xu JJ. Decoupling control
method and device based on nonlinear MIMO system CN103399487. (2013).
[6] 
Zhu YQ, Ru JT, Jin W, Li YY. Construction method of AC
hybrid magnetic bearing decoupling controller CN103486134. (2013).
[7] 
Jiang HB, Chen L, Sun XD, Wang SH, Yin CF, Li K. Construction method of generalized inverse controller for fuzzy
neural network of chassis nonlinear system CN104049536. (2014).
[8] 
Sun XD, Chen LJ, Hao B, Yang ZB, Li K. Radial active
magnetic bearing controller and construction method CN103425052. (2013).
[9] 
Ye BS, Xiong S, Guo XJ, Tang XQ, Song B, Shen YQ. Motion control method for decoupled six-degree-of-freedom industrial
robot CN102785248. (2012).
[10] 
Zeng GQ, Xie XQ, Chen MR, Weng J. Adaptive population extremal optimization based PID neural network for multivariable nonlinear control systems. Swarm Evol Comput  2019; 44: 320-34.
[http://dx.doi.org/10.1016/j.swevo.2018.04.008] 
[11] 
Zeng GQ, Chen J, Dai YX, Li LM, Zheng CW, Chen MR. Design of fractional order PID controller for automatic regulator voltage system based on multi-objective extremal optimization. Neurocomputing  2015; 160: 173-84.
[http://dx.doi.org/10.1016/j.neucom.2015.02.051] 
[12] 
Zhuang M, Yu ZW, Gong DP. Xu Ml, Dai ZD. Gait planning and simulation of quadruped robot with hydraulic drive based on ADAMS. Mach Des Manu  2012; 7: 100-2.
[13] 
Enoch AM. Robot leg US20180170466. (2018).
[14] 
Shao JP, Zhang YH, Sun GT. A method for rigid support
phase control of a hydraulic quadruped robot with one leg CN20181117810. (2018).
[15] 
Lai CB. Hydraulic drive quadruped robot CN206749957. (2017).
[16] 
Li YB, Hua ZS, Hao YZ, Rong XW, Tian GH, Li B. Variable topological structure's quadruped robot mechanism CN206704341. (2017).
[17] 
Ma ZL, Zhang PQ, Liu YC, Li R J, Wang JM. Bionic
climbing quadruped robot CN105235769. (2017).
[18] 
Ma ZL, Zhang PQ, Liu YC, Li QY, Feng S, Wang JM. Dog-like quadruped robot CN105109575. (2017).
[19] 
Ding LH, Wang RX, Feng HS, Li J. Brief analysis of a BigDog quadruped robot. Chin J Constr Mach  2012; 23(5): 505-14.
[20] 
Jackowski ZJ, Khripin A, Berard S, Rizzi AA. Robotic hydraulic
system US20180106276. (2018).
[21] 
Jackowski ZJ, Khripin AY, Rizzi AA. Hydraulic pressure
variation in a legged robot US20190063468. (2019).
[22] 
Jackowski ZJ, Rogers K, Young A. A Motor and controller integration
for a legged robot US20180169868. (2018).
[23] 
Kong XD, Yu B, Quan LX, Zhai FG, Zhang W, Zhang YT. High integration hydraulic driving unit structure CN103233932. (2015).
[24] 
Wos P, Dindorf R. Adaptive control of the electro-hydraulic servo-system with external disturbances. Asian J Control  2013; 15(6): 1764-71.
[http://dx.doi.org/10.1002/asjc.602] 
[25] 
Takagi Y, Tanaka C, Watabe T, Kaneko H, Kanazawa M. Control device for mobile robot US20170183047. (2017).
[26] 
Murphy M, Saunders JA, Potter SD. Discretized valve state
control for multi-level hydraulic systems US20170191505. (2017).
[27] 
Saunders JA, Hansen M, Komsta J. Integrated valve for a
legged robot US20170219106. (2017).
[28] 
Chatty A, Gaussier P, Hasnain SK, Kallel I, Alimi AM. The effect of learning by imitation on a multi-robot system based on the coupling of low-level imitation strategy and online learning for cognitive map building. Adv Robot  2014; 28(11): 731-43.
[http://dx.doi.org/10.1080/01691864.2014.883170] 
[29] 
Shao JP, Liu MM, Sun GT. Hydraulic quadruped robot
power mechanism load matching method CN108897318. (2018).
[30] 
Zhang AD, Sun CM, Lin J. Electric drive quadruped robot
that can adapt to high bearing force of complicated rugged topography CN207683655. (2018).
[31] 
Chen DL, Wang H, Liu Q. Bionic quadruped robot with
spine joints and elastic legs CN203780644. (2014).
[32] 
Li YB, Chai H, Zhang H, Zhang GT, Ma XL. Distributed
type control system of hydraulic quadruped robot and control
method CN103279113. (2015).
[33] 
Swilling B, Whitman E, Berard S, Rizzi AA, Khripin AY, Fay GC. Achieving a target gait behavior in a legged robot US20190054965. (2019).
[34] 
Jackowski ZJ, Young A. Transmission with integrated overload
protection for a legged robot US20180172080. (2018).
[35] 
Sun XD, Zhu HQ. Neuron PID control for a bpmsm based on RBF neural network on-line identification. Asian J Control  2013; 15(6): 1772-84.
[http://dx.doi.org/10.1002/asjc.547] 
[36] 
Shu H, Zhang J. Dual-capacity liquid level control system based
on PID neural network CN206563911. (2017).
[37] 
Chen F, Yao AB. Neural network calibration mechanism US20180285734. (2018).
[38] 
Chen YK, Yang SW, Ndiour IJ, et al. Multi-domain convolutional neural
network US20190042870. (2019).
[39] 
Li YJ, Jiang H, Zhang CG, Yue SC, Yang M. Phase angle
amplitude PID adaptive method based on BP neural network
for three-dimensional magnetic property measurement CN109034390. (2018).
[40] 
Zhang Y, Fang LC, Huang C, Chen Z. Temperature control
method of dynamically predicting PID based on RBF neural
network CN108958020. (2018).
[41] 
Moharam A, El-Hosseini MA, Hesham AA. Design of optimal PID controller using hybrid differential evolution and particle swarm optimization with an aging leader and challengers. Appl Soft Comput  2016; 38: 727-37.
[http://dx.doi.org/10.1016/j.asoc.2015.10.041] 
[42] 
Li SH, Fairbank M, Fu XG, Wunsch D, Alonso E. Systems,
methods and devices for vector control of permanent magnet synchronous
machines using artificial neural networks US20150039545. (2015).
[43] 
Driscoll JJ, Kesse ML, Robel WJ, Jayachandran A. Nox control using a neural network US20070251218. (2007).
[44] 
Han HG, Liu Z. Dissolved oxygen model prediction control
method based on adaptive fuzzy neural network CN108563118. (2018).
[45] 
Campos J, Lewis FL. Backlash compensation with filtered prediction
in discrete time nonlinear systems by dynamic inversion using
neural networks US20040015933. (2004).
[46] 
Chen SY, Lin FJ. Decentralized PID neural network control for five degree-of-freedom active magnetic bearing. Eng Appl Artif Intell  2013; 26(3): 962-73.
[http://dx.doi.org/10.1016/j.engappai.2012.11.002] 
[47] 
Xu GH, Zhu YP, Zhang XL, Xie YJ, Yang G, Wang J. Intelligent tracking vehicle based on BP neural network PID control
device CN205229800. (2016).
[48] 
Zheng S, Lu DX, Chen YB, et al. Control method for boiler drum water level based
on fuzzy neural network PID control CN103968367. (2014).
[49] 
Yehezkel Rohekar RY, Koren G, Nisimov S, Novik G. Efficient
learning and using of topologies of neural networks in machine
learning US20180322385. (2018).
[50] 
Drees KH. Building management system with augmented deep
learning using combined regression and artificial neural network
modeling US20190041811. (2019).
[51] 
Jiang YB, Qing CD. Air-conditioner control method based on
neural network CN108895618. (2018).
[52] 
Liu XL, Li Z. Steering engine electric loading system intelligent
control method based on cerebellar neural network CN108828952. (2018).
[53] 
Choi HH, Yun HM, Kim Y. Implementation of evolutionary fuzzy PID speed controller for PM synchronous motor. IEEE Trans Industr Inform  2015; 11(2): 540-7.
[http://dx.doi.org/10.1109/TII.2013.2284561] 
[54] 
Izzat IH, Comer ML, Nijim YW. Dynamic rate adaptation
using neural networks for transmitting video data US20050025053. (2005).
[55] 
Klimasauskas CC, Guiver JP. Hybrid linear-neural network
process control US20010025232. (2001).
[56] 
Morishige K. Heat exchange system, controller and construction
method of neural network JP2018105571. (2018).
[57] 
Wan JQ, Huang MZ, Ma YW, Wang Y. Method and system
for wastewater treatment based on dissolved oxygen control by
fuzzy neural network US20140052422. (2014).
[58] 
Jacobson EE. Engine control system using a cascaded neural
network US20030217021. (2003).
[59] 
Cho CN, Kim HJ, Song YH. PID System and method for
tuning the gains of PID controller using neural network KR20180032453. (2018).
[60] 
Zemouri R, Gouriveau R, Paul CP. Combining a recurrent neural network and a PID controller for prognostic purpose: A way to improve the accuracy of predictions. WSEAS T Syst Contr  2010; 5(5): 353-71.
[61] 
Liu GH, Wang ZX, Mei CL, Yu S, Ding YH. Feedforward
decoupling method of permanent magnet synchronous motor based
on neural network online learning CN103219936. (2013).
[62] 
Chen YK, Yang SW, Ndiour IJ, et al. Multi-domain cascade convolutional
neural network US20190042867. (2019).
[63] 
Turney RD. Predictive building control sysytem with neural network
based constraint generation US20180306459. (2018).
[64] 
Xu B, Wang X. Aircraft global finite time neural network
control method based on switching mechanism CN108828957. (2018).
[65] 
Chen YH, Liu XY, Shi SY, Guan SY, Xia YH. Greenhouse
irrigation system and method based on neural network
prediction CN108781926. (2018).
[66] 
Claessens B, Vrancx P. Methods, controllers and systems for the
control of distribution systems using a neural network architecture US20190019080. (2019).
[67] 
Wang CW. Analog turntable control system based on neural
network PID control CN107908101. (2018).
[68] 
Nagashima F. Neural network learning device, method, and program US20090132449. (2009).
[69] 
Tokuda M, Yamamoto T, Monden Y. A design of multiloop PID controllers with a neural-net based decoupler. Asian J Controlasian J Control  2005; 7(3): 275-85.
[http://dx.doi.org/10.1111/j.1934-6093.2005.tb00237.x] 
[70] 
Sun XD, Chen L, Li K, Yang ZB, Zhu YQ. Construction
method of neural network generalized inverse decoupling controller
for bearing less asynchronous motor CN102790578. (2012).
[71] 
Xia CL, Guo C, Shi TN. Mechanical decoupling control
method of permanent magnet spherical motor based on neural network
identifier CN101369132. (2009).
[72] 
Henry S. Using a neural network to optimize procession of user
requests US20190065948. (2019).
[73] 
Mellempudi N, Das D. Scaling half-precision floating point tensors
for training deep neural networks US20180322382. (2018).
[74] 
Wang J, Deng YM. Intelligent setting method for tea machine
processing control parameters based on RBF neural network CN108719516. (2018).
[75] 
Wang XB, Ge S, Meng MR. DNN (Depth Neural Network)
neural network self-adaptive control method based on tendondriven
dexterous hand CN108555914. (2018).
[76] 
Fu XG, Li SH. Systems, methods and devices for vector control
of induction machines using artificial neural networks US20160301334. (2016).
[77] 
Xu Q, Yang ZP. Heating furnace temperature computer control
method based on process neural network CN107870565. (2018).

Rights & Permissions Print Cite

Article Metrics

16

Journal Information

For Authors

For Editors

For Reviewers

Explore Articles

Open Access

Open Access Articles

For Visitors

DOI https://dx.doi.org/10.2174/2212797612666190819161320	Print ISSN 2212-7976
Publisher Name Bentham Science Publisher	Online ISSN 1874-477X

Recent Patents on Mechanical Engineering

Research on PID Neural Network Decoupling Control Among Joints of Hydraulic Quadruped Robot

Abstract Play Pause

Related Journals

Related Books

Abstract