This article is concerned with the prediction of time delays and a control method for networked control systems (NCSs). We propose to predict the network-induced delays online with least squares support vector machines (LSSVM) optimized by particle swarm optimization (PSO). Then self-tuning proportional–integral–derivative (PID) control with variable delays is adopted in the NCSs. The recursive least squares (RLS) method is used to identify the parameters of the controlled objects, which can adapt to changes in dynamic models. Simulations verified the excellent performance of network delay prediction and networked control, and stable closed-loop control can be realized.
BabakTParvizJMNasserR (2009) Tuning of control systems over CSMA networks. IEEE Transactions on Industrial Electronics56(4): 1282–1291.
2.
CaoJDingWYZhaoDS. (2015) Time series forecast of foundation pit deformation based on PSO-LSSVM. Control Engineering of China22(3): 475–480.
3.
ChenDXiNWangYC. (2009) Generalized predictive control scheme for the internet-based telerobot control system. Journal of Mechanical Engineering45(3): 191–196.
4.
DongLWangJHZhouH. (2014) The statistics method of key parameters in network control system. In: Proceedings of the 2014 International Conference on Control Engineering and Information Systems, pp.77–81.
5.
EulerCFabioG (2010) Design of networked control systems with explicit compensation for time-delay variations. IEEE Transactions on Systems, Man and Cybernetics40(3): 308–318.
6.
FuWYangXYChaiY. (2012) Design of self-adjusting PID controller for networked control systems. Control and Decision27(8): 1231–1236.
7.
GuoSTFengXYuCT (2012) Predictive compensation for variable network delays and packet losses in networked control systems. Computers and Chemical Engineering39(4): 152–162
8.
HacibTLeBSmailM. (2011) Microwave characterization using ridge polynomial neural networks and least-square support vector machines. IEEE Transactions on Magnetics47(5): 990–993.
9.
HaleviYRayA (1988) Integrated communication and control systems. Part I: Analysis. Journal of Dynamic Systems Measurement and Control110(4): 367–373.
10.
HespanhaJNaghshtabriziPXuY (2007) A survey of recent results in networked control systems. Proceedings of the IEEE, pp. 138–162.
11.
HuangLLChenJ (2012) PD control of networked control system based on Smith compensation and neural network. System Engineering and Electronics34(9): 1884–1888.
12.
HuasongMTianmiaoWHongxingW. (2010) Timestamp based predictive robot control system over real-time industrial ethernet. In: Proceedings of the Third International Conference on Intelligent Robotics and Applications, Shanghai, pp.183–194
13.
HuSYueDLiuJ (2012) H∞ filtering for networked systems with partly known distribution transmission delays. Information Science194: 270–282.
14.
JinhuiZJamesLYuanqingX (2014) Output feedback delay compensation control for networked control systems with random delays. Information Sciences265: 154–166.
15.
KiyongKRaoPBurnworthJ (2010) Self-tuning of the PID controller for a digital excitation control system. IEEE Transactions on Industry Applications46(4): 1518–1524.
16.
LiCMXiaoJZhangY (2007) Time delay estimation and adaptive control of networked control systems. Journal of Southwest Jiaotong University42(2): 175–180.
17.
LiKXZhangJBCaoA (2008) Design and simulation of an useful self-tuning PID controller. Computer Simulation25(9): 167–170.
18.
MiranianAAbdollahzadeM (2013) Developing a local least-squares support vector machines-based neuro-fuzzy model for nonlinear and chaotic time series prediction. IEEE Transactions on Neural Networks and Learning Systems24(2): 207–218.
19.
SantosMStemmerMVasquesF (2003) Evaluation of the timing properties of two control networks: Can and Profibus. IEEE International Symposium on Industrial Electronics, pp. 874–879.
20.
ShuliS (2012) Linear optimal state and input estimators for networked control systems with multiple packet dropouts. International Journal of Innovative Computing, Information and Control8(10(B)): 7289–7305.
21.
ShrivastavaNKhosraviAPanigrahiB (2015) Prediction interval estimation of electricity prices using PSO-tuned support vector machines. IEEE Transactions on Industrial Informatics11(2): 322–331.
22.
TianZDGaoXWLiK (2013) Networked control system time-delay prediction based on KPCA and LSSVM. Systems Engineering and Electronics35(5): 1281–1285.
23.
VapnikVN (1995) The Nature of Statistical Learning Theory. New York: Springer.
24.
WuJChenT (2007) Design of networked control systems with packet dropouts. IEEE Transactions on Automatic Control52(7): 1314–1319.
25.
XuXY (2007) Adaptive Control Theory and Applications. Beijing: Publishing House of Electronics Industry.
26.
YuJMaXJNiF. (2013) Short-term power forecasting of wind farm based on an improved PSO-LSSVM. Journal of Xi’an University of Technology29(2): 176–181.
27.
YuXMJiangJP (2012) Model states feedback networked control method based on delay prediction. Control Engineering of China19(2): 211–213.
28.
ZhaoYPZhangLYLiDC. (2013) Chaotic time series prediction using filtering window based least squares support vector regression. Acta Physica Sinica62(12): 120511-1–120511-9.
