Abstract
Predictive control is often used to improve control performance because most industrial sites are inertial lag objects, but it is difficult to establish predictive model. In this paper, artificial intelligence method is applied to control object modeling. A deep learning based modeling method is proposed, which includes open-loop modeling and closed-loop modeling. Closed-loop modeling is based on open-loop modeling. Firstly, the DNN deep learning algorithm used in this paper is introduced. Aiming at open-loop data of multi-order inertial system, a deep learning DNN network system based on Multiple Inertial filters is designed. After training step disturbance data, a deep learning neural network model with object characteristics is obtained. Secondly, a closed-loop modeling method based on two DNN models is proposed for multi-order inertial closed-loop systems. Firstly, forward and backward step disturbances are added to the control variables, then model 1 is obtained after training the DNN network system with deep learning based on Multiple Inertial filters, and then forward and backward step disturbances are added to the set values. The output data of model 1 and the output data of controlled objects are trained as inputs of deep learning DNN random inactivation network, and the closed-loop object model is finally obtained.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hornik, K., Stichcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2, 359–366 (1989)
Keshmiri, S., et al.: Application of deep neural network in estimation of the weld bead parameters. arXiv preprint arXiv:1502.04187 (2015)
Shaw, A.M., Doyle, F.J., Schwaber, J.S.: A dynamic neural network approach to nonlinear process modeling. Comput. Chem. Eng. 21(4), 371–385 (1997)
Freitas, F.D., De Souza, A.F., de Almeida, A.R.: Prediction-based portfolio optimization model using neural networks. Neurocomputing 72(10), 2155–2170 (2009)
Rogers, S.K., et al.: Neural networks for automatic target recognition. Neural Netw. 8(7), 1153–1184 (1995)
Zhu, B.: Thermal Automation System Test of Thermal Power Plant. China Electric Power Press (2006)
Xi, Y.: Predictive Control. National Defense Industry Press (1993)
Wang, W.: A new direct method of generalized predictive adaptive control. J. Autom. 22(3) (1996)
Wang, G., et al.: Application of PFC-PID cascade control strategy in main steam temperature control system. Proc. CSEE 22(12), 50–55 (2002)
Li, Q., et al.: Model predictive control of denitrification system for supercritical units. Zhejiang Electr. Power 35(11), 34–36 (2016)
Jin, X., Wang, S., Rong, G.: Predictive functional control (PFC) – a new predictive control strategy. Chem. Autom. Instrum. 26(2), 74–80 (1999)
Schmidhuber, J.: Deep learning in neural in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Beale, R., Jackson, T.: Neural Computing-An Introduction. CRC Press, Boca Raton (1990)
Berniker, M., Kording, K.P.: Deep networks for motor control functions. Front. Comput. Neurosci. 9, 32 (2015)
Moed, M.C., Saridis, G.N.: A Boltzmann machine for the organization of intelligent machines. IEEE Trans. Syst. Man Cybern. 20(5), 1094–1102 (1990)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Yin, F., Ye, S., Li, Q., Sun, J., Cai, J. (2020). Research and Application of Process Object Modeling Method Based on Deep Learning. In: Xhafa, F., Patnaik, S., Tavana, M. (eds) Advances in Intelligent Systems and Interactive Applications. IISA 2019. Advances in Intelligent Systems and Computing, vol 1084. Springer, Cham. https://doi.org/10.1007/978-3-030-34387-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-34387-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-34386-6
Online ISBN: 978-3-030-34387-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)