Abstract
Neural networks (NNs) are extensively used in modelling, optimization, and control of nonlinear plants. NN-based inverse type point prediction models are commonly used for nonlinear process control. However, prediction errors (root mean square error (RMSE), mean absolute percentage error (MAPE) etc.) significantly increase in the presence of disturbances and uncertainties. In contrast to point forecast, prediction interval (PI)-based forecast bears extra information such as the prediction accuracy. The PI provides tighter upper and lower bounds with considering uncertainties due to the model mismatch and time dependent or time independent noises for a given confidence level. The use of PIs in the NN controller (NNC) as additional inputs can improve the controller performance. In the present work, the PIs are utilized in control applications, in particular PIs are integrated in the NN internal model-based control framework. A PI-based model that developed using lower upper bound estimation method (LUBE) is used as an online estimator of PIs for the proposed PI-based controller (PIC). PIs along with other inputs for a traditional NN are used to train the PIC to predict the control signal. The proposed controller is tested for two case studies. These include, a chemical reactor, which is a continuous stirred tank reactor (case 1) and a numerical nonlinear plant model (case 2). Simulation results reveal that the tracking performance of the proposed controller is superior to the traditional NNC in terms of setpoint tracking and disturbance rejections. More precisely, 36% and 15% improvements can be achieved using the proposed PIC over the NNC in terms of IAE for case 1 and case 2, respectively for setpoint tracking with step changes.
Similar content being viewed by others
References
X. Hu, J. Xia, Z. Wang, X. Song, and H. Shen, “Robust distributed state estimation for markov coupled neural networks under imperfect measurements,” Journal of the Franklin Institute, vol. 357, no. 4, pp. 2420–2436, 2020.
G. I. Parisi, R. Kemker, J. L. Part, C. Kanan, and S. Wermter, “Continual lifelong learning with neural networks: A review,” Neural Networks, vol. 113, pp. 54–71, 2019.
H. Zhao, S. Gao, Z. He, X. Zeng, W. Jin, and T. Li, “Identification of nonlinear dynamic system using a novel recurrent wavelet neural network based on the pipelined architecture,” IEEE Trans. Ind. Electron., vol. 61, no. 8, pp. 4171–4182, 2014.
H. Kang, S. Yang, J. Huang, and J. Oh, “Time series prediction of wastewater flow rate by bidirectional LSTM deep learning,” International Journal of Control, Automation and Systems, vol. 18, no. 12, pp. 3023–3030, 2020.
L. Ma, N. Xu, X. Huo, and X. Zhao, “Adaptive finite-time output-feedback control design for switched pure-feedback nonlinear systems with average dwell time,” Nonlinear Analysis: Hybrid Systems, vol. 37, p. 100908, 2020.
S. Ding, H. Li, C. Su, J. Yu, and F. Jin, “Evolutionary artificial neural networks: A review,” Artificial Intelligence Review, vol. 39, no. 3, pp. 251–260, 2013.
M. Rahmani and M. H. Rahman, “Adaptive neural network fast fractional sliding mode control of a 7-DoF exoskeleton robot,” International Journal of Control, Automation and Systems, vol. 18, no. 1, pp. 124–133, 2020.
K. Vonsevych, M. F. Goethel, J. Mrozowski, J. Awrejcewicz, and M. Bezuglyi, “Fingers movements control system based on artificial neural network model,” Radio-electronics and Communications Systems, vol. 62, no. 1, pp. 23–33, 2019.
L. Ma, X. Huo, X. Zhao, and G. D. Zong, “Observer-based adaptive neural tracking control for output-constrained switched MIMO nonstrict-feedback nonlinear systems with unknown dead zone,” Nonlinear Dynamics, vol. 99, no. 2, pp. 1019–1036, 2020.
Z. Jin, J. Chen, Y. Sheng, and X. Liu, “Neural network based adaptive fuzzy PID-type sliding mode attitude control for a reentry vehicle,” International Journal of Control, Automation and Systems, vol. 15, no. 1, pp. 404–415, 2017.
N. Wang, C. Chen, and C. Yang, “A robot learning framework based on adaptive admittance control and generalizable motion modeling with neural network controller,” Neurocomputing, vol. 390, pp. 260–267, 2020.
H. Ren and P. Ben-Tzvi, “Learning inverse kinematics and dynamics of a robotic manipulator using generative adversarial networks,” Robotics and Autonomous Systems, vol. 124, p. 103386, 2020.
W. Zheng, H.-B. Wang, Z.-M. Zhang, N. Li, and P.-H. Yin, “Multi-layer feed-forward neural network deep learning control with hybrid position and virtual-force algorithm for mobile robot obstacle avoidance,” International Journal of Control, Automation and Systems, vol. 17, no. 4, pp. 1007–1018, 2019.
F. Weber, S. Bhowmik, and J. Høgsberg, “Extended neural network-based scheme for real-time force tracking with magnetorheological dampers,” Struct. Control Health Monit., vol. 21, no. 2, pp. 225–247, 2014.
A. Rahideh, A. Bajodah, and M. H. Shaheed, “Real time adaptive nonlinear model inversion control of a twin rotor MIMO system using neural networks,” Eng. Appl. Artif. Intell., vol. 25, no. 6, pp. 1289–1297, 2012.
L. Rincon, Y. Kubota, G. Venture, and Y. Tagawa, “Inverse dynamic control via simulation of feedback control by artificial neural networks for a crane system,” Control Engineering Practice, vol. 94, p. 104203, 2020.
I. Kasireddy, A. W. Nasir, and A. K. Singh, “IMC based controller design for automatic generation control of multi area power system via simplified decoupling,” International Journal of Control, Automation and Systems, vol. 16, no. 3, pp. 994–1010, 2018.
J. Li, S. Li, X. Chen, and J. Yang, “Rbfndob-based neural network inverse control for non-minimum phase MIMO system with disturbances,” ISA transactions, vol. 53, no. 4, pp. 983–993, 2014.
Y.-J. Yoon and M. H. Lee, “Dynamic simulation of vapor-compression cycle using neural networks,” International Journal of Control, Automation and Systems, vol. 8, no. 6, pp. 1241–1249, 2010.
S. Maiti, V. Verma, C. Chakraborty, and Y. Hori, “An adaptive speed sensorless induction motor drive with artificial neural network for stability enhancement,” IEEE Trans. Ind. Informat., vol. 8, no. 4, pp. 757–766, 2012.
Z. Xu, S. Li, X. Zhou, and T. Cheng, “Dynamic neural networks based adaptive admittance control for redundant manipulators with model uncertainties,” Neurocomputing, vol. 357, pp. 271–281, 2019.
M. A. Hosen, A. Khosravi, D. Creighton, and S. Nahavandi, “Prediction interval-based modelling of polymerization reactor: A new modelling strategy for chemical reactors,” J. Taiwan Inst. Chem. Eng., vol. 45, no. 5, pp. 2246–2257, 2014.
M. A. Hosen, A. Khosravi, S. Nahavandi, and D. Creighton, “Improving the quality of prediction intervals through optimal aggregation,” IEEE Trans. Ind. Electron., vol. 62, no. 7, pp. 4420–4429, 2015.
H. M. D. Kabir, A. Khosravi, M. A. Hosen, and S. Nahavandi, “Neural network-based uncertainty quantification: A survey of methodologies and applications,” IEEE Access, vol. 6, pp. 36218–36234, 2018.
H. Quan, D. Srinivasan, and A. Khosravi, “Particle swarm optimization for construction of neural network-based prediction intervals,” Neurocomputing, vol. 127, pp. 172–180, 2014.
M. A. Hosen, A. Khosravi, S. Nahavandi, D. Creighton, and S. M. Salaken, “Prediction interval-based neural network controller for nonlinear processes,” Proc. of International Joint Conference on Neural Networks (IJCNN), IEEE, pp. 1–6, 2015.
A. Khosravi, S. Nahavandi, D. Creighton, and A. F. Atiya, “Comprehensive review of neural network-based prediction intervals and new advances,” IEEE Trans. Neural Netw., vol. 22, no. 9, pp. 1341–1356, 2011.
A. Khosravi, S. Nahavandi, D. Creighton, and A. Atiya, “Lower upper bound estimation method for construction of neural network-based prediction intervals,” IEEE Trans. Neural Netw., vol. 22, no. 3, pp. 337–346, 2011.
M. A. Hosen, Prediction Interval-based Modelling and Control of Nonlinear Processes, Ph.D. Dissertation, 2015.
M. A. Hosen, A. Khosravi, S. Nahavandi, and L. Sinnott, “Prediction interval-based ANFIS controller for nonlinear processes,” Proc. of International Joint Conference on Neural Networks (IJCNN), pp. 4901–4907, July 2016.
N. K. Kandasamy, G. Karunagaran, C. Spanos, K. J. Tseng, and B.-H. Soong, “Smart lighting system using ANN-IMC for personalized lighting control and daylight harvesting,” Building and Environment, vol. 139, pp. 170–180, 2018.
G. Liu, L. Chen, W. Zhao, Y. Jiang, and L. Qu, “Internal model control of permanent magnet synchronous motor using support vector machine generalized inverse,” IEEE Trans. Ind. Informat., vol. 9, no. 2, pp. 890–898, May 2013.
S. Tamura and M. Tateishi, “Capabilities of a four-layered feedforward neural network: Four layers versus three,” IEEE Trans. Neural Netw., vol. 8, no. 2, pp. 251–255, 1997.
C. Kambhampati, R. Craddock, M. Tham, and K. Warwick, “Inverse model control using recurrent networks,” Mathemat. Comput. Sim., vol. 51, no. 3, pp. 181–199, 2000.
S. Tasoujian, S. Salavati, M. Franchek, and K. Grigoriadis, “Robust IMC-PID and parameter-varying control strategies for automated blood pressure regulation,” International Journal of Control, Automation and Systems, vol. 17, no. 7, pp. 1803–1813, 2019.
U. M. Nath, C. Dey, and R. K. Mudi, “Designing of fuzzy rule based switching mechanism for IMC controller for temperature controlling process,” Procedia Computer Science, vol. 167, pp. 1363–1369, 2020.
G. E. Box, G. M. Jenkins, and G. C. Reinsel, Time Series Analysis: Forecasting and Control, vol. 734, John Wiley & Sons, 2011.
M. A. Hosen, A. Khosravi, S. Nahavandi, and D. Creighton, “Prediction interval-based neural network modelling of polystyrene polymerization reactor: A new perspective of data-based modelling,” Chem. Eng. Res. and Des., vol. 92, no. 11, pp. 2041–2051, 2014.
M. A. Hosen, S. Nahavandi, A. Khosravi, P. Shi, and L. Sinnott, “Prediction interval-based controller for chemical reactor,” Proc. of IEEE 30th Canadian Conference on Electrical and Computer Engineering (CCECE), IEEE, pp. 475–478, 2017.
R. Salman, “Neural networks of adaptive inverse control systems,” Applied Mathemat. Comput., vol. 163, no. 2, pp. 931–939, 2005.
A. Shamiri, S. W. Wong, M. F. Zanil, M. A. Hussain, and N. Mostoufi, “Modified two-phase model with hybrid control for gas phase propylene copolymerization in fluidized bed reactors,” Chem. Eng. J., vol. 264, pp. 706–719, 2014.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This research was fully supported by the Institute for Intelligent Systems Research and Innovation (IISRI) at Deakin University, Australia.
Mohammad Anwar Hosen received his B.Sc.(Hons.) degree in chemical engineering from the Bangladesh University of Engineering and Technology, Dhaka, Bangladesh, in 2004, an M.Eng.Sc. degree in chemical engineering from the University of Malaya, Kuala Lumpur, Malaysia, in 2010 and a Ph.D. degree from the Deakin University, Waurn Ponds, Australia, in 2015. He joined to IISRI as a Research Fellow just after completing his Ph.D. degree in 2015. His current research interests include the development and application of AI techniques for modelling and control of nonlinear systems, uncertainty quantification, analytical modelling and process simulation.
Abbas Khosravi received his Ph.D. degree from Deakin University, Australia in 2010. He is currently an associate professor in the Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University. His research interests include the development and application of artificial intelligence techniques for data analysis, pattern recognition, uncertainty quantification, and optimisation.
H. M. Dipu Kabir received his B.Sc. degree from the Department of EEE, Bangladesh University of Engineering and Technology, in 2011. He received an M.Phil. degree from the Department of ECE, the Hong Kong University of Science and Technology, in 2016. He received a Ph.D. degree from the Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, in 2020. He was with the Samsung Bangladesh R&D Center as a Software Engineer from 2011 to 2013. He is currently working as a Research Fellow at Deakin University.
Michael Johnstone received his B.Eng. and Ph.D. degrees from Deakin University, Australia, in 2000 and 2010, respectively. He is currently an Associate Professor at the Institute for Intelligent Systems Research and Innovation at Deakin University. His main research interests are in systems dynamics, agent-based modelling and discrete event simulation for decision support.
Douglas Creighton is a Professor of Systems Engineering at Deakin University and Deputy Director of the Institute of Intelligent Systems Research and Innovation. He received a Bachelor of Systems Engineering and a Bachelor of Science (Physics) from the Australian National University and a Ph.D. degree in industrial engineering/AI from Deakin University. His expertise in modelling and simulation, data analytics and systems thinking is used to inform system design, and strategic and operational decision making for today’s complex infrastructure systems. His research interests include algorithms and methodologies to improve estimation and performance of complex systems operating under uncertainty, variability, and continuous change. He has a 20-year track record working with industry and government in transport, manufacturing, logistics, defence and government, and fostering cross sector innovation.
Saeid Nahavandi received his B.Sc. (Hons.), M.Sc., and Ph.D. degrees in control engineering from Durham University, UK, in 1985, 1986, and 1991, respectively. He is an Alfred Deakin Professor, Pro Vice-Chancellor, Chair of Engineering, and the Founding Director of the Institute for Intelligent Systems Research and Innovation at Deakin University. His research interests include modeling of complex systems, robotics and haptics. He has published over 1000 scientific papers in various international journals and conferences, and been awarded over 50 competitive grants over the past 30 year and holds six patents, two of which have resulted in two very successful startups (Universal Motion Simulator Pty Ltd and FLAIM Systems Pty Ltd). Prof. Nahavandi is a Fellow of IEEE (FIEEE), Engineers Australia (FIEAust), the Institution of Engineering and Technology (FIET). He is a Fellow of the Australian Academy of Technology and Engineering (ATSE).
Peng Shi received his Ph.D. degree in electrical engineering from the University of Newcastle, Australia in 1994 and a Ph.D. degree in mathematics from the University of South Australia in 1998. He was awarded the Doctor of Science degree from the University of Glamorgan, Wales in 2006; and the Doctor of Engineering degree from the University of Adelaide, Australia in 2015.
Rights and permissions
About this article
Cite this article
Hosen, M.A., Khosravi, A., Kabir, H.M.D. et al. NN-based Prediction Interval for Nonlinear Processes Controller. Int. J. Control Autom. Syst. 19, 3239–3252 (2021). https://doi.org/10.1007/s12555-020-0342-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12555-020-0342-8