Home > Research > Publications & Outputs > Convergence Analysis and Digital Implementation...

Research

Links

Text available via DOI:

View graph of relations

Convergence Analysis and Digital Implementation of A Discrete-Time Neural Network for Model Predictive Control

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Convergence Analysis and Digital Implementation of A Discrete-Time Neural Network for Model Predictive Control. / Lu, Yang; Li, Dewei; Xu, Zuhua et al.
In: IEEE Transactions on Industrial Electronics, Vol. 61, No. 12, 31.12.2014, p. 7035 - 7045.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Lu, Y, Li, D, Xu, Z & Yugeng, XI 2014, 'Convergence Analysis and Digital Implementation of A Discrete-Time Neural Network for Model Predictive Control', IEEE Transactions on Industrial Electronics, vol. 61, no. 12, pp. 7035 - 7045. https://doi.org/10.1109/TIE.2014.2316250

APA

Lu, Y., Li, D., Xu, Z., & Yugeng, XI. (2014). Convergence Analysis and Digital Implementation of A Discrete-Time Neural Network for Model Predictive Control. IEEE Transactions on Industrial Electronics, 61(12), 7035 - 7045. https://doi.org/10.1109/TIE.2014.2316250

Vancouver

Lu Y, Li D, Xu Z, Yugeng XI. Convergence Analysis and Digital Implementation of A Discrete-Time Neural Network for Model Predictive Control. IEEE Transactions on Industrial Electronics. 2014 Dec 31;61(12):7035 - 7045. Epub 2014 Sept 12. doi: 10.1109/TIE.2014.2316250

Author

Lu, Yang ; Li, Dewei ; Xu, Zuhua et al. / Convergence Analysis and Digital Implementation of A Discrete-Time Neural Network for Model Predictive Control. In: IEEE Transactions on Industrial Electronics. 2014 ; Vol. 61, No. 12. pp. 7035 - 7045.

Bibtex

@article{12fe62f82b3e46fd954a67575071eef9,
title = "Convergence Analysis and Digital Implementation of A Discrete-Time Neural Network for Model Predictive Control",
abstract = "In this paper, a discrete-time neural network for solving convex quadratic programming (QP) problems in constrained model predictive control (MPC) technology is investigated and implemented on a digital signal processor (DSP) device. This makes it possible to apply MPC technology to local control for high-dimensional multiple-input-multiple-output systems. The convergence issue of the discrete-time neural network is first studied. By choosing a proper error function, a sufficient condition is obtained under which the neural network converges to the exact optimal solution globally. This is the theoretical basis of this paper. An integrated hardware and software design method to implement the neural network on a DSP chip as a universal QP solver is then developed. With the QP solver handling the computational tasks in MPC problems, a general DSP-based MPC controller is achieved. A prototype system is built on a TMDSEVM6678L DSP development board. It is then applied to an air-separation-unit system and achieves satisfactory control performance. This verifies the effectiveness of the whole design.",
author = "Yang Lu and Dewei Li and Zuhua Xu and XI Yugeng",
year = "2014",
month = dec,
day = "31",
doi = "10.1109/TIE.2014.2316250",
language = "English",
volume = "61",
pages = "7035 -- 7045",
journal = "IEEE Transactions on Industrial Electronics",
issn = "0278-0046",
publisher = "IEEE",
number = "12",

}

RIS

TY - JOUR

T1 - Convergence Analysis and Digital Implementation of A Discrete-Time Neural Network for Model Predictive Control

AU - Lu, Yang

AU - Li, Dewei

AU - Xu, Zuhua

AU - Yugeng, XI

PY - 2014/12/31

Y1 - 2014/12/31

N2 - In this paper, a discrete-time neural network for solving convex quadratic programming (QP) problems in constrained model predictive control (MPC) technology is investigated and implemented on a digital signal processor (DSP) device. This makes it possible to apply MPC technology to local control for high-dimensional multiple-input-multiple-output systems. The convergence issue of the discrete-time neural network is first studied. By choosing a proper error function, a sufficient condition is obtained under which the neural network converges to the exact optimal solution globally. This is the theoretical basis of this paper. An integrated hardware and software design method to implement the neural network on a DSP chip as a universal QP solver is then developed. With the QP solver handling the computational tasks in MPC problems, a general DSP-based MPC controller is achieved. A prototype system is built on a TMDSEVM6678L DSP development board. It is then applied to an air-separation-unit system and achieves satisfactory control performance. This verifies the effectiveness of the whole design.

AB - In this paper, a discrete-time neural network for solving convex quadratic programming (QP) problems in constrained model predictive control (MPC) technology is investigated and implemented on a digital signal processor (DSP) device. This makes it possible to apply MPC technology to local control for high-dimensional multiple-input-multiple-output systems. The convergence issue of the discrete-time neural network is first studied. By choosing a proper error function, a sufficient condition is obtained under which the neural network converges to the exact optimal solution globally. This is the theoretical basis of this paper. An integrated hardware and software design method to implement the neural network on a DSP chip as a universal QP solver is then developed. With the QP solver handling the computational tasks in MPC problems, a general DSP-based MPC controller is achieved. A prototype system is built on a TMDSEVM6678L DSP development board. It is then applied to an air-separation-unit system and achieves satisfactory control performance. This verifies the effectiveness of the whole design.

U2 - 10.1109/TIE.2014.2316250

DO - 10.1109/TIE.2014.2316250

M3 - Journal article

VL - 61

SP - 7035

EP - 7045

JO - IEEE Transactions on Industrial Electronics

JF - IEEE Transactions on Industrial Electronics

SN - 0278-0046

IS - 12

ER -