Recurrent neural network for solving model predictive control problem in application of four-tank benchmark

详细信息    查看全文

• 作者：Jing Xu^a ; ^{xujinggg223@163.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Chuandong Li^a ; ^{licdswu@163.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Xing He^a ; ^{hexingdoc@swu.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Tingwen Huang^b ; ^{tingwen.huang@qatar.tamu.edu" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Four-tank benchmark ; Discrete-time recurrent neural network ; Globally exponentially stable
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：19 May 2016
• 年：2016
• 卷：190
• 期：Complete
• 页码：172-178
• 全文大小：662 K

文摘

Based on model predictive control techniques, this paper presents a discrete-time recurrent neural network for solving four-tank benchmark problem which is reformulated to a convex programming problem. If the weighting matrices are positive definite symmetric, it is shown that the proposed neural network is globally exponentially stable and exponentially convergent to the exact optimal solutions. Finally, the experimental results have testified the effectiveness of the proposed approach and shown that the four-tank benchmark problem can be well resolved.