Optimized PID neural network closed-loop control for basal ganglia network in Parkinson’s disease

doi:10.1088/1674-1056/ae0d55

中国物理B ›› 2025, Vol. 34 ›› Issue (12): 120701-120701.doi: 10.1088/1674-1056/ae0d55

Optimized PID neural network closed-loop control for basal ganglia network in Parkinson’s disease

Hengxi Zhang(张恒熙)^1,2, Honghui Zhang(张红慧)^1,2,†, Shuang Liu(柳爽)³, and Lin Du(都琳)^1,2

1 School of Mathematics and Statistics, Northwestern Polytechnical University, Xi'an 710129, China;
2 MIIT Key Laboratory of Dynamics and Control of Complex Systems, Xi'an 710129, China;
3 Shanghai Engineering Research Center of Physical Vapor Deposition (PVD) Superhard Coating and Equipment, Shanghai Institute of Technology, Shanghai 201418, China

收稿日期:2025-07-11 修回日期:2025-09-29 接受日期:2025-09-30 发布日期:2025-12-10
通讯作者: Honghui Zhang E-mail:haozhucy@nwpu.edu.cn
基金资助:
This project was supported by the National Natural Science Foundation of China (Grant Nos. 12372064 and 12172291) and the Youth and Middle-Aged Science and Technology Development Program of Shanghai Institute of Technology (Grant No. ZQ2024-10).

Optimized PID neural network closed-loop control for basal ganglia network in Parkinson’s disease

Hengxi Zhang(张恒熙)^1,2, Honghui Zhang(张红慧)^1,2,†, Shuang Liu(柳爽)³, and Lin Du(都琳)^1,2

1 School of Mathematics and Statistics, Northwestern Polytechnical University, Xi'an 710129, China;
2 MIIT Key Laboratory of Dynamics and Control of Complex Systems, Xi'an 710129, China;
3 Shanghai Engineering Research Center of Physical Vapor Deposition (PVD) Superhard Coating and Equipment, Shanghai Institute of Technology, Shanghai 201418, China

Received:2025-07-11 Revised:2025-09-29 Accepted:2025-09-30 Published:2025-12-10
Contact: Honghui Zhang E-mail:haozhucy@nwpu.edu.cn
Supported by:
This project was supported by the National Natural Science Foundation of China (Grant Nos. 12372064 and 12172291) and the Youth and Middle-Aged Science and Technology Development Program of Shanghai Institute of Technology (Grant No. ZQ2024-10).

摘要/Abstract

摘要： Conventional open-loop deep brain stimulation (DBS) systems with fixed parameters fail to accommodate inter-individual pathological differences in Parkinson’s disease (PD) management while potentially inducing adverse effects and causing excessive energy consumption. In this paper, we present an adaptive closed-loop framework integrating a Yogi-optimized proportional-integral-derivative neural network (Yogi-PIDNN) controller. The Yogi-augmented gradient adaptation mechanism accelerates the convergence of general PIDNN controllers in high-dimensional nonlinear control systems while reducing control energy usage. In addition, a system identification method establishes input-output dynamics for pre-training stimulation waveforms, bypassing real-time parameter-tuning constraints and thereby enhancing closed-loop adaptability. Finally, a theoretical analysis based on Lyapunov stability criteria establishes a sufficient condition for closed-loop stability within the identified model. Computational validations demonstrate that our approach restores thalamic relay reliability while reducing energy consumption by (81.0 ±0.7)% across multi-frequency tests. This study advances adaptive neuromodulation by synergizing data-driven pre-training with stability-guaranteed real-time control, offering a novel framework for energy-efficient and personalized Parkinson’s therapy.

关键词: Parkinson’s disease, closed-loop deep brain stimulation, PID neural network, adaptive control

Abstract: Conventional open-loop deep brain stimulation (DBS) systems with fixed parameters fail to accommodate inter-individual pathological differences in Parkinson’s disease (PD) management while potentially inducing adverse effects and causing excessive energy consumption. In this paper, we present an adaptive closed-loop framework integrating a Yogi-optimized proportional-integral-derivative neural network (Yogi-PIDNN) controller. The Yogi-augmented gradient adaptation mechanism accelerates the convergence of general PIDNN controllers in high-dimensional nonlinear control systems while reducing control energy usage. In addition, a system identification method establishes input-output dynamics for pre-training stimulation waveforms, bypassing real-time parameter-tuning constraints and thereby enhancing closed-loop adaptability. Finally, a theoretical analysis based on Lyapunov stability criteria establishes a sufficient condition for closed-loop stability within the identified model. Computational validations demonstrate that our approach restores thalamic relay reliability while reducing energy consumption by (81.0 ±0.7)% across multi-frequency tests. This study advances adaptive neuromodulation by synergizing data-driven pre-training with stability-guaranteed real-time control, offering a novel framework for energy-efficient and personalized Parkinson’s therapy.

Key words: Parkinson’s disease, closed-loop deep brain stimulation, PID neural network, adaptive control

中图分类号: (Neural networks, fuzzy logic, artificial intelligence)

07.05.Mh

87.19.lj (Neuronal network dynamics) 87.19.lr (Control theory and feedback) 87.85.dq (Neural networks)

Hengxi Zhang(张恒熙), Honghui Zhang(张红慧), Shuang Liu(柳爽), and Lin Du(都琳). Optimized PID neural network closed-loop control for basal ganglia network in Parkinson’s disease[J]. 中国物理B, 2025, 34(12): 120701-120701.

参考文献

[1] Benabid A L 2003 Curr. Opin. Neurobiol. 13 696
[2] Okun M S 2012 N. Engl. J. Med. 367 1529
[3] Hariz M and Blomstedt P 2022 J. Intern. Med. 292 764
[4] Limousin P and Foltynie T 2019 Nat. Rev. Neurol. 15 234
[5] Lozano A M, Lipsman N, Bergman H, et al. 2019 Nat. Rev. Neurol. 15 148
[6] Guidetti M, Marceglia S, Loh A, Harmsen I E, Meoni S, Foffani G, Lozano A M, Moro E, Volkmann J and Priori A 2021 Brain Stimul. 14 1238
[7] Bouthour W, Mégevand P, Donoghue J, Lüscher C, Birbaumer N and Krack P 2019 Nat. Rev. Neurol. 15 343
[8] Krauss J K, Lipsman N, Aziz T, Boutet A, Brown P, Chang JW, Davidson B, Grill W M, Hariz M I and Horn A 2021 Nat. Rev. Neurol. 17 75
[9] Rosa M, Arlotti M, Ardolino G, Cogiamanian F, Marceglia S, Di Fonzo A, Cortese F, Rampini P M and Priori A 2015 Mov. Disord. 30 1003
[10] Gorzelic P, Schiff S and Sinha A 2013 J. Neural Eng. 10 026016
[11] Chen L, Jiang W, Bin D, et al. 2016 IEEE Trans. Neural Syst. Rehabil. Eng. 24 1109
[12] Coronel-Escamilla A, Gomez-Aguilar J F, Stamova I and Santamaria F 2020 Chaos Solitons Fractals 140 110149
[13] Liu C, Zhao G, Meng Z, et al. 2021 Cogn. Neurodyn. 15 1157
[14] Fleming J E, Dunn E and Lowery M M 2020 Front. Neurosci. 14 166
[15] Shu H and Pi Y 2000 Comput. Chem. Eng. 24 859
[16] Zeng G Q, Xie X Q, ChenMR andWeng J 2019 Swarm Evol. Comput. 44 320
[17] Ding J, WuMand XiaoM2022 IEEE Trans. Neural Netw. Learn. Syst. 35 8715
[18] Psaltis D, Sideris A and Yamamura A A 1988 IEEE Control Syst. Mag. 8 17
[19] Yang H and Liu J 2018 IEEECAA J. Autom. Sin. 5 457
[20] Liu Y J, Zeng Q, Tong S, Chen C P and Liu L 2019 IEEE Trans. Ind. Electron. 66 9458
[21] Liu Y J, Zhao W, Liu L, Li D, Tong S and Chen C P 2021 IEEE Trans. Neural Netw. Learn. Syst. 34 2732
[22] Khan S, Khan F, Sikander Q U A, Alam M M and Su’Ud M M 2021 IEEE Access 9 136929
[23] Liu C, Zhao G, Wang J, Wu H, Li H, Fietkiewicz C and Loparo K A 2020 IEEE Access 8 161067
[24] Wang K, Wang J, Zhu Y, Li H, Liu C, Fietkiewicz C and Loparo K A 2022 Biomed. Signal Process. Control 77 103776
[25] Zaheer M, Reddi S, Sachan D, Kale S and Kumar S 2018 Adv. Neural Inf. Process. Syst. 31
[26] Kingma D P 2014 arXiv:1412.6980
[27] Abdulkadirov R, Lyakhov P, Bergerman M and Reznikov D 2024 Chaos Solitons Fractals 179 114432
[28] Chang Z, Zhang Y and Chen W 2019 Energy 187 115804
[29] Böttcher L, Antulov-Fantulin N and Asikis T 2022 Nat. Commun. 13 333
[30] So R Q, Kent A R and Grill W M 2012 J. Comput. Neurosci. 32 499
[31] Terman D, Rubin J E, Yew A and Wilson C 2002 J. Neurosci. 22 2963
[32] Rubin J E and Terman D 2004 J. Comput. Neurosci. 16 211
[33] Liu C, Wang J, Li H, Lu M, Deng B, Yu H, Wei X, Fietkiewicz C and Loparo K A 2016 IEEE Trans. Neural Netw. Learn. Syst. 28 371
[34] Schiff S J 2010 Philos. Trans. R. Soc. A 368 2269
[35] Lu M, Wei X, Che Y, Wang J and Loparo K A 2019 IEEE Trans. Neural Syst. Rehabil. Eng. 28 339
[36] Feng X J, Shea-Brown E, Greenwald B, Kosut R and Rabitz H 2007 J. Comput. Neurosci. 23 265
[37] Lin N, Chi R and Huang B 2020 Appl. Math. Model. 81 787
[38] Glorot X and Bengio Y 2010 Proc. 13th Int. Conf. Artif. Intell. Stat. (JMLR Workshop and Conference Proceedings) pp. 249–256
[39] Birdno M J and Grill W M 2008 Neurotherapeutics 5 14
[40] Zhao T, Faustino B L, Jagatheesaperumal S K, Rolim F d P S and de Albuquerque V H C 2025 Expert Syst. Appl. 267 126154
[41] Holgado A J N, Terry J R and Bogacz R 2010 J. Neurosci. 30 12340
[42] Liu C, Wang J, Yu H, Deng B, Wei X, Li H, Loparo K A and Fietkiewicz C 2015 Commun. Nonlinear Sci. Numer. Simul. 28 10
[43] Yu Y, Wang X, Wang Q and Wang Q 2020 Appl. Math. Mech. 41 1747
[44] Kumaravelu K, Brocker D T and GrillWM 2016 J. Comput. Neurosci. 40 207
[45] Yu Y and Wang Q 2019 Nonlinear Dyn. 98 1065

Optimized PID neural network closed-loop control for basal ganglia network in Parkinson’s disease

Optimized PID neural network closed-loop control for basal ganglia network in Parkinson’s disease

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	Ximing Wang(王希铭), Jinsheng Sun(孙金生), Zhitao Li(李志韬), and Zixing Wu(吴梓杏). Memory-augmented adaptive flocking control for multi-agent systems subject to uncertain external disturbances[J]. 中国物理B, 2022, 31(2): 20203-020203.
[2]	杨宁宁, 韩宇超, 吴朝俊, 贾嵘, 刘崇新. Dynamic analysis and fractional-order adaptive sliding mode control for a novel fractional-order ferroresonance system[J]. 中国物理B, 2017, 26(8): 80503-080503.
[3]	张翔, 王金环, 杨德东, 徐勇. Tracking consensus for nonlinear heterogeneous multi-agent systems subject to unknown disturbances via sliding mode control[J]. 中国物理B, 2017, 26(7): 70501-070501.
[4]	高士根, 董海荣, 宁滨, Roberts Clive, 陈磊, 孙绪彬. Cooperative adaptive bidirectional control of a train platoon for efficient utility and string stability[J]. 中国物理B, 2015, 24(9): 90506-090506.
[5]	王乔, 丁冬生, 齐冬莲. Mittag-Leffler synchronization of fractional-order uncertain chaotic systems[J]. 中国物理B, 2015, 24(6): 60508-060508.
[6]	魏伟. Synchronization of coupled chaotic Hindmarsh Rose neurons: An adaptive approach[J]. 中国物理B, 2015, 24(10): 100503-100503.
[7]	高士根, 董海荣, 孙绪彬, 宁滨. Neural adaptive chaotic control with constrained input using state and output feedback[J]. , 2015, 24(1): 10501-010501.
[8]	Muhammad Riaz, Muhammad Rehan, Keum-Shik Hong, Muhammad Ashraf, Haroon Ur Rasheed. Static and adaptive feedback control for synchronization of different chaotic oscillators with mutually Lipschitz nonlinearities[J]. 中国物理B, 2014, 23(11): 110502-110502.
[9]	李科赞, 何恩, 曾朝蓉, 谢智刚. Generalized projective synchronization of two coupled complex networks with different sizes[J]. 中国物理B, 2013, 22(7): 70504-070504.
[10]	王树国, 郑松. Adaptive function projective synchronization of uncertain complex dynamical networks with disturbance[J]. 中国物理B, 2013, 22(7): 70503-070503.
[11]	于海涛, 王江, 邓斌, 魏熙乐, 陈颖源. Adaptive synchronization control of coupled chaotic neurons in the external electrical stimulation[J]. 中国物理B, 2013, 22(5): 58701-058701.
[12]	李宁, 袁惠群, 孙海义, 张庆灵. Adaptive control of bifurcation and chaos in a time-delayed system[J]. 中国物理B, 2013, 22(3): 30508-030508.
[13]	张若洵, 杨世平. A single adaptive controller with one variable for synchronization of fractional-order chaotic systems[J]. 中国物理B, 2012, 21(8): 80505-080505.
[14]	戴浩, 贾立新, 张彦斌. Adaptive generalized matrix projective lag synchronization between two different complex networks with non-identical nodes and different dimensions[J]. Chin. Phys. B, 2012, 21(12): 120508-120508.
[15]	姚洪兴, 王树国 . Cluster projective synchronization of complex networks with nonidentical dynamical nodes[J]. 中国物理B, 2012, 21(11): 110506-110506.