基于BP神经网络的旋转血泵生理控制

doi:10.3969/j.issn.0258-8021.2019.05.009

摘要
图/表
参考文献
相关文章 (9)

全文: PDF (1120 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要提出一种基于BP神经网络的旋转血泵生理控制方法,实现血泵植入者生理状态变化下控制器的自适应调节。控制器以临床主动脉平均压100 mmHg作为控制目标,利用神经网络自动学习的特性,采用3层神经网络在循环系统生理状态发生变化时在线调优血泵PID控制器的参数。该控制方法在血液循环系统数学模型中进行数值模拟验证,分别在模拟左心室衰竭、体循环阻力发生生理变化以及左心室收缩能力动态变化等条件下,接入改进后的PID控制器控制血泵转速,使循环系统中主动脉压力达到设定的正常值。结果表明,在上述多种不同的生理状态下,基于BP神经网络改进后的PID控制器均可以克服扰动,在经过约150 s调整时间后达到主动脉平均压100 mmHg的控制目标,并且稳态误差为零。该控制方法可以适应循环系统多种生理状态的变化,为后续的体外和动物试验提供有效的旋转血泵控制方法。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	朱卓玲
	赵伟国
	黄峰

关键词 ：血泵, BP神经网络, PID, 生理控制

Abstract：In this study, a physiological controller of rotary blood pumps based on BP neural networks was proposed, which realized the adaptive adjustment of the controller while the states of the recipients are changing. Choosing the mean arterial pressure as the control object, the controller adopted a three-layer neural network to optimize the PID parameters of the blood pump controller online when the physiological state of the circulatory system changed. This method was verified numerically on the mathematical model of blood circulation system. The controller was carried out under different conditions including left ventricle failure, physiological changing in systemic resistance and dynamic changing in left ventricular contractility. Results showed that in all of the cases the BP neural network based controller could overcome the disturbances well and the mean arterial pressure was stabilized at 100 mmHg after about 150 s since the controller took effect, with the steady-state error of 0 mmHg. This control method could adapt to the changes of various physiological states of the circulatory system and provide an effective control method of rotary blood pump for the subsequent in vitro and animal experiments.

Key words： blood pump BP neural networks PID physiological control

收稿日期: 2018-03-28

PACS:

R318

基金资助:国家自然科学基金青年基金(51505455); 流体动力与机电系统国家重点实验室开放基金(GZKF-201713); 浙江省仪器科学与技术重中之重学科开放基金资助(JL150515)

通讯作者: E-mail: hf@cjlu.edu.cn

引用本文:

朱卓玲, 赵伟国, 黄峰. 基于BP神经网络的旋转血泵生理控制[J]. 中国生物医学工程学报, 2019, 38(5): 581-589.
Zhu Zhuoling, Zhao Weiguo, Huang Feng. Physiological Control of Rotary Blood Pumps Based on BP Neural Networks. Chinese Journal of Biomedical Engineering, 2019, 38(5): 581-589.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2019.05.009 或 http://cjbme.csbme.org/CN/Y2019/V38/I5/581

[1] 黄智才,谭建平,程立志,等. 基于血泵转速与功率特性曲线的流量压力控制[J]. 测控技术,2015,34(12):54-57.
[2] 王芳群, 徐庆, 吴振海,等. 基于左心辅助的血液循环系统的控制研究[J]. 生物医学工程学杂志, 2016,33(6):1075-1083.
[3] 杨磊,杨明,许自豪,等. 基于自整定模糊PI算法的磁耦合离心血泵控制研究[J]. 生物医学工程学杂志,2014, 31(5):1050-1056.
[4] Huang Feng, Ruan Xiaodong, Fu Xin. Pulse-pressure-enhancing controller for better physiologic perfusion of rotary blood pumps based on speed modulation [J]. 2014, 60(3):269-279.
[5] Tarcísio L, Fonseca J, Andrade A, et al. Left ventricle failure and blood flow estimation for centrifugal blood pumps [J]. 机械工程与自动化(英文版), 2016(3):162-166.
[6] Ng BC, Salamonsen RF, Gregory SD, et al. Application of multiobjective neural predictive control to biventricular assistance using dual rotary blood pumps [J]. Biomedical Signal Processing & Control, 2018, 39:81-93.
[7] Petrou A, Monn M, Meboldt M, et al. A novel multi-objective physiological control system for rotary left ventricular assist devices [J]. Annals of Biomedical Engineering, 2017,45(12):1-12.
[8] Boston JR, Antaki JF, Simaan MA. Hierarchical control of heart-assist devices [J]. Robotics & Automation Magazine IEEE, 2003, 10(1):54-64.
[9] Haykin Simon. 神经网络与机器学习[M]. 北京: 机械工业出版社, 2017:572.
[10] Colacino FM, Moscato F, Piedimonte F, et al. Left ventricle load impedance control by apical VAD can help heart recovery and patient perfusion: A numerical study [J]. ASAIO, 2007, 53(3):263-277.
[11] Toy SM, Melbin J, Noordergraaf A. Reduced models of arterial systems [J]. IEEE Transactions on Biomedical Engineering, 1985, 32(2):174-176.
[12] Newman BJ. Circulatory physiology: Cardiac output and its regulation [J]. American Journal of Cardiology, 1974, 33(7):935-935.
[13] Sun Y, Sjöberg BJ, Ask P, et al. Mathematical model that characterizes transmitral and pulmonary venous flow velocity patterns [J]. American Journal of Physiology, 1995, 268(37):476-489.
[14] Choi S, Boston JR, Thomas D, et al. Modeling and identification of an axial flow blood pump [C] // Proceedings of the American Control Conference. Albuquerque: IEEE, 1997: 3714-3715.
[15] 何正风. MATLAB R2015b神经网络技术[M]. 北京: 清华大学出版社,2016: 404.
[16] 刘金琨. 先进PID控制Matlab仿真[M]. 北京:电子工业出版社, 2005.
[17] Ochsner G, Amacher R, Amstutz A. A novel interface for hybrid mock circulations to evaluate ventricular assist devices [J]. IEEE Transactions on Biomedical Engineering, 2013, 60(2):507-516.
[18] 王庭槐. 生理学[M]. 北京: 人民卫生出版社, 2015:161-175.
[19] Ferreira A, Boston JR, Antaki JF. A control system for rotary blood pumps based on suction detection [J]. IEEE Transactions on Biomedical Engineering, 2009, 56(3):656-665.
[20] Bakouri MA, Salamonsen RF, Savkin AV, et al. Physiological control of implantable rotary blood pumps for heart failure patients [C] // The 35th Annual International Conference of the IEEE EMBS. Osaka: IEEE, 2013: 675-678.
[21] Petrou A, Ochsner G, Amacher R, et al. A physiological controller for turbodynamic ventricular assist devices based on left ventricular systolic pressure [J]. Artificial Organs, 2016, 40(9):842-855.