基于心率的神经网络最小参数血泵滑模控制

doi:10.16182/j.issn1004731x.joss.201805022

系统仿真学报 ›› 2018, Vol. 30 ›› Issue (5): 1796-1802.doi: 10.16182/j.issn1004731x.joss.201805022

基于心率的神经网络最小参数血泵滑模控制

刘慧博, 刘木

内蒙古科技大学信息工程学院,内蒙古包头 014010

收稿日期:2016-05-25 修回日期:2016-07-27 出版日期:2018-05-08 发布日期:2019-01-03
作者简介:刘慧博(1972-),女,内蒙古包头,博士,副教授,研究方向为智能控制与导航制导;刘木(1991-),女,河北秦皇岛,硕士生,研究方向为智能控制理论与应用。
基金资助:
国家自然科学基金(61563041),内蒙古自然科学基金(2015MS0603)

Neural Network Minimun Parameter Sliding Control of Blood Pump Based on Heart Rate

Liu Huibo, Liu Mu

School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou 014010, China

Received:2016-05-25 Revised:2016-07-27 Online:2018-05-08 Published:2019-01-03

摘要/Abstract

摘要： 设计一种智能算法,控制分体式血泵辅助自然心脏搏血,满足血液灌注需求。此算法结合了不依赖对象模型的滑模控制和具有最佳逼近特性的RBF神经网络设计控制器,并采用最小参数学习法设计自适应律,调整神经网络权值。为保证实时性,转速信号由血流量、血泵转速与心率的函数关系给定。通过与PID算法的对比研究表明：在RBF滑模控制下,血泵转速最大调节时间为0.23 s,稳态误差为5rpm,流量最大相对误差为0.89%,系统动静态性能良好,故RBF神经网络最小参数滑模控制算法充分满足血泵控制要求。

关键词: 血泵, 滑模, RBF神经网络, 最小参数法, 心率

Abstract: An intelligent algorithm is designed to control the blood pump to assist natural cardiac blood pumping and to meet the needs of blood perfusion. The algorithm combines sliding mode control which does not depend on object model and RBF neural network which has optimal approximation properties to design controller. Minimum parameter learning method is used to design the adaptive law, adjust the weights of neural network. In order to ensure the real time, the speed signal is given by the function of blood flow, blood pump speed and heart rate. Through comparing with PID algorithm, the research shows that: under the RBF sliding mode control, the biggest blood pump speed regulating time is 0.23 s, steady-state error is 5 RPM, flow maximum relative error is 0.89%, both dynamic and static performance of this system is good, so the minimum parameters of RBF neural network sliding mode control algorithm fully meets the requirements of the blood pump control system.

Key words: blood pump, sliding mode, RBF neural network, minimum parameter algorithm, heart rate

中图分类号:

TP391.9

刘慧博, 刘木. 基于心率的神经网络最小参数血泵滑模控制[J]. 系统仿真学报, 2018, 30(5): 1796-1802.

Liu Huibo, Liu Mu. Neural Network Minimun Parameter Sliding Control of Blood Pump Based on Heart Rate[J]. Journal of System Simulation, 2018, 30(5): 1796-1802.

参考文献

[1] 高斌. 面向心功能恢复的人工心脏泵分层控制策略研究[D]. 北京: 北京工业大学, 2013.
Gao Bin.Study on the hierarchical control strategy of artificial heart pump for cardiac function recovery [D].Beijing: Beijing university of technology, 2013.
[2] G A Giridharan, G M Pantalos, K J Gillars, et al.Physiologic Control of Rotary Blood Pumps: An in Vitro Study[J]. Asaio Journal (S1058-2916), 2004, 50(5): 403-409.
[3] F Casas, A Orozco, W A Smith, et al.A Fuzzy System Cardio Pulmmonary Bypass Rotary Pump Controller[J]. Expert Sys Appl (S0957-4174), 2012, 26: 357-361.
[4] 谷凯云, 常斌, 高宇. 基于心率的主动脉血泵流量控制[J]. 中国组织工程研究与临床康复, 2011, 15(13): 2390-2393.
Gu Kaiyun, Chang Bin, Gao Yu.Flow control of aortic blood pump based on heart rate[J]. China tissue engineering research and clinical rehabilitation, 2011, 15(13): 2390-2393.
[5] Chang Yu, Gao Bin.Modeling and identification of an intra- aorta pump[J]. Asaio J (S1058-2916), 2010, 56(6): 504-509.
[6] 王贞艳, 张井岗, 陈志梅. 神经网络滑模变结构控制研究综述[J]. 信息与控制, 2005, 34(4): 451-455.
Wang Zhenyan, Zhang Jinggang, Chen Zhimei.Research review on the structural control of neural network sliding mode[J]. Information and control, 2005, 34(4): 451-455.
[7] C S Hayward, R Salamonsen, A M Keogh, et al.Effect of Alter-ation in Pump Speed on Pump Output and Left Ventricular Filling with Continuous-flow Left Ventricular Assist Device[J]. Asaio J (S1058-2916), 2011, 57: 495-500.
[8] 轩艳姣, 常宇. 基于两级级联神经网络估计血泵转速及压力变化对血流量的影响[J]. 中国组织工程研究与临床康复, 2011, 15(9): 1631-1634.
Xuan Yanjiao, Chang Yu.Based on the estimation of the influence of blood pump speed and pressure changes on blood flow based on the two-level cascade neural network[J]. China tissue engineering research and clinical rehabilitation, 2011, 15(9): 1631-1634.
[9] 陆柳, 李景锡. 心率对每搏输出量和心输出量影响的讨论[J]. 中国医学物理学杂志, 2002, 19(4): 237-238.
Lu Liu, Li Jingxi.Discussion on the influence of heart rate on output of each stroke and cardiac output[J]. Journal of Chinese medical physics, 2002, 19(4): 237-238.
[10] Steven G Chopski, Carson S Fox, Kell L McKenna, et al. Physics-driven Impeller Designs for a Novel Intravascular Blood Pump for patients with Congenital Heart Disease Original Research Article[J]. Medical Engineering & Physics (S1350-4533), 2016, 7(38): 622-632.
[11] 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.
Huang Zhicai, Tan Jianping, Cheng Lizhi, et al.Flow pressure control based on blood pump speed and power characteristic curve[J]. Measurement and control technology, 2015, 34(12): 54-57.
[12] 夏长亮. 无刷直流电机控制系统[M]. 北京: 科学出版社, 2009.
Xia Changliang.Brushless dc motor control system [M]. Beijing: Science Press, 2009.
[13] Weissler A M, Harris W S, Schoenfeld C D.Systolic time in intervals in heart failure in man[J]. Circulation (S0009-7322), 1986, 37: 149-153.
[14] Boston J R, Antika J F, Siman M A.Hierarchical control of heart-assist devices[J]. IEEE Robot Autom Mag (S1070-9932), 2003; 10(1): 54-64.
[15] 封志刚, 曾培, 茹伟民, 等. 人工心脏输出流量和压力的神经网络估算法[J]. 中国生物医学工程学报, 2002, 21(6): 568-571.
Feng Zhigang, Zeng Pei, Ru Weimin, et al.Neural network estimation of artificial cardiac output flow and pressure[J]. Journal of Chinese biomedical engineering, 2002, 21(6), 568-571.
[16] Hyeung sik C, Yong-heon P, Yongsung C, et al. Global sliding-mode control-Improved design for a brushless DC motor[J]. IEEE Contr Syst Mag (S1066-033X), 2001, 21(3): 27-35.
[17] 苗卓广, 谢寿生, 丁键, 等. 基于RBF网络的航空发动机预测滑模控制[J]. 北京航空航天大学学报. 2013, 39(12): 1601-1606.
Miao Zhuguang, Xie Shousheng, Ding Jian, et al.Based on RBF network, aeroengine prediction of slide mode control[J]. Journal of Beijing university of aeronautics and astronautics, 2013, 39(12): 1601-1606.
[18] 刘金琨. 智能控制[M]. 北京: 电子工业出版社, 2006.
Liu Jinkun.Intelligent control [M]. Beijing: electronic industry press, 2006.
[19] 刘金琨. 滑模变结构控制Matlab仿真[M]. 北京: 清华大学出版社, 2005.
Liu Jinkun.Sliding mode variable structure control Matlab[M]. Beijing: Tsinghua University Press, 2005.
[20] LIU Jin-kun, SUN Fu-chun.Nominal Model-Based Sliding Mode Control with Backstepping for 3-Axis Flight[J]. Chinese Journal of Aeronautics (S1000-9361), 2006, 19(1): 65-71.

基于心率的神经网络最小参数血泵滑模控制

Neural Network Minimun Parameter Sliding Control of Blood Pump Based on Heart Rate

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	杜宝林, 朱大昌, 盘意华. 机械臂模糊超螺旋二阶滑模轨迹跟踪控制[J]. 系统仿真学报, 2022, 34(6): 1343-1352.
[2]	赵静, 王鹏, 丁筱茜, 蒋国平, 徐丰羽, 孙雁飞. 基于观测器的四旋翼容错控制及仿真研究[J]. 系统仿真学报, 2022, 34(1): 1-10.
[3]	张瑞民, 陈巧玉. 基于光滑二阶滑模的机械臂轨迹跟踪控制[J]. 系统仿真学报, 2021, 33(6): 1315-1322.
[4]	王伟, 陈志梅, 王贞艳. 直角坐标机器人补偿滑模交叉耦合控制研究[J]. 系统仿真学报, 2021, 33(4): 867-874.
[5]	马立新, 朱勇杰, 季乐延. 神经网络优化的无感永磁同步电机控制系统[J]. 系统仿真学报, 2021, 33(3): 622-630.
[6]	司玉洁, 熊华, 李喆. 拦截机动目标的三维自适应神经网络制导律[J]. 系统仿真学报, 2021, 33(2): 453-460.
[7]	范存礼, 戴娟, 刘海涛, 苏中, 朱翠, 徐文婷. 基于神经网络与分数阶滑模的行星进入段轨迹跟踪控制[J]. 系统仿真学报, 2021, 33(11): 2697-2703.
[8]	李中奇, 邢月霜. 动车组进站过程精准停车控制方法研究[J]. 系统仿真学报, 2021, 33(1): 149-158.
[9]	张鑫, 李嘉欣. 基于分数阶微积分的机械臂滑模控制的研究[J]. 系统仿真学报, 2020, 32(5): 911-917.
[10]	黄小琴, 陈力. 双柔臂空间机器人运动、振动一体化抗死区控制[J]. 系统仿真学报, 2020, 32(3): 430-437.
[11]	韩凯伟, 王艳, 纪志成. 一种直线感应电机的新型积分滑模控制器的设计与仿真[J]. 系统仿真学报, 2020, 32(11): 2146-2154.
[12]	米根锁, 梁骅旗. 基于干扰观测器的机械臂非线性滑模控制[J]. 系统仿真学报, 2019, 31(9): 1935-1941.
[13]	侯利民, 任一夫, 刘恒飞, 林栋. 基于无速度传感器的永磁同步电机滑模自抗扰控制[J]. 系统仿真学报, 2019, 31(5): 963-970.
[14]	王丹力, 杨心盼, 岳康, 胡海琛. 基于ECG的立体3D显示视疲劳的评估和建模[J]. 系统仿真学报, 2019, 31(2): 212-217.
[15]	刘晓岑, 吴云洁, 徐鹏. 考虑输入饱和的高超声速飞行器姿态控制[J]. 系统仿真学报, 2019, 31(11): 2553-2561.