基于模糊逻辑算法的智能膝关节假肢步态相位识别

doi:10.3969/j.issn.1006-9771.2023.08.005

《中国康复理论与实践》 ›› 2023, Vol. 29 ›› Issue (8): 896-902.doi: 10.3969/j.issn.1006-9771.2023.08.005

• 专题运动和平衡功能康复 • 上一篇下一篇

基于模糊逻辑算法的智能膝关节假肢步态相位识别

张意彬¹^,², 吕杰¹, 喻洪流²()

1.上海健康医学院医疗器械学院，上海市 201318
2.上海理工大学健康科学与工程学院，上海市 200093

收稿日期:2023-03-20 修回日期:2023-06-26 出版日期:2023-08-25 发布日期:2023-10-09
通讯作者: 喻洪流 E-mail:yhl98@hotmail.com
作者简介:张意彬(1979-)，男，蒙古族，内蒙古赤峰市人，硕士，主要研究方向：康复工程。
基金资助:
国家自然科学基金项目(62073224)

Gait phase recognition in intelligent above-knee prosthesis based on fuzzy logic algorithm

ZHANG Yibin¹^,², LÜ Jie¹, YU Hongliu²()

1. Medical Instruments Institute, Shanghai University of Medicine & Health Sciences, Shanghai 201318, China
2. School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

Received:2023-03-20 Revised:2023-06-26 Published:2023-08-25 Online:2023-10-09
Contact: YU Hongliu E-mail:yhl98@hotmail.com
Supported by:
National Natural Science Foundation of China(62073224)

摘要/Abstract

摘要：

目的针对智能膝关节假肢控制策略切换的需要，以人体行走的足底压力为研究对象，以模糊逻辑算法为基础，提出一种基于假肢足底压力信息的步态相位划分方法。
方法利用安装在假脚足底的3个薄膜压力传感器采集测试对象在3种不同行走模式(平路行走、下坡行走、下楼行走)下的足底压力信息，经数据融合处理后，送入模糊逻辑控制器，建立IF-THEN规则，通过调整灵敏度系数A_i以及比例系数B_i，输出识别结果。
结果经过对5例健康人的模拟测试，平路行走、下楼行走和下坡行走的步态相位识别准确率分别为(95.3±2.4)%、(81.5±6.3)%和(90.7±3.5)%。
结论最终的识别准确率满足使用需求，该方法可以在智能膝关节假肢的步态相位识别中应用。

关键词: 膝关节假肢, 步态检测, 足底反力, 模糊逻辑, 步态相位

Abstract:

Objective Aiming at the need of control strategy switching of intelligent above-knee prosthetic, taking the plantar pressure of human walking as the research object, and based on fuzzy logic algorithm, a gait phase division method based on plantar pressure of prosthetic is proposed.
Methods Three flexible force sensors installed on the soles of the false feet were used to collect the plantar pressure information of the test object under three different walking modes (walking on the flat road, walking downhill and walking down the stairs). After data fusion processing, it was sent to the fuzzy logic controller, and the recognition results were output according to the IF-THEN rule, the scale and sensitivity factor.
Results Through the testing of five healthy people as substitute, the results showed that the accuracy of gait phase recognition for walking on the flat road, walking down the stairs and walking downhill were (95.3±2.4)%, (81.5±6.3)% and (90.7±3.5)%, respectively.
Conclusion The accuracy of recognition basically meets the requirements in this project. This method can be applied in the gait phase recognition of intelligent above-knee prosthetic.

Key words: above-knee prostheses, gait detection, ground reaction force, fuzzy logic, gait phase

中图分类号:

R496

张意彬, 吕杰, 喻洪流. 基于模糊逻辑算法的智能膝关节假肢步态相位识别[J]. 《中国康复理论与实践》, 2023, 29(8): 896-902.

ZHANG Yibin, LÜ Jie, YU Hongliu. Gait phase recognition in intelligent above-knee prosthesis based on fuzzy logic algorithm[J]. 《Chinese Journal of Rehabilitation Theory and Practice》, 2023, 29(8): 896-902.

图/表 10

图1

图2

图3

图4

表1

图5

表2

图6

图7

图8

参考文献 16

[1]	MIYAKE T, YAMAMOTO S, HOSONO S, et al. Gait phase detection based on muscle deformation with static standing-based calibration[J]. Sensors, 2021, 21(4): 1081. doi: 10.3390/s21041081
[2]	PINHEY S R, MURATA H, HISANO G, et al. Effects of walking speed and prosthetic knee control type on external mechanical work in transfemoral prosthesis users[J]. J Biomech, 2022, 134: 110984. doi: 10.1016/j.jbiomech.2022.110984
[3]	ALVES A, ANDRIETTA L T, LOPES R Z, et al. Integrating audio signal processing and deep learning algorithms for gait pattern classification in brazilian gaited horses[J]. Front Genet, 2021, 2: 681557.
[4]	罗鸿, 刘方, 李顺华, 等. 步态分析应用在前交叉韧带损伤诊断中的意义[J]. 中国组织工程研究, 2019, 23(31): 4969-4973.
	LUO H, LIU F, LI S H, et al. Significance of gait analysis in the diagnosis of anterior cruciate ligament injury[J]. Chin J Tissue Engineer Res, 2019, 23(31): 4969-4973.
[5]	APOORVA G, KEE M, YUSUF O, et al. Extraction and analysis of respiratory motion using wearable inertial sensor system during trunk motion[J]. Sensors, 2017, 17(12): 1-25. doi: 10.3390/s17010001
[6]	黄悦, 余洪俊, 谭小丹, 等. 运用步态分析系统评估下肢康复机器人对脑卒中偏瘫患者步态的临床疗效[J]. 现代医药卫生, 2022, 38(24): 4190-4194.
	HUANG Y, YU H J, TAN X D, et al. Evaluation of the clinical efficacy of lower limb rehabilitation robot on gait of stroke patients with hemiplegia by gait analysis system[J]. J Modern Med Health, 2022, 38(24): 4190-4194.
[7]	EIZENTALS P, KATASHEV A, OKSS A. Gait partitioning with smart socks system[C]. Society Integration Education Proceedings of the International Scientific Conference, 2019: 134.
[8]	DONG D B, MA C, WANG M, et al. A low-cost framework for the recognition of human motion gait phases and patterns based on multi-source perception fusion[J]. Eng Appl Artif Intell, 2023, 120: 105886. doi: 10.1016/j.engappai.2023.105886
[9]	FEI G, LIU G, LIANG F, et al. IMU-based locomotion mode identification for transtibial prostheses, orthoses, and exoskeletons[J]. IEEE Trans Neural Syst Rehabil Eng, 2020, 28(6): 1334-1343. doi: 10.1109/TNSRE.7333
[10]	WEI F, CRECHIOLO A, HAUT R C. Prediction of ground reaction forces in level and incline/decline walking from a multistage analysis of plantar pressure data[J]. J Biomech, 2018, 6(8): 698-707.
[11]	喻洪流, 张意彬, 商怀超, 等.可调仿真膝关节步态数据采集系统及其方法:2018102718039[P]. 2020-10-09.
[12]	张意彬, 吕杰, 喻洪流. 一种智能膝关节假肢及其控制算法研究[J]. 现代仪器与医疗, 2022, 28(6): 19-27.
	ZHANG Y B, LÜ J, YU H L. Research on an intelligent above-knee prosthesis and its control algorithm[J]. Modern Instrum Med Treat, 2022, 28(6): 19-27.
[13]	李根. 基于MATLAB的模糊逻辑控制系统设计[J]. 机电信息, 2020(6): 72-73.
	LI G. Design of fuzzy logic control system based on MATLAB[J]. Mech Electr Inform, 2020(6): 72-73.
[14]	SAVELBERG H H, DE LANGE A L. Assessment of the horizontal, fore-aft component of the ground reaction force from insole pressure patterns by using artificial neural networks[J]. Clin Biomech, 1999, 14(8): 585-592. doi: 10.1016/S0268-0033(99)00036-4
[15]	MANGOLIKA B, PAT O, MARK S, et al. Use of artificial neural networks in the design of adaptive fuzzy logic controllers in the manufacturing of prosthetic knees[J]. Procedia Computer Sci, 2023, 218: 2820-2829. doi: 10.1016/j.procs.2023.01.253
[16]	张意彬, 李剑峰, 喻洪流. 一种智能膝关节假肢及其步态对称性评价[J]. 中国康复理论与实践, 2023, 29(4): 402-407. doi: 10.3969/j.issn.1006-9771.2023.04.005
	ZHANG Y B, LI J F, YU H L. A microprocessor-controlled prosthetic knee and its gait symmetry assessment[J]. Chin J Rehabil Theory Pract, 2023, 29(4): 402-407.

步态相位	FSR₁	FSR₂	FSR₃
HS	weak	weak	strong
MS	strong	strong	strong
PSw	strong	strong	weak
Sw	weak	weak	weak

编号	性别	年龄/岁	身高/m	体质量/kg	大腿长/m	小腿长/m	步幅/m
1	男	53	1.70	70	0.42	0.48	0.63
2	男	43	1.65	61	0.40	0.47	0.61
3	男	29	1.78	75	0.44	0.51	0.66
4	女	41	1.52	55	0.37	0.43	0.56
5	女	55	1.60	57	0.39	0.46	0.59
平均		44.2±10.45	1.65±0.10	63.6±8.59	0.404±0.03	0.47±0.03	0.61±0.04

基于模糊逻辑算法的智能膝关节假肢步态相位识别

Gait phase recognition in intelligent above-knee prosthesis based on fuzzy logic algorithm

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 16

相关文章 2

Metrics

本文评价

推荐阅读 0

[1]	张意彬, 李剑峰, 喻洪流. 一种智能膝关节假肢及其步态对称性评价[J]. 《中国康复理论与实践》, 2023, 29(4): 402-407.
[2]	顾洪，李伟达，李娟. 智能膝关节假肢研究现状及发展趋势①[J]. 《中国康复理论与实践》, 2016, 22(9): 1080-1085.