In order to adapt to the specific task, the six-axis dynamic contact force between end-effectors of intelligent robots and working condition needs to be perceived. Therefore, the dynamic property of six-axis force sen...In order to adapt to the specific task, the six-axis dynamic contact force between end-effectors of intelligent robots and working condition needs to be perceived. Therefore, the dynamic property of six-axis force sensor which is installed on the end-effectors of intelligent robots will have influence on the veracity of detection and judgment to working environment contact force by intelligent robots directly. In this paper, dynamic analysis to double-layer and pre-stressed multi-limb six-axis force sensor is conducted. First, the structure of the sensor is introduced, and the limb number is confirmed by introducing the related definitions of convex analysis. Then, based on vibration of multiple-degree-of-freedom system, a mechanical vibration simplified model of double-layer and pre-stressed multiple limb six-axis force sensor is set up. After that, movement differential equations of sensor and the response of analytical expression are deduced, and the movement differential equations is solved. Finally, taking the double-layer and pre-stressed seven limb six-axis force sensor as an example, numerical calculation and simulation of deriving result is conducted, which verify the correctness and feasibility of the theoretical analysis.展开更多
下肢外骨骼需要通过识别穿戴者的运动意图为穿戴者日常活动提供助力,然而当前的研究很少关注能够提供新受试者意图信息的下肢运动模式预测.为此,本文提出了一种基于多传感器信息融合和迁移学习的下肢运动模式预测方法.本文首先设计了一...下肢外骨骼需要通过识别穿戴者的运动意图为穿戴者日常活动提供助力,然而当前的研究很少关注能够提供新受试者意图信息的下肢运动模式预测.为此,本文提出了一种基于多传感器信息融合和迁移学习的下肢运动模式预测方法.本文首先设计了一个下肢运动模式预测模型,采用长短时记忆单元(Long-Short Term Memory,LSTM)提取表面肌电信号(surface ElectroMyoGraphy,sEMG)中的模式特征,然后将sEMG的模式特征与关节角度特征融合预测下肢运动模式.考虑到受试者之间的生理信号差异,本文设计的迁移学习策略分两步训练预测模型,第一步在源域受试者数据集上预训练模型,第二步冻结sEMG模式特征提取器的网络权值,并在目标域数据集上微调全连接层.实验采集了受试者自由行走和穿戴外骨骼行走的数据.通过预测时间长度为100 ms的实验可以得出,所提出的方法分别能够有效提升新受试者自由行走状态下和穿戴外骨骼行走时9.53%和8.29%的运动模式预测准确率.实验结果表明,所提出方法可通过提升新受试者运动模式预测准确率,从而保障下肢外骨骼可靠的人体运动意图感知.展开更多
目的:分析多通道功能性电刺激四肢联动用于脑卒中患者中的效果。方法:选取2021年1月—2023年12月福建省荣誉军人康复医院收治的88例脑卒中患者,按照随机数表法分为两组,两组均接受常规康复训练,常规组(n=44)为常规四肢联动干预,试验组(n...目的:分析多通道功能性电刺激四肢联动用于脑卒中患者中的效果。方法:选取2021年1月—2023年12月福建省荣誉军人康复医院收治的88例脑卒中患者,按照随机数表法分为两组,两组均接受常规康复训练,常规组(n=44)为常规四肢联动干预,试验组(n=44)为多通道功能性电刺激下四肢联动干预。比较两组Fugl-Meyer运动功能评定量表下肢部分(FMA-L)、Berg平衡量表(BBS)、功能性步行量表(FAC)、起立-行走计时测试(TUGT)、10 m最大步行速度(10 m MWS)、脑卒中专业生活质量量表(SS-QOL)、日常生活活动能力量表(ADL)及满意度。结果:干预后,试验组FMA-L评分(25.36±2.33)分、BBS评分(40.52±3.66)分、FAC评分(3.66±1.03)分、10 m MWS(0.88±0.15)m/s、SS-QOL评分(186.55±22.45)分、ADL评分(72.58±5.72)分,均高于常规组的(21.56±2.35)分、(33.56±3.65)分、(2.68±1.02)分、(0.71±0.16)m/s、(156.52±22.53)分、(60.52±5.66)分,TUGT为(24.66±4.33)s,低于常规组的(28.65±4.35)s,差异有统计学意义(P<0.05)。试验组总满意率为95.45%,高于常规组的77.27%,差异有统计学意义(P<0.05)。结论:经多通道功能性电刺激下四肢联动干预可有效改善脑卒中患者下肢功能,提高其平衡力,促使其运动功能恢复,提高其生活质量,获取其满意度。展开更多
基金Supported by the National Natural Science Foundation of China(No.51505124)the Natural Science Foundation of Hebei Province(No.E2016209312)the Foster Fund Projects of North China University of Science and Technology(No.JP201505)
文摘In order to adapt to the specific task, the six-axis dynamic contact force between end-effectors of intelligent robots and working condition needs to be perceived. Therefore, the dynamic property of six-axis force sensor which is installed on the end-effectors of intelligent robots will have influence on the veracity of detection and judgment to working environment contact force by intelligent robots directly. In this paper, dynamic analysis to double-layer and pre-stressed multi-limb six-axis force sensor is conducted. First, the structure of the sensor is introduced, and the limb number is confirmed by introducing the related definitions of convex analysis. Then, based on vibration of multiple-degree-of-freedom system, a mechanical vibration simplified model of double-layer and pre-stressed multiple limb six-axis force sensor is set up. After that, movement differential equations of sensor and the response of analytical expression are deduced, and the movement differential equations is solved. Finally, taking the double-layer and pre-stressed seven limb six-axis force sensor as an example, numerical calculation and simulation of deriving result is conducted, which verify the correctness and feasibility of the theoretical analysis.
文摘下肢外骨骼需要通过识别穿戴者的运动意图为穿戴者日常活动提供助力,然而当前的研究很少关注能够提供新受试者意图信息的下肢运动模式预测.为此,本文提出了一种基于多传感器信息融合和迁移学习的下肢运动模式预测方法.本文首先设计了一个下肢运动模式预测模型,采用长短时记忆单元(Long-Short Term Memory,LSTM)提取表面肌电信号(surface ElectroMyoGraphy,sEMG)中的模式特征,然后将sEMG的模式特征与关节角度特征融合预测下肢运动模式.考虑到受试者之间的生理信号差异,本文设计的迁移学习策略分两步训练预测模型,第一步在源域受试者数据集上预训练模型,第二步冻结sEMG模式特征提取器的网络权值,并在目标域数据集上微调全连接层.实验采集了受试者自由行走和穿戴外骨骼行走的数据.通过预测时间长度为100 ms的实验可以得出,所提出的方法分别能够有效提升新受试者自由行走状态下和穿戴外骨骼行走时9.53%和8.29%的运动模式预测准确率.实验结果表明,所提出方法可通过提升新受试者运动模式预测准确率,从而保障下肢外骨骼可靠的人体运动意图感知.
文摘目的:分析多通道功能性电刺激四肢联动用于脑卒中患者中的效果。方法:选取2021年1月—2023年12月福建省荣誉军人康复医院收治的88例脑卒中患者,按照随机数表法分为两组,两组均接受常规康复训练,常规组(n=44)为常规四肢联动干预,试验组(n=44)为多通道功能性电刺激下四肢联动干预。比较两组Fugl-Meyer运动功能评定量表下肢部分(FMA-L)、Berg平衡量表(BBS)、功能性步行量表(FAC)、起立-行走计时测试(TUGT)、10 m最大步行速度(10 m MWS)、脑卒中专业生活质量量表(SS-QOL)、日常生活活动能力量表(ADL)及满意度。结果:干预后,试验组FMA-L评分(25.36±2.33)分、BBS评分(40.52±3.66)分、FAC评分(3.66±1.03)分、10 m MWS(0.88±0.15)m/s、SS-QOL评分(186.55±22.45)分、ADL评分(72.58±5.72)分,均高于常规组的(21.56±2.35)分、(33.56±3.65)分、(2.68±1.02)分、(0.71±0.16)m/s、(156.52±22.53)分、(60.52±5.66)分,TUGT为(24.66±4.33)s,低于常规组的(28.65±4.35)s,差异有统计学意义(P<0.05)。试验组总满意率为95.45%,高于常规组的77.27%,差异有统计学意义(P<0.05)。结论:经多通道功能性电刺激下四肢联动干预可有效改善脑卒中患者下肢功能,提高其平衡力,促使其运动功能恢复,提高其生活质量,获取其满意度。
