Research on Climbing Operation Mode Recognition Based on Plantar Pressure Characteristics

YU Guangkai; ZHAO Buling; LIU Ting; LIU Kai; KOU Jiange²

doi:10.3969/j.issn.1008-0198.2026.01.016

您当前的位置：

首页 >

文章列表页 >

Research on Climbing Operation Mode Recognition Based on Plantar Pressure Characteristics

更新时间：2026-03-11

- Research on Climbing Operation Mode Recognition Based on Plantar Pressure Characteristics
- Vol. 46, Issue 1, Pages: 118-124(2026)
- 作者机构：
  
  1. 中国电力科学研究院有限公司电网环境保护国家重点实验室,湖北,武汉,430074
  2. 北京航空航天大学,北京,100191
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1008-0198.2026.01.016
  CLC： TM754
- Online First：10 March 2026，
  
  Published：10 March 2026
- 稿件说明：
移动端阅览
余光凯, 赵不伶, 刘庭, 刘凯, 寇建阁. 基于足底压力特征的登杆作业模式识别研究[J]. 湖南电力, 2026, 46(1): 118-124.

YU Guangkai, ZHAO Buling, LIU Ting, et al. Research on Climbing Operation Mode Recognition Based on Plantar Pressure Characteristics[J]. 2026, 46(1): 118-124.
余光凯, 赵不伶, 刘庭, 刘凯, 寇建阁. 基于足底压力特征的登杆作业模式识别研究[J]. 湖南电力, 2026, 46(1): 118-124. DOI： 10.3969/j.issn.1008-0198.2026.01.016.

YU Guangkai, ZHAO Buling, LIU Ting, et al. Research on Climbing Operation Mode Recognition Based on Plantar Pressure Characteristics[J]. 2026, 46(1): 118-124. DOI： 10.3969/j.issn.1008-0198.2026.01.016.

摘要

针对登杆带电作业模式复杂、非周期性及多模态特征对外骨骼助力控制带来的挑战

提出一种基于足底压力与深度可逆语义一致性学习（deep reversible consistency learning

DRCL）的识别方法。构建足底压力数据采集系统

提取压力中心（center of pressure

COP）及其多种衍生特征作为主要输入。结合DRCL方法

通过选择性先验学习、语义一致性约束和模态不变表示重塑

实现多模态特征融合与鲁棒识别。试验结果表明

COP衍生特征在平地行走和上杆前准备模式下的F

值均高于0.99。模型训练后

三名受试者的识别准确率最高达98.1%

平均准确率达94.4%。该方法显著提升了登杆带电作业模式识别的准确性与鲁棒性

为外骨骼机器人实现人机协同实时助力控制提供了可靠依据。

Abstract

To address the challenges posed by the complex

non-periodic

and multi-modal characteristics of climbing and working on energized poles for exoskeleton assistance control

a recognition method based on plantar pressure and deep reversible consistency learning(DRCL) is proposed. A plantar pressure data collection system is constructed

and the center of pressure(COP) and various derived features are extracted as the main inputs. Combined with the DRCL method

multi-modal feature fusion and robust recognition are achieved through selective prior learning

semantic consistency constraints

and modality-invariant representation resha

ping. Experimental results show that the COP-derived features achieve F

values above 0.99 under both level ground walking and pre-pole-climbing preparation modes. After model training

the recognition accuracy for three subjects reaches a maximum of 98.1%

with an average accuracy of 94.4%. This method significantly improves the accuracy and robustness of mode recognition for climbing and working on energized poles

providing a reliable basis for exoskeleton robots to achieve real-time human-robot collaborative assistive control.

关键词

Keywords

references

胡毅,刘凯,彭勇,等. 带电作业关键技术研究进展与趋势[J]. 高电压技术,2014,40(7):1921-1931.

胡毅. 配电线路带电作业技术[M]. 北京:中国电力出版社,2002.

王富江,金旭,娜扎开提•买买提,等. 制造业工人肌肉骨骼疾患发生模式及影响因素[J]. 北京大学学报(医学版),2020,52(3):535-540.

WESSLÉN J. Exoskeleton exploration:Research,development,and applicability of industrial exoskeletons in the automotive industry[D]. Jönköping:School of Engineering,Jönköping University,2018.

BUTLER T,GILLETTE J C.Exoskeletons used as a PPE for injury prevention[J]. Professional safety,2019,64(3):32-37.

GOLABCHI A,CHAO A,TAVAKOLI M.A systematic review of industrial exoskeletons for injury prevention:efficacy evaluation metrics,target tasks,and supported body postures[J]. Sensors,2022,22(7):2714.

李怀仙,程文明,刘放,等. 外骨骼助力负重中下肢肌肉收缩与协作机制[J]. 西南交通大学学报,2018,53(6):1286-1294.

TIJJANI I,KUMAR S,BOUKHEDDIMI M.A survey on design and control of lower extremity exoskeletons for bipedal walking[J]. Applied Sciences,2022,12(5):2395.

GONG N.Study on the rehabilitation training effect of exoskeletal diseases based on the skeletal muscle geometry modeling method[J]. Applied Mathematics and Nonlinear Sciences,2023,8(2):3139-3156.

张莹莹. 基于足底压力的外骨骼康复训练模型的研究[D]. 长春:中国科学院大学(中国科学院长春光学精密机械与物理研究所),2018.

YANG J Y,LI G C,ZHAO X F,et al.Research on joint-angle prediction based on artificial neural network for above-knee amputees[J]. Sensors,2021,21(21):7199.

方敦宇. 面向外骨骼膝关节助行机器人足底压力特征分析 [D]. 南昌:南昌大学,2021.

宋广玥,宋智斌,项忠霞. 基于足底压力传感器的不控制减重比例下步态相位识别[J]. 工程设计学报,2019,26(3):260-266.

姚健. 基于足底压力测量的步态识别与预测[D]. 成都:西南交通大学,2017.

宋鹏,莫新民,邓亚萍,等. 基于比例归一化阈值的外骨骼步态识别方法[J]. 火炮发射与控制学报,2018,39(2):81-85.

CHEN L F,LIN Q Y,CHENG H Y,et al.A deep learning hybrid model for identifying gait patterns and transition states of lower limb exoskeleton wearer[J]. IEEE Sensors Journal,2025,25(4):7698-7707.

PU R T,QIN Y,PENG D Z,et al.Deep reversible consistency learning for cross-modal retrieval[J]. IEEE Transactions on Multimedia,2025,27:4095-4106.

DING F,LIU X,WANG X Y,et al.Dual-mix for cross-modal retrieval with noisy labels[C]//ICASSP 2024-2024 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP). Seoul,Korea,Republic of. IEEE,2024:6505-6509.

YUE C,LIN X,ZHANG X,et al.Design and performance evaluation of a wearable sensing system for lower‐limb exoskeleton[J]. Applied Bionics And Biomechanics,2018(1):8610458.

曾德政,吕继亮,屈盛官,等. 基于SVMBP的下肢外骨骼步态检测及识别研究[J]. 机械工程学报,2022,58(12):29-38.

卢宗兴,苏永生,东辉,等. 基于足底力反馈的踝关节主被动康复策略[J]. 机械工程学报,2022,58(21):50-59.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

AI问答

⁰