Abstract：For ground reaction force (GRF), there exists huge difference on different terrains because of human leg's random movement and unstructured ground. Therefore, an experiment shoe with insole-type pressure sensors is developed for detecting GRF in real time, and a PSO-SVM (particle swarm optimization based support vector machine) algorithm for gait classification is presented. 7 pressure sensors are installed into the shoes redundantly according to the plantar pressure distribution. The GRFs when a person walks on treadmill (5 km/h), concrete pavement and field grass are collected and processed. Corresponding labels are set in advance for the GRFs from the basic group, which is used as training set. Based on the training set, an ordinary classifier I and a classifier Ⅱ based on PSO-SVM algorithm are constructed to classifying the walking data on concrete pavement and field grass respectively. The experiment results demonstrate that, compared with the ordinary classifier I, the proposed optimization algorithm shows a great advantage of gait classification on complex terrains, gait identification accuracies on concrete pavement and field grass are improved by 32.9% and 42.8% respectively, and still a fast optimization speed and a good robustness are implemented after some insole-type pressure sensors malfunction.
 杨智勇,张静,归丽华,等.外骨骼机器人控制方法综述[J].海军航空工程学院学报,2009(5):520-526.Yang Z Y, Zhang J, Gui L H, et al. Summarize on the control method of exoskeleton robot[J]. Journal of Naval Aeronautical and Astronautical University, 2009(5):520-526.
 Cha D, Kang D, Kim K I, et al. Faster detection of step initiation for the lower limb exoskeleton with vertical GRF events[J]. Journal of Electrical Engineering & Technology, 2014, 9(2):733-738.
 Cha D, Oh S, Kim K I, et al. Implementation of precedence walking assistance mechanism in exoskeleton with only vertical ground reaction forces[J]. Electronics Letters, 2014, 50(3):146-148.
 Jung J, Jang I, Riener R, et al. Walking intent detection algorithm for paraplegic patients using a robotic exoskeleton walking assistant with crutches[J]. International Journal of Control, Automation, and Systems, 2012, 10(5):954-962.
 曹恒,孟宪伟,凌正阳,等.两足外骨骼机器人足底压力测量系统[J].传感技术学报,2010,23(3):326-330.Cao H, Meng X W, Ling Z Y, et al. Measurement system for plantar pressure of biped exoskeleton robot[J]. Chinese Journal of Sensors and Actuators, 2010, 23(3):326-330.
 曹恒,贺成坤,孟宪伟,等.下肢外骨骼服传感靴的结构优化分析[J].工程设计学报,2010,17(1):35-39,65.Cao H, He C K, Meng X W, et al. Structure optimization analysis for exoskeleton foot[J]. Journal of Engineering Design, 2010, 17(1):35-39,65.
 Wheeler J, Rohrer B, Kholwadwala D, et al. In-sole MEMS pressure sensing for a lower-extremity exoskeleton[M]//1st IEEE RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics. Piscataway, USA:IEEE, 2006:787-790.
 张志成.外骨骼下肢助力机器人技术研究[D].哈尔滨:哈尔滨工业大学,2011.Zhang Z C. Research on lower extremity exoskeleton of power assist robot[D]. Harbin:Harbin Institute of Technology, 2011.
 Zhang X G, Guo Q, Zhao C Y, et al. Development of a lower extremity exoskeleton suit actuated by hydraulic[C]//IEEE International Conference on Mechatronics and Automation. Piscataway, USA:IEEE, 2012:587-591.
 焦晓璇,景博,羌晓清,等.机载燃油泵故障诊断及实验平台研究[J].振动与冲击,2017,36(1):120-128.Jiao X X, Jing B, Qiang X Q, et al. Fault diagnosis and test platform for airborne fuel pumps[J]. Journal of Vibration and Shock, 2017, 36(1):120-128.