Location and Tracking Mode of Sports Rehabilitation Training With Self-Powered Sensors Based on Particle Swarm Optimization Algorithm

Abstract

With the growth of the country’s economic strength, people’s living standards have steadily improved. Sports have become the main means to change physical fitness and maintain the per capita health index. The state also puts forward higher requirements for the security work of athletes, elderly groups and rehabilitation patients. Traditional rehabilitation training mainly relies on various sensor devices, such as acceleration sensing, pressure sensing and so on. These devices need a lot of energy to supply power for the equipment in the process of use, which is no longer suitable for today’s modern development environment. Based on the concept of self-powered sensors, this paper proposes a sports rehabilitation training model updated by particle swarm optimization algorithm. First of all, the performance and indicators of self-powered sensor devices are analyzed, and the self-powered electrical components are optimized using friction nano new energy technology. Starting from the basic characteristics of wearable models, we can ensure the consistency of posture in sports rehabilitation. During training, the wearing process will stretch 10% of the length in advance to ensure comfort and sensitivity. According to the results of the test record, the pulse index is clear and obvious, consistent with the actual number of minutes per minute. Finally, the sensor array model and function model are improved under the particle swarm optimization algorithm to realize the positioning and tracking function in sports rehabilitation training. The results show that the wearable training equipment optimized by particle swarm optimization can better locate and track the movement track than the traditional sports rehabilitation equipment. It can adjust the movement posture and protect the safety of trainers. At the same time, it is more prominent in performance and power supply duration.