Design And Implementation Of Medical Moped System Based On Recognition Of Manipulation Intention

With the seriousness of China's aging population,the problem of medical resources is becoming increasingly prominent,and the hospital bed is one of the key resources.The hospital is facing many challenges in patient transportation,mainly including reasons such as limited manpower,work injury,and low efficiency of the push bed method.Aiming at this problem,this paper proposes a medical moped based on operator's intention recognition.The moped can be installed at the bottom of the hospital bed and run under the control of medical staff,which can greatly reduce manpower and benefit the health of hospital staff.The medical moped can recognize the manipulation intention by the pressure sensor on the push hand of the medical staff,so as to control the medical moped to achieve horizontal,vertical and rotary movements.Its unique right-angle lateral movement feature allows it to move better in a small space.And the medical moped is easy to operate,more effective and safer.The main research contents of this paper are as follows:(1)According to the actual functional requirements of the system,the overall scheme of the medical moped system is designed,which mainly includes the driving system,the control intention recognition system and the mechanical structure.And according to the overall plan of the system,using Solid Works to do a three-dimensional simulation of the medical part of the moped.(2)Design a method for recognizing the direction steering intention of a medical moped.The control intention of the membrane pressure sensor based on the support vector machine algorithm is used for identification,and the kernel function parameters and penalty coefficients in the support vector machine algorithm are optimized.The effectiveness of hand control intention identification is verified through experiments.At the same time,the fuzzy inference algorithm is used to study the maneuvering intention.Before using the fuzzy algorithm,the pressure sensor signal is proportionally processed,and then the membership function is used toperform fuzzy,eigenvalue extraction,and feature fusion.By comparing the results and response time of maneuvering intention recognition based on support vector machine and fuzzy inference,it is concluded that the method of manipulating intention recognition based on fuzzy inference has better recognition effect.(3)Research on the recognition of speed control intention of medical mopeds,analyze the influence of individual difference factors such as height and weight,and the direction of movement on the result of speed control intention recognition.Analyze the data recorded in the experiment,and study the force characteristics of the hand when the experiment object moves in different directions.Considering the individual differences and the characteristics of hand force application,a speed control intention recognition algorithm for medical mopeds is designed.Experiments have verified the effectiveness of the speed control intent recognition algorithm.(4)Build an experimental platform for medical mopeds,control the medical mopeds through the interaction between humans and machines to carry out different modes of motion,analyze the causes of errors in the experimental process and give solutions.The experimental results also verified the rationality and practicability of the design of the medical moped.