Fuzzy Evaluation of Mechanical Motion Device Design Performance Based on Deep Learning Algorithm

Nowadays, with the improvement of people’s living standards, people are increasingly concerned about their physical health. Exercise can effectively improve physical fitness, alleviate and release mental stress, and improve people’s physical and mental health. Nowadays, indoor fitness is becoming increasingly popular, and there are various types of equipment designed. Some equipment is practical and cheap, while others are not only of little use but also very expensive. Therefore, it is very important to evaluate the performance of the designed device. Evaluating a device requires consideration of its practicality, safety, and cost-effectiveness. For example, there are differences in the structure of each person’s body, and the mode of their power generation would also be different, ensuring that most people can use the equipment, which makes it more practical. For example, the treadmill can be equipped with an intelligent system, which can calculate and adjust adaptively according to the user’s pace, step frequency, stride length, etc., to enhance the practicability of the device. This paper studies the deep learning algorithm, studies a variety of neural network structures, and discusses how deep learning can automatically learn the knowledge of human structural mechanics and mechanical motion device design, aiming to establish an evaluation model for fuzzy evaluation of mechanical motion device design performance. Experimental results have shown that using deep learning algorithms for performance fuzzy evaluation of mechanical motion device design is effective. The difference between the comprehensive scoring results and the actual testing results of the device is about 0.5%, indicating that its evaluation is very objective and accurate.