By the method of documentation and logical analysis, based on the data, based on logic and based on the knowledge of three kinds of artificial intelligence in the sports education, the intelligent learning system feedback delay are studied, combined with mobile communication which led to the artificial intelligence online sports games teaching, pattern recognition, and virtual technology combined with innovative teaching interaction and experience. Promoting the development of green PE teaching machine learning can identify the types of PE activities and realize efficient PE learning diagnosis. Intelligent decision support system can identify sports talents and improve the effect of personalized PE teaching evaluation. From the perspective of psychological development and education, the key problems to be solved in the integration of artificial intelligence and physical education are examined. Then, the consistent model predictive control for feedback delay of nonlinear sports learning multiagent system with network induced delay and random communication protocol is studied. Under the communication waiting mechanism designed, each agent has a certain tolerance of delay, and this tolerance can be determined by ensuring the stability of the system. At the same time, a random communication protocol is designed to ensure the ordered communication of the multiagent system. Finally, the effectiveness of the proposed algorithm is verified by numerical simulation. To solve the channel competition access problem of the sports intelligent learning system with special structure feedback delay model predictive control, a dual channel awareness scheduling strategy under the model predictive control framework was proposed, and the distributed threshold strategy of sensors and the priority threshold strategy of controllers were designed. It is proved that the sensor will eventually work at Nash equilibrium point under the policy updating mechanism, and the priority threshold strategy of the controller is better than the traditional independent and identically distributed access strategy. By avoiding the data transmission when the channel status is poor, the channel access of the system is efficient and saves energy.

In order to improve the performance of sports performance prediction, based on computational learning algorithms, this article builds a sports performance prediction model based on ensemble learning algorithms under the guidance of machine learning ideas. Moreover, this article applies the cascade principle to improve the accuracy of the model and determines the cascade structure, studies the characteristics of spatio-temporal sequence data and the modeling methods of spatio-temporal sequence models, and combines the idea of selective integration learning to improve the spatio-temporal neural network model. In addition, this paper uses the L1 regularization method to sparsely weight and combine multiple STELM models to achieve selective integration. Finally, this paper designs experiments to predict the performance of this model in sports performance prediction. The research results show that the prediction results of the sports performance prediction model constructed in this paper are accurate.

Based on the constant speed driving mode of servo motor, analysis of capacitor energy storage device’s parameter design was made, and then a group of reasonable capacitor energy storage parameters were given. Based on the parameters, to realize variable speed driving and multi-adaptability of the press, it put emphasis on analysis of the servo driver’s control parameters and the press’s output ability. And important conclusion was also provided. To confirm the accuracy of the conclusion, the special permanent magnet AC servo system was designed and experiment was carried on it. The results prove that the designed capacitor energy storage device can satisfy the power and control request of press stamping. Analysis on control parameters of the servo driver and output ability of the press is reasonable, which provides the reference for the development of servo press’s flexibility.

In order to improve the performance of sports performance prediction, based on computational learning algorithms, this article builds a sports performance prediction model based on ensemble learning algorithms under the guidance of machine learning ideas. Moreover, this article applies the cascade principle to improve the accuracy of the model and determines the cascade structure, studies the characteristics of spatio-temporal sequence data and the modeling methods of spatio-temporal sequence models, and combines the idea of selective integration learning to improve the spatio-temporal neural network model. In addition, this paper uses the L1 regularization method to sparsely weight and combine multiple STELM models to achieve selective integration. Finally, this paper designs experiments to predict the performance of this model in sports performance prediction. The research results show that the prediction results of the sports performance prediction model constructed in this paper are accurate.