Real-time RPE Monitoring and Machine Learning Algorithm were Used to Optimize the Training Load of Youth Competitive Aerobics

The fault identification system often has false positives and false positives. In order to improve the accuracy of the fault identification of aerobics strength trainer, an automatic fault identification system of aerobics strength trainer based on particle group algorithm is designed. In the hardware, the microcontroller alarm circuit is designed, the connection mechanism of the high level output port and the alarm circuit is improved, and the SIM card communication circuit is designed to ensure that the strength trainer can timely alarm and send notification when the fault is detected. In the software, the trainer fault features are extracted, the empirical signal frequency of other ports is calculated, the square sum of the trainer fault extraction is calculated, based on the particle group algorithm to obtain the individual extreme value and global extreme value of particles, and design the fault identification algorithm of the strength trainer. Compared with the recognition accuracy of the four algorithms in no fault, bearing fault, rotor fault and stator winding fault characteristics, the accuracy of the particle swarm algorithm is higher than $99 \%$, while the accuracy of the other three algorithms is between $97 \%$ and $99 \%$, which shows that the system is better than other systems in terms of recognition accuracy.