Search

• There are nonlinear characteristics in the turntable servo system. • A controller based on deep deterministic policy gradient algorithm is proposed. • Experimentations of six control strategies in four conditions are compared. • The tracking accuracy and stability of turntable servo system are improved. In automotive manufacturing, brake disc balance accuracy is critical for braking system reliability. The tracking accuracy of the balancing machine's turntable servo system directly influences production efficiency and disc balance. To enhance turntable servo control in position and velocity tracking, this paper proposes a fractional order proportional integral derivative (FOPID) controller using a deep deterministic policy gradient (DDPG) algorithm inspired by deep reinforcement learning (DRL). A dynamic model of the servo system is developed to support the design of the DDPG FOPID control strategy. Anti-interference and anti-noise experiments are conducted to compare control strategies including fuzzy logic (Fuzzy), genetic algorithm (GA) PID, particle swarm optimization (PSO) PID, Q-learning PID, DDPG PID and DDPG FOPID through the physical experimental platform of the turntable servo system. Experimental results demonstrate that the DDPG FOPID strategy offers superior robustness and tracking performance, suggesting its potential to advance intelligent control methods in automotive manufacturing. [ABSTRACT FROM AUTHOR]

• Enhanced by the resonance, the sensitivity increased by 47.2%. • The average error of the REME method was 9.5%. • The method can measure monotonically varying stress and alternating stress. • The REME sensor has a good dynamic response and needs a low power supply. • The resonance enhancement can be applied to other coil-based sensors. To increase the test sensitivity, the resonance theory was introduced to the magnetoelastic method. After analyzing the correlation between the stress and the induced voltage, the resonance enhanced magnetoelastic (REME) method was proposed. A REME sensor with a low resonant frequency was made to carry out the experiment. The results showed that the resonant frequency, the resonant voltage, and the induced voltage could be used to measure stress, the test errors were 12.5%, 11.9%, and 9.5%, respectively. To measure stress, the excitation frequency should be close and lower than the resonant frequency. Enhanced by the resonance theory, the sensitivity of the REME method was 132.47% and 286.50% higher than that corresponding to the resonant voltage and the resonant frequency. The REME method has the advantages of low power supply and good dynamic response. Besides, using the resonance theory to enhance the measurement is applied to other coil-based sensors and methods. [ABSTRACT FROM AUTHOR]