An Adaptive Genetic Algorithm for Tension Control in Air-Jet Weaving Machines

In air-jet weaving, precise control of warp yarn tension is essential for maintaining both production quality and efficiency. Traditional control algorithms often exhibit low accuracy due to the time-varying characteristics of the warp-feeding system and the presence of external disturbances. To mitigate this limitation, a collaborative tension control model was developed by integrating the dynamics of the warp feed motor and yarn mechanics. A genetic algorithm was employed to optimize the three parameters of the PID controller, incorporating an adaptive crossover-mutation operator and simulated annealing to enhance the global search capabilities. Simulation and experimental results demonstrated that this method significantly improved tension stability and accuracy in comparison to conventional algorithms,