At present, the parameters of the controllers in hot rolling roughing microtension control systems are not adaptively adjustable to variations in working conditions, which compromises both width accuracy and production stability. To address this issue, this paper introduces an ATKB-PID adaptive micro tension control method. This method incorporates a linear attention layer and utilizes a K-Nearest Neighbors (KNN) algorithm to predict the optimal learning rate and inertia coefficient under actual operating conditions. Furthermore, an objective function is tailored to production indices to enhance model performance. Comparative experiments with both established and recently introduced controllers demonstrate that the proposed ATKB-PID method exhibits a smaller steady-state error and quicker adjustment time. The ATKB-PID control method is well-suited for the complex and dynamic microtension control demands in thermal roughing processes, showing promising application potential.
© 2025. The Author(s).