Neural network predictive control applied to automotive paint drying and curing processes

Abstract

In the automotive painting process, maintaining optimal operating conditions in drying and curing ovens is crucial to ensure high-quality paint finishes, particularly for specific car body-in-white (BIW) parts' temperature profiles. This paper presents a methodology for developing and implementing a Neural Network Predictive Control (NNPC) system for painting drying and curing processes in an automotive oven used in the electrodeposition stage (Elpo oven). The objective is to enhance temperature control for BIW parts. To train the Artificial Neural Networks (ANN) in the various zones of the Elpo oven, a dataset was generated using a phenomenological model based on first principles. Random disturbances were applied to the input variables (conveyor speed and zone temperatures) to capture the dynamic response of the output variables (temperature in specific BIW parts). The dataset was split into training (80 %), validation (10 %), and test (10 %) sets, and the ANN training was performed using the backpropagation algorithm. The implemented NNPC utilizes the trained ANNs to predict future temperature values in specific BIW parts (controlled variables). To determine the optimal control signals (manipulated variables), an optimizer based on the Generalized Predictive Control (GPC) model was employed, and the objective function was minimized using the Ant Colony Optimization Algorithm (ACO). Through simulations of four operational scenarios with applied disturbances, the results demonstrate satisfactory performance of the NNPC, effectively maintaining controlled temperatures of BIW parts close to predefined setpoints. The utilization of NNPC offers improved temperature control for BIW parts, mitigating painting issues, reducing rework and operating costs, while ensuring painting quality is uncompromised.