Lateral Register Error Control of Paper Gravure Printing Machine based on AGA-Elman Neural Network

The lateral expansion–contraction register error in water-based ink paper printing exhibits significant strong coupling and nonlinearity—a key factor restricting high-quality printing. To address issues such as long manual adjustment times and severe material waste, this paper proposes a lateral expansion–contraction register control method based on an improved Elman neural network. First, a linear circular register error detection color mark is designed, and actual printing condition data is collected to construct a lateral expansion–contraction register error dataset. Based on this, the mapping relationship between paper lateral expansion–contraction register error and oven temperature/fan air volume is studied. A lateral expansion–contraction register control method based on the Elman neural network is proposed, and its parameters are optimized by introducing the Adaptive Genetic Algorithm (AGA). Finally, the improved Elman neural network is compared with BP and CNN neural networks to validate the effectiveness of different methods in controlling lateral expansion–contraction register error. Experimental results show that the proposed AGA-Elman method can effectively control the lateral expansion–contraction register error within ±0.1 mm, meeting the requirements for high-speed, high-precision printing on paper gravure machines.