An Innovative Quality Prediction Method for Injection-Molded Products: A Multistage Fusion Regression Model Based on the IA-BiGRU and Multihead Self-Attention Mechanism

Injection molding is a critical manufacturing process for lean production, encompassing multiple production stages. Since the quality of injection-molded products is significantly influenced by factors such as process parameters, equipment conditions, and mold status, real-time quality monitoring has become essential for the intelligent development of the injection molding industry. However, existing quality prediction methods often neglect the stage-specific impact on quality, resulting in reduced prediction efficiency and accuracy. To address this issue, this article proposes a multistage fusion regression model (MSFRM) for quality prediction in injection molding. The proposed model integrates an input-attention bidirectional gated recurrent unit (IA-BiGRU) and a multihead self-attention mechanism (MSAM) to evaluate the individual and cumulative effects of each production stage, enabling precise predictions. To tackle the challenge of missing process data in injection molding, an input attention (IA) mechanism tailored for BiGRU is designed to extract critical process variable features. Moreover, a multistage fusion module based on an MSAM is developed to enhance global information sharing and stage-specific feature learning. The experimental results demonstrate that the proposed model outperforms the traditional methods in terms of prediction accuracy and robustness on real-world injection molding datasets.