Process Optimization of Multi-Stage Continuous Production System Based on Feature Fusion Modeling

Modeling and process optimization of Multi-stage Continuous Production System (MCPS) is an important research topic in the field of intelligent manufacturing today. However, due to the inherent properties of MCPS, existing researches face difficulties in 1) coupling optimization across multiple stages under diverse constraints and objectives, and 2) accurately mapping controllable process variables to critical production outputs. In this work, we propose a novel multi-objective optimization method for MCPS based on feature fusion modeling, with main innovations including: 1) For MCPS modeling, we propose a Transformer network structure with a parallel dual-branch attention mechanism for linking process variables to production outputs. A multi-stage feature fusion prediction model based on DenseNet is developed, which not only improves prediction accuracy but also provides intermediate stage prediction results. 2) For process optimization of MCPS, we design a multi-constraint and multi-objective optimization model. Subsequently, we propose a dynamic multi-objective optimization algorithm framework to enhance the performance of the algorithm and improve the quality of solutions. Furthermore, we conducted experiments with a real Coke-Chem integrated production dataset, and the results show that our predictive model achieves an average MAE of 0.11, MSE of 0.04, and RMSE of 0.20, outperforming state-of-the-art methods and boosts solution coverage (up to 80%) and hypervolume (up to $2.5\times $ ) when integrated with classical algorithms like NSGA-II and GDE3. Note to Practitioners—The PO-MCPS commonly found in modern industrial production is a complex issue, especially when some intermediate stages also produce end products. For example, optimizing a single stage may deteriorate other stages, causing a global loss; simply increasing production volume may also increase raw material costs and reduce overall profitability. The strategy proposed in this work can help practitioners build predictive models similar to Coke-Chem integrated production, thereby enabling the prediction of outputs at various stages of the production and supporting the overall optimization of process variables. This strategy has a high value for engineering applications.