To deal with the increasing demand for low-volume customization of the mechanical properties of cold-rolled products, a two-way control method based on mechanical property prediction and process parameter optimization (PPO) has become an effective solution. Aiming at the multi-objective quality control problem of a company’s cold-rolled products, based on industrial production data, we proposed a process parameter design and optimization method that combined multi-objective quality prediction and PPO. This method used the multi-output support vector regression (MSVR) method to simultaneously predict multiple quality indices. The MSVR prediction model was used as the effect verification model of the PPO results. It performed multi-process parameter collaborative design and realized the optimization of production process parameters for customized multi-objective quality requirements. The experimental results showed that, compared with the traditional single-objective quality prediction model based on support vector regression (SVR), the multi-objective prediction model could better take into account the coupling effect between process parameters and quality index, the MSVR model prediction accuracy was higher than that of the SVR, and the optimized process parameters were more capable and reflected the influence of metallurgical mechanism on the quality index, which were more in line with actual production process requirements.

为应对冷轧产品机械性能小批量定制需求的日益增长，基于力学性能预测和工艺参数优化（PPO）的双向控制方法已成为有效的解决方案。针对某公司冷轧产品的多目标质量控制问题，基于工业生产数据，提出了多目标质量预测与PPO相结合的工艺参数设计与优化方法。该方法使用多输出支持向量回归（MSVR）方法同时预测多个质量指标。MSVR预测模型被用作PPO结果的效果验证模型。进行多工艺参数协同设计，实现定制化多目标质量要求的生产工艺参数优化。实验结果表明，与传统的基于支持向量回归（SVR）的单目标质量预测模型相比，多目标预测模型能够更好地考虑工艺参数与质量指标之间的耦合效应，MSVR模型预测精度高于SVR，优化后的工艺参数更能反映冶金机理对质量指标的影响，更符合实际生产工艺要求。