工业工程研究生智能制造系统优化能力培养的"虚实融合"路径研究

Research on the "Virtual-Real Fusion" Path of Intelligent Manufacturing System Optimization Ability Training for Graduate Students in Industrial Engineering

摘要:

随着智能制造加速推进,工业工程人才亟需掌握数据驱动优化、虚实协同管控等核心能力,而传统培养模式因实践场景局限、复杂系统训练不足,难以满足上述需求。文章聚焦于"虚实融合"教学路径,首先,解析智能制造系统优化能力的核心维度(系统建模、多目标决策、动态调度),结合数字孪生、AR/VR等技术特性,构建"认知—实践—反馈"三阶段培养模型;其次,设计虚实互补的实践路径,涵盖课程重构(虚拟仿真与物理实验映射)、平台建设(数据—仿真—应用三层架构)及动态评价体系;最后,通过对"虚实融合"培养路径实施成效与机制分析,进一步明确了此路径在提升工业工程研究生智能制造系统优化能力方面的重要作用。研究证实,"虚实融合"路径通过数字孪生的动态反馈机制,可有效弥合理论教学与工业实践的鸿沟,为智能制造人才培养提供可复用的方法论支撑。

Abstract:

With the acceleration of intelligent manufacturing, industrial engineering talents need to master core capabilities such as data-driven optimization and virtual-real collaborative management and control, while the traditional training model is difficult to meet the above needs due to the limitations of practical scenarios and the lack of complex system training. This paper focuses on the teaching path of "virtual-real integration". First, it analyzes the core dimensions of intelligent manufacturing system optimization ability (system modeling, multi-objective decision making, dynamic scheduling), combines digital twin, AR/VR and other technical characteristics, and builds a three-stage training model of "cognitive-practice-feedback". Secondly, the practical path of virtual-real complementarity is designed, which covers course reconstruction (mapping between virtual simulation and physical experiment), platform construction (data-simulation-application three-layer architecture) and dynamic evaluation system. Finally, through the analysis of the implementation effect and mechanism of the virtual and real integration training path, the important role of this path in improving the optimization ability of intelligent manufacturing system for industrial engineering graduate students is further clarified. The research proves that the virtual and real integration path can effectively bridge the gap between theoretical teaching and industrial practice through the dynamic feedback mechanism of digital twin, and provide reusable methodology support for the training of intelligent manufacturing talents.