This scientific paper explores two distinct approaches for identifying and approximating the simulation model, particularly in the context of the snap process crucial to medical device assembly. Simulation models play a pivotal role in providing engineers with insights into industrial processes, enabling experimentation and troubleshooting before physical assembly. However, their complexity often results in time-consuming computations. To mitigate this complexity, we present two distinct methods for identifying simulation models: one utilizing Spline functions and the other harnessing Machine Learning (ML) models. Our goal is to create adaptable models that accurately represent the snap process and can accommodate diverse scenarios. Such models hold promise for enhancing process understanding and aiding in decision-making, especially when data availability is limited.

翻译：本科学论文探讨了两种不同的方法来识别和近似仿真模型，特别是在医疗器械装配中关键的卡扣过程背景下。仿真模型在工程师理解工业过程中发挥着关键作用，能够在物理装配之前进行实验和故障排除。然而，其复杂性常导致耗时计算。为缓解这一复杂性，我们提出了两种不同的仿真模型识别方法：一种利用样条函数，另一种利用机器学习模型。我们的目标是创建能够准确表示卡扣过程并适应多种场景的自适应模型。这类模型有望增强对过程的理解并辅助决策，尤其是在数据可用性有限的情况下。