Novel Computational Techniques for Machining Advanced Materials

该项目的目的是产生新的数学技术和机器学习，用于研究先进合金的切削刀具设计和材料切削机制。这将包括为各种加工场景开发有限元模型和基于传感器的数字孪生。各行各业的大多数高精度部件都是通过机械加工制造的。它是通过使用硬切削工具去除材料将原材料转化为成品的过程。平均而言，总制造成本的17%与切削刀具有关。对于专业合金，由于对其加工性能的了解有限，这一比例可高达25%。新材料和复合材料的引入需要每天调整切割几何形状和制造工艺，这在实验上是不可行的。机械加工是一个复杂的多物理场问题，其中机械能用于工件材料的塑性变形。用于切削的大部分机械能转化为热，导致热化学和热机械工具磨损和表面损伤。开发加工过程的数字孪生可以更好地理解加工过程中的材料行为，并有助于在加工和刀具设计过程中做出决策，以实现最佳生产率。

The aim of the project is to generate novel mathematical techniques and machine learning for investigating cutting tool design and material cutting mechanism for advanced alloys. This will include developing finite element models and sensor based digital twins for various machining scenarios.The majority of high precision components across various industries are made by machining. It is a process of converting raw material into finished products by removing material using a hard cutting tool. On average, 17% of the total manufacturing cost is associated with cutting tools. This can be as high as 25% for specialist alloys where limited knowledge exists on their machining behaviour. The introduction of new materials and composites requires daily adjustments to the cutting geometries and manufacturing processes which is not viable experimentally. Machining is a complex multiphysics problem where mechanical energy is used for plastically deforming the workpiece material. Majority of the mechanical energy used for cutting transforms into heat leading to thermochemical and thermomechanical tool wear and surface damage. Developing the digital twin of the machining processes can lead to better understanding of material behaviour during machining and facilitate decision making during machining and cutting tool design for optimum productivity.