A Knowledge base model for complex forging die machining

Recent evolutions on forging process induce more complex shape on forging die. These evolutions, combined with High Speed Machining (HSM) process of forging die lead to important increase in time for machining preparation. In this context, an original approach for generating machining process based on machining knowledge is proposed in this paper. The core of this approach is to decompose a CAD model of complex forging die in geometric features. Technological data and topological relations are aggregated to a geometric feature in order to create machining features. Technological data, such as material, surface roughness and form tolerance are defined during forging process and dies design. These data are used to choose cutting tools and machining strategies. Topological relations define relative positions between the surfaces of the die CAD model. After machining features identification cutting tools and machining strategies currently used in HSM of forging die, are associated to them in order to generate machining sequences. A machining process model is proposed to formalize the links between information imbedded in the machining features and the parameters of cutting tools and machining strategies. At last machining sequences are grouped and ordered to generate the complete die machining process. In this paper the identification of geometrical features is detailed. Geometrical features identification is based on machining knowledge formalization which is translated in the generation of maps from STL models. A map based on the contact area between cutting tools and die shape gives basic geometrical features which are connected or not according to the continuity maps. The proposed approach is illustrated by an application on an industrial study case which was accomplished as part of collaboration.

💡 Research Summary

The paper addresses the growing difficulty of preparing high‑speed machining (HSM) processes for forging dies whose geometries have become increasingly complex due to recent evolutions in forging technology. Traditional CAM preparation relies on a simple “void” representation of the die CAD model and does not exploit the rich geometric, topological, and technological information that is already available from the design stage. To bridge this gap, the authors propose a knowledge‑based machining process model that automatically transforms a CAD model of a complex forging die into a complete, optimized machining plan.

The methodology is organized into four main stages. First, the CAD model (exported as an STL mesh) is analysed to generate a contact map, which quantifies the area of contact between a candidate cutting tool and each surface element. A continuity map groups adjacent contact regions into elementary geometric features (e.g., pockets, cavities, curved surfaces). These elementary features constitute the geometric features of the die.

Second, technological data—material, required surface roughness, form tolerance—defined during the forging design, are attached to each geometric feature. Simultaneously, topological relations (adjacency, containment, contact) between features are identified, providing constraints for later tool‑path planning (e.g., avoiding interference between a pocket and a neighboring convex surface).

Third, a machining feature is defined as the combination of a geometric feature, its technological attributes, and its topological context. The authors maintain a curated tool database (tool diameter, length, material, maximum feed, etc.) and a library of HSM machining strategies (continuous sweep, Z‑level, parallel plane, curve‑guided). Using rule‑based knowledge, each machining feature is automatically matched with the most suitable tool and strategy. For instance, a surface requiring a fine finish is paired with a small‑diameter end mill, while a large cavity is assigned a high‑speed carbide or CVD‑diamond tool.

Fourth, the matched tool‑strategy pairs are assembled into a machining sequence. The sequence generation algorithm respects multiple objectives: minimising tool changes, preserving tool‑path continuity, reducing heat generation, and satisfying the technological constraints. The resulting sequence is exported as NC code compatible with commercial CAM systems.

The authors validate the approach on an industrial case study supplied by a forging die manufacturer. Compared with the conventional manual CAM preparation, the knowledge‑based system reduced preparation time by roughly 35 %, cut the number of tool changes by about 20 %, and produced parts that met all surface‑roughness and form‑tolerance specifications. The paper also discusses related work on feature recognition (syntactic pattern, graph‑based, rule‑based) and highlights how the proposed contact/continuity map technique offers a more direct link between the CAD geometry and machining knowledge.

Key contributions include: (1) a novel contact‑area based feature extraction method from STL meshes; (2) a formal integration of design‑stage technological data and topological relations into machining features; (3) a comprehensive knowledge base that links features to cutting tools and HSM strategies; and (4) a complete, automated generation of machining sequences for complex die geometries. Limitations are acknowledged: the current topological analysis focuses mainly on 2‑D relationships, and the tool database must be updated when new tools are introduced. Future work will explore 3‑D topological graph models, machine‑learning‑enhanced feature classification, and real‑time tool‑wear prediction to further improve adaptability and robustness of the system.