Knowledge-Based Adaptation of Product and Process Design in Blisk Manufacturing

Abstract

Early and efficient harmonization between product design and manufacturing represents one of the most challenging tasks in engineering. Concepts such as simultaneous engineering aim for a product creation process, which addresses both, functional requirements as well as requirements from production. However, existing concepts mostly focus on organizational tasks and heavily rely on the human factor for the exchange of complex information across different domains, organizations or systems. Nowadays product and process design make use of advanced software tools such as computer-aided design, manufacturing and engineering systems (CAD/CAM/CAE). Modern systems already provide a seamless integration of both worlds in a single digital environment to ensure a continuous workflow. Yet, for the holistic harmonization between product and process design, a complete and data consistent digital twin, an adaptation of product and process design for a balanced functionality and manufacturability, as well as systematic long-term data analytics across different product and process designs are missing. This paper presents an exploration concept which couples product design (CAD), process design (CAM), process simulation (CAE) and process adaptation in a single software system. The approach provides insights into correlations and dependencies between input parameters of product/process design and the process output. The insights potentially allow for a knowledge-based adaptation, tackling well-known optimization issues such as parameter choice or operation sequencing. First results are demonstrated using the example of a blade integrated disk (blisk).

The Elements of Flexibility for Task-Performing Systems

“…Moreover, flexibility considerations are becoming more complex, taking very deep aspects of the production processes into account such as material properties and not only the operational phase but also development and ramp-up. Hence, software systems such as CAD, CAE, and CAM are increasingly included in automation and flexibility considerations [30].…”

“…Let us now describe one variant of LCFP that is actually addressed in [88] using the language of the flexibility formalism. The considered task context consists of tasks T that all share the same environment E but have different goals t : X → Y of the form t(x 1 , x 2 , x 3 , x 4 ) = f (g(x 1 , x 2 ), h(x 3 , x 4 )) (30) where g, h ∈ {EQ, XOR} and f ∈ {AND, OR}. More specifically, we have a training task context…”

A Survey on AI-Driven Digital Twins in Industry 4.0: Smart Manufacturing and Advanced Robotics

“…AI-driven digital process twins are envisioned to learn and interpret implicit correlations between manufacturing processes and material/process/environmental parameters from an aggregation of (heterogeneous) data with the objective of optimizing process development, production ramp-up, and quality assurance cycle. From an engineering implementation perspective, we have noted that despite the significance of algorithms and models, novel sensor technologies [167,[213][214][215][216][217] and networked digital process chains [218][219][220][221][222] should not be neglected, as they are essential pillars for constructing DTs and can considerably influence the effectiveness and efficiency of their development and deployment in practice. Figure 5 shows an example of a DT dynamically mapping the manufacturing process of an aerospace part and the data sources involved from the contextualized CAD-CAM-CNC-CAQ process chain.…”