This work aims to evaluate the current state of research on the use of artificial intelligence, deep learning, digitalization, and Data Mining in product development, mainly in the mechanical and mechatronic domain. These methods, collectively referred to as “digital engineering”, have the potential to disrupt the way products are developed and improve the efficiency of the product development process. However, their integration into current product development processes is not yet widespread. This work presents a novel consolidated view of the current state of research on digital engineering in product development by a literature review. This includes discussing the methods of digital engineering, introducing a product development process, and presenting results classified by their individual area of application. The work concludes with an evaluation of the literature analysis results and a discussion of future research potentials.

Access to internal fields such as stress, temperature, and fatigue indicators is essential for condition monitoring, yet direct sensing is often impractical. Finite element method (FEM)-based virtual sensors address this gap by combining sparse measurements with physics-based models. This work compares two virtual sensor workflows. The live FEM approach executes a model on demand and provides high-fidelity estimates at the cost of multi-second runtimes. The lookup database approach shifts computation offline by precomputing responses and answering online queries by fast interpolation. We introduce a quantitative cost model that links measured runtime scaling, offline construction effort, and online latency to deployment choices. The cost model is evaluated through timing studies, accuracy assessments, and an empirical break-even analysis relating offline effort to the expected number of online queries. Two case studies illustrate the method, a nonlinear tension-bar benchmark and a steady-state thermal model of a CPU die. Live FEM runtime follows a power law with $\alpha \approx 1.2$ for the tensile case and an effective $\alpha \approx 0.66$ for the CPU case due to dominant overheads. The resulting rules translate accuracy targets and latency budgets into workflow-selection criteria that support integration into digital-twin and monitoring pipelines.

We present a geometry-based complexity factor for additive manufacturing that estimates relative printing effort of fused filament fabricated parts from STL geometry alone. A reference effort is derived by slicing thousands of parts and volume-equivalent cubes. Eight interpretable geometric metrics feed a constrained, regularised index with monotonic calibration, achieving robust test accuracy and revealing which shape features dominate structural complexity.