Fig. 1 Main scope and some common methods of casting simulation

Fig. 2 VAC process flowchart [84]

Fig. 3 ICME framework for casting design and process development as compared to industrial CAD-CAE-CAM approach [79]

Fig. 4 a The distribution of different areas of the casting; b the actual measured elongation results of each area [97]

Fig. 5 CA-FEA method based on ICME concept [28]

Fig. 6 Development elements of material genome engineering

Fig. 7 Neural network model for casting quality prediction

Fig. 8 Data-driven framework for prediction of porosity and process design in investment casting (HTC—heat transfer coefficient) [145]

Fig. 9 Hybrid model architecture of convolution neural network and depth neural network [135]

Fig. 10 Workflow of the filling system design with ANN-GA optimization loop [171]

Fig. 11 An example of temperature predictions of the solidifying steel: a actual and predicted temperature distributions at time step 2700, i.e., baseline model using bidirectional gated recurrent unit and proposed model using bidirectional long short-term memory; b actual and predicted temperature values along the distance from meniscus at the surface, middle, and center point [182]

Fig. 12 Flowchart of data-driven casting process design

Fig. 13 ICME for casting design (PVT—pressure-specific volume-temperature) [145]

Fig. 14 Prototyping platform of die-casting and processing cells: a data acquisition; b data transmission; c quality prediction [220]