Is it possible to link such geometrical features with the entire injection production process? The difficulty relies on the unknown correlation among process variables, polymer material, molds and pieces geometries, and structural features.

A lot of effort has been put to study and monitor the correlations between process control variables, or to validate, at the design time, mold geometries by simulating the material flow dynamics inside the mold. However, no approach considers as a whole the entire industrialization and production process, starting from the desired features and the geometry of the piece, to the geometry of the mold, the material properties, and the process control through sensorized molds and machine parameters. This is the focus of Des-MOLD.

Our hypothesis is that within the new scenario where plastic converters industry has moved from highly standardized molds to customized products with small batches, it is possible to construct an intelligent knowledge-based system that uses as a main source, past empirical experiences and simulation data to optimize, at the design time, the geometries of the pieces and molds according to the desired features, and to the expected process control variables that will be monitored during production time. Artificial intelligence techniques such as case-based reasoning and computational argumentation permit both the inference of quantitative and qualitative information based on a large variety of empirical data and the justification of each decision.