GOST R 71688-2024 Artificial intelligence in the field of additive production

Chronicle

2024: GOST approval

In mid-November 2024, Rosstandart approved GOST R 71688-2024 - "Artificial Intelligence. Data sets for the development and verification of machine learning models for indirect measurement of the physical and mechanical properties of additive production objects. General requirements. " The document was developed by the Federal State Budgetary Institution "Russian Institute of Standardization."

It is noted that one of the main goals in the field of designing new composite materials is to predict their reliability and durability. Existing methods of property prediction are related to the state of the internal structure of the material, and therefore the corresponding calculations are a resource-intensive task. However, the physical and mechanical parameters obtained from standard tests can be used to "indirectly" predict the durability and durability of the product without additional studies of the internal structure of the material using machine learning and AI algorithms.

𝓲

Freepik

The adopted standard establishes the requirements for data sets used for the development and verification of machine learning for indirect measurements of the physical and mechanical properties of additive production (3D printing) objects. The document defines the selection of methods for collection, analysis, post-processing of the additive manufacturing data set, as well as methods for quality control and completeness of the data sets for indirect measurement of the properties of nodes and subassemblies.

For an effective approach to the process of structuring information and input data, as noted, it is necessary to use two classes of indicators: the technological parameters of additive production itself and the physical and mechanical properties of objects obtained by 3D printing. This approach should take into account various aspects of production processes and allow the creation of machine learning models that improve the quality of end objects.^[1]

Notes