Manufacturing / Industry / Healthcare & Insurance

DATA-DRIVEN INSPECTION EXPERT SYSTEM FOR ADDITIVE MANUFACTURING

Code:

REACH-2021-THEMEDRIVEN-CERR_8

Domain:

Manufacturing / Industry / Healthcare & Insurance

Description of the DVC THEME

Additive manufacturing (AM) technology is considered one of the most promising advanced technologies for manufacturing. Compared with traditional manufacturing such as CNC tools, forging, and welding, AM technology has advantages such as no need for tools or molds, high material utilization, short product manufacturing cycle, and the ability to manufacture complex structures. All AM systems work on the same principle of building a structure additively from a substrate. Some AM processes have the ability to print various materials including polymers, metals, ceramics, and composites. AM is especially suitable for low-cost, short-cycle, rapid prototyping or even production of large and complex metal structures.
At present, AM alone is not fully capable of producing parts with suitable mechanical properties and surface roughness that meet the requirements of most applications. AM components are known to have various defects, such as powder agglomeration, balling, porosity, internal cracks and thermal/internal stress, which can significantly affect the quality, mechanical properties and safety of final parts.
Defect inspection methods are critical for reducing manufactured defects, controlling the process during manufacturing or improving the surface quality and keeping under control the mechanical properties of AM components. Traditional defect detection technology can be combined with high-resolution visual images to optimise defect detection and fault prediction and diagnosis technology.

Sub-challenges composing this experiment:

This DVC THEME is composed of one main challenge:

Expected global results:

  1. Optimize printing process understanding defects source and occurrences during manufacturing
  2. Improve process efficiency developing descriptive-predictive-prescriptive data-driven models
  3. Increase processes sustainability level, total cost of ownership savings