NDE Big Data Framework

NDE data has become "Big Data", and is overwhelming the abilities of NDE technicians and commercially available tools to deal with it. In the current state of the art in industrial practice, there is no integration of the NDE data into design data, NDE models, and structural integrity models for a holistic structural capability assessment. Our proposal responds to these issues described in the subtopic H13.01, Advanced NDE Modeling and Analysis. TRI/Austin, Iowa State University's Center for Nondestructive Evaluation (CNDE), and Computational Tools are teaming to develop a coherent set of tools for NDE and SHM data: the NDEToolbox™. The significance of the innovations are that these sets of tools enable "big data" methods to be applied to NDE, and to integrate NDE within the digital thread of design, manufacturing, and operation of large composite structures for space and aerospace applications.

The two main categories of NASA applications are in support of in house R&D, and in the inspection of structures for NASA applications by NASA or its suppliers. Simple file management does not support contextual searching or Big Data tools, and the Databrowse component of the NDEToolbox™ will answer that problem. HDF5 formatting will enable storage of data that outlasts proprietary vendor formats, while supporting advanced tools like Databrowse and optimized routines for reading, writing, and searching in Python, the language of NDEToolbox™. Existing databases or network storage facilities can be accommodated without changes. The implementation of NDEToolbox™ in Python is by definition and by our choice an open source implementation. The plug-in architecture provides a simple path for many customizations. The basic, everyday needs of opening, viewing, processing NDE data will be at hand and will be open for the researcher to understand and extend as needed.

We envision three main categories of users for the NDEToolbox™ outside of NASA. The first category is universities. University laboratories like those at CNDE suffer from the same issues of data management and the need to have access to their data for research purposes. By making NDEToolbox™ open source and easily extended, we hope to gain traction in the university community and to benefit from contributions of additional technology back to the NDEToolbox™. Other commercial laboratories and government R&D laboratories share many of the same needs as NASA and can similarly benefit. Finally, we do see the possibility for commercial implementations of specialized sets of algorithms, such as those being developed by Computational Tools and TRI/Austin for suppliers to the F-35 program.

This is early/mid-stage (TRL 6) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.