Automated Generation of Custom Fit PPE Inserts: For Respiratory Masks Using 2D and 3D Anthropometric Data
2021 Association for Computer Aided Design in Architecture Annual Conference, ACADIA 2021
; 2021.
Article
in English
| Scopus | ID: covidwho-1981240
ABSTRACT
This research presents a machine learning-based interactive design method for the creation of customized inserts that improve the fit of the PPE 3M 1863 and 3M 8833 respiratory face masks. These two models are the most commonly used by doctors and professionals during the recent COVID-19 pandemic. The proper fit of masks is crucial for their performance. Characteristics and fit of current leading market brands were analyzed to develop a parametric design software workflow that resulted in a 3D printed insert customized to specific facial features and the mask that will be used. The insert provides a perfect fit for the respirator mask. Statistical face meshes were generated from an anthropometric database, and 3D facial scans and photos were taken from two hundred doctors and nurses on an NHS Trust hospital. The software workflow can start from either a 2D image of the face (picture) or a 3D mesh taken from a scanning device. The platform uses machine learning and a parametric design workflow based on key performance facial parameters to output the insert between the face and the 3M masks. It also generates the 3D printing file, which can be processed onsite at the hospital. The 2D image approach and the 3D scan approach used to initialize the system were digitally compared, and the resultant inserts were physically tested by twenty frontline personnel in an NHS Trust hospital. Finally, we demonstrate the criticality of proper fit on masks for doctors and nurses and the versatility of our approach augmenting an already tested product through customized digital design and fabrication. © Association for Computer Aided Design in Architecture Annual Conference, ACADIA 2021.
3D printers; Anthropometry; Computer architecture; Hospitals; Machine learning; Nursing; Product design; 2D images; Anthropometric data; Automated generation; Custom fits; Interactive design; Machine-learning; Parametric design; Performance; Respiratory masks; Software workflow; Computer aided design
Search on Google
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
2021 Association for Computer Aided Design in Architecture Annual Conference, ACADIA 2021
Year:
2021
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS