Deep Learning Unlocks X‐ray Microtomography Segmentation of Multiclass Microdamage in Heterogeneous Materials. Issue 11 (14th February 2022)

• Record Type: Journal Article
• Authors: Kopp, Reed; Joseph, Joshua; Ni, Xinchen; Roy, Nicholas; Wardle, Brian L.
• Is Part Of: Advanced materials. Volume 34:Issue 11(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-02-14
• Subjects: 3D multiclass damage -- deep learning -- heterogeneous materials -- machine learning -- material characterization; Materials -- Periodicals; Chemical vapor deposition -- Periodicals; 620.11
• DOI: 10.1002/adma.202107817
• Languages: English
• ISSNs: 0935-9648

Abstract

Abstract: Four‐dimensional quantitative characterization of heterogeneous materials using in situ synchrotron radiation computed tomography can reveal 3D sub‐micrometer features, particularly damage, evolving under load, leading to improved materials. However, dataset size and complexity increasingly require time‐intensive and subjective semi‐automatic segmentations. Here, the first deep learning (DL) convolutional neural network (CNN) segmentation of multiclass microscale damage in heterogeneous bulk materials is presented, teaching on advanced aerospace‐grade composite damage using ≈65 000 (trained) human‐segmented tomograms. The trained CNN machine segments complex and sparse (<<1% of volume) composite damage classes to ≈99.99% agreement, unlocking both objectivity and efficiency, with nearly 100% of the human time eliminated, which traditional rule‐based algorithms do not approach. The trained machine is found to perform as well or better than the human due to "machine‐discovered" human segmentation error, with machine improvements manifesting primarily as new damage discovery and segmentation augmentation/extension in artifact‐rich tomograms. Interrogating a high‐level network hyperparametric space on two material configurations, DL is found to be a disruptive approach to quantitative structure–property characterization, enabling high‐throughput knowledge creation (accelerated by two orders of magnitude) via generalizable, ultrahigh‐resolution feature segmentation. Abstract : A deep‐learning machine is created to segment sparse, multiclass microdamage in advanced composite laminates that feature complex microstructures and failure behavior, with ≈99.99% binary accuracy using 65 000 tomograms in 3D X‐ray datasets. The deep‐learning approach accelerates heterogeneous materials knowledge creation by two orders of magnitude in a generalizable way, breaking a longstanding bottleneck while additionally introducing objectivity.