skip to main content

Title: A machine learning framework for damage mechanism identification from acoustic emissions in unidirectional SiC/SiC composites

In this work, we demonstrate that damage mechanism identification from acoustic emission (AE) signals generated in minicomposites with elastically similar constituents is possible. AE waveforms were generated by SiC/SiC ceramic matrix minicomposites (CMCs) loaded under uniaxial tension and recorded by four sensors (two models with each model placed at two ends). Signals were encoded with a modified partial power scheme and subsequently partitioned through spectral clustering. Matrix cracking and fiber failure were identified based on the frequency information contained in the AE event they produced, despite the similar constituent elastic properties of the matrix and fiber. Importantly, the resultant identification of AE events closely followed CMC damage chronology, wherein early matrix cracking is later followed by fiber breaks, even though the approach is fully domain-knowledge agnostic. Additionally, the partitions were highly precise across both the model and location of the sensors, and the partitioning was repeatable. The presented approach is promising for CMCs and other composite systems with elastically similar constituents.

; ; ; ; ; ; ; ; ;
Award ID(s):
Publication Date:
Journal Name:
npj Computational Materials
Nature Publishing Group
Sponsoring Org:
National Science Foundation
More Like this
  1. The relationship between acoustic emission (AE) and damage source areas in SiC/SiC minicomposites was modeled using insights from tensile testing in-scanning electron microscope (SEM). Damage up to matrix crack saturation was bounded by: (1) AE generated by matrix cracking (lower bound) and (2) AE generated by matrix cracking, and fiber debonding and sliding in crack wakes (upper bound). While fiber debonding and sliding exhibit lower strain energy release rates than matrix cracking and fiber breakage, they contribute significant damage area and likely produce AE. Fiber breaks beyond matrix crack saturation were modeled by two conditions: (i) only fiber breaks generated AE; and (ii) fiber breaks occurred simultaneously with fiber sliding to generate AE. While fiber breaks are considered the dominant late-stage mechanism, our modeling indicates that other mechanisms are active, a finding that is supported by experimental in-SEM observations of matrix cracking in conjunction with fiber failure at rupture.
  2. Abstract

    The article examines degradation of a SiC‐based fiber composite containing Tyranno ZMI fibers in water vapor at elevated temperatures (800°C and 1100°C). Degradation is characterized through mechanical tests under cyclic and quasi‐static tensile loading in the near‐threshold regime, at stresses at or slightly above the matrix cracking limit. These tests are augmented by examinations of fracture surfaces and polished cross‐sections, measurements of fracture mirror radii, and measurements of interfacial debond toughness and sliding resistance. Degradation involves highly localized consumption of fibers through reactions of water vapor with the fibers and the BN coatings in regions adjacent to the few matrix cracks present at low stresses; the global hysteresis response and the average interfacial properties are minimally affected. Boria formed by oxidation of BN appears to play a fluxing role; it combines with silica on the fibers to form a non‐protective molten glass. Inhomogeneous fiber consumption leads to stress concentrations in the fibers and hence reduced fiber strength. Spatial variations in the degradation process occur at two length scales: at the macroscopic scale, because of cracking of the external CVI SiC overcoat and subsequent water ingress through the cracks, and at the tow‐scale, because of cracking of the CVI SiCmore »around the tows. Parsing the kinetic processes over the two length scales remains a significant challenge.

    « less
  3. Abstract

    Among many structural assessment methods, the change of modal characteristics is considered a well‐accepted damage detection method. However, the presence of environmental or operational variations may pollute the baseline and prevent a dependable assessment of the change. In recent years, the use of machine learning algorithms gained interest within structural health community, especially due to their ability and success in the elimination of ambient uncertainty. This paper proposes an end‐to‐end architecture to detect damage reliably by employing machine learning algorithms. The proposed approach streamlines (a) collection of structural response data, (b) modal analysis using system identification, (c) learning model, and (d) novelty detection. The proposed system aims to extract latent features of accessible modal parameters such as natural frequencies and mode shapes measured at undamaged target structure under temperature uncertainty and to reconstruct a new representation of these features that is similar to the original using well‐established machine learning methods for damage detection. The deviation between measured and reconstructed parameters, also known as novelty index, is the essential information for detecting critical changes in the system. The approach is evaluated by analyzing the structural response data obtained from finite element models and experimental structures. For the machine learning componentmore »of the approach, both principal component analysis (PCA) and autoencoder (AE) are examined. While mode shapes are known to be a well‐researched damage indicator in the literature, to our best knowledge, this research is the first time that unsupervised machine learning is applied using PCA and AE to utilize mode shapes in addition to natural frequencies for effective damage detection. The detection performance of this pipeline is compared to a similar approach where its learning model does not utilize mode shapes. The results demonstrate that the effectiveness of the damage detection under temperature variability improves significantly when mode shapes are used in the training of learning algorithm. Especially for small damages, the proposed algorithm performs better in discriminating system changes.

    « less
  4. Composite materials are increasingly used in the wind industries. Damage detection and health monitoring of composite materials are challenging due to the complex internal structure and unique material properties. Digital image correlation (DIC) and acoustic emission (AE) are both used for damage detection in structures. In this work, DIC performs a full-field strain measurement on the surface of the carbon-fiber specimen while AE continuously monitors and records the AE signals generated from specimen subsurface structure failures. These health monitoring techniques are integrated and evaluated in this study to correlate surface strain measurements and acoustic emission measurements on carbon-fiber specimens. The AE measurement results show that there is a correlation between the occurrence of AE events and the timing of complete specimen failure. DIC with a high-speed stereo camera system is also adopted to extract the change in the resonance frequencies and displacement and strain mode shapes of the specimen during experiments in cyclic loading.

  5. Abstract
    Site description. This data package consists of data obtained from sampling surface soil (the 0-7.6 cm depth profile) in black mangrove (Avicennia germinans) dominated forest and black needlerush (Juncus roemerianus) saltmarsh along the Gulf of Mexico coastline in peninsular west-central Florida, USA. This location has a subtropical climate with mean daily temperatures ranging from 15.4 °C in January to 27.8 °C in August, and annual precipitation of 1336 mm. Precipitation falls as rain primarily between June and September. Tides are semi-diurnal, with 0.57 m median amplitudes during the year preceding sampling (U.S. NOAA National Ocean Service, Clearwater Beach, Florida, station 8726724). Sea-level rise is 4.0 ± 0.6 mm per year (1973-2020 trend, mean ± 95 % confidence interval, NOAA NOS Clearwater Beach station). The A. germinans mangrove zone is either adjacent to water or fringed on the seaward side by a narrow band of red mangrove (Rhizophora mangle). A near-monoculture of J. roemerianus is often adjacent to and immediately landward of the A. germinans zone. The transition from the mangrove to the J. roemerianus zone is variable in our study area. An abrupt edge between closed-canopy mangrove and J. roemerianus monoculture may extend for up to several hundred metersMore>>