&lt;title&gt;Composite damage assessment employing an optical neural network processor and an embedded fiber-optic sensor array&lt;/title&gt;

Grossman, Barry G.; Gao, Xing; Thursby, Michael H.

doi:10.1117/12.50165

Cited by 8 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They can learn to process data one way, and when conditions change, the processing can adapt to new conditions. ANN applications for delamination detection in composite structures, including damage assessment and fatigue monitoring, have been extensively studied [24][25][26][27][28][29][30][31][32][33][34][35][36][37][38]. Neural networks have been coupled with advanced sensing technologies to predict and generalize unknown parameters in physical systems.…”

Section: Introductionmentioning

confidence: 99%

Impact-induced damage characterization of composite plates using neural networks

Watkins

Akhavan

Dua

et al. 2007

Smart Mater. Struct.

View full text Add to dashboard Cite

Impact-induced damage in fiber-reinforced laminated composite plates is characterized. An instrumented impact tower was used to carry out low-velocity impacts on thirteen clamped glass/epoxy composite plates. A range of impact energies was experimentally investigated by progressively varying impactor masses (holding the impact height constant) and varying impact heights (holding the impactor mass constant). The in-plane strain profiles as measured by polyvinylidene fluoride (PVDF) piezoelectric sensors are shown to indicate damage initiation and to correlate to impact energy. Plate damage included matrix cracking, fiber breakage, and delamination. Electronic shearography validated the existence of the impact damage and demonstrated an actual damage area larger than visible indications. The strain profiles that are associated with damage were replicated using an in-house finite element code. Using these simulated strain signatures and the shearography results, a backpropagation artificial neural network (ANN) is shown to detect and classify the type and severity of damage.

show abstract

Section: Introductionmentioning

confidence: 99%

Impact-induced damage characterization of composite plates using neural networks

Watkins

Akhavan

Dua

et al. 2007

Smart Mater. Struct.

View full text Add to dashboard Cite

show abstract

“…ANNs are numerical models whose inputs are strain readings from sensors. They can be 'trained' on the basis of results from finite element modelling [41,47,141,147], fast Fourier transform [138,142,145] or phenomenological models [143,144,146] for known damage/deformed states. The trained networks are then used to deduce the locations of unknown impact damage from measured strain values.…”

Section: Determination For the Location Of Impact Damagementioning

confidence: 99%

Damage detection and assessment in fibre-reinforced composite structures with embedded fibre optic sensors-review

Zhou¹,

Sim

2002

Smart Mater. Struct.

233

140

View full text Add to dashboard Cite

A state-of-the-art review is presented regarding the research and development of in situ fibre optic damage detection and assessment systems (FODDAS) embedded in fibre-reinforced composite structures. Representative individual fibre optic strain sensors and distributed sensor networks are briefly described. A major emphasis is placed on their capabilities for detecting damage, determining damage location and assessing the nature of damage, arising primarily from specific events such as impacts or quasi-static stress overloads. The main features of such systems as custom-built and structure-specific units with minimal human involvement are highlighted. Issues that could affect the validity of the performance of such strain sensors are discussed. Fracture and non-fracture of fibre optic sensors are identified as two fundamentally different approaches for damage detection and their primary features are discussed in relation to location determination and evaluation of the nature of damage. The major advantages and limitations of each approach are discussed. Directions and areas of potential future research in the development of related FODDAS are highlighted.

show abstract

Fiber Optics, Theory and Applications

Udd¹

2002

Encyclopedia of Smart Materials

View full text Add to dashboard Cite

Most fiber‐optic smart structure applications fall into one of four major categories. The first is smart manufacturing where fiber‐optic sensors are embedded or attached to parts during the manufacturing process. They are then used to monitor such parameters as temperature, pressure, viscosity, degree of cure, and residual strain. After the parts have been made, the same sensors or another set may be used for the second application area of nondestructive testing. Here, the fiber sensors may be used to measure acoustic signatures, changes in strain profiles, delamination, and other indications of changes in the structural characteristics of fabricated parts. The third aspect of fiber‐optic smart structures that has been the focus of many efforts is health and damage assessment systems for structures. In the parts of the structure that have been assembled, fiber‐optic sensor technology is used to monitor the overall health of the structure. Examples include the status of buildings, bridges, and dams and checks to support the maintenance of aircraft. Finally, fiber‐optic smart structures may be used to support control systems. Unlike health and damage assessment systems, which simply monitor changes in the structure, these control systems measure the environmental effects that act on the structure and then react to them. Examples of these types of structures are buildings that sense and readjust to earthquakes to minimize damage and airplanes that are designed to react to structural changes by adjusting their flight envelopes. Fiber‐optic sensors that are particularly useful for smart structures are briefly overviewed, followed by examples of applications.

show abstract

<title>Composite damage assessment employing an optical neural network processor and an embedded fiber-optic sensor array</title>

Cited by 8 publications

References 0 publications

Impact-induced damage characterization of composite plates using neural networks

Impact-induced damage characterization of composite plates using neural networks

Damage detection and assessment in fibre-reinforced composite structures with embedded fibre optic sensors-review

Fiber Optics, Theory and Applications

Contact Info

Product

Resources

About