Automated fibre layup techniques are commonly used composite manufacturing processes in the aviation sector and require a manual visual inspection. Neural Network classification of defects has the potential to automate this visual inspection, however, the machine decision-making processes are hard to verify. Thus, we present an approach for visualising Convolutional Neural Network (CNN) based classifications of manufacturing defects and quantifying its robustness suitably. Our investigations have shown that especially Smoothed Integrated Gradients and DeepSHAP are particularly well suited for the visualisation of CNN classifications. The Smoothed Integrated Gradients technique also reveals advantages in robustness when evaluating degraded input images.
After the rediscovery of the normal tissue sparing effect of high dose rate radiation, i.e. the so-called FLASH effect, by Favaudon et al. in 2014, research activities on this topic have been revived and are flourishing ever since. Yet, the exact biological mechanism as well as the required boundary conditions and radiation qualities to reach said sparing remain mostly unclear.
We present a laser-based irradiation platform at the Draco PW facility that enables systematic studies into the FLASH regime using proton peak dose rates of up to 10^9 Gy/s. Besides the PW class laser acceleration source, a key component is a pulsed high-field beamline to transport and shape the laser driven proton bunches spectrally and spatially in order to generate homogeneous dose distributions tailored to match the irradiation sample.
Making use of the diverse capabilities of the laser driven irradiation platform a pilot experiment of highest complexity has been conducted – a systematic in-vivo tumor irradiation in a specifically developed mouse model.
A plethora of online particle diagnostics, including Time-of-Flight, bulk scintillators and screens as well as ionization chambers, in conjunction with diagnostics for retrospective absolute dosimetry (radiochromic films) allowed for an unprecedented level of precision in mean dose delivery (±10 %) and dose homogeneity (±5 %) for the challenging beam qualities of a laser accelerator. The tailored detector suite is complemented by predictive simulations.
The talk addresses how our interdisciplinary team overcame all hurdles from animal model development, over enhancing the laser and laser acceleration stability, to dose delivery and online dose monitoring. Results on radiation induced tumor growth delay by laser driven as well as conventionally accelerated proton beams are critically discussed.
The Automated Fiber Placement process is established in the aerospace industry for the production of composite components. This technique places several narrow material strips in parallel. Within current industrial Automated Fiber Placement processes the visual inspection takes typically up to 50% of overall production time. Furthermore, inspection quality highly depends on the inspector. Therefore, automation of visual inspection offers a great improvement potential. To ensure reliable defect detection the segmentation of individual defects must be investigated. For this reason, this paper focusses on an assessment of defect segmentation algorithms. Therefore, 29 structural, statistical and spectral algorithms from related work were assessed, theoretically, using the 12 most relevant criteria as assessed from literature and process requirements. Then, seven most auspicious algorithms were analysed in detail. For reasons of determinism, Neural Network approaches are not part of this paper. Manually labelled prepreg defect images from a laser line scan sensor were used for tests. The test samples contain five defect types with 50 samples of each. Additionally, layups without defects were analysed. It was concluded that Adaptive Thresholding works best for global defect segmentation. The Cell Wise Standard Deviation Thresholding performs also quite well, but is very sensitive to grid size. Feasible algorithms perform reliable defect segmentation for layed up material.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.