Historically, the development of armor ceramics can be largely described as heuristic. Recently, advanced machine learning algorithms are being developed to accelerate advanced material discovery. As many important material properties depend on microstructure, segmentation algorithms applied to scanning electron microscope (SEM) images enable quantification of identified features. The desired goal is to relate key image metrics to quantified physical properties and make useful performance predictions and improvements faster than otherwise possible. Collecting large image datasets with high signal to noise ratio, even with automation, can be laborious. Moreover, traditional methods of establishing image ground truth often rely on supervised hand-tracing, which precludes application to 1000’s of images. This study creates an approximate ground truth automatically using Otsu’s algorithm to evaluate large image data sets with varying signal to noise ratio and understand the influence of noise on network model efficiency. The robustness of a U-net algorithm, commonly used for image segmentation, was optimized by introducing artificial noise to the training data. Initial work assessed the performance of generative adversarial networks in applying artificial noise to the images. Next, a U-net was generated while incorporating artificial and real noise into the training and validation sets respectively. The impact of training using artificial noise upon the accuracy of the resulting U-Net in segmenting real images of low quality are described below.
Magnesium aluminate spinel is a durable, broadband, electro-optical material that can be readily manufactured into
transparent domes for multimode seeker applications. Actual spinel domes have suffered from manufacturing difficulties
and light-scattering inclusions. The program described herein has solved many of the difficulties to achieve better optical
properties and better process yields.
Transparent magnesium aluminate spinel is an attractive material for use in a wide range of optical applications
including windows, domes, armor, and lenses, which require excellent transmission from the visible through to the mid
IR. Theoretical transmission is very uniform and approaches 87% between 0.3 to 5 microns. Transmission
characteristics rival that of ALON and sapphire in the mid-wave IR, making it especially attractive for the everincreasing
performance requirements of current and next-generation IR imaging systems. Future designs in missile
technology will require materials that can meet stringent performance demands in both optical and RF wavelengths. Loss
characteristics for spinel are being investigated to meet those demands. Technology Assessment and Transfer Inc. (TA&T), have established a 9000 ft2 production facility for optical quality
spinel based on the traditional hot-pressing followed by hot isostatic pressing (HIPing) route. Additionally, TA&T is
developing pressureless sintering - a highly scalable, near net shape processing method based on traditional ceramic
processing technology - to fabricate optical components. These two main processing approaches allow the widest
variety of applications to be addressed using a range of optical components and configurations. The polycrystalline
nature of spinel facilitates near net shape processing, which provides the potential to fabricate physically larger optical
parts or larger quantities of parts at significantly lower costs compared to single crystal materials such as sapphire.
Current research is focused at optimizing the processing parameters for both synthesis routes to maximize strength and
transparency while minimizing the cost of fabrication.
There are presently three materials (sapphire, ALON and spinel) which exhibit a desirable combination of material properties such as hardness, strength, and transmission in MWIR that are considered for various window/dome applications. Of the three, sapphire exists in a number of service applications. It is, however, the most expensive of the three and depending on application, can have significant drawbacks owing to its birefringent nature. ALON, by comparison is less expensive, benefits from greater development efforts, is an easily shaped polycrystalline ceramic, optically does not possess the birefringent nature of sapphire, but requires very high formation temperatures for the starting powders and equally long processing times for fabricated parts. The remaining material, transparent spinel, offers improved optical performance over the spectrum from UV to MWIR, comparable mechanical properties, and can be fabricated at much lower temperatures and shorter times than the other materials making it less expensive to produce. Data will be described which compares the transparency and mechanical properties and discusses the relevant processing efforts for spinel products.
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.