This approach lacks the extra information on individual systems with interval-censored data and time-varying weapon system characteristics. A recent method introduced the covariates. We analyze and benchmark our approach, Weibull-Cox Bayesian Neural Network tested on several LaplaceNN, on synthetic and real datasets with standard weapon systems, albeit requiring a held-out validation set [7]. classification metrics such as Receiver Operating Characteristic Moreover, while understanding the population reliability trends (ROC) Area Under Curve (AUC) Precision-Recall (PR) AUC, via a Weibull distribution is informative, this formulation does and reliability curve visualizations.

We propose to integrate weapon system features (such as weapon system manufacturer, deployment time and location, storage time and location, etc.) into a parameterized Cox-Weibull [1] reliability model via a neural network, like DeepSurv [2], to improve predictive maintenance. In parallel, we develop an alternative Bayesian model by parameterizing the Weibull parameters with a neural network and employing dropout methods such as Monte-Carlo (MC)-dropout for comparative purposes. Due to data collection procedures in weapon system testing we employ a novel interval-censored log-likelihood which incorporates Monte-Carlo Markov Chain (MCMC) [3] sampling of the Weibull parameters during gradient descent optimization. We compare classification metrics such as receiver operator curve (ROC) area under the curve (AUC), precision-recall (PR) AUC, and F scores to show our model generally outperforms traditional powerful models such as XGBoost and the current standard conditional Weibull probability density estimation model.

DECEMBER 30, 2021 – Naval Surface Warfare Center, Crane Division (NSWC Crane), Office of Naval Research (ONR) and the NavalX Midwest Tech Bridge (MTB) recently announced the winners of the Artificial Intelligence for Small Unit Maneuvers (AISUM) Prize Challenge. EpiSys Science, Inc. (Episci) took first place and Draper, Inc. (Draper) took second place. According to their website, Episci is "a multidisciplinary innovation company that develops next-generation autonomous technologies for defense, aerospace, and commercial applications." Draper's website says the organization "serves our nation's interests and security needs; advances technologies at the intersection of government, academia, and industry; cultivates the next generation of innovators; and solves the most complex challenges." "The overall goal of this challenge was to move the technology needle," said Amy Ross, Program Manager for the AISUM Prize Challenge.

NAVSEA, Naval Surface Warfare Center, Crane Division has been using Instaknow-ACE software for the last two years for several important applications. We have found this innovative Information Technology tool to be ideal for the 21st Century Information Age. The efficiencies this tool brings to the business models are enormous. We have found that extracting data from the different sources and turning this into enriched information allows you to readily obtain knowledge for solid System Engineering judgments.