Bayesian Weapon System Reliability Modeling with Cox-Weibull Neural Network

TL;DR

This paper introduces a novel Bayesian Cox-Weibull neural network model incorporating weapon system features for improved reliability prediction and maintenance, outperforming traditional models in classification metrics.

Contribution

It develops a new neural network-based Bayesian reliability model with interval-censored likelihood and MCMC sampling, enhancing predictive accuracy over existing methods.

Findings

Model outperforms XGBoost and standard Weibull models in ROC AUC.

Incorporates weapon system features into reliability modeling.

Uses novel interval-censored likelihood with MCMC sampling.

Abstract

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.