Predicting Breakdown Risk Based on Historical Maintenance Data for Air Force Ground Vehicles

Jeff Jang; Dilan Nana; Jack Hochschild; Jordi Vila Hernandez de Lorenzo

Home/Archive/arXiv

arXiv · 2112.13922

Predicting Breakdown Risk Based on Historical Maintenance Data for Air Force Ground Vehicles

Jeff Jang·Dilan Nana·Jack Hochschild·Jordi Vila Hernandez de Lorenzo

View original source ↗Read source document ↗Export metadata ↓

Abstract

Unscheduled maintenance has contributed to longer downtime for vehicles and increased costs for Logistic Readiness Squadrons (LRSs) in the Air Force. When vehicles are in need of repair outside of their scheduled time, depending on their priority level, the entire squadron's slated repair schedule is transformed negatively. The repercussions of unscheduled maintenance are specifically seen in the increase of man hours required to maintain vehicles that should have been working well: this can include more man hours spent on maintenance itself, waiting for parts to arrive, hours spent re-organizing the repair schedule, and more. The dominant trend in the current maintenance system at LRSs is that they do not have predictive maintenance infrastructure to counteract the influx of unscheduled repairs they experience currently, and as a result, their readiness and performance levels are lower than desired. We use data pulled from the Defense Property and Accountability System (DPAS), that the LRSs currently use to store their vehicle maintenance information. Using historical vehicle maintenance data we receive from DPAS, we apply three different algorithms independently to construct an accurate predictive system to optimize maintenance schedules at any given time. Through the application of Logistics Regression, Random Forest, and Gradient Boosted Trees algorithms, we found that a Logistic Regression algorithm, fitted to our data, produced the most accurate results. Our findings indicate that not only would continuing the use of Logistic Regression be prudent for our research purposes, but that there is opportunity to further tune and optimize our Logistic Regression model for higher accuracy.

Explore related subjects

cs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Jeff Jang, Dilan Nana, Jack Hochschild, Jordi Vila Hernandez de Lorenzo. 2021-12-22. Predicting Breakdown Risk Based on Historical Maintenance Data for Air Force Ground Vehicles. https://arxiv.org/abs/2112.13922

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Rollout Total Correlation for Deep Reinforcement Learning

Learning task-relevant representations is crucial for reinforcement learning. Recent approaches aim to learn such representations by improving the temporal consistency in the observed transitions. However, they only consider individual transitions and can fail to achieve long-term consistency. Instead, we argue that capturing aspects of the state that correlate with other states and actions of the trajectory---even more distant in the future---could further help in extracting task-relevant information. Hence, in this paper we investigate how to learn representations by maximizing the rollout total correlation, the correlation among all learned representations and actions within the trajectories produced by the agent. For improving rollout total correlation, we propose to combine two complementary lower bounds based on a generative and a discriminative model, combined with a simple and effective technique of chunk-wise mini-batching. Furthermore, we propose an intrinsic reward based on the learned representation for better exploration. Experimental evaluations on a set of challenging image-based simulated control tasks show that our method achieves better sample efficiency, and robustness to both white noise and natural video backgrounds compared to leading baselines.

cs.LG↗

arXiv2026

Reward Shaping to Mitigate Reward Hacking in RLHF

Reinforcement learning from human feedback (RLHF) is widely used to align large language models (LLMs) with human preferences. However, RLHF remains vulnerable to \emph{reward hacking}, whereby a policy exploits imperfections in the reward function instead of learning the intended behavior, thereby undermining alignment. Although reward shaping can stabilize RLHF training and partially mitigate reward hacking, shaping methods and their underlying design principles have not been systematically investigated. To address this gap, we conduct a comprehensive study of prevalent reward-shaping techniques. Our analysis identifies two key design principles: (1) the reinforcement-learning reward should be bounded, and (2) it should grow rapidly at first and then gradually saturate. Motivated by these principles, we propose Preference as Reward (PAR), a novel method that uses the latent preferences encoded in the reward model as the reinforcement-learning signal. We further show that PAR possesses two variance-reduction properties that stabilize RLHF training and substantially widen the practical window for early stopping. Our evaluation consists of two parts. First, we compare PAR with several other reward-shaping strategies using Proximal Policy Optimization (PPO) as the reinforcement-learning algorithm and Gemma2-2B as the base model. Second, we compare PAR with the vanilla baseline (i.e., unshaped reward) across four base models and four reinforcement-learning algorithms. In the first set of experiments, PAR consistently outperforms other reward-shaping methods and also reflects high data efficiency and robustness. The second set of experiments shows that PAR is particularly effective for actor-critic RL algorithms when value estimates become unstable and demonstrates its effectiveness across different base models. The code is available at https://github.com/PorUna-byte/PAR.

cs.LG↗

arXiv2026

Trajectory Entropy Reinforcement Learning for Robust Robot Motor Skill Learning

Simplicity is a critical inductive bias for designing data-driven controllers, especially when robustness is important. Despite the impressive results of deep reinforcement learning in complex control tasks, it is prone to capturing intricate and spurious correlations between observations and actions, leading to failure under slight perturbations to the environment. To tackle this problem, in this work we introduce a novel inductive bias towards simple policies in reinforcement learning. The simplicity inductive bias is introduced by minimizing the entropy of entire action trajectories, corresponding to the number of bits required to describe information in action trajectories after the agent observes state trajectories. Our reinforcement learning agent, Trajectory Entropy Reinforcement Learning, is optimized to minimize the trajectory entropy while maximizing rewards. We show that the trajectory entropy can be effectively estimated by learning a variational parameterized action prediction model, and use the prediction model to construct an information-regularized reward function. Furthermore, we construct a practical algorithm that enables the joint optimization of models, including the policy and the prediction model. Experimental evaluations on several high-dimensional locomotion tasks show that our learned policies produce more cyclical and consistent action trajectories, and achieve superior performance, and robustness to noise and dynamic changes than the state-of-the-art.

cs.LG↗