arXiv subjects

Boyang Xu

Publications and source records attributed to Boyang Xu.

6 recordsLinked to original sources

arXiv2026

Adaptive Sampling for Automated Post-Disaster Rapid Damage Assessment via Level-Set Cost-Aware Bayesian Optimization

Natural disasters frequently inflict severe damage to the built environment, which demands a rapid, reliable, and cost-effective damage assessment for emergency response. However, traditional methods for post-disaster damage assessment often rely on static, labor-intensive data collection strategies that can be prohibitively expensive and struggle to adapt to dynamic post-disaster conditions. In this study, we propose a cost-aware Bayesian optimization framework combined with level-set estimation that continuously guides autonomous data collectors, e.g., an unmanned aerial vehicle (UAV), toward the most informative regions. By dynamically updating damage estimates across different geographic zones, our approach systematically reduces uncertainty while minimizing operational costs. The proposed framework is first validated using a controlled synthetic toy study, demonstrating the agent's ability to efficiently trace damage boundaries, recover the underlying damage map, and rapidly reduce predictive uncertainty. Furthermore, the approach is evaluated using high-fidelity disaster data generated by the Regional Resilience Determination (R2D) software. The results of the algorithm provide accurate and timely damage estimates that support informative and fast emergency response.

cs.LG↗

arXiv2026

General Value Functions for Remaining Useful Life and Failure-Mode Prediction

Remaining useful life (RUL) prediction and failure-mode classification are central tasks in predictive maintenance. Many data-driven pipelines use fixed-window supervised learning with complete terminal labels; such routes do not naturally encode the temporal recursion linking successive degradation-state predictions when observations are partial or unit identities are unavailable. We formulate prognostics as vector General Value Function (GVF) prediction on an absorbing degradation process, treating RUL and failure-mode probabilities as temporally consistent targets rather than independent window-level labels, and estimate them with a multi-step temporal-difference estimator, TD($n,\lambda$). Supporting theory identifies the Bellman fixed point of the vector GVFs, characterizes the linear projected-TD limit and its relation to complete-return Monte Carlo regression under realizability, and explains when bootstrapped TD targets are less variable than Monte Carlo returns. On an event-triggered multimode simulation and NASA C-MAPSS label-scarce stitch data, TD improves RUL and failure-mode prediction relative to a supervised same-backbone Monte Carlo control, especially under scarce complete labels. Practically, fragmented, identity-free degradation records can contribute local Bellman transitions instead of being discarded until complete run-to-failure labels are available.

stat.ML↗

arXiv2026

Path-Coupled Bellman Flows for Distributional Reinforcement Learning

Distributional reinforcement learning (DRL) models the full return distribution, but existing finite-support or quantile-based methods rely on projections, while recent flow-based approaches can suffer from \emph{boundary mismatch} at the flow source or from \emph{high-variance} bootstrapping when current and successor noises are independent. We propose Path-Coupled Bellman Flows (PCBF), a continuous-time DRL method that learns return distributions with flow matching using \textbf{source-consistent Bellman-coupled paths}: the current path starts from the required base prior at $t{=}0$, reaches the Bellman target at $t{=}1$, and maintains a pathwise affine relation to the successor flow at intermediate times (without requiring time-$t$ marginals to satisfy a distributional Bellman fixed point for all $t$). PCBF couples current and successor return flows through shared base noise and uses a $\lambda$-parameterized control-variate target: $\lambda{=}0$ recovers an unbiased sample Bellman target, while $\lambda{>}0$ trades controlled bias for variance reduction. Experiments on analytically tractable MRPs, OGBench, and D4RL show improved distributional fidelity and training stability, and competitive offline RL performance.

cs.LG↗

arXiv2025

Partially Observable Markov Decision Process Framework for Operating Condition Optimization Using Real-Time Degradation Signals

In many engineering systems, proper predictive maintenance and operational control are essential to increase efficiency and reliability while reducing maintenance costs. However, one of the major challenges is that many sensors are used for system monitoring. Analyzing these sensors simultaneously for better predictive maintenance optimization is often very challenging. In this paper, we propose a systematic decision-making framework to improve the system performance in manufacturing practice, considering the real-time degradation signals generated by multiple sensors. Specifically, we propose a partially observed Markov decision process (POMDP) model to generate the optimal capacity and predictive maintenance policies, given the fact that the observation of the system state is imperfect. Such work provides a systematic approach that focuses on jointly controlling the operating conditions and preventive maintenance utilizing the real-time machine deterioration signals by incorporating the degradation constraint and non-observable states. We apply this technique to the bearing degradation data and NASA aircraft turbofan engine dataset, demonstrating the effectiveness of the proposed method.

stat.AP↗

arXiv2022

Nonlinear simulation of wave group attenuation due to scattering in broken floe fields

Direct phase-resolved simulations are performed to investigate the propagation and scattering of nonlinear ocean waves in fragmented sea ice. The numerical model solves the full time-dependent equations for nonlinear potential flow coupled with a nonlinear thin-plate representation of the ice cover, and neglects dissipative processes. The two-dimensional setting with incident wave groups on deep water is considered, in view of applications to wave attenuation along transects of the marginal ice zone. A spatially-varying weight is assigned to the surface pressure so that irregular distributions of ice floes can be directly specified in the physical domain. For various wave regimes and floe configurations, a local wave spectrum across the ice field is computed and then least-squares fitted to extract a spatial attenuation rate as a function of wave frequency. A general increase with frequency is found, consistent with typical predictions from linear theory. However, a non-monotonic behavior around a certain frequency is also observed, especially in cases with a highly fragmented ice cover. Comparison to field data shows that this result closely resembles the roll-over phenomenon as reported from Arctic Ocean experiments. The key role played by nonlinear interactions in the roll-over development is highlighted.

physics.flu-dyn↗

arXiv2021

Assessment of a porous viscoelastic model for wave attenuation in ice-covered seas

Chen et al. (Eur. J. Mech. B/Fluids 78, pp. 88-105, 2019) recently proposed a two-dimensional continuum model for linear gravity waves propagating in ice-covered seas. It is based on a two-layer formulation where the ice cover is viewed as a porous viscoelastic medium. In the present paper, extensive tests against both laboratory experiments and field observations are performed to assess this model's ability at describing wave attenuation in various types of sea ice. The theoretical predictions are fitted to data on attenuation rate via error minimization and numerical solution of the corresponding dispersion relation. Detailed comparison with other existing viscoelastic theories is also presented. Estimates for effective rheological parameters such as shear modulus and kinematic viscosity are obtained from the fits and are found to vary significantly among the models. For this poroelastic system, the range of estimated values turns out to be relatively narrow in orders of magnitude over all the cases considered. Against field measurements from the Arctic Ocean, this model is able to reasonably reproduce the roll-over of attenuation rate as a function of frequency. Given the rather large number of physical parameters in such a formulation, a sensitivity analysis is also conducted to gauge the relevance of a representative set of them to the attenuation process.

physics.flu-dyn↗