讲座时间：2025年12月19日（周五）  16:00

地点： 综合楼644会议室

报告题目：A nonparametric degradation model with monotonicity constraint on trend

报告人简介：  

沈雁，博士毕业于新加坡国立大学工业系统工程与管理系，现为厦门大学经济学院统计学与数据科学系教授。研究领域为工业统计，可靠性建模分析。在可靠性领域发表多篇论文，并主持多项国家和省部级课题。

报告摘要： 

The monotonicity constraint plays a crucial role in applied statistical modeling, particularly for degradation processes characterized by an underlying monotonic trend accompanied by stochastic fluctuations. Incorporating such constraint not only enhances the accuracy of model estimation but also improves the predictive reliability of downstream analyses. In this paper, we propose a nonparametric modeling framework that simultaneously estimates the monotonic overall trend and the associated stochastic fluctuations of degradation processes under monotonicity constraint. We establish the asymptotic properties of the proposed estimators and analyze how the monotonicity constraint influences both trend and fluctuations. Furthermore, we address the remaining useful lifetime (RUL) prediction, which critically depends on both the overall trend and the associated stochastic fluctuations. A closed-form expression for the RUL distribution is derived based on the estimated model components, enabling efficient implementation in practical reliability applications. The effectiveness of the proposed approach is validated through extensive simulation studies and a real-world case study. The results demonstrate that imposing the monotonicity constraint leads to substantial gains in estimation accuracy and predictive performance.