题目：Robust conditon-based production and maintenance planning

时间：2023年6月20日 10:00-12:00

地点：bat365在线中国官网登录入口 F310会议室

报告人：孙秋壮 助理教授（悉尼大学）

邀请人：刘冉 副教授（工业工程与管理系）

报告人简介

悉尼大学数学与统计学院助理教授。研究兴趣包括数据驱动的决策分析、工业统计和可靠性工程。

研究成果在Technometrics、Automatica、IISE Transactions等期刊发表，并获得2023 INFORMS Quality, Statistics, Reliability (QSR) Conference最佳论文奖，2022 INFORMS QSR Industrial Data Challenge Competition冠军等。

报告摘要

We study the robust production and maintenance control for a production system subject to degradation. Optimal control of the degradation rate aims to strike a balance between the risk of failure and the production profit. Different from the existing literature that posits a parametric stochastic degradation process, we suppose the degradation increment during a decision epoch lies in an uncertainty set. We formulate a robust optimization model and establish structural properties of the optimal production plan. We derive closed-form solutions that facilitate the real-time implementation of our model on Internet-of-Things (IoT)-enabled systems. Numerical results show that our model significantly outperforms benchmarks in terms of the mean and variance of cost rate when model misspecification presents.