Data-driven maintenance and remanufacturing optimization of complex systems



Journal Title

Journal ISSN

Volume Title



Maintenance, repair and overhaul (MRO) activities, including remanufacturing, make up an important part of several critical industry sectors (e.g., aerospace, automotive, machinery, and heavy-duty and off-road equipment). MRO activities improve the reliability of systems in these sectors and in particular, keep components and their embodied material in use for longer time so that significant energy use and emissions to air and water can be avoided. They are also an important driver to a sustainable manufacturing industry and a key strategy within the circular economy. As the demand for reliability and sustainability of many industrial systems increases, it is imperative to develop effective maintenance and remanufacturing strategies.

The research conducted in this dissertation considers maintenance and remanufacturing planning problem from a data-driven perspective. We identify and formulate stochastic optimization problems for finding optimal planning policies in the presence of various uncertainties, including the internal stochastic nature of a component’s deterioration and the external statistical estimation errors due to data inadequacy. The utilities of the proposed models are tested on both real-world data sets and computational studies.

In Chapter 1, we provide a brief introduction of the background information and motivation examples. and identify existing research gaps on maintenance and remanufacturing optimization research.

In Chapter 2, we consider the problem of remanufacturing planning in the presence of statistical estimation errors. Determining the optimal remanufacturing timing, first and foremost, requires modeling of the state transitions of a system. The estimation of these probabilities, however, often suffers from data inadequacy and is far from accurate, resulting in serious degradation in performance. To mitigate the impacts of the uncertainty in transition probabilities, we develop a novel data-driven modeling framework for remanufacturing planning in which decision makers can remain robust with respect to statistical estimation errors. We model the remanufacturing planning problem as a robust Markov decision process, and construct ambiguity sets that contain the true transition probability distributions with high confidence. We further establish structural properties of optimal robust policies and insights for remanufacturing planning, and develop a monotone value iteration algorithm based on solution structures. A computational study on the NASA turbofan engine shows that our data-driven decision framework consistently yields better worst-case performances and higher reliability of the performance guarantee.

In Chapter 3, we further consider the parameter estimation errors on both reward functions and system transition probabilities in a remanufacturing planning problem. We consider a manufacturer who leases or operates a piece of equipment and is responsible for equipment maintenance during the usage period. When manufacturers stop the use of the equipment, they sell the equipment to a third-party remanufacturer who buys used equipment, referred to as "cores". The price of a core is assumed to be dependent on its condition. We formulate this problem as an optimal stopping problem with parameter uncertainty, that is, the decision maker seeks an optimal timing to sell the core to maximize its gain. We provide tractable reformulations for two types of ambiguity sets of the reward function and investigate the impacts of these ambiguity sets on the optimal robust policy.

In Chapter 4, we study the multi-component maintenance problem over a finite planning horizon and formulate the problem as a multi-stage stochastic integer program with decision-dependent uncertainty. Maintenance optimization has been extensively studied in the literature. However, most of the existing maintenance models focus on single-component systems and are not applicable for complex systems consisting of multiple components, due to various interactions among the components. Multi-component maintenance optimization problem, which joins the stochastic processes regarding the failures of the components with the combinatorial problems regarding the grouping of maintenance activities, is challenging in both modeling and solution techniques, and has remained an open issue in the literature. To address this challenge, we use a novel approach to model the underlying failure process and develop a novel two-stage model without decision-dependent uncertainty. Structural properties of the two-stage problem are investigated, and a progressive-hedging-based heuristic is developed based on the structural properties. Our heuristic algorithm demonstrates a significantly improved capacity to handle practically large-size two-stage problems comparing to three conventional methods for stochastic integer programming, and solving the two-stage model by our heuristic in a rolling horizon provides a good approximation of the multi-stage problem. The heuristic is further benchmarked with a dynamic programming approach and a structural policy, which are two commonly adopted approaches in the literature. Numerical results show that our heuristic can lead to significant cost savings compared with the benchmark approaches.

In Chapter 5, we study the condition-based optimization problem for multi-component systems. We first develop a multi-stage stochastic integer model with the objective of minimizing the total maintenance cost over a finite planning horizon. We then investigate the structural properties of a two-stage model. Based on the structural properties, two efficient algorithms are designed to solve the two-stage model. Algorithm 1 solves the problem to its optimality and Algorithm 2 heuristically searches for high-quality solutions based on Algorithm 1. Our computational studies show that Algorithm 1 obtains optimal solutions in a reasonable amount of time and Algorithm 2 can find high-quality solutions quickly. The multi-stage problem is solved using a rolling horizon approach based on the algorithms for the two-stage problem.

Embargo status: Restricted until 01/2023. To request the author grant access, click on the PDF link to the left.



Remanufacturing Planning, Robust Markov Decision Process, Maintenance Optimization, Stochastic Programming