Data-Driven Maintenance Planning, Scheduling, and Control
Abstract
Maintenance refers to acts undertaken to improve the availability and integrity of ageing productive systems, and is at the nexus of the broader concepts of system resilience and system effectiveness. Compromised system resilience can reduce system effectiveness and can lead to catastrophic consequences such as cost to human life due to process safety incidents, lost revenue due to downtime, as well as damage to the system and the environment. Data analytics and mathematical optimization are key research areas that are well positioned to offer solutions that leverage increasing data proliferation and help address the complexities associated with process-maintenance interactions. The present work optimizes maintenance at multiple time-scales using both data-driven and first-principles methods while simultaneously optimizing production. The work is divided into three major areas: (1) maintenance planning, which explores the effects of imperfect maintenance and uncertainty in model parameters; (2) data-driven prescriptive maintenance, which involves future failure prediction via machine learning and optimal process and maintenance scheduling; and (3) maintenance-aware predictive control, which lies at the interface of predictive maintenance and multi-parametric model predictive control. This work makes advances in process safety engineering and process systems engineering while also developing advanced, systematic and mathematical tools for decision support.
Citation
Gordon, Christopher A. K. (2021). Data-Driven Maintenance Planning, Scheduling, and Control. Doctoral dissertation, Texas A&M University. Available electronically from https : / /hdl .handle .net /1969 .1 /195666.