Maintenance optimization for capital goods when information is incomplete and environment-dependent

We study the problem of inspection and maintenance planning of capital goods based on observations of the capital good’s degradation state. However, the observations are imprecise, and their quality depends on the environment. For example, when performing maintenance for Heating, Ventilation, and Air-Conditioning units (HVACs) in trains, the health of the cooling component of an HVAC can be assessed from temperature readouts of the car in which the HVAC is mounted. Temperature information is useful in the summer when high car temperatures can indicate a failed cooling component, but this information has limited value during the winter. We model the problem as a partially observable Markov decision process with a fully observed environment. We analytically show that an environment-dependent monotonic at-most-4-region policy is optimal. Furthermore, we numerically analyze an example motivated by HVAC maintenance at Dutch Railways. This analysis shows that, in many cases, including the environment in the model can lead to cost savings of more than 10%. In a broad numerical experiment, we show that a simple policy cannot always substitute an optimal policy.