Digital twin predictive maintenance strategy based on machine learning improving facility management in built environment

Predictive maintenance is a concept linked to Industry 4.0, the fourth industrial revolution, which monitors the performance and condition of equipment during normal operation to reduce failure rates. This chapter deals with a predictive maintenance strategy to reduce mechanical and electrical plants malfunctioning for residential technical plant systems. The developed strategy can guarantee a tailored maintenance service based on machine learning systems, drastically reducing breakdowns after a maximum period of 3 years. The developed strategy evaluates an acceptable components failure rate based on statistical data and combining the average labor costs with the duration of each maintenance operation. The predictive strategies are elaborated on the minimum cost increase necessary to achieve the abovementioned objectives. A case study based on a 3-year period has been developed on a modern residential district in Rome comprised of 16 buildings and 911 apartments. In particular, the analysis has been performed considering mechanical, electrical, and lighting systems supplying the external and common areas, excluding the apartments to avoid data perturbation due to differenced users’ behaviors. The overall benefits of predictive maintenance management through Big Data analysis have proven to substantially improve the overall operation of different plants such as mechanical and electrical plants of residential systems.