A data science approach to modelling a manufacturing facility's electrical energy profile from plant production data

Sustainable manufacturing is of increasing interest to a large number of batch production facilities. Energy efficiencies achieved through optimized scheduling is a desired target for such facilities. To achieve these energy efficiencies, the initial step is accurately modelling plant energy profiles from historical production schedule data. This poses several challenges as the data required to model plant energy is stored in various sources and does not conform to a common sampling rate or data type. Also, separating the energy consumption caused by plant production from the base load of lighting and HVAC systems is difficult unless each production process is metered adequately. This paper focuses on developing a methodology to deal with the complexities of data collection, data processing and modelling within a pharmaceutical batch production facility. Historical energy and scheduling data have been utilized to generate a model for the site's energy profile. The approach incorporates data science and machine learning tools which pose a possible solution to the problem outlined. The results from this work can feed into an overarching goal of more sustainable manufacturing processes by allowing site energy engineers to predict and better manage plant energy load.