An I4.0 data intensive platform suitable for the deployment of machine learning models: a predictive maintenance service case study

The Artificial Intelligence is one of the key enablers of the Industry 4.0. The building of learning models as well as their deployment in environments where the rate of data generation is high and their analysis must meet real time requirements lead to the need of selecting a big data platform suitable for this purpose. The heterogeneous and distributed nature of I4.0 environments where data becomes highly relevant requires the use of a data centric, distributed and scalable platform where the different applications are deployed as services. In this paper we present an I4.0 digital platform based on RAI4.0 reference architecture on which a predictive maintenance service has been built and deployed in Amazon Web Service cloud. Different strategies to build the predictor are described as well as the stages carried out for its construction. Finally, the predictor built with k-nearest algorithm is chosen because it is the fastest in producing an answer and its accuracy of 99.87% is quite close to the best model for our case study. (C) 2022 The Authors. Published by Elsevier B.V.