Industrial IoT Sensor Data Federation in an Enterprise for an Early Failure Prediction

Abstract

The recent availability of powerful (SBC) Single Board Computing devices has facilitated edge computing, filled a gap with lower power consumption at the edge. Preventive maintenance intervention in the industry is needed. These predictions with data privacy and accuracy to take care of chronic spare replacements before things fail. We are proposing preventive maintenance procedures based on (IIoT) Industrial Internet of Things data from multiple sensors installed in an industrial setup across a varied geography. The SBC ensured low powered 15W of power operation mode and was adequately cooled with a passive aluminium heat-sink and fans. We are proposing a unique method of federation, specifically, using HDF5 model file transfer. Preset cron jobs at the clients allow real-time federation as a quick solution using off-the-shelf hardware. The setup has a central server or alternatively a cloud server for fallback, in the monitoring station and is implemented using Split Federation and Linear, DNN, CNN, RNN models. Federated Learning (FL) models were used to predict the sensor values and make decisions. The Machine Learning (ML) techniques only operated at the edge. Data privacy is upheld and maintained. The quick and simple approach can help in a cheaper implementation in public service projects where site data needs to be private. Even the possibility of power cuts in rural areas will not affect the federation and decision making can happen even in the harshest of field situations. This has a lot of impact in decentralized decision making. Failure patterns can be identified and in general, an accurate model can be generated with limited resources.