Mímir: Building and Deploying an ML Framework for Industrial IoT

In this paper we describe Mímir, a production grade cloud and edge spanning ML framework for Industrial IoT applications. We first describe our infrastructure for optimized capture, streaming and multi-resolution storage of manufacturing data and its context. We then describe our workflow for scalable ML model training, validation, and deployment that leverages a manufacturing taxonomy and parameterized ML pipelines to determine the best metrics, hyper-parameters and models to use for a given task. We also discuss our design decisions on model deployment for real-time and batch data in the cloud and at the edge. Finally, we describe the use of the framework in building and deploying an application for Predictive Quality monitoring during a Plastics Extrusion manufacturing process.