A Proposal for Edge Application Framework for Smart Factory
Masaki Sakai, Tsuyoshi Nakajima, Kazuya Takahashi · 2020
In order to improve the productivity of a factory, it is often the case to create an inference model by analyzing data from the machines in the production line, and then to develop an edge application which judges the quality of the products or diagnoses faults of the machines in real time. However, it is difficult to generate an edge application only by deploying the model, because of the variety of data collection and preprocessing methods. To solve this problem, a framework for developing edge applications semi-automatically from inference models is proposed. An actual edge application is prototyped, which proves that the proposed framework concept is feasible.