This standard specifies the protocols used by the edge computing node of buffering, filtering and pre-processing data collected from controllers including programmable logic controllers, computer numerical controllers (CNC) and industrial robots. The data acquisition from field devices with different interfaces must be automatically stored, filtered and calculated according to reconfigurable rules (including buffering data from selected time frame, convert data format and filter invalid data) from industrial clouds and other edge computing nodes.
This standard specifies the collaboration protocols of enabling machine learning on the edge computing node with support from industrial clouds. This standard provides implementation reference of machine learning upon lower powered, cheaper, embedded devices, a specific hardware-based method of accepting the introduced machine learning models and then online optimization, i.e. comparing the models with incoming live data.