Analytics

you can use the analytics module to create and manage analytics flows analytics flows enable you to process and analyze data at the edge a flow includes a series of connected processors, using at least one of the following types input retrieves data from a tag, database, or generator see input processors docid 2xzb8kidbyzavj7rq n7x for details function processes the input data using built in kpis (key performance indicators) see key performance indicators docid\ gsinmt9psndga1re0ndhp for details statistical functions see statistical functions docid 5rajnux ihl22jtmr0jz6 for details output writes the function results to a tag or databases see output processors docid\ moajvzjgathx1cwl3wwvb for details see create an analytics flow docid\ ayg jr6 mt3z5whsvy26 and add processors and processor connections docid\ npkrhfefmri9kcvoshrdo to learn more review analytics guides docid rtbnjcuaomwwyqzssiy3 important you may see the following error message when working with analytics "http failure response for /analytics/v2/version 0 unknown error" if you see this message, disable any ad blockers your browser may have you can build a flow manually by adding instances and then connecting them with one of the following connection types events (individual data source) used only for both input/function and function/output connections makes the receiving processor react to each individual data value immediately values (combined data sources) used only for input/function connections makes the function processor wait for values from all of the combined data sources before reacting for example, if the function processor compares values from input processors a and b, it will wait for a value from both a and b before performing the comparison you can also add a flow in a more automated way see create an analytics flow docid\ ayg jr6 mt3z5whsvy26 for details the analytics module also enables you to use machine learning models for prediction, classification, and anomaly detection you can create and save a model from tensorflow a saved model contains a complete tensorflow program, including weights and computation the analytics ui includes the following panes instances , where you can create and manage processors and flows view the debug panel organize your flows into groups instances table , where you get tabular view of instance flows created models , where you upload and remove models access analytics ui to access analytics log in to manufacturing connect edge from the navigation panel, select analytics the analytics canvas appears next steps analytics flows and processors docid 0avdce3m59yqk8ux0gytv analytics flow groups docid\ xth krxhfiv2lxwux5iit instances table docid\ m0bjksevkdozn9thhw6ub machine learning models docid\ dw4dkeacnykk8ku0e mpm input processors docid 2xzb8kidbyzavj7rq n7x output processors docid\ moajvzjgathx1cwl3wwvb statistical functions docid 5rajnux ihl22jtmr0jz6 key performance indicators docid\ gsinmt9psndga1re0ndhp analytics guides docid rtbnjcuaomwwyqzssiy3