Visual Data's Pythia Root Cause Analysis is build around "Installations" and "Objects".
Installations contain Objects. And objects are entities with characteristcs, behavior and properties. Installaitions are used by humans to perform certain tasks like producing goods (in machines) or providing shelter and safety (in buildings). Often an installation can be seen as a group (machines or "objects") that is designed to help us to maintain our living environment (example: in water management or food production).
Nowadays, most new objects that are put into use, have lots of sensoring devices build in that monitor the correct working of that object. But in older equipment this in not always the case. Then small sensoring devices come into view. These sensors are capable of detecting a lot of different parameters types and they are often able, through the software that comes with them, to signal "out of tolerance" situations. If this occurs, some kind of warning will be issued to any operator to take responsive action.
In this case it is so that all individual parameters are monitored, and a warning goes out when one (or more) of these parameters is out of tolerance. This might result in loss of time and/or rejection of produced goods, or even form a threat for safety for people or employees!
But what if there is NO warning issued, but still products are rejected because there are quality issues?
This is where Visual Data Root Cause Analysis (RCA) kicks in!
RCA collects all types of data that are produced by sensoring systems, or that are put in manually, and stores these data in a database, thus building a history of production parameter data.
This data is analised and the analysis is presented in easy-to-read diagrams.