CHEMICAL Energy Optimization

Business Problem

Heating of various processes is often a large cost for the industry. There is usually one or several heaters that work alone or together to feed one or several processes. Multiple heaters are also frequent for redundancy purposes. In the end excess heat is frequently generated resulting in high cost.

Challenge

The production is usually controlled by a basic control system (e.g. DCS or SCADA), however as the process needs vary the production is not always optimized.

SentianController solution

SentianController can automate the control of the heating system (burners/furnace) by learning system dynamics from the historical data, which will then be used to predict the optimal set points for the desired output, even if the desired output was never seen before, while at the same time it reduces variation of the output.