Online industrial flare smoke auto-detection and off-line smoking event reporting

Abstract

A system and computer software mechanism is disclosed that can automatically detect smoking conditions for industrial flares. In an online mode, the software mechanism can analyze live video images to identify smoking conditions and generate a “Smoke Level” value to represent the seriousness of the smoking events. In an off-line mode, the software mechanism can load saved video files and analyze video images to identify smoking conditions and generate a “Smoke Level” value to represent the seriousness of the smoking events. In the online mode, the Smoke Level data can be sent to the plant distributed control system (DCS) or other control devices so alarms can be generated and automatic or manual control actions can be taken quickly to stop the flare from smoking. In both online and off-line modes, Smoke Level data can also be saved in historical files for reporting and smoke event tracking purposes. Using the described system and software mechanism, industrial plants can comply with EPA regulations at all times, improve flare control and monitoring, be better prepared for EPA reporting and auditing, and save energy and manpower.

Dependencies are inferred from the claim text.