Leveraging Analytics to Improve Drilling Performance and Safety: The Experience of ‘Shell’ and ‘CoVar’

 

Topic 1: Shell Machine Learning Inplementation : Automated Kick Detection during Connections

In 2010 Shell began investigating how to automate the initial response to a well control incident.  Since at least 25% of kicks in deep water GoM wells occur on connections it was quickly realized that robust kick detection during connections was important but especially challenging due to the associated transient flow and pit volume signatures.  A work stream was kicked-off to develop new software based on pattern recognition technology and machine learning. The resulting IDAPS (Influx Detection at Pumps Stopped) software has now been implemented as a real-time monitoring application for all Shell operated GoM deep water wells.  Presentation will include IDAPS development roadmap and implementation results, including adding a ballooning discriminator.  

 

Topic 2: Covar's Adaptive Alarms and Computer Vision applications for drilling industry

Machine learning technology, including data analytics and computer vision, have been maturing rapidly over the past decade and applications range from autonomous driving to facial recognition to defense applications.  CoVar has developing applications for these technologies in the oil and gas drilling industry.  This talk will focus on two technology lines: CoVar Adaptive Alarms and CoVar Computer Vision.  CoVar Adaptive Alarms applies machine learning pattern recognition approaches to real-time drilling traces to better inform the driller of impending issues and hazards, including influxes, losses, and stuck pipe/pack-off while reducing alarm fatigue and workload.  CoVar Computer Vision applications offers a new sensing modality for rig-floor sensing problems that are difficult or impossible to instrument with conventional instrumentation.  These include automated pipe measurement, shaker table solids measurement, and equipment and personnel location.  CoVar’s unique technical approach to these problems combines domain expertise derived simplified physical models and big-data statistical methodologies into a reliable and intelligent AI solution.

 

Parking and Venue Directions:
Please refer to the map for directions to parking and the venue. 
 
1A/1B: You can enter the facility premises via Westheimer Rd (1A) or Sage Rd (1B). 
 
2: Please use IHS Markit's covered garage for parking your vehicle. Grab the ticket from the ticket meter as you are entering the parking lot* 
 
3: Use the stairs to come to Level 1 and follow the passage as shown in the map to enter the building. Follow the arrows to enter the Red/Rio Rooms. 
 
* The parking is estimated to cost between $2-$4 for the entire duration. You can pay for the parking after the event; either via parking ticket meter on Floor 1 or while exiting the parking lot through the meter at the entrance. 
 
Map for reference:
 

Location: IHS Markit
5333 Westheimer Rd, Suite 100
Houston , TX 77056

Date: March 23, 2017, 5:30 p.m. - March 23, 2017, 7:30 p.m.