Time is the major cost driver in any drilling and completion operation. Different Exebenus Spotter ML agents target specific problems, that being invisible lost time caused by non-optimized ROP or non-productive time caused by stuck pipe.

Exebenus Spotter is built on the philosophy of “one problem – one agent”. The Exebenus Spotter ML agents provide immediate customer value as a true plug & play solution, that requires no training on offset well data and is fully scalable by not needing tedious configuration or human intervention during operation.

Exebenus Spotter plugs into your existing WITSML data stream, relying only on surface data, is vendor neutral and visualizes the output in your existing viewers. There is no need for any additional investment in data or infrastructure as Exebenus Spotter plugs into your existing set-up.

During execution, the Real-time ROP Optimization agent provides advice and identifies parameter combinations and changes that may not be apparent through traditional routines alone. This real-time advice has been proven in field operations to significantly increase ROP, within safe operating limits, and reduce drilling time.

In operation, the Stuck pipe agents – Differential Sticking, Mechanical Sticking and Hole Cleaning – utilize real-time data to detect deteriorating conditions that could lead to stuck pipe and other related issues. By providing your crew with a 30-minute to four-hour heads-up prior to potential events, it prompts them to implement mitigation measures and prevent downtime.

Get in touch
Exceptional benefits
  • No need for training on offset data
  • Use on exploration wells
  • Vendor-neutral plug & play solution 
  • Self-adaptive to any lithology, bit type, BHA or mud properties
  • Minimal configuration time to get started
  • Easily scalable to any # of wells

Real-time ROP Optimization

The rate of penetration (ROP) is a major contributor to drilling time and costs. Today, optimized ROP is achieved by adjusting the weight-on-bit, RPM and fluid flow rates, where the allowed rangesare typically obtained using time consuming and complex simulation models. In addition, uncontrollable factors such as bit dulling, buckling, vibration and formation strength influence the ROP.

Exebenus Spotter Real-time ROP Optimization machine learning agent is unique in its ability to decipher the relationship between the controllable and uncontrollable drilling parameter relationships, without needing specific training on a particular well or field.

The agent provides reliable and consistent advice, by identifying combinations of drilling parameter values – weight-on-bit, RPM and mud flow rate – that increase ROP within safe operating limits, and which may not be obvious to the naked eye based on traditional routines.

The agent’s advice is proven in field operations to increase ROP and reduce drilling time significantly.

Exceptional benefits

  • Multiparameter recommendations – RPM, WOB, fluid flow
  • Usable anywhere; no customization required
  • Consistent and reliable
  • Reduce risk of human error

Stuck Pipe

Exebenus Spotter Stuck Pipe agents are designed to predict, in real time, high-risk conditions related to pressure differentials, hole cleaning conditions, restricted movement and wellbore geometry—conditions that, without intervention, typically result in costly stuck pipe situations. Warnings are provided 30 minutes to hours prior to potential events, giving rig crews sufficient time to take mitigating actions.

When used on historical real-time data as part of offset well analysis, the agents can identify unreported near-misses and potential risk areas, and provide guidance for optimizing performance in the future.

 

Exceptional benefits

  • Predict hazardous events
  • Optimize offset well and root cause analysis
  • Provide real-time situational awareness

Flexible Agents

At Exebenus, we have chosen to develop targeted machine learning models rather than complex models. Why this approach?

Complex models consume vast amounts of data, and take longer to set up, train and run. In contrast, our targeted models solve well-defined problems and deliver more accurate predictions. They use data that’s always available in real time on the rig, which means our agents can be used anytime, anywhere, easily.

Our generalized “out of the box” models are adaptive enough to be used in any geographic area. They provide risk awareness and ROP optimization opportunities in various well operations.

Our robust stuck pipe agents return useful predictions based on a range of data quality. In fact, they do their best work when consuming raw, unfiltered data, and even handle data gaps.

Exebenus Spotter Stuck Pipe agents provide reliable risk predictions within a useable timeframe, requiring only a connection to the existing WITSML system.

Our plug & play agents required no configuration and are easy to adopt and use in any well operation. The Exebenus Spotter Real-Time ROP Optimization agent provides easy to interpret advice and recommendations on RPM, weight on bit and fluid flow to optimize ROP.

Plug and Play

Exebenus Spotter agents consume real-time or historical WITSML data that is readily available in all well operations. Minimal human intervention and no data filtering or cleaning required.

In trials, our agents have performed “out of the box” using raw data that was not prepared in any way.

For ease and speed, the agents output WITSML data to integrate with your operation center’s workflows and familiar real-time WITSML viewers. Within only a few days, your teams can be monitoring and analyzing data, and advising rig crews.

Exebenus Spotter is cloud-based, and agents can be deployed stand alone or as a package.

Services

The Exebenus services team works to ensure that your company’s workflows are properly integrated and digitalized when deploying and implementing the Exebenus Spotter solution.

“We’re seeing machine learning coming into the real-time operations space primarily to do two things: to predict and to optimize. Often it’s about detecting anomalies early and avoiding hazards… uses where machine learning is improving safety and reducing operating costs.”