In our previous post, we discussed how important situational awareness is for drilling automation. Full situational awareness requires the use of not one, but many models – both physics based as well as data-based (AI). Are there strategies that one can employ to get the rig crew to trust AI? The rig crew in general…

What do you imagine the future of drilling to be? Will there be more automation? Will the automation solutions on a rig come from one vendor, or multiple vendors? Do you believe interoperability between the vendors will become commonplace? Will one company supervise all automation solutions? Will automating one part of the operation lead to…

In this post, we will provide some parting takeaways on automatic sensor data validation and cleansing. 1) Detecting missing data / outliers in time series data is relatively straightforward. Do this before any analysis to improve the quality of your output. Otherwise – Garbage In Garbage Out. 2) Detecting drifting or biased data is hard….

Last week, we spent some time on the concept of redundancy as a basis for automatic data validation. We also discussed four ways to achieve redundancy. This week, we will detail model-based redundancy and outline an approach to using it for data validation. The first step here is to take all the sensor data we…

We are a company that got started by building a data quality product. In 2013, we licensed technology that was developed at the University of Texas at Austin and spent most of 2014 building the core data quality engine for Sentinel RT. If you are involved in drilling data analysis/analytics, you already know how good…

The primary goal with this advisory is to alert drillers, directional drillers, well site supervisors and drilling engineers, to dysfunctions that may be happening that is not always easy to detect without real-time models or pattern recognition algorithms.  At its core, there is an index (between 0 and 1) called Slide Optimal Drilling Index that…

In this post, we will discuss two other dysfunctions that can occur when slide drilling with a mud motor, namely buckling and poor toolface control. With respect to buckling, the most dangerous scenario is helical buckling. Here the drill pipe deforms as a spring pressing against the formation, increasing friction severely and potentially locking up…

We are not going to talk about geosteering, or directional drilling optimization (where the focus is on when and whether to rotate or slide and what toolface to proceed with) in this post. Instead, we will show you how to identify dysfunctions that might be happening when one is slide drilling with a mud motor,…

In this post, we will close out our discussion on the detection of abnormal loss and gain. As you can see from Slide 1, the network lays quite a bit of emphasis on the modeled gain/loss rate (which is based on the filtered mud volume discussed in the last two posts), the flow out trend…

It is time again for a Bayesian network. This time a simpler one – a naïve Bayesian network. Last week, we mentioned that if we are able to filter out noises from the “total mud volume” channel, we can determine more accurately and with lesser false alarms, whether the hole is flowing or not. One…