We introduced the concept of a Bayesian belief network for hole cleaning a few weeks back. When the hole cleaning belief goes below a certain threshold, it is a reminder that some action might need to be taken or care exercised as we restart drilling. To that end, one example user interface that was deployed…

Continuing from where we left off last week, tracking frequent tight spots is an important aspect of monitoring hole cleaning issues. So, how can we detect tight spots in data? Here, a real-time torque and drag model (a soft string model is often sufficient) can be quite useful. As shown in Slide 1, when the…

When we drill fast (aiming for the best ROP possible), we also have to keep up with better hole cleaning actions. Otherwise, the time gained by faster drilling may very well be lost through subsequent potential stuck pipe events, loss in production, etc. While everyone understand that hole cleaning is important, automated hole condition monitoring…

Slide # 1 tells you why ROP Optimization is like boxing, ice hockey, football etc. It is a collision sport. That is, if you really want to make improvements, you must keep pushing and try new things to outperform the opponent – in this case, the formation. But first, you need a plan. You do…

Whirl as you know can be extremely difficult to detect (unlike stick slip, bit bounce, etc.) from surface data. Some say that it cannot really be detected using surface data. So, what is the trick to this model that we have posted here? The trick is that we infer (not detect) a whirl (more accurately…

Bit bounce is generally regarded as not a problem issue when drilling with PDC bits. It is of course well known that they are an issue for roller cone bits especially when drilling hard formations, due to the possibility of forming a three lobed pattern on the rock being drilled. With PDC bits, bit bounce is…

This is a tough one. Unlike stick slip, the signs are way more subtle. This post will inform you what we have learned by looking at data. We hope you find it helpful. To identify bit balling from surface data in real-time, we need to be looking for a long-term decrease in torque as well…

So, let us first define “full stick” – at least for use within this post. We define a full stick event as an extreme case of stick-slip, where the bit comes to a complete stop for a slightly “extended” duration. These events are violent and can be extremely damaging to the drill bit, mud motor,…

Stick slip: It is a topic that has been extensively studied and investigated. And there have been many approaches invented to mitigate them over the years. So, you might wonder whether there is anything new to talk about when it comes to stick slip. Perhaps you already know that sometimes a little stick slip is…

We mentioned in last week’s post that we can detect pump failure from EDR data (1Hz to 0.2Hz). We also mentioned that washout and pump failure signatures are so similar that often there is not sufficient basis to differentiate between them. In effect, washout and pump failure signatures are the same except for the flow…