R2.11 Release Notes

The short version

R2.11 makes Spotter easier to use and easier to trust. A cleaner admin UI cuts setup time. Several improvements further reduce false positives on stuck pipe and torque. And the output now explains itself better, so the crew understands not just what Spotter is flagging, but why. When it has nothing to recommend, it now tells them why too.

The release also brings a step-change in real-time hole cleaning. Spotter's ECD model now calibrates in under a minute instead of ten, which opens up accurate hole cleaning assessment at ROPs above 200 m/hr (600 ft/hr).
‍

Hole cleaning and ECD: real-time at high ROP

This is the headline of the release.

Spotter's downhole ECD model has always produced accurate predictions. The constraint was calibration time: the model needed around ten minutes of stable data before it could start delivering reliable ECD output. For most operations that worked fine. But on stands drilled at ROPs above 60 m/hr (180 ft/hr), ten minutes is already most of the stand, leaving the crew with too few ECD readings per stand to act on.

In R2.11, calibration time drops to under one minute while keeping the same prediction accuracy. That makes real-time ECD-based hole cleaning assessment practical at ROPs up to and beyond 200 m/hr (600 ft/hr), and yes, those rates happen in some areas.

Under the hood: Spotter now estimates ECD from surface parameters and flags increasing-ECD risk situations on timescales of seconds to minutes. It runs alongside the existing longer-horizon hole cleaning models and catches risk patterns on short stands those models can't reach in time. Real-time ECD estimates are written to WITSML under ECD_estim in the Exebenus Spotter log, with a configurable cooldown on alerts. For systems running without live mud density, the configured default density feeds the calculation, so output stays consistent regardless of sensor availability.
‍

Fewer false positives across stuck pipe and torque

Several improvements in R2.11 reduce the conditions that have historically triggered false stuck pipe and torque alerts. Each one closes off a specific source.

Shoe-track risk now covered. Sometimes stuck pipe risk shows up inside the bottom of the casing string, typically from residual cement in the shoe track. Previously, Spotter suppressed alerts in this zone alongside the rest of the cased section. R2.11 extends stuck pipe coverage into the shoe track and labels these alerts as "in casing safe-guard zone" so the crew immediately knows the context. Shoe-track sticking is most often pre-warned by torque spikes and string stalling, both of which Spotter now picks up in this region. Warning types that should remain suppressed inside casing continue to be suppressed.

Torque spikes during direction changes. Starting or stopping a trip, or reversing direction, produces torque behavior that looks like a spike but is operationally normal. The torque spike detector now accounts for axial motion reversals and suppresses these spikes when they correlate with a direction change. Fewer false torque alerts, more reliable signal during actual drilling.

Better handling of poor data quality on differential sticking inputs. Asynchronous sensor timestamps, hookload readings taken during connections, and other data quality issues have been a known source of false differential sticking warnings across the industry. R2.11 hardens Spotter against these cases: each DS input sample is validated against a minimum value threshold and a configurable change limit versus the previous sample. Failed samples are skipped, buffered, and linearly interpolated once clean data resumes. Static friction risk is only evaluated on a clean input sequence. The result is one more source of false positives eliminated.

String weight test reminders. Knowing your pick-up and slack-off weights matters in challenging wells; they're key operational context for anticipating tight hole conditions. In R2.11, Spotter sends an INFO-level reminder when these weights haven't been refreshed within a configurable distance (default 500 m). It's not an alarm, it's a nudge that helps the drilling team stay prepared and keeps Spotter's friction-based predictions accurate. A cooldown (default one day) prevents the reminder from repeating too frequently.
‍

ROP Agent: explainable recommendations

Sometimes the rig is drilling outside the parameter limits set for the ROP optimization model. When that happens, the ROP Agent doesn't make a recommendation, by design. This is one of several operational safeguards built into the agent, the reason crews can drill safely and at high ROP with Spotter running.

What R2.11 adds is the explanation. When current drilling parameters fall outside the configured ROP optimization limits, Spotter publishes a message to the ROP_message curve identifying which parameters are out of range (e.g. RPM, or WOB and Flow). If the optimization service determines the configured limits themselves are too narrow to find a solution, it publishes a message pointing the user to the configuration UI. A cooldown caps these messages at one per 60 minutes.

For crews monitoring Spotter in real time, the difference between "no recommendation because nothing is better" and "no recommendation because the limits are wrong" matters. Now Spotter tells them which.
‍

Stick-slip: long-term trends for along-string instability

Real-time stick-slip information is useful for both drilling optimization and stuck pipe risk assessment. In particular, when drilling through conglomerates, creeping salts, or swelling shales, long-term stick-slip trends from surface data have proven to be a strong indicator of along-the-string wellbore instability.

R2.11 adds a long-term moving average to Spotter's stick-slip output, alongside the existing short-term probability. The smoother curve makes it easier to spot gradual increases in vibration severity that point to developing stuck pipe risk and helps the crew reason about root cause. The smoothed probability is published with stick-slip status messages and written to WITSML as StickSlipProbMovAvg in the Exebenus Spotter ROP Status log.
‍

Admin UI: a refresh for system administrators

Spotter has matured significantly over the years, gaining capability with each release. With that growth, the admin UI had accumulated workflows and layouts that no longer matched the standard we hold the rest of the product to. R2.11 reworks it from the ground up so administrators can do their job with minimum effort.

Single stuck pipe toggle. Instead of separate DS/MS/HC checkboxes, there's now a single "Stuck Pipe Risk" option. When enabled, all associated functionality runs automatically: DS, MS, HC predictive alerts, SPP/torque/breakover torque detection, downlinking, string weight tracking, alert aggregation and escalation. Individual sub-functions can still be disabled via other configuration flags if needed.

Context-aware field display. Configuration pages now hide fields that aren't relevant to the agents selected for a wellbore. Stuck pipe settings only appear when Stuck Pipe Risk is enabled; ROP-specific configuration only when the ROP Optimization agent is selected. Default mud density stays visible for all jobs since it feeds multiple agents. Less clutter, fewer mistakes.

New landing page. After login, Spotter opens to a configuration overview showing all wellbore configurations with status indicators and group names, with filter and search built in. Clicking a wellbore opens its full configuration detail.
‍

Access control: role-based with group scoping

R2.11 expands Spotter's access model to better fit operators running across many wells and teams. Access is now role-based with group-scoped visibility.

Two roles. Administrator and User. Administrators manage users, groups, wells, and WITSML server connections. Users create, update, and delete wellbore configurations within their assigned groups, and start/stop wellbores they're authorized for.

Group-based access. Wells and wellbores can be assigned to one or more user groups. Users can belong to multiple groups, and access to configurations is determined by group membership. If a user tries to access a wellbore restricted to a group they're not part of, the UI explains why and directs them to contact their administrator. Administrators get a shortcut from the same dialog into Group Management to make the assignment.

New management pages. Dedicated pages for User Management (listing users with role and group filters, user detail views) and Group Management (create groups, assign wells, manage membership). Regular users see only their own user page. Group Management is administrator-only.
‍

Bug fixes

Two fixes in this release. A bug where restarting Spotter agents on an existing well configuration could delete output records outside the intended time range has been resolved; deleted records now consistently match the unprocessed interval of the well dataset. Internal warning and comment generation for certain stuck pipe alerts has also been hardened, reducing cases where an alert fires without a corresponding explanatory message.

‍