While many techniques for outlier detection have been proposed in the literature, the interpretation of detected outliers is often left to users. As a result, it is difficult for users to promptly take appropriate actions concerning the detected outliers. To lessen this difficulty, when outliers are identified, they should be presented together with their explanations. There are survey papers on outlier detection, but none exists for outlier explanations. To fill this gap, in this paper, we present a survey on outlier explanations in which meaningful knowledge is mined from anomalous data to explain them. We define different types of outlier explanations and discuss the challenges in generating each type. We review the existing outlier explanation techniques and discuss how they address the challenges. We also discuss the applications of outlier explanations and review the existing methods used to evaluate outlier explanations. Furthermore, we discuss possible future research directions.

Despite being the most widely used artificial lift method for high-producing oil wells, ESPs still experience unplanned failures that impact well productivity and overall field economics. Our advanced ESP Predictive Failure Analytics (PFA) can help detect ESP events ahead of time and extend the overall ESP run life. PFA enabled a major Latin American operator, experiencing frequent unplanned ESP failures, to identify critical events while pumps were running and take remedial actions to extend ESPs run life. Methods, Procedures, Process PFA leverages artificial intelligence (AI), statistical and physics-based models to reliably predict Remaining Useful Life (RUL) and possible failure cause. The models are trained using historical sensor time-series from both running and failed ESPs. The trained models are deployed to predict short-term events that may lead to immediate failure, such as a broken shaft, short-circuit, grounded downhole failure; as well as long-term events which build up over time, such as pump low efficiency, sand, scale deposition and gassy conditions. Results, Observations, Conclusions For this study, we used two ESPs. For ESP-1, PFA predicted broken shaft/missed pump stages after a sudden decline in motor current and production rate. As the production rate declined beyond the minimum recommended operating range, PFA identified downthrust condition and estimated a significant RUL reduction. PFA enables the operator to quickly schedule a workover, reducing downtime. For ESP-2, intake pressure and motor current started decreasing and motor temperature started increasing. PFA predicted sand influx and estimated a significant RUL reduction. A chemical injection was applied to reduce sand, and avoid an imminent failure leading to PFA estimating an increased RUL. Novel/Additive Information PFA is an innovative approach which combines AI, statistical and physics-based methods to provide explainable predictions of ESP failure. Unlike commonly used threshold-based approaches, PFA tends to generate fewer alarms which enables proactive optimization of ESP performance, avoiding unplanned failures and extend ESP run life.

Unplanned Electrical Submersible Pump (ESP) failures can have a profound impact on well production and overall field economics; therefore, it is important to reliably predict the onset of damaging operating conditions and take proactive action to prevent early failure of an ESP. Most operators rely on production engineers to monitor and optimize equipment performance with remote monitoring and surveillance technologies that provide threshold-based diagnostics to detect electrical or mechanical problems. Due to inherent limitations in exception-based monitoring, it is extremely difficult to reliably predict the root cause of equipment failure and remaining useful life (RUL) of an ESP. A major operator in the Americas was experiencing similar operational challenges in three of its producing assets. Unplanned failures happen frequently since they are hard to predict ahead of time with the data available to production engineers. This case study demonstrates how Advanced ESP Predictive Failure Analytics (PFA) technology has helped this operator to detect such events and extend ESP run life. Methods, Procedures, Process PFA is an innovative technique that leverages artificial intelligence (AI), life data analysis, physics, and knowledge-based methods to predict electrical and mechanical events and provides an estimate of RUL of an ESP. The data-driven models are trained using sensor time-series of historical failures and entail advanced data processing, interpolation, quality evaluation and feature engineering. The trained models are deployed to predict short term damage events that may lead to immediate failure, such as broken shaft, short-circuit, grounded downhole sensor failure, as well as long term events which build up over time, such as sand, and scale deposition. Results, Observations, Conclusions For one ESP, PFA detected scale deposition and predicted a sharp decline in RUL. After confirming the decrease in production fluid, and other surface and downhole sensor trends indicating scale deposition in the ESP, the production engineer applied chemical injection and avoided the failure. For a second ESP in this case study, PFA detected a grounding condition and predicted sudden decline in RUL. The production engineer noticed motor amps increased beyond the recommended threshold and performed electrical optimization to reduce motor amps. The ESP ran for another year and eventually failed due to grounded downhole sensor failure, which PFA had detected two weeks prior to the failure.

Oilfield power demand is extremely dynamic in both time and space, and a lack of accurate forecasting causes increased cost for electric utilities to extend their grids to the field. It also causes increased demand charges for producers, which increases their lifting costs. As well production declines with time, electric utilities may end up with stranded assets which represent a large investment that is costly to maintain but is not being fully utilized. Therefore, both producers and utilities have a common interest in improved load forecasting to cut down on cost of power, especially during times of low oil prices. In this research, we show how data analytics can be used to predict load growth evolution in time and space. We incorporate production operational data, well location and geometry, and historical power consumption of neighboring wells into a data analytics engine to develop a platform for improved oilfield load forecasting. This data-driven approach is shown to decrease a utility's kilowatt prediction error for new well pads by 48 to 78% for annual average power and by 10 to 26% for peak power.