An Aker BP operated oil field in the North Sea has occasionally experienced production flow instabilities in the production lines and risers. The oscillations in multiphase rates are kept within the process capacity limitation at the host installation typically by increasing backpressure (planned flaring is not allowed for on the Norwegian Continental Shelf). The heightened backpressure impacts the production potential of the field. The objective of the project described in this paper has been to develop and implement a new method for real-time production optimization providing an online assessment of slugging severity and suggested actions in order to mitigate slugging and increase production. The developed software tool has been validated using field data. A statistical approach based on the physical characteristics of the separator has been developed. A combination of transient multiphase flow simulations and data analysis has been employed in order to formulate the risk of exceeding separator constraints as a multidimensional function of the operational conditions. In order to generate a three-dimensional heat map of the risk related to the current state, operational data is continuously gathered from production sensors and transformed into pseudo-steady state values. A heat map is defined by a function where four relevant operational values can be selected. These values are: oil production rate, topside choke setting, gas lift rates and water cut. The software solution is run on a cloud infrastructure with an interactive web user interface. In a pilot program we have evaluated the ability of the stability advisor to continuously assess the severity of flow instabilities, identify measures to reduce the risk level and minimize associated production losses. The operator has identified valuable operational insights from the tool in a pilot program. The flow instabilities predicted by the model correlate well with observed data from the field. The tool is scalable to other fields with similar flow problems. Previous papers on slug flow prediction are in general conducted as offline study projects. There has been little success in making real-time scalable solutions available to continuous operations. This paper explains a method on how physical modelling of the flow system combined with statistical methods and access to real-time sensor data can provide a new approach for real-time slug flow prediction. The result demonstrates a scalable solution where output is presented in a format that can be applied by daily operations to act on and provide new and valuable production insights.

This paper introduces a multimodal virtual flow meter (VFM) that merges physics-driven multiphase flow simulations with machine learning models to accurately estimate flow rates in oil and gas wells. The combining algorithm takes advantage of the confidence decay and historical performance factors to assign confidence and contribution weights to the base estimators and then aggregates their estimates to arrive at more accurate flow rate estimates. Furthermore, the proposed multimodal VFM provides an indication of the confidence level for each estimate based on the underlying agreement of the base estimates and the historical performance. The proposed VFM was tested in a 6 months online pilot in two oil wells. The proposed multimodal algorithm resulted in almost 50% improvements in performance compared to individual VFMs. The proposed robust multimodal approach can provide a complimentary benefit as an optimal VFM and reduce the overall system uncertainty. The developed VFM can be used for real-time production monitoring, verification and backup of physical meters, and well-test validation.

Traditionally, a field’s wax management and operating philosophy have been developed by conducting a rigorous Flow Assurance (FA) study. Optimization at field level warrants the study to be updated from time to time to reflect the actual field performance. This accounts for overall field performance but does not incorporate variations due to operational changes. Rather, the operating philosophy is based on representative scenarios where conservative measures are often used to safeguard operations. With the increasing number of waxy crude oil pipelines within company that demands immediate attention, an online prediction/monitoring tool that quickly adapts to operational changes is one important enabler, not only to optimize operations and address the huge Operating Expenses (OPEX), but also to address remote/unmanned operation’s requirement especially for subsea operation. Unfortunately, to date, such a tool is not commercially available or deployed widely. To address this gap, this paper aims to present the Online Wax Smart Meter development concept and to showcase the performance of an online wax monitoring tool which enables fast and optimum wax management.