Multi-task and few-shot learning in virtual flow metering

TL;DR

This paper introduces a hierarchical deep learning model for multi-unit soft sensing in industrial processes, enabling effective few-shot learning of virtual flow meters across multiple wells, even with minimal data.

Contribution

It proposes a probabilistic hierarchical model for multi-unit soft sensing and demonstrates its ability to perform few-shot learning in a large-scale industrial setting.

Findings

Multi-unit models improve generalization across wells.

Few-shot learning achieves high accuracy with only 1-3 data points.

Model scales well with the number of wells and data availability.

Abstract

Recent literature has explored various ways to improve soft sensors by utilizing learning algorithms with transferability. A performance gain is generally attained when knowledge is transferred among strongly related soft sensor learning tasks. One setting where it is reasonable to expect strongly related tasks, is when learning soft sensors for separate process units that are of the same type. Applying methods that exploit transferability in this setting leads to what we call multi-unit soft sensing. This paper formulates a probabilistic, hierarchical model for multi-unit soft sensing. The model is implemented using a deep neural network. The proposed learning method is studied empirically on a large-scale industrial case by developing virtual flow meters (a type of soft sensor) for 80 petroleum wells. We investigate how the model generalizes with the number of wells/units. We demonstrate that multi-unit models learned from data from many wells permit few-shot learning of virtual flow meters for new wells. Surprisingly, regarding the difficulty of the tasks, few-shot learning on 1-3 data points often leads to high performance on new wells.