The Deployment of Deep Learning Models for Performance Optimization and Failure Prevention of Electric Submersible Pumps

Abstract

Abstract Real-time sensors are crucial for monitoring electrical submersible pump (ESP) operation. However, manually analyzing the whole data from these sensors is virtually impossible due to its overwhelming volume. Artificial intelligence (AI) is a game-changing tool that can leverage the big data from ESP sensors more efficiently. Coupled with ESP knowledge, AI could reveal insights into ESP behaviors, well performances, and reservoirs dynamics, leading to ESP life extension and better production optimization. In this paper, we present the development and deployment of an AI workflow to enhance ESP surveillance. The workflow is developed in-house using the Python programming language and consists of the following four main modules: Data ingestion – to ingest all ESP-relevant databases Data preprocess – to transform the databases in the format ready for AI modelling AI modelling – to experiment several AI models, e.g., to detect ESP critical events, and predict ESP run life. Deployment – To automatically notify ESP critical events and visualize insight from the AI models The application of a hierarchical clustering algorithm reveals that the ESP run life in our fields are most influenced by gas production. Then, after more than 1000 runs of experiments, we achieve a deep learning model to predict whether an ESP will fail within the next 90 days. We also develop a module to automate nodal analysis as part of the AI workflow. Combining this physics-based model with a data-driven approach, the resulting AI models can accurately detect ESP critical events, such as ESP degradation, imminent gas lock, and sand production. To deploy the AI workflow, we build a dashboard to effectively visualize actionable insights from the AI models on our local server. The workflow sends notifications of ESP critical events to users for prompt troubleshooting actions and collects user feedbacks for improvement of the AI models in the next model development cycle. This paper demonstrates a holistic approach to develop a closed-loop ESP surveillance workflow that integrates the powers of AI, automation, and ESP knowledge including nodal analysis. The AI workflow potentially creates value of several million dollars or higher per year by extending ESP run lives and optimizing production. The lessons learnt from this AI workflow development are shared to assist the development and deploying of similar AI methods throughout the oil and gas industry.