This paper presents an Artificial Intelligence (AI) based implementation for anomaly detection in critical industrial equipment at TotalEnergies. The approach was initially inspired by the work of Sipple, J. (2020), on AI anomaly detection in smart buildings. This approach has since then been adapted, applied, and extended to also handle multidimensional time series data effectively, whilst keeping model interpretability by design. The AI models have been successfully deployed in various North Sea assets and have been able to detect anomalous behaviour in the industrial rotating equipment, leading to improved visibility, efficiency, and reliability. The paper also discusses the motivations for the business case and change management processes associated with the implementation of the AI models.

Keywords:
united kingdom government, europe government, denmark government, anomaly detection, upstream oil & gas, artificial intelligence, norway government, data mining, project management, autoencoder
Subjects:
Strategic Planning and Management, Information Management and Systems, Project management, Artificial intelligence
Copyright 2023, Society of Petroleum Engineers DOI 10.2118/215491-MS
You can access this article if you purchase or spend a download.