Predictive Maintenance for optimizing assets management in oil & gas field: case Halliburton Algeria

Abstract

In asset-intensive industries like oil and gas, maintenance strategies are central to operational performance. This thesis investigates the feasibility of implementing predictive maintenance (PdM) at Halliburton Algeria, using a qualitative case study approach. The research is structured into three main chapters: a combined literature review and theoretical framework; a methodological framework including a company overview; and an empirical study comprising findings, discussion, and recommendations. The study explores the evolution from traditional maintenance to data-driven strategies enabled by IoT and AI. It reveals that although Halliburton uses preventive and corrective methods supported by SAP, it lacks the digital infrastructure, organizational readiness, and workforce training required for PdM. The thesis introduces a PdM Readiness Framework based on strategic, technical, and human dimensions, offering practical steps toward phased adoption. This work contributes to understanding the real-world barriers to PdM and emphasizes the need for a holistic transformation across systems, skills, and strategy in brownfield environments.