Artificial intelligence for piping and instrumentation diagrams: a review and perspective

Abstract

Driven by the urgent demands for process efficiency, operational safety, and industrial intelligence, piping and instrumentation diagrams are evolving from static design documents into dynamic knowledge-intensive carriers. However, the intelligent digitization of piping and instrumentation diagrams faces systemic challenges due to their highly unstructured data format, dense symbolic information, and heterogeneous drafting styles, which hinder automated information extraction and result in a fragmented data ecosystem. Recent advancements in artificial intelligence, particularly in pattern recognition and nonlinear feature modeling, have enabled the automated extraction of core elements such as symbols, annotations, and connecting lines from piping and instrumentation diagrams, the reconstruction of process topologies, and the establishment of semantically enriched knowledge models. These developments provide a foundational framework for high-level applications including automated compliance checking, intelligent piping and instrumentation diagram generation, hazard and operability analysis, and digital twin development. This paper provides a systematic review of the state-of-the-art artificial intelligence-driven methodologies across the “perception-cognition-application” pipeline, analyzes current technical bottlenecks, and outlines future directions.

Keywords

artificial intelligence / piping and instrumentation diagrams / image processing / information extraction

RIGHTS & PERMISSIONS

Higher Education Press 2026

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.