Artificial Intelligence and Predictive Maintenance for Super High-Rise Building Operations: A China-Focused Framework

Abstract

Super high-rise buildings in China concentrate extreme structural loads, complex mechanical and electrical systems, and dense occupant populations into vertical envelopes whose failure modes are costly and difficult to reverse. This article proposes a China-focused framework for the application of artificial intelligence (AI) and predictive maintenance (PdM) in the operation of super-tall buildings, drawing on Chinese empirical evidence from landmark projects such as Shanghai Tower and Tianjin 117, as well as pilot integrated safety platforms in Shanghai. Grounded in the Technology Acceptance Model (TAM) and socio-technical systems theory, the study adopts a conceptual methodology supported by secondary data analysis. The proposed framework integrates four layers: sensor and data acquisition, AI analytics, decision orchestration, and institutional governance. Findings suggest that AI-enabled PdM can shift super high-rise operations from reactive and schedule-based maintenance toward condition-based and prognostic regimes, reducing downtime, energy waste, and safety risk. Implications are discussed for Chinese operators and for Belt and Road Initiative (BRI) partner economies such as Kazakhstan, where similar systems are emerging in logistics hubs and high-rise public facilities. The article concludes with policy, managerial, and research recommendations.