Artificial Intelligence for Condition Monitoring and Evaluation of Circulating Fluidized Bed Boilers: A Review

Abstract

Circulating fluidized bed (CFB) boilers combine multiphase dynamics, long transport delays, and multimode operation that challenge condition monitoring and performance evaluation. This structured narrative review surveys artificial intelligence for CFB state monitoring, fault diagnosis, performance assessment, and combustion optimization (2005–2026), supported by a reproducible literature search, structured evidence workbook, and concise quality appraisal. The literature is organized by monitoring objectives and method families from soft sensors and deep learning to physics-informed hybrids, digital twins, and multimodal non-destructive testing. Most included evidence remains single-unit and retrospective or offline; accuracy gains in publications often outpace verified sustained online use. One 150 MW project report estimated approximately EUR 699,000 in annualized benefits (not independently audited). Remaining gaps include cross-unit generalization, standardized benchmarks, secure deployment, and closed-loop diagnostics–maintenance integration.