Driven by China’s dual-carbon strategy, green transformation of existing buildings has become essential for sustainable urban renewal. Current renovation practice still suffers from fragmented planning, insufficient intelligent decision-making, and incomplete efficiency evaluation. This study constructs a full-process technical system of diagnosis, optimization, evaluation, and decision support by integrating BIM, artificial intelligence, IoT sensing, and multi-physics simulation. The system first establishes multidimensional perception of existing buildings through 3D laser scanning, IoT monitoring, infrared thermal imaging, and reverse BIM modeling. A machine-learning-based diagnostic model identifies defects in structural safety, thermal performance, energy consumption, indoor environment, and functional adaptation. A multi-objective optimization method combining improved NSGA-III and deep reinforcement learning is then used to select renovation strategies under constraints of safety, economy, comfort, and carbon reduction. Finally, a lifecycle efficiency evaluation system assesses environmental, economic, social, safety, and cultural value. The method is validated through renovation of an old office building, demonstrating improved model accuracy, optimized renovation schemes, and practical decision support. Because green-building renovation increasingly depends on electromagnetic sensing, smart monitoring, wireless control, and energy-management systems, the proposed framework contributes not only to building sustainability but also to engineering applications involving intelligent sensing and electromagnetic-compatible building environments.
Ni et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: