Guest Editors:
Hua-Peng Chen
Ying Lei
Ling Yu

Damage diagnosis and prognosis for condition assessments of civil engineering structures in service are key elements in health monitoring of structural systems. A typical structural health monitoring strategy comprises several components, including sensors, data acquisition, data transmission, data processing, data management, health evaluation and decision making. Sensing technology (for acquiring and transmitting data) and signal interpretation algorithms (used for signal processing to extract key features sensitive to local damage) are two key factors in successful structural health monitoring strategies for engineering systems. Structural damage diagnosis techniques based on online measurements and advanced artificial intelligence (AI) technology can provide essential information for the assessment of current condition and the prediction of future performance. Using data from measurements collected during a structure’s life cycle, structural damage prognosis methods and lifecycle performance assessment techniques are able to ensure that a structure will operate safely and can aid in determining cost‐effective maintenance policy. The aim of the Special Collection is to share the latest developments in theoretical and experimental investigations of advanced AI techniques for damage diagnosis and prognosis of structural systems. Covered topics of the Special Collection include but are not limited to the latest advances in theory, techniques, methods, and future trends to advance knowledge in different aspects of AI such as deep learning, artificial neural networks, advanced sensors, soft computing, data mining and processing, damage diagnosis and prognosis, and smart structures, as well as case studies demonstrating practical applications of advanced AI techniques.