The widespread application of reinforced concrete structures in different environmental conditions has underscored the need for effective maintenance and repair strategies. These structures offer numerous advantages, but are not impervious to the deleterious effects of chemical deterioration. The outcomes of this research hold significant implications for the management system of reinforced concrete structures. This study proposes the utilization of a fuzzy expert system as a means of enhancing the diagnosis of chemical deterioration in reinforced concrete structures that is a valuable tool for engineers and decision-makers involved in the maintenance and repair of these structures. The fuzzy expert system serves as an intelligent tool that can incorporate various symptoms of deterioration and inspection data to improve the accuracy and reliability of the diagnostic process. By integrating these inputs, the system evaluates 21 different data points, each representing a specific aspect of deterioration, on a scale ranging from 0 to 100. This numerical representation allows for a quantification of the level of deterioration, with 0 denoting minimal deterioration and 100 indicating severe deterioration. The effectiveness of the fuzzy expert system lies in its ability to process the vast amount of data and apply fuzzy operations on 352 fuzzy rules. These rules define the relationships between the inspection data, the type of deterioration, and its extent. Through this computational process, the fuzzy expert system can provide valuable insights into 10 distinct types of chemical deterioration, facilitating a more precise and comprehensive diagnosis. The implementation of the fuzzy expert system has the potential to revolutionize the field of diagnosing chemical deterioration in reinforced concrete structures. By addressing the limitations of traditional methods, this advanced approach can significantly improve the clarity and accuracy of the diagnostic process. The ability to obtain more precise information regarding the type and extent of deterioration is vital for developing effective maintenance and repair strategies. Ultimately, the fuzzy expert system holds great promise in enhancing the overall durability and performance of reinforced concrete structures in various environments.

The importance of structural health monitoring, especially for bridges that have exceeded their design life, has increased significantly to reduce maintenance costs, improve safety, and optimize performance. This article proposes a combination of machine learning tools for automatic detection of anomalies in bridge structures from accelerometer data. The Z-24 bridge, which has a comprehensive database of accelerometer data, was considered as a case study. By extracting modal frequencies from accelerometer data using operational modal analysis, the proposed framework, which combines machine learning methods, identifies damage-sensitive features and provides a coherent framework for structural health monitoring. One of the main innovations of the proposed method is the integration of reinforcement learning with autoencoders. The proposed method, Reinforcement Learning Autoencoder Neural Network (RLAENN), is validated using real accelerometer data, and its performance is compared with the classical benchmark algorithms, including Principal Component Analysis (PCA), Kernel PCA (KPCA), Gaussian Mixture Model (GMM), and Mahalanobis Square Distance (MSD). By eliminating the need to tune sensitive parameters, this method achieves significant improvements in accuracy and F1 score over conventional methods, confirming its performance and effectiveness.