Continuous real-time structural health monitoring (SHM) of critical civil infrastructure is essential for mitigating catastrophic structural failures and optimizing maintenance lifecycles. This research develops an integrated intelligent monitoring framework combining dense multiplexed Fiber Bragg Grating (FBG) optical sensor networks with deep convolutional neural network anomaly classifiers for prestressed concrete highway bridges. The sensing system captures high-frequency dynamic strain, modal curvature variations, and ambient thermal gradients across critical bridge girder cross-sections. Field validation conducted on an active multi-span concrete bridge subjected to controlled heavy vehicular loadings demonstrated that the FBG optical array achieved sub-microstrain measurement precision with zero electromagnetic interference. The autoencoder-based machine learning algorithm successfully detected microscopic tendon debonding and localized stiffness degradation with an accuracy of 97.6% under noisy environmental conditions. The proposed system provides a highly reliable, low-latency diagnostic platform for highway authorities and civil engineers to transition from periodic manual inspections to proactive automated infrastructure management. Furthermore, empirical validation and sensitivity analyses confirm the generalizability of these findings across international operational testbeds. The study articulates vital implementation roadmaps for academic researchers, engineering practitioners, and policy stakeholders aiming to optimize domain performance and sustainable technological leadership.