Distributed fiber-optic sensing (DFOS) with intentionally spaced mechanical fixity points was experimentally evaluated for the structural health monitoring (SHM) of reinforced concrete (RC) members. A full-scale four-point bending test was conducted on a 12 m RC beam (400 × 400 mm) instrumented with a single-mode DFOS cable incorporating internal anchors at 2 m intervals and bonded externally with structural epoxy. Brillouin time-domain analysis (BOTDA) provided distributed strain measurements at approximately 0.5 m spatial resolution, with all cables calibrated to ±15,000 µε. Under stepwise monotonic loading, the system captured smooth, repeatable strain baselines and clearly resolved localized tensile peaks associated with crack initiation and propagation. Long-gauge averages exhibited a near-linear load–strain response (R² ≈ 0.99) consistent with discrete foil and vibrating-wire strain gauges. Even after cracking, the DFOS signal remained continuous, while some discrete sensors showed saturation or scatter. Temperature compensation via a parallel fiber ensured thermally stable interpretation during load holds. The fixed-point configuration mitigated local debonding effects and yielded unbiased long-gauge strain data suitable for assessing serviceability and differential settlement. Overall, the results confirm the suitability of fixed-point DFOS as a durable, SHM-ready sensing approach for RC foundation elements and as a dense data source for emerging digital-twin frameworks.

Reliable interpretation of distributed fiber optic sensing (DFOS) data from large building foundations requires accounting for thermal effects, temporal response, and structural context while preserving distributed spatial resolution. This study develops a machine-learning-assisted framework for pointwise screening and engineering interpretation of DFOS measurements from a reinforced-concrete piled-raft foundation. The workflow integrates temperature compensation, reference-profile comparison, deterministic engineering screening, structural-zone mapping, and Isolation Forest analysis using analysis strain, reference-relative strain change, and temperature change as ML inputs. The framework was demonstrated using 11 sequential profiles comprising 77,990 pointwise observations from the Block R Y-direction sensing segment. Two observations, at chainages 148.82 m and 367.94 m, shared the maximum Isolation Forest anomaly score. Independent post-processing showed that only the 148.82 m observation fell within the configured chainage-based screening neighborhood of R-Y-Z01. This result illustrates the value of combining response-based anomaly screening with independently retained structural context for engineering prioritization. The framework is intended to support engineering review rather than validated damage diagnosis; its current limitations include the short monitoring interval, route-based structural mapping, an adopted temperature-compensation coefficient, and the absence of independently labeled damage states.