Integrated Sensing and Modeling for Infrastructure Maintenance: SHM/Drones/AI and BIM/CIM/Digital-Twins (2016–2026)

Integrated Sensing and Modeling for Infrastructure Maintenance

A literature review of SHM / Drones / AI converging with BIM / CIM / Digital Twins for roads, bridges, and buildings (incl. heritage), 2016–2026.

TL;DR

Two research pillars are converging. Pillar A (sensing & diagnostics) — structural health monitoring (SHM), UAVs/drones, and AI computer vision — generates condition data ever faster and cheaper. Pillar B (modeling & management) — BIM/CIM, digital twins, and HBIM — turns that data into life-cycle decisions. Their meeting point is the digital twin: a living model fed by live sensing and AI. This review synthesizes ~50 papers (Consensus, 2016–2026) across both pillars, four emphasis angles — heritage/HBIM, low-cost/accessibility, disaster & seismic resilience, and automation/data fusion — and a dedicated strand on corrosion (monitoring, maintenance & repair), the dominant deterioration mechanism for reinforced-concrete and steel infrastructure. It ends with research gaps relevant to road/bridge/building (and heritage) maintenance in budget-constrained settings.

1. Scope, question, and method

Aging infrastructure, a shrinking inspection workforce, and tight budgets are pushing maintenance from periodic manual inspection toward continuous, data-driven, and increasingly automated practice (He et al., 2022; Rizzo et al., 2021). This review asks: how are sensing technologies (SHM, drones, AI) and digital modeling technologies (BIM/CIM, digital twins, HBIM) developing — and converging — for the maintenance of roads, bridges, and buildings, including heritage structures — and how is the field’s dominant deterioration mechanism, corrosion, monitored and repaired?

Sources were retrieved via the Consensus academic search engine, restricted to 2016–2026, prioritizing landmark (highly cited) and recent review papers across twelve thematic queries, then curated to ~50 works. This is a narrative thematic synthesis, not an exhaustive PRISMA review; author lists in the references are abbreviated and should be completed from the linked source before any formal reuse.

How this maps to the workshop

Pillar A deepens SHM-Drones-AI; Pillar B deepens BIM-CIM-Digital-Twin; the corrosion strand connects to host Prof. Miyazato’s durability research and the maintenance cycle; the seismic-resilience strand connects to Disaster-Damage-Restoration and the Noto visit.

Theme	Coverage	Anchor works
A1 SHM & sensor networks	Wired→wireless, integrated SHM, sensor placement	He et al. 2022; Noel et al. 2017; Sun et al. 2025
A2 UAV/drone inspection	Access, 3D models, NDT payloads	Shakhatreh et al. 2018; Feroz et al. 2021
A3 AI defect detection	CNN→segmentation→YOLO	Cha et al. 2017; Dung & Anh 2019
B1 BIM/CIM maintenance	3D data models, 6D, MR, SHM viz	Wan et al. 2019; Medrano-Sánchez et al. 2025
B2 Digital twins	Living models, cloud+DL, hybrid fusion	Ye et al. 2019; Dang et al. 2021; Sakr & Sadhu 2024
B3 HBIM (heritage)	Scan-to-BIM, conservation data	López et al. 2018; Bruno et al. 2019
Heritage SHM	Masonry NDT/OMA, ML	Pallarés et al. 2021; Mishra 2020
Seismic/disaster	Rapid AI damage assessment	Lu et al. 2021; López-Castro et al. 2022
Low-cost	MEMS/IoT/smartphone	Di Nuzzo et al. 2021; Sarmadi et al. 2023
Corrosion monitoring	Electrochemical/EMI/embedded sensors	Fan et al. 2021; Hu et al. 2022
Corrosion repair & protection	Patch/FRP, cathodic protection, inhibitors, LCC	James et al. 2019; Wittocx et al. 2022

2. Pillar A — Sensing and diagnostics

2.1 Structural health monitoring and sensor networks

SHM has shifted decisively from wired to wireless sensor networks (WSN) to cut installation and maintenance cost (Noel et al., 2017). Contemporary “integrated SHM” couples diverse sensing (fiber-optic, piezoelectric, GNSS, magnetostrictive), low-power wireless transmission (ZigBee, Bluetooth, NB-IoT, Wi-Fi, LoRa), and AI-based data processing into end-to-end diagnosis and early-warning systems (He et al., 2022). Yet reviews repeatedly stress a persistent gap between academic capability and real-world deployment, alongside unsolved problems in detecting specific damage (stiffness loss, fatigue, corrosion, scour) and in sensor drift over long deployments (Rizzo et al., 2021). Optimal sensor placement remains foundational and is increasingly tackled with machine learning while being explicitly linked to digital-twin implementation (Sun et al., 2025). Crucially, “next-generation” sensing now spans smartphones, UAVs, cameras, and robotic platforms — already foreshadowing the convergence with the other pillar (Sony et al., 2019).

2.2 UAV / drone inspection

UAVs have become a viable augmentation to manual inspection, reaching otherwise inaccessible elements (decks, piers, towers), reducing cost, time, and risk, and avoiding lane closures (Shakhatreh et al., 2018; Feroz et al., 2021). Beyond visual capture, drones enable image-based 3D reconstruction of structures (Khaloo et al., 2018) and, when paired with deep learning (e.g., region-based CNNs), automated crack identification and quantification on aging concrete bridges (Kim et al., 2018). Camera-equipped UAVs are also used with BIM priors for construction and condition monitoring — an early convergence signal (Ham et al., 2016). Remaining barriers are as much regulatory and operational (airspace, privacy, big-data processing) as technical (Feroz et al., 2021).

2.3 AI and computer-vision defect detection

The defining shift of the decade is from hand-crafted image processing to deep learning. Cha et al. (2017), one of the most cited works in the field (~2,900 citations), showed CNNs detecting concrete cracks at ~98% accuracy and robustly under realistic lighting and shadow, without explicit feature engineering. Comparative work confirmed DCNNs outperform classical edge detectors and resolve far finer cracks (Dorafshan et al., 2018). The field then advanced from classification to pixel-level semantic segmentation via fully convolutional networks, enabling crack mapping and quantification (~90% average precision; Dung & Anh, 2019). Subsequent systematic reviews trace the move toward instance segmentation (Mask R-CNN) and real-time detectors (YOLO) reaching mean average precision around 0.9 (Ali et al., 2022; Medrano-Sánchez et al., 2025).

3. Pillar B — Modeling and management

3.1 BIM / CIM for maintenance

BIM/CIM reframes maintenance around a data-rich 3D model rather than 2D drawings and paper records. Bridge management systems built on BIM integrate inspection data, IFC standards, GIS, and web/QR access for collaborative, visual management (Wan et al., 2019), with later work formalizing maintenance data schemas so safety-diagnosis information is machine-interpretable (Byun et al., 2021). Extensions include 6D BIM that adds time, cost, and carbon for life-cycle asset management (Kaewunruen et al., 2020); BIM as a platform to visualize SHM sensor streams (Boddupalli et al., 2019); and mixed-reality (HoloLens) interfaces for on-site inspection (Nguyen et al., 2021). A 2025 PRISMA review nonetheless finds BIM-based bridge maintenance still fragmentary, naming interoperability (IFC 4.3), high LiDAR cost (>10% of annual budgets), scarce visual-programming skills, and cybersecurity as the dominant adoption barriers (Medrano-Sánchez et al., 2025).

3.2 Digital twins

A digital twin (DT) is a virtual replica updated in near-real-time from its physical counterpart, supporting “what-if” simulation and predictive maintenance (Ye et al., 2019). Demonstrations have matured from concept to practice: cloud-based DT frameworks using deep learning detect damage on model and real bridges (~92%; Dang et al., 2021); hybrid model-data DTs fuse finite-element models, BIM, and IoT for full-field “virtual sensing” (Sun et al., 2024); and DTs are extended to resilience and climate-change adaptation for railway bridges, quantifying cost and emissions across the life cycle (Kaewunruen et al., 2022). A recent systematic review organizes DT-for-SHM by asset class and modeling approach (FE, BIM, surrogate, hybrid) and articulates the open gaps (Sakr & Sadhu, 2024).

3.3 HBIM — heritage building information modeling

For heritage structures, BIM is adapted into HBIM: laser scanning and photogrammetry feed semantically rich models capturing irregular historic fabric and, importantly, non-geometric historical, diagnostic, and conservation data (López et al., 2018; Bruno et al., 2019). HBIM supports documentation, planned conservation, and decision-making across a monument’s life cycle, but adoption is constrained by complex geometry modeling, specialized skills, and a lack of shared standards and interoperability (Penjor et al., 2024). The frontier integrates HBIM with GIS and UAV photogrammetry for evidence-based, element-level conservation planning even under constrained-access, resource-limited conditions (Dammag et al., 2026).

4. Convergence — from sensing to digital twins

The two pillars increasingly meet in a single pipeline: sensors + drones + AI → BIM/CIM model → digital twin → decision. Integrated-SHM and DT reviews both describe this fusion as the field’s trajectory (He et al., 2022; Sakr & Sadhu, 2024). Concrete instances already exist — BIM used to organize and visualize SHM data (Boddupalli et al., 2019; Ye et al., 2019), cloud + deep-learning twins (Dang et al., 2021), and hybrid FE+BIM+IoT data fusion with virtual sensing (Sun et al., 2024). The 2025 bridge-maintenance review explicitly frames the BIM ↔ digital-twin ↔ IoT ↔ AI convergence, with CNN/YOLO crack detection feeding the model (Medrano-Sánchez et al., 2025). The overarching trend is a move from static information models toward living, predictive, and partly automated management systems.

5. Corrosion: monitoring, maintenance, and repair

Reinforcement corrosion is the single most important deterioration mechanism for reinforced-concrete (RC) infrastructure — implicated in more than ~70% of RC damage, with a global corrosion cost on the order of trillions of dollars per year (Renne et al., 2022; Topcu et al., 2020). It is also the host institution’s research core (durability/chloride corrosion), making this strand directly workshop-relevant and a concrete instance of the diagnosis → countermeasure steps of the maintenance cycle.

5.1 Corrosion monitoring (sensing)

Monitoring spans electrochemical methods (half-cell potential, linear-polarization corrosion rate, concrete resistivity) and physical/wave methods. Comprehensive reviews classify the main sensor families — electrochemical, optical-fiber, elastic-wave, electromagnetic, and “untouched” sensors — and assess maturity, range, and limitations to guide selection (Fan et al., 2021); electrochemical sensors are reviewed specifically for new, existing, and repaired structures (Freitas, 2017). A fast-growing SHM-style thread embeds piezoelectric (PZT) sensors and uses the electro-mechanical impedance (EMI) technique to track chloride-induced corrosion in real time (Morwal et al., 2023). Practically, autonomous distributed embedded systems now stream corrosion rate, potential, temperature, and resistivity to the cloud to build corrosion-penetration “damage diagrams” and support service-life prediction (Monreal-Trigo et al., 2024). This ties corrosion sensing directly to Pillar A (SHM) and to Pillar B (LCC decisions). Open issues remain spatial resolution, long-term stability, quantitative interpretation, and cost (Fan et al., 2021).

5.2 Detection, protection, and repair

The literature increasingly treats detection → protection → repair as one decision chain. Hu et al. (2022) organize protection into “prevention” solutions (high-performance fiber-reinforced cementitious composite overlays, anti-corrosion coatings, inhibitors) and “therapy” solutions (cathodic protection, electrochemical chloride extraction), highlighting dual-function materials such as CFRP acting as both strengthening and anode. For coastal/marine structures, James et al. (2019) compile deterioration-level tests and categorize protection, maintenance, and repair against international codes, addressing both carbonation and chloride attack. Goyal et al. (2018) compare inhibitors, alternative reinforcement, coatings, and electrochemical techniques (per BS 1504-9), concluding electrochemical methods are generally most effective. For restoring already-corroded members, strengthening reviews and tests show steel-, FRP-, ECC-, and FRCM-jacketing can recover or exceed lost capacity, with design recommendations by loading scenario (Brindha et al., 2023). Durability modeling now couples ionic transport, electrochemical rehabilitation (chloride removal, inhibition, crack repair), and service-life prediction (Liu, 2022).

5.3 Cathodic protection and inhibitors (preventive levers)

Cathodic protection (CP) — galvanic or impressed-current (ICCP) — is a mature preventive technology that can arrest chloride-induced corrosion for decades; field experience over 10–20+ years documents principles, economics, and practical pitfalls (Polder, 2020), while long-term field studies reveal side effects such as localized phase changes and neutralization around anodes (Geiker et al., 2025). Corrosion inhibitors (anodic, cathodic, mixed; admixed or migrating; increasingly “green”/non-toxic) delay initiation and extend service life (Topcu et al., 2020). These are precisely the preventive levers in the preventive-vs-corrective argument that drives whole-life cost down.

5.4 Choosing a repair strategy — life-cycle thinking

Because options range from a cheap patch to full replacement, repair-strategy selection is fundamentally a life-cycle problem. Coupled LCA/LCC studies of corrosion-damaged elements find that for short service-life extension (~5 y) a minimal patch repair is most efficient, whereas conventional repair or cathodic protection become competitive for longer extensions (~40 y), and full demolition-and-replacement is usually the costliest, highest-impact option (Wittocx et al., 2022). Broader LCA/LCCA reviews of concrete repair stress strong case-specificity and the need for standardized methods (Renne et al., 2022) — connecting corrosion repair back to 6D BIM and life-cycle asset management and closing the loop with Pillar B.

6. Cross-cutting emphasis angles

6.1 Heritage conservation

Heritage adds hard constraints: heterogeneous masonry, poorly known material properties, hidden defects, and a strict need for non-invasive methods (Pallarés et al., 2021). Practice centers on operational modal analysis, radar interferometry, and acoustic emission for slender masonry (towers, bell towers), with low-impact wireless MEMS networks enabling continuous, minimally intrusive monitoring of historic towers (Barsocchi et al., 2020; Pallarés et al., 2021). Machine learning is now applied to predict masonry strength, damage scenarios, and seismic vulnerability of heritage buildings (Mishra, 2020), while HBIM provides the documentation and management backbone (López et al., 2018). Systematic reviews still flag missing standards, interoperability, and the difficulty of revealing hidden defects (Soleymani et al., 2023; Penjor et al., 2024).

6.2 Low-cost and accessibility

A vigorous recent thread aims to democratize SHM. MEMS accelerometers combined with NB-IoT achieve multi-year battery life and accuracy approaching piezoelectric references at a fraction of the cost (Di Nuzzo et al., 2021). Smartphone sensing is reviewed as a scalable, accessible platform — particularly for resource-limited regions — using built-in accelerometers, cameras, and GPS (Sarmadi et al., 2023). Low-cost reviews catalogue Arduino/NodeMCU-based systems and their practical pitfalls (Komary et al., 2024). Notably, an affordable digital twin using cheap wireless accelerometers, machine learning, and edge computing is presented explicitly as a way to “democratize SHM” to thousands of railway bridges (Armijo et al., 2024) — directly relevant to developing-country road agencies.

6.3 Disaster and seismic resilience

AI is accelerating post-earthquake assessment, where speed saves lives. Approaches include CNNs with transfer learning to classify damage from images (Ogunjinmi et al., 2022), YOLOv4 for multicategory reinforced-concrete damage and rapid safety assessment (Zou et al., 2022), and deep learning on ground-motion time–frequency representations for near-real-time regional damage estimation (Lu et al., 2021). A systematic review argues SHM should strengthen post-earthquake procedures and emphasizes cost-effective wireless MEMS for seismically active, resource-limited regions (López-Castro et al., 2022); DTs further support resilience and climate adaptation (Kaewunruen et al., 2022). This strand connects directly to Disaster-Damage-Restoration and the Noto reconstruction context.

6.4 Automation and data fusion

The convergence frontier is automation plus fusion. Hybrid digital twins combine physics-based (FE) and data-driven (ML) models for virtual sensing (Sun et al., 2024); cloud and edge pipelines automate detection (Dang et al., 2021; Armijo et al., 2024); and transformer/attention models forecast structural response and flag anomalies as early-warning indicators (Zhou et al., 2026). A complementary “human–machine collaboration” view keeps experts in the loop for judgment while ML handles routine detection — pragmatic where labeled damage data are scarce (Muin & Mosalam, 2021). The recurring vision is fusing heterogeneous data (sensors, images, models) into one decision platform (He et al., 2022; Sakr & Sadhu, 2024).

7. Research gaps and future directions

Synthesized gaps (where the field is thin)

1. Academia-to-practice gap. Few long-term, in-service deployments; SHM does not yet legally replace mandated visual inspection (Rizzo et al., 2021; Sony et al., 2019).
2. Interoperability & standards. IFC 4.3 / open schemas for BIM and HBIM; standardized performance metrics (Medrano-Sánchez et al., 2025; Penjor et al., 2024).
3. Cost vs. reliability. Low-cost sensing is advancing fast, but data reliability, time synchronization, and cross-device consistency are unresolved (Sarmadi et al., 2023; Di Nuzzo et al., 2021).
4. Data scarcity for ML. Labeled damage data are rare; SHM often has only healthy-state data, limiting supervised learning and generalization across structures (Muin & Mosalam, 2021).
5. Heritage specifics. Modeling irregular geometry, ensuring non-invasiveness, and revealing hidden defects, with few shared standards (Soleymani et al., 2023; Penjor et al., 2024).
6. Immature convergence. True closed-loop digital twins (real-time update + prediction + decision) and physics-plus-data fusion remain early-stage (Sun et al., 2024; Sakr & Sadhu, 2024).
7. Robustness & governance. Environmental/operational variability, sensor drift, edge/energy limits, and cybersecurity of cloud-IoT-DT systems (Sun et al., 2025; Medrano-Sánchez et al., 2025).
8. Corrosion monitoring maturity & integration. Many corrosion sensors (esp. embedded EMI/electrochemical) remain lab-validated; long-term field reliability, quantitative interpretation, and integration into BMS/digital-twin platforms are still open (Fan et al., 2021; Hu et al., 2022).

Promising directions: edge-AI and energy-neutral nodes; blockchain-secured data exchange; smartphone/citizen sensing at scale; climate-resilience digital twins; standardized benchmarks and open datasets; ML-driven sensor placement; and embedded corrosion sensing fused into life-cycle decision platforms (Sun et al., 2025; Medrano-Sánchez et al., 2025; Monreal-Trigo et al., 2024).

Opportunities aligned to your context (CMU; roads, bridges, buildings, heritage; budget-constrained)

• Low-cost SHM + lightweight digital twin for Thai bridges, adapting MEMS/IoT + ML pipelines (Di Nuzzo et al., 2021; Armijo et al., 2024) to local budgets.
• Embedded corrosion monitoring + LCC-driven repair selection for chloride-exposed (coastal/de-iced) Thai RC structures, linking sensors to repair-strategy choice (Monreal-Trigo et al., 2024; Wittocx et al., 2022).
• HBIM + non-invasive monitoring for SE-Asian heritage (e.g., temples/historic timber-masonry), combining scan-to-HBIM with low-impact sensing (Bruno et al., 2019; Barsocchi et al., 2020).
• Smartphone/UAV + AI for post-flood and seismic rapid assessment, transferring Japanese SIP-style methods under resource constraints (Ogunjinmi et al., 2022; López-Castro et al., 2022).

8. Conclusion

Across 2016–2026, sensing (SHM, drones, AI) and modeling (BIM/CIM, digital twins, HBIM) have matured from separate toolsets into a converging pipeline whose endpoint is the predictive digital twin — and corrosion, the field’s dominant deterioration mechanism, is increasingly monitored and repaired within that same data-driven, life-cycle framework. The strongest near-term opportunities for road/bridge/building and heritage maintenance — especially in budget-constrained settings — lie not in any single frontier technology but in integrating affordable sensing (including embedded corrosion sensors), automated AI diagnostics, and lightweight digital models into deployable, low-cost decision systems. That integration, and the data, standards, and skills it requires, is where the open research questions now concentrate.

---

References (APA 7; author lists abbreviated — verify before formal use)

1. Ali, R., et al. (2022). Structural crack detection using deep convolutional neural networks. Automation in Construction.
2. Armijo, A., et al. (2024). Integration of railway bridge structural health monitoring into the Internet of Things with a digital twin: A case study. Sensors.
3. Barsocchi, P., et al. (2020). Wireless sensor networks for continuous structural health monitoring of historic masonry towers. International Journal of Architectural Heritage.
4. Boddupalli, C., et al. (2019). Improved visualization of infrastructure monitoring data using building information modeling. Structure and Infrastructure Engineering.
5. Brindha, U., et al. (2023). Quantitative assessment of strengthening strategies and design recommendations for the repair of corrosion-damaged reinforced concrete members. Buildings.
6. Bruno, N., et al. (2019). HBIM for conservation: A new proposal for information modeling. Remote Sensing.
7. Byun, N.-J., et al. (2021). Development of BIM-based bridge maintenance system considering maintenance data schema and information system. Sustainability.
8. Cha, Y.-J., et al. (2017). Deep learning-based crack damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering.
9. Dammag, B. Q. D., et al. (2026). A geospatially enabled HBIM–GIS framework for sustainable documentation and conservation of heritage buildings. Buildings.
10. Dang, H. V., et al. (2021). Cloud-based digital twinning for structural health monitoring using deep learning. IEEE Transactions on Industrial Informatics.
11. Di Nuzzo, F., et al. (2021). Structural health monitoring system with narrowband IoT and MEMS sensors. IEEE Sensors Journal.
12. Dorafshan, S., et al. (2018). Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete. Construction and Building Materials.
13. Dung, C. V., & Anh, L. D. (2019). Autonomous concrete crack detection using deep fully convolutional neural network. Automation in Construction.
14. Fan, L., et al. (2021). Techniques of corrosion monitoring of steel rebar in reinforced concrete structures: A review. Structural Health Monitoring.
15. Feroz, S., et al. (2021). UAV-based remote sensing applications for bridge condition assessment. Remote Sensing.
16. Freitas, R. (2017). Electrochemical sensors for monitoring the corrosion conditions of reinforced concrete structures: A review. Applied Sciences.
17. Geiker, M., et al. (2025). Long-term phase changes in cathodically protected marine reinforced concrete bridge. Materials and Structures.
18. Goyal, A., et al. (2018). A review of corrosion and protection of steel in concrete. Arabian Journal for Science and Engineering.
19. Ham, Y., et al. (2016). Visual monitoring of civil infrastructure systems via camera-equipped unmanned aerial vehicles (UAVs): A review of related works. Visualization in Engineering.
20. He, Z., et al. (2022). Integrated structural health monitoring in bridge engineering. Automation in Construction.
21. Hu, J., et al. (2022). A review on corrosion detection and protection of existing reinforced concrete (RC) structures. Construction and Building Materials.
22. James, A., et al. (2019). Rebar corrosion detection, protection, and rehabilitation of reinforced concrete structures in coastal environments: A review. Construction and Building Materials.
23. Kaewunruen, S., et al. (2020). Sustainability-based lifecycle management for bridge infrastructure using 6D BIM. Sustainability.
24. Kaewunruen, S., et al. (2022). Digital twins for managing railway bridge maintenance, resilience, and climate change adaptation. Sensors.
25. Khaloo, A., et al. (2018). Unmanned aerial vehicle inspection of the Placer River Trail Bridge through image-based 3D modelling. Structure and Infrastructure Engineering.
26. Kim, I.-H., et al. (2018). Application of crack identification techniques for an aging concrete bridge inspection using an unmanned aerial vehicle. Sensors.
27. Komary, M., et al. (2024). Advancing smart health monitoring: A review of low-cost sensors for structural assessment. Procedia Structural Integrity.
28. Liu, Q.-f. (2022). Progress and research challenges in concrete durability: Ionic transport, electrochemical rehabilitation and service life prediction. RILEM Technical Letters.
29. López, F. J., et al. (2018). A review of heritage building information modeling (H-BIM). Multimodal Technologies and Interaction.
30. López-Castro, B., et al. (2022). A systematic review of structural health monitoring systems to strengthen post-earthquake assessment procedures. Sensors.
31. Lu, X., et al. (2021). A deep learning approach to rapid regional post-event seismic damage assessment using time-frequency distributions of ground motions. Earthquake Engineering & Structural Dynamics.
32. Medrano-Sánchez, E., et al. (2025). Strategies for bridge maintenance using BIM: An analysis of methodologies and tools. Frontiers in Built Environment.
33. Mishra, M. (2020). Machine learning techniques for structural health monitoring of heritage buildings: A state-of-the-art review and case studies. Journal of Cultural Heritage.
34. Monreal-Trigo, J., et al. (2024). Distributed embedded system for multiparametric assessment of infrastructure durability using electrochemical techniques. Sensors.
35. Morwal, T., et al. (2023). Monitoring chloride-induced corrosion in metallic and reinforced/prestressed concrete structures using piezo sensors-based electro-mechanical impedance technique: A review. Measurement.
36. Muin, S., & Mosalam, K. M. (2021). Human-machine collaboration framework for structural health monitoring and resiliency. Engineering Structures.
37. Nguyen, D.-C., et al. (2021). BIM-based mixed-reality application for bridge inspection and maintenance. Construction Innovation.
38. Noel, A. B., et al. (2017). Structural health monitoring using wireless sensor networks: A comprehensive survey. IEEE Communications Surveys & Tutorials.
39. Ogunjinmi, P. D., et al. (2022). Rapid post-earthquake structural damage assessment using convolutional neural networks and transfer learning. Sensors.
40. Pallarés, F. J., et al. (2021). Structural health monitoring (SHM) and nondestructive testing (NDT) of slender masonry structures: A practical review. Construction and Building Materials.
41. Penjor, T., et al. (2024). Heritage building information modeling (HBIM) for heritage conservation: Framework of challenges, gaps, and existing limitations of HBIM. Digital Applications in Archaeology and Cultural Heritage.
42. Polder, R. (2020). Cathodic protection of reinforced concrete structures in the Netherlands — Experience and developments. (Venue not indexed in source.)
43. Renne, N., et al. (2022). Sustainable assessment of concrete repairs through life cycle assessment (LCA) and life cycle cost analysis (LCCA). Infrastructures.
44. Rizzo, P., et al. (2021). Challenges in bridge health monitoring: A review. Sensors.
45. Sakr, M., & Sadhu, A. (2024). Recent progress and future outlook of digital twins in structural health monitoring of civil infrastructure. Smart Materials and Structures.
46. Sarmadi, H., et al. (2023). Review on smartphone sensing technology for structural health monitoring. Measurement.
47. Shakhatreh, H., et al. (2018). Unmanned aerial vehicles (UAVs): A survey on civil applications and key research challenges. IEEE Access.
48. Soleymani, A., et al. (2023). Damage detection and monitoring in heritage masonry structures: Systematic review. Construction and Building Materials.
49. Sony, S., et al. (2019). A literature review of next-generation smart sensing technology in structural health monitoring. Structural Control and Health Monitoring.
50. Sun, L., et al. (2024). Hybrid monitoring methodology: A model-data integrated digital twin framework for structural health monitoring and full-field virtual sensing. Advanced Engineering Informatics.
51. Sun, Z., et al. (2025). Optimal sensor placement for structural health monitoring: A comprehensive review. Journal of Sensor and Actuator Networks.
52. Topcu, I. B., et al. (2020). Properties of corrosion inhibitors on reinforced concrete. (Venue not indexed in source.)
53. Wan, C., et al. (2019). Development of a bridge management system based on the building information modeling technology. Sustainability.
54. Wittocx, L., et al. (2022). Revamping corrosion damaged reinforced concrete balconies: Life cycle assessment and life cycle cost of life-extending repair methods. Journal of Building Engineering.
55. Ye, C., et al. (2019). A digital twin of bridges for structural health monitoring. Structural Health Monitoring.
56. Zhou, F., et al. (2026). Transformer self-attention encoder–decoder with multimodal deep learning for response time series forecasting and digital twin support in wind structural health monitoring. Computers & Structures.
57. Zou, D., et al. (2022). Multicategory damage detection and safety assessment of post-earthquake reinforced concrete structures using deep learning. Computer-Aided Civil and Infrastructure Engineering.

Provenance & caveats

Retrieved via Consensus (Semantic Scholar, PubMed, Scopus, arXiv), filtered to 2016–2026. ~57 works are listed; the synthesis foregrounds ~50 core papers. Citation counts and journal names are as reported by Consensus at retrieval (two venues were not indexed in the source and are marked accordingly). Author lists are abbreviated and a few first-author initials are inferred — confirm full metadata via each linked source (or run /ars-citation-check) before using in a submission.