Sistem Deteksi Dini Kerusakan Bangunan Berbasis Artificial Intelligence: Peluang Technopreneurship untuk Pemeliharaan Infrastruktur Berkelanjutan
Abstract
Abstrak
Tantangan dalam menjaga keselamatan dan keberlanjutan infrastruktur bangunan di Indonesia kian mendesak seiring meningkatnya tingkat degradasi struktur akibat faktor lingkungan dan usia bahan. Pendekatan pemantauan konvensional acap kali dinilai kurang efisien untuk merespons dinamika kerusakan tersebut. Studi ini mengkaji potensi integrasi kecerdasan buatan (Artificial Intelligence), khususnya pemanfaatan Deep Learning dan Computer Vision, sebagai instrumen pemeliharaan preventif yang presisi. Melalui pendekatan Systematic Literature Review (SLR), penelitian ini mengevaluasi performa sejumlah arsitektur Deep Learning terkemuka—termasuk Inception V3, ResNet50, dan YOLO—dalam mendeteksi serta mengklasifikasikan cacat struktural seperti retakan beton. Temuan menunjukkan bahwa pemodelan berbasis Convolutional Neural Network (CNN) mampu menghasilkan tingkat akurasi hingga 99,98%, menghadirkan alternatif inspeksi yang jauh lebih cepat dibandingkan pengujian manual. Dilihat dari kacamata technopreneurship, efektivitas teknologi ini menciptakan ruang bagi lahirnya entitas start-up di bidang Construction Technology (ConTech) yang menawarkan solusi Structural Health Monitoring (SHM) otomatis, skema pemeliharaan prediktif, hingga pemetaan Digital Twin. Selain mendukung pemenuhan standar regulasi pemeliharaan gedung (Permen PUPR No. 24/2008), pemanfaatan sistem pintar ini berpeluang memangkas Life Cycle Cost (LCC) sekaligus memperkokoh keamanan ekosistem konstruksi nasional.
Kata Kunci: Technopreneurship, Kecerdasan Buatan, Monitoring Struktur Gedung, Deep Learning, Structural Health Monitoring, Infrastruktur Berkelanjutan
Abstract
Managing the structural safety and long-term reliability of building infrastructure in Indonesia has become an increasingly urgent issue, driven by environmental exposure and material degradation over time. Traditional monitoring practices often prove insufficient in addressing early-stage structural defects promptly. This study explores the application of Artificial Intelligence (AI)—specifically leveraging Deep Learning and Computer Vision techniques—as an advanced mechanism for preventive maintenance. Employing a Systematic Literature Review (SLR) methodology, this paper conducts a comparative analysis of prominent Deep Learning frameworks, including Inception V3, ResNet50, and YOLO, in identifying and categorizing structural flaws such as concrete cracks. The evaluation demonstrates that Convolutional Neural Network (CNN) architectures can attain detection accuracy levels up to 99.98%, offering a vastly more efficient alternative to conventional manual inspections. From an entrepreneurial standpoint, this technological advancement creates fertile ground for Construction Technology (ConTech) startups to introduce automated Structural Health Monitoring (SHM) platforms, predictive maintenance frameworks, and Digital Twin integrations. Ultimately, adopting AI-driven inspection tools not only reinforces compliance with national building maintenance mandates (Ministerial Regulation PUPR No. 24/2008) but also substantially lowers Life Cycle Costs (LCC) while fostering a safer, more sustainable built environment.
Keywords: Technopreneurship, Artificial Intelligence, Structural Damage Detection, Deep Learning, Structural Health Monitoring, Sustainable Infrastructure
Keywords
References
Bouabdallaoui, Y., Lafhaj, Z., Yim, P., Ducoulombier, L., & Bennadji, B. (2021). Predictive maintenance in building facilities: A machine learning-based approach. Sensors, 21(4), 1044. https://doi.org/10.3390/s21041044
Cheng, J. C. P., Chen, W., Chen, K., & Wang, Q. (2020). Data-driven predictive maintenance planning framework for MEP components based on BIM and IoT using machine learning algorithms. Automation in Construction, 112, 103087. https://doi.org/10.1016/j.autcon.2020.103087
Hacıefendioğlu, K., Altunışık, A. C., & Abdioğlu, T. (2023). Deep learning-based automated detection of cracks in historical masonry structures. Buildings, 13(12), 3113. https://doi.org/10.3390/buildings13123113
Hu, W., Ou, Y., Liu, H., Ni, P., & Chang, C. (2026). Integrating digital twin technologies for maintenance 4.0 in the building industry: A review and conceptual framework. Building and Environment, 288, 113997.
https://doi.org/10.1016/j.buildenv.2025.113997
Krishnan, S. S. R., Nalla Karuppan, M. K., Khadidos, A. O., Selvarajan, S., Tandon, S., & Balusamy, B. (2025). Comparative analysis of deep learning models for crack detection in buildings. Scientific Reports, 15, 2125. https://doi.org/10.1038/s41598-025-85983-3
Liu, S. S., & Arifin, M. F. A. (2021). Preventive maintenance model for national school buildings in Indonesia using a constraint programming approach. Sustainability, 13(4), 1874. https://doi.org/10.3390/su13041874
Mondal, T. G., & Chen, G. (2022). Artificial intelligence in civil infrastructure health monitoring—Historical perspectives, current trends, and future visions. Frontiers in Built Environment, 8, 1007886. https://doi.org/10.3389/fbuil.2022.1007886
Plevris, V., & Papazafeiropoulos, G. (2024). AI in structural health monitoring for infrastructure maintenance and safety. Infrastructures, 9(12), 225. https://doi.org/10.3390/infrastructures9120225
Su, M., Wan, J., Zhou, Q., Wang, R., Xie, Y., & Peng, H. (2024). Utilizing pretrained convolutional neural networks for crack detection and geometric feature recognition in concrete surface images. Journal of Building Engineering, 98, 111386. https://doi.org/10.1016/j.jobe.2024.111386
Villa, V., Naticchia, B., Bruno, G., Aliev, K., Piantanida, P., & Antonelli, D. (2021). IoT open-source architecture for the maintenance of building facilities. Applied Sciences, 11(12), 5374. https://doi.org/10.3390/app11125374
Wu, Y., Li, S., Li, J., Yu, Y., Li, J., & Li, Y. (2025). Deep learning in crack detection: A comprehensive scientometric review. Journal of Infrastructure Intelligence and Resilience, 4(3), 100144. https://doi.org/10.1016/j.iintel.2025.100144
Refbacks
- There are currently no refbacks.