<![CDATA[AbstrakTantangan 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 BerkelanjutanAbstractManaging 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]]>
