2026-07-13T11:29:03+03:30 http://ijmt.ir/browse.php?mag_id=48&slc_lang=en&sid=1

48-883 2026-07-13 10.1002

International Journal of Maritime Technology ijmt 2345-6000 2476-5333 10.66224/ijmt 2025 21 2 Kimia Nazarizadeh nzryzadhkymya@gmail.com Hashem Nowruzi h.nowruzi@nit.ac.ir In marine engineering, ship vibration analysis is crucial for ensuring structural integrity, operational safety, and environmental sustainability. Traditional analysis, following classical paradigms established by early contributors such as Todd, Kumai, and Schlick, relies primarily on costly simulations and empirical tests. This study seeks to overcome these limitations by integrating machine learning (ML) methodologies with semi-empirical models to develop a predictive hybrid model, thereby advancing vibration analysis toward a data-driven paradigm. The research is significant for improving ship design, mitigating vibration-related risks, and reducing reliance on resource-intensive approaches, aligning with global efforts to promote energy-efficient and sustainable maritime operations. The proposed hybrid model combines Random Forest (RF) and Logistic Regression (LR), leveraging RF’s capacity for modeling nonlinear relationships and LR’s interpretability for linear adjustments. Trained on Kumai’s seminal dataset and validated on 373 cases spanning 34 ship types, the model accurately predicts critical parameters (α, τ₂, N₂, N₃, and c̄) with exceptional precision. Performance metrics demonstrate strong results, including near-perfect R² values (0.9938 for α) and minimal MSE (0.0000 for α, 0.0701 for N₃). Natural frequency predictions exhibit less than 3% error, as validated against empirical data for crude oil tankers. Feature importance analysis identifies structural parameters (length, displacement, block coefficient) as key predictors, enhancing interpretability for engineering applications. This work bridges the gap between classical vibration theory and modern ML, offering a cost-effective, scalable alternative to conventional simulations. By enabling precise vibration predictions across diverse vessels, the model facilitates predictive maintenance, design optimization, and operational safety. The findings highlight the transformative potential of hybrid ML in maritime engineering, paving the way for digital twins and sustainability-driven ship design. Hybrid Machine Learning Random Forest Logistic Regression Ship Vibrations Predictive Maintenance 2025 8 01 1 10 http://ijmt.ir/article-1-883-en.pdf 10.61882/ijmt.21.2.1

48-854 2026-07-13 10.1002

International Journal of Maritime Technology ijmt 2345-6000 2476-5333 10.66224/ijmt 2025 21 2 seyed morteza marashian m.marashian@stu.qom.ac.ir Ruhollah Amirabadi r.amirabadi@qom.ac.ir Mehdi Adjami adjami@shahroodut.ac.ir Robust critical infrastructure resilience is imperative for sustaining economic stability, national security, and societal well-being amid escalating multi-hazard threats. This study analyzes the process of designing resilient critical infrastructure through a comprehensive hybrid methodology, employing the logical framework of observation-assertion-argument. Meaningful integration of systemic thinking with core resilience indicators is achieved via synthesis of prior research and the developed hybrid approach. Empirical observation of the 2025 Shahid Rajaee Port explosion (70 fatalities, $198M losses) exposed systemic vulnerabilities within Iran’s International North-South Transport Corridor (INSTC), demonstrating that conventional redundancy measures failed to prevent service disruption during cascading failures. Shahid Beheshti Port’s role as Rajaee’s backup—sustaining INSTC operations—confirms that critical infrastructure resilience requires proportional capacity distribution across port networks and hazard-diversified risk management. We assert that true resilience necessitates intelligent redundancy harmonizing three pillars: inherent capacity (applying ecological adaptability principles to infrastructure), correlation-centric component design (mapping dynamic interdependencies), and stakeholder-driven self-organization. This is evidenced by the Rajaee incident, where centralized control exacerbated fire propagation, and further validated by seismic exposure analysis: despite Chabahar’s limited throughput, strategic enhancement of this sustainably developed port can mitigate future operational collapse at Rajaee. We argue that operationalizing resilience requires: (1) converting strategic policies into technical metrics (e.g., chaos-theoretic container handling capacity dispersion and multi-hazard contingency planning), (2) embedding modular metabolic flexibility to absorb localized shocks, and (3) institutionalizing learning loops through distributed adaptive control nuclei to complete critical infrastructure self-organization cycles. This study confirms that only integrated correlation-aware redundancy—not isolated backups—aligns socio-economic-environmental performance with sustainability across hazard cycles. Dynamic Resilience Critical Infrastructure System Performance Levels Inherent Resilience Component Interconnectivity Self-Organization Sustainability Backup Port INSTC. 2025 8 01 11 34 http://ijmt.ir/article-1-854-en.pdf 10.61882/ijmt.21.2.11

48-880 2026-07-13 10.1002

International Journal of Maritime Technology ijmt 2345-6000 2476-5333 10.66224/ijmt 2025 21 2 YASAMIN HASANI ASYABDAREH YHASANIASIYABDAREH139@gmail.com hassan akbari H.AKBARI@modares.ac.ir Resilient and sustainable port infrastructures are vital in addressing the growing complexities and uncertainties of modern maritime systems. This study emphasizes the necessity of an integrated understanding of four interrelated concepts (risk, resilience, reliability, and sustainability) in the context of port planning and operations. Despite the abundance of research on each of these dimensions individually, a comprehensive framework that effectively combines them for practical decision-making in port environments remains underdeveloped. Through a conceptual and comparative analysis, this research proposes a cohesive approach to these four dimensions and applies it in a case study of Shahid Rajaee Port, one of the most significant ports in southern Iran. The study identifies key deficiencies in current operational practices and recommends strategic solutions, including the integration of multimodal transport systems, implementation of IoT-based monitoring technologies, and employment of skilled and experienced personnel. A SWOT analysis is employed to assess internal and external factors influencing port performance, and tailored strategies are proposed to enhance long-term resilience and promote sustainable development. This integrated approach offers a comprehensive framework to support decision-making in port management under both environmental and human-induced risks.   Reliability Risk Resiliency Social and Economical Sustainability Environmental Sustainability Port Planning and Management SWOT Analysis 2025 8 01 35 45 http://ijmt.ir/article-1-880-en.pdf 10.61882/ijmt.21.2.35

48-873 2026-07-13 10.1002

International Journal of Maritime Technology ijmt 2345-6000 2476-5333 10.66224/ijmt 2025 21 2 Seyed Reza Samaei samaei@srbiau.ac.ir Mohammad Asadian Ghahfarokhi m.asadian@srbiau.ac.ir This study investigates the hydrodynamic performance of modular, chain-type floating docks designed for high-speed boat deployment within the operational zone of Shahid Bahonar Port. Given the limitations of fixed dock infrastructure—particularly in regions with soft seabeds and tidal variations—floating docks offer a flexible, cost-effective alternative. A modular pontoon system was designed using CATIA and analyzed in ANSYS AQWA under various wave conditions (0°, 45°, 90°, 135°, and 180°). Comparative simulations between single-body and multi-body configurations revealed that multi-hull docks significantly reduce vertical displacement and better distribute wave-induced forces, especially at connection points. Time-domain analyses further confirmed that joint stiffness and orientation strongly influence structural response. Elastic mooring systems enhanced the dock’s adaptability to dynamic sea conditions while minimizing environmental impact. These findings support the development of resilient floating marine structures tailored to the hydrodynamic conditions of semi-enclosed ports like Shahid Bahonar, with implications for both defense and commercial applications in high-salinity environments. Multi-hull floating docks hydrodynamic analysis Response Amplitude Operators (RAO) Hydrodynamic Behavior High-speed Boats. 2025 8 01 46 60 http://ijmt.ir/article-1-873-en.pdf 10.61882/ijmt.21.2.46

48-879 2026-07-13 10.1002

International Journal of Maritime Technology ijmt 2345-6000 2476-5333 10.66224/ijmt 2025 21 2 Kianoosh Salek kiaengsalek@yahoo.com Tahere Taghizade Firozjaee t.taghizade@shahroodut.ac.ir Maintaining a precisely controlled atmospheric environment is paramount for optimizing the operational effectiveness and survivability of military submarines. Early submarines operated with rudimentary atmospheric management, severely limiting submerged endurance. However, the escalating demands of naval warfare, particularly during and following World War I, catalyzed the development of progressively sophisticated air revitalization systems. These advancements enabled extended submerged operations, a key tactical advantage. The advent of nuclear-powered submarines marked a watershed moment, revolutionizing atmospheric control by eliminating the reliance on atmospheric oxygen for propulsion. This technological leap not only transformed submarine propulsion but also spurred the development of highly advanced air purification systems, subsequently influencing conventional diesel-electric submarine designs. More recently, the emergence of air-independent propulsion (AIP) submarines has further underscored the critical importance of efficient and reliable air revitalization, as these platforms strive for prolonged submerged durations. This comprehensive review examines the historical evolution of air purification methods in military submarines, specifically focusing on the pivotal technological advancements that have enabled extended submerged operations and significantly enhanced crew survivability. It highlights the development and refinement of key technologies, including electrochemical and chemical oxygen generation, advanced carbon dioxide removal techniques such as amine scrubbing and solid sorbents, and sophisticated contaminant control strategies utilizing catalytic converters and filtration systems. This review also explores how these advancements have been seamlessly integrated into both nuclear and AIP submarine platforms, detailing the unique challenges and solutions associated with each.   Air purification Pollution Submarine Atmosphere control Environment 2025 8 01 61 71 http://ijmt.ir/article-1-879-en.pdf 10.61882/ijmt.21.2.61

48-872 2026-07-13 10.1002

International Journal of Maritime Technology ijmt 2345-6000 2476-5333 10.66224/ijmt 2025 21 2 Ali Tasbihi a.tasbihi@ics.org.ir Ashkan Babazadeh ashkanbabazadeh@aut.ac.ir Seyed Mohsen Moosavi s.m.moosavi@ics.org.ir The line heating process is widely used in shipbuilding to form complex curvatures in steel plates, particularly in the bow and stern sections. However, the method’s reliance on skilled operators often leads to inconsistent results. This study presents the development of a deep neural network (DNN) model to predict optimal operational parameters for plate forming via line heating, thereby improving precision, repeatability, and automation. A coupled thermomechanical finite element model was developed using ANSYS APDL to simulate temperature distribution and deformation for various heating configurations. The simulation results were used to train the DNN, which consists of multiple hidden layers with dropout regularization to enhance generalization. The model successfully learned the nonlinear relationships between input parameters (heat source speed, heat input, and the number of heating passes) and resulting deformations. The trained DNN achieved high predictive accuracy, demonstrating its potential as a real-time decision-support tool in automated plate forming systems. This integration of FEM-based simulation and AI enables more efficient, consistent, and cost-effective manufacturing in the shipbuilding industry. The proposed DNN model achieved an average predictive accuracy of 49.92%, with performance exceeding 80% for cases with distinct deformation patterns. Plate Bending Line Heating Finite Element Analysis Thermo-mechanical Analysis Machine Learning 2025 8 01 72 79 http://ijmt.ir/article-1-872-en.pdf 10.61882/ijmt.21.2.72