Journal of Moeslim Research Technik

ALGORITHMIC INTELLIGENCE IN ENGINEERING DESIGN: INTEGRATING MACHINE LEARNING WITH PHYSICAL MODELING

2026-03-10T22:03:46+07:00

Increasing complexity in engineering systems demands design methodologies that balance computational efficiency, predictive accuracy, and physical reliability. Traditional physics-based simulations ensure mechanistic consistency but are computationally expensive, while purely data-driven machine learning models offer speed yet often lack interpretability and physical compliance. Integrating algorithmic intelligence with physical modeling has therefore emerged as a promising paradigm in advanced engineering design. This study aims to develop and evaluate a hybrid framework that integrates machine learning algorithms with governing physical equations to enhance design performance, robustness, and computational efficiency. A mixed-methods computational design was employed using 15,000 high-fidelity simulation datasets across structural, aerodynamic, and thermal engineering cases. Three modeling configurations—physics-based models, data-driven models, and hybrid physics-informed machine learning models—were comparatively analyzed using performance metrics including mean squared error, R², runtime efficiency, robustness testing, and constraint violation indices. Statistical analyses were conducted to determine significance of performance differences. Hybrid models achieved superior balance, reaching R² = 0.97 with significantly reduced runtime compared to physics-based simulations (p < 0.001), while maintaining substantially lower physical constraint violations than purely data-driven models. Sensitivity and uncertainty analyses confirmed enhanced robustness under parameter perturbation. Algorithmic intelligence integrated with physical modeling represents an epistemologically coherent and practically effective approach, advancing engineering design toward trustworthy, efficient, and physically consistent computational frameworks.

COST OPTIMIZATION OF JETTY RETROFIT USING VALUE ENGINEERING AND LIFE CYCLE COST ANALYSIS

2026-04-30T14:14:34+07:00

The increasing demand for sustainable infrastructure has led to a focus on cost optimization in retrofit projects, particularly in maritime infrastructure such as jetties. Sustainable development aims to balance economic growth, environmental protection, and social welfare, highlighting the need for efficient resource utilization. Jetty retrofit projects, crucial for port operations, often face high construction and maintenance costs. This study aims to evaluate the effectiveness of Value Engineering (VE) and Life Cycle Cost Analysis (LCCA) in optimizing the costs of jetty retrofit projects while ensuring long-term sustainability. A mixed-method research design was employed, combining quantitative data from questionnaires and statistical analysis with qualitative insights from field observations and interviews. The study found that integrating VE significantly reduced operational costs, particularly through the substitution of conventional energy systems with renewable energy sources such as solar panels. The application of LCCA demonstrated that long-term savings from energy efficiency could offset higher initial investments. The findings show that the use of VE and LCCA together can achieve cost savings of up to 5.21% and enhance financial viability, with a Benefit-Cost Ratio (BCR) of 2.20, Net Present Value (NPV) of IDR 40.40 billion, and an Internal Rate of Return (IRR) of 46.93%. These results underline the financial and environmental feasibility of green retrofit projects. This research contributes to sustainable infrastructure practices by highlighting cost-effective strategies for jetty retrofitting.

BEYOND DETERMINISTIC MODELS: PROBABILISTIC APPROACHES TO RISK-AWARE CIVIL ENGINEERING SYSTEMS

2026-04-12T17:33:58+07:00

Civil engineering systems increasingly operate under conditions of uncertainty, variability, and exposure to extreme events, challenging the adequacy of deterministic modeling approaches that rely on fixed assumptions and simplified safety margins. Probabilistic methods offer a more realistic representation by explicitly incorporating uncertainty into analysis and decision-making processes. This study aims to develop a risk-aware probabilistic framework that enhances reliability assessment and supports more informed engineering decisions. A mixed-methods computational design was employed, integrating stochastic modeling, Monte Carlo simulation, Bayesian updating, and reliability analysis across representative infrastructure systems. Results indicate that probabilistic and hybrid models achieve higher reliability indices, lower probabilities of failure, and reduced expected losses compared to deterministic approaches. Statistical analysis confirms significant differences in performance, while case-based validation demonstrates strong agreement between probabilistic predictions and observed system behavior. Findings further reveal that adaptive integration of data-driven techniques improves model accuracy and responsiveness under dynamic conditions. This study concludes that probabilistic approaches provide a robust and scalable paradigm for risk-aware civil engineering, offering substantial implications for infrastructure design, maintenance, and resilience planning.

ARCHITECTURAL ENGINEERING IN THE DIGITAL ERA: PARAMETRIC DESIGN AND STRUCTURAL RATIONALIZATION

2026-04-12T17:38:42+07:00

Architectural engineering in the digital era is increasingly shaped by parametric design methodologies that enable complex form generation and performance-driven optimization. Rapid advancements in computational tools have transformed design processes, yet a persistent gap remains between architectural exploration and structural rationalization, often resulting in inefficiencies and post-design adjustments. This study aims to develop an integrated computational framework that aligns parametric design with structural performance, ensuring that architectural forms are both innovative and structurally feasible. A computational design-based methodology was employed, combining parametric modeling, finite element analysis, and algorithmic optimization across representative architectural typologies. Iterative workflows were implemented to establish continuous feedback between geometric parameters and structural responses. Results indicate that integrated parametric-structural models achieve higher structural efficiency, reduced material consumption, and improved deformation control compared to conventional and non-integrated approaches. Statistical analysis confirms significant performance improvements, while case-based validation demonstrates strong alignment between simulated and expected structural behavior. Findings further reveal that real-time integration enhances design adaptability and decision-making efficiency. This study concludes that the integration of parametric design and structural rationalization represents a robust and scalable paradigm for contemporary architectural engineering, offering significant implications for sustainability, performance optimization, and interdisciplinary collaboration.

INTEGRATED ENGINEERING SYSTEMS THINKING: CROSS-DOMAIN METHODOLOGIES FOR COMPLEX TECHNOLOGICAL CHALLENGES

2026-04-29T21:48:40+07:00

The complexity of modern technological systems requires a shift from isolated engineering disciplines to more integrated approaches. Traditional engineering methodologies often fail to address the interconnected challenges presented by multi-disciplinary problems. Systems thinking, particularly when applied across domains, offers a more holistic framework that can optimize technological solutions by considering the interrelationships between various system components. This research investigates the application of integrated engineering systems thinking to complex technological challenges, emphasizing the value of cross-domain methodologies in improving efficiency, sustainability, and innovation. The study aims to develop a comprehensive framework for applying systems thinking across different engineering domains and to evaluate its effectiveness in real-world scenarios. A mixed-methods approach was employed, combining case studies from diverse sectors such as energy, manufacturing, and infrastructure, with data collected through interviews, surveys, and performance metrics. The findings reveal significant improvements in cost reduction, efficiency enhancement, and sustainability outcomes in organizations employing cross-domain methodologies. The research concludes that integrated engineering systems thinking provides a robust framework for solving complex technological problems, driving both operational performance and sustainable outcomes. Future studies should explore the long-term impacts and institutionalization of cross-domain collaboration in engineering practice.

SUSTAINABLE INDUSTRIAL ENGINEERING: SYSTEMS OPTIMIZATION UNDER RESOURCE CONSTRAINTS

2026-04-29T21:38:13+07:00

The increasing pressure to integrate sustainability into industrial practices has led to the need for more efficient systems optimization models that address resource constraints. Traditional optimization models in industrial engineering have focused predominantly on maximizing efficiency and minimizing costs, often overlooking the long-term environmental and social impacts. This research explores the intersection of sustainable development and systems optimization under resource limitations, aiming to develop a comprehensive framework that balances economic, environmental, and social factors in industrial processes. The study employs a mixed-methods approach, combining literature review, case studies from various industrial sectors, and mathematical optimization models. The results demonstrate that the integration of resource constraints into industrial systems significantly improves both operational performance and sustainability outcomes. Industries, particularly in manufacturing and logistics, showed considerable improvements in production efficiency and reductions in energy consumption and material waste. The research concludes that resource-constrained optimization models can lead to more sustainable industrial practices without compromising economic efficiency. The findings provide a valuable contribution to the field of industrial engineering, offering a framework that can be applied across diverse sectors seeking to optimize their systems within the boundaries of available resources. Future studies should extend these models to include more complex industrial sectors and explore long-term sustainability impacts.