Improving Concrete Performance in Urban and Industrial Applications with Novel Technologies

This research aims to address two major challenges in the construction industry-increasing the resistance of concrete structures in heavy industries and reducing the environmental pollution of building materials-by investigating the integration of two advanced technologies: macro-synthetic fiber-reinforced concrete and optimized recycled concrete with neural networks. Background and Necessity of Research: In the oil industry, particularly in the oil-rich regions of southern Iran, concrete structures used in drilling rigs are susceptible to failure due to dynamic loads, chemical corrosion, and thermal stresses. On the other hand, in urban environments, millions of tons of concrete waste are landfilled annually, which not only wastes natural resources but also increases greenhouse gas emissions. This study, by combining novel technologies, offers a solution to mitigate these challenges. Methodology and Innovation: Macro-synthetic Fiber-Reinforced Concrete: Adding ۵۰ mm long polymer fibers to the concrete matrix increases tensile strength by up to ۳۰% and flexural strength by up to ۲۵%. Simulation tests show that this concrete experiences only a ۲% reduction in strength after ۲۰,۰۰۰ loading cycles (equivalent to ۱۰ years of rig operation). Optimized Recycled Concrete with Neural Networks: Using the backpropagation algorithm, a mix design was developed that replaces ۴۰% of natural aggregates with concrete waste. Results indicate that this concrete consumes ۱۵% less energy in production compared to conventional concrete, and its compressive strength improves by up to ۲۰% under freeze-thaw conditions. Integration of Technologies: Proposing the simultaneous use of macro-synthetic fibers in recycled concrete for joint projects (such as bridge foundations in cities near oil regions). Training a complex neural network to predict the behavior of the combined concrete under multiple stresses (mechanical load, corrosion, and freeze-thaw). Key Findings: Fiber-Reinforced Concrete, Recycled Concrete, Neural Network, Environmental Sustainability. Cost Reduction: Replacing ۵۰% of natural aggregates with concrete waste reduces raw material costs by up to ۲۵%. Using a neural network reduces the mix design optimization time from ۶ months to ۲ weeks. Improved Sustainability: Reduces the ۳۵% carbon footprint in the production cycle of combined concrete. Increases the service life of concrete structures from ۲۰ years to ۳۵ years in corrosive environments. Practical Applications: Construction of access roads to oil rigs with combined concrete: reducing costs and increasing resistance to crude oil. Use of recycled fiber-reinforced concrete in urban retaining walls: reducing water permeability and increasing earthquake resistance. Socio-Economic Impacts: Oil Industry: Reducing downtime in drilling operations due to the destruction of concrete structures, resulting in annual savings of approximately ۵۰۰ billion Tomans. Urban Development: Creating a concrete recycling cycle, generating employment in the waste management sector, and reducing ۲۰% of air pollution caused by cement production. Future Directions: Development of deep learning algorithms to predict concrete behavior at extremely high temperatures (up to ۲۰۰°C). Implementation of pilot projects in the cities of Bandar Abbas and Ahvaz for field evaluation. Investigating the possibility of using recycled fibers (such as PET fibers) to enhance durability. Final Conclusion: This study demonstrates that the integration of novel technologies in the field of concrete can not only bridge the gap between industry and the environment but also pave the way for the realization of smart urban development and sustainable oil industries.

کلیدواژه ها:

Fiber-Reinforced Concrete ، Recycled Concrete ، Neural Network ، Environmental Sustainability