A promising approach using Fibonacci sequence-based optimization algorithms and advanced computing.

Area of Science:

• Engineering
• Computational Science

Background:

• Optimization Algorithms (OAs) are widely used but face challenges in real-world applications like large-scale structural health monitoring (SHM).
• High computational cost and accuracy limitations hinder the practical deployment of OAs for complex structures such as railway bridges.

Purpose of the Study:

• To investigate the feasibility of a novel Fibonacci Sequence (FS)-based Optimization Algorithm (OA) for SHM of large-scale railway bridges.
• To address the limitations of existing OAs by improving accuracy and reducing computational expense.

Main Methods:

• Developed a novel FS-based OA by integrating the golden ratio properties of FS to enhance the accuracy of the Salp Swarm Algorithm (SSA).
• Employed superscalar processors for parallel computation of OA iterations to reduce high computational costs.
• Utilized the vectorization technique to minimize data size.

Main Results:

• The proposed FS-based OA demonstrated improved accuracy in addressing SHM challenges.
• The integration of superscalar processors and vectorization significantly reduced the computational cost.
• The approach proved highly potential for practical SHM applications in large-scale structures.

Conclusions:

• The novel FS-based OA, combined with advanced computing techniques, offers a viable solution for accurate and efficient SHM of large-scale railway bridges.
• This research overcomes key barriers to OA implementation in real-world structural monitoring.