RIMNI SPECIAL ISSUE - Hybrid Intelligence Models and Numerical Techniques in Computational Engineering: Trends and Applications

Deadline Date: 31 March 2026

The increasing complexity of engineering systems in the modern digital age requires advanced approaches that combine the strengths of human reasoning and artificial intelligence (AI). Hybrid Intelligence, a multidisciplinary field that merges human cognitive abilities with AI-based computational systems, is emerging as a key factor in enhancing performance, adaptability, and decision-making in engineering design and analysis. This convergence is changing how numerical methods are developed and used in computational engineering. Numerical techniques are still essential for solving many engineering problems, such as structural mechanics, thermal analysis, fluid dynamics, materials simulation, and control system design. However, traditional methods often face challenges in scalability, real-time responsiveness, and managing uncertain or incomplete data. By integrating hybrid intelligence into these frameworks, researchers and engineers can overcome these challenges, resulting in models that are more robust, adaptable, and context-aware.

In hybrid intelligent systems, AI components like neural networks, fuzzy inference systems, genetic algorithms, and reinforcement learning are integrated into the computational pipeline. These systems not only automate routine simulations but also assist human experts by providing predictive analytics, optimizing computational processes, and adapting to real-time constraints. This human-in-the-loop collaboration creates systems that evolve with expert feedback, improving learning efficiency and interpretability two key challenges in AI-based engineering applications. Additionally, hybrid intelligence supports data-driven modeling approaches that complement traditional numerical simulations. Engineering fields increasingly depend on large amounts of data generated by sensors, digital twins, and simulation platforms. Combining AI models that learn from this data with domain-specific numerical solvers results in systems capable of high-fidelity predictions, uncertainty quantification, and dynamic model adjustments, even when faced with changing boundary conditions or nonlinear behavior.

This special issue aims to gather original research contributions, review articles, and case studies that explore recent advances in hybrid intelligence methods combined with numerical techniques in engineering. The focus is on showcasing new computational methods, theoretical innovations, software tools, and practical applications where hybrid models improve accuracy, speed, or efficiency in engineering simulations and design processes. Submissions are welcomed that demonstrate applications across various engineering fields, including but not limited to civil, mechanical, aerospace, electrical, materials, and computational engineering. Contributions providing experimental validation, algorithmic benchmarking, or interdisciplinary insights between numerical mathematics and AI are especially encouraged.

Suggested topics include, but are not limited to, the following:

Hybrid intelligence-based numerical models for engineering applications

Human-in-the-loop computational frameworks for design and optimization

Soft computing and machine learning techniques in finite element analysis

AI-enhanced numerical simulations in mechanical, civil, or structural engineering

Intelligent decision-support systems in complex engineering environments

Hybrid intelligent systems for multi-physics and multi-scale modeling

Evolutionary algorithms and hybrid intelligence in structural optimization

Data-driven modeling and hybrid prediction systems in engineering design

Integration of symbolic and connectionist approaches in numerical computation

Uncertainty quantification and hybrid reasoning in engineering simulations

Adaptive mesh refinement and hybrid learning-based computational models