International Journal of Web Applications Pit Pichappan 18 2 2026 https://doi.org/10.6025/ijwa/2026/18/2/66-93 https://www.dline.info/ijwa/fulltext/v18n2/ijwav18n2_2.pdf Industrial Internet of Things (IIoT) systems underpin modern smart manufacturing, yet their heterogeneous, interconnected architectures pose significant challenges for regression testing and software validation. This study proposes a requirement-aware intelligent regression test prioritization framework designed to enhance fault detection efficiency and testing scalability in IIoT environments. The framework integrates requirement traceability analysis, multi-factor prioritization scoring, and optimization-driven test selection to dynamically order regression test cases based on fault detection capability, execution time, requirement criticality, and interface complexity. Empirical evaluation using a GSM2017 Mobile IoT dataset comprising 51 requirements and 41 test cases demonstrates that the proposed Dynamic Prioritization strategy achieves superior performance across multiple metrics: Average Percentage of Fault Detection (APFD) of 0.92, runtime reduction of 44.14%, fault coverage of 96%, and requirement coverage retention of 98.04%. Statistical validation via Wilcoxon Signed-Rank and Friedman tests confirms the significance of observed improvements. Convergence analysis indicates that Genetic Algorithm and Simulated Annealing metaheuristics effectively balance exploration and exploitation in large-scale test suite optimization. Feature importance analysis reveals fault detection capability as the dominant prioritization factor, while Pareto optimization demonstrates achievable trade-offs between execution efficiency and verification completeness. Machine learning classification using XGBoost and Neural Networks further validates the framework’s capacity for autonomous, AI-driven test prioritization. Collectively, these findings establish a robust, scalable methodology for intelligent IIoT regression testing that supports requirement traceability, adaptive prioritization, and statistically verified performance gains, advancing the state of software validation in Industry 4.0 ecosystems.