Failure-Aware Bidirectional Evolutionary Knowledge Assimilation with Dynamic Regulation for Adaptive Optimization

Efficient exploitation of evolutionary knowledge while preserving population diversity remains a central challenge in optimization. Existing knowledge-learning evolutionary algorithms primarily rely on successful experiences, overlooking structural information embedded in failed search attempts. This asymmetric learning limits adaptability and may cause premature convergence in high-dimensional landscapes. To address this issue, a failure-aware bidirectional evolutionary knowledge assimilation framework is developed within the honey badger optimization algorithm. Unsuccessful offspring are treated as negative knowledge carriers and transformed through symmetric adversarial reflection, enabling simultaneous extraction of positive and negative structural information. A time-dependent regulation mechanism dynamically adjusts knowledge assimilation intensity across evolutionary phases to balance exploration and exploitation. In addition, a continuous mutation spectrum transition strategy adaptively integrates Cauchy and Gaussian perturbations, facilitating smooth migration from global exploration to local refinement. Comprehensive experiments conducted on the CEC 2017 benchmark suite across 10, 30, and 50 dimensions validate the proposed framework, establishing a novel failure-aware bidirectional evolutionary learning paradigm for knowledge-driven optimization. The results demonstrate that our method achieves statistically significant and consistent performance improvements over classical baseline algorithms. Furthermore, its robustness and cross-domain adaptability are corroborated through successful application to a real-world constrained engineering problem: welded beam design.