Enhancing the Adaptive Capability of Fuzzy Petri Net by an Improved Whale Optimization Algorithm

Fuzzy Petri Nets (FPNs) are an advanced topological model that extends traditional Petri nets (PNs) by integrating fuzzy theory. However, the generalization capability of FPN models is often limited due to their reliance on expert-driven parameter determination. This paper proposes an improved whale optimization algorithm (IWOA) for optimizing FPN models to address this challenge. The IWOA employs an adaptive weighting strategy, optimal search techniques, population grouping, and the Lévy flight strategy to dynamically adjust the search process, enhancing the WOA's effectiveness in handling complex problems and improving the balance between exploration and exploitation. The IWOA is tested on six classical benchmark functions in the experimental section and applied to the FPN model. The results demonstrate that the IWOA-FPN model exhibits strong generalization capabilities and superior convergence performance.