Optimization of intelligent anchorage management for ships based on OBS-MLP fusion algorithm

To address the low efficiency and high safety risks associated with multi-ship anchoring during offshore wind farm construction, an intelligent anchoring management method is proposed based on an optimal brain surgery-multi-layer perceptron (OBS-MLP) fusion algorithm.

Initially, a three-level optimization framework of feature decoupling-dynamic pruning-preference decision was constructed, integrating the advantages of decision trees and neural networks. This framework uses OBS pruning strategies to reduce model parameter redundancy, thus overcoming the curse of dimensionality faced by traditional algorithms in high-dimensional decision spaces. Subsequently, a multi-modal feature fusion mechanism was established for the hierarchical extraction and collaborative optimization of static environmental features and dynamic interaction features. Finally, a preference decision-making model with mixed-integer programming constraints was designed to quantify the economic and safety weights of different adjustment strategies.

Taking an offshore wind farm in Guangdong as an example, the average accuracy of the algorithm is 95.3%, which is 8.05% higher than that of the individual algorithm. The average response time is shortened to 0.9 seconds, a 30.77% reduction. The potential economic loss is reduced by about 240 000 yuan per year, thereby effectively reducing safety risks in ship anchoring operations.

The research provides an efficient solution to multi-ship anchoring collaborative optimization and promotes the digital transformation of maritime safety management.