Research on Power Load Prediction of Unmanned Boats Based on PSO-SVM

Unmanned boats, as surface unmanned platforms, play an important role in transportation, ocean surveying, and other aspects. On the one hand, it can transport goods for long-distance transportation, and on the other hand, it can carry various payloads for offshore, offshore and other sea area detection and environmental perception. The power distribution system of unmanned boats is the prerequisite and foundation for all activities. It is the energy source for electric propulsion and the heart of ship navigation, which is particularly important for unmanned boats. A reliable and safe unmanned power distribution system can ensure the safe navigation of unmanned boats and the reliable operation of equipment. Compared with shore power on land, the unmanned boat power distribution system has the characteristics of smaller power supply energy, complex working conditions, and more random load changes. Therefore, research on predicting the power load of unmanned boats can help strengthen the health management and monitoring of the unmanned boat power distribution system, A smart method based on the combination of PSO particle swarm optimization and SVM support vector machine is proposed to optimize the penalty coefficient C and kernel function parameters using particle swarm optimization algorithm γ, Using optimized optimal parameters for SVM support vector machine prediction to ensure the safe and reliable operation of the unmanned boat power distribution system.