Research on fault diagnosis of ship hydraulic system based on particle swarm optimization probabilistic

The ship hydraulic system is a complex mechatronics system, and its motion process data is nonlinear, dynamic, and non-Gaussian. paper presents a fault diagnosis method for ship hydraulic systems that uses the fast computing speed and strong robustness of probabilistic neural network algorithm. The particle swarm optimization (PSO) algorithm is proposed to optimize the Spread parameter of the PNN model, which improves the recognition accuracy of the probabilistic neural network. A speed perturbation PSO algorithm is proposed to solve the problem of PSO being easily trapped in local optima, which improves the optimization effect. The model is tested using numerical methods to verify its accuracy and validity.