Optimum research on the temperature of the ship stern-shaft mechanical seal end faces based on finite element coupled analysis

Abstract

Abstract Due to the complicated working conditions of the ship stern-shaft mechanical seals, it is very difficult to evaluate and optimize the temperature on the sealed end faces. In the paper, one FEA model of the small taper convergent stern-shaft mechanical seals was put forward, and the nonlinear end-face liquid film pressure distribution was derived from different end-face gaps based on the simplified Reynolds equation as the end-face input parameters in FEA model. To prove the correction of the FEA results, one experiment was designed and completed. At the same time, combined with a parametrically coupled FEA model and an orthogonal experimental design, one PSO-BP-GA method based on the combination of particle swarm optimization (PSO), BP neural network and genetic algorithm (GA) was proposed to optimize the temperature of the sealed end faces. The results show that aiming at the prediction accuracy of the temperature on the sealed end faces, the PSO-BP algorithm is higher than BP algorithm and GA-BP algorithm, which error interval is shortened about 40% and 29%, respectively. Subsequently, PSO-BP-GA algorithm is obviously better than BP-GA algorithm and GA-BP-GA algorithm, which validates its effectiveness and feasibility. It will help to lay a theoretical foundation for temperature evaluation on the sealed end faces.