To address the issues of long testing periods and small sample sizes while evaluating the service life of heavy-load self-lubricating liners, we propose a succinct method based on Monte Carlo simulation that is significantly fast and requires a small sample size. First, the support vector regression algorithm was applied to fit the degradation trajectories of the wear depth, and the first and second characteristic parameter vectors of the wear depth as well as the corresponding distribution models were obtained. Next, sample expansion was performed using Monte Carlo simulation and the inverse transform method. Finally, based on the failure criterion of the self-lubricating liner, the service lives and distribution models of the expanded samples were obtained; subsequently, the corresponding reliability life indices were provided. Our results indicate that when the expanded sample was large enough, the proposed prediction method exhibited a relatively high prediction accuracy. Therefore, these results provide theoretical support for shortening the testing cycle used to evaluate the service life of self-lubricating liners and for accelerating the research and development of self-lubricating spherical plain bearing products.