In order to obtain comprehensive assessment of the factors influencing fatigue life and to further improve the accuracy of fatigue life prediction of welded joints, soft computing methods, including entropy-based neighborhood rough set reduction algorithm, the particle swarm optimization (PSO) algorithm and support vector regression machine (SVRM) are combined to construct a fatigue life prediction model of titanium alloy welded joints. By using an entropy-based neighborhood rough set reduction algorithm, the influencing factors of the fatigue life of titanium alloy welded joints such as joint type, plate thickness, etc. are analyzed and the reduction results are obtained. Fatigue characteristic domains are proposed and determined subsequently according to the reduction results. The PSO-SVRM model for fatigue life prediction of titanium alloy welded joints is established in the suggested fatigue characteristic domains. Experimental results show that by taking into account the impact of joint type, the PSO-SVRM model could better predict the fatigue life of titanium alloy welded joints. The PSO-SVRM model indicates the relationship between fatigue life and fatigue life influencing factors in multidimensional space compared with the conventional least-square S-N curve fitting method, it could predict the fatigue life of the titanium alloy welded joints more accurately thus helps to the reliability design of the structure.

An evaluation model of aluminum alloy welded joint low-cycle fatigue data based on information entropy is proposed. Through calculating and analyzing the information entropy of decision attributes, quantitative contribution of stress concentration, plate thickness, and loading mode to the fatigue destruction are researched. Results reveal that the total information entropy of the fatigue data based on nominal stress, structural stress and equivalent structural stress are, respectively, 0.9702, 0.8881, and 0.8294. There is consistency between the reducing trend of the weight-based information entropy and the smaller and smaller standard deviation of the S-N curves. In the structural stress based S-N curve, total stress concentration factor is crucial for the distribution of the fatigue data and the weight based information entropy of membrane stress concentration factor is 0.6754, which illustrates that stress concentration is a key issue of welded structure to which ought to be attached great importance. Subsequently, in the equivalent structural stress-based S-N curve, the weight based information entropy of stress ratio is 0.5759, which plays an important role in the distribution of fatigue data. With the importance level of the attributes on the S-N curves investigated, the correction of R in the equivalent structural stress based master S-N curve method should be carried out to make the welding fatigue prediction much more accurate.