Bootstrap confidence limits for P-S-N curves

Since fatigue tests to provide information for fatigue life curve are often limited to small size sample, conventional P-S-N curves, i.e. survivability-stress-life curves, may be inclined to be non-conservative. At present, the confidence-survivability-stress-life (usually denoted as C-P-S-N) curves are popularly suggested to improve the believability of fatigue test estimation. A new method on the basis of Bootstrap technique is developed to determine the C-P-S-N curves under limited fatigue tests in the present study, and its implementation is constructed in detail. By use of the developed method, the C-P-S-N curves can be estimated at arbitrary confidence and survivability. Comparing with the conventional P-S-N curves, the developed method can give the more accurate and safer estimation by the constructed simple implementation. The analysis on the fatigue tests data of LY12CZ Aluminum alloy plates shows the rationality and feasibility of the developed method.