Evaluation of Charpy-V transition curve fitting based on distribution-free statistical assessment

A non-parametric, distribution-free, statistical assessment of 5 large Charpy transition curve data sets is used for the optimum fitting equations for smaller data sets. The assessment makes use of a combination of rank probability and binomial probability analysis of the data. The original non-parametric assessment method is improved by combining upper and lower bound binomial estimates, thus removing a bias that exists in the original method. The non-parametric assessment is not suitable as a standard method because it requires too many data points to give a reliable result. It is, however, ideal as a research tool to examine transition curve shape and scatter. Based on the assessment several recommendations for transition curve fitting can be made.

Automated summary

This study utilizes a non-parametric, distribution-free statistical assessment method to analyze 5 large Charpy transition curve data sets and derive optimum fitting equations for smaller data sets. The method combines rank probability and binomial probability analysis to improve the original method and eliminate bias. However, it is not suitable as a standard method due to the requirement of a large number of data points. Nevertheless, it serves as an ideal research tool for examining the shape and scatter of transition curves. Based on the assessment, several recommendations for transition curve fitting can be made.