Community Manager
The reliability of particular parts is related to cyclic loads of stress and is determined by the stress level. Fatigue modeling is relevant for a whole host of products using metal, including bridges, springs, turbine blades, airplane wings, tooling devices, and any product made with metals and other materials subjected to tension, compression, shear, bending, or torsion. The relationship between reliability and stress is analyzed by collecting fatigue test data and characterized by the so-called S-N curves.
In response to customer need, JMP 18 introduces Fatigue Model capabilities, which are based on a revolutionary approach to modeling fatigue data from research led by William Meeker. The research team included Luis Escobar, Francis Pascual, Yili Hong, Peng Liu, Wayne M. Falk, and Balajee Ananthasayanam. The team’s approach provides a relationship between life distribution and strength distribution, plus a way to model both distributions simultaneously.
This interactive approach, which is just one of the new features found in JMP 18, offers 24 different models, provides an interactive way for engineers to explore the data and to find plausible models, and supplies comprehensive ways to extract critical information.
I recently spoke with JMP Principal Research Statistician Developer Peng Liu. In addition to being part of the team that researched the new approach to fatigue modeling, he led the charge to implement it using JMP.
According to Peng, there are just a few key steps for using the new Fatigue Model capabilities:
- Choose one of six S-N curve types, along with one of four distributions, to assemble a model in four clicks.
- After fitting models easily, compare the different models graphically and numerically.
- Get detailed information for individual models, including:
- Parameter estimates and their confidence intervals.
- Model diagnostics.
- Distribution profilers for fatigue life and fatigue strength distributions.
- Quantile profilers for the two distributions.
- Custom estimations of probabilities and quantiles with both Wald and likelihood intervals.
Peng and JMP Senior Analytics Software Tester Rajneesh Rajneesh demonstrated and explained the new capabilities during a live webinar on March 14. If you missed the session, or attended and want to view it again, we captured their Developer Tutorial: Analyzing Fatigue Testing Data using JMP Fatigue Modeling video and Q&A.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.