Machine learning approach for fatigue life prediction of additive manufactured components
A fatigue life, additive manufacturing technology, applied in machine learning, nuclear methods, additive manufacturing, etc., can solve the problems of not describing different characteristics, difficult to develop, define and calibrate mathematical models, etc., to optimize product design and achieve good product quality. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0022] The invention starts with test data from experimental tests or numerical simulations provided by the user in the first block "calibration" (step 1a "experimental test data" and step 1b "numerical simulation data"). The test data from step 1a, step 1b is fed into machine learning (step 2 "training machine learning model"). In an advantageous embodiment, a Gaussian process regression with a squared exponential covariance function is used. Train the machine learning algorithm in step 2. In parallel, the end user defines the use case (second block "Use Case Definition"), defines its components in step 3 "Complex User Components", and defines the parameters corresponding to the different parameters in step 4 "User Definition of Zones and Associated Parameters" The different regions of (eg, sections machined for better surface roughness, sections containing increased porosity...).
[0023] The use case from the use case definition achieved through steps 3 and 4 is fed to a ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 

