首页|New Artificial Intelligence Study Findings Recently Were Reported by Researchers at Texas A&M University (Explainable Artificial Intelligence Predi ction of Defect Characterization In Composite Materials)
New Artificial Intelligence Study Findings Recently Were Reported by Researchers at Texas A&M University (Explainable Artificial Intelligence Predi ction of Defect Characterization In Composite Materials)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Artificial Intelligenc e is the subject of a report. According to news reporting originating from Colle ge Station, Texas, by NewsRx correspondents, research stated, "Nondestructive e valuation (NDE) techniques are integral across diverse applications for void det ection within composites. Infrared (IR) thermography (IRT) is a prevalent NDE te chnique that utilizes reverse heat transfer principles to infer defect character istics by analyzing temperature distribution." Financial support for this research came from Department of Aerospace Engineerin g at Texas A M University. Our news editors obtained a quote from the research from Texas A&M University, "Although the forward heat transfer problem is well-posed, its inver se counterpart lacks uniqueness, posing non-unique solutions. The present study performs simulations using finite element analysis (FEA) in defective (a penny-s haped defect) composites through which the heat transfer flux is modeled. A tota l of 2100 simulations with various defect positions and sizes (depth, size, and thickness) are executed, and the corresponding surface temperature vs. time and vs. distance diagrams are extracted. The FEA outputs provide ample input data fo r developing an explainable artificial intelligence (XAI) model to estimate the defect characteristics. A detailed feature engineering task is performed to sele ct the representative information from the diagrams. Explainable decision tree-b ased machine learning (ML) models with transparent decision paths based on deriv ed features are developed to predict the defect depth, size, and thickness. The ML models' results suggest superb accuracy (R2 R 2 = 0.92 to 0.99) across All th ree defect characteristics."
College StationTexasUnited StatesN orth and Central AmericaArtificial IntelligenceEmerging TechnologiesMachin e LearningTexas A&M University
NETL
NSTL
