Semi-Parametric Learning for Classification of Pitting Corrosion Detected by Acoustic Emission

Asa Prateepasen; Pakorn Kaewtrakulpong; Chalermkiat Jirarungsatean

doi:10.4028/www.scientific.net/KEM.321-323.549

Paper Titles

A Study on Material Degradation in Carbon Steel for Pressure Vessel at 179°C
p.532

Evaluation of the Ductile-Brittle Transition Behaviour of Aging Specimens by the Fracture Toughness Test
p.536

A Study on Estimation of the Pipe Fracture Characteristics
p.541

Identification of AE Source in Corrosion Process
p.545

Semi-Parametric Learning for Classification of Pitting Corrosion Detected by Acoustic Emission
p.549

Effect of Sulfuric Acid Concentration on Acoustic Emission Signals in Uniform-Corrosion
p.553

Development of a Novel Rod Compression Technique for Characterizing Local Surface Strength
p.557

Assessment of Mechanical Degradation in Pressure Vessel Steel by Morphological Analysis of Carbides
p.561

Creep Rupture Studies of Zirlo Tubing Using Ring Tensile Specimen
p.565

HomeKey Engineering MaterialsKey Engineering Materials Vols. 321-323Semi-Parametric Learning for Classification of...

Semi-Parametric Learning for Classification of Pitting Corrosion Detected by Acoustic Emission

Abstract:

This paper presents a Non-Destructive Testing (NDT) technique, Acoustic Emission (AE) to classify pitting corrosion severity in austenitic stainless steel 304 (SS304). The corrosion severity is graded roughly into five levels based on the depth of corrosion. A number of timedomain AE parameters were extracted and used as features in our classification methods. In this work, we present practical classification techniques based on Bayesian Statistical Decision Theory, namely Maximum A Posteriori (MAP) and Maximum Likelihood (ML) classifiers. Mixture of Gaussian distributions is used as the class-conditional probability density function for the classifiers. The mixture model has several appealing attributes such as the ability to model any probability density function (pdf) with any precision and the efficiency of parameter-estimation algorithm. However, the model still suffers from model-order-selection and initialization problems which greatly limit its applications. In this work, we introduced a semi-parametric scheme for learning the mixture model which can solve the mentioned difficulties. The method was compared with conventional Feed-Forward Neural Network (FFNN) and Probabilistic Neural Network (PNN) to evaluate its performance. We found that our proposed methods gave much lower classificationerror rate and also far smaller variance of the classifiers.