Effect of different environmental parameters on pitting behavior of AISI type 316L stainless steel: Experimental studies and neural network modeling

被引：79

作者：

Ramana, K. V. S. ^{[2
,3
]}

Anita, T. ^{[1
]}

Mandal, Sumantra ^{[1
]}

Kahappan, S. ^{[2
]}

Shaikh, H. ^{[1
]}

Sivaprasad, P. V. ^{[1
]}

Dayal, R. K. ^{[1
]}

Khatak, H. S. ^{[1
]}

机构：

[1] Indira Gandhi Ctr Atom Res, Met & Mat Grp, Kalpakkam 603102, Tamil Nadu, India

[2] Anna Univ, Ctr Environm Studies, Madras 600025, Tamil Nadu, India

[3] RMD Engn Coll, Madras 601206, Tamil Nadu, India

来源：

MATERIALS & DESIGN | 2009年 / 30卷 / 09期

关键词：

Austenitic stainless steel; Pitting corrosion; Artificial neural network; CORROSION BEHAVIOR; TEMPERATURE; DEFORMATION; EVALUATE;

D O I：

10.1016/j.matdes.2009.01.039

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

AISI type 316L stainless steel was subjected to electrochemical polarization tests in an aqueous environment of varying chloride ion concentration (17,500-70,000 ppm), pH (1.23-5.0) and temperature (298-333 K). Values of critical pitting potentials (E-pit) were determined from the polarization tests. Increasing concentration and temperature, and decreasing pH were found to decrease the E-pit. Eighty values of E-pit, at different chloride concentrations, pH and temperature were used to model the pitting corrosion behavior of type 316L stainless steel using the artificial neural network (ANN) approach. A good correlation between experimental and predicted data was obtained. The developed ANN model was employed to simulate the intricate inter-relationships between E-pit and various environmental parameters in AISI type 316L stainless steel. (C) 2009 Elsevier Ltd. All rights reserved.

引用

页码：3770 / 3775

页数：6

共 31 条

[1]

Abd El Meguid E. A., 1994, Materials Transactions, JIM, V35, P699

[2]

BIANCHI G, 1974, INT C LOC CORR, P399

[3]

BOGAERTS W, 1981, P 8 INT C MET CORR M, V1, P31

[4] Neural network methods for corrosion data reduction [J].

Cottis, RA ;

Li, Q ;

Owen, G ;

Gartland, SJ ;

Helliwell, IA ;

Turega, M .

MATERIALS & DESIGN, 1999, 20 (04) :169-178

[5] Modelling beta transus temperature of titanium alloys using artificial neural network [J].

Guo, Z ;

Malinov, S ;

Sha, W .

COMPUTATIONAL MATERIALS SCIENCE, 2005, 32 (01) :1-12

[6]

Haykin S., 1999, NEURAL NETWORKS COMP, DOI DOI 10.1017/S0269888998214044

[7]

Hoar T.P., 1965, Corrosion Science, V5, P279, DOI [10.1016/S0010-938X(65)90614-1, DOI 10.1016/S0010-938X(65)90614-1, 10.1016/S0010-938X, DOI 10.1016/S0010-938X]

[8] MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS [J].

HORNIK, K ;

STINCHCOMBE, M ;

WHITE, H .

NEURAL NETWORKS, 1989, 2 (05) :359-366

[9] Temperature dependence of pitting potentials for austenitic stainless steels above their critical pitting temperature [J].

Laycock, NJ ;

Newman, RC .

CORROSION SCIENCE, 1998, 40 (06) :887-902

[10] ENVIRONMENTAL FACTORS AFFECTING CRITICAL POTENTIAL FOR PITTING IN 18-8 STAINLESS STEEL [J].

LECKIE, HP ;

UHLIG, HH .

JOURNAL OF THE ELECTROCHEMICAL SOCIETY, 1966, 113 (12) :1262-&

← 1 2 3 4 →