Analysis of electrochemical noise data by use of recurrence quantification analysis and machine learning methods

2017 ◽  
Vol 256 ◽  
pp. 337-347 ◽  
Author(s):  
Y. Hou ◽  
C. Aldrich ◽  
K. Lepkova ◽  
L.L. Machuca ◽  
B. Kinsella
Keyword(s):  
Machine Learning ◽  
Electrochemical Noise ◽  
Recurrence Quantification Analysis ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Recurrence Quantification ◽  
Noise Data ◽  
Quantification Analysis

RECURRENCE QUANTIFICATION ANALYSIS OF ELECTROCHEMICAL NOISE DATA DURING PIT DEVELOPMENT

2007 ◽  
Vol 17 (10) ◽  
pp. 3725-3728 ◽  
Author(s):  
LUIS SANTOS MONTALBÁN ◽  
PÄIVI HENTTU ◽  
ROBERT PICHÉ
Keyword(s):  
Time Series ◽  
Pitting Corrosion ◽  
Electrochemical Noise ◽  
Recurrence Quantification Analysis ◽  
Corrosion Process ◽  
Current Time ◽  
Recurrence Quantification ◽  
Noise Data ◽  
Quantification Analysis ◽  
Aisi 316

Electrochemical noise (EN) data is commonly used to monitor corrosion of metals in various environments. In this work we use recurrence quantification analysis (RQA) to study EN time series of stainless steel AISI 316 samples immersed in a mildly corrosive electrolyte. It is found that RQA of current and potential time series reveal different information: current time series provides detailed information on the kinetics of the pitting corrosion process, while the potential time series identifies the transitions from one thermodynamic state to another in the pitting corrosion process.

Sign in / Sign up

Export Citation Format

Share Document