Premium
Automated AC Voltammetric Sensor for Early Fault Detection and Diagnosis in Monitoring of Electroplating Processes
Author(s) -
Jaworski Aleksander,
Wikiel Hanna,
Wikiel Kazimierz
Publication year - 2013
Publication title -
electroanalysis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.574
H-Index - 128
eISSN - 1521-4109
pISSN - 1040-0397
DOI - 10.1002/elan.201200380
Subject(s) - mahalanobis distance , computer science , electroplating , pattern recognition (psychology) , projection (relational algebra) , artificial intelligence , biological system , soft sensor , process (computing) , materials science , algorithm , nanotechnology , operating system , layer (electronics) , biology
An in situ sensor employing AC‐voltammetry techniques was designed to provide a response strongly affected by the presence of specific disturbances like foreign contaminants, accumulated degradation products, severely out‐of‐target concentrations of electroplating bath constituents and out‐of‐target physical conditions of the plating process (i.e. temperature). Soft Independent Modelling of Class Analogy (SIMCA) is a pattern recognition method which describes each class separately in eigenvector space. In this supervised classification technique the projected new measurements are evaluated to determine whether they belong to a certain class or not. An automated analytical system was developed capable of collecting on‐line AC voltammetric data and investigating similarities between measurements in proper conditions and measurements with upset behavior with known disturbances which can be utilized to recognize a likely pattern of behavior. The shape differences between deformed and reference set voltammograms are quantified by Mahalanobis Distance (MD)‐SIMCA. In addition to the numerical approach, a graphical projection is utilized to diagnose the root cause of the detected process disturbances.