Multivariate Data Analytics in PV Manufacturing—Four Case Studies Using Manufacturing Datasets

Many industries are being revolutionized through the use of advanced analytical tools that generate insights from large sets of data. These tools are used as a part of a diversely described but analogous set of pursuits, such as "data science," "data mining," and "big data.&...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of photovoltaics 2018-01, Vol.8 (1), p.38-47
Main Authors: Evans, Rhett, Boreland, Matthew
Format: Article
Language:English
Subjects:
Analytical models
Big data
Covariance matrices
data mining
Data models
Manufacturing
Mathematical model
multivariate statistics
Numerical analysis
photovoltaic cells
process control
Software
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Many industries are being revolutionized through the use of advanced analytical tools that generate insights from large sets of data. These tools are used as a part of a diversely described but analogous set of pursuits, such as "data science," "data mining," and "big data." In manufacturing, they result in improved quality, improved cost of manufacturing, and more streamlined approaches. Many of these tools are applicable to PV manufacturing data and so present significant opportunities for the industry, but there are limited published studies and limited public domain knowledge of commercial activities in the area. This paper highlights these opportunities for PV manufacturing by describing four case studies applying different analytical approaches to sets of data from different manufacturing facilities. The analyses primarily provide insight into the source of variance in manufacturing, offering manufacturers a detailed and quantifiable way to measure and improve quality. These types of approaches will become more necessary to keep control of manufacturing facilities that continue to grow at high rates, and thus they offer a glimpse for the future operation and organization of large-scale PV manufacturing.
ISSN:2156-3381
2156-3403
DOI:10.1109/JPHOTOV.2017.2778571