Managing the uncertainty of conformity assessment in environmental testing by machine learning

•A machine learning approach is applied to thermal environmental testing.•The analysis of images of pin solder joints is compared with judgement of expert.•A third class of output: “ambiguous” is added to a binary good/damaged judgment.•The method strongly reduces the percentage of errors.•The perce...

Full description

Saved in:
Bibliographic Details
Published in:Measurement : journal of the International Measurement Confederation 2018-08, Vol.124, p.560-567
Main Authors: D'Emilia, Giulio, Di Gasbarro, David, Gaspari, Antonella, Natale, Emanuela
Format: Article
Language:English
Subjects:
Artificial intelligence
Confidence intervals
Cybernetics
Data processing
Electronic devices
Environmental testing
Fatigue
Machine learning
Measurement
Neural networks
Probability distribution
Solder joint
Thermal stress
Thermal testing
Uncertainty
Vibration
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:•A machine learning approach is applied to thermal environmental testing.•The analysis of images of pin solder joints is compared with judgement of expert.•A third class of output: “ambiguous” is added to a binary good/damaged judgment.•The method strongly reduces the percentage of errors.•The percentage of ambiguous cases is satisfactory. A machine learning approach is described, with reference to the conformity assessment of pin solder joints for electronic devices after tests based on cyclic thermal stresses. Metrological concepts, in particular expanded uncertainty, confidence level and conformity assessment, are used to reinterpret expert judgements, with the aim of transferring as much as possible the expert judgement know-how into a semi-automated evaluation process of X-ray images. This also allows us to reduce to an acceptable level the percentage of errors of the method, with respect to the identification of faulted specimens. A tailored procedure is set, which is able to reach a satisfactory level of correct acknowledgment of the status of pieces, giving also indication of cases where the level of confidence is unsatisfactory. The obtained results show that in this way the occurrence of mistakes strongly decreases. The paper also analyses the effect of algorithms and of the most relevant data processing settings on the ambiguity percentage.
ISSN:0263-2241
1873-412X
DOI:10.1016/j.measurement.2017.12.034