A novel method based on Bayesian regularized artificial neural networks for measurement uncertainty evaluation

Moschos Papananias, Simon Fletcher, Andrew Longstaff, Azibananye Mengot

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Coordinate measuring machines (CMMs) are complex measuring systems that are widely used in manufacturing industry for form, size, position, and orientation assessment. In essence, these systems collect a set of individual data points that in practice is often a relatively small sample of an object. Their software then processes these points in order to produce a geometric result or to establish a local coordinate system from datum features. The subject of CMM evaluation is a broad and multifaceted one. This paper is concerned with the uncertainty in the coordinates of each point within the measuring volume of the CMM. Therefore, a novel method for measurement uncertainty evaluation using limited-size data sets is conceived and developed. The proposed method is based on a Bayesian regularized artificial neural network (BRANN) model consisting of three inputs and one output. The inputs are: The nominal coordinates; the ambient temperature; and the temperature of the workpiece. The output is the measured (actual) coordinates. An algorithm is developed and implemented before training the BRANN in order to map each nominal coordinate associated with the other inputs to the target coordinate. For validation the model is trained using a relatively small sample size of ten data sets to predict the variability of a larger sample size of ninety data sets. The calculated uncertainty is improved by more than 80% using the predicted variability compared to the uncertainty from the limited sample data set.

Original languageEnglish
Title of host publicationProceedings of the 16th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2016
Publishereuspen
Number of pages2
ISBN (Electronic)9780956679086
Publication statusPublished - 2016
Event16th International Conference of the European Society for Precision Engineering and Nanotechnology - East Midlands Conference Centre, Nottingham, United Kingdom
Duration: 30 May 20163 Jun 2016
Conference number: 16
https://www.euspen.eu/events/16th-international-conference-exhibition/ (Link to Conference Website)

Conference

Conference16th International Conference of the European Society for Precision Engineering and Nanotechnology
Abbreviated titleEUSPEN 2016
CountryUnited Kingdom
CityNottingham
Period30/05/163/06/16
OtherThis event offers the possibility to see latest advances in traditional precision engineering fields such as metrology, ultra precision machining, additive and replication processes, precision mechatronic systems & control and precision cutting processes.
Internet address

Fingerprint

Coordinate measuring machines
Neural networks
evaluation
Temperature
Uncertainty
output
Industry
ambient temperature
education
manufacturing
industries
computer programs

Cite this

Papananias, M., Fletcher, S., Longstaff, A., & Mengot, A. (2016). A novel method based on Bayesian regularized artificial neural networks for measurement uncertainty evaluation. In Proceedings of the 16th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2016 euspen.
Papananias, Moschos ; Fletcher, Simon ; Longstaff, Andrew ; Mengot, Azibananye. / A novel method based on Bayesian regularized artificial neural networks for measurement uncertainty evaluation. Proceedings of the 16th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2016. euspen, 2016.
@inproceedings{14d9fd8b3d7c41ddbc6405bde4b6018d,
title = "A novel method based on Bayesian regularized artificial neural networks for measurement uncertainty evaluation",
abstract = "Coordinate measuring machines (CMMs) are complex measuring systems that are widely used in manufacturing industry for form, size, position, and orientation assessment. In essence, these systems collect a set of individual data points that in practice is often a relatively small sample of an object. Their software then processes these points in order to produce a geometric result or to establish a local coordinate system from datum features. The subject of CMM evaluation is a broad and multifaceted one. This paper is concerned with the uncertainty in the coordinates of each point within the measuring volume of the CMM. Therefore, a novel method for measurement uncertainty evaluation using limited-size data sets is conceived and developed. The proposed method is based on a Bayesian regularized artificial neural network (BRANN) model consisting of three inputs and one output. The inputs are: The nominal coordinates; the ambient temperature; and the temperature of the workpiece. The output is the measured (actual) coordinates. An algorithm is developed and implemented before training the BRANN in order to map each nominal coordinate associated with the other inputs to the target coordinate. For validation the model is trained using a relatively small sample size of ten data sets to predict the variability of a larger sample size of ninety data sets. The calculated uncertainty is improved by more than 80{\%} using the predicted variability compared to the uncertainty from the limited sample data set.",
keywords = "Bayesian regularized artificial neural network (BRANN), Coordinate measuring machine (CMM), Uncertainty of measurement",
author = "Moschos Papananias and Simon Fletcher and Andrew Longstaff and Azibananye Mengot",
year = "2016",
language = "English",
booktitle = "Proceedings of the 16th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2016",
publisher = "euspen",

}

Papananias, M, Fletcher, S, Longstaff, A & Mengot, A 2016, A novel method based on Bayesian regularized artificial neural networks for measurement uncertainty evaluation. in Proceedings of the 16th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2016. euspen, 16th International Conference of the European Society for Precision Engineering and Nanotechnology, Nottingham, United Kingdom, 30/05/16.

A novel method based on Bayesian regularized artificial neural networks for measurement uncertainty evaluation. / Papananias, Moschos; Fletcher, Simon; Longstaff, Andrew; Mengot, Azibananye.

Proceedings of the 16th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2016. euspen, 2016.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A novel method based on Bayesian regularized artificial neural networks for measurement uncertainty evaluation

AU - Papananias, Moschos

AU - Fletcher, Simon

AU - Longstaff, Andrew

AU - Mengot, Azibananye

PY - 2016

Y1 - 2016

N2 - Coordinate measuring machines (CMMs) are complex measuring systems that are widely used in manufacturing industry for form, size, position, and orientation assessment. In essence, these systems collect a set of individual data points that in practice is often a relatively small sample of an object. Their software then processes these points in order to produce a geometric result or to establish a local coordinate system from datum features. The subject of CMM evaluation is a broad and multifaceted one. This paper is concerned with the uncertainty in the coordinates of each point within the measuring volume of the CMM. Therefore, a novel method for measurement uncertainty evaluation using limited-size data sets is conceived and developed. The proposed method is based on a Bayesian regularized artificial neural network (BRANN) model consisting of three inputs and one output. The inputs are: The nominal coordinates; the ambient temperature; and the temperature of the workpiece. The output is the measured (actual) coordinates. An algorithm is developed and implemented before training the BRANN in order to map each nominal coordinate associated with the other inputs to the target coordinate. For validation the model is trained using a relatively small sample size of ten data sets to predict the variability of a larger sample size of ninety data sets. The calculated uncertainty is improved by more than 80% using the predicted variability compared to the uncertainty from the limited sample data set.

AB - Coordinate measuring machines (CMMs) are complex measuring systems that are widely used in manufacturing industry for form, size, position, and orientation assessment. In essence, these systems collect a set of individual data points that in practice is often a relatively small sample of an object. Their software then processes these points in order to produce a geometric result or to establish a local coordinate system from datum features. The subject of CMM evaluation is a broad and multifaceted one. This paper is concerned with the uncertainty in the coordinates of each point within the measuring volume of the CMM. Therefore, a novel method for measurement uncertainty evaluation using limited-size data sets is conceived and developed. The proposed method is based on a Bayesian regularized artificial neural network (BRANN) model consisting of three inputs and one output. The inputs are: The nominal coordinates; the ambient temperature; and the temperature of the workpiece. The output is the measured (actual) coordinates. An algorithm is developed and implemented before training the BRANN in order to map each nominal coordinate associated with the other inputs to the target coordinate. For validation the model is trained using a relatively small sample size of ten data sets to predict the variability of a larger sample size of ninety data sets. The calculated uncertainty is improved by more than 80% using the predicted variability compared to the uncertainty from the limited sample data set.

KW - Bayesian regularized artificial neural network (BRANN)

KW - Coordinate measuring machine (CMM)

KW - Uncertainty of measurement

UR - http://www.scopus.com/inward/record.url?scp=84984636154&partnerID=8YFLogxK

UR - http://www.euspen.eu/events/16th-international-conference-exhibition/

M3 - Conference contribution

BT - Proceedings of the 16th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2016

PB - euspen

ER -

Papananias M, Fletcher S, Longstaff A, Mengot A. A novel method based on Bayesian regularized artificial neural networks for measurement uncertainty evaluation. In Proceedings of the 16th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2016. euspen. 2016