Application of multi sensor data fusion based on principal component analysis and artificial neural network for machine tool thermal monitoring

Akshay A. Potdar; Andrew P. Longstaff; Simon Fletcher; Naeem S. Mian

Application of multi sensor data fusion based on principal component analysis and artificial neural network for machine tool thermal monitoring

Akshay A. Potdar, Andrew P. Longstaff, Simon Fletcher, Naeem S. Mian

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Due to the various heat sources on a machine tool, there exists a complex temperature distribution across its structure. This causes an inherent thermal hysteresis which is undesirable as it affects the systematic tool -to-workpiece positioning capability. To monitor this, two physical quantities (temperature and strain) are measured at multiple locations. This article is concerned with the use of Principal Component Analysis (PCA) and Artificial Neural Networks (ANN) to fuse this potentially large amount of data from multiple sources. PCA reduces the dimensionality of the data and thus reduces training time for the ANN which is being used for thermal modelling. This paper shows the effect of different levels of data compression and the application of rate of change of sensor values to reduce the effect of system hysteresis. This methodology has been successfully applied to the ram of a 5-axis gantry machine with 90 % correlation to the measured displacement.

Original language	English
Title of host publication	Laser Metrology and Machine Performance XI - 11th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2015
Publisher	euspen
Pages	224-233
Number of pages	10
ISBN (Electronic)	9780956679055
Publication status	Published - 2015
Event	11th International Conference and Exhibition on Laser Metrology, Coordinate Measuring Machine and Machine Tool Performance - Huddersfield, United Kingdom Duration: 17 Mar 2015 → 18 Mar 2015 Conference number: 11

Conference

Conference	11th International Conference and Exhibition on Laser Metrology, Coordinate Measuring Machine and Machine Tool Performance
Abbreviated title	LAMDAMAP 2015
Country/Territory	United Kingdom
City	Huddersfield
Period	17/03/15 → 18/03/15

Access to Document

https://www.euspen.eu/knowledge-base/LAMP15123.pdfLicence: Unspecified

Cite this

Potdar, A. A., Longstaff, A. P., Fletcher, S., & Mian, N. S. (2015). Application of multi sensor data fusion based on principal component analysis and artificial neural network for machine tool thermal monitoring. In Laser Metrology and Machine Performance XI - 11th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2015 (pp. 224-233). euspen. https://www.euspen.eu/knowledge-base/LAMP15123.pdf

Potdar, Akshay A. ; Longstaff, Andrew P. ; Fletcher, Simon et al. / Application of multi sensor data fusion based on principal component analysis and artificial neural network for machine tool thermal monitoring. Laser Metrology and Machine Performance XI - 11th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2015. euspen, 2015. pp. 224-233

@inproceedings{437a364608ca401996a60c477280e398,

title = "Application of multi sensor data fusion based on principal component analysis and artificial neural network for machine tool thermal monitoring",

abstract = "Due to the various heat sources on a machine tool, there exists a complex temperature distribution across its structure. This causes an inherent thermal hysteresis which is undesirable as it affects the systematic tool -to-workpiece positioning capability. To monitor this, two physical quantities (temperature and strain) are measured at multiple locations. This article is concerned with the use of Principal Component Analysis (PCA) and Artificial Neural Networks (ANN) to fuse this potentially large amount of data from multiple sources. PCA reduces the dimensionality of the data and thus reduces training time for the ANN which is being used for thermal modelling. This paper shows the effect of different levels of data compression and the application of rate of change of sensor values to reduce the effect of system hysteresis. This methodology has been successfully applied to the ram of a 5-axis gantry machine with 90 % correlation to the measured displacement.",

keywords = "Complex networks, Coordinate measuring machines, Data compression, Data fusion, Data handling, Data reduction, Hysteresis, Machine tools, Neural networks, Sensor data fusion, Units of measurement",

author = "Potdar, {Akshay A.} and Longstaff, {Andrew P.} and Simon Fletcher and Mian, {Naeem S.}",

year = "2015",

language = "English",

pages = "224--233",

booktitle = "Laser Metrology and Machine Performance XI - 11th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2015",

publisher = "euspen",

address = "United Kingdom",

note = "11th International Conference and Exhibition on Laser Metrology, Coordinate Measuring Machine and Machine Tool Performance, LAMDAMAP 2015 ; Conference date: 17-03-2015 Through 18-03-2015",

}

Potdar, AA, Longstaff, AP , Fletcher, S & Mian, NS 2015, Application of multi sensor data fusion based on principal component analysis and artificial neural network for machine tool thermal monitoring. in Laser Metrology and Machine Performance XI - 11th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2015. euspen, pp. 224-233, 11th International Conference and Exhibition on Laser Metrology, Coordinate Measuring Machine and Machine Tool Performance, Huddersfield, United Kingdom, 17/03/15. <https://www.euspen.eu/knowledge-base/LAMP15123.pdf>

Application of multi sensor data fusion based on principal component analysis and artificial neural network for machine tool thermal monitoring. / Potdar, Akshay A.; Longstaff, Andrew P.; Fletcher, Simon et al.

Laser Metrology and Machine Performance XI - 11th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2015. euspen, 2015. p. 224-233.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Application of multi sensor data fusion based on principal component analysis and artificial neural network for machine tool thermal monitoring

AU - Potdar, Akshay A.

AU - Longstaff, Andrew P.

AU - Fletcher, Simon

AU - Mian, Naeem S.

N1 - Conference code: 11

PY - 2015

Y1 - 2015

N2 - Due to the various heat sources on a machine tool, there exists a complex temperature distribution across its structure. This causes an inherent thermal hysteresis which is undesirable as it affects the systematic tool -to-workpiece positioning capability. To monitor this, two physical quantities (temperature and strain) are measured at multiple locations. This article is concerned with the use of Principal Component Analysis (PCA) and Artificial Neural Networks (ANN) to fuse this potentially large amount of data from multiple sources. PCA reduces the dimensionality of the data and thus reduces training time for the ANN which is being used for thermal modelling. This paper shows the effect of different levels of data compression and the application of rate of change of sensor values to reduce the effect of system hysteresis. This methodology has been successfully applied to the ram of a 5-axis gantry machine with 90 % correlation to the measured displacement.

AB - Due to the various heat sources on a machine tool, there exists a complex temperature distribution across its structure. This causes an inherent thermal hysteresis which is undesirable as it affects the systematic tool -to-workpiece positioning capability. To monitor this, two physical quantities (temperature and strain) are measured at multiple locations. This article is concerned with the use of Principal Component Analysis (PCA) and Artificial Neural Networks (ANN) to fuse this potentially large amount of data from multiple sources. PCA reduces the dimensionality of the data and thus reduces training time for the ANN which is being used for thermal modelling. This paper shows the effect of different levels of data compression and the application of rate of change of sensor values to reduce the effect of system hysteresis. This methodology has been successfully applied to the ram of a 5-axis gantry machine with 90 % correlation to the measured displacement.

KW - Complex networks

KW - Coordinate measuring machines

KW - Data compression

KW - Data fusion

KW - Data handling

KW - Data reduction

KW - Hysteresis

KW - Machine tools

KW - Neural networks

KW - Sensor data fusion

KW - Units of measurement

UR - http://www.scopus.com/inward/record.url?scp=84947094008&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84947094008

SP - 224

EP - 233

BT - Laser Metrology and Machine Performance XI - 11th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2015

PB - euspen

T2 - 11th International Conference and Exhibition on Laser Metrology, Coordinate Measuring Machine and Machine Tool Performance

Y2 - 17 March 2015 through 18 March 2015

ER -

Potdar AA, Longstaff AP , Fletcher S , Mian NS. Application of multi sensor data fusion based on principal component analysis and artificial neural network for machine tool thermal monitoring. In Laser Metrology and Machine Performance XI - 11th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2015. euspen. 2015. p. 224-233

Application of multi sensor data fusion based on principal component analysis and artificial neural network for machine tool thermal monitoring

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Naeem Mian

Cite this

Application of multi sensor data fusion based on principal component analysis and artificial neural network for machine tool thermal monitoring

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Profiles

Naeem Mian

Cite this