Comparative study of ANN and ANFIS predprediction models for thermal error compensation on CNC machine tools

A. Abdulshahed, A. Longstaff, S. Fletcher, A. Myers

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

8 Citations (Scopus)

Abstract

Thermal errors can have significant effects on CNC machine tool accuracy. The errors usually come from thermal deformations of the machine elements created by heat sources within the machine structure or from ambient change. The performance of a thermal error compensation system inherently depends on the accuracy and robustness of the thermal error model. In this paper, Adaptive Neuro Fuzzy Inference System (ANFIS), Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) techniques were employed to design four thermal prediction models: ANFIS by dividing the data space into rule patches (ANFIS-Scatter partition model); ANFIS by dividing the data space into rectangular sub-spaces (ANFIS-Grid partition model); ANN with a back-propagation algorithm (ANN-BP model) and ANN with a PSO algorithm (ANN-PSO model). Grey system theory was also used to obtain the influence ranking of the input sensors on the thermal drift of the machine structure. Four different models were designed, based on the higher-ranked sensors on thermal drift of the spindle. According to the results, the ANFIS models are superior in terms of the accuracy of their predictive ability; the results also show ANN-BP to have a relatively good level of accuracy. In all the models used in this study, the accuracy of the results produced by the ANFIS models was higher than that produced by the ANN models.

Original languageEnglish
Title of host publicationLaser Metrology and Machine Performance X
Subtitle of host publication10th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2013
EditorsLiam Blunt
Publishereuspen
Pages79-89
Number of pages11
ISBN (Print)9780956679017
Publication statusPublished - 1 Mar 2013
Event10th International Conference and Exhibition on Laser Metrology, Coordinate Measuring Machine and Machine Tool Performance - Buckinghamshire, United Kingdom
Duration: 20 Mar 201321 Mar 2013
Conference number: 10

Conference

Conference10th International Conference and Exhibition on Laser Metrology, Coordinate Measuring Machine and Machine Tool Performance
Abbreviated titleLAMDAMAP 2013
CountryUnited Kingdom
CityBuckinghamshire
Period20/03/1321/03/13

Fingerprint

machine tools
Error compensation
Fuzzy inference
inference
Machine tools
Neural networks
Particle swarm optimization (PSO)
optimization
partitions
Hot Temperature
spindles
ranking
Backpropagation algorithms
sensors
Sensors
System theory
heat sources
grids

Cite this

Abdulshahed, A., Longstaff, A., Fletcher, S., & Myers, A. (2013). Comparative study of ANN and ANFIS predprediction models for thermal error compensation on CNC machine tools. In L. Blunt (Ed.), Laser Metrology and Machine Performance X : 10th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2013 (pp. 79-89). euspen.
Abdulshahed, A. ; Longstaff, A. ; Fletcher, S. ; Myers, A. / Comparative study of ANN and ANFIS predprediction models for thermal error compensation on CNC machine tools. Laser Metrology and Machine Performance X : 10th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2013. editor / Liam Blunt. euspen, 2013. pp. 79-89
@inproceedings{70fd3ae26bff45e9a9d2473c47a9ef59,
title = "Comparative study of ANN and ANFIS predprediction models for thermal error compensation on CNC machine tools",
abstract = "Thermal errors can have significant effects on CNC machine tool accuracy. The errors usually come from thermal deformations of the machine elements created by heat sources within the machine structure or from ambient change. The performance of a thermal error compensation system inherently depends on the accuracy and robustness of the thermal error model. In this paper, Adaptive Neuro Fuzzy Inference System (ANFIS), Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) techniques were employed to design four thermal prediction models: ANFIS by dividing the data space into rule patches (ANFIS-Scatter partition model); ANFIS by dividing the data space into rectangular sub-spaces (ANFIS-Grid partition model); ANN with a back-propagation algorithm (ANN-BP model) and ANN with a PSO algorithm (ANN-PSO model). Grey system theory was also used to obtain the influence ranking of the input sensors on the thermal drift of the machine structure. Four different models were designed, based on the higher-ranked sensors on thermal drift of the spindle. According to the results, the ANFIS models are superior in terms of the accuracy of their predictive ability; the results also show ANN-BP to have a relatively good level of accuracy. In all the models used in this study, the accuracy of the results produced by the ANFIS models was higher than that produced by the ANN models.",
keywords = "machine tools, errors, thermal errors",
author = "A. Abdulshahed and A. Longstaff and S. Fletcher and A. Myers",
year = "2013",
month = "3",
day = "1",
language = "English",
isbn = "9780956679017",
pages = "79--89",
editor = "Liam Blunt",
booktitle = "Laser Metrology and Machine Performance X",
publisher = "euspen",

}

Abdulshahed, A, Longstaff, A, Fletcher, S & Myers, A 2013, Comparative study of ANN and ANFIS predprediction models for thermal error compensation on CNC machine tools. in L Blunt (ed.), Laser Metrology and Machine Performance X : 10th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2013. euspen, pp. 79-89, 10th International Conference and Exhibition on Laser Metrology, Coordinate Measuring Machine and Machine Tool Performance, Buckinghamshire, United Kingdom, 20/03/13.

Comparative study of ANN and ANFIS predprediction models for thermal error compensation on CNC machine tools. / Abdulshahed, A.; Longstaff, A.; Fletcher, S.; Myers, A.

Laser Metrology and Machine Performance X : 10th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2013. ed. / Liam Blunt. euspen, 2013. p. 79-89.

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

TY - GEN

T1 - Comparative study of ANN and ANFIS predprediction models for thermal error compensation on CNC machine tools

AU - Abdulshahed, A.

AU - Longstaff, A.

AU - Fletcher, S.

AU - Myers, A.

PY - 2013/3/1

Y1 - 2013/3/1

N2 - Thermal errors can have significant effects on CNC machine tool accuracy. The errors usually come from thermal deformations of the machine elements created by heat sources within the machine structure or from ambient change. The performance of a thermal error compensation system inherently depends on the accuracy and robustness of the thermal error model. In this paper, Adaptive Neuro Fuzzy Inference System (ANFIS), Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) techniques were employed to design four thermal prediction models: ANFIS by dividing the data space into rule patches (ANFIS-Scatter partition model); ANFIS by dividing the data space into rectangular sub-spaces (ANFIS-Grid partition model); ANN with a back-propagation algorithm (ANN-BP model) and ANN with a PSO algorithm (ANN-PSO model). Grey system theory was also used to obtain the influence ranking of the input sensors on the thermal drift of the machine structure. Four different models were designed, based on the higher-ranked sensors on thermal drift of the spindle. According to the results, the ANFIS models are superior in terms of the accuracy of their predictive ability; the results also show ANN-BP to have a relatively good level of accuracy. In all the models used in this study, the accuracy of the results produced by the ANFIS models was higher than that produced by the ANN models.

AB - Thermal errors can have significant effects on CNC machine tool accuracy. The errors usually come from thermal deformations of the machine elements created by heat sources within the machine structure or from ambient change. The performance of a thermal error compensation system inherently depends on the accuracy and robustness of the thermal error model. In this paper, Adaptive Neuro Fuzzy Inference System (ANFIS), Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) techniques were employed to design four thermal prediction models: ANFIS by dividing the data space into rule patches (ANFIS-Scatter partition model); ANFIS by dividing the data space into rectangular sub-spaces (ANFIS-Grid partition model); ANN with a back-propagation algorithm (ANN-BP model) and ANN with a PSO algorithm (ANN-PSO model). Grey system theory was also used to obtain the influence ranking of the input sensors on the thermal drift of the machine structure. Four different models were designed, based on the higher-ranked sensors on thermal drift of the spindle. According to the results, the ANFIS models are superior in terms of the accuracy of their predictive ability; the results also show ANN-BP to have a relatively good level of accuracy. In all the models used in this study, the accuracy of the results produced by the ANFIS models was higher than that produced by the ANN models.

KW - machine tools

KW - errors

KW - thermal errors

UR - http://www.scopus.com/inward/record.url?scp=84908287786&partnerID=8YFLogxK

UR - https://www.tib.eu/en/search/id/TIBKAT%3A770626580/Laser-metrology-and-machine-performance-X-10th/

M3 - Conference contribution

SN - 9780956679017

SP - 79

EP - 89

BT - Laser Metrology and Machine Performance X

A2 - Blunt, Liam

PB - euspen

ER -

Abdulshahed A, Longstaff A, Fletcher S, Myers A. Comparative study of ANN and ANFIS predprediction models for thermal error compensation on CNC machine tools. In Blunt L, editor, Laser Metrology and Machine Performance X : 10th International Conference and Exhibition on Laser Metrology, Machine Tool, CMM and Robotic Performance, LAMDAMAP 2013. euspen. 2013. p. 79-89