research-article

Feature selection using non-binary decision trees applied to condition monitoring

Authors:

V. PereiraAuthors Info & Claims

2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)

Pages 1 - 7

https://doi.org/10.1109/ETFA.2017.8247642

Published: 12 September 2017 Publication History

Abstract

Process monitoring is a key aspect of industrial automation nowadays and paves the way towards unmanned machine operation. Machine learning has been favoured in condition monitoring since it provides the ability to model even the most complex processes. This paper presents an approach concerning feature selection and process monitoring using decision trees with continuous variables. Through the use of time as well as other commonly used features condition monitoring of the turning process is evaluated. Results demonstrate the applicability of decision trees to multi-sensor process monitoring with underlying continuous variables. This approach revealed that decision trees can be applied for feature selection purposes in a simple and transparent fashion even in the presence of noisy data.

References

[1]

N. Ambhore, D. Kamble, S. Chinchanikar, and V. Wayal, “Tool condition monitoring system: A review,” Mater. Today Proc., vol. 2, no. 4-5, pp. 3419–3428, 2015.

[2]

A. Siddhpura and R. Paurobally, “A review of flank wear prediction methods for tool condition monitoring in a turning process,” Int. J. Adv. Manuf. Technol., vol. 65, no. 1-4, pp. 371–393, 2013.

[3]

D. Dimla and P. Lister, “On-line metal cutting tool condition monitoring,” Int. J. Mach. Tools Manuf., vol. 40, no. 5, pp. 769–781, 2000.

[4]

R. G. Silva, R. L. Reuben, K. J. Baker, and S. J. Wilcox, “Tool wear monitoring of turning operations by neural network and expert system classification of a feature set generated from multiple sensors,” Mech. Syst. Signal Process., vol. 12, no. 2, pp. 319–332, 1998.

[5]

M. Compare, F. Martini, and E. Zio, “Genetic algorithms forcondition-based maintenance optimization under uncertainty,” Eur. J. Oper. Res., vol. 244, no. 2, pp. 611–623, 2015.

[6]

M. Yuwono, Y. Guo, J. Wall, J. Li, S. West, G. Platt, and S. W. Su, “Unsupervised feature selection using swarm intelligence and consensus clustering for automatic fault detection and diagnosis in Heating Ventilation and Air Conditioning systems,” Appl. Soft Comput. J., vol. 34, pp. 402–425, 2015.

Digital Library

[7]

T. Segreto, A. Simeone, and R. Teti, “Multiple sensor monitoring in nickel alloy turning for tool wear assessment via sensor fusion,” Procedia CIRP, vol. 12, no. Fig 2, pp. 85–90, 2013.

[8]

M. S. H. Bhuiyan, I. a. Choudhury, and M. Dahari, “Monitoring the tool wear, surface roughness and chip formation occurrences using multiple sensors in turning,” J. Manuf. Syst., vol. 33, no. 4, pp. 476–487, 2014.

[9]

B. S. Prasad, K. A. Prabha, and P. V. S. G. Kumar, “Condition monitoring of turning process using infrared thermography technique-An experimental approach,” Infrared Phys. Technol., vol. 81, pp. 137–147, 2017.

[10]

G. Wang, Z. Guo, and Y. Yang, “Force sensor based online tool wear monitoring using distributed Gaussian ARTMAP network,” Sensors Actuators, A Phys., vol. 192, pp. 111–118, 2013.

[11]

J. a. Duro, J. a. Padget, C. R. Bowen, H. A. Kim, and A. Nassehi, “Multi-sensor data fusion framework for CNC machining monitoring,” Mech. Syst. Signal Process., vol. 66-67, pp. 505–520, 2016.

[12]

M. a. Shahin, “State-of-the-art review of some artificial intelligence applications in pile foundations,” Geosci. Front., pp. 1–12, 2014.

[13]

D. Pérez-Canales, J. Álvarez-Ramírez, J. C. Jáuregui-Correa, L. Vela-Martínez, and G. Herrera-Ruiz, “Identification of dynamic instabilities in machining process using the approximate entropy method,” Int. J. Mach. Tools Manuf., vol. 51, no. 6, pp. 556–564, 2011.

[14]

M. Gerdes, “Decision trees and genetic algorithms for condition monitoring forecasting of aircraft air conditioning,” Expert Syst. Appl., vol. 40, no. 12, pp. 5021–5026, 2013.

Digital Library

[15]

H. K. Sok, M. P. L. Ooi, Y. C. Kuang, and S. Demidenko, “Multivariate alternating decision trees,” Pattern Recognit., vol. 50, pp. 195–209, 2016.

Digital Library

[16]

X. Wang, X. Liu, W. Pedrycz, and L. Zhang, “Fuzzy rule based decision trees,” Pattern Recognit., vol. 48, no. 1, pp. 50–59, 2015.

Digital Library

[17]

J. R. Quinlan, “Induction of Decision Trees,” Mach. Learn., vol. 1, no. 1, pp. 81–106, 1986.

Digital Library

[18]

O. F. J. Martínez-Carranza, “Using C4. 5 as Variable Selection Criterion in Classification Tasks,” in Proceedings of the 9th IASTED Internacional Conference on Artificial Intelligence and Soft Computing ASC, 2005, pp. 171–176.

[19]

S. Gowid, R. Dixon, and S. Ghani, “Performance Comparison Between Fast Fourier Transform-Based Segmentation, Feature Selection, and Fault Identification Algorithm and Neural Network for the Condition Monitoring of Centrifugal Equipment,” J. Dyn. Syst. Meas. Control, vol. 139, no. 6, p. 61013, 2017.

[20]

Z. Hu, Y. Bao, T. Xiong, and R. Chiong, “Hybrid filter-wrapper feature selection for short-term load forecasting,” Eng. Appl. Artif. Intell., vol. 40, pp. 17–27, 2015.

Digital Library

[21]

Y. Liang, M. Zhang, and W. N. Browne, “Image feature selection using genetic programming for figure-ground segmentation,” Eng. Appl. Artif. Intell., vol. 62, no. April, pp. 96–108, 2017.

Digital Library

[22]

C. Shao, K. Paynabar, T. H. Kim, J. Jin, S. J. Hu, J. P. Spicer, H. Wang, and J. a. Abell, “Feature selection for manufacturing process monitoring using cross-validation,” J. Manuf. Syst., vol. 32, no. 4, pp. 550–555, 2013.

[23]

H. Alkhadafe, A. Al-Habaibeh, and A. Lotfi, “Condition monitoringof helical gears using automated selection of features and sensors,” Meas. J. Int. Meas. Confed., vol. 93, pp. 164–177, 2016.

[24]

D. E. Dimla Snr. D. E., “Sensor signals for tool-wear monitoring in metal cutting operations-a review of methods,” Int. J. Mach. Tools Manuf., vol. 40, no. 8, pp. 1073–1098, 2000.

[25]

F. Girardin, D. Rémond, and J. F. Rigal, “Tool wear detection in milling-An original approach with a non-dedicated sensor,” Mech. Syst. Signal Process., vol. 24, no. 6, pp. 1907–1920, 2010.

[26]

C. L. Yen, M. C. Lu, and J. L. Chen, “Applying the self-organization feature map (SOM) algorithm to AE-based tool wearmonitoring in micro-cutting,” Mech. Syst. Signal Process., vol. 34, no. 1-2, pp. 353–366, 2013.

[27]

R. Silva, R., Wilcox, S. and Reuben, “Development of a system for monitoring tool wear using artificial intelligence techniques,” Proc. Inst. Mech. Eng. Part B J. Eng. Manuf., vol. 220, no. B8, p. 1333–1346., 2006.

[28]

R. J. Kuo, “Multi-sensor integration for on-line tool wear estimation through artificial neural networks and fuzzy neural network,” Eng. Appl. Artif. In tell., vol. 13, no. 3, pp. 249–261, 2000.

[29]

ISO 3685. International Organization for Standardization, 1993.

Cited By

Friesel DSpinczyk OCrnkovic I(2022)Black-box models for non-functional properties of AI software systemsProceedings of the 1st International Conference on AI Engineering: Software Engineering for AI10.1145/3522664.3528602(170-180)Online publication date: 16-May-2022
https://dl.acm.org/doi/10.1145/3522664.3528602

Index Terms

Feature selection using non-binary decision trees applied to condition monitoring
1. Applied computing
  1. Operations research
2. Computing methodologies
  1. Artificial intelligence
    1. Search methodologies
  2. Machine learning
    1. Learning paradigms
      1. Supervised learning
    2. Machine learning approaches
      1. Classification and regression trees

Index terms have been assigned to the content through auto-classification.

Recommendations

Split Criterions for Variable Selection Using Decision Trees
ECSQARU '07: Proceedings of the 9th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty

In the field of attribute mining, several feature selection methods have recently appeared indicating that the use of sets of decision trees learnt from a data set can be an useful tool for selecting relevant and informative variables regarding to a ...
Effective hybrid feature subset selection for multilevel datasets using decision tree classifiers

Feature selection is one of the most significant procedures in machine learning algorithms. It is particularly to improve the performance and prediction accuracy for complex data classification. This paper discusses a hybrid feature selection technique ...
Feature selection using decision trees in the problem of JSM classification

A method of feature selection is considered for training a classification algorithm based on the JSM method. The method is based on the use of decision trees. It includes construction of a maximal tree using the C4.5 algorithm and the preparation of a ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)

Sep 2017

1377 pages

Copyright © 2017.

Publisher

IEEE Press

Publication History

Published: 12 September 2017

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 02 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Friesel DSpinczyk OCrnkovic I(2022)Black-box models for non-functional properties of AI software systemsProceedings of the 1st International Conference on AI Engineering: Software Engineering for AI10.1145/3522664.3528602(170-180)Online publication date: 16-May-2022
https://dl.acm.org/doi/10.1145/3522664.3528602

View Options

View options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents