Abstract
Broaching tool condition monitoring is the basis of intelligent manufacturing of high-end broaching equipment. There are still technical bottlenecks in tool wear recognition accuracy and response speed. Aiming at the characteristics of complex cutter tooth shape and variable spatial distribution of turbine disc fir-tree slot broaching tool, a method of wear state recognition for broaching tool based on maximum relevance and minimum redundancy and gray wolf optimization algorithm is proposed. In the process of broaching, the broach vibration signals are collected in real time. The signal characteristics in time domain, frequency domain and time-frequency domain are extracted by signal processing technology, and the support vector machine (SVM) recognition model of broach wear state is established. The maximum relevance and minimum redundancy (mRMR) method is used to reduce the dimension of data, grey wolf optimization algorithm (GWO) is used to optimize parameters to improve the recognition accuracy of SVM. The experimental results show that the model can accurately recognize the wear state of fir-tree slot broach at different stages. In addition, grey wolf optimization-support vector machine (GWO-SVM) model shows higher accu-racy in classification than particle swarm optimization based support vector machine (PSO-SVM) and genetic algorithm based support vector machine (GA-SVM) models. Compared with PSO-SVM and GA-SVM models, the computational time of GWO-SVM is reduced by 54.2 % and 60.5 % respectively.
Similar content being viewed by others
Abbreviations
- SVM :
-
Support vector machine
- mRMR :
-
Maximum relevance and minimum redundancy
- GWO :
-
Grey wolf optimization
- PSO :
-
Particle swarm optimization
- GA :
-
Genetic algorithm
- MCA :
-
Morphological component analysis
- PCA :
-
Principal component analysis
- LS :
-
Least squares
- RPT :
-
Rise-per-tooth
- RBF :
-
Radial basis function
- w :
-
Normal vector
- ξ i :
-
Slack variable
- C :
-
Penalty parameters
- x i :
-
i feature vector
- x j :
-
j feature vector
- y i :
-
Class label
- K(x j, x j):
-
Kernel function
- σ:
-
Kernel parameters
- X :
-
Random variables
- Y :
-
Random variables
- p(x) :
-
Probability density of x
- p(y) :
-
Probability density of y
- P(x, y) :
-
Joint probability density of x and y
- S :
-
Collection of data signal characteristics xi
- c :
-
Target categories
- D(S,c) :
-
Correlation between the feature set S and the target category c
- l(x i;c):
-
Mutual information between xi and c
- R(S) :
-
Redundancy of all features in the set S
- S m-1 :
-
Feature space
- t :
-
Number of iterations
- \(\mathop {{X_p}}\limits^ \rightharpoonup \) :
-
Prey position vector
- \({\vec X}\) :
-
Position vector of gray wolf
- \({\vec C}\) :
-
Coefficient vectors
- \(\overrightarrow A \) :
-
Coefficient vectors
- \({\vec a}\) :
-
Maximum number of iterations
- \({{\vec r}_1}\) :
-
Random number
- \({\overrightarrow X _\alpha }\) :
-
Current positions of α with strong recognition capability
- \({\overrightarrow X _\beta }\) :
-
Current positions of β with strong recognition capability
- \({\overrightarrow X _\delta }\) :
-
Current positions of δ with strong recognition capability
- ω:
-
Remaining wolves
- \({{\vec C}_1}\) :
-
Random disturbances of α
- \({{\vec C}_2}\) :
-
Random disturbances of β
- \({{\vec C}_3}\) :
-
Random disturbances of δ
- \({{\vec X}_1}\) :
-
Distance vector of grey wolves α between grey wolf ω
- \({{\vec X}_2}\) :
-
Distance vector of grey wolves β between grey wolf ω
- \({{\vec X}_3}\) :
-
Distance vector of grey wolves δ between grey wolf ω
- \({{\vec X}_{\left( {t + 1} \right)}}\) :
-
Final position of the ω gray wolf
- VB :
-
Average wear status
- \({\bar x}\) :
-
Mean value
- x rms :
-
Root mean square
- σ2 :
-
Variance
- x peak :
-
Peak difference
- x Kur :
-
Kurtosis
- CF :
-
Peak factor
- SF :
-
Pulse factor
- MF :
-
Margin factor
- FC :
-
Center of gravity
- FV :
-
Frequency variance
- MSF :
-
Mean square frequency
References
R. Madhavan, The 2016 airbus shopfloor challenge, IEEE Robotics and Automation Magazine, 23(3) (2016) 21–22.
K. Suhrutha and G. Srinivas, Recent developments of materials used in air breathing and advanced air breathing engines, IOP Conference Series Materials Science and Engineering, 872 (2020) 012082.
T. M. Pollock, Alloy design for aircraft engines, Nature Materials, 15(8) (2016) 809.
M. Seimann, B. X. Peng, F. Klocke and B. Döbbeler, Multi flank chip formation in fir-tree broaching inconel 718 with cemented carbide, Procedia Manufacturing, 26 (2018) 503–508.
S. Gierlings, D. Lung, D. Veselovac, F. Klocke and P. Vogtel, Broaching of inconel 718 with cemented carbide, Production Engineering, 7 (2013) 593–600.
J. Zhao, Y. C. Xiang and C. Fan, A new method for polishing the inner wall of a circular tube with a soft abrasive rotating jet, Powder Technology, 398 (2022) 117068.
L. H. Aiken, W. Sermeus, K. V. D. Heede, D. M. Sloane, R. Busse, M. McKee, L. Bruyneel, A. M. Rafferty, P. Griffiths, M. T. Moreno-Casbas, C. Tishelman, A. Scott, T. Brzoste, J. Kinnunen, R. Schwendimann, M. Heinen, D. Zikos, I. S. Sjetne, H. L. Smith and A. Kutney-Lee, Patient safety, satisfaction, and quality of hospital care: cross sectional surveys of nurses and patients in 12 countries in Europe and the United States, BMJ, 344 (7851) (2012).
D. A. Axinte and N. Gindy, Tool condition monitoring in broaching, Wear, 254(3) (2003) 370–382.
D. Axinte, F. Boud, J. Penny and N. Gindy, Broaching of Ti-6-4-Detection of workpiece surface anomalies on dovetail slots through process monitoring, CIRP Annals-Manufacturing Technology, 54(1) (2005) 87–90.
D. A. Axinte, D. R. Natarajan and N. Gindy, An approach to use an array of three acoustic emission sensors to locate uneven events in machining—part 1: method and validation, International Journal of Machine Tools and Manufacture, 45(14) (2005) 1605–1613.
D. A. Axinte, Approach into the use of probabilistic neural networks for automated classification of tool malfunctions in broaching, International Journal of Machine Tools and Manufacture, 46(12–13) (2006) 1445–1448.
D. F. Shi, D. A. Axinte and N. N. Gindy, Online machining process monitoring using wavelet transform and SPC, IEEE Instrumentation and Measurement Technology Conference (2006) 2081–2086.
D. Shi, D. A. Axinte and N. N. Gindy, Development of an online machining process monitoring system: a case study of the broaching process, International Journal of Advanced Manufacturing Technology, 34(1–2) (2007) 34–46.
J. Zhao, R. Wang, E. Y. Jiang and S. Ji, Research on a new method for optimizing surface roughness of cavitation abrasive flow polishing monocrystalline silicon, The International of Advanced Manufacturing Technology, 113(5–6) (2021) 1649–1661.
P. J. Bagga, M. A. Makhesana, H. D. Patel and K. M. Patel, Indirect method of tool wear measurement and prediction using ANN network in machining process, Materials Today: Proceedings, 44 (2021) 1549–1554.
J. Malhotra and J. Sunila, Fuzzy c-means clustering based colour image segmentation for tool wear monitoring in micro-milling, Precision Engineering, 72 (2021) 690–705.
K. P. Zhu and X. L. Yu, The monitoring of micro milling tool wear conditions by wear area estimation, Mechanical Systems and Signal Processing, 93 (2017) 80–91.
Y. Takaya, K. Maruno, M. Michihata and Y. Mizutani, Measurement of a tool wear profile using confocal fluorescence microscopy of the cutting fluid layer, CIRP Annals — Manufacturing Technology, 65(1) (2016) 467–470.
D. D. Kong, Y. J. Chen, N. Li and S. L. Tan, Tool wear monitoring based on kernel principal component analysis and v-support vector regression, International Journal of Advanced Manufacturing Technology, 89(1–4) (2017) 175–190.
M. He and D. He, A new hybrid deep signal processing approach for bearing fault diagnosis using vibration signals, Neurocomputing, 396 (2020) 542–555.
J. Xu, X. Liu, Q. H. Han and W. X. Wang, A particle swarm optimization-support vector machine hybrid system with acoustic emission on damage degree judgment of carbon fiber reinforced polymer cables, Structural Health Monitoring, 20(4) (2021) 1551–1562.
A. del Olmo, L. N. López de Lacalle, G. Martínez, D. Pissón, C. Pérez-Salinas, J. A. Ealo, L. Sastoque and M. H. Fernandes, Tool wear monitoring of high-speed broaching process with carbide tools to reduce production errors, Mechanical Systems and Signal Processing, 172 (2022) 109003.
D. F. Shi and N. N. Gindy, Tool wear predictive model based on least squares support vector machines, Mechanical Systems and Signal Processing, 21(4) (2007) 1799–1814.
S. X. Sun, X. F. Hu, W. L. Cai and J. Zhong, Tool breakage detection of milling cutter insert based on SVM, IFAC-PapersOnLine, 52(13) (2019) 1549–1554.
T. Han, L. W. Zhang, Z. J. Yin and A. C. C. Tan, Rolling bearing fault diagnosis with combined convolutional neural networks and support vector machine, Measurement, 177(1) (2021) 109022.
B. Kumar, A. Sinha, S. Chakrabarti and O. P. Vyas, A fast learning algorithm for one-class slab support vector machines, Knowledge-Based Systems, 228(7) (2021) 107267.
R. Duangsoithong and T. Windeatt, Relevant and redundant feature analysis with ensemble classification, Proceedings of the 7th International Conference on Advances in Pattern Recognition, 2009 (2009) 247–250.
D. Taniki, Computationally intelligent optimization of metal cutting regimes, Measurement, 152 (2019) 107358.
Y. N. Guo, Z. R. Zhang and F. Z. Tang, Feature selection with kernelized multi-class support vector machine, Pattern Recognition, 117(5324) (2021) 107988.
C. Cortes and V. Vapnik, Support-vector networks, Machine Learning, 20(3) (1995) 273–297.
H. C. Peng, F. H. Long and C. Ding, Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy, IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8) (2005) 1226–1238.
S. Mirjalili, S. M. Mirjalili and Lewis, Grey wolf optimizer, Advances in Engineering Software, 69(3) (2014) 46–61.
M. Moodi, M. Ghazvini and H. Moodi, A hybrid intelligent approach to detect android botnet using smart self-adaptive learning-based PSO-SVM, Knowledge-Based Systems, 222 (2021) 106988.
H. P. Yin and H. P. Ren, Direct symbol decoding using GA-SVM in chaotic baseband wireless communication system, Journal of the Franklin Institute, 358(12) (2021) 6348–6367.
R. Hassan, B. Cohanim and O. D. Weck, A comparison of particle swarm optimization and the genetic algorithm, Structural Dynamics and Materials Conference, 7(1) (2005) 1–7.
Acknowledgments
This work was supported by the Zhejiang Province Welfare Technology Applied Research Project with the Grant No. LGG21E050017, China.
Author information
Authors and Affiliations
Corresponding author
Additional information
Shunqi Zhang is a Full Professor at the School of Mechatronic Engineering and Automation (SMEA), Shanghai University, China. He obtained the doctoral degree with “outstanding” from RWTH Aachen University, Germany; obtained the Master and Bachelor degrees from Northwestern Polytechnical University respectively in 2010 and 2007. His research interest includes modeling of multi-physics coupled structures, active vibration control of smart structures, structural health monitoring for advanced machine tools.
Rights and permissions
About this article
Cite this article
Ying, S., Sun, Y., Fu, C. et al. Grey wolf optimization based support vector machine model for tool wear recognition in fir-tree slot broaching of aircraft turbine discs. J Mech Sci Technol 36, 6261–6273 (2022). https://doi.org/10.1007/s12206-022-1139-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-022-1139-x