Enhanced CNC Fault Prognostics with K-Means Clustering and Particle Swarm Optimization for Pattern Analysis and Reduction
DOI:
https://doi.org/10.21467/proceedings.7.6.15Keywords:
Predictive Maintenance, K-means clustering, particle swarm optimizationAbstract
CNC machines form a backbone to current production systems, but prediction of failure is challenging because of the complexity of defect patterns and high-dimensional data. For enhanced computing efficiency, clustering accuracy, and CNC system fault detection, this paper introduces a hybrid framework that incorporates PSO and K-Means Clustering. The proposed method aims to enhance predictive maintenance accuracy, reliability, and dimensionality reduction by optimizing cluster center initialization using PSO. For comparison with existing methods, performance metrics such as execution time, objective value, silhouette score, error rate, and clustering accuracy are utilized. With decreased computation time (12.6 s), the hybrid method outperformed existing methods with silhouette score of 75.0%, 6.9% error, and clustering accuracy of 93.1%. The results indicate improved clustering accuracy, computation, and fault analysis by a large margin. By ensuring stable CNC fault prognostics, the proposed method allows for reliable industrial operation and supports preventative maintenance schedules with minimized downtime.
References
[1] Sathish Kumar, S. Naveen, R. Vijayakumar, V. Suresh, A. R. Asary, S. Madhu, and K. Palani, “An intelligent fuzzy-particle swarm optimization supervisory-based control of robot manipulator for industrial welding applications,” Sci. Rep., vol. 13, no. 1, p. 8253, 2023.
[2] M. Soori, F. K. G. Jough, R. Dastres, and B. Arezoo, “Robotical automation in CNC machine tools: a review,” Acta Mech. Automatica, vol. 18, no. 3, 2024.
[3] Q. Li, H. Zheng, T. Cui, and Y. Zhang, “Identification and location method of strip ingot for autonomous robot system using kmeans clustering and color segmentation,” IET Control Theory Appl., vol. 17, no. 16, pp. 2124–2135, 2023.
[4] M. Makulavičius, S. Petkevičius, J. Rožėnė, A. Dzedzickis, and V. Bučinskas, “Industrial robots in mechanical machining: Perspectives and limitations,” Robotics, vol. 12, no. 6, p. 160, 2023.
[5] P. Aghelpour, R. Graf, and E. Tomaszewski, “Coupling ANFIS with ant colony optimization (ACO) algorithm for 1-, 2-, and 3-days ahead forecasting of daily streamflow, a case study in Poland,” Environ. Sci. Pollut. Res., vol. 30, no. 19, pp. 56440–56463, 2023.
[6] Y. C. Huang and C. C. Hou, “Using Feature Engineering and Principal Component Analysis for Monitoring Spindle Speed Change Based on Kullback–Leibler Divergence with a Gaussian Mixture Model,” Sensors, vol. 23, no. 13, p. 6174, 2023.
[7] A. Martins, B. Mateus, I. Fonseca, J. T. Farinha, J. Rodrigues, M. Mendes, and A. M. Cardoso, “Predicting the health status of a pulp press based on deep neural networks and hidden markov models,” Energies, vol. 16, no. 6, p. 2651, 2023.
[8] Y. Liang, Y. Wang, C. Gu, J. Tang, and X. Pang, “Fog computing-enabled adaptive prognosis of cutting tool remaining life through multi-source data,” J. Comput. Des. Eng., vol. 11, no. 6, pp. 180–192, 2024.
[9] K. Liang, W. Dai, T. Huang, and Z. Lu, “Tool condition monitoring in milling process based on Multi-Source Pattern Recognition Model,” J. Comput. Des. Eng., 2021.
[10] M. Shah, H. Borade, V. Sanghavi, A. Purohit, V. Wankhede, and V. Vakharia, “Enhancing tool wear prediction accuracy using Walsh–Hadamard transform, DCGAN and dragonfly algorithm-based feature selection,” Sensors, vol. 23, no. 8, p. 3833, 2023.
[11] T. Ademujimi and V. Prabhu, “Digital twin for training Bayesian networks for fault diagnostics of manufacturing systems,” Sensors, vol. 22, no. 4, p. 1430, 2022.
[12] V. Nasir and F. Sassani, “A review on deep learning in machining and tool monitoring: Methods, opportunities, and challenges,” Int. J. Adv. Manuf. Technol., vol. 115, no. 9, pp. 2683–2709, 2021.
[13] A. Ercetin, O. Der, F. Akkoyun, M. P. Gowdru Chandrashekarappa, R. Şener, M. Çalışan, and K. N. Bharath, “Review of Image Processing Methods for Surface and Tool Condition Assessments in Machining,” J. Manuf. Mater. Process., vol. 8, no. 6, p. 244, 2024.
[14] M. Züfle, F. Moog, V. Lesch, C. Krupitzer, and S. Kounev, “A machine learning-based workflow for automatic detection of anomalies in machine tools,” ISA Trans., vol. 125, pp. 445–458, 2022.
[15] M. Nacchia, F. Fruggiero, A. Lambiase, and K. Bruton, “A systematic mapping of the advancing use of machine learning techniques for predictive maintenance in the manufacturing sector,” Appl. Sci., vol. 11, no. 6, p. 2546, 2021.
[16] Z. Wu and J. Li, “A framework of dynamic data driven digital twin for complex engineering products: the example of aircraft engine health management,” Procedia Manuf., vol. 55, pp. 139–146, 2021.
[17] M. Elahi, S. O. Afolaranmi, J. L. M. Lastra, and J. A. P. Garcia, “Discover Artificial Intelligence,” 2023.
[18] F. Aggogeri, N. Pellegrini, and F. L. Tagliani, “Recent advances on machine learning applications in machining processes,” Appl. Sci., vol. 11, no. 18, p. 8764, 2021.
[19] G. Sa, Z. Jiang, J. Sun, C. Qiu, Z. Liu, and J. Tan, “Hierarchical explicit–implicit combined sensing-based real-time monitoring method for the service performance of complex equipment,” J. Intell. Manuf. Spec. Equip., vol. 5, no. 3, pp. 301–311, 2024.
[20] R. Gudivaka, “Smart comrade robot for elderly: Leveraging IBM Watson Health and Google Cloud AI for advanced health and emergency systems,” Int. J. Eng. Res. Sci. Technol., vol. 20, no. 3, pp. 334–352, 2024.
[21] K. R. Basani and B. R. Gudivaka, “Support vector machine with tunicate swarm optimization algorithm for emotion recognition in human-robot interaction,” IEEE Xplore, 2024.
[22] R. L. Gudivaka, “IoT-based weighted K-means clustering with decision tree for sedentary behavior analysis in smart healthcare industry,” 2024 Second International Conference on Data Science and Information System (ICDSIS), 2024.
[23] V. Kumaresan, B. R. Gudivaka, R. L. Gudivaka, M. Al-Farouni, and R. Palanivel, “Machine learning-based chi-square improved binary cuckoo search algorithm for condition monitoring system in IIoT,” Proc. 2024 Int. Conf. Data Sci. Netw. Secur., pp. 1–5, 2024.
[24] R. Palanivel, D. K. R. Basani, B. R. Gudivaka, M. H. Fallah, and N. Hindumathy, “Support vector machine with tunicate swarm optimization algorithm for emotion recognition in human-robot interaction,” Proc. 2024 Int. Conf. Intell. Algorithms Comput. Intell. Syst., pp. 1–4, 2024.
[25] S. R. Sitaraman, P. Alagarsundaram, K. Gattupalli, V. S. B. Harish, H. Gollavilli, and H. Nagarajan, “Advanced IoMT-enabled chronic kidney disease prediction leveraging robotic automation with autoencoder-LSTM and fuzzy cognitive maps,” Int. J. Mod. Electron. Commun. Eng., vol. 12, no. 3, 2024.
[26] K. Gattupalli and H. M. Khalid, “Increasing clustering efficiency with QRDSO and WAC-HACK: A hybrid optimization framework in software testing,” J. Inf. Technol. Digit. World, vol. 6, no. 4, pp. 333–346, 2024.
[27] DATASET LINK: https://github.com/mint-lab/awesome-robotics-datasets
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
