Fuzzy Logic-Enhanced Expert System for Real Time Anomaly Detection in CNC Machines

Fuzzy Logic-Enhanced Expert System for Real Time Anomaly Detection in CNC Machines Atulya Gupta Department of Computer Science and Engineering, SRM Institute of Science and Technology, Delhi-NCR Campus, Ghaziabad, Uttar Pradesh, India. Josphin Mary J Department of Computer Science and Applications, Faculty of Science and Humanities, SRM Institute of Science and Technology, Ramapuram. Chennai, Tamil Nadu, India. Nandhini I Department of Information Technology, V.S.B. Engineering College, Karur, Tamil Nadu, India. Thivya Lakshmi R T Department of Computer Science and Engineering (Artificial Intelligence and Machine Learning), Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology (Deemed to be University), Avadi, Chennai, Tamil Nadu, India. Santhi M V B T Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, India. Pari R Department of Computer Science and Engineering, VELS Institute of Science, Technology and Advanced Studies, Chennai, Tamil Nadu, India.

Computer Numerical Control (CNC) machines play a pivotal role in modern precision manufacturing, where real-time monitoring is essential to prevent catastrophic failures and minimize downtime. This study proposes a Fuzzy Logic-Enhanced Expert System (FLEES) for real-time anomaly detection in CNC machines, leveraging linguistic rule inference fused with physical constraints and data-driven optimization. The system processes 14 distinct sensory inputs, including spindle vibration, cutting torque, thermal gradients, and acoustic emissions, gathered from 120 hours of high-frequency CNC machine operation under varying load conditions. Fuzzification maps raw sensor signals to 42 linguistic variables using Gaussian and trapezoidal membership functions. A total of 96 fuzzy rules were formulated based on expert knowledge and refined via Particle Swarm Optimization (PSO) guided by energy consistency and classification loss minimization. Experiments conducted on a benchmark CNC dataset show that FLEES achieves 96.7% anomaly classification accuracy, with 95.3% sensitivity and 97.9% specificity, outperforming existing methods, including SVM (91.2%) and LSTM (94.1%). Moreover, the system maintains a real-time response under 180 milliseconds per inference cycle. These results confirm that integrating fuzzy reasoning with physics-informed optimization enhances reliability and interpretability for real-time fault diagnostics in smart manufacturing.
10 5 2025 10 5 2025 2615 2624 10.53759/7669/jmc202505201 10.53759/7669/jmc202505201 https://anapub.co.ke/journals/jmc/jmc_abstract/2025/jmc_volume_05_issue_04/jmc_volume5_issue4_201.html https://anapub.co.ke/journals/jmc/jmc_pdf/2025/jmc_volume_5-issue_4/JMC202505201.pdf 10.1109/access.2021.3110479 T. Zabinski, Z. Hajduk, J. Kluska, and L. Gniewek, “FPGA-Embedded Anomaly Detection System for Milling Process,” IEEE Access, vol. 9, pp. 124059–124069, 2021, doi: 10.1109/access.2021.3110479. 10.1016/j.isatra.2021.07.010 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 Transactions, vol. 125, pp. 445–458, Jun. 2022, doi: 10.1016/j.isatra.2021.07.010. 10.1007/978-3-031-49008-8_24 J. M. Silva, A. R. Nogueira, J. Pinto, A. C. Alves, and R. Sousa, “Time-Series Pattern Verification in CNC Machining Data,” Progress in Artificial Intelligence, pp. 299–310, 2023, doi: 10.1007/978-3-031-49008-8_24. 10.55092/am20240010 E. Li, Y. Li, S. Kakarla, W. Melek, and S. Bedi, “Transfer learning methods for Three-Axis CNC anomaly detection,” Advanced Manufacturing, 2024, doi: 10.55092/am20240010. 10.1007/978-3-030-67270-6_7 A. Alghassi, “Generalized Anomaly Detection Algorithm Based on Time Series Statistical Features,” Implementing Industry 4.0, pp. 177–200, 2021, doi: 10.1007/978-3-030-67270-6_7. 10.3390/s20174896 G. Li, Y. Fu, D. Chen, L. Shi, and J. Zhou, “Deep Anomaly Detection for CNC Machine Cutting Tool Using Spindle Current Signals,” Sensors, vol. 20, no. 17, p. 4896, Aug. 2020, doi: 10.3390/s20174896. 10.3390/app15063179 R. Çekik and A. Turan, “Deep Learning for Anomaly Detection in CNC Machine Vibration Data: A RoughLSTM-Based Approach,” Applied Sciences, vol. 15, no. 6, p. 3179, Mar. 2025, doi: 10.3390/app15063179. 10.1016/j.micpro.2022.104629 V. Justus and K. G R, “Intelligent Single-Board Computer for Industry 4.0: Efficient Real-Time Monitoring System for Anomaly Detection in CNC Machines,” Microprocessors and Microsystems, vol. 93, p. 104629, Sep. 2022, doi: 10.1016/j.micpro.2022.104629. 10.1007/s00170-023-11617-5 E. Li, S. Bedi, and W. Melek, “Anomaly detection in three-axis CNC machines using LSTM networks and transfer learning,” The International Journal of Advanced Manufacturing Technology, vol. 127, no. 11–12, pp. 5185–5198, Jul. 2023, doi: 10.1007/s00170-023-11617-5. 10.7717/peerj-cs.2389 A. Athar, M. A. I. Mozumder, Abdullah, S. Ali, and H.-C. Kim, “Deep learning-based anomaly detection using one-dimensional convolutional neural networks (1D CNN) in machine centers (MCT) and computer numerical control (CNC) machines,” PeerJ Computer Science, vol. 10, p. e2389, Oct. 2024, doi: 10.7717/peerj-cs.2389. 10.36001/phmconf.2019.v11i1.806 L. Zhang, S. Elghazoly, and B. Tweedie, “Introducing AnomDB: An Unsupervised Anomaly Detection Method for CNC Machine Control Data,” Annual Conference of the PHM Society, vol. 11, no. 1, Sep. 2019, doi: 10.36001/phmconf.2019.v11i1.806. 10.3390/systems13070534 J.-M. Woo, S.-H. Ju, J.-H. Sung, and K.-M. Seo, “Meta-Learning-Based LSTM-Autoencoder for Low-Data Anomaly Detection in Retrofitted CNC Machine Using Multi-Machine Datasets,” Systems, vol. 13, no. 7, p. 534, Jul. 2025, doi: 10.3390/systems13070534. 10.3390/jmmp3040097 G. Herranz, A. Antolínez, J. Escartín, A. Arregi, and J. K. Gerrikagoitia, “Machine Tools Anomaly Detection Through Nearly Real-Time Data Analysis,” Journal of Manufacturing and Materials Processing, vol. 3, no. 4, p. 97, Dec. 2019, doi: 10.3390/jmmp3040097. Boltshauser, F. (2023). Anomaly detection for prediction of failures in manufacturing environments: Machine learning based semi-supervised anomaly detection for multivariate time series to predict failures in a CNC machine. 10.1016/j.eng.2019.03.012 Y. C. Liang, S. Wang, W. D. Li, and X. Lu, “Data-Driven Anomaly Diagnosis for Machining Processes,” Engineering, vol. 5, no. 4, pp. 646–652, Aug. 2019, doi: 10.1016/j.eng.2019.03.012. 10.1016/j.rcim.2022.102441 S. Yan, H. Shao, Y. Xiao, B. Liu, and J. Wan, “Hybrid robust convolutional autoencoder for unsupervised anomaly detection of machine tools under noises,” Robotics and Computer-Integrated Manufacturing, vol. 79, p. 102441, Feb. 2023, doi: 10.1016/j.rcim.2022.102441. 10.1109/access.2023.3333242 S. F. Chevtchenko et al., “Anomaly Detection in Industrial Machinery Using IoT Devices and Machine Learning: A Systematic Mapping,” IEEE Access, vol. 11, pp. 128288–128305, 2023, doi: 10.1109/access.2023.3333242. 10.1007/s00170-023-12713-2 E. Li, Y. Li, S. Bedi, W. Melek, and P. Gray, “Incremental learning of LSTM-autoencoder anomaly detection in three-axis CNC machines,” The International Journal of Advanced Manufacturing Technology, vol. 130, no. 3–4, pp. 1265–1277, Dec. 2023, doi: 10.1007/s00170-023-12713-2. 10.1007/s11465-025-0837-3 Y. Li, Z. Zhao, Z. Peng, L. Zhang, W. Ding, and Y. Fu, “An innovative strategy for real-time tool anomaly detection in CNC milling processes using time series monitoring,” Frontiers of Mechanical Engineering, vol. 20, no. 3, Jun. 2025, doi: 10.1007/s11465-025-0837-3. 10.1007/978-3-031-04826-5_3 H. Ha, D. Min, and J. Jeong, “A Novel Clustering Anomaly Detection of PCA Based Time Series Features with CNC Machines Data,” Information Systems and Technologies, pp. 22–31, 2022, doi: 10.1007/978-3-031-04826-5_3. Li, E. (2024). Anomaly Detection in CNC Milling Machines using Transfer and Incremental Ensemble Learning of LSTM Autoencoder Networks. https://archive.ics.uci.edu/dataset/752/bosch+cnc+machining+dataset.