Analysis of the stator current prediction capabilities in induction motor drive using the LSTM network

• Autorzy: Teler Krystian , Orlowska-Kowalska Teresa

Identyfikatory

DOI

10.2478/pead-2023-0003

• Języki publikacji: EN

Abstrakty

EN

In modern areas of knowledge related to electric drive automation, there is often a need to predict the state variables of the drive system state variables, such as phase current and voltage, electromagnetic torque, stator and rotor flux, and others. This need arises mainly from the use of predictive control algorithms but also from the need to monitor the state of the drive to diagnose possible faults that have not yet occurred but may occur in the future. This paper presents a method for predicting stator phase current signals using a network composed of long-short-term memory units, allowing the simultaneous prediction of two signals. The developed network was trained on a set of current signals generated by software. Its operation was verified by simulation tests in a direct rotor flux-oriented control (DRFOC) structure for an induction motor drive in the Matlab/Simulink environment. An important property of this method is the possibility of obtaining a filtering action on the output of the network, whose intensity can be controlled by varying the sampling frequency of the training signals.

Słowa kluczowe

EN

current sensors; faults; signal prediction; LSTM networks; induction motor drive

• Wydawca: De Gruyter
• Czasopismo: Power Electronics and Drives
• Rocznik: 2023
• Tom: Vol. 8 (43)
• Strony: 31--52
• Opis fizyczny: Bibliogr. 20 poz., rys., tab.

Twórcy

autor

Teler Krystian

• Department of Electrical Machines, Drives and Measurements, Wrocław University of Science and Technology, Wrocław, Poland

• https://orcid.org/0000-0001-5790-6856

autor

Orlowska-Kowalska Teresa

• Department of Electrical Machines, Drives and Measurements, Wrocław University of Science and Technology, Wrocław, Poland

• https://orcid.org/0000-0002-4592-5336

Bibliografia

• Adamczyk, M. and Orlowska-Kowalska, T. (2019). Virtual Current Sensor in the Fault-Tolerant Field-Oriented Control Structure of An Induction Motor Drive. Sensors (Switzerland), 19(22), art. 4979.
• Adamczyk, M. and Orlowska-Kowalska, T. (2022). Postfault Direct Field-Oriented Control of Induction Motor Drive Using Adaptive Virtual Current Sensor. IEEE Transactions on Industrial Electronics, 69(4), pp. 3418–3427.
• Blanke, M., Kinnaert, M., Lunze, J. and Staroswiecki, M. (2006). Diagnosis and Fault-Tolerant Control, 2nd ed. Heidelberg: Springer Berlin.
• Goodfellow, I., Bengio, Y. and Courville, A. (2016). Deep Learning. The MIT Press.
• Ha, J. I. (2010). Current Prediction in Vector-Controlled PWM Inverters Using Single DC-Link Current Sensor. In: IEEE Transactions on Industrial Electronics. February 2010, pp. 716-726.
• Im, J. H. and Kim, R. Y. (2018). Improved Saliency-Based Position Sensorless Control of Interior Permanent-Magnet Synchronous Machines with Single DC-Link Current Sensor Using Current Prediction Method. IEEE Transactions on Industrial Electronics, 65(7), pp. 5335-5343.
• Kingma, D. P. and Ba, J. (2015). Adam: A Method for Stochastic Optimization. In: Proceedings of the 3rd International Conference for Learning Representations, San Diego, December 2015.
• Lee, K. S. and Ryu, J. S. (2003). Instrument Fault Detection and Compensation Scheme for Direct Torque Controlled Induction Motor Drives. IEE Proceedings: Control Theory and Applications, 150, pp. 376-382.
• Leonhard, W. (1996). Control of Electrical Drives, 2nd ed. Berlin, Heidelberg: Springer Berlin Heidelberg.
• Li, J. and Akilan, T. (2022). Global Attention-based Encoder-Decoder LSTM Model for Temperature Prediction of Permanent Magnet Synchronous Motors. arXiv preprint http://arxiv.org/ abs/2208.00293.
• Li, Z., Gao, Q. and Zhang, W. (2016). An improved current sampling scheme using three resistors for induction motor drives based on current prediction. In: 2016 IEEE 8th International Power Electronics and Motion Control Conference, IPEMCECCE Asia 2016. 13 July 2016, Hefei, China, pp. 104-108.
• Li, P., Liao, Y., Lin, H. and Yan, L. (2019). An Improved Three-Phase Current Reconstruction Strategy Using Single Current Sensor with Current Prediction. In: 2019 22nd International Conference on Electrical Machines and Systems (ICEMS). 11-14 August 2019, Harbin, China.
• Orlowska-Kowalska, T. and Dybkowski, M. (2016). Industrial Drive Systems. Current State and Development Trends. Power Electronics and Drives, 1(36), pp. 5-25.
• Peralta-Sanchez, E., Al-Rifai, F. and Schofield, N. (2009). Direct torque control of permanent magnet motors using a single current sensor. In: 2009 IEEE International Electric Machines and Drives Conference, IEMDC ’09, Miami, FL, USA, 2009, pp. 89-94.
• Skowron, M., Teler, K., Adamczyk, M. and Orlowska-Kowalska T. (2022). Classification of Single Current Sensor Failures in Fault-Tolerant Induction Motor Drive Using Neural Network Approach. Energies, 15(18), art. 6646.
• Tunia, H., Smirnow, A., Nowak, M. and Barlik, R. (1982). Power Electronics Systems-Calculation, Modeling, Design. Scientific-Technical Editorial Office (In Polish).
• 1Wang, X., Zhang, Y., Yang, H., Zhang, B., Rodriguez, J. and Garcia, C. (2020). A Model-Free Predictive Current Control of Induction Motor Based on Current Difference. In: 2020 IEEE 9th International Power Electronics and Motion Control Conference, IPEMC 2020 ECCE Asia. 29 November 2020, Nanjing, China, pp. 1038-1042.
• Wang, W., Yan, H., Xu, Y., Zou, J. and Buticchi, G. (2022). Improved Three-Phase Current Reconstruction Technique for PMSM Drive with Current Prediction. IEEE Transactions on Industrial Electronics, 69(4), pp. 3449-3459.
• Yan, L., Wang, F. and Rodriguez, J. (2020). Luenberger prediction model-based robust predictive current control of induction machine drives. In: 2020 IEEE 9th International Power Electronics and Motion Control Conference, IPEMC 2020 ECCE Asia. 29 November 2020, Nanjing, China, pp. 1006-1010.
• Ziegler, S., Woodward, R. C., Iu, H. H. C. and Borle, L. J. (2009). Current Sensing Techniques: A Review. IEEE Sensors Journal, 9(4), pp. 354-376.

Uwagi

Special Section - Artificial Intelligent Based Designs and Applications for the Control of Electrical Drives

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).