An Artificial Neural Networks Approach to Stator Current Sensor Faults Detection for DTC-SVM Structure

Kamil Klimkowski

doi:10.5277/ped160110

Abstract

In the paper, an analysis is made of the stator current sensor fault detector based on artificial neural network for vector controlled induction motor drive system. The systems with different learning algorithms and structures are analyzed and tested in different drive conditions. Simulation results are ob-tained in direct torque control algorithm (DTC-SVM) and performed in MATLAB/SimPowerSystem software.

References

[1] ALAG S., GOEBEL K., AGOGINO A., A Methodology for Intelligent Sensor Validation and Fusion Used in Tracking and Avoidance of Objects for Automated Vehicles, Proc. IEEE Am. Control Conf. 1995, 3647-3653.
Search in Google Scholar Back to article
[2] ADOUNI A., BEN HAMED M., FLAH A., SBITA L., Sensor and actuator fault detection and isolation based on artificial neural networks and fuzzy logic applied on induction motor, 2013 Int. Conf. on Control, Decision and Information Technologies CoDIT, 2013.10.1109/CoDIT.2013.6689665
Search in Google Scholar Back to article
[3] RUSIECKI A., Neural networks learning algorithms robust to data errors, Ph.D. dissertation, Wrocław University of Technology, Poland, 2007.
Search in Google Scholar Back to article
[4] BLANKE M., KINNAERT M., LUNZE J., Diagnosis and fault-tolerant control, Springer-Verlag, 2003.10.1007/978-3-662-05344-7
Search in Google Scholar Back to article
[5] DYBKOWSKI M., Estimation of speed in a vector controlled induction motor drive - selected problems, Scientific Papers of the Institute of Electrical Machines, Drives and Measurements of Wrocław Univ. of Technology. No. 67, ser. Monographs, No. 20, Wrocław, Poland, 2013, (in Polish).
Search in Google Scholar Back to article
[6] ORŁOWSKA-KOWALSKA T., Sensorless induction motor drives, Oficyna Wydawnicza Politechniki Wrocławskiej, Wroclaw, Poland, 2003, (in Polish).
Search in Google Scholar Back to article
[7] ISERMANN R., Fault Diagnosis Systems. An Introduction from Fault Detection to Fault Tolerance, Springer, New York 2006.10.1007/3-540-30368-5
Search in Google Scholar Back to article
[8] KOWALSKI C.T., Monitoring and diagnostics of the induction motor faults using neural networks, Scientific Papers of the Institute of Electrical Machines, Drives and Measurements of Wrocław Univ. of Technology, No. 57. ser. Monographs No. 20, Wrocław, Poland, 2005.
Search in Google Scholar Back to article
[9] GAEID K., Fault Tolerant Control of Induction Motor, Modern Applied Science, 2011, Vol. 5, No. 4.10.5539/mas.v5n4p83
Open DOI Search in Google Scholar Back to article
[10] JIANG L., Sensor fault detection and isolation using system dynamics identification techniques, Ph.D. dissertation, The University of Michigan, 2011.
Search in Google Scholar Back to article
[11] KLIMKOWSKI K., Compensation algorithm based on hardware redundancy of chosen measurement sensors faults in drive systems with induction motor, The XII National Conference Control in Power Electronics and Electric Drives, SENE’2015, Łódź, Poland, 2015, 1-8, (in Polish).
Search in Google Scholar Back to article
[12] VAS P., Artificial-intelligence-based electrical machines and drives, Oxford University Press, Oxford 1999.10.1109/MPER.1999.808172
Search in Google Scholar Back to article
[13] OSOWSKI S., Neural Networks for Information Processing, Warsaw University of Technology Press, Warsaw, 2006.
Search in Google Scholar Back to article
[14] LIVIERIS I.E., PINTELAS P., Performance evaluation of descent CG methods for neural network training, 9th Hellenic European Research on Computer Mathematics its Applications Conference HERCMA’09, 2009, 40-46.
Search in Google Scholar Back to article
[15] LIKAS A., STAFYLOPATIS A., Training the random neural network using quasi-Newton methods, Eur. J. Operat. Res., 2000, Vol. 126, 331-339.10.1016/S0377-2217(99)00482-8
Search in Google Scholar Back to article

An Artificial Neural Networks Approach to Stator Current Sensor Faults Detection for DTC-SVM Structure

Abstract

Paradigm

My account