A Comparative Study between the Two Applications ofthe Neural Network and Space Vector PWM for DirectTorque Control of a DSIM Fed by Multi-Level Inverters

Type : Article de conférence
Auteur(s) :  O. F. Benaouda, M. MEZAACHE, R.ABDELKADER, A. Bendiabdellah
Année :  2022
Domaine : Electrotechnique
Conférence: The 2nd International Conference on Artificial Intelligence and its Applications (aiap2021)
Lieu de la conférence:  El-oued-Algérie
Résumé en PDF :  (résumé en pdf)
Fulltext en PDF :  (.pdf)
Mots clés :  GMAW, DSIM, Neural Network Algorithm NNA, Space Vector PWM SVM, DTNC, DTCSVM, Three-level NPC inverter

Résumé : 

Nowadays, thanks to the development of control and power electronics, the dualstator induction machine DSIM has become among the most important multi-phase machinesincluded in the industrial application of welding process, this is due to its positive featuresamong them is its high reliability and reduce both losses and rotor torque ripple.This paper aims to apply both techniques of artificial intelligence represented by the neuralnetwork algorithm NNA and the Space Vector PWM SVM for direct torque control DTC of theDSIM to improve the machine performance to control speed wire of Gas Metal Arc Welding(GMAW), and control algorithms DTNC and DTC-SVM.Generalization capacity, the parallelism of operation, computational speed, and learning ca-pacity all these features made it possible to exploit the neural network algorithm to control themachine. Fixed switching frequency obtained, dispensed with the vector selection table and thehysteresis controller, the three pros allowed the inclusion of SVM technique in DTC strategy.The converters are included to feed the DSIM and the GMAW process. A several of the re-sults obtained prove the two applied techniques (NNA, SVPWM) in improving the quality ofboth electromagnetic torque and flux and the dynamic responses of the DSIM.