Application of soft computing methods to detect fault in A.C motor

Puhan, Pratap Sekhar; Behera, Sudersan

doi:10.1109/icac3.2017.8318754

Cited by 2 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dynamic development of artificial intelligence methods has contributed to many changes in the technique of diagnostic tests carried out within AC motors. For many years, shallow neural networks in the form of multilayer perceptron (Moosavi et al, 2015;Sá et al, 2019), self-organising Kohonen maps (Chuang et al, 2017;Skowron et al, 2023), networks with radial activation functions (Önel et al, 2006;Pietrowski, 2011;Puhan and Behera, 2017), or recurrent structures (Asfani et al, 2012;Gao and Ovaska, 2002) were mostly used. The shallow neural structures solved the problem of assessing membership in one of the declared classes (categories or degree of defect).…”

Section: Introductionmentioning

confidence: 99%

Analysis of PMSM Short-Circuit Detection Systems Using Transfer Learning of Deep Convolutional Networks

Skowron

2024

Power Electronics and Drives

View full text Add to dashboard Cite

Modern permanent magnet synchronous motor (PMSM) diagnostic systems are now combined with advanced artificial intelligence techniques, such as deep neural networks. However, the design of such systems is mainly focussed on a selected type of damage or motor type with a limited range of rated parameters. The application of the idea of transfer learning (TL) allows the fully automatic extraction of universal fault symptoms, which can be used for various diagnostic tasks. In the research, the possibility of using the TL idea in the implementation of PMSM stator windings fault-detection systems was considered. The method is based on the characteristic symptoms of stator defects determined for another type of motor or mathematical model in the target diagnostic application of PMSM. This paper presents a comparison of PMSM motor inter-turn short circuit fault detection systems using TL of a deep convolutional network. Due to the use of direct phase current signal analysis by the convolutional neural network (CNN), it was possible to ensure high accuracy of fault detection with simultaneously short reaction time to occurring fault. The technique used was based on the use of a weight coefficient matrix of a pre-trained structure, the adaptation of which was carried out for different sources of diagnostic information.

show abstract