MACHINE LEARNING FOR INTER-TURN SHORT-CIRCUIT FAULT DIAGNOSIS IN PERMANENT MAGNET SYNCHRONOUS MOTORS
ABSTARCT :
Permanent Magnet Synchronous Motor (PMSM) is widely used due to its advantages of high power density, high efficiency and so on. In order to ensure the reliability of a PMSM system, it is extremely vital to accurately diagnose the incipient faults. In this paper, a variety of optimization algorithms are utilized to realize the diagnosis of the faulty position and severity of the inter-turn short-circuit (ITSC) fault, which is one of the most destructive and frequent faults in PMSMCompared with the existing research results gained by particle swarm optimization algorithms, in this paper, the methods using other optimization algorithms incorporating genetic algorithm, whale optimization algorithm and stochastic parallel gradient descent algorithm (SPGD) can acquire more stable and precise results
EXISTING SYSTEM :
? ITSC fault of PMSM, which has several advantages over the existing mainstream fault diagnosis methods.
? In the simulation, the genetic algorithm, whale optimization algorithm and stochastic parallel gradient descent are compared with the existing fault diagnosis method based on particle swarm optimization under ideal circumstances, respectively.
DISADVANTAGE :
With the development of research, the algorithm has been successfully applied in wind speed prediction, feature selection, optimal reactive power scheduling, secondary allocation problem, clustering, scheduling optimization, image classification and other fields.
PROPOSED SYSTEM :
? Therefore, some fault diagnosis methods using the signal of PMSM are proposed. With the development of machine learning and artificial intelligence, many data classification and recognition methods have been proposed, such as neural network (NN), support vector machine (SVM), and fuzzy logic system (FLS).
? Moreover, compared with the method based on the particle swarm optimization algorithm, which has been proposed by other scholars, it is proved that the performance of proposed methods based on heuristic optimization algorithms in this research have been improved a lot, whereas, due to the randomness of the heuristic algorithms, it is difficult to obtain satisfactory results stably
ADVANTAGE :
? Machine learning (ML) has become an increasingly used technology in every aspect of our lives.
? Then offers a broad overview of the most widely used and efficient methodologies for dealing with adversary attacks in AI fields.
? The perturbations performed by the adversarial machine learning attacks aim to be minimal to fool the model without an obvious change in the data used.
? We chose the mentioned algorithms as they are among the most used ones for binary classification problems in recent machine learning literature
|